diff options
Diffstat (limited to 'contrib')
157 files changed, 28799 insertions, 0 deletions
diff --git a/contrib/README b/contrib/README new file mode 100644 index 000000000000..05f291c1f1d3 --- /dev/null +++ b/contrib/README @@ -0,0 +1,43 @@ +Contributed Software + +Although these pieces are available as part of the official git +source tree, they are in somewhat different status. The +intention is to keep interesting tools around git here, maybe +even experimental ones, to give users an easier access to them, +and to give tools wider exposure, so that they can be improved +faster. + +I am not expecting to touch these myself that much. As far as +my day-to-day operation is concerned, these subdirectories are +owned by their respective primary authors. I am willing to help +if users of these components and the contrib/ subtree "owners" +have technical/design issues to resolve, but the initiative to +fix and/or enhance things _must_ be on the side of the subtree +owners. IOW, I won't be actively looking for bugs and rooms for +enhancements in them as the git maintainer -- I may only do so +just as one of the users when I want to scratch my own itch. If +you have patches to things in contrib/ area, the patch should be +first sent to the primary author, and then the primary author +should ack and forward it to me (git pull request is nicer). +This is the same way as how I have been treating gitk, and to a +lesser degree various foreign SCM interfaces, so you know the +drill. + +I expect that things that start their life in the contrib/ area +to graduate out of contrib/ once they mature, either by becoming +projects on their own, or moving to the toplevel directory. On +the other hand, I expect I'll be proposing removal of disused +and inactive ones from time to time. + +If you have new things to add to this area, please first propose +it on the git mailing list, and after a list discussion proves +there are some general interests (it does not have to be a +list-wide consensus for a tool targeted to a relatively narrow +audience -- for example I do not work with projects whose +upstream is svn, so I have no use for git-svn myself, but it is +of general interest for people who need to interoperate with SVN +repositories in a way git-svn works better than git-svnimport), +submit a patch to create a subdirectory of contrib/ and put your +stuff there. + +-jc diff --git a/contrib/buildsystems/Generators.pm b/contrib/buildsystems/Generators.pm new file mode 100644 index 000000000000..aa4cbaa2adac --- /dev/null +++ b/contrib/buildsystems/Generators.pm @@ -0,0 +1,42 @@ +package Generators; +require Exporter; + +use strict; +use File::Basename; +no strict 'refs'; +use vars qw($VERSION @AVAILABLE); + +our $VERSION = '1.00'; +our(@ISA, @EXPORT, @EXPORT_OK, @AVAILABLE); +@ISA = qw(Exporter); + +BEGIN { + local(*D); + my $me = $INC{"Generators.pm"}; + die "Couldn't find myself in \@INC, which is required to load the generators!" if ("$me" eq ""); + $me = dirname($me); + if (opendir(D,"$me/Generators")) { + foreach my $gen (readdir(D)) { + next unless ($gen =~ /\.pm$/); + require "${me}/Generators/$gen"; + $gen =~ s,\.pm,,; + push(@AVAILABLE, $gen); + } + closedir(D); + my $gens = join(', ', @AVAILABLE); + } + + push @EXPORT_OK, qw(available); +} + +sub available { + return @AVAILABLE; +} + +sub generate { + my ($gen, $git_dir, $out_dir, $rel_dir, %build_structure) = @_; + return eval("Generators::${gen}::generate(\$git_dir, \$out_dir, \$rel_dir, \%build_structure)") if grep(/^$gen$/, @AVAILABLE); + die "Generator \"${gen}\" is not available!\nAvailable generators are: @AVAILABLE\n"; +} + +1; diff --git a/contrib/buildsystems/Generators/QMake.pm b/contrib/buildsystems/Generators/QMake.pm new file mode 100644 index 000000000000..ff3b657e6105 --- /dev/null +++ b/contrib/buildsystems/Generators/QMake.pm @@ -0,0 +1,189 @@ +package Generators::QMake; +require Exporter; + +use strict; +use vars qw($VERSION); + +our $VERSION = '1.00'; +our(@ISA, @EXPORT, @EXPORT_OK, @AVAILABLE); +@ISA = qw(Exporter); + +BEGIN { + push @EXPORT_OK, qw(generate); +} + +sub generate { + my ($git_dir, $out_dir, $rel_dir, %build_structure) = @_; + + my @libs = @{$build_structure{"LIBS"}}; + foreach (@libs) { + createLibProject($_, $git_dir, $out_dir, $rel_dir, %build_structure); + } + + my @apps = @{$build_structure{"APPS"}}; + foreach (@apps) { + createAppProject($_, $git_dir, $out_dir, $rel_dir, %build_structure); + } + + createGlueProject($git_dir, $out_dir, $rel_dir, %build_structure); + return 0; +} + +sub createLibProject { + my ($libname, $git_dir, $out_dir, $rel_dir, %build_structure) = @_; + print "Generate $libname lib project\n"; + $rel_dir = "../$rel_dir"; + + my $sources = join(" \\\n\t", sort(map("$rel_dir/$_", @{$build_structure{"LIBS_${libname}_SOURCES"}}))); + my $defines = join(" \\\n\t", sort(@{$build_structure{"LIBS_${libname}_DEFINES"}})); + my $includes= join(" \\\n\t", sort(map("$rel_dir/$_", @{$build_structure{"LIBS_${libname}_INCLUDES"}}))); + my $cflags = join(" ", sort(@{$build_structure{"LIBS_${libname}_CFLAGS"}})); + + my $cflags_debug = $cflags; + $cflags_debug =~ s/-MT/-MTd/; + $cflags_debug =~ s/-O.//; + + my $cflags_release = $cflags; + $cflags_release =~ s/-MTd/-MT/; + + my @tmp = @{$build_structure{"LIBS_${libname}_LFLAGS"}}; + my @tmp2 = (); + foreach (@tmp) { + if (/^-LTCG/) { + } elsif (/^-L/) { + $_ =~ s/^-L/-LIBPATH:$rel_dir\//; + } + push(@tmp2, $_); + } + my $lflags = join(" ", sort(@tmp)); + + my $target = $libname; + $target =~ s/\//_/g; + $defines =~ s/-D//g; + $defines =~ s/"/\\\\"/g; + $includes =~ s/-I//g; + mkdir "$target" || die "Could not create the directory $target for lib project!\n"; + open F, ">$target/$target.pro" || die "Could not open $target/$target.pro for writing!\n"; + print F << "EOM"; +TEMPLATE = lib +TARGET = $target +DESTDIR = $rel_dir + +CONFIG -= qt +CONFIG += static + +QMAKE_CFLAGS = +QMAKE_CFLAGS_RELEASE = $cflags_release +QMAKE_CFLAGS_DEBUG = $cflags_debug +QMAKE_LIBFLAGS = $lflags + +DEFINES += \\ + $defines + +INCLUDEPATH += \\ + $includes + +SOURCES += \\ + $sources +EOM + close F; +} + +sub createAppProject { + my ($appname, $git_dir, $out_dir, $rel_dir, %build_structure) = @_; + print "Generate $appname app project\n"; + $rel_dir = "../$rel_dir"; + + my $sources = join(" \\\n\t", sort(map("$rel_dir/$_", @{$build_structure{"APPS_${appname}_SOURCES"}}))); + my $defines = join(" \\\n\t", sort(@{$build_structure{"APPS_${appname}_DEFINES"}})); + my $includes= join(" \\\n\t", sort(map("$rel_dir/$_", @{$build_structure{"APPS_${appname}_INCLUDES"}}))); + my $cflags = join(" ", sort(@{$build_structure{"APPS_${appname}_CFLAGS"}})); + + my $cflags_debug = $cflags; + $cflags_debug =~ s/-MT/-MTd/; + $cflags_debug =~ s/-O.//; + + my $cflags_release = $cflags; + $cflags_release =~ s/-MTd/-MT/; + + my $libs; + foreach (sort(@{$build_structure{"APPS_${appname}_LIBS"}})) { + $_ =~ s/\//_/g; + $libs .= " $_"; + } + my @tmp = @{$build_structure{"APPS_${appname}_LFLAGS"}}; + my @tmp2 = (); + foreach (@tmp) { + # next if ($_ eq "-NODEFAULTLIB:MSVCRT.lib"); + if (/^-LTCG/) { + } elsif (/^-L/) { + $_ =~ s/^-L/-LIBPATH:$rel_dir\//; + } + push(@tmp2, $_); + } + my $lflags = join(" ", sort(@tmp)); + + my $target = $appname; + $target =~ s/\.exe//; + $target =~ s/\//_/g; + $defines =~ s/-D//g; + $defines =~ s/"/\\\\"/g; + $includes =~ s/-I//g; + mkdir "$target" || die "Could not create the directory $target for app project!\n"; + open F, ">$target/$target.pro" || die "Could not open $target/$target.pro for writing!\n"; + print F << "EOM"; +TEMPLATE = app +TARGET = $target +DESTDIR = $rel_dir + +CONFIG -= qt embed_manifest_exe +CONFIG += console + +QMAKE_CFLAGS = +QMAKE_CFLAGS_RELEASE = $cflags_release +QMAKE_CFLAGS_DEBUG = $cflags_debug +QMAKE_LFLAGS = $lflags +LIBS = $libs + +DEFINES += \\ + $defines + +INCLUDEPATH += \\ + $includes + +win32:QMAKE_LFLAGS += -LIBPATH:$rel_dir +else: QMAKE_LFLAGS += -L$rel_dir + +SOURCES += \\ + $sources +EOM + close F; +} + +sub createGlueProject { + my ($git_dir, $out_dir, $rel_dir, %build_structure) = @_; + my $libs = join(" \\ \n", map("\t$_|$_.pro", @{$build_structure{"LIBS"}})); + my $apps = join(" \\ \n", map("\t$_|$_.pro", @{$build_structure{"APPS"}})); + $libs =~ s/\.a//g; + $libs =~ s/\//_/g; + $libs =~ s/\|/\//g; + $apps =~ s/\.exe//g; + $apps =~ s/\//_/g; + $apps =~ s/\|/\//g; + + my $filename = $out_dir; + $filename =~ s/.*\/([^\/]+)$/$1/; + $filename =~ s/\/$//; + print "Generate glue project $filename.pro\n"; + open F, ">$filename.pro" || die "Could not open $filename.pro for writing!\n"; + print F << "EOM"; +TEMPLATE = subdirs +CONFIG += ordered +SUBDIRS += \\ +$libs \\ +$apps +EOM + close F; +} + +1; diff --git a/contrib/buildsystems/Generators/Vcproj.pm b/contrib/buildsystems/Generators/Vcproj.pm new file mode 100644 index 000000000000..737647e76afd --- /dev/null +++ b/contrib/buildsystems/Generators/Vcproj.pm @@ -0,0 +1,579 @@ +package Generators::Vcproj; +require Exporter; + +use strict; +use vars qw($VERSION); +use Digest::SHA qw(sha256_hex); + +our $VERSION = '1.00'; +our(@ISA, @EXPORT, @EXPORT_OK, @AVAILABLE); +@ISA = qw(Exporter); + +BEGIN { + push @EXPORT_OK, qw(generate); +} + +sub generate_guid ($) { + my $hex = sha256_hex($_[0]); + $hex =~ s/^(.{8})(.{4})(.{4})(.{4})(.{12}).*/{$1-$2-$3-$4-$5}/; + $hex =~ tr/a-z/A-Z/; + return $hex; +} + +sub generate { + my ($git_dir, $out_dir, $rel_dir, %build_structure) = @_; + my @libs = @{$build_structure{"LIBS"}}; + foreach (@libs) { + createLibProject($_, $git_dir, $out_dir, $rel_dir, \%build_structure); + } + + my @apps = @{$build_structure{"APPS"}}; + foreach (@apps) { + createAppProject($_, $git_dir, $out_dir, $rel_dir, \%build_structure); + } + + createGlueProject($git_dir, $out_dir, $rel_dir, %build_structure); + return 0; +} + +sub createLibProject { + my ($libname, $git_dir, $out_dir, $rel_dir, $build_structure) = @_; + print "Generate $libname vcproj lib project\n"; + $rel_dir = "..\\$rel_dir"; + $rel_dir =~ s/\//\\/g; + + my $target = $libname; + $target =~ s/\//_/g; + $target =~ s/\.a//; + + my $uuid = generate_guid($libname); + $$build_structure{"LIBS_${target}_GUID"} = $uuid; + + my @srcs = sort(map("$rel_dir\\$_", @{$$build_structure{"LIBS_${libname}_SOURCES"}})); + my @sources; + foreach (@srcs) { + $_ =~ s/\//\\/g; + push(@sources, $_); + } + my $defines = join(",", sort(@{$$build_structure{"LIBS_${libname}_DEFINES"}})); + my $includes= join(";", sort(map(""$rel_dir\\$_"", @{$$build_structure{"LIBS_${libname}_INCLUDES"}}))); + my $cflags = join(" ", sort(@{$$build_structure{"LIBS_${libname}_CFLAGS"}})); + $cflags =~ s/\"/"/g; + $cflags =~ s/</</g; + $cflags =~ s/>/>/g; + + my $cflags_debug = $cflags; + $cflags_debug =~ s/-MT/-MTd/; + $cflags_debug =~ s/-O.//; + + my $cflags_release = $cflags; + $cflags_release =~ s/-MTd/-MT/; + + my @tmp = @{$$build_structure{"LIBS_${libname}_LFLAGS"}}; + my @tmp2 = (); + foreach (@tmp) { + if (/^-LTCG/) { + } elsif (/^-L/) { + $_ =~ s/^-L/-LIBPATH:$rel_dir\//; + } + push(@tmp2, $_); + } + my $lflags = join(" ", sort(@tmp)); + + $defines =~ s/-D//g; + $defines =~ s/\"/\\"/g; + $defines =~ s/</</g; + $defines =~ s/>/>/g; + $defines =~ s/\'//g; + $includes =~ s/-I//g; + mkdir "$target" || die "Could not create the directory $target for lib project!\n"; + open F, ">$target/$target.vcproj" || die "Could not open $target/$target.pro for writing!\n"; + binmode F, ":crlf"; + print F << "EOM"; +<?xml version="1.0" encoding = "Windows-1252"?> +<VisualStudioProject + ProjectType="Visual C++" + Version="9,00" + Name="$target" + ProjectGUID="$uuid"> + <Platforms> + <Platform + Name="Win32"/> + </Platforms> + <ToolFiles> + </ToolFiles> + <Configurations> + <Configuration + Name="Debug|Win32" + OutputDirectory="$rel_dir" + ConfigurationType="4" + CharacterSet="0" + IntermediateDirectory="\$(ProjectDir)\$(ConfigurationName)" + > + <Tool + Name="VCPreBuildEventTool" + /> + <Tool + Name="VCCustomBuildTool" + /> + <Tool + Name="VCXMLDataGeneratorTool" + /> + <Tool + Name="VCMIDLTool" + /> + <Tool + Name="VCCLCompilerTool" + AdditionalOptions="$cflags_debug" + Optimization="0" + InlineFunctionExpansion="1" + AdditionalIncludeDirectories="$includes" + PreprocessorDefinitions="WIN32,_DEBUG,$defines" + MinimalRebuild="true" + RuntimeLibrary="1" + UsePrecompiledHeader="0" + ProgramDataBaseFileName="\$(IntDir)\\\$(TargetName).pdb" + WarningLevel="3" + DebugInformationFormat="3" + /> + <Tool + Name="VCManagedResourceCompilerTool" + /> + <Tool + Name="VCResourceCompilerTool" + /> + <Tool + Name="VCPreLinkEventTool" + /> + <Tool + Name="VCLibrarianTool" + SuppressStartupBanner="true" + /> + <Tool + Name="VCALinkTool" + /> + <Tool + Name="VCXDCMakeTool" + /> + <Tool + Name="VCBscMakeTool" + /> + <Tool + Name="VCFxCopTool" + /> + <Tool + Name="VCPostBuildEventTool" + /> + </Configuration> + <Configuration + Name="Release|Win32" + OutputDirectory="$rel_dir" + ConfigurationType="4" + CharacterSet="0" + WholeProgramOptimization="1" + IntermediateDirectory="\$(ProjectDir)\$(ConfigurationName)" + > + <Tool + Name="VCPreBuildEventTool" + /> + <Tool + Name="VCCustomBuildTool" + /> + <Tool + Name="VCXMLDataGeneratorTool" + /> + <Tool + Name="VCMIDLTool" + /> + <Tool + Name="VCCLCompilerTool" + AdditionalOptions="$cflags_release" + Optimization="2" + InlineFunctionExpansion="1" + EnableIntrinsicFunctions="true" + AdditionalIncludeDirectories="$includes" + PreprocessorDefinitions="WIN32,NDEBUG,$defines" + RuntimeLibrary="0" + EnableFunctionLevelLinking="true" + UsePrecompiledHeader="0" + ProgramDataBaseFileName="\$(IntDir)\\\$(TargetName).pdb" + WarningLevel="3" + DebugInformationFormat="3" + /> + <Tool + Name="VCManagedResourceCompilerTool" + /> + <Tool + Name="VCResourceCompilerTool" + /> + <Tool + Name="VCPreLinkEventTool" + /> + <Tool + Name="VCLibrarianTool" + SuppressStartupBanner="true" + /> + <Tool + Name="VCALinkTool" + /> + <Tool + Name="VCXDCMakeTool" + /> + <Tool + Name="VCBscMakeTool" + /> + <Tool + Name="VCFxCopTool" + /> + <Tool + Name="VCPostBuildEventTool" + /> + </Configuration> + </Configurations> + <Files> + <Filter + Name="Source Files" + Filter="cpp;c;cxx;def;odl;idl;hpj;bat;asm;asmx" + UniqueIdentifier="{4FC737F1-C7A5-4376-A066-2A32D752A2FF}"> +EOM + foreach(@sources) { + print F << "EOM"; + <File + RelativePath="$_"/> +EOM + } + print F << "EOM"; + </Filter> + </Files> + <Globals> + </Globals> +</VisualStudioProject> +EOM + close F; +} + +sub createAppProject { + my ($appname, $git_dir, $out_dir, $rel_dir, $build_structure) = @_; + print "Generate $appname vcproj app project\n"; + $rel_dir = "..\\$rel_dir"; + $rel_dir =~ s/\//\\/g; + + my $target = $appname; + $target =~ s/\//_/g; + $target =~ s/\.exe//; + + my $uuid = generate_guid($appname); + $$build_structure{"APPS_${target}_GUID"} = $uuid; + + my @srcs = sort(map("$rel_dir\\$_", @{$$build_structure{"APPS_${appname}_SOURCES"}})); + my @sources; + foreach (@srcs) { + $_ =~ s/\//\\/g; + push(@sources, $_); + } + my $defines = join(",", sort(@{$$build_structure{"APPS_${appname}_DEFINES"}})); + my $includes= join(";", sort(map(""$rel_dir\\$_"", @{$$build_structure{"APPS_${appname}_INCLUDES"}}))); + my $cflags = join(" ", sort(@{$$build_structure{"APPS_${appname}_CFLAGS"}})); + $cflags =~ s/\"/"/g; + $cflags =~ s/</</g; + $cflags =~ s/>/>/g; + + my $cflags_debug = $cflags; + $cflags_debug =~ s/-MT/-MTd/; + $cflags_debug =~ s/-O.//; + + my $cflags_release = $cflags; + $cflags_release =~ s/-MTd/-MT/; + + my $libs; + foreach (sort(@{$$build_structure{"APPS_${appname}_LIBS"}})) { + $_ =~ s/\//_/g; + $libs .= " $_"; + } + my @tmp = @{$$build_structure{"APPS_${appname}_LFLAGS"}}; + my @tmp2 = (); + foreach (@tmp) { + if (/^-LTCG/) { + } elsif (/^-L/) { + $_ =~ s/^-L/-LIBPATH:$rel_dir\//; + } + push(@tmp2, $_); + } + my $lflags = join(" ", sort(@tmp)) . " -LIBPATH:$rel_dir"; + + $defines =~ s/-D//g; + $defines =~ s/\"/\\"/g; + $defines =~ s/</</g; + $defines =~ s/>/>/g; + $defines =~ s/\'//g; + $defines =~ s/\\\\/\\/g; + $includes =~ s/-I//g; + mkdir "$target" || die "Could not create the directory $target for lib project!\n"; + open F, ">$target/$target.vcproj" || die "Could not open $target/$target.pro for writing!\n"; + binmode F, ":crlf"; + print F << "EOM"; +<?xml version="1.0" encoding = "Windows-1252"?> +<VisualStudioProject + ProjectType="Visual C++" + Version="9,00" + Name="$target" + ProjectGUID="$uuid"> + <Platforms> + <Platform + Name="Win32"/> + </Platforms> + <ToolFiles> + </ToolFiles> + <Configurations> + <Configuration + Name="Debug|Win32" + OutputDirectory="$rel_dir" + ConfigurationType="1" + CharacterSet="0" + IntermediateDirectory="\$(ProjectDir)\$(ConfigurationName)" + > + <Tool + Name="VCPreBuildEventTool" + /> + <Tool + Name="VCCustomBuildTool" + /> + <Tool + Name="VCXMLDataGeneratorTool" + /> + <Tool + Name="VCMIDLTool" + /> + <Tool + Name="VCCLCompilerTool" + AdditionalOptions="$cflags_debug" + Optimization="0" + InlineFunctionExpansion="1" + AdditionalIncludeDirectories="$includes" + PreprocessorDefinitions="WIN32,_DEBUG,$defines" + MinimalRebuild="true" + RuntimeLibrary="1" + UsePrecompiledHeader="0" + ProgramDataBaseFileName="\$(IntDir)\\\$(TargetName).pdb" + WarningLevel="3" + DebugInformationFormat="3" + /> + <Tool + Name="VCManagedResourceCompilerTool" + /> + <Tool + Name="VCResourceCompilerTool" + /> + <Tool + Name="VCPreLinkEventTool" + /> + <Tool + Name="VCLinkerTool" + AdditionalDependencies="$libs" + AdditionalOptions="$lflags" + LinkIncremental="2" + GenerateDebugInformation="true" + SubSystem="1" + TargetMachine="1" + /> + <Tool + Name="VCALinkTool" + /> + <Tool + Name="VCXDCMakeTool" + /> + <Tool + Name="VCBscMakeTool" + /> + <Tool + Name="VCFxCopTool" + /> + <Tool + Name="VCPostBuildEventTool" + /> + </Configuration> + <Configuration + Name="Release|Win32" + OutputDirectory="$rel_dir" + ConfigurationType="1" + CharacterSet="0" + WholeProgramOptimization="1" + IntermediateDirectory="\$(ProjectDir)\$(ConfigurationName)" + > + <Tool + Name="VCPreBuildEventTool" + /> + <Tool + Name="VCCustomBuildTool" + /> + <Tool + Name="VCXMLDataGeneratorTool" + /> + <Tool + Name="VCMIDLTool" + /> + <Tool + Name="VCCLCompilerTool" + AdditionalOptions="$cflags_release" + Optimization="2" + InlineFunctionExpansion="1" + EnableIntrinsicFunctions="true" + AdditionalIncludeDirectories="$includes" + PreprocessorDefinitions="WIN32,NDEBUG,$defines" + RuntimeLibrary="0" + EnableFunctionLevelLinking="true" + UsePrecompiledHeader="0" + ProgramDataBaseFileName="\$(IntDir)\\\$(TargetName).pdb" + WarningLevel="3" + DebugInformationFormat="3" + /> + <Tool + Name="VCManagedResourceCompilerTool" + /> + <Tool + Name="VCResourceCompilerTool" + /> + <Tool + Name="VCPreLinkEventTool" + /> + <Tool + Name="VCLinkerTool" + AdditionalDependencies="$libs" + AdditionalOptions="$lflags" + LinkIncremental="1" + GenerateDebugInformation="true" + SubSystem="1" + TargetMachine="1" + OptimizeReferences="2" + EnableCOMDATFolding="2" + /> + <Tool + Name="VCALinkTool" + /> + <Tool + Name="VCXDCMakeTool" + /> + <Tool + Name="VCBscMakeTool" + /> + <Tool + Name="VCFxCopTool" + /> + <Tool + Name="VCPostBuildEventTool" + /> + </Configuration> + </Configurations> + <Files> + <Filter + Name="Source Files" + Filter="cpp;c;cxx;def;odl;idl;hpj;bat;asm;asmx" + UniqueIdentifier="{4FC737F1-C7A5-4376-A066-2A32D752A2FF}"> +EOM + foreach(@sources) { + print F << "EOM"; + <File + RelativePath="$_"/> +EOM + } + print F << "EOM"; + </Filter> + </Files> + <Globals> + </Globals> +</VisualStudioProject> +EOM + close F; +} + +sub createGlueProject { + my ($git_dir, $out_dir, $rel_dir, %build_structure) = @_; + print "Generate solutions file\n"; + $rel_dir = "..\\$rel_dir"; + $rel_dir =~ s/\//\\/g; + my $SLN_HEAD = "Microsoft Visual Studio Solution File, Format Version 10.00\n# Visual Studio 2008\n"; + my $SLN_PRE = "Project(\"{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}\") = "; + my $SLN_POST = "\nEndProject\n"; + + my @libs = @{$build_structure{"LIBS"}}; + my @tmp; + foreach (@libs) { + $_ =~ s/\//_/g; + $_ =~ s/\.a//; + push(@tmp, $_); + } + @libs = @tmp; + + my @apps = @{$build_structure{"APPS"}}; + @tmp = (); + foreach (@apps) { + $_ =~ s/\//_/g; + $_ =~ s/\.exe//; + if ($_ eq "git" ) { + unshift(@tmp, $_); + } else { + push(@tmp, $_); + } + } + @apps = @tmp; + + open F, ">git.sln" || die "Could not open git.sln for writing!\n"; + binmode F, ":crlf"; + print F "$SLN_HEAD"; + + my $uuid_libgit = $build_structure{"LIBS_libgit_GUID"}; + my $uuid_xdiff_lib = $build_structure{"LIBS_xdiff_lib_GUID"}; + foreach (@apps) { + my $appname = $_; + my $uuid = $build_structure{"APPS_${appname}_GUID"}; + print F "$SLN_PRE"; + print F "\"${appname}\", \"${appname}\\${appname}.vcproj\", \"${uuid}\"\n"; + print F " ProjectSection(ProjectDependencies) = postProject\n"; + print F " ${uuid_libgit} = ${uuid_libgit}\n"; + print F " ${uuid_xdiff_lib} = ${uuid_xdiff_lib}\n"; + print F " EndProjectSection"; + print F "$SLN_POST"; + } + foreach (@libs) { + my $libname = $_; + my $uuid = $build_structure{"LIBS_${libname}_GUID"}; + print F "$SLN_PRE"; + print F "\"${libname}\", \"${libname}\\${libname}.vcproj\", \"${uuid}\""; + print F "$SLN_POST"; + } + + print F << "EOM"; +Global + GlobalSection(SolutionConfigurationPlatforms) = preSolution + Debug|Win32 = Debug|Win32 + Release|Win32 = Release|Win32 + EndGlobalSection +EOM + print F << "EOM"; + GlobalSection(ProjectConfigurationPlatforms) = postSolution +EOM + foreach (@apps) { + my $appname = $_; + my $uuid = $build_structure{"APPS_${appname}_GUID"}; + print F "\t\t${uuid}.Debug|Win32.ActiveCfg = Debug|Win32\n"; + print F "\t\t${uuid}.Debug|Win32.Build.0 = Debug|Win32\n"; + print F "\t\t${uuid}.Release|Win32.ActiveCfg = Release|Win32\n"; + print F "\t\t${uuid}.Release|Win32.Build.0 = Release|Win32\n"; + } + foreach (@libs) { + my $libname = $_; + my $uuid = $build_structure{"LIBS_${libname}_GUID"}; + print F "\t\t${uuid}.Debug|Win32.ActiveCfg = Debug|Win32\n"; + print F "\t\t${uuid}.Debug|Win32.Build.0 = Debug|Win32\n"; + print F "\t\t${uuid}.Release|Win32.ActiveCfg = Release|Win32\n"; + print F "\t\t${uuid}.Release|Win32.Build.0 = Release|Win32\n"; + } + + print F << "EOM"; + EndGlobalSection +EndGlobal +EOM + close F; +} + +1; diff --git a/contrib/buildsystems/Generators/Vcxproj.pm b/contrib/buildsystems/Generators/Vcxproj.pm new file mode 100644 index 000000000000..576ccabe1dbd --- /dev/null +++ b/contrib/buildsystems/Generators/Vcxproj.pm @@ -0,0 +1,388 @@ +package Generators::Vcxproj; +require Exporter; + +use strict; +use vars qw($VERSION); +use Digest::SHA qw(sha256_hex); + +our $VERSION = '1.00'; +our(@ISA, @EXPORT, @EXPORT_OK, @AVAILABLE); +@ISA = qw(Exporter); + +BEGIN { + push @EXPORT_OK, qw(generate); +} + +sub generate_guid ($) { + my $hex = sha256_hex($_[0]); + $hex =~ s/^(.{8})(.{4})(.{4})(.{4})(.{12}).*/{$1-$2-$3-$4-$5}/; + $hex =~ tr/a-z/A-Z/; + return $hex; +} + +sub generate { + my ($git_dir, $out_dir, $rel_dir, %build_structure) = @_; + my @libs = @{$build_structure{"LIBS"}}; + foreach (@libs) { + createProject($_, $git_dir, $out_dir, $rel_dir, \%build_structure, 1); + } + + my @apps = @{$build_structure{"APPS"}}; + foreach (@apps) { + createProject($_, $git_dir, $out_dir, $rel_dir, \%build_structure, 0); + } + + createGlueProject($git_dir, $out_dir, $rel_dir, %build_structure); + return 0; +} + +sub createProject { + my ($name, $git_dir, $out_dir, $rel_dir, $build_structure, $static_library) = @_; + my $label = $static_library ? "lib" : "app"; + my $prefix = $static_library ? "LIBS_" : "APPS_"; + my $config_type = $static_library ? "StaticLibrary" : "Application"; + print "Generate $name vcxproj $label project\n"; + my $cdup = $name; + $cdup =~ s/[^\/]+/../g; + $cdup =~ s/\//\\/g; + $rel_dir = $rel_dir eq "." ? $cdup : "$cdup\\$rel_dir"; + $rel_dir =~ s/\//\\/g; + + my $target = $name; + if ($static_library) { + $target =~ s/\.a//; + } else { + $target =~ s/\.exe//; + } + + my $uuid = generate_guid($name); + $$build_structure{"$prefix${target}_GUID"} = $uuid; + my $vcxproj = $target; + $vcxproj =~ s/(.*\/)?(.*)/$&\/$2.vcxproj/; + $vcxproj =~ s/([^\/]*)(\/lib)\/(lib.vcxproj)/$1$2\/$1_$3/; + $$build_structure{"$prefix${target}_VCXPROJ"} = $vcxproj; + + my @srcs = sort(map("$rel_dir\\$_", @{$$build_structure{"$prefix${name}_SOURCES"}})); + my @sources; + foreach (@srcs) { + $_ =~ s/\//\\/g; + push(@sources, $_); + } + my $defines = join(";", sort(@{$$build_structure{"$prefix${name}_DEFINES"}})); + my $includes= join(";", sort(map { s/^-I//; s/\//\\/g; File::Spec->file_name_is_absolute($_) ? $_ : "$rel_dir\\$_" } @{$$build_structure{"$prefix${name}_INCLUDES"}})); + my $cflags = join(" ", sort(map { s/^-[GLMOWZ].*//; s/.* .*/"$&"/; $_; } @{$$build_structure{"$prefix${name}_CFLAGS"}})); + $cflags =~ s/</</g; + $cflags =~ s/>/>/g; + + my $libs_release = "\n "; + my $libs_debug = "\n "; + if (!$static_library) { + $libs_release = join(";", sort(grep /^(?!libgit\.lib|xdiff\/lib\.lib|vcs-svn\/lib\.lib)/, @{$$build_structure{"$prefix${name}_LIBS"}})); + $libs_debug = $libs_release; + $libs_debug =~ s/zlib\.lib/zlibd\.lib/; + } + + $defines =~ s/-D//g; + $defines =~ s/</</g; + $defines =~ s/>/>/g; + $defines =~ s/\'//g; + + die "Could not create the directory $target for $label project!\n" unless (-d "$target" || mkdir "$target"); + + open F, ">$vcxproj" or die "Could not open $vcxproj for writing!\n"; + binmode F, ":crlf :utf8"; + print F chr(0xFEFF); + print F << "EOM"; +<?xml version="1.0" encoding="utf-8"?> +<Project DefaultTargets="Build" ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003"> + <ItemGroup Label="ProjectConfigurations"> + <ProjectConfiguration Include="Debug|Win32"> + <Configuration>Debug</Configuration> + <Platform>Win32</Platform> + </ProjectConfiguration> + <ProjectConfiguration Include="Release|Win32"> + <Configuration>Release</Configuration> + <Platform>Win32</Platform> + </ProjectConfiguration> + <ProjectConfiguration Include="Debug|x64"> + <Configuration>Debug</Configuration> + <Platform>x64</Platform> + </ProjectConfiguration> + <ProjectConfiguration Include="Release|x64"> + <Configuration>Release</Configuration> + <Platform>x64</Platform> + </ProjectConfiguration> + </ItemGroup> + <PropertyGroup Label="Globals"> + <ProjectGuid>$uuid</ProjectGuid> + <Keyword>Win32Proj</Keyword> + <VCPKGArch Condition="'\$(Platform)'=='Win32'">x86-windows</VCPKGArch> + <VCPKGArch Condition="'\$(Platform)'!='Win32'">x64-windows</VCPKGArch> + <VCPKGArchDirectory>$cdup\\compat\\vcbuild\\vcpkg\\installed\\\$(VCPKGArch)</VCPKGArchDirectory> + <VCPKGBinDirectory Condition="'\(Configuration)'=='Debug'">\$(VCPKGArchDirectory)\\debug\\bin</VCPKGBinDirectory> + <VCPKGLibDirectory Condition="'\(Configuration)'=='Debug'">\$(VCPKGArchDirectory)\\debug\\lib</VCPKGLibDirectory> + <VCPKGBinDirectory Condition="'\(Configuration)'!='Debug'">\$(VCPKGArchDirectory)\\bin</VCPKGBinDirectory> + <VCPKGLibDirectory Condition="'\(Configuration)'!='Debug'">\$(VCPKGArchDirectory)\\lib</VCPKGLibDirectory> + <VCPKGIncludeDirectory>\$(VCPKGArchDirectory)\\include</VCPKGIncludeDirectory> + <VCPKGLibs Condition="'\(Configuration)'=='Debug'">$libs_debug</VCPKGLibs> + <VCPKGLibs Condition="'\(Configuration)'!='Debug'">$libs_release</VCPKGLibs> + </PropertyGroup> + <Import Project="\$(VCTargetsPath)\\Microsoft.Cpp.Default.props" /> + <PropertyGroup Condition="'\$(Configuration)'=='Debug'" Label="Configuration"> + <UseDebugLibraries>true</UseDebugLibraries> + <LinkIncremental>true</LinkIncremental> + </PropertyGroup> + <PropertyGroup Condition="'\$(Configuration)'=='Release'" Label="Configuration"> + <UseDebugLibraries>false</UseDebugLibraries> + <WholeProgramOptimization>true</WholeProgramOptimization> + </PropertyGroup> + <PropertyGroup> + <ConfigurationType>$config_type</ConfigurationType> + <PlatformToolset>v140</PlatformToolset> + <!-- <CharacterSet>UTF-8</CharacterSet> --> + <OutDir>..\\</OutDir> + <!-- <IntDir>\$(ProjectDir)\$(Configuration)\\</IntDir> --> + </PropertyGroup> + <Import Project="\$(VCTargetsPath)\\Microsoft.Cpp.props" /> + <ImportGroup Label="ExtensionSettings"> + </ImportGroup> + <ImportGroup Label="Shared"> + </ImportGroup> + <ImportGroup Label="PropertySheets"> + <Import Project="\$(UserRootDir)\\Microsoft.Cpp.\$(Platform).user.props" Condition="exists('\$(UserRootDir)\\Microsoft.Cpp.\$(Platform).user.props')" Label="LocalAppDataPlatform" /> + </ImportGroup> + <PropertyGroup Label="UserMacros" /> + <PropertyGroup> + <GenerateManifest>false</GenerateManifest> + <EnableManagedIncrementalBuild>true</EnableManagedIncrementalBuild> + </PropertyGroup> + <ItemDefinitionGroup> + <ClCompile> + <AdditionalOptions>$cflags %(AdditionalOptions)</AdditionalOptions> + <AdditionalIncludeDirectories>$cdup;$cdup\\compat;$cdup\\compat\\regex;$cdup\\compat\\win32;$cdup\\compat\\poll;$cdup\\compat\\vcbuild\\include;\$(VCPKGIncludeDirectory);%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories> + <EnableParallelCodeGeneration /> + <InlineFunctionExpansion>OnlyExplicitInline</InlineFunctionExpansion> + <PrecompiledHeader /> + <DebugInformationFormat>ProgramDatabase</DebugInformationFormat> + </ClCompile> + <Lib> + <SuppressStartupBanner>true</SuppressStartupBanner> + </Lib> + <Link> + <AdditionalLibraryDirectories>\$(VCPKGLibDirectory);%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories> + <AdditionalDependencies>\$(VCPKGLibs);\$(AdditionalDependencies)</AdditionalDependencies> + <AdditionalOptions>invalidcontinue.obj %(AdditionalOptions)</AdditionalOptions> + <EntryPointSymbol>wmainCRTStartup</EntryPointSymbol> + <ManifestFile>$cdup\\compat\\win32\\git.manifest</ManifestFile> + <SubSystem>Console</SubSystem> + </Link> +EOM + if ($target eq 'libgit') { + print F << "EOM"; + <PreBuildEvent Condition="!Exists('$cdup\\compat\\vcbuild\\vcpkg\\installed\\\$(VCPKGArch)\\include\\openssl\\ssl.h')"> + <Message>Initialize VCPKG</Message> + <Command>del "$cdup\\compat\\vcbuild\\vcpkg"</Command> + <Command>call "$cdup\\compat\\vcbuild\\vcpkg_install.bat"</Command> + </PreBuildEvent> +EOM + } + print F << "EOM"; + </ItemDefinitionGroup> + <ItemDefinitionGroup Condition="'\$(Platform)'=='Win32'"> + <Link> + <TargetMachine>MachineX86</TargetMachine> + </Link> + </ItemDefinitionGroup> + <ItemDefinitionGroup Condition="'\$(Configuration)'=='Debug'"> + <ClCompile> + <Optimization>Disabled</Optimization> + <PreprocessorDefinitions>WIN32;_DEBUG;$defines;%(PreprocessorDefinitions)</PreprocessorDefinitions> + <RuntimeLibrary>MultiThreadedDebugDLL</RuntimeLibrary> + </ClCompile> + <Link> + <GenerateDebugInformation>true</GenerateDebugInformation> + </Link> + </ItemDefinitionGroup> + <ItemDefinitionGroup Condition="'\$(Configuration)'=='Release'"> + <ClCompile> + <Optimization>MaxSpeed</Optimization> + <IntrinsicFunctions>true</IntrinsicFunctions> + <PreprocessorDefinitions>WIN32;NDEBUG;$defines;%(PreprocessorDefinitions)</PreprocessorDefinitions> + <RuntimeLibrary>MultiThreadedDLL</RuntimeLibrary> + <FunctionLevelLinking>true</FunctionLevelLinking> + <FavorSizeOrSpeed>Speed</FavorSizeOrSpeed> + </ClCompile> + <Link> + <GenerateDebugInformation>true</GenerateDebugInformation> + <EnableCOMDATFolding>true</EnableCOMDATFolding> + <OptimizeReferences>true</OptimizeReferences> + </Link> + </ItemDefinitionGroup> + <ItemGroup> +EOM + foreach(@sources) { + print F << "EOM"; + <ClCompile Include="$_" /> +EOM + } + print F << "EOM"; + </ItemGroup> +EOM + if (!$static_library || $target =~ 'vcs-svn' || $target =~ 'xdiff') { + my $uuid_libgit = $$build_structure{"LIBS_libgit_GUID"}; + my $uuid_xdiff_lib = $$build_structure{"LIBS_xdiff/lib_GUID"}; + + print F << "EOM"; + <ItemGroup> + <ProjectReference Include="$cdup\\libgit\\libgit.vcxproj"> + <Project>$uuid_libgit</Project> + <ReferenceOutputAssembly>false</ReferenceOutputAssembly> + </ProjectReference> +EOM + if (!($name =~ 'xdiff')) { + print F << "EOM"; + <ProjectReference Include="$cdup\\xdiff\\lib\\xdiff_lib.vcxproj"> + <Project>$uuid_xdiff_lib</Project> + <ReferenceOutputAssembly>false</ReferenceOutputAssembly> + </ProjectReference> +EOM + } + if ($name =~ /(test-(line-buffer|svn-fe)|^git-remote-testsvn)\.exe$/) { + my $uuid_vcs_svn_lib = $$build_structure{"LIBS_vcs-svn/lib_GUID"}; + print F << "EOM"; + <ProjectReference Include="$cdup\\vcs-svn\\lib\\vcs-svn_lib.vcxproj"> + <Project>$uuid_vcs_svn_lib</Project> + <ReferenceOutputAssembly>false</ReferenceOutputAssembly> + </ProjectReference> +EOM + } + print F << "EOM"; + </ItemGroup> +EOM + } + print F << "EOM"; + <Import Project="\$(VCTargetsPath)\\Microsoft.Cpp.targets" /> +EOM + if (!$static_library) { + print F << "EOM"; + <Target Name="${target}_AfterBuild" AfterTargets="AfterBuild"> + <ItemGroup> + <DLLsAndPDBs Include="\$(VCPKGBinDirectory)\\*.dll;\$(VCPKGBinDirectory)\\*.pdb" /> + </ItemGroup> + <Copy SourceFiles="@(DLLsAndPDBs)" DestinationFolder="\$(OutDir)" SkipUnchangedFiles="true" UseHardlinksIfPossible="true" /> + <MakeDir Directories="..\\templates\\blt\\branches" /> + </Target> +EOM + } + if ($target eq 'git') { + print F " <Import Project=\"LinkOrCopyBuiltins.targets\" />\n"; + } + print F << "EOM"; +</Project> +EOM + close F; +} + +sub createGlueProject { + my ($git_dir, $out_dir, $rel_dir, %build_structure) = @_; + print "Generate solutions file\n"; + $rel_dir = "..\\$rel_dir"; + $rel_dir =~ s/\//\\/g; + my $SLN_HEAD = "Microsoft Visual Studio Solution File, Format Version 11.00\n# Visual Studio 2010\n"; + my $SLN_PRE = "Project(\"{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}\") = "; + my $SLN_POST = "\nEndProject\n"; + + my @libs = @{$build_structure{"LIBS"}}; + my @tmp; + foreach (@libs) { + $_ =~ s/\.a//; + push(@tmp, $_); + } + @libs = @tmp; + + my @apps = @{$build_structure{"APPS"}}; + @tmp = (); + foreach (@apps) { + $_ =~ s/\.exe//; + if ($_ eq "git" ) { + unshift(@tmp, $_); + } else { + push(@tmp, $_); + } + } + @apps = @tmp; + + open F, ">git.sln" || die "Could not open git.sln for writing!\n"; + binmode F, ":crlf :utf8"; + print F chr(0xFEFF); + print F "$SLN_HEAD"; + + foreach (@apps) { + my $appname = $_; + my $uuid = $build_structure{"APPS_${appname}_GUID"}; + print F "$SLN_PRE"; + my $vcxproj = $build_structure{"APPS_${appname}_VCXPROJ"}; + $vcxproj =~ s/\//\\/g; + $appname =~ s/.*\///; + print F "\"${appname}\", \"${vcxproj}\", \"${uuid}\""; + print F "$SLN_POST"; + } + foreach (@libs) { + my $libname = $_; + my $uuid = $build_structure{"LIBS_${libname}_GUID"}; + print F "$SLN_PRE"; + my $vcxproj = $build_structure{"LIBS_${libname}_VCXPROJ"}; + $vcxproj =~ s/\//\\/g; + $libname =~ s/\//_/g; + print F "\"${libname}\", \"${vcxproj}\", \"${uuid}\""; + print F "$SLN_POST"; + } + + print F << "EOM"; +Global + GlobalSection(SolutionConfigurationPlatforms) = preSolution + Debug|x64 = Debug|x64 + Debug|x86 = Debug|x86 + Release|x64 = Release|x64 + Release|x86 = Release|x86 + EndGlobalSection +EOM + print F << "EOM"; + GlobalSection(ProjectConfigurationPlatforms) = postSolution +EOM + foreach (@apps) { + my $appname = $_; + my $uuid = $build_structure{"APPS_${appname}_GUID"}; + print F "\t\t${uuid}.Debug|x64.ActiveCfg = Debug|x64\n"; + print F "\t\t${uuid}.Debug|x64.Build.0 = Debug|x64\n"; + print F "\t\t${uuid}.Debug|x86.ActiveCfg = Debug|Win32\n"; + print F "\t\t${uuid}.Debug|x86.Build.0 = Debug|Win32\n"; + print F "\t\t${uuid}.Release|x64.ActiveCfg = Release|x64\n"; + print F "\t\t${uuid}.Release|x64.Build.0 = Release|x64\n"; + print F "\t\t${uuid}.Release|x86.ActiveCfg = Release|Win32\n"; + print F "\t\t${uuid}.Release|x86.Build.0 = Release|Win32\n"; + } + foreach (@libs) { + my $libname = $_; + my $uuid = $build_structure{"LIBS_${libname}_GUID"}; + print F "\t\t${uuid}.Debug|x64.ActiveCfg = Debug|x64\n"; + print F "\t\t${uuid}.Debug|x64.Build.0 = Debug|x64\n"; + print F "\t\t${uuid}.Debug|x86.ActiveCfg = Debug|Win32\n"; + print F "\t\t${uuid}.Debug|x86.Build.0 = Debug|Win32\n"; + print F "\t\t${uuid}.Release|x64.ActiveCfg = Release|x64\n"; + print F "\t\t${uuid}.Release|x64.Build.0 = Release|x64\n"; + print F "\t\t${uuid}.Release|x86.ActiveCfg = Release|Win32\n"; + print F "\t\t${uuid}.Release|x86.Build.0 = Release|Win32\n"; + } + + print F << "EOM"; + EndGlobalSection + GlobalSection(SolutionProperties) = preSolution + HideSolutionNode = FALSE + EndGlobalSection +EndGlobal +EOM + close F; +} + +1; diff --git a/contrib/buildsystems/engine.pl b/contrib/buildsystems/engine.pl new file mode 100755 index 000000000000..fba8a3f056a0 --- /dev/null +++ b/contrib/buildsystems/engine.pl @@ -0,0 +1,394 @@ +#!/usr/bin/perl -w +###################################################################### +# Do not call this script directly! +# +# The generate script ensures that @INC is correct before the engine +# is executed. +# +# Copyright (C) 2009 Marius Storm-Olsen <mstormo@gmail.com> +###################################################################### +use strict; +use File::Basename; +use File::Spec; +use Cwd; +use Generators; +use Text::ParseWords; + +my (%build_structure, %compile_options, @makedry); +my $out_dir = getcwd(); +my $git_dir = $out_dir; +$git_dir =~ s=\\=/=g; +$git_dir = dirname($git_dir) while (!-e "$git_dir/git.c" && "$git_dir" ne ""); +die "Couldn't find Git repo" if ("$git_dir" eq ""); + +my @gens = Generators::available(); +my $gen = "Vcproj"; + +sub showUsage +{ + my $genlist = join(', ', @gens); + print << "EOM"; +generate usage: + -g <GENERATOR> --gen <GENERATOR> Specify the buildsystem generator (default: $gen) + Available: $genlist + -o <PATH> --out <PATH> Specify output directory generation (default: .) + --make-out <PATH> Write the output of GNU Make into a file + -i <FILE> --in <FILE> Specify input file, instead of running GNU Make + -h,-? --help This help +EOM + exit 0; +} + +# Parse command-line options +my $make_out; +while (@ARGV) { + my $arg = shift @ARGV; + if ("$arg" eq "-h" || "$arg" eq "--help" || "$arg" eq "-?") { + showUsage(); + exit(0); + } elsif("$arg" eq "--out" || "$arg" eq "-o") { + $out_dir = shift @ARGV; + } elsif("$arg" eq "--make-out") { + $make_out = shift @ARGV; + } elsif("$arg" eq "--gen" || "$arg" eq "-g") { + $gen = shift @ARGV; + } elsif("$arg" eq "--in" || "$arg" eq "-i") { + my $infile = shift @ARGV; + open(F, "<$infile") || die "Couldn't open file $infile"; + @makedry = <F>; + close(F); + } else { + die "Unknown option: " . $arg; + } +} + +# NOT using File::Spec->rel2abs($path, $base) here, as +# it fails badly for me in the msysgit environment +$git_dir = File::Spec->rel2abs($git_dir); +$out_dir = File::Spec->rel2abs($out_dir); +my $rel_dir = makeOutRel2Git($git_dir, $out_dir); + +# Print some information so the user feels informed +print << "EOM"; +----- +Generator: $gen +Git dir: $git_dir +Out dir: $out_dir +----- +Running GNU Make to figure out build structure... +EOM + +# Pipe a make --dry-run into a variable, if not already loaded from file +# Capture the make dry stderr to file for review (will be empty for a release build). + +my $ErrsFile = "msvc-build-makedryerrors.txt"; +@makedry = `make -C $git_dir -n MSVC=1 SKIP_VCPKG=1 V=1 2>$ErrsFile` +if !@makedry; +# test for an empty Errors file and remove it +unlink $ErrsFile if -f -z $ErrsFile; + +if (defined $make_out) { + open OUT, ">" . $make_out; + print OUT @makedry; + close OUT; +} + +# Parse the make output into usable info +parseMakeOutput(); + +# Finally, ask the generator to start generating.. +Generators::generate($gen, $git_dir, $out_dir, $rel_dir, %build_structure); + +# main flow ends here +# ------------------------------------------------------------------------------------------------- + + +# 1) path: /foo/bar/baz 2) path: /foo/bar/baz 3) path: /foo/bar/baz +# base: /foo/bar/baz/temp base: /foo/bar base: /tmp +# rel: .. rel: baz rel: ../foo/bar/baz +sub makeOutRel2Git +{ + my ($path, $base) = @_; + my $rel; + if ("$path" eq "$base") { + return "."; + } elsif ($base =~ /^$path/) { + # case 1 + my $tmp = $base; + $tmp =~ s/^$path//; + foreach (split('/', $tmp)) { + $rel .= "../" if ("$_" ne ""); + } + } elsif ($path =~ /^$base/) { + # case 2 + $rel = $path; + $rel =~ s/^$base//; + $rel = "./$rel"; + } else { + my $tmp = $base; + foreach (split('/', $tmp)) { + $rel .= "../" if ("$_" ne ""); + } + $rel .= $path; + } + $rel =~ s/\/\//\//g; # simplify + $rel =~ s/\/$//; # don't end with / + return $rel; +} + +sub parseMakeOutput +{ + print "Parsing GNU Make output to figure out build structure...\n"; + my $line = 0; + while (my $text = shift @makedry) { + my $ate_next; + do { + $ate_next = 0; + $line++; + chomp $text; + chop $text if ($text =~ /\r$/); + if ($text =~ /\\$/) { + $text =~ s/\\$//; + $text .= shift @makedry; + $ate_next = 1; + } + } while($ate_next); + + if ($text =~ /^test /) { + # options to test (eg -o) may be mistaken for linker options + next; + } + + if ($text =~ /^(mkdir|msgfmt) /) { + # options to the Portable Object translations + # the line "mkdir ... && msgfmt ..." contains no linker options + next; + } + + if($text =~ / -c /) { + # compilation + handleCompileLine($text, $line); + + } elsif ($text =~ / -o /) { + # linking executable + handleLinkLine($text, $line); + + } elsif ($text =~ /\.o / && $text =~ /\.a /) { + # libifying + handleLibLine($text, $line); +# +# } elsif ($text =~ /^cp /) { +# # copy file around +# +# } elsif ($text =~ /^rm -f /) { +# # shell command +# +# } elsif ($text =~ /^make[ \[]/) { +# # make output +# +# } elsif ($text =~ /^echo /) { +# # echo to file +# +# } elsif ($text =~ /^if /) { +# # shell conditional +# +# } elsif ($text =~ /^tclsh /) { +# # translation stuff +# +# } elsif ($text =~ /^umask /) { +# # handling boilerplates +# +# } elsif ($text =~ /\$\(\:\)/) { +# # ignore +# +# } elsif ($text =~ /^FLAGS=/) { +# # flags check for dependencies +# +# } elsif ($text =~ /^'\/usr\/bin\/perl' -MError -e/) { +# # perl commands for copying files +# +# } elsif ($text =~ /generate-cmdlist\.sh/) { +# # command for generating list of commands +# +# } elsif ($text =~ /new locations or Tcl/) { +# # command for detecting Tcl/Tk changes +# +# } elsif ($text =~ /mkdir -p/) { +# # command creating path +# +# } elsif ($text =~ /: no custom templates yet/) { +# # whatever +# +# } else { +# print "Unhandled (line: $line): $text\n"; + } + } + +# use Data::Dumper; +# print "Parsed build structure:\n"; +# print Dumper(%build_structure); +} + +# variables for the compilation part of each step +my (@defines, @incpaths, @cflags, @sources); + +sub clearCompileStep +{ + @defines = (); + @incpaths = (); + @cflags = (); + @sources = (); +} + +sub removeDuplicates +{ + my (%dupHash, $entry); + %dupHash = map { $_, 1 } @defines; + @defines = keys %dupHash; + + %dupHash = map { $_, 1 } @incpaths; + @incpaths = keys %dupHash; + + %dupHash = map { $_, 1 } @cflags; + @cflags = keys %dupHash; +} + +sub handleCompileLine +{ + my ($line, $lineno) = @_; + my @parts = shellwords($line); + my $sourcefile; + shift(@parts); # ignore cmd + while (my $part = shift @parts) { + if ("$part" eq "-o") { + # ignore object file + shift @parts; + } elsif ("$part" eq "-c") { + # ignore compile flag + } elsif ("$part" eq "-c") { + } elsif ($part =~ /^.?-I/) { + push(@incpaths, $part); + } elsif ($part =~ /^.?-D/) { + push(@defines, $part); + } elsif ($part =~ /^-/) { + push(@cflags, $part); + } elsif ($part =~ /\.(c|cc|cpp)$/) { + $sourcefile = $part; + } else { + die "Unhandled compiler option @ line $lineno: $part"; + } + } + @{$compile_options{"${sourcefile}_CFLAGS"}} = @cflags; + @{$compile_options{"${sourcefile}_DEFINES"}} = @defines; + @{$compile_options{"${sourcefile}_INCPATHS"}} = @incpaths; + clearCompileStep(); +} + +sub handleLibLine +{ + my ($line, $lineno) = @_; + my (@objfiles, @lflags, $libout, $part); + # kill cmd and rm 'prefix' + $line =~ s/^rm -f .* && .* rcs //; + my @parts = shellwords($line); + while ($part = shift @parts) { + if ($part =~ /^-/) { + push(@lflags, $part); + } elsif ($part =~ /\.(o|obj)$/) { + push(@objfiles, $part); + } elsif ($part =~ /\.(a|lib)$/) { + $libout = $part; + $libout =~ s/\.a$//; + } else { + die "Unhandled lib option @ line $lineno: $part"; + } + } +# print "LibOut: '$libout'\nLFlags: @lflags\nOfiles: @objfiles\n"; +# exit(1); + foreach (@objfiles) { + my $sourcefile = $_; + $sourcefile =~ s/\.o$/.c/; + push(@sources, $sourcefile); + push(@cflags, @{$compile_options{"${sourcefile}_CFLAGS"}}); + push(@defines, @{$compile_options{"${sourcefile}_DEFINES"}}); + push(@incpaths, @{$compile_options{"${sourcefile}_INCPATHS"}}); + } + removeDuplicates(); + + push(@{$build_structure{"LIBS"}}, $libout); + @{$build_structure{"LIBS_${libout}"}} = ("_DEFINES", "_INCLUDES", "_CFLAGS", "_SOURCES", + "_OBJECTS"); + @{$build_structure{"LIBS_${libout}_DEFINES"}} = @defines; + @{$build_structure{"LIBS_${libout}_INCLUDES"}} = @incpaths; + @{$build_structure{"LIBS_${libout}_CFLAGS"}} = @cflags; + @{$build_structure{"LIBS_${libout}_LFLAGS"}} = @lflags; + @{$build_structure{"LIBS_${libout}_SOURCES"}} = @sources; + @{$build_structure{"LIBS_${libout}_OBJECTS"}} = @objfiles; + clearCompileStep(); +} + +sub handleLinkLine +{ + my ($line, $lineno) = @_; + my (@objfiles, @lflags, @libs, $appout, $part); + my @parts = shellwords($line); + shift(@parts); # ignore cmd + while ($part = shift @parts) { + if ($part =~ /^-IGNORE/) { + push(@lflags, $part); + } elsif ($part =~ /^-[GRIMDO]/) { + # eat compiler flags + } elsif ("$part" eq "-o") { + $appout = shift @parts; + } elsif ("$part" eq "-lz") { + push(@libs, "zlib.lib"); + } elsif ("$part" eq "-lcrypto") { + push(@libs, "libeay32.lib"); + } elsif ("$part" eq "-lssl") { + push(@libs, "ssleay32.lib"); + } elsif ("$part" eq "-lcurl") { + push(@libs, "libcurl.lib"); + } elsif ("$part" eq "-lexpat") { + push(@libs, "expat.lib"); + } elsif ("$part" eq "-liconv") { + push(@libs, "libiconv.lib"); + } elsif ($part =~ /^[-\/]/) { + push(@lflags, $part); + } elsif ($part =~ /\.(a|lib)$/) { + $part =~ s/\.a$/.lib/; + push(@libs, $part); + } elsif ($part eq 'invalidcontinue.obj') { + # ignore - known to MSVC + } elsif ($part =~ /\.o$/) { + push(@objfiles, $part); + } elsif ($part =~ /\.obj$/) { + # do nothing, 'make' should not be producing .obj, only .o files + } else { + die "Unhandled link option @ line $lineno: $part"; + } + } +# print "AppOut: '$appout'\nLFlags: @lflags\nLibs : @libs\nOfiles: @objfiles\n"; +# exit(1); + foreach (@objfiles) { + my $sourcefile = $_; + $sourcefile =~ s/\.o$/.c/; + push(@sources, $sourcefile); + push(@cflags, @{$compile_options{"${sourcefile}_CFLAGS"}}); + push(@defines, @{$compile_options{"${sourcefile}_DEFINES"}}); + push(@incpaths, @{$compile_options{"${sourcefile}_INCPATHS"}}); + } + removeDuplicates(); + + removeDuplicates(); + push(@{$build_structure{"APPS"}}, $appout); + @{$build_structure{"APPS_${appout}"}} = ("_DEFINES", "_INCLUDES", "_CFLAGS", "_LFLAGS", + "_SOURCES", "_OBJECTS", "_LIBS"); + @{$build_structure{"APPS_${appout}_DEFINES"}} = @defines; + @{$build_structure{"APPS_${appout}_INCLUDES"}} = @incpaths; + @{$build_structure{"APPS_${appout}_CFLAGS"}} = @cflags; + @{$build_structure{"APPS_${appout}_LFLAGS"}} = @lflags; + @{$build_structure{"APPS_${appout}_SOURCES"}} = @sources; + @{$build_structure{"APPS_${appout}_OBJECTS"}} = @objfiles; + @{$build_structure{"APPS_${appout}_LIBS"}} = @libs; + clearCompileStep(); +} diff --git a/contrib/buildsystems/generate b/contrib/buildsystems/generate new file mode 100755 index 000000000000..bc10f25ff24a --- /dev/null +++ b/contrib/buildsystems/generate @@ -0,0 +1,29 @@ +#!/usr/bin/perl -w +###################################################################### +# Generate buildsystem files +# +# This script generate buildsystem files based on the output of a +# GNU Make --dry-run, enabling Windows users to develop Git with their +# trusted IDE with native projects. +# +# Note: +# It is not meant as *the* way of building Git with MSVC, but merely a +# convenience. The correct way of building Git with MSVC is to use the +# GNU Make tool to build with the maintained Makefile in the root of +# the project. If you have the msysgit environment installed and +# available in your current console, together with the Visual Studio +# environment you wish to build for, all you have to do is run the +# command: +# make MSVC=1 +# +# Copyright (C) 2009 Marius Storm-Olsen <mstormo@gmail.com> +###################################################################### +use strict; +use File::Basename; +use Cwd; + +my $git_dir = getcwd(); +$git_dir =~ s=\\=/=g; +$git_dir = dirname($git_dir) while (!-e "$git_dir/git.c" && "$git_dir" ne ""); +die "Couldn't find Git repo" if ("$git_dir" eq ""); +exec join(" ", ("PERL5LIB=${git_dir}/contrib/buildsystems ${git_dir}/contrib/buildsystems/engine.pl", @ARGV)); diff --git a/contrib/buildsystems/parse.pl b/contrib/buildsystems/parse.pl new file mode 100755 index 000000000000..c9656ece9931 --- /dev/null +++ b/contrib/buildsystems/parse.pl @@ -0,0 +1,228 @@ +#!/usr/bin/perl -w +###################################################################### +# Do not call this script directly! +# +# The generate script ensures that @INC is correct before the engine +# is executed. +# +# Copyright (C) 2009 Marius Storm-Olsen <mstormo@gmail.com> +###################################################################### +use strict; +use File::Basename; +use Cwd; + +my $file = $ARGV[0]; +die "No file provided!" if !defined $file; + +my ($cflags, $target, $type, $line); + +open(F, "<$file") || die "Couldn't open file $file"; +my @data = <F>; +close(F); + +while (my $text = shift @data) { + my $ate_next; + do { + $ate_next = 0; + $line++; + chomp $text; + chop $text if ($text =~ /\r$/); + if ($text =~ /\\$/) { + $text =~ s/\\$//; + $text .= shift @data; + $ate_next = 1; + } + } while($ate_next); + + if($text =~ / -c /) { + # compilation + handleCompileLine($text, $line); + + } elsif ($text =~ / -o /) { + # linking executable + handleLinkLine($text, $line); + + } elsif ($text =~ /\.o / && $text =~ /\.a /) { + # libifying + handleLibLine($text, $line); + +# } elsif ($text =~ /^cp /) { +# # copy file around +# +# } elsif ($text =~ /^rm -f /) { +# # shell command +# +# } elsif ($text =~ /^make[ \[]/) { +# # make output +# +# } elsif ($text =~ /^echo /) { +# # echo to file +# +# } elsif ($text =~ /^if /) { +# # shell conditional +# +# } elsif ($text =~ /^tclsh /) { +# # translation stuff +# +# } elsif ($text =~ /^umask /) { +# # handling boilerplates +# +# } elsif ($text =~ /\$\(\:\)/) { +# # ignore +# +# } elsif ($text =~ /^FLAGS=/) { +# # flags check for dependencies +# +# } elsif ($text =~ /^'\/usr\/bin\/perl' -MError -e/) { +# # perl commands for copying files +# +# } elsif ($text =~ /generate-cmdlist\.sh/) { +# # command for generating list of commands +# +# } elsif ($text =~ /^test / && $text =~ /|| rm -f /) { +# # commands removing executables, if they exist +# +# } elsif ($text =~ /new locations or Tcl/) { +# # command for detecting Tcl/Tk changes +# +# } elsif ($text =~ /mkdir -p/) { +# # command creating path +# +# } elsif ($text =~ /: no custom templates yet/) { +# # whatever + + } else { +# print "Unhandled (line: $line): $text\n"; + } +} +close(F); + +# use Data::Dumper; +# print "Parsed build structure:\n"; +# print Dumper(%build_structure); + +# ------------------------------------------------------------------- +# Functions under here +# ------------------------------------------------------------------- +my (%build_structure, @defines, @incpaths, @cflags, @sources); + +sub clearCompileStep +{ + @defines = (); + @incpaths = (); + @cflags = (); + @sources = (); +} + +sub removeDuplicates +{ + my (%dupHash, $entry); + %dupHash = map { $_, 1 } @defines; + @defines = keys %dupHash; + + %dupHash = map { $_, 1 } @incpaths; + @incpaths = keys %dupHash; + + %dupHash = map { $_, 1 } @cflags; + @cflags = keys %dupHash; + + %dupHash = map { $_, 1 } @sources; + @sources = keys %dupHash; +} + +sub handleCompileLine +{ + my ($line, $lineno) = @_; + my @parts = split(' ', $line); + shift(@parts); # ignore cmd + while (my $part = shift @parts) { + if ("$part" eq "-o") { + # ignore object file + shift @parts; + } elsif ("$part" eq "-c") { + # ignore compile flag + } elsif ("$part" eq "-c") { + } elsif ($part =~ /^.?-I/) { + push(@incpaths, $part); + } elsif ($part =~ /^.?-D/) { + push(@defines, $part); + } elsif ($part =~ /^-/) { + push(@cflags, $part); + } elsif ($part =~ /\.(c|cc|cpp)$/) { + push(@sources, $part); + } else { + die "Unhandled compiler option @ line $lineno: $part"; + } + } + #print "Sources: @sources\nCFlags: @cflags\nDefine: @defines\nIncpat: @incpaths\n"; + #exit(1); +} + +sub handleLibLine +{ + my ($line, $lineno) = @_; + my (@objfiles, @lflags, $libout, $part); + # kill cmd and rm 'prefix' + $line =~ s/^rm -f .* && .* rcs //; + my @parts = split(' ', $line); + while ($part = shift @parts) { + if ($part =~ /^-/) { + push(@lflags, $part); + } elsif ($part =~ /\.(o|obj)$/) { + push(@objfiles, $part); + } elsif ($part =~ /\.(a|lib)$/) { + $libout = $part; + } else { + die "Unhandled lib option @ line $lineno: $part"; + } + } + #print "LibOut: '$libout'\nLFlags: @lflags\nOfiles: @objfiles\n"; + #exit(1); + removeDuplicates(); + push(@{$build_structure{"LIBS"}}, $libout); + @{$build_structure{"LIBS_${libout}"}} = ("_DEFINES", "_INCLUDES", "_CFLAGS", "_SOURCES", + "_OBJECTS"); + @{$build_structure{"LIBS_${libout}_DEFINES"}} = @defines; + @{$build_structure{"LIBS_${libout}_INCLUDES"}} = @incpaths; + @{$build_structure{"LIBS_${libout}_CFLAGS"}} = @cflags; + @{$build_structure{"LIBS_${libout}_SOURCES"}} = @sources; + @{$build_structure{"LIBS_${libout}_OBJECTS"}} = @objfiles; + clearCompileStep(); +} + +sub handleLinkLine +{ + my ($line, $lineno) = @_; + my (@objfiles, @lflags, @libs, $appout, $part); + my @parts = split(' ', $line); + shift(@parts); # ignore cmd + while ($part = shift @parts) { + if ($part =~ /^-[GRIDO]/) { + # eat compiler flags + } elsif ("$part" eq "-o") { + $appout = shift @parts; + } elsif ($part =~ /^-/) { + push(@lflags, $part); + } elsif ($part =~ /\.(a|lib)$/) { + push(@libs, $part); + } elsif ($part =~ /\.(o|obj)$/) { + push(@objfiles, $part); + } else { + die "Unhandled lib option @ line $lineno: $part"; + } + } + #print "AppOut: '$appout'\nLFlags: @lflags\nLibs : @libs\nOfiles: @objfiles\n"; + #exit(1); + removeDuplicates(); + push(@{$build_structure{"APPS"}}, $appout); + @{$build_structure{"APPS_${appout}"}} = ("_DEFINES", "_INCLUDES", "_CFLAGS", "_LFLAGS", + "_SOURCES", "_OBJECTS", "_LIBS"); + @{$build_structure{"APPS_${appout}_DEFINES"}} = @defines; + @{$build_structure{"APPS_${appout}_INCLUDES"}} = @incpaths; + @{$build_structure{"APPS_${appout}_CFLAGS"}} = @cflags; + @{$build_structure{"APPS_${appout}_LFLAGS"}} = @lflags; + @{$build_structure{"APPS_${appout}_SOURCES"}} = @sources; + @{$build_structure{"APPS_${appout}_OBJECTS"}} = @objfiles; + @{$build_structure{"APPS_${appout}_LIBS"}} = @libs; + clearCompileStep(); +} diff --git a/contrib/coccinelle/.gitignore b/contrib/coccinelle/.gitignore new file mode 100644 index 000000000000..d3f29646dc3a --- /dev/null +++ b/contrib/coccinelle/.gitignore @@ -0,0 +1 @@ +*.patch* diff --git a/contrib/coccinelle/README b/contrib/coccinelle/README new file mode 100644 index 000000000000..f0e80bd7f037 --- /dev/null +++ b/contrib/coccinelle/README @@ -0,0 +1,43 @@ +This directory provides examples of Coccinelle (http://coccinelle.lip6.fr/) +semantic patches that might be useful to developers. + +There are two types of semantic patches: + + * Using the semantic transformation to check for bad patterns in the code; + The target 'make coccicheck' is designed to check for these patterns and + it is expected that any resulting patch indicates a regression. + The patches resulting from 'make coccicheck' are small and infrequent, + so once they are found, they can be sent to the mailing list as per usual. + + Example for introducing new patterns: + 67947c34ae (convert "hashcmp() != 0" to "!hasheq()", 2018-08-28) + b84c783882 (fsck: s/++i > 1/i++/, 2018-10-24) + + Example of fixes using this approach: + 248f66ed8e (run-command: use strbuf_addstr() for adding a string to + a strbuf, 2018-03-25) + f919ffebed (Use MOVE_ARRAY, 2018-01-22) + + These types of semantic patches are usually part of testing, c.f. + 0860a7641b (travis-ci: fail if Coccinelle static analysis found something + to transform, 2018-07-23) + + * Using semantic transformations in large scale refactorings throughout + the code base. + + When applying the semantic patch into a real patch, sending it to the + mailing list in the usual way, such a patch would be expected to have a + lot of textual and semantic conflicts as such large scale refactorings + change function signatures that are used widely in the code base. + A textual conflict would arise if surrounding code near any call of such + function changes. A semantic conflict arises when other patch series in + flight introduce calls to such functions. + + So to aid these large scale refactorings, semantic patches can be used. + However we do not want to store them in the same place as the checks for + bad patterns, as then automated builds would fail. + That is why semantic patches 'contrib/coccinelle/*.pending.cocci' + are ignored for checks, and can be applied using 'make coccicheck-pending'. + + This allows to expose plans of pending large scale refactorings without + impacting the bad pattern checks. diff --git a/contrib/coccinelle/array.cocci b/contrib/coccinelle/array.cocci new file mode 100644 index 000000000000..46b8d2ee1115 --- /dev/null +++ b/contrib/coccinelle/array.cocci @@ -0,0 +1,90 @@ +@@ +expression dst, src, n, E; +@@ + memcpy(dst, src, n * sizeof( +- E[...] ++ *(E) + )) + +@@ +type T; +T *ptr; +T[] arr; +expression E, n; +@@ +( + memcpy(ptr, E, +- n * sizeof(*(ptr)) ++ n * sizeof(T) + ) +| + memcpy(arr, E, +- n * sizeof(*(arr)) ++ n * sizeof(T) + ) +| + memcpy(E, ptr, +- n * sizeof(*(ptr)) ++ n * sizeof(T) + ) +| + memcpy(E, arr, +- n * sizeof(*(arr)) ++ n * sizeof(T) + ) +) + +@@ +type T; +T *dst_ptr; +T *src_ptr; +T[] dst_arr; +T[] src_arr; +expression n; +@@ +( +- memcpy(dst_ptr, src_ptr, (n) * sizeof(T)) ++ COPY_ARRAY(dst_ptr, src_ptr, n) +| +- memcpy(dst_ptr, src_arr, (n) * sizeof(T)) ++ COPY_ARRAY(dst_ptr, src_arr, n) +| +- memcpy(dst_arr, src_ptr, (n) * sizeof(T)) ++ COPY_ARRAY(dst_arr, src_ptr, n) +| +- memcpy(dst_arr, src_arr, (n) * sizeof(T)) ++ COPY_ARRAY(dst_arr, src_arr, n) +) + +@@ +type T; +T *dst; +T *src; +expression n; +@@ +( +- memmove(dst, src, (n) * sizeof(*dst)); ++ MOVE_ARRAY(dst, src, n); +| +- memmove(dst, src, (n) * sizeof(*src)); ++ MOVE_ARRAY(dst, src, n); +| +- memmove(dst, src, (n) * sizeof(T)); ++ MOVE_ARRAY(dst, src, n); +) + +@@ +type T; +T *ptr; +expression n; +@@ +- ptr = xmalloc((n) * sizeof(*ptr)); ++ ALLOC_ARRAY(ptr, n); + +@@ +type T; +T *ptr; +expression n; +@@ +- ptr = xmalloc((n) * sizeof(T)); ++ ALLOC_ARRAY(ptr, n); diff --git a/contrib/coccinelle/commit.cocci b/contrib/coccinelle/commit.cocci new file mode 100644 index 000000000000..d03453341e84 --- /dev/null +++ b/contrib/coccinelle/commit.cocci @@ -0,0 +1,34 @@ +@@ +expression c; +@@ +- &c->maybe_tree->object.oid ++ get_commit_tree_oid(c) + +@@ +expression c; +@@ +- c->maybe_tree->object.oid.hash ++ get_commit_tree_oid(c)->hash + +@@ +identifier f !~ "^set_commit_tree$"; +expression c; +expression s; +@@ + f(...) {<... +- c->maybe_tree = s ++ set_commit_tree(c, s) + ...>} + +// These excluded functions must access c->maybe_tree direcly. +// Note that if c->maybe_tree is written somewhere outside of these +// functions, then the recommended transformation will be bogus with +// repo_get_commit_tree() on the LHS. +@@ +identifier f !~ "^(repo_get_commit_tree|get_commit_tree_in_graph_one|load_tree_for_commit|set_commit_tree)$"; +expression c; +@@ + f(...) {<... +- c->maybe_tree ++ repo_get_commit_tree(specify_the_right_repo_here, c) + ...>} diff --git a/contrib/coccinelle/flex_alloc.cocci b/contrib/coccinelle/flex_alloc.cocci new file mode 100644 index 000000000000..e9f7f6d861a4 --- /dev/null +++ b/contrib/coccinelle/flex_alloc.cocci @@ -0,0 +1,13 @@ +@@ +expression str; +identifier x, flexname; +@@ +- FLEX_ALLOC_MEM(x, flexname, str, strlen(str)); ++ FLEX_ALLOC_STR(x, flexname, str); + +@@ +expression str; +identifier x, ptrname; +@@ +- FLEXPTR_ALLOC_MEM(x, ptrname, str, strlen(str)); ++ FLEXPTR_ALLOC_STR(x, ptrname, str); diff --git a/contrib/coccinelle/free.cocci b/contrib/coccinelle/free.cocci new file mode 100644 index 000000000000..4490069df965 --- /dev/null +++ b/contrib/coccinelle/free.cocci @@ -0,0 +1,18 @@ +@@ +expression E; +@@ +- if (E) + free(E); + +@@ +expression E; +@@ +- if (!E) + free(E); + +@@ +expression E; +@@ +- free(E); ++ FREE_AND_NULL(E); +- E = NULL; diff --git a/contrib/coccinelle/object_id.cocci b/contrib/coccinelle/object_id.cocci new file mode 100644 index 000000000000..3e536a9834b6 --- /dev/null +++ b/contrib/coccinelle/object_id.cocci @@ -0,0 +1,119 @@ +@@ +struct object_id OID; +@@ +- is_null_sha1(OID.hash) ++ is_null_oid(&OID) + +@@ +struct object_id *OIDPTR; +@@ +- is_null_sha1(OIDPTR->hash) ++ is_null_oid(OIDPTR) + +@@ +struct object_id OID; +@@ +- sha1_to_hex(OID.hash) ++ oid_to_hex(&OID) + +@@ +identifier f != oid_to_hex; +struct object_id *OIDPTR; +@@ + f(...) {<... +- sha1_to_hex(OIDPTR->hash) ++ oid_to_hex(OIDPTR) + ...>} + +@@ +expression E; +struct object_id OID; +@@ +- sha1_to_hex_r(E, OID.hash) ++ oid_to_hex_r(E, &OID) + +@@ +identifier f != oid_to_hex_r; +expression E; +struct object_id *OIDPTR; +@@ + f(...) {<... +- sha1_to_hex_r(E, OIDPTR->hash) ++ oid_to_hex_r(E, OIDPTR) + ...>} + +@@ +struct object_id OID; +@@ +- hashclr(OID.hash) ++ oidclr(&OID) + +@@ +identifier f != oidclr; +struct object_id *OIDPTR; +@@ + f(...) {<... +- hashclr(OIDPTR->hash) ++ oidclr(OIDPTR) + ...>} + +@@ +struct object_id OID1, OID2; +@@ +- hashcmp(OID1.hash, OID2.hash) ++ oidcmp(&OID1, &OID2) + +@@ +identifier f != oidcmp; +struct object_id *OIDPTR1, OIDPTR2; +@@ + f(...) {<... +- hashcmp(OIDPTR1->hash, OIDPTR2->hash) ++ oidcmp(OIDPTR1, OIDPTR2) + ...>} + +@@ +struct object_id *OIDPTR; +struct object_id OID; +@@ +- hashcmp(OIDPTR->hash, OID.hash) ++ oidcmp(OIDPTR, &OID) + +@@ +struct object_id *OIDPTR; +struct object_id OID; +@@ +- hashcmp(OID.hash, OIDPTR->hash) ++ oidcmp(&OID, OIDPTR) + +@@ +struct object_id *OIDPTR1; +struct object_id *OIDPTR2; +@@ +- oidcmp(OIDPTR1, OIDPTR2) == 0 ++ oideq(OIDPTR1, OIDPTR2) + +@@ +identifier f != hasheq; +expression E1, E2; +@@ + f(...) {<... +- hashcmp(E1, E2) == 0 ++ hasheq(E1, E2) + ...>} + +@@ +struct object_id *OIDPTR1; +struct object_id *OIDPTR2; +@@ +- oidcmp(OIDPTR1, OIDPTR2) != 0 ++ !oideq(OIDPTR1, OIDPTR2) + +@@ +identifier f != hasheq; +expression E1, E2; +@@ + f(...) {<... +- hashcmp(E1, E2) != 0 ++ !hasheq(E1, E2) + ...>} diff --git a/contrib/coccinelle/preincr.cocci b/contrib/coccinelle/preincr.cocci new file mode 100644 index 000000000000..7fe1e8d2d9a0 --- /dev/null +++ b/contrib/coccinelle/preincr.cocci @@ -0,0 +1,5 @@ +@ preincrement @ +identifier i; +@@ +- ++i > 1 ++ i++ diff --git a/contrib/coccinelle/qsort.cocci b/contrib/coccinelle/qsort.cocci new file mode 100644 index 000000000000..22b93a99664d --- /dev/null +++ b/contrib/coccinelle/qsort.cocci @@ -0,0 +1,37 @@ +@@ +expression base, nmemb, compar; +@@ +- qsort(base, nmemb, sizeof(*base), compar); ++ QSORT(base, nmemb, compar); + +@@ +expression base, nmemb, compar; +@@ +- qsort(base, nmemb, sizeof(base[0]), compar); ++ QSORT(base, nmemb, compar); + +@@ +type T; +T *base; +expression nmemb, compar; +@@ +- qsort(base, nmemb, sizeof(T), compar); ++ QSORT(base, nmemb, compar); + +@@ +expression base, nmemb, compar; +@@ +- if (nmemb) + QSORT(base, nmemb, compar); + +@@ +expression base, nmemb, compar; +@@ +- if (nmemb > 0) + QSORT(base, nmemb, compar); + +@@ +expression base, nmemb, compar; +@@ +- if (nmemb > 1) + QSORT(base, nmemb, compar); diff --git a/contrib/coccinelle/strbuf.cocci b/contrib/coccinelle/strbuf.cocci new file mode 100644 index 000000000000..d9ada69b4323 --- /dev/null +++ b/contrib/coccinelle/strbuf.cocci @@ -0,0 +1,62 @@ +@ strbuf_addf_with_format_only @ +expression E; +constant fmt !~ "%"; +@@ +- strbuf_addf ++ strbuf_addstr + (E, +( + fmt +| + _(fmt) +) + ); + +@@ +expression E; +struct strbuf SB; +format F =~ "s"; +@@ +- strbuf_addf(E, "%@F@", SB.buf); ++ strbuf_addbuf(E, &SB); + +@@ +expression E; +struct strbuf *SBP; +format F =~ "s"; +@@ +- strbuf_addf(E, "%@F@", SBP->buf); ++ strbuf_addbuf(E, SBP); + +@@ +expression E; +struct strbuf SB; +@@ +- strbuf_addstr(E, SB.buf); ++ strbuf_addbuf(E, &SB); + +@@ +expression E; +struct strbuf *SBP; +@@ +- strbuf_addstr(E, SBP->buf); ++ strbuf_addbuf(E, SBP); + +@@ +expression E1, E2; +format F =~ "s"; +@@ +- strbuf_addf(E1, "%@F@", E2); ++ strbuf_addstr(E1, E2); + +@@ +expression E1, E2, E3; +@@ +- strbuf_addstr(E1, find_unique_abbrev(E2, E3)); ++ strbuf_add_unique_abbrev(E1, E2, E3); + +@@ +expression E1, E2; +@@ +- strbuf_addstr(E1, real_path(E2)); ++ strbuf_add_real_path(E1, E2); diff --git a/contrib/coccinelle/swap.cocci b/contrib/coccinelle/swap.cocci new file mode 100644 index 000000000000..a0934d1fdaf0 --- /dev/null +++ b/contrib/coccinelle/swap.cocci @@ -0,0 +1,28 @@ +@ swap_with_declaration @ +type T; +identifier tmp; +T a, b; +@@ +- T tmp = a; ++ T tmp; ++ tmp = a; + a = b; + b = tmp; + +@ swap @ +type T; +T tmp, a, b; +@@ +- tmp = a; +- a = b; +- b = tmp; ++ SWAP(a, b); + +@ extends swap @ +identifier unused; +@@ + { + ... +- T unused; + ... when != unused + } diff --git a/contrib/coccinelle/the_repository.pending.cocci b/contrib/coccinelle/the_repository.pending.cocci new file mode 100644 index 000000000000..2ee702ecf7fe --- /dev/null +++ b/contrib/coccinelle/the_repository.pending.cocci @@ -0,0 +1,144 @@ +// This file is used for the ongoing refactoring of +// bringing the index or repository struct in all of +// our code base. + +@@ +expression E; +expression F; +expression G; +@@ +- read_object_file( ++ repo_read_object_file(the_repository, + E, F, G) + +@@ +expression E; +@@ +- has_sha1_file( ++ repo_has_sha1_file(the_repository, + E) + +@@ +expression E; +expression F; +@@ +- has_sha1_file_with_flags( ++ repo_has_sha1_file_with_flags(the_repository, + E) + +@@ +expression E; +@@ +- has_object_file( ++ repo_has_object_file(the_repository, + E) + +@@ +expression E; +expression F; +@@ +- has_object_file_with_flags( ++ repo_has_object_file_with_flags(the_repository, + E) + +@@ +expression E; +expression F; +expression G; +@@ +- parse_commit_internal( ++ repo_parse_commit_internal(the_repository, + E, F, G) + +@@ +expression E; +expression F; +@@ +- parse_commit_gently( ++ repo_parse_commit_gently(the_repository, + E, F) + +@@ +expression E; +@@ +- parse_commit( ++ repo_parse_commit(the_repository, + E) + +@@ +expression E; +expression F; +@@ +- get_merge_bases( ++ repo_get_merge_bases(the_repository, + E, F); + +@@ +expression E; +expression F; +expression G; +@@ +- get_merge_bases_many( ++ repo_get_merge_bases_many(the_repository, + E, F, G); + +@@ +expression E; +expression F; +expression G; +@@ +- get_merge_bases_many_dirty( ++ repo_get_merge_bases_many_dirty(the_repository, + E, F, G); + +@@ +expression E; +expression F; +@@ +- in_merge_bases( ++ repo_in_merge_bases(the_repository, + E, F); + +@@ +expression E; +expression F; +expression G; +@@ +- in_merge_bases_many( ++ repo_in_merge_bases_many(the_repository, + E, F, G); + +@@ +expression E; +expression F; +@@ +- get_commit_buffer( ++ repo_get_commit_buffer(the_repository, + E, F); + +@@ +expression E; +expression F; +@@ +- unuse_commit_buffer( ++ repo_unuse_commit_buffer(the_repository, + E, F); + +@@ +expression E; +expression F; +expression G; +@@ +- logmsg_reencode( ++ repo_logmsg_reencode(the_repository, + E, F, G); + +@@ +expression E; +expression F; +expression G; +expression H; +@@ +- format_commit_message( ++ repo_format_commit_message(the_repository, + E, F, G, H); diff --git a/contrib/coccinelle/xstrdup_or_null.cocci b/contrib/coccinelle/xstrdup_or_null.cocci new file mode 100644 index 000000000000..8e05d1ca4b61 --- /dev/null +++ b/contrib/coccinelle/xstrdup_or_null.cocci @@ -0,0 +1,13 @@ +@@ +expression E; +expression V; +@@ +- if (E) +- V = xstrdup(E); ++ V = xstrdup_or_null(E); + +@@ +expression E; +@@ +- xstrdup(absolute_path(E)) ++ absolute_pathdup(E) diff --git a/contrib/completion/.gitattributes b/contrib/completion/.gitattributes new file mode 100644 index 000000000000..19116944c15c --- /dev/null +++ b/contrib/completion/.gitattributes @@ -0,0 +1 @@ +*.bash eol=lf diff --git a/contrib/completion/git-completion.bash b/contrib/completion/git-completion.bash new file mode 100644 index 000000000000..e087c4bf0085 --- /dev/null +++ b/contrib/completion/git-completion.bash @@ -0,0 +1,3151 @@ +# bash/zsh completion support for core Git. +# +# Copyright (C) 2006,2007 Shawn O. Pearce <spearce@spearce.org> +# Conceptually based on gitcompletion (http://gitweb.hawaga.org.uk/). +# Distributed under the GNU General Public License, version 2.0. +# +# The contained completion routines provide support for completing: +# +# *) local and remote branch names +# *) local and remote tag names +# *) .git/remotes file names +# *) git 'subcommands' +# *) git email aliases for git-send-email +# *) tree paths within 'ref:path/to/file' expressions +# *) file paths within current working directory and index +# *) common --long-options +# +# To use these routines: +# +# 1) Copy this file to somewhere (e.g. ~/.git-completion.bash). +# 2) Add the following line to your .bashrc/.zshrc: +# source ~/.git-completion.bash +# 3) Consider changing your PS1 to also show the current branch, +# see git-prompt.sh for details. +# +# If you use complex aliases of form '!f() { ... }; f', you can use the null +# command ':' as the first command in the function body to declare the desired +# completion style. For example '!f() { : git commit ; ... }; f' will +# tell the completion to use commit completion. This also works with aliases +# of form "!sh -c '...'". For example, "!sh -c ': git commit ; ... '". +# +# Compatible with bash 3.2.57. +# +# You can set the following environment variables to influence the behavior of +# the completion routines: +# +# GIT_COMPLETION_CHECKOUT_NO_GUESS +# +# When set to "1", do not include "DWIM" suggestions in git-checkout +# and git-switch completion (e.g., completing "foo" when "origin/foo" +# exists). + +case "$COMP_WORDBREAKS" in +*:*) : great ;; +*) COMP_WORDBREAKS="$COMP_WORDBREAKS:" +esac + +# Discovers the path to the git repository taking any '--git-dir=<path>' and +# '-C <path>' options into account and stores it in the $__git_repo_path +# variable. +__git_find_repo_path () +{ + if [ -n "$__git_repo_path" ]; then + # we already know where it is + return + fi + + if [ -n "${__git_C_args-}" ]; then + __git_repo_path="$(git "${__git_C_args[@]}" \ + ${__git_dir:+--git-dir="$__git_dir"} \ + rev-parse --absolute-git-dir 2>/dev/null)" + elif [ -n "${__git_dir-}" ]; then + test -d "$__git_dir" && + __git_repo_path="$__git_dir" + elif [ -n "${GIT_DIR-}" ]; then + test -d "${GIT_DIR-}" && + __git_repo_path="$GIT_DIR" + elif [ -d .git ]; then + __git_repo_path=.git + else + __git_repo_path="$(git rev-parse --git-dir 2>/dev/null)" + fi +} + +# Deprecated: use __git_find_repo_path() and $__git_repo_path instead +# __gitdir accepts 0 or 1 arguments (i.e., location) +# returns location of .git repo +__gitdir () +{ + if [ -z "${1-}" ]; then + __git_find_repo_path || return 1 + echo "$__git_repo_path" + elif [ -d "$1/.git" ]; then + echo "$1/.git" + else + echo "$1" + fi +} + +# Runs git with all the options given as argument, respecting any +# '--git-dir=<path>' and '-C <path>' options present on the command line +__git () +{ + git ${__git_C_args:+"${__git_C_args[@]}"} \ + ${__git_dir:+--git-dir="$__git_dir"} "$@" 2>/dev/null +} + +# Removes backslash escaping, single quotes and double quotes from a word, +# stores the result in the variable $dequoted_word. +# 1: The word to dequote. +__git_dequote () +{ + local rest="$1" len ch + + dequoted_word="" + + while test -n "$rest"; do + len=${#dequoted_word} + dequoted_word="$dequoted_word${rest%%[\\\'\"]*}" + rest="${rest:$((${#dequoted_word}-$len))}" + + case "${rest:0:1}" in + \\) + ch="${rest:1:1}" + case "$ch" in + $'\n') + ;; + *) + dequoted_word="$dequoted_word$ch" + ;; + esac + rest="${rest:2}" + ;; + \') + rest="${rest:1}" + len=${#dequoted_word} + dequoted_word="$dequoted_word${rest%%\'*}" + rest="${rest:$((${#dequoted_word}-$len+1))}" + ;; + \") + rest="${rest:1}" + while test -n "$rest" ; do + len=${#dequoted_word} + dequoted_word="$dequoted_word${rest%%[\\\"]*}" + rest="${rest:$((${#dequoted_word}-$len))}" + case "${rest:0:1}" in + \\) + ch="${rest:1:1}" + case "$ch" in + \"|\\|\$|\`) + dequoted_word="$dequoted_word$ch" + ;; + $'\n') + ;; + *) + dequoted_word="$dequoted_word\\$ch" + ;; + esac + rest="${rest:2}" + ;; + \") + rest="${rest:1}" + break + ;; + esac + done + ;; + esac + done +} + +# The following function is based on code from: +# +# bash_completion - programmable completion functions for bash 3.2+ +# +# Copyright © 2006-2008, Ian Macdonald <ian@caliban.org> +# © 2009-2010, Bash Completion Maintainers +# <bash-completion-devel@lists.alioth.debian.org> +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2, or (at your option) +# any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, see <http://www.gnu.org/licenses/>. +# +# The latest version of this software can be obtained here: +# +# http://bash-completion.alioth.debian.org/ +# +# RELEASE: 2.x + +# This function can be used to access a tokenized list of words +# on the command line: +# +# __git_reassemble_comp_words_by_ref '=:' +# if test "${words_[cword_-1]}" = -w +# then +# ... +# fi +# +# The argument should be a collection of characters from the list of +# word completion separators (COMP_WORDBREAKS) to treat as ordinary +# characters. +# +# This is roughly equivalent to going back in time and setting +# COMP_WORDBREAKS to exclude those characters. The intent is to +# make option types like --date=<type> and <rev>:<path> easy to +# recognize by treating each shell word as a single token. +# +# It is best not to set COMP_WORDBREAKS directly because the value is +# shared with other completion scripts. By the time the completion +# function gets called, COMP_WORDS has already been populated so local +# changes to COMP_WORDBREAKS have no effect. +# +# Output: words_, cword_, cur_. + +__git_reassemble_comp_words_by_ref() +{ + local exclude i j first + # Which word separators to exclude? + exclude="${1//[^$COMP_WORDBREAKS]}" + cword_=$COMP_CWORD + if [ -z "$exclude" ]; then + words_=("${COMP_WORDS[@]}") + return + fi + # List of word completion separators has shrunk; + # re-assemble words to complete. + for ((i=0, j=0; i < ${#COMP_WORDS[@]}; i++, j++)); do + # Append each nonempty word consisting of just + # word separator characters to the current word. + first=t + while + [ $i -gt 0 ] && + [ -n "${COMP_WORDS[$i]}" ] && + # word consists of excluded word separators + [ "${COMP_WORDS[$i]//[^$exclude]}" = "${COMP_WORDS[$i]}" ] + do + # Attach to the previous token, + # unless the previous token is the command name. + if [ $j -ge 2 ] && [ -n "$first" ]; then + ((j--)) + fi + first= + words_[$j]=${words_[j]}${COMP_WORDS[i]} + if [ $i = $COMP_CWORD ]; then + cword_=$j + fi + if (($i < ${#COMP_WORDS[@]} - 1)); then + ((i++)) + else + # Done. + return + fi + done + words_[$j]=${words_[j]}${COMP_WORDS[i]} + if [ $i = $COMP_CWORD ]; then + cword_=$j + fi + done +} + +if ! type _get_comp_words_by_ref >/dev/null 2>&1; then +_get_comp_words_by_ref () +{ + local exclude cur_ words_ cword_ + if [ "$1" = "-n" ]; then + exclude=$2 + shift 2 + fi + __git_reassemble_comp_words_by_ref "$exclude" + cur_=${words_[cword_]} + while [ $# -gt 0 ]; do + case "$1" in + cur) + cur=$cur_ + ;; + prev) + prev=${words_[$cword_-1]} + ;; + words) + words=("${words_[@]}") + ;; + cword) + cword=$cword_ + ;; + esac + shift + done +} +fi + +# Fills the COMPREPLY array with prefiltered words without any additional +# processing. +# Callers must take care of providing only words that match the current word +# to be completed and adding any prefix and/or suffix (trailing space!), if +# necessary. +# 1: List of newline-separated matching completion words, complete with +# prefix and suffix. +__gitcomp_direct () +{ + local IFS=$'\n' + + COMPREPLY=($1) +} + +__gitcompappend () +{ + local x i=${#COMPREPLY[@]} + for x in $1; do + if [[ "$x" == "$3"* ]]; then + COMPREPLY[i++]="$2$x$4" + fi + done +} + +__gitcompadd () +{ + COMPREPLY=() + __gitcompappend "$@" +} + +# Generates completion reply, appending a space to possible completion words, +# if necessary. +# It accepts 1 to 4 arguments: +# 1: List of possible completion words. +# 2: A prefix to be added to each possible completion word (optional). +# 3: Generate possible completion matches for this word (optional). +# 4: A suffix to be appended to each possible completion word (optional). +__gitcomp () +{ + local cur_="${3-$cur}" + + case "$cur_" in + --*=) + ;; + --no-*) + local c i=0 IFS=$' \t\n' + for c in $1; do + if [[ $c == "--" ]]; then + continue + fi + c="$c${4-}" + if [[ $c == "$cur_"* ]]; then + case $c in + --*=*|*.) ;; + *) c="$c " ;; + esac + COMPREPLY[i++]="${2-}$c" + fi + done + ;; + *) + local c i=0 IFS=$' \t\n' + for c in $1; do + if [[ $c == "--" ]]; then + c="--no-...${4-}" + if [[ $c == "$cur_"* ]]; then + COMPREPLY[i++]="${2-}$c " + fi + break + fi + c="$c${4-}" + if [[ $c == "$cur_"* ]]; then + case $c in + --*=*|*.) ;; + *) c="$c " ;; + esac + COMPREPLY[i++]="${2-}$c" + fi + done + ;; + esac +} + +# Clear the variables caching builtins' options when (re-)sourcing +# the completion script. +if [[ -n ${ZSH_VERSION-} ]]; then + unset $(set |sed -ne 's/^\(__gitcomp_builtin_[a-zA-Z0-9_][a-zA-Z0-9_]*\)=.*/\1/p') 2>/dev/null +else + unset $(compgen -v __gitcomp_builtin_) +fi + +# This function is equivalent to +# +# __gitcomp "$(git xxx --git-completion-helper) ..." +# +# except that the output is cached. Accept 1-3 arguments: +# 1: the git command to execute, this is also the cache key +# 2: extra options to be added on top (e.g. negative forms) +# 3: options to be excluded +__gitcomp_builtin () +{ + # spaces must be replaced with underscore for multi-word + # commands, e.g. "git remote add" becomes remote_add. + local cmd="$1" + local incl="$2" + local excl="$3" + + local var=__gitcomp_builtin_"${cmd/-/_}" + local options + eval "options=\$$var" + + if [ -z "$options" ]; then + # leading and trailing spaces are significant to make + # option removal work correctly. + options=" $incl $(__git ${cmd/_/ } --git-completion-helper) " || return + + for i in $excl; do + options="${options/ $i / }" + done + eval "$var=\"$options\"" + fi + + __gitcomp "$options" +} + +# Variation of __gitcomp_nl () that appends to the existing list of +# completion candidates, COMPREPLY. +__gitcomp_nl_append () +{ + local IFS=$'\n' + __gitcompappend "$1" "${2-}" "${3-$cur}" "${4- }" +} + +# Generates completion reply from newline-separated possible completion words +# by appending a space to all of them. +# It accepts 1 to 4 arguments: +# 1: List of possible completion words, separated by a single newline. +# 2: A prefix to be added to each possible completion word (optional). +# 3: Generate possible completion matches for this word (optional). +# 4: A suffix to be appended to each possible completion word instead of +# the default space (optional). If specified but empty, nothing is +# appended. +__gitcomp_nl () +{ + COMPREPLY=() + __gitcomp_nl_append "$@" +} + +# Fills the COMPREPLY array with prefiltered paths without any additional +# processing. +# Callers must take care of providing only paths that match the current path +# to be completed and adding any prefix path components, if necessary. +# 1: List of newline-separated matching paths, complete with all prefix +# path components. +__gitcomp_file_direct () +{ + local IFS=$'\n' + + COMPREPLY=($1) + + # use a hack to enable file mode in bash < 4 + compopt -o filenames +o nospace 2>/dev/null || + compgen -f /non-existing-dir/ >/dev/null || + true +} + +# Generates completion reply with compgen from newline-separated possible +# completion filenames. +# It accepts 1 to 3 arguments: +# 1: List of possible completion filenames, separated by a single newline. +# 2: A directory prefix to be added to each possible completion filename +# (optional). +# 3: Generate possible completion matches for this word (optional). +__gitcomp_file () +{ + local IFS=$'\n' + + # XXX does not work when the directory prefix contains a tilde, + # since tilde expansion is not applied. + # This means that COMPREPLY will be empty and Bash default + # completion will be used. + __gitcompadd "$1" "${2-}" "${3-$cur}" "" + + # use a hack to enable file mode in bash < 4 + compopt -o filenames +o nospace 2>/dev/null || + compgen -f /non-existing-dir/ >/dev/null || + true +} + +# Execute 'git ls-files', unless the --committable option is specified, in +# which case it runs 'git diff-index' to find out the files that can be +# committed. It return paths relative to the directory specified in the first +# argument, and using the options specified in the second argument. +__git_ls_files_helper () +{ + if [ "$2" == "--committable" ]; then + __git -C "$1" -c core.quotePath=false diff-index \ + --name-only --relative HEAD -- "${3//\\/\\\\}*" + else + # NOTE: $2 is not quoted in order to support multiple options + __git -C "$1" -c core.quotePath=false ls-files \ + --exclude-standard $2 -- "${3//\\/\\\\}*" + fi +} + + +# __git_index_files accepts 1 or 2 arguments: +# 1: Options to pass to ls-files (required). +# 2: A directory path (optional). +# If provided, only files within the specified directory are listed. +# Sub directories are never recursed. Path must have a trailing +# slash. +# 3: List only paths matching this path component (optional). +__git_index_files () +{ + local root="$2" match="$3" + + __git_ls_files_helper "$root" "$1" "$match" | + awk -F / -v pfx="${2//\\/\\\\}" '{ + paths[$1] = 1 + } + END { + for (p in paths) { + if (substr(p, 1, 1) != "\"") { + # No special characters, easy! + print pfx p + continue + } + + # The path is quoted. + p = dequote(p) + if (p == "") + continue + + # Even when a directory name itself does not contain + # any special characters, it will still be quoted if + # any of its (stripped) trailing path components do. + # Because of this we may have seen the same direcory + # both quoted and unquoted. + if (p in paths) + # We have seen the same directory unquoted, + # skip it. + continue + else + print pfx p + } + } + function dequote(p, bs_idx, out, esc, esc_idx, dec) { + # Skip opening double quote. + p = substr(p, 2) + + # Interpret backslash escape sequences. + while ((bs_idx = index(p, "\\")) != 0) { + out = out substr(p, 1, bs_idx - 1) + esc = substr(p, bs_idx + 1, 1) + p = substr(p, bs_idx + 2) + + if ((esc_idx = index("abtvfr\"\\", esc)) != 0) { + # C-style one-character escape sequence. + out = out substr("\a\b\t\v\f\r\"\\", + esc_idx, 1) + } else if (esc == "n") { + # Uh-oh, a newline character. + # We cant reliably put a pathname + # containing a newline into COMPREPLY, + # and the newline would create a mess. + # Skip this path. + return "" + } else { + # Must be a \nnn octal value, then. + dec = esc * 64 + \ + substr(p, 1, 1) * 8 + \ + substr(p, 2, 1) + out = out sprintf("%c", dec) + p = substr(p, 3) + } + } + # Drop closing double quote, if there is one. + # (There isnt any if this is a directory, as it was + # already stripped with the trailing path components.) + if (substr(p, length(p), 1) == "\"") + out = out substr(p, 1, length(p) - 1) + else + out = out p + + return out + }' +} + +# __git_complete_index_file requires 1 argument: +# 1: the options to pass to ls-file +# +# The exception is --committable, which finds the files appropriate commit. +__git_complete_index_file () +{ + local dequoted_word pfx="" cur_ + + __git_dequote "$cur" + + case "$dequoted_word" in + ?*/*) + pfx="${dequoted_word%/*}/" + cur_="${dequoted_word##*/}" + ;; + *) + cur_="$dequoted_word" + esac + + __gitcomp_file_direct "$(__git_index_files "$1" "$pfx" "$cur_")" +} + +# Lists branches from the local repository. +# 1: A prefix to be added to each listed branch (optional). +# 2: List only branches matching this word (optional; list all branches if +# unset or empty). +# 3: A suffix to be appended to each listed branch (optional). +__git_heads () +{ + local pfx="${1-}" cur_="${2-}" sfx="${3-}" + + __git for-each-ref --format="${pfx//\%/%%}%(refname:strip=2)$sfx" \ + "refs/heads/$cur_*" "refs/heads/$cur_*/**" +} + +# Lists tags from the local repository. +# Accepts the same positional parameters as __git_heads() above. +__git_tags () +{ + local pfx="${1-}" cur_="${2-}" sfx="${3-}" + + __git for-each-ref --format="${pfx//\%/%%}%(refname:strip=2)$sfx" \ + "refs/tags/$cur_*" "refs/tags/$cur_*/**" +} + +# Lists refs from the local (by default) or from a remote repository. +# It accepts 0, 1 or 2 arguments: +# 1: The remote to list refs from (optional; ignored, if set but empty). +# Can be the name of a configured remote, a path, or a URL. +# 2: In addition to local refs, list unique branches from refs/remotes/ for +# 'git checkout's tracking DWIMery (optional; ignored, if set but empty). +# 3: A prefix to be added to each listed ref (optional). +# 4: List only refs matching this word (optional; list all refs if unset or +# empty). +# 5: A suffix to be appended to each listed ref (optional; ignored, if set +# but empty). +# +# Use __git_complete_refs() instead. +__git_refs () +{ + local i hash dir track="${2-}" + local list_refs_from=path remote="${1-}" + local format refs + local pfx="${3-}" cur_="${4-$cur}" sfx="${5-}" + local match="${4-}" + local fer_pfx="${pfx//\%/%%}" # "escape" for-each-ref format specifiers + + __git_find_repo_path + dir="$__git_repo_path" + + if [ -z "$remote" ]; then + if [ -z "$dir" ]; then + return + fi + else + if __git_is_configured_remote "$remote"; then + # configured remote takes precedence over a + # local directory with the same name + list_refs_from=remote + elif [ -d "$remote/.git" ]; then + dir="$remote/.git" + elif [ -d "$remote" ]; then + dir="$remote" + else + list_refs_from=url + fi + fi + + if [ "$list_refs_from" = path ]; then + if [[ "$cur_" == ^* ]]; then + pfx="$pfx^" + fer_pfx="$fer_pfx^" + cur_=${cur_#^} + match=${match#^} + fi + case "$cur_" in + refs|refs/*) + format="refname" + refs=("$match*" "$match*/**") + track="" + ;; + *) + for i in HEAD FETCH_HEAD ORIG_HEAD MERGE_HEAD REBASE_HEAD; do + case "$i" in + $match*) + if [ -e "$dir/$i" ]; then + echo "$pfx$i$sfx" + fi + ;; + esac + done + format="refname:strip=2" + refs=("refs/tags/$match*" "refs/tags/$match*/**" + "refs/heads/$match*" "refs/heads/$match*/**" + "refs/remotes/$match*" "refs/remotes/$match*/**") + ;; + esac + __git_dir="$dir" __git for-each-ref --format="$fer_pfx%($format)$sfx" \ + "${refs[@]}" + if [ -n "$track" ]; then + # employ the heuristic used by git checkout + # Try to find a remote branch that matches the completion word + # but only output if the branch name is unique + __git for-each-ref --format="$fer_pfx%(refname:strip=3)$sfx" \ + --sort="refname:strip=3" \ + "refs/remotes/*/$match*" "refs/remotes/*/$match*/**" | \ + uniq -u + fi + return + fi + case "$cur_" in + refs|refs/*) + __git ls-remote "$remote" "$match*" | \ + while read -r hash i; do + case "$i" in + *^{}) ;; + *) echo "$pfx$i$sfx" ;; + esac + done + ;; + *) + if [ "$list_refs_from" = remote ]; then + case "HEAD" in + $match*) echo "${pfx}HEAD$sfx" ;; + esac + __git for-each-ref --format="$fer_pfx%(refname:strip=3)$sfx" \ + "refs/remotes/$remote/$match*" \ + "refs/remotes/$remote/$match*/**" + else + local query_symref + case "HEAD" in + $match*) query_symref="HEAD" ;; + esac + __git ls-remote "$remote" $query_symref \ + "refs/tags/$match*" "refs/heads/$match*" \ + "refs/remotes/$match*" | + while read -r hash i; do + case "$i" in + *^{}) ;; + refs/*) echo "$pfx${i#refs/*/}$sfx" ;; + *) echo "$pfx$i$sfx" ;; # symbolic refs + esac + done + fi + ;; + esac +} + +# Completes refs, short and long, local and remote, symbolic and pseudo. +# +# Usage: __git_complete_refs [<option>]... +# --remote=<remote>: The remote to list refs from, can be the name of a +# configured remote, a path, or a URL. +# --track: List unique remote branches for 'git checkout's tracking DWIMery. +# --pfx=<prefix>: A prefix to be added to each ref. +# --cur=<word>: The current ref to be completed. Defaults to the current +# word to be completed. +# --sfx=<suffix>: A suffix to be appended to each ref instead of the default +# space. +__git_complete_refs () +{ + local remote track pfx cur_="$cur" sfx=" " + + while test $# != 0; do + case "$1" in + --remote=*) remote="${1##--remote=}" ;; + --track) track="yes" ;; + --pfx=*) pfx="${1##--pfx=}" ;; + --cur=*) cur_="${1##--cur=}" ;; + --sfx=*) sfx="${1##--sfx=}" ;; + *) return 1 ;; + esac + shift + done + + __gitcomp_direct "$(__git_refs "$remote" "$track" "$pfx" "$cur_" "$sfx")" +} + +# __git_refs2 requires 1 argument (to pass to __git_refs) +# Deprecated: use __git_complete_fetch_refspecs() instead. +__git_refs2 () +{ + local i + for i in $(__git_refs "$1"); do + echo "$i:$i" + done +} + +# Completes refspecs for fetching from a remote repository. +# 1: The remote repository. +# 2: A prefix to be added to each listed refspec (optional). +# 3: The ref to be completed as a refspec instead of the current word to be +# completed (optional) +# 4: A suffix to be appended to each listed refspec instead of the default +# space (optional). +__git_complete_fetch_refspecs () +{ + local i remote="$1" pfx="${2-}" cur_="${3-$cur}" sfx="${4- }" + + __gitcomp_direct "$( + for i in $(__git_refs "$remote" "" "" "$cur_") ; do + echo "$pfx$i:$i$sfx" + done + )" +} + +# __git_refs_remotes requires 1 argument (to pass to ls-remote) +__git_refs_remotes () +{ + local i hash + __git ls-remote "$1" 'refs/heads/*' | \ + while read -r hash i; do + echo "$i:refs/remotes/$1/${i#refs/heads/}" + done +} + +__git_remotes () +{ + __git_find_repo_path + test -d "$__git_repo_path/remotes" && ls -1 "$__git_repo_path/remotes" + __git remote +} + +# Returns true if $1 matches the name of a configured remote, false otherwise. +__git_is_configured_remote () +{ + local remote + for remote in $(__git_remotes); do + if [ "$remote" = "$1" ]; then + return 0 + fi + done + return 1 +} + +__git_list_merge_strategies () +{ + LANG=C LC_ALL=C git merge -s help 2>&1 | + sed -n -e '/[Aa]vailable strategies are: /,/^$/{ + s/\.$// + s/.*:// + s/^[ ]*// + s/[ ]*$// + p + }' +} + +__git_merge_strategies= +# 'git merge -s help' (and thus detection of the merge strategy +# list) fails, unfortunately, if run outside of any git working +# tree. __git_merge_strategies is set to the empty string in +# that case, and the detection will be repeated the next time it +# is needed. +__git_compute_merge_strategies () +{ + test -n "$__git_merge_strategies" || + __git_merge_strategies=$(__git_list_merge_strategies) +} + +__git_merge_strategy_options="ours theirs subtree subtree= patience + histogram diff-algorithm= ignore-space-change ignore-all-space + ignore-space-at-eol renormalize no-renormalize no-renames + find-renames find-renames= rename-threshold=" + +__git_complete_revlist_file () +{ + local dequoted_word pfx ls ref cur_="$cur" + case "$cur_" in + *..?*:*) + return + ;; + ?*:*) + ref="${cur_%%:*}" + cur_="${cur_#*:}" + + __git_dequote "$cur_" + + case "$dequoted_word" in + ?*/*) + pfx="${dequoted_word%/*}" + cur_="${dequoted_word##*/}" + ls="$ref:$pfx" + pfx="$pfx/" + ;; + *) + cur_="$dequoted_word" + ls="$ref" + ;; + esac + + case "$COMP_WORDBREAKS" in + *:*) : great ;; + *) pfx="$ref:$pfx" ;; + esac + + __gitcomp_file "$(__git ls-tree "$ls" \ + | sed 's/^.* // + s/$//')" \ + "$pfx" "$cur_" + ;; + *...*) + pfx="${cur_%...*}..." + cur_="${cur_#*...}" + __git_complete_refs --pfx="$pfx" --cur="$cur_" + ;; + *..*) + pfx="${cur_%..*}.." + cur_="${cur_#*..}" + __git_complete_refs --pfx="$pfx" --cur="$cur_" + ;; + *) + __git_complete_refs + ;; + esac +} + +__git_complete_file () +{ + __git_complete_revlist_file +} + +__git_complete_revlist () +{ + __git_complete_revlist_file +} + +__git_complete_remote_or_refspec () +{ + local cur_="$cur" cmd="${words[1]}" + local i c=2 remote="" pfx="" lhs=1 no_complete_refspec=0 + if [ "$cmd" = "remote" ]; then + ((c++)) + fi + while [ $c -lt $cword ]; do + i="${words[c]}" + case "$i" in + --mirror) [ "$cmd" = "push" ] && no_complete_refspec=1 ;; + -d|--delete) [ "$cmd" = "push" ] && lhs=0 ;; + --all) + case "$cmd" in + push) no_complete_refspec=1 ;; + fetch) + return + ;; + *) ;; + esac + ;; + --multiple) no_complete_refspec=1; break ;; + -*) ;; + *) remote="$i"; break ;; + esac + ((c++)) + done + if [ -z "$remote" ]; then + __gitcomp_nl "$(__git_remotes)" + return + fi + if [ $no_complete_refspec = 1 ]; then + return + fi + [ "$remote" = "." ] && remote= + case "$cur_" in + *:*) + case "$COMP_WORDBREAKS" in + *:*) : great ;; + *) pfx="${cur_%%:*}:" ;; + esac + cur_="${cur_#*:}" + lhs=0 + ;; + +*) + pfx="+" + cur_="${cur_#+}" + ;; + esac + case "$cmd" in + fetch) + if [ $lhs = 1 ]; then + __git_complete_fetch_refspecs "$remote" "$pfx" "$cur_" + else + __git_complete_refs --pfx="$pfx" --cur="$cur_" + fi + ;; + pull|remote) + if [ $lhs = 1 ]; then + __git_complete_refs --remote="$remote" --pfx="$pfx" --cur="$cur_" + else + __git_complete_refs --pfx="$pfx" --cur="$cur_" + fi + ;; + push) + if [ $lhs = 1 ]; then + __git_complete_refs --pfx="$pfx" --cur="$cur_" + else + __git_complete_refs --remote="$remote" --pfx="$pfx" --cur="$cur_" + fi + ;; + esac +} + +__git_complete_strategy () +{ + __git_compute_merge_strategies + case "$prev" in + -s|--strategy) + __gitcomp "$__git_merge_strategies" + return 0 + ;; + -X) + __gitcomp "$__git_merge_strategy_options" + return 0 + ;; + esac + case "$cur" in + --strategy=*) + __gitcomp "$__git_merge_strategies" "" "${cur##--strategy=}" + return 0 + ;; + --strategy-option=*) + __gitcomp "$__git_merge_strategy_options" "" "${cur##--strategy-option=}" + return 0 + ;; + esac + return 1 +} + +__git_all_commands= +__git_compute_all_commands () +{ + test -n "$__git_all_commands" || + __git_all_commands=$(__git --list-cmds=main,others,alias,nohelpers) +} + +# Lists all set config variables starting with the given section prefix, +# with the prefix removed. +__git_get_config_variables () +{ + local section="$1" i IFS=$'\n' + for i in $(__git config --name-only --get-regexp "^$section\..*"); do + echo "${i#$section.}" + done +} + +__git_pretty_aliases () +{ + __git_get_config_variables "pretty" +} + +# __git_aliased_command requires 1 argument +__git_aliased_command () +{ + local word cmdline=$(__git config --get "alias.$1") + for word in $cmdline; do + case "$word" in + \!gitk|gitk) + echo "gitk" + return + ;; + \!*) : shell command alias ;; + -*) : option ;; + *=*) : setting env ;; + git) : git itself ;; + \(\)) : skip parens of shell function definition ;; + {) : skip start of shell helper function ;; + :) : skip null command ;; + \'*) : skip opening quote after sh -c ;; + *) + echo "$word" + return + esac + done +} + +# __git_find_on_cmdline requires 1 argument +__git_find_on_cmdline () +{ + local word subcommand c=1 + while [ $c -lt $cword ]; do + word="${words[c]}" + for subcommand in $1; do + if [ "$subcommand" = "$word" ]; then + echo "$subcommand" + return + fi + done + ((c++)) + done +} + +# Echo the value of an option set on the command line or config +# +# $1: short option name +# $2: long option name including = +# $3: list of possible values +# $4: config string (optional) +# +# example: +# result="$(__git_get_option_value "-d" "--do-something=" \ +# "yes no" "core.doSomething")" +# +# result is then either empty (no option set) or "yes" or "no" +# +# __git_get_option_value requires 3 arguments +__git_get_option_value () +{ + local c short_opt long_opt val + local result= values config_key word + + short_opt="$1" + long_opt="$2" + values="$3" + config_key="$4" + + ((c = $cword - 1)) + while [ $c -ge 0 ]; do + word="${words[c]}" + for val in $values; do + if [ "$short_opt$val" = "$word" ] || + [ "$long_opt$val" = "$word" ]; then + result="$val" + break 2 + fi + done + ((c--)) + done + + if [ -n "$config_key" ] && [ -z "$result" ]; then + result="$(__git config "$config_key")" + fi + + echo "$result" +} + +__git_has_doubledash () +{ + local c=1 + while [ $c -lt $cword ]; do + if [ "--" = "${words[c]}" ]; then + return 0 + fi + ((c++)) + done + return 1 +} + +# Try to count non option arguments passed on the command line for the +# specified git command. +# When options are used, it is necessary to use the special -- option to +# tell the implementation were non option arguments begin. +# XXX this can not be improved, since options can appear everywhere, as +# an example: +# git mv x -n y +# +# __git_count_arguments requires 1 argument: the git command executed. +__git_count_arguments () +{ + local word i c=0 + + # Skip "git" (first argument) + for ((i=1; i < ${#words[@]}; i++)); do + word="${words[i]}" + + case "$word" in + --) + # Good; we can assume that the following are only non + # option arguments. + ((c = 0)) + ;; + "$1") + # Skip the specified git command and discard git + # main options + ((c = 0)) + ;; + ?*) + ((c++)) + ;; + esac + done + + printf "%d" $c +} + +__git_whitespacelist="nowarn warn error error-all fix" +__git_patchformat="mbox stgit stgit-series hg mboxrd" +__git_am_inprogress_options="--skip --continue --resolved --abort --quit --show-current-patch" + +_git_am () +{ + __git_find_repo_path + if [ -d "$__git_repo_path"/rebase-apply ]; then + __gitcomp "$__git_am_inprogress_options" + return + fi + case "$cur" in + --whitespace=*) + __gitcomp "$__git_whitespacelist" "" "${cur##--whitespace=}" + return + ;; + --patch-format=*) + __gitcomp "$__git_patchformat" "" "${cur##--patch-format=}" + return + ;; + --*) + __gitcomp_builtin am "" \ + "$__git_am_inprogress_options" + return + esac +} + +_git_apply () +{ + case "$cur" in + --whitespace=*) + __gitcomp "$__git_whitespacelist" "" "${cur##--whitespace=}" + return + ;; + --*) + __gitcomp_builtin apply + return + esac +} + +_git_add () +{ + case "$cur" in + --chmod=*) + __gitcomp "+x -x" "" "${cur##--chmod=}" + return + ;; + --*) + __gitcomp_builtin add + return + esac + + local complete_opt="--others --modified --directory --no-empty-directory" + if test -n "$(__git_find_on_cmdline "-u --update")" + then + complete_opt="--modified" + fi + __git_complete_index_file "$complete_opt" +} + +_git_archive () +{ + case "$cur" in + --format=*) + __gitcomp "$(git archive --list)" "" "${cur##--format=}" + return + ;; + --remote=*) + __gitcomp_nl "$(__git_remotes)" "" "${cur##--remote=}" + return + ;; + --*) + __gitcomp " + --format= --list --verbose + --prefix= --remote= --exec= --output + " + return + ;; + esac + __git_complete_file +} + +_git_bisect () +{ + __git_has_doubledash && return + + local subcommands="start bad good skip reset visualize replay log run" + local subcommand="$(__git_find_on_cmdline "$subcommands")" + if [ -z "$subcommand" ]; then + __git_find_repo_path + if [ -f "$__git_repo_path"/BISECT_START ]; then + __gitcomp "$subcommands" + else + __gitcomp "replay start" + fi + return + fi + + case "$subcommand" in + bad|good|reset|skip|start) + __git_complete_refs + ;; + *) + ;; + esac +} + +__git_ref_fieldlist="refname objecttype objectsize objectname upstream push HEAD symref" + +_git_branch () +{ + local i c=1 only_local_ref="n" has_r="n" + + while [ $c -lt $cword ]; do + i="${words[c]}" + case "$i" in + -d|--delete|-m|--move) only_local_ref="y" ;; + -r|--remotes) has_r="y" ;; + esac + ((c++)) + done + + case "$cur" in + --set-upstream-to=*) + __git_complete_refs --cur="${cur##--set-upstream-to=}" + ;; + --*) + __gitcomp_builtin branch + ;; + *) + if [ $only_local_ref = "y" -a $has_r = "n" ]; then + __gitcomp_direct "$(__git_heads "" "$cur" " ")" + else + __git_complete_refs + fi + ;; + esac +} + +_git_bundle () +{ + local cmd="${words[2]}" + case "$cword" in + 2) + __gitcomp "create list-heads verify unbundle" + ;; + 3) + # looking for a file + ;; + *) + case "$cmd" in + create) + __git_complete_revlist + ;; + esac + ;; + esac +} + +_git_checkout () +{ + __git_has_doubledash && return + + case "$cur" in + --conflict=*) + __gitcomp "diff3 merge" "" "${cur##--conflict=}" + ;; + --*) + __gitcomp_builtin checkout + ;; + *) + # check if --track, --no-track, or --no-guess was specified + # if so, disable DWIM mode + local flags="--track --no-track --no-guess" track_opt="--track" + if [ "$GIT_COMPLETION_CHECKOUT_NO_GUESS" = "1" ] || + [ -n "$(__git_find_on_cmdline "$flags")" ]; then + track_opt='' + fi + __git_complete_refs $track_opt + ;; + esac +} + +__git_cherry_pick_inprogress_options="--continue --quit --abort" + +_git_cherry_pick () +{ + __git_find_repo_path + if [ -f "$__git_repo_path"/CHERRY_PICK_HEAD ]; then + __gitcomp "$__git_cherry_pick_inprogress_options" + return + fi + + __git_complete_strategy && return + + case "$cur" in + --*) + __gitcomp_builtin cherry-pick "" \ + "$__git_cherry_pick_inprogress_options" + ;; + *) + __git_complete_refs + ;; + esac +} + +_git_clean () +{ + case "$cur" in + --*) + __gitcomp_builtin clean + return + ;; + esac + + # XXX should we check for -x option ? + __git_complete_index_file "--others --directory" +} + +_git_clone () +{ + case "$cur" in + --*) + __gitcomp_builtin clone + return + ;; + esac +} + +__git_untracked_file_modes="all no normal" + +_git_commit () +{ + case "$prev" in + -c|-C) + __git_complete_refs + return + ;; + esac + + case "$cur" in + --cleanup=*) + __gitcomp "default scissors strip verbatim whitespace + " "" "${cur##--cleanup=}" + return + ;; + --reuse-message=*|--reedit-message=*|\ + --fixup=*|--squash=*) + __git_complete_refs --cur="${cur#*=}" + return + ;; + --untracked-files=*) + __gitcomp "$__git_untracked_file_modes" "" "${cur##--untracked-files=}" + return + ;; + --*) + __gitcomp_builtin commit + return + esac + + if __git rev-parse --verify --quiet HEAD >/dev/null; then + __git_complete_index_file "--committable" + else + # This is the first commit + __git_complete_index_file "--cached" + fi +} + +_git_describe () +{ + case "$cur" in + --*) + __gitcomp_builtin describe + return + esac + __git_complete_refs +} + +__git_diff_algorithms="myers minimal patience histogram" + +__git_diff_submodule_formats="diff log short" + +__git_diff_common_options="--stat --numstat --shortstat --summary + --patch-with-stat --name-only --name-status --color + --no-color --color-words --no-renames --check + --full-index --binary --abbrev --diff-filter= + --find-copies-harder --ignore-cr-at-eol + --text --ignore-space-at-eol --ignore-space-change + --ignore-all-space --ignore-blank-lines --exit-code + --quiet --ext-diff --no-ext-diff + --no-prefix --src-prefix= --dst-prefix= + --inter-hunk-context= + --patience --histogram --minimal + --raw --word-diff --word-diff-regex= + --dirstat --dirstat= --dirstat-by-file + --dirstat-by-file= --cumulative + --diff-algorithm= + --submodule --submodule= --ignore-submodules +" + +_git_diff () +{ + __git_has_doubledash && return + + case "$cur" in + --diff-algorithm=*) + __gitcomp "$__git_diff_algorithms" "" "${cur##--diff-algorithm=}" + return + ;; + --submodule=*) + __gitcomp "$__git_diff_submodule_formats" "" "${cur##--submodule=}" + return + ;; + --*) + __gitcomp "--cached --staged --pickaxe-all --pickaxe-regex + --base --ours --theirs --no-index + $__git_diff_common_options + " + return + ;; + esac + __git_complete_revlist_file +} + +__git_mergetools_common="diffuse diffmerge ecmerge emerge kdiff3 meld opendiff + tkdiff vimdiff gvimdiff xxdiff araxis p4merge bc + codecompare smerge +" + +_git_difftool () +{ + __git_has_doubledash && return + + case "$cur" in + --tool=*) + __gitcomp "$__git_mergetools_common kompare" "" "${cur##--tool=}" + return + ;; + --*) + __gitcomp_builtin difftool "$__git_diff_common_options + --base --cached --ours --theirs + --pickaxe-all --pickaxe-regex + --relative --staged + " + return + ;; + esac + __git_complete_revlist_file +} + +__git_fetch_recurse_submodules="yes on-demand no" + +_git_fetch () +{ + case "$cur" in + --recurse-submodules=*) + __gitcomp "$__git_fetch_recurse_submodules" "" "${cur##--recurse-submodules=}" + return + ;; + --filter=*) + __gitcomp "blob:none blob:limit= sparse:oid=" "" "${cur##--filter=}" + return + ;; + --*) + __gitcomp_builtin fetch + return + ;; + esac + __git_complete_remote_or_refspec +} + +__git_format_patch_extra_options=" + --full-index --not --all --no-prefix --src-prefix= + --dst-prefix= --notes +" + +_git_format_patch () +{ + case "$cur" in + --thread=*) + __gitcomp " + deep shallow + " "" "${cur##--thread=}" + return + ;; + --*) + __gitcomp_builtin format-patch "$__git_format_patch_extra_options" + return + ;; + esac + __git_complete_revlist +} + +_git_fsck () +{ + case "$cur" in + --*) + __gitcomp_builtin fsck + return + ;; + esac +} + +_git_gitk () +{ + _gitk +} + +# Lists matching symbol names from a tag (as in ctags) file. +# 1: List symbol names matching this word. +# 2: The tag file to list symbol names from. +# 3: A prefix to be added to each listed symbol name (optional). +# 4: A suffix to be appended to each listed symbol name (optional). +__git_match_ctag () { + awk -v pfx="${3-}" -v sfx="${4-}" " + /^${1//\//\\/}/ { print pfx \$1 sfx } + " "$2" +} + +# Complete symbol names from a tag file. +# Usage: __git_complete_symbol [<option>]... +# --tags=<file>: The tag file to list symbol names from instead of the +# default "tags". +# --pfx=<prefix>: A prefix to be added to each symbol name. +# --cur=<word>: The current symbol name to be completed. Defaults to +# the current word to be completed. +# --sfx=<suffix>: A suffix to be appended to each symbol name instead +# of the default space. +__git_complete_symbol () { + local tags=tags pfx="" cur_="${cur-}" sfx=" " + + while test $# != 0; do + case "$1" in + --tags=*) tags="${1##--tags=}" ;; + --pfx=*) pfx="${1##--pfx=}" ;; + --cur=*) cur_="${1##--cur=}" ;; + --sfx=*) sfx="${1##--sfx=}" ;; + *) return 1 ;; + esac + shift + done + + if test -r "$tags"; then + __gitcomp_direct "$(__git_match_ctag "$cur_" "$tags" "$pfx" "$sfx")" + fi +} + +_git_grep () +{ + __git_has_doubledash && return + + case "$cur" in + --*) + __gitcomp_builtin grep + return + ;; + esac + + case "$cword,$prev" in + 2,*|*,-*) + __git_complete_symbol && return + ;; + esac + + __git_complete_refs +} + +_git_help () +{ + case "$cur" in + --*) + __gitcomp_builtin help + return + ;; + esac + if test -n "$GIT_TESTING_ALL_COMMAND_LIST" + then + __gitcomp "$GIT_TESTING_ALL_COMMAND_LIST $(__git --list-cmds=alias,list-guide) gitk" + else + __gitcomp "$(__git --list-cmds=main,nohelpers,alias,list-guide) gitk" + fi +} + +_git_init () +{ + case "$cur" in + --shared=*) + __gitcomp " + false true umask group all world everybody + " "" "${cur##--shared=}" + return + ;; + --*) + __gitcomp_builtin init + return + ;; + esac +} + +_git_ls_files () +{ + case "$cur" in + --*) + __gitcomp_builtin ls-files + return + ;; + esac + + # XXX ignore options like --modified and always suggest all cached + # files. + __git_complete_index_file "--cached" +} + +_git_ls_remote () +{ + case "$cur" in + --*) + __gitcomp_builtin ls-remote + return + ;; + esac + __gitcomp_nl "$(__git_remotes)" +} + +_git_ls_tree () +{ + case "$cur" in + --*) + __gitcomp_builtin ls-tree + return + ;; + esac + + __git_complete_file +} + +# Options that go well for log, shortlog and gitk +__git_log_common_options=" + --not --all + --branches --tags --remotes + --first-parent --merges --no-merges + --max-count= + --max-age= --since= --after= + --min-age= --until= --before= + --min-parents= --max-parents= + --no-min-parents --no-max-parents +" +# Options that go well for log and gitk (not shortlog) +__git_log_gitk_options=" + --dense --sparse --full-history + --simplify-merges --simplify-by-decoration + --left-right --notes --no-notes +" +# Options that go well for log and shortlog (not gitk) +__git_log_shortlog_options=" + --author= --committer= --grep= + --all-match --invert-grep +" + +__git_log_pretty_formats="oneline short medium full fuller email raw format: mboxrd" +__git_log_date_formats="relative iso8601 iso8601-strict rfc2822 short local default raw unix format:" + +_git_log () +{ + __git_has_doubledash && return + __git_find_repo_path + + local merge="" + if [ -f "$__git_repo_path/MERGE_HEAD" ]; then + merge="--merge" + fi + case "$prev,$cur" in + -L,:*:*) + return # fall back to Bash filename completion + ;; + -L,:*) + __git_complete_symbol --cur="${cur#:}" --sfx=":" + return + ;; + -G,*|-S,*) + __git_complete_symbol + return + ;; + esac + case "$cur" in + --pretty=*|--format=*) + __gitcomp "$__git_log_pretty_formats $(__git_pretty_aliases) + " "" "${cur#*=}" + return + ;; + --date=*) + __gitcomp "$__git_log_date_formats" "" "${cur##--date=}" + return + ;; + --decorate=*) + __gitcomp "full short no" "" "${cur##--decorate=}" + return + ;; + --diff-algorithm=*) + __gitcomp "$__git_diff_algorithms" "" "${cur##--diff-algorithm=}" + return + ;; + --submodule=*) + __gitcomp "$__git_diff_submodule_formats" "" "${cur##--submodule=}" + return + ;; + --*) + __gitcomp " + $__git_log_common_options + $__git_log_shortlog_options + $__git_log_gitk_options + --root --topo-order --date-order --reverse + --follow --full-diff + --abbrev-commit --abbrev= + --relative-date --date= + --pretty= --format= --oneline + --show-signature + --cherry-mark + --cherry-pick + --graph + --decorate --decorate= + --walk-reflogs + --parents --children + $merge + $__git_diff_common_options + --pickaxe-all --pickaxe-regex + " + return + ;; + -L:*:*) + return # fall back to Bash filename completion + ;; + -L:*) + __git_complete_symbol --cur="${cur#-L:}" --sfx=":" + return + ;; + -G*) + __git_complete_symbol --pfx="-G" --cur="${cur#-G}" + return + ;; + -S*) + __git_complete_symbol --pfx="-S" --cur="${cur#-S}" + return + ;; + esac + __git_complete_revlist +} + +_git_merge () +{ + __git_complete_strategy && return + + case "$cur" in + --*) + __gitcomp_builtin merge + return + esac + __git_complete_refs +} + +_git_mergetool () +{ + case "$cur" in + --tool=*) + __gitcomp "$__git_mergetools_common tortoisemerge" "" "${cur##--tool=}" + return + ;; + --*) + __gitcomp "--tool= --prompt --no-prompt --gui --no-gui" + return + ;; + esac +} + +_git_merge_base () +{ + case "$cur" in + --*) + __gitcomp_builtin merge-base + return + ;; + esac + __git_complete_refs +} + +_git_mv () +{ + case "$cur" in + --*) + __gitcomp_builtin mv + return + ;; + esac + + if [ $(__git_count_arguments "mv") -gt 0 ]; then + # We need to show both cached and untracked files (including + # empty directories) since this may not be the last argument. + __git_complete_index_file "--cached --others --directory" + else + __git_complete_index_file "--cached" + fi +} + +_git_notes () +{ + local subcommands='add append copy edit get-ref list merge prune remove show' + local subcommand="$(__git_find_on_cmdline "$subcommands")" + + case "$subcommand,$cur" in + ,--*) + __gitcomp_builtin notes + ;; + ,*) + case "$prev" in + --ref) + __git_complete_refs + ;; + *) + __gitcomp "$subcommands --ref" + ;; + esac + ;; + *,--reuse-message=*|*,--reedit-message=*) + __git_complete_refs --cur="${cur#*=}" + ;; + *,--*) + __gitcomp_builtin notes_$subcommand + ;; + prune,*|get-ref,*) + # this command does not take a ref, do not complete it + ;; + *) + case "$prev" in + -m|-F) + ;; + *) + __git_complete_refs + ;; + esac + ;; + esac +} + +_git_pull () +{ + __git_complete_strategy && return + + case "$cur" in + --recurse-submodules=*) + __gitcomp "$__git_fetch_recurse_submodules" "" "${cur##--recurse-submodules=}" + return + ;; + --*) + __gitcomp_builtin pull + + return + ;; + esac + __git_complete_remote_or_refspec +} + +__git_push_recurse_submodules="check on-demand only" + +__git_complete_force_with_lease () +{ + local cur_=$1 + + case "$cur_" in + --*=) + ;; + *:*) + __git_complete_refs --cur="${cur_#*:}" + ;; + *) + __git_complete_refs --cur="$cur_" + ;; + esac +} + +_git_push () +{ + case "$prev" in + --repo) + __gitcomp_nl "$(__git_remotes)" + return + ;; + --recurse-submodules) + __gitcomp "$__git_push_recurse_submodules" + return + ;; + esac + case "$cur" in + --repo=*) + __gitcomp_nl "$(__git_remotes)" "" "${cur##--repo=}" + return + ;; + --recurse-submodules=*) + __gitcomp "$__git_push_recurse_submodules" "" "${cur##--recurse-submodules=}" + return + ;; + --force-with-lease=*) + __git_complete_force_with_lease "${cur##--force-with-lease=}" + return + ;; + --*) + __gitcomp_builtin push + return + ;; + esac + __git_complete_remote_or_refspec +} + +_git_range_diff () +{ + case "$cur" in + --*) + __gitcomp " + --creation-factor= --no-dual-color + $__git_diff_common_options + " + return + ;; + esac + __git_complete_revlist +} + +_git_rebase () +{ + __git_find_repo_path + if [ -f "$__git_repo_path"/rebase-merge/interactive ]; then + __gitcomp "--continue --skip --abort --quit --edit-todo --show-current-patch" + return + elif [ -d "$__git_repo_path"/rebase-apply ] || \ + [ -d "$__git_repo_path"/rebase-merge ]; then + __gitcomp "--continue --skip --abort --quit --show-current-patch" + return + fi + __git_complete_strategy && return + case "$cur" in + --whitespace=*) + __gitcomp "$__git_whitespacelist" "" "${cur##--whitespace=}" + return + ;; + --*) + __gitcomp " + --onto --merge --strategy --interactive + --rebase-merges --preserve-merges --stat --no-stat + --committer-date-is-author-date --ignore-date + --ignore-whitespace --whitespace= + --autosquash --no-autosquash + --fork-point --no-fork-point + --autostash --no-autostash + --verify --no-verify + --keep-empty --root --force-rebase --no-ff + --rerere-autoupdate + --exec + " + + return + esac + __git_complete_refs +} + +_git_reflog () +{ + local subcommands="show delete expire" + local subcommand="$(__git_find_on_cmdline "$subcommands")" + + if [ -z "$subcommand" ]; then + __gitcomp "$subcommands" + else + __git_complete_refs + fi +} + +__git_send_email_confirm_options="always never auto cc compose" +__git_send_email_suppresscc_options="author self cc bodycc sob cccmd body all" + +_git_send_email () +{ + case "$prev" in + --to|--cc|--bcc|--from) + __gitcomp "$(__git send-email --dump-aliases)" + return + ;; + esac + + case "$cur" in + --confirm=*) + __gitcomp " + $__git_send_email_confirm_options + " "" "${cur##--confirm=}" + return + ;; + --suppress-cc=*) + __gitcomp " + $__git_send_email_suppresscc_options + " "" "${cur##--suppress-cc=}" + + return + ;; + --smtp-encryption=*) + __gitcomp "ssl tls" "" "${cur##--smtp-encryption=}" + return + ;; + --thread=*) + __gitcomp " + deep shallow + " "" "${cur##--thread=}" + return + ;; + --to=*|--cc=*|--bcc=*|--from=*) + __gitcomp "$(__git send-email --dump-aliases)" "" "${cur#--*=}" + return + ;; + --*) + __gitcomp_builtin send-email "--annotate --bcc --cc --cc-cmd --chain-reply-to + --compose --confirm= --dry-run --envelope-sender + --from --identity + --in-reply-to --no-chain-reply-to --no-signed-off-by-cc + --no-suppress-from --no-thread --quiet --reply-to + --signed-off-by-cc --smtp-pass --smtp-server + --smtp-server-port --smtp-encryption= --smtp-user + --subject --suppress-cc= --suppress-from --thread --to + --validate --no-validate + $__git_format_patch_extra_options" + return + ;; + esac + __git_complete_revlist +} + +_git_stage () +{ + _git_add +} + +_git_status () +{ + local complete_opt + local untracked_state + + case "$cur" in + --ignore-submodules=*) + __gitcomp "none untracked dirty all" "" "${cur##--ignore-submodules=}" + return + ;; + --untracked-files=*) + __gitcomp "$__git_untracked_file_modes" "" "${cur##--untracked-files=}" + return + ;; + --column=*) + __gitcomp " + always never auto column row plain dense nodense + " "" "${cur##--column=}" + return + ;; + --*) + __gitcomp_builtin status + return + ;; + esac + + untracked_state="$(__git_get_option_value "-u" "--untracked-files=" \ + "$__git_untracked_file_modes" "status.showUntrackedFiles")" + + case "$untracked_state" in + no) + # --ignored option does not matter + complete_opt= + ;; + all|normal|*) + complete_opt="--cached --directory --no-empty-directory --others" + + if [ -n "$(__git_find_on_cmdline "--ignored")" ]; then + complete_opt="$complete_opt --ignored --exclude=*" + fi + ;; + esac + + __git_complete_index_file "$complete_opt" +} + +_git_switch () +{ + case "$cur" in + --conflict=*) + __gitcomp "diff3 merge" "" "${cur##--conflict=}" + ;; + --*) + __gitcomp_builtin switch + ;; + *) + # check if --track, --no-track, or --no-guess was specified + # if so, disable DWIM mode + local track_opt="--track" only_local_ref=n + if [ "$GIT_COMPLETION_CHECKOUT_NO_GUESS" = "1" ] || + [ -n "$(__git_find_on_cmdline "--track --no-track --no-guess")" ]; then + track_opt='' + fi + # explicit --guess enables DWIM mode regardless of + # $GIT_COMPLETION_CHECKOUT_NO_GUESS + if [ -n "$(__git_find_on_cmdline "--guess")" ]; then + track_opt='--track' + fi + if [ -z "$(__git_find_on_cmdline "-d --detach")" ]; then + only_local_ref=y + else + # --guess --detach is invalid combination, no + # dwim will be done when --detach is specified + track_opt= + fi + if [ $only_local_ref = y -a -z "$track_opt" ]; then + __gitcomp_direct "$(__git_heads "" "$cur" " ")" + else + __git_complete_refs $track_opt + fi + ;; + esac +} + +__git_config_get_set_variables () +{ + local prevword word config_file= c=$cword + while [ $c -gt 1 ]; do + word="${words[c]}" + case "$word" in + --system|--global|--local|--file=*) + config_file="$word" + break + ;; + -f|--file) + config_file="$word $prevword" + break + ;; + esac + prevword=$word + c=$((--c)) + done + + __git config $config_file --name-only --list +} + +__git_config_vars= +__git_compute_config_vars () +{ + test -n "$__git_config_vars" || + __git_config_vars="$(git help --config-for-completion | sort | uniq)" +} + +_git_config () +{ + local varname + + if [ "${BASH_VERSINFO[0]:-0}" -ge 4 ]; then + varname="${prev,,}" + else + varname="$(echo "$prev" |tr A-Z a-z)" + fi + + case "$varname" in + branch.*.remote|branch.*.pushremote) + __gitcomp_nl "$(__git_remotes)" + return + ;; + branch.*.merge) + __git_complete_refs + return + ;; + branch.*.rebase) + __gitcomp "false true merges preserve interactive" + return + ;; + remote.pushdefault) + __gitcomp_nl "$(__git_remotes)" + return + ;; + remote.*.fetch) + local remote="${prev#remote.}" + remote="${remote%.fetch}" + if [ -z "$cur" ]; then + __gitcomp_nl "refs/heads/" "" "" "" + return + fi + __gitcomp_nl "$(__git_refs_remotes "$remote")" + return + ;; + remote.*.push) + local remote="${prev#remote.}" + remote="${remote%.push}" + __gitcomp_nl "$(__git for-each-ref \ + --format='%(refname):%(refname)' refs/heads)" + return + ;; + pull.twohead|pull.octopus) + __git_compute_merge_strategies + __gitcomp "$__git_merge_strategies" + return + ;; + color.branch|color.diff|color.interactive|\ + color.showbranch|color.status|color.ui) + __gitcomp "always never auto" + return + ;; + color.pager) + __gitcomp "false true" + return + ;; + color.*.*) + __gitcomp " + normal black red green yellow blue magenta cyan white + bold dim ul blink reverse + " + return + ;; + diff.submodule) + __gitcomp "$__git_diff_submodule_formats" + return + ;; + help.format) + __gitcomp "man info web html" + return + ;; + log.date) + __gitcomp "$__git_log_date_formats" + return + ;; + sendemail.aliasfiletype) + __gitcomp "mutt mailrc pine elm gnus" + return + ;; + sendemail.confirm) + __gitcomp "$__git_send_email_confirm_options" + return + ;; + sendemail.suppresscc) + __gitcomp "$__git_send_email_suppresscc_options" + return + ;; + sendemail.transferencoding) + __gitcomp "7bit 8bit quoted-printable base64" + return + ;; + --get|--get-all|--unset|--unset-all) + __gitcomp_nl "$(__git_config_get_set_variables)" + return + ;; + *.*) + return + ;; + esac + case "$cur" in + --*) + __gitcomp_builtin config + return + ;; + branch.*.*) + local pfx="${cur%.*}." cur_="${cur##*.}" + __gitcomp "remote pushRemote merge mergeOptions rebase" "$pfx" "$cur_" + return + ;; + branch.*) + local pfx="${cur%.*}." cur_="${cur#*.}" + __gitcomp_direct "$(__git_heads "$pfx" "$cur_" ".")" + __gitcomp_nl_append $'autoSetupMerge\nautoSetupRebase\n' "$pfx" "$cur_" + return + ;; + guitool.*.*) + local pfx="${cur%.*}." cur_="${cur##*.}" + __gitcomp " + argPrompt cmd confirm needsFile noConsole noRescan + prompt revPrompt revUnmerged title + " "$pfx" "$cur_" + return + ;; + difftool.*.*) + local pfx="${cur%.*}." cur_="${cur##*.}" + __gitcomp "cmd path" "$pfx" "$cur_" + return + ;; + man.*.*) + local pfx="${cur%.*}." cur_="${cur##*.}" + __gitcomp "cmd path" "$pfx" "$cur_" + return + ;; + mergetool.*.*) + local pfx="${cur%.*}." cur_="${cur##*.}" + __gitcomp "cmd path trustExitCode" "$pfx" "$cur_" + return + ;; + pager.*) + local pfx="${cur%.*}." cur_="${cur#*.}" + __git_compute_all_commands + __gitcomp_nl "$__git_all_commands" "$pfx" "$cur_" + return + ;; + remote.*.*) + local pfx="${cur%.*}." cur_="${cur##*.}" + __gitcomp " + url proxy fetch push mirror skipDefaultUpdate + receivepack uploadpack tagOpt pushurl + " "$pfx" "$cur_" + return + ;; + remote.*) + local pfx="${cur%.*}." cur_="${cur#*.}" + __gitcomp_nl "$(__git_remotes)" "$pfx" "$cur_" "." + __gitcomp_nl_append "pushDefault" "$pfx" "$cur_" + return + ;; + url.*.*) + local pfx="${cur%.*}." cur_="${cur##*.}" + __gitcomp "insteadOf pushInsteadOf" "$pfx" "$cur_" + return + ;; + *.*) + __git_compute_config_vars + __gitcomp "$__git_config_vars" + ;; + *) + __git_compute_config_vars + __gitcomp "$(echo "$__git_config_vars" | sed 's/\.[^ ]*/./g')" + esac +} + +_git_remote () +{ + local subcommands=" + add rename remove set-head set-branches + get-url set-url show prune update + " + local subcommand="$(__git_find_on_cmdline "$subcommands")" + if [ -z "$subcommand" ]; then + case "$cur" in + --*) + __gitcomp_builtin remote + ;; + *) + __gitcomp "$subcommands" + ;; + esac + return + fi + + case "$subcommand,$cur" in + add,--*) + __gitcomp_builtin remote_add + ;; + add,*) + ;; + set-head,--*) + __gitcomp_builtin remote_set-head + ;; + set-branches,--*) + __gitcomp_builtin remote_set-branches + ;; + set-head,*|set-branches,*) + __git_complete_remote_or_refspec + ;; + update,--*) + __gitcomp_builtin remote_update + ;; + update,*) + __gitcomp "$(__git_remotes) $(__git_get_config_variables "remotes")" + ;; + set-url,--*) + __gitcomp_builtin remote_set-url + ;; + get-url,--*) + __gitcomp_builtin remote_get-url + ;; + prune,--*) + __gitcomp_builtin remote_prune + ;; + *) + __gitcomp_nl "$(__git_remotes)" + ;; + esac +} + +_git_replace () +{ + case "$cur" in + --format=*) + __gitcomp "short medium long" "" "${cur##--format=}" + return + ;; + --*) + __gitcomp_builtin replace + return + ;; + esac + __git_complete_refs +} + +_git_rerere () +{ + local subcommands="clear forget diff remaining status gc" + local subcommand="$(__git_find_on_cmdline "$subcommands")" + if test -z "$subcommand" + then + __gitcomp "$subcommands" + return + fi +} + +_git_reset () +{ + __git_has_doubledash && return + + case "$cur" in + --*) + __gitcomp_builtin reset + return + ;; + esac + __git_complete_refs +} + +_git_restore () +{ + case "$cur" in + --conflict=*) + __gitcomp "diff3 merge" "" "${cur##--conflict=}" + ;; + --source=*) + __git_complete_refs --cur="${cur##--source=}" + ;; + --*) + __gitcomp_builtin restore + ;; + esac +} + +__git_revert_inprogress_options="--continue --quit --abort" + +_git_revert () +{ + __git_find_repo_path + if [ -f "$__git_repo_path"/REVERT_HEAD ]; then + __gitcomp "$__git_revert_inprogress_options" + return + fi + __git_complete_strategy && return + case "$cur" in + --*) + __gitcomp_builtin revert "" \ + "$__git_revert_inprogress_options" + return + ;; + esac + __git_complete_refs +} + +_git_rm () +{ + case "$cur" in + --*) + __gitcomp_builtin rm + return + ;; + esac + + __git_complete_index_file "--cached" +} + +_git_shortlog () +{ + __git_has_doubledash && return + + case "$cur" in + --*) + __gitcomp " + $__git_log_common_options + $__git_log_shortlog_options + --numbered --summary --email + " + return + ;; + esac + __git_complete_revlist +} + +_git_show () +{ + __git_has_doubledash && return + + case "$cur" in + --pretty=*|--format=*) + __gitcomp "$__git_log_pretty_formats $(__git_pretty_aliases) + " "" "${cur#*=}" + return + ;; + --diff-algorithm=*) + __gitcomp "$__git_diff_algorithms" "" "${cur##--diff-algorithm=}" + return + ;; + --submodule=*) + __gitcomp "$__git_diff_submodule_formats" "" "${cur##--submodule=}" + return + ;; + --*) + __gitcomp "--pretty= --format= --abbrev-commit --oneline + --show-signature + $__git_diff_common_options + " + return + ;; + esac + __git_complete_revlist_file +} + +_git_show_branch () +{ + case "$cur" in + --*) + __gitcomp_builtin show-branch + return + ;; + esac + __git_complete_revlist +} + +_git_stash () +{ + local save_opts='--all --keep-index --no-keep-index --quiet --patch --include-untracked' + local subcommands='push list show apply clear drop pop create branch' + local subcommand="$(__git_find_on_cmdline "$subcommands save")" + if [ -n "$(__git_find_on_cmdline "-p")" ]; then + subcommand="push" + fi + if [ -z "$subcommand" ]; then + case "$cur" in + --*) + __gitcomp "$save_opts" + ;; + sa*) + if [ -z "$(__git_find_on_cmdline "$save_opts")" ]; then + __gitcomp "save" + fi + ;; + *) + if [ -z "$(__git_find_on_cmdline "$save_opts")" ]; then + __gitcomp "$subcommands" + fi + ;; + esac + else + case "$subcommand,$cur" in + push,--*) + __gitcomp "$save_opts --message" + ;; + save,--*) + __gitcomp "$save_opts" + ;; + apply,--*|pop,--*) + __gitcomp "--index --quiet" + ;; + drop,--*) + __gitcomp "--quiet" + ;; + list,--*) + __gitcomp "--name-status --oneline --patch-with-stat" + ;; + show,--*|branch,--*) + ;; + branch,*) + if [ $cword -eq 3 ]; then + __git_complete_refs + else + __gitcomp_nl "$(__git stash list \ + | sed -n -e 's/:.*//p')" + fi + ;; + show,*|apply,*|drop,*|pop,*) + __gitcomp_nl "$(__git stash list \ + | sed -n -e 's/:.*//p')" + ;; + *) + ;; + esac + fi +} + +_git_submodule () +{ + __git_has_doubledash && return + + local subcommands="add status init deinit update set-branch summary foreach sync absorbgitdirs" + local subcommand="$(__git_find_on_cmdline "$subcommands")" + if [ -z "$subcommand" ]; then + case "$cur" in + --*) + __gitcomp "--quiet" + ;; + *) + __gitcomp "$subcommands" + ;; + esac + return + fi + + case "$subcommand,$cur" in + add,--*) + __gitcomp "--branch --force --name --reference --depth" + ;; + status,--*) + __gitcomp "--cached --recursive" + ;; + deinit,--*) + __gitcomp "--force --all" + ;; + update,--*) + __gitcomp " + --init --remote --no-fetch + --recommend-shallow --no-recommend-shallow + --force --rebase --merge --reference --depth --recursive --jobs + " + ;; + set-branch,--*) + __gitcomp "--default --branch" + ;; + summary,--*) + __gitcomp "--cached --files --summary-limit" + ;; + foreach,--*|sync,--*) + __gitcomp "--recursive" + ;; + *) + ;; + esac +} + +_git_svn () +{ + local subcommands=" + init fetch clone rebase dcommit log find-rev + set-tree commit-diff info create-ignore propget + proplist show-ignore show-externals branch tag blame + migrate mkdirs reset gc + " + local subcommand="$(__git_find_on_cmdline "$subcommands")" + if [ -z "$subcommand" ]; then + __gitcomp "$subcommands" + else + local remote_opts="--username= --config-dir= --no-auth-cache" + local fc_opts=" + --follow-parent --authors-file= --repack= + --no-metadata --use-svm-props --use-svnsync-props + --log-window-size= --no-checkout --quiet + --repack-flags --use-log-author --localtime + --add-author-from + --ignore-paths= --include-paths= $remote_opts + " + local init_opts=" + --template= --shared= --trunk= --tags= + --branches= --stdlayout --minimize-url + --no-metadata --use-svm-props --use-svnsync-props + --rewrite-root= --prefix= $remote_opts + " + local cmt_opts=" + --edit --rmdir --find-copies-harder --copy-similarity= + " + + case "$subcommand,$cur" in + fetch,--*) + __gitcomp "--revision= --fetch-all $fc_opts" + ;; + clone,--*) + __gitcomp "--revision= $fc_opts $init_opts" + ;; + init,--*) + __gitcomp "$init_opts" + ;; + dcommit,--*) + __gitcomp " + --merge --strategy= --verbose --dry-run + --fetch-all --no-rebase --commit-url + --revision --interactive $cmt_opts $fc_opts + " + ;; + set-tree,--*) + __gitcomp "--stdin $cmt_opts $fc_opts" + ;; + create-ignore,--*|propget,--*|proplist,--*|show-ignore,--*|\ + show-externals,--*|mkdirs,--*) + __gitcomp "--revision=" + ;; + log,--*) + __gitcomp " + --limit= --revision= --verbose --incremental + --oneline --show-commit --non-recursive + --authors-file= --color + " + ;; + rebase,--*) + __gitcomp " + --merge --verbose --strategy= --local + --fetch-all --dry-run $fc_opts + " + ;; + commit-diff,--*) + __gitcomp "--message= --file= --revision= $cmt_opts" + ;; + info,--*) + __gitcomp "--url" + ;; + branch,--*) + __gitcomp "--dry-run --message --tag" + ;; + tag,--*) + __gitcomp "--dry-run --message" + ;; + blame,--*) + __gitcomp "--git-format" + ;; + migrate,--*) + __gitcomp " + --config-dir= --ignore-paths= --minimize + --no-auth-cache --username= + " + ;; + reset,--*) + __gitcomp "--revision= --parent" + ;; + *) + ;; + esac + fi +} + +_git_tag () +{ + local i c=1 f=0 + while [ $c -lt $cword ]; do + i="${words[c]}" + case "$i" in + -d|--delete|-v|--verify) + __gitcomp_direct "$(__git_tags "" "$cur" " ")" + return + ;; + -f) + f=1 + ;; + esac + ((c++)) + done + + case "$prev" in + -m|-F) + ;; + -*|tag) + if [ $f = 1 ]; then + __gitcomp_direct "$(__git_tags "" "$cur" " ")" + fi + ;; + *) + __git_complete_refs + ;; + esac + + case "$cur" in + --*) + __gitcomp_builtin tag + ;; + esac +} + +_git_whatchanged () +{ + _git_log +} + +_git_worktree () +{ + local subcommands="add list lock move prune remove unlock" + local subcommand="$(__git_find_on_cmdline "$subcommands")" + if [ -z "$subcommand" ]; then + __gitcomp "$subcommands" + else + case "$subcommand,$cur" in + add,--*) + __gitcomp_builtin worktree_add + ;; + list,--*) + __gitcomp_builtin worktree_list + ;; + lock,--*) + __gitcomp_builtin worktree_lock + ;; + prune,--*) + __gitcomp_builtin worktree_prune + ;; + remove,--*) + __gitcomp "--force" + ;; + *) + ;; + esac + fi +} + +__git_complete_common () { + local command="$1" + + case "$cur" in + --*) + __gitcomp_builtin "$command" + ;; + esac +} + +__git_cmds_with_parseopt_helper= +__git_support_parseopt_helper () { + test -n "$__git_cmds_with_parseopt_helper" || + __git_cmds_with_parseopt_helper="$(__git --list-cmds=parseopt)" + + case " $__git_cmds_with_parseopt_helper " in + *" $1 "*) + return 0 + ;; + *) + return 1 + ;; + esac +} + +__git_complete_command () { + local command="$1" + local completion_func="_git_${command//-/_}" + if ! declare -f $completion_func >/dev/null 2>/dev/null && + declare -f _completion_loader >/dev/null 2>/dev/null + then + _completion_loader "git-$command" + fi + if declare -f $completion_func >/dev/null 2>/dev/null + then + $completion_func + return 0 + elif __git_support_parseopt_helper "$command" + then + __git_complete_common "$command" + return 0 + else + return 1 + fi +} + +__git_main () +{ + local i c=1 command __git_dir __git_repo_path + local __git_C_args C_args_count=0 + + while [ $c -lt $cword ]; do + i="${words[c]}" + case "$i" in + --git-dir=*) __git_dir="${i#--git-dir=}" ;; + --git-dir) ((c++)) ; __git_dir="${words[c]}" ;; + --bare) __git_dir="." ;; + --help) command="help"; break ;; + -c|--work-tree|--namespace) ((c++)) ;; + -C) __git_C_args[C_args_count++]=-C + ((c++)) + __git_C_args[C_args_count++]="${words[c]}" + ;; + -*) ;; + *) command="$i"; break ;; + esac + ((c++)) + done + + if [ -z "$command" ]; then + case "$prev" in + --git-dir|-C|--work-tree) + # these need a path argument, let's fall back to + # Bash filename completion + return + ;; + -c|--namespace) + # we don't support completing these options' arguments + return + ;; + esac + case "$cur" in + --*) __gitcomp " + --paginate + --no-pager + --git-dir= + --bare + --version + --exec-path + --exec-path= + --html-path + --man-path + --info-path + --work-tree= + --namespace= + --no-replace-objects + --help + " + ;; + *) + if test -n "$GIT_TESTING_PORCELAIN_COMMAND_LIST" + then + __gitcomp "$GIT_TESTING_PORCELAIN_COMMAND_LIST" + else + __gitcomp "$(__git --list-cmds=list-mainporcelain,others,nohelpers,alias,list-complete,config)" + fi + ;; + esac + return + fi + + __git_complete_command "$command" && return + + local expansion=$(__git_aliased_command "$command") + if [ -n "$expansion" ]; then + words[1]=$expansion + __git_complete_command "$expansion" + fi +} + +__gitk_main () +{ + __git_has_doubledash && return + + local __git_repo_path + __git_find_repo_path + + local merge="" + if [ -f "$__git_repo_path/MERGE_HEAD" ]; then + merge="--merge" + fi + case "$cur" in + --*) + __gitcomp " + $__git_log_common_options + $__git_log_gitk_options + $merge + " + return + ;; + esac + __git_complete_revlist +} + +if [[ -n ${ZSH_VERSION-} ]] && + # Don't define these functions when sourced from 'git-completion.zsh', + # it has its own implementations. + [[ -z ${GIT_SOURCING_ZSH_COMPLETION-} ]]; then + echo "WARNING: this script is deprecated, please see git-completion.zsh" 1>&2 + + autoload -U +X compinit && compinit + + __gitcomp () + { + emulate -L zsh + + local cur_="${3-$cur}" + + case "$cur_" in + --*=) + ;; + *) + local c IFS=$' \t\n' + local -a array + for c in ${=1}; do + c="$c${4-}" + case $c in + --*=*|*.) ;; + *) c="$c " ;; + esac + array[${#array[@]}+1]="$c" + done + compset -P '*[=:]' + compadd -Q -S '' -p "${2-}" -a -- array && _ret=0 + ;; + esac + } + + __gitcomp_direct () + { + emulate -L zsh + + local IFS=$'\n' + compset -P '*[=:]' + compadd -Q -- ${=1} && _ret=0 + } + + __gitcomp_nl () + { + emulate -L zsh + + local IFS=$'\n' + compset -P '*[=:]' + compadd -Q -S "${4- }" -p "${2-}" -- ${=1} && _ret=0 + } + + __gitcomp_file_direct () + { + emulate -L zsh + + local IFS=$'\n' + compset -P '*[=:]' + compadd -f -- ${=1} && _ret=0 + } + + __gitcomp_file () + { + emulate -L zsh + + local IFS=$'\n' + compset -P '*[=:]' + compadd -p "${2-}" -f -- ${=1} && _ret=0 + } + + _git () + { + local _ret=1 cur cword prev + cur=${words[CURRENT]} + prev=${words[CURRENT-1]} + let cword=CURRENT-1 + emulate ksh -c __${service}_main + let _ret && _default && _ret=0 + return _ret + } + + compdef _git git gitk + return +fi + +__git_func_wrap () +{ + local cur words cword prev + _get_comp_words_by_ref -n =: cur words cword prev + $1 +} + +# Setup completion for certain functions defined above by setting common +# variables and workarounds. +# This is NOT a public function; use at your own risk. +__git_complete () +{ + local wrapper="__git_wrap${2}" + eval "$wrapper () { __git_func_wrap $2 ; }" + complete -o bashdefault -o default -o nospace -F $wrapper $1 2>/dev/null \ + || complete -o default -o nospace -F $wrapper $1 +} + +# wrapper for backwards compatibility +_git () +{ + __git_wrap__git_main +} + +# wrapper for backwards compatibility +_gitk () +{ + __git_wrap__gitk_main +} + +__git_complete git __git_main +__git_complete gitk __gitk_main + +# The following are necessary only for Cygwin, and only are needed +# when the user has tab-completed the executable name and consequently +# included the '.exe' suffix. +# +if [ Cygwin = "$(uname -o 2>/dev/null)" ]; then +__git_complete git.exe __git_main +fi diff --git a/contrib/completion/git-completion.tcsh b/contrib/completion/git-completion.tcsh new file mode 100644 index 000000000000..4a790d8f4ec1 --- /dev/null +++ b/contrib/completion/git-completion.tcsh @@ -0,0 +1,126 @@ +# tcsh completion support for core Git. +# +# Copyright (C) 2012 Marc Khouzam <marc.khouzam@gmail.com> +# Distributed under the GNU General Public License, version 2.0. +# +# When sourced, this script will generate a new script that uses +# the git-completion.bash script provided by core Git. This new +# script can be used by tcsh to perform git completion. +# The current script also issues the necessary tcsh 'complete' +# commands. +# +# To use this completion script: +# +# 0) You need tcsh 6.16.00 or newer. +# 1) Copy both this file and the bash completion script to ${HOME}. +# You _must_ use the name ${HOME}/.git-completion.bash for the +# bash script. +# (e.g. ~/.git-completion.tcsh and ~/.git-completion.bash). +# 2) Add the following line to your .tcshrc/.cshrc: +# source ~/.git-completion.tcsh +# 3) For completion similar to bash, it is recommended to also +# add the following line to your .tcshrc/.cshrc: +# set autolist=ambiguous +# It will tell tcsh to list the possible completion choices. + +set __git_tcsh_completion_version = `\echo ${tcsh} | \sed 's/\./ /g'` +if ( ${__git_tcsh_completion_version[1]} < 6 || \ + ( ${__git_tcsh_completion_version[1]} == 6 && \ + ${__git_tcsh_completion_version[2]} < 16 ) ) then + echo "git-completion.tcsh: Your version of tcsh is too old, you need version 6.16.00 or newer. Git completion will not work." + exit +endif +unset __git_tcsh_completion_version + +set __git_tcsh_completion_original_script = ${HOME}/.git-completion.bash +set __git_tcsh_completion_script = ${HOME}/.git-completion.tcsh.bash + +# Check that the user put the script in the right place +if ( ! -e ${__git_tcsh_completion_original_script} ) then + echo "git-completion.tcsh: Cannot find: ${__git_tcsh_completion_original_script}. Git completion will not work." + exit +endif + +cat << EOF >! ${__git_tcsh_completion_script} +#!bash +# +# This script is GENERATED and will be overwritten automatically. +# Do not modify it directly. Instead, modify git-completion.tcsh +# and source it again. + +source ${__git_tcsh_completion_original_script} + +# Remove the colon as a completion separator because tcsh cannot handle it +COMP_WORDBREAKS=\${COMP_WORDBREAKS//:} + +# For file completion, tcsh needs the '/' to be appended to directories. +# By default, the bash script does not do that. +# We can achieve this by using the below compatibility +# method of the git-completion.bash script. +__git_index_file_list_filter () +{ + __git_index_file_list_filter_compat +} + +# Set COMP_WORDS in a way that can be handled by the bash script. +COMP_WORDS=(\$2) + +# The cursor is at the end of parameter #1. +# We must check for a space as the last character which will +# tell us that the previous word is complete and the cursor +# is on the next word. +if [ "\${2: -1}" == " " ]; then + # The last character is a space, so our location is at the end + # of the command-line array + COMP_CWORD=\${#COMP_WORDS[@]} +else + # The last character is not a space, so our location is on the + # last word of the command-line array, so we must decrement the + # count by 1 + COMP_CWORD=\$((\${#COMP_WORDS[@]}-1)) +fi + +# Call _git() or _gitk() of the bash script, based on the first argument +_\${1} + +IFS=\$'\n' +if [ \${#COMPREPLY[*]} -eq 0 ]; then + # No completions suggested. In this case, we want tcsh to perform + # standard file completion. However, there does not seem to be way + # to tell tcsh to do that. To help the user, we try to simulate + # file completion directly in this script. + # + # Known issues: + # - Possible completions are shown with their directory prefix. + # - Completions containing shell variables are not handled. + # - Completions with ~ as the first character are not handled. + + # No file completion should be done unless we are completing beyond + # the git sub-command. An improvement on the bash completion :) + if [ \${COMP_CWORD} -gt 1 ]; then + TO_COMPLETE="\${COMP_WORDS[\${COMP_CWORD}]}" + + # We don't support ~ expansion: too tricky. + if [ "\${TO_COMPLETE:0:1}" != "~" ]; then + # Use ls so as to add the '/' at the end of directories. + COMPREPLY=(\`ls -dp \${TO_COMPLETE}* 2> /dev/null\`) + fi + fi +fi + +# tcsh does not automatically remove duplicates, so we do it ourselves +echo "\${COMPREPLY[*]}" | sort | uniq + +# If there is a single completion and it is a directory, we output it +# a second time to trick tcsh into not adding a space after it. +if [ \${#COMPREPLY[*]} -eq 1 ] && [ "\${COMPREPLY[0]: -1}" == "/" ]; then + echo "\${COMPREPLY[*]}" +fi + +EOF + +# Don't need this variable anymore, so don't pollute the users environment +unset __git_tcsh_completion_original_script + +complete git 'p,*,`bash ${__git_tcsh_completion_script} git "${COMMAND_LINE}"`,' +complete gitk 'p,*,`bash ${__git_tcsh_completion_script} gitk "${COMMAND_LINE}"`,' diff --git a/contrib/completion/git-completion.zsh b/contrib/completion/git-completion.zsh new file mode 100644 index 000000000000..886bf95d1f59 --- /dev/null +++ b/contrib/completion/git-completion.zsh @@ -0,0 +1,243 @@ +#compdef git gitk + +# zsh completion wrapper for git +# +# Copyright (c) 2012-2013 Felipe Contreras <felipe.contreras@gmail.com> +# +# You need git's bash completion script installed somewhere, by default it +# would be the location bash-completion uses. +# +# If your script is somewhere else, you can configure it on your ~/.zshrc: +# +# zstyle ':completion:*:*:git:*' script ~/.git-completion.zsh +# +# The recommended way to install this script is to copy to '~/.zsh/_git', and +# then add the following to your ~/.zshrc file: +# +# fpath=(~/.zsh $fpath) + +complete () +{ + # do nothing + return 0 +} + +zstyle -T ':completion:*:*:git:*' tag-order && \ + zstyle ':completion:*:*:git:*' tag-order 'common-commands' + +zstyle -s ":completion:*:*:git:*" script script +if [ -z "$script" ]; then + local -a locations + local e + locations=( + $(dirname ${funcsourcetrace[1]%:*})/git-completion.bash + '/etc/bash_completion.d/git' # fedora, old debian + '/usr/share/bash-completion/completions/git' # arch, ubuntu, new debian + '/usr/share/bash-completion/git' # gentoo + ) + for e in $locations; do + test -f $e && script="$e" && break + done +fi +GIT_SOURCING_ZSH_COMPLETION=y . "$script" + +__gitcomp () +{ + emulate -L zsh + + local cur_="${3-$cur}" + + case "$cur_" in + --*=) + ;; + *) + local c IFS=$' \t\n' + local -a array + for c in ${=1}; do + c="$c${4-}" + case $c in + --*=*|*.) ;; + *) c="$c " ;; + esac + array+=("$c") + done + compset -P '*[=:]' + compadd -Q -S '' -p "${2-}" -a -- array && _ret=0 + ;; + esac +} + +__gitcomp_direct () +{ + emulate -L zsh + + local IFS=$'\n' + compset -P '*[=:]' + compadd -Q -- ${=1} && _ret=0 +} + +__gitcomp_nl () +{ + emulate -L zsh + + local IFS=$'\n' + compset -P '*[=:]' + compadd -Q -S "${4- }" -p "${2-}" -- ${=1} && _ret=0 +} + +__gitcomp_nl_append () +{ + emulate -L zsh + + local IFS=$'\n' + compadd -Q -S "${4- }" -p "${2-}" -- ${=1} && _ret=0 +} + +__gitcomp_file_direct () +{ + emulate -L zsh + + local IFS=$'\n' + compset -P '*[=:]' + compadd -f -- ${=1} && _ret=0 +} + +__gitcomp_file () +{ + emulate -L zsh + + local IFS=$'\n' + compset -P '*[=:]' + compadd -p "${2-}" -f -- ${=1} && _ret=0 +} + +__git_zsh_bash_func () +{ + emulate -L ksh + + local command=$1 + + local completion_func="_git_${command//-/_}" + declare -f $completion_func >/dev/null && $completion_func && return + + local expansion=$(__git_aliased_command "$command") + if [ -n "$expansion" ]; then + words[1]=$expansion + completion_func="_git_${expansion//-/_}" + declare -f $completion_func >/dev/null && $completion_func + fi +} + +__git_zsh_cmd_common () +{ + local -a list + list=( + add:'add file contents to the index' + bisect:'find by binary search the change that introduced a bug' + branch:'list, create, or delete branches' + checkout:'checkout a branch or paths to the working tree' + clone:'clone a repository into a new directory' + commit:'record changes to the repository' + diff:'show changes between commits, commit and working tree, etc' + fetch:'download objects and refs from another repository' + grep:'print lines matching a pattern' + init:'create an empty Git repository or reinitialize an existing one' + log:'show commit logs' + merge:'join two or more development histories together' + mv:'move or rename a file, a directory, or a symlink' + pull:'fetch from and merge with another repository or a local branch' + push:'update remote refs along with associated objects' + rebase:'forward-port local commits to the updated upstream head' + reset:'reset current HEAD to the specified state' + rm:'remove files from the working tree and from the index' + show:'show various types of objects' + status:'show the working tree status' + tag:'create, list, delete or verify a tag object signed with GPG') + _describe -t common-commands 'common commands' list && _ret=0 +} + +__git_zsh_cmd_alias () +{ + local -a list + list=(${${${(0)"$(git config -z --get-regexp '^alias\.')"}#alias.}%$'\n'*}) + _describe -t alias-commands 'aliases' list $* && _ret=0 +} + +__git_zsh_cmd_all () +{ + local -a list + emulate ksh -c __git_compute_all_commands + list=( ${=__git_all_commands} ) + _describe -t all-commands 'all commands' list && _ret=0 +} + +__git_zsh_main () +{ + local curcontext="$curcontext" state state_descr line + typeset -A opt_args + local -a orig_words + + orig_words=( ${words[@]} ) + + _arguments -C \ + '(-p --paginate --no-pager)'{-p,--paginate}'[pipe all output into ''less'']' \ + '(-p --paginate)--no-pager[do not pipe git output into a pager]' \ + '--git-dir=-[set the path to the repository]: :_directories' \ + '--bare[treat the repository as a bare repository]' \ + '(- :)--version[prints the git suite version]' \ + '--exec-path=-[path to where your core git programs are installed]:: :_directories' \ + '--html-path[print the path where git''s HTML documentation is installed]' \ + '--info-path[print the path where the Info files are installed]' \ + '--man-path[print the manpath (see `man(1)`) for the man pages]' \ + '--work-tree=-[set the path to the working tree]: :_directories' \ + '--namespace=-[set the git namespace]' \ + '--no-replace-objects[do not use replacement refs to replace git objects]' \ + '(- :)--help[prints the synopsis and a list of the most commonly used commands]: :->arg' \ + '(-): :->command' \ + '(-)*:: :->arg' && return + + case $state in + (command) + _alternative \ + 'alias-commands:alias:__git_zsh_cmd_alias' \ + 'common-commands:common:__git_zsh_cmd_common' \ + 'all-commands:all:__git_zsh_cmd_all' && _ret=0 + ;; + (arg) + local command="${words[1]}" __git_dir + + if (( $+opt_args[--bare] )); then + __git_dir='.' + else + __git_dir=${opt_args[--git-dir]} + fi + + (( $+opt_args[--help] )) && command='help' + + words=( ${orig_words[@]} ) + + __git_zsh_bash_func $command + ;; + esac +} + +_git () +{ + local _ret=1 + local cur cword prev + + cur=${words[CURRENT]} + prev=${words[CURRENT-1]} + let cword=CURRENT-1 + + if (( $+functions[__${service}_zsh_main] )); then + __${service}_zsh_main + else + emulate ksh -c __${service}_main + fi + + let _ret && _default && _ret=0 + return _ret +} + +_git diff --git a/contrib/completion/git-prompt.sh b/contrib/completion/git-prompt.sh new file mode 100644 index 000000000000..1d510cd47bef --- /dev/null +++ b/contrib/completion/git-prompt.sh @@ -0,0 +1,564 @@ +# bash/zsh git prompt support +# +# Copyright (C) 2006,2007 Shawn O. Pearce <spearce@spearce.org> +# Distributed under the GNU General Public License, version 2.0. +# +# This script allows you to see repository status in your prompt. +# +# To enable: +# +# 1) Copy this file to somewhere (e.g. ~/.git-prompt.sh). +# 2) Add the following line to your .bashrc/.zshrc: +# source ~/.git-prompt.sh +# 3a) Change your PS1 to call __git_ps1 as +# command-substitution: +# Bash: PS1='[\u@\h \W$(__git_ps1 " (%s)")]\$ ' +# ZSH: setopt PROMPT_SUBST ; PS1='[%n@%m %c$(__git_ps1 " (%s)")]\$ ' +# the optional argument will be used as format string. +# 3b) Alternatively, for a slightly faster prompt, __git_ps1 can +# be used for PROMPT_COMMAND in Bash or for precmd() in Zsh +# with two parameters, <pre> and <post>, which are strings +# you would put in $PS1 before and after the status string +# generated by the git-prompt machinery. e.g. +# Bash: PROMPT_COMMAND='__git_ps1 "\u@\h:\w" "\\\$ "' +# will show username, at-sign, host, colon, cwd, then +# various status string, followed by dollar and SP, as +# your prompt. +# ZSH: precmd () { __git_ps1 "%n" ":%~$ " "|%s" } +# will show username, pipe, then various status string, +# followed by colon, cwd, dollar and SP, as your prompt. +# Optionally, you can supply a third argument with a printf +# format string to finetune the output of the branch status +# +# The repository status will be displayed only if you are currently in a +# git repository. The %s token is the placeholder for the shown status. +# +# The prompt status always includes the current branch name. +# +# In addition, if you set GIT_PS1_SHOWDIRTYSTATE to a nonempty value, +# unstaged (*) and staged (+) changes will be shown next to the branch +# name. You can configure this per-repository with the +# bash.showDirtyState variable, which defaults to true once +# GIT_PS1_SHOWDIRTYSTATE is enabled. +# +# You can also see if currently something is stashed, by setting +# GIT_PS1_SHOWSTASHSTATE to a nonempty value. If something is stashed, +# then a '$' will be shown next to the branch name. +# +# If you would like to see if there're untracked files, then you can set +# GIT_PS1_SHOWUNTRACKEDFILES to a nonempty value. If there're untracked +# files, then a '%' will be shown next to the branch name. You can +# configure this per-repository with the bash.showUntrackedFiles +# variable, which defaults to true once GIT_PS1_SHOWUNTRACKEDFILES is +# enabled. +# +# If you would like to see the difference between HEAD and its upstream, +# set GIT_PS1_SHOWUPSTREAM="auto". A "<" indicates you are behind, ">" +# indicates you are ahead, "<>" indicates you have diverged and "=" +# indicates that there is no difference. You can further control +# behaviour by setting GIT_PS1_SHOWUPSTREAM to a space-separated list +# of values: +# +# verbose show number of commits ahead/behind (+/-) upstream +# name if verbose, then also show the upstream abbrev name +# legacy don't use the '--count' option available in recent +# versions of git-rev-list +# git always compare HEAD to @{upstream} +# svn always compare HEAD to your SVN upstream +# +# You can change the separator between the branch name and the above +# state symbols by setting GIT_PS1_STATESEPARATOR. The default separator +# is SP. +# +# By default, __git_ps1 will compare HEAD to your SVN upstream if it can +# find one, or @{upstream} otherwise. Once you have set +# GIT_PS1_SHOWUPSTREAM, you can override it on a per-repository basis by +# setting the bash.showUpstream config variable. +# +# If you would like to see more information about the identity of +# commits checked out as a detached HEAD, set GIT_PS1_DESCRIBE_STYLE +# to one of these values: +# +# contains relative to newer annotated tag (v1.6.3.2~35) +# branch relative to newer tag or branch (master~4) +# describe relative to older annotated tag (v1.6.3.1-13-gdd42c2f) +# tag relative to any older tag (v1.6.3.1-13-gdd42c2f) +# default exactly matching tag +# +# If you would like a colored hint about the current dirty state, set +# GIT_PS1_SHOWCOLORHINTS to a nonempty value. The colors are based on +# the colored output of "git status -sb" and are available only when +# using __git_ps1 for PROMPT_COMMAND or precmd. +# +# If you would like __git_ps1 to do nothing in the case when the current +# directory is set up to be ignored by git, then set +# GIT_PS1_HIDE_IF_PWD_IGNORED to a nonempty value. Override this on the +# repository level by setting bash.hideIfPwdIgnored to "false". + +# check whether printf supports -v +__git_printf_supports_v= +printf -v __git_printf_supports_v -- '%s' yes >/dev/null 2>&1 + +# stores the divergence from upstream in $p +# used by GIT_PS1_SHOWUPSTREAM +__git_ps1_show_upstream () +{ + local key value + local svn_remote svn_url_pattern count n + local upstream=git legacy="" verbose="" name="" + + svn_remote=() + # get some config options from git-config + local output="$(git config -z --get-regexp '^(svn-remote\..*\.url|bash\.showupstream)$' 2>/dev/null | tr '\0\n' '\n ')" + while read -r key value; do + case "$key" in + bash.showupstream) + GIT_PS1_SHOWUPSTREAM="$value" + if [[ -z "${GIT_PS1_SHOWUPSTREAM}" ]]; then + p="" + return + fi + ;; + svn-remote.*.url) + svn_remote[$((${#svn_remote[@]} + 1))]="$value" + svn_url_pattern="$svn_url_pattern\\|$value" + upstream=svn+git # default upstream is SVN if available, else git + ;; + esac + done <<< "$output" + + # parse configuration values + for option in ${GIT_PS1_SHOWUPSTREAM}; do + case "$option" in + git|svn) upstream="$option" ;; + verbose) verbose=1 ;; + legacy) legacy=1 ;; + name) name=1 ;; + esac + done + + # Find our upstream + case "$upstream" in + git) upstream="@{upstream}" ;; + svn*) + # get the upstream from the "git-svn-id: ..." in a commit message + # (git-svn uses essentially the same procedure internally) + local -a svn_upstream + svn_upstream=($(git log --first-parent -1 \ + --grep="^git-svn-id: \(${svn_url_pattern#??}\)" 2>/dev/null)) + if [[ 0 -ne ${#svn_upstream[@]} ]]; then + svn_upstream=${svn_upstream[${#svn_upstream[@]} - 2]} + svn_upstream=${svn_upstream%@*} + local n_stop="${#svn_remote[@]}" + for ((n=1; n <= n_stop; n++)); do + svn_upstream=${svn_upstream#${svn_remote[$n]}} + done + + if [[ -z "$svn_upstream" ]]; then + # default branch name for checkouts with no layout: + upstream=${GIT_SVN_ID:-git-svn} + else + upstream=${svn_upstream#/} + fi + elif [[ "svn+git" = "$upstream" ]]; then + upstream="@{upstream}" + fi + ;; + esac + + # Find how many commits we are ahead/behind our upstream + if [[ -z "$legacy" ]]; then + count="$(git rev-list --count --left-right \ + "$upstream"...HEAD 2>/dev/null)" + else + # produce equivalent output to --count for older versions of git + local commits + if commits="$(git rev-list --left-right "$upstream"...HEAD 2>/dev/null)" + then + local commit behind=0 ahead=0 + for commit in $commits + do + case "$commit" in + "<"*) ((behind++)) ;; + *) ((ahead++)) ;; + esac + done + count="$behind $ahead" + else + count="" + fi + fi + + # calculate the result + if [[ -z "$verbose" ]]; then + case "$count" in + "") # no upstream + p="" ;; + "0 0") # equal to upstream + p="=" ;; + "0 "*) # ahead of upstream + p=">" ;; + *" 0") # behind upstream + p="<" ;; + *) # diverged from upstream + p="<>" ;; + esac + else + case "$count" in + "") # no upstream + p="" ;; + "0 0") # equal to upstream + p=" u=" ;; + "0 "*) # ahead of upstream + p=" u+${count#0 }" ;; + *" 0") # behind upstream + p=" u-${count% 0}" ;; + *) # diverged from upstream + p=" u+${count#* }-${count% *}" ;; + esac + if [[ -n "$count" && -n "$name" ]]; then + __git_ps1_upstream_name=$(git rev-parse \ + --abbrev-ref "$upstream" 2>/dev/null) + if [ $pcmode = yes ] && [ $ps1_expanded = yes ]; then + p="$p \${__git_ps1_upstream_name}" + else + p="$p ${__git_ps1_upstream_name}" + # not needed anymore; keep user's + # environment clean + unset __git_ps1_upstream_name + fi + fi + fi + +} + +# Helper function that is meant to be called from __git_ps1. It +# injects color codes into the appropriate gitstring variables used +# to build a gitstring. +__git_ps1_colorize_gitstring () +{ + if [[ -n ${ZSH_VERSION-} ]]; then + local c_red='%F{red}' + local c_green='%F{green}' + local c_lblue='%F{blue}' + local c_clear='%f' + else + # Using \[ and \] around colors is necessary to prevent + # issues with command line editing/browsing/completion! + local c_red='\[\e[31m\]' + local c_green='\[\e[32m\]' + local c_lblue='\[\e[1;34m\]' + local c_clear='\[\e[0m\]' + fi + local bad_color=$c_red + local ok_color=$c_green + local flags_color="$c_lblue" + + local branch_color="" + if [ $detached = no ]; then + branch_color="$ok_color" + else + branch_color="$bad_color" + fi + c="$branch_color$c" + + z="$c_clear$z" + if [ "$w" = "*" ]; then + w="$bad_color$w" + fi + if [ -n "$i" ]; then + i="$ok_color$i" + fi + if [ -n "$s" ]; then + s="$flags_color$s" + fi + if [ -n "$u" ]; then + u="$bad_color$u" + fi + r="$c_clear$r" +} + +# Helper function to read the first line of a file into a variable. +# __git_eread requires 2 arguments, the file path and the name of the +# variable, in that order. +__git_eread () +{ + test -r "$1" && IFS=$'\r\n' read "$2" <"$1" +} + +# see if a cherry-pick or revert is in progress, if the user has committed a +# conflict resolution with 'git commit' in the middle of a sequence of picks or +# reverts then CHERRY_PICK_HEAD/REVERT_HEAD will not exist so we have to read +# the todo file. +__git_sequencer_status () +{ + local todo + if test -f "$g/CHERRY_PICK_HEAD" + then + r="|CHERRY-PICKING" + return 0; + elif test -f "$g/REVERT_HEAD" + then + r="|REVERTING" + return 0; + elif __git_eread "$g/sequencer/todo" todo + then + case "$todo" in + p[\ \ ]|pick[\ \ ]*) + r="|CHERRY-PICKING" + return 0 + ;; + revert[\ \ ]*) + r="|REVERTING" + return 0 + ;; + esac + fi + return 1 +} + +# __git_ps1 accepts 0 or 1 arguments (i.e., format string) +# when called from PS1 using command substitution +# in this mode it prints text to add to bash PS1 prompt (includes branch name) +# +# __git_ps1 requires 2 or 3 arguments when called from PROMPT_COMMAND (pc) +# in that case it _sets_ PS1. The arguments are parts of a PS1 string. +# when two arguments are given, the first is prepended and the second appended +# to the state string when assigned to PS1. +# The optional third parameter will be used as printf format string to further +# customize the output of the git-status string. +# In this mode you can request colored hints using GIT_PS1_SHOWCOLORHINTS=true +__git_ps1 () +{ + # preserve exit status + local exit=$? + local pcmode=no + local detached=no + local ps1pc_start='\u@\h:\w ' + local ps1pc_end='\$ ' + local printf_format=' (%s)' + + case "$#" in + 2|3) pcmode=yes + ps1pc_start="$1" + ps1pc_end="$2" + printf_format="${3:-$printf_format}" + # set PS1 to a plain prompt so that we can + # simply return early if the prompt should not + # be decorated + PS1="$ps1pc_start$ps1pc_end" + ;; + 0|1) printf_format="${1:-$printf_format}" + ;; + *) return $exit + ;; + esac + + # ps1_expanded: This variable is set to 'yes' if the shell + # subjects the value of PS1 to parameter expansion: + # + # * bash does unless the promptvars option is disabled + # * zsh does not unless the PROMPT_SUBST option is set + # * POSIX shells always do + # + # If the shell would expand the contents of PS1 when drawing + # the prompt, a raw ref name must not be included in PS1. + # This protects the user from arbitrary code execution via + # specially crafted ref names. For example, a ref named + # 'refs/heads/$(IFS=_;cmd=sudo_rm_-rf_/;$cmd)' might cause the + # shell to execute 'sudo rm -rf /' when the prompt is drawn. + # + # Instead, the ref name should be placed in a separate global + # variable (in the __git_ps1_* namespace to avoid colliding + # with the user's environment) and that variable should be + # referenced from PS1. For example: + # + # __git_ps1_foo=$(do_something_to_get_ref_name) + # PS1="...stuff...\${__git_ps1_foo}...stuff..." + # + # If the shell does not expand the contents of PS1, the raw + # ref name must be included in PS1. + # + # The value of this variable is only relevant when in pcmode. + # + # Assume that the shell follows the POSIX specification and + # expands PS1 unless determined otherwise. (This is more + # likely to be correct if the user has a non-bash, non-zsh + # shell and safer than the alternative if the assumption is + # incorrect.) + # + local ps1_expanded=yes + [ -z "${ZSH_VERSION-}" ] || [[ -o PROMPT_SUBST ]] || ps1_expanded=no + [ -z "${BASH_VERSION-}" ] || shopt -q promptvars || ps1_expanded=no + + local repo_info rev_parse_exit_code + repo_info="$(git rev-parse --git-dir --is-inside-git-dir \ + --is-bare-repository --is-inside-work-tree \ + --short HEAD 2>/dev/null)" + rev_parse_exit_code="$?" + + if [ -z "$repo_info" ]; then + return $exit + fi + + local short_sha="" + if [ "$rev_parse_exit_code" = "0" ]; then + short_sha="${repo_info##*$'\n'}" + repo_info="${repo_info%$'\n'*}" + fi + local inside_worktree="${repo_info##*$'\n'}" + repo_info="${repo_info%$'\n'*}" + local bare_repo="${repo_info##*$'\n'}" + repo_info="${repo_info%$'\n'*}" + local inside_gitdir="${repo_info##*$'\n'}" + local g="${repo_info%$'\n'*}" + + if [ "true" = "$inside_worktree" ] && + [ -n "${GIT_PS1_HIDE_IF_PWD_IGNORED-}" ] && + [ "$(git config --bool bash.hideIfPwdIgnored)" != "false" ] && + git check-ignore -q . + then + return $exit + fi + + local r="" + local b="" + local step="" + local total="" + if [ -d "$g/rebase-merge" ]; then + __git_eread "$g/rebase-merge/head-name" b + __git_eread "$g/rebase-merge/msgnum" step + __git_eread "$g/rebase-merge/end" total + if [ -f "$g/rebase-merge/interactive" ]; then + r="|REBASE-i" + else + r="|REBASE-m" + fi + else + if [ -d "$g/rebase-apply" ]; then + __git_eread "$g/rebase-apply/next" step + __git_eread "$g/rebase-apply/last" total + if [ -f "$g/rebase-apply/rebasing" ]; then + __git_eread "$g/rebase-apply/head-name" b + r="|REBASE" + elif [ -f "$g/rebase-apply/applying" ]; then + r="|AM" + else + r="|AM/REBASE" + fi + elif [ -f "$g/MERGE_HEAD" ]; then + r="|MERGING" + elif __git_sequencer_status; then + : + elif [ -f "$g/BISECT_LOG" ]; then + r="|BISECTING" + fi + + if [ -n "$b" ]; then + : + elif [ -h "$g/HEAD" ]; then + # symlink symbolic ref + b="$(git symbolic-ref HEAD 2>/dev/null)" + else + local head="" + if ! __git_eread "$g/HEAD" head; then + return $exit + fi + # is it a symbolic ref? + b="${head#ref: }" + if [ "$head" = "$b" ]; then + detached=yes + b="$( + case "${GIT_PS1_DESCRIBE_STYLE-}" in + (contains) + git describe --contains HEAD ;; + (branch) + git describe --contains --all HEAD ;; + (tag) + git describe --tags HEAD ;; + (describe) + git describe HEAD ;; + (* | default) + git describe --tags --exact-match HEAD ;; + esac 2>/dev/null)" || + + b="$short_sha..." + b="($b)" + fi + fi + fi + + if [ -n "$step" ] && [ -n "$total" ]; then + r="$r $step/$total" + fi + + local w="" + local i="" + local s="" + local u="" + local c="" + local p="" + + if [ "true" = "$inside_gitdir" ]; then + if [ "true" = "$bare_repo" ]; then + c="BARE:" + else + b="GIT_DIR!" + fi + elif [ "true" = "$inside_worktree" ]; then + if [ -n "${GIT_PS1_SHOWDIRTYSTATE-}" ] && + [ "$(git config --bool bash.showDirtyState)" != "false" ] + then + git diff --no-ext-diff --quiet || w="*" + git diff --no-ext-diff --cached --quiet || i="+" + if [ -z "$short_sha" ] && [ -z "$i" ]; then + i="#" + fi + fi + if [ -n "${GIT_PS1_SHOWSTASHSTATE-}" ] && + git rev-parse --verify --quiet refs/stash >/dev/null + then + s="$" + fi + + if [ -n "${GIT_PS1_SHOWUNTRACKEDFILES-}" ] && + [ "$(git config --bool bash.showUntrackedFiles)" != "false" ] && + git ls-files --others --exclude-standard --directory --no-empty-directory --error-unmatch -- ':/*' >/dev/null 2>/dev/null + then + u="%${ZSH_VERSION+%}" + fi + + if [ -n "${GIT_PS1_SHOWUPSTREAM-}" ]; then + __git_ps1_show_upstream + fi + fi + + local z="${GIT_PS1_STATESEPARATOR-" "}" + + # NO color option unless in PROMPT_COMMAND mode + if [ $pcmode = yes ] && [ -n "${GIT_PS1_SHOWCOLORHINTS-}" ]; then + __git_ps1_colorize_gitstring + fi + + b=${b##refs/heads/} + if [ $pcmode = yes ] && [ $ps1_expanded = yes ]; then + __git_ps1_branch_name=$b + b="\${__git_ps1_branch_name}" + fi + + local f="$w$i$s$u" + local gitstring="$c$b${f:+$z$f}$r$p" + + if [ $pcmode = yes ]; then + if [ "${__git_printf_supports_v-}" != yes ]; then + gitstring=$(printf -- "$printf_format" "$gitstring") + else + printf -v gitstring -- "$printf_format" "$gitstring" + fi + PS1="$ps1pc_start$gitstring$ps1pc_end" + else + printf -- "$printf_format" "$gitstring" + fi + + return $exit +} diff --git a/contrib/contacts/.gitignore b/contrib/contacts/.gitignore new file mode 100644 index 000000000000..f385ee643c74 --- /dev/null +++ b/contrib/contacts/.gitignore @@ -0,0 +1,3 @@ +git-contacts.1 +git-contacts.html +git-contacts.xml diff --git a/contrib/contacts/Makefile b/contrib/contacts/Makefile new file mode 100644 index 000000000000..a2990f0dcb53 --- /dev/null +++ b/contrib/contacts/Makefile @@ -0,0 +1,71 @@ +# The default target of this Makefile is... +all:: + +-include ../../config.mak.autogen +-include ../../config.mak + +prefix ?= /usr/local +gitexecdir ?= $(prefix)/libexec/git-core +mandir ?= $(prefix)/share/man +man1dir ?= $(mandir)/man1 +htmldir ?= $(prefix)/share/doc/git-doc + +../../GIT-VERSION-FILE: FORCE + $(MAKE) -C ../../ GIT-VERSION-FILE + +-include ../../GIT-VERSION-FILE + +# this should be set to a 'standard' bsd-type install program +INSTALL ?= install +RM ?= rm -f + +ASCIIDOC = asciidoc +XMLTO = xmlto + +ifndef SHELL_PATH + SHELL_PATH = /bin/sh +endif +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) + +ASCIIDOC_CONF = ../../Documentation/asciidoc.conf +MANPAGE_XSL = ../../Documentation/manpage-normal.xsl + +GIT_CONTACTS := git-contacts + +GIT_CONTACTS_DOC := git-contacts.1 +GIT_CONTACTS_XML := git-contacts.xml +GIT_CONTACTS_TXT := git-contacts.txt +GIT_CONTACTS_HTML := git-contacts.html + +doc: $(GIT_CONTACTS_DOC) $(GIT_CONTACTS_HTML) + +install: $(GIT_CONTACTS) + $(INSTALL) -d -m 755 $(DESTDIR)$(gitexecdir) + $(INSTALL) -m 755 $(GIT_CONTACTS) $(DESTDIR)$(gitexecdir) + +install-doc: install-man install-html + +install-man: $(GIT_CONTACTS_DOC) + $(INSTALL) -d -m 755 $(DESTDIR)$(man1dir) + $(INSTALL) -m 644 $^ $(DESTDIR)$(man1dir) + +install-html: $(GIT_CONTACTS_HTML) + $(INSTALL) -d -m 755 $(DESTDIR)$(htmldir) + $(INSTALL) -m 644 $^ $(DESTDIR)$(htmldir) + +$(GIT_CONTACTS_DOC): $(GIT_CONTACTS_XML) + $(XMLTO) -m $(MANPAGE_XSL) man $^ + +$(GIT_CONTACTS_XML): $(GIT_CONTACTS_TXT) + $(ASCIIDOC) -b docbook -d manpage -f $(ASCIIDOC_CONF) \ + -agit_version=$(GIT_VERSION) $^ + +$(GIT_CONTACTS_HTML): $(GIT_CONTACTS_TXT) + $(ASCIIDOC) -b xhtml11 -d manpage -f $(ASCIIDOC_CONF) \ + -agit_version=$(GIT_VERSION) $^ + +clean: + $(RM) $(GIT_CONTACTS) + $(RM) *.xml *.html *.1 + +.PHONY: FORCE diff --git a/contrib/contacts/git-contacts b/contrib/contacts/git-contacts new file mode 100755 index 000000000000..85ad732fc063 --- /dev/null +++ b/contrib/contacts/git-contacts @@ -0,0 +1,203 @@ +#!/usr/bin/perl + +# List people who might be interested in a patch. Useful as the argument to +# git-send-email --cc-cmd option, and in other situations. +# +# Usage: git contacts <file | rev-list option> ... + +use strict; +use warnings; +use IPC::Open2; + +my $since = '5-years-ago'; +my $min_percent = 10; +my $labels_rx = qr/Signed-off-by|Reviewed-by|Acked-by|Cc|Reported-by/i; +my %seen; + +sub format_contact { + my ($name, $email) = @_; + return "$name <$email>"; +} + +sub parse_commit { + my ($commit, $data) = @_; + my $contacts = $commit->{contacts}; + my $inbody = 0; + for (split(/^/m, $data)) { + if (not $inbody) { + if (/^author ([^<>]+) <(\S+)> .+$/) { + $contacts->{format_contact($1, $2)} = 1; + } elsif (/^$/) { + $inbody = 1; + } + } elsif (/^$labels_rx:\s+([^<>]+)\s+<(\S+?)>$/o) { + $contacts->{format_contact($1, $2)} = 1; + } + } +} + +sub import_commits { + my ($commits) = @_; + return unless %$commits; + my $pid = open2 my $reader, my $writer, qw(git cat-file --batch); + for my $id (keys(%$commits)) { + print $writer "$id\n"; + my $line = <$reader>; + if ($line =~ /^([0-9a-f]{40}) commit (\d+)/) { + my ($cid, $len) = ($1, $2); + die "expected $id but got $cid\n" unless $id eq $cid; + my $data; + # cat-file emits newline after data, so read len+1 + read $reader, $data, $len + 1; + parse_commit($commits->{$id}, $data); + } + } + close $reader; + close $writer; + waitpid($pid, 0); + die "git-cat-file error: $?\n" if $?; +} + +sub get_blame { + my ($commits, $source, $from, $ranges) = @_; + return unless @$ranges; + open my $f, '-|', + qw(git blame --porcelain -C), + map({"-L$_->[0],+$_->[1]"} @$ranges), + '--since', $since, "$from^", '--', $source or die; + while (<$f>) { + if (/^([0-9a-f]{40}) \d+ \d+ \d+$/) { + my $id = $1; + $commits->{$id} = { id => $id, contacts => {} } + unless $seen{$id}; + $seen{$id} = 1; + } + } + close $f; +} + +sub blame_sources { + my ($sources, $commits) = @_; + for my $s (keys %$sources) { + for my $id (keys %{$sources->{$s}}) { + get_blame($commits, $s, $id, $sources->{$s}{$id}); + } + } +} + +sub scan_patches { + my ($sources, $id, $f) = @_; + my $source; + while (<$f>) { + if (/^From ([0-9a-f]{40}) Mon Sep 17 00:00:00 2001$/) { + $id = $1; + $seen{$id} = 1; + } + next unless $id; + if (m{^--- (?:a/(.+)|/dev/null)$}) { + $source = $1; + } elsif (/^@@ -(\d+)(?:,(\d+))?/ && $source) { + my $len = defined($2) ? $2 : 1; + push @{$sources->{$source}{$id}}, [$1, $len] if $len; + } + } +} + +sub scan_patch_file { + my ($commits, $file) = @_; + open my $f, '<', $file or die "read failure: $file: $!\n"; + scan_patches($commits, undef, $f); + close $f; +} + +sub parse_rev_args { + my @args = @_; + open my $f, '-|', + qw(git rev-parse --revs-only --default HEAD --symbolic), @args + or die; + my @revs; + while (<$f>) { + chomp; + push @revs, $_; + } + close $f; + return @revs if scalar(@revs) != 1; + return "^$revs[0]", 'HEAD' unless $revs[0] =~ /^-/; + return $revs[0], 'HEAD'; +} + +sub scan_rev_args { + my ($commits, $args) = @_; + my @revs = parse_rev_args(@$args); + open my $f, '-|', qw(git rev-list --reverse), @revs or die; + while (<$f>) { + chomp; + my $id = $_; + $seen{$id} = 1; + open my $g, '-|', qw(git show -C --oneline), $id or die; + scan_patches($commits, $id, $g); + close $g; + } + close $f; +} + +sub mailmap_contacts { + my ($contacts) = @_; + my %mapped; + my $pid = open2 my $reader, my $writer, qw(git check-mailmap --stdin); + for my $contact (keys(%$contacts)) { + print $writer "$contact\n"; + my $canonical = <$reader>; + chomp $canonical; + $mapped{$canonical} += $contacts->{$contact}; + } + close $reader; + close $writer; + waitpid($pid, 0); + die "git-check-mailmap error: $?\n" if $?; + return \%mapped; +} + +if (!@ARGV) { + die "No input revisions or patch files\n"; +} + +my (@files, @rev_args); +for (@ARGV) { + if (-e) { + push @files, $_; + } else { + push @rev_args, $_; + } +} + +my %sources; +for (@files) { + scan_patch_file(\%sources, $_); +} +if (@rev_args) { + scan_rev_args(\%sources, \@rev_args) +} + +my $toplevel = `git rev-parse --show-toplevel`; +chomp $toplevel; +chdir($toplevel) or die "chdir failure: $toplevel: $!\n"; + +my %commits; +blame_sources(\%sources, \%commits); +import_commits(\%commits); + +my $contacts = {}; +for my $commit (values %commits) { + for my $contact (keys %{$commit->{contacts}}) { + $contacts->{$contact}++; + } +} +$contacts = mailmap_contacts($contacts); + +my $ncommits = scalar(keys %commits); +for my $contact (keys %$contacts) { + my $percent = $contacts->{$contact} * 100 / $ncommits; + next if $percent < $min_percent; + print "$contact\n"; +} diff --git a/contrib/contacts/git-contacts.txt b/contrib/contacts/git-contacts.txt new file mode 100644 index 000000000000..dd914d126123 --- /dev/null +++ b/contrib/contacts/git-contacts.txt @@ -0,0 +1,94 @@ +git-contacts(1) +=============== + +NAME +---- +git-contacts - List people who might be interested in a set of changes + + +SYNOPSIS +-------- +[verse] +'git contacts' (<patch>|<range>|<rev>)... + + +DESCRIPTION +----------- + +Given a set of changes, specified as patch files or revisions, determine people +who might be interested in those changes. This is done by consulting the +history of each patch or revision hunk to find people mentioned by commits +which touched the lines of files under consideration. + +Input consists of one or more patch files or revision arguments. A revision +argument can be a range or a single `<rev>` which is interpreted as +`<rev>..HEAD`, thus the same revision arguments are accepted as for +linkgit:git-format-patch[1]. Patch files and revision arguments can be combined +in the same invocation. + +This command can be useful for determining the list of people with whom to +discuss proposed changes, or for finding the list of recipients to Cc: when +submitting a patch series via `git send-email`. For the latter case, `git +contacts` can be used as the argument to `git send-email`'s `--cc-cmd` option. + + +DISCUSSION +---------- + +`git blame` is invoked for each hunk in a patch file or revision. For each +commit mentioned by `git blame`, the commit message is consulted for people who +authored, reviewed, signed, acknowledged, or were Cc:'d. Once the list of +participants is known, each person's relevance is computed by considering how +many commits mentioned that person compared with the total number of commits +under consideration. The final output consists only of participants who exceed +a minimum threshold of participation. + + +OUTPUT +------ + +For each person of interest, a single line is output, terminated by a newline. +If the person's name is known, ``Name $$<user@host>$$'' is printed; otherwise +only ``$$<user@host>$$'' is printed. + + +EXAMPLES +-------- + +* Consult patch files: ++ +------------ +$ git contacts feature/*.patch +------------ + +* Revision range: ++ +------------ +$ git contacts R1..R2 +------------ + +* From a single revision to `HEAD`: ++ +------------ +$ git contacts origin +------------ + +* Helper for `git send-email`: ++ +------------ +$ git send-email --cc-cmd='git contacts' feature/*.patch +------------ + + +LIMITATIONS +----------- + +Several conditions controlling a person's significance are currently +hard-coded, such as minimum participation level (10%), blame date-limiting (5 +years), and `-C` level for detecting moved and copied lines (a single `-C`). In +the future, these conditions may become configurable. + + +GIT +--- +Part of the linkgit:git[1] suite diff --git a/contrib/coverage-diff.sh b/contrib/coverage-diff.sh new file mode 100755 index 000000000000..4ec419f90048 --- /dev/null +++ b/contrib/coverage-diff.sh @@ -0,0 +1,108 @@ +#!/bin/sh + +# Usage: Run 'contrib/coverage-diff.sh <version1> <version2>' from source-root +# after running +# +# make coverage-test +# make coverage-report +# +# while checked out at <version2>. This script combines the *.gcov files +# generated by the 'make' commands above with 'git diff <version1> <version2>' +# to report new lines that are not covered by the test suite. + +V1=$1 +V2=$2 + +diff_lines () { + perl -e ' + my $line_num; + while (<>) { + # Hunk header? Grab the beginning in postimage. + if (/^@@ -\d+(?:,\d+)? \+(\d+)(?:,\d+)? @@/) { + $line_num = $1; + next; + } + + # Have we seen a hunk? Ignore "diff --git" etc. + next unless defined $line_num; + + # Deleted line? Ignore. + if (/^-/) { + next; + } + + # Show only the line number of added lines. + if (/^\+/) { + print "$line_num\n"; + } + # Either common context or added line appear in + # the postimage. Count it. + $line_num++; + } + ' +} + +files=$(git diff --name-only "$V1" "$V2" -- \*.c) + +# create empty file +>coverage-data.txt + +for file in $files +do + git diff "$V1" "$V2" -- "$file" | + diff_lines | + sort >new_lines.txt + + if ! test -s new_lines.txt + then + continue + fi + + hash_file=$(echo $file | sed "s/\//\#/") + + if ! test -s "$hash_file.gcov" + then + continue + fi + + sed -ne '/#####:/{ + s/ #####:// + s/:.*// + s/ //g + p + }' "$hash_file.gcov" | + sort >uncovered_lines.txt + + comm -12 uncovered_lines.txt new_lines.txt | + sed -e 's/$/\)/' | + sed -e 's/^/ /' >uncovered_new_lines.txt + + grep -q '[^[:space:]]' <uncovered_new_lines.txt && + echo $file >>coverage-data.txt && + git blame -s "$V2" -- "$file" | + sed 's/\t//g' | + grep -f uncovered_new_lines.txt >>coverage-data.txt && + echo >>coverage-data.txt + + rm -f new_lines.txt uncovered_lines.txt uncovered_new_lines.txt +done + +cat coverage-data.txt + +echo "Commits introducing uncovered code:" + +commit_list=$(cat coverage-data.txt | + grep -E '^[0-9a-f]{7,} ' | + awk '{print $1;}' | + sort | + uniq) + +( + for commit in $commit_list + do + git log --no-decorate --pretty=format:'%an %h: %s' -1 $commit + echo + done +) | sort + +rm coverage-data.txt diff --git a/contrib/credential/gnome-keyring/.gitignore b/contrib/credential/gnome-keyring/.gitignore new file mode 100644 index 000000000000..88d8fcdbce7d --- /dev/null +++ b/contrib/credential/gnome-keyring/.gitignore @@ -0,0 +1 @@ +git-credential-gnome-keyring diff --git a/contrib/credential/gnome-keyring/Makefile b/contrib/credential/gnome-keyring/Makefile new file mode 100644 index 000000000000..22c19df94b81 --- /dev/null +++ b/contrib/credential/gnome-keyring/Makefile @@ -0,0 +1,25 @@ +MAIN:=git-credential-gnome-keyring +all:: $(MAIN) + +CC = gcc +RM = rm -f +CFLAGS = -g -O2 -Wall +PKG_CONFIG = pkg-config + +-include ../../../config.mak.autogen +-include ../../../config.mak + +INCS:=$(shell $(PKG_CONFIG) --cflags gnome-keyring-1 glib-2.0) +LIBS:=$(shell $(PKG_CONFIG) --libs gnome-keyring-1 glib-2.0) + +SRCS:=$(MAIN).c +OBJS:=$(SRCS:.c=.o) + +%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(INCS) -o $@ -c $< + +$(MAIN): $(OBJS) + $(CC) -o $@ $(LDFLAGS) $^ $(LIBS) + +clean: + @$(RM) $(MAIN) $(OBJS) diff --git a/contrib/credential/gnome-keyring/git-credential-gnome-keyring.c b/contrib/credential/gnome-keyring/git-credential-gnome-keyring.c new file mode 100644 index 000000000000..d389bfadceeb --- /dev/null +++ b/contrib/credential/gnome-keyring/git-credential-gnome-keyring.c @@ -0,0 +1,470 @@ +/* + * Copyright (C) 2011 John Szakmeister <john@szakmeister.net> + * 2012 Philipp A. Hartmann <pah@qo.cx> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +/* + * Credits: + * - GNOME Keyring API handling originally written by John Szakmeister + * - ported to credential helper API by Philipp A. Hartmann + */ + +#include <stdio.h> +#include <string.h> +#include <stdlib.h> +#include <glib.h> +#include <gnome-keyring.h> + +#ifdef GNOME_KEYRING_DEFAULT + + /* Modern gnome-keyring */ + +#include <gnome-keyring-memory.h> + +#else + + /* + * Support ancient gnome-keyring, circ. RHEL 5.X. + * GNOME_KEYRING_DEFAULT seems to have been introduced with Gnome 2.22, + * and the other features roughly around Gnome 2.20, 6 months before. + * Ubuntu 8.04 used Gnome 2.22 (I think). Not sure any distro used 2.20. + * So the existence/non-existence of GNOME_KEYRING_DEFAULT seems like + * a decent thing to use as an indicator. + */ + +#define GNOME_KEYRING_DEFAULT NULL + +/* + * ancient gnome-keyring returns DENIED when an entry is not found. + * Setting NO_MATCH to DENIED will prevent us from reporting DENIED + * errors during get and erase operations, but we will still report + * DENIED errors during a store. + */ +#define GNOME_KEYRING_RESULT_NO_MATCH GNOME_KEYRING_RESULT_DENIED + +#define gnome_keyring_memory_alloc g_malloc +#define gnome_keyring_memory_free gnome_keyring_free_password +#define gnome_keyring_memory_strdup g_strdup + +static const char *gnome_keyring_result_to_message(GnomeKeyringResult result) +{ + switch (result) { + case GNOME_KEYRING_RESULT_OK: + return "OK"; + case GNOME_KEYRING_RESULT_DENIED: + return "Denied"; + case GNOME_KEYRING_RESULT_NO_KEYRING_DAEMON: + return "No Keyring Daemon"; + case GNOME_KEYRING_RESULT_ALREADY_UNLOCKED: + return "Already UnLocked"; + case GNOME_KEYRING_RESULT_NO_SUCH_KEYRING: + return "No Such Keyring"; + case GNOME_KEYRING_RESULT_BAD_ARGUMENTS: + return "Bad Arguments"; + case GNOME_KEYRING_RESULT_IO_ERROR: + return "IO Error"; + case GNOME_KEYRING_RESULT_CANCELLED: + return "Cancelled"; + case GNOME_KEYRING_RESULT_ALREADY_EXISTS: + return "Already Exists"; + default: + return "Unknown Error"; + } +} + +/* + * Support really ancient gnome-keyring, circ. RHEL 4.X. + * Just a guess for the Glib version. Glib 2.8 was roughly Gnome 2.12 ? + * Which was released with gnome-keyring 0.4.3 ?? + */ +#if GLIB_MAJOR_VERSION == 2 && GLIB_MINOR_VERSION < 8 + +static void gnome_keyring_done_cb(GnomeKeyringResult result, gpointer user_data) +{ + gpointer *data = (gpointer *)user_data; + int *done = (int *)data[0]; + GnomeKeyringResult *r = (GnomeKeyringResult *)data[1]; + + *r = result; + *done = 1; +} + +static void wait_for_request_completion(int *done) +{ + GMainContext *mc = g_main_context_default(); + while (!*done) + g_main_context_iteration(mc, TRUE); +} + +static GnomeKeyringResult gnome_keyring_item_delete_sync(const char *keyring, guint32 id) +{ + int done = 0; + GnomeKeyringResult result; + gpointer data[] = { &done, &result }; + + gnome_keyring_item_delete(keyring, id, gnome_keyring_done_cb, data, + NULL); + + wait_for_request_completion(&done); + + return result; +} + +#endif +#endif + +/* + * This credential struct and API is simplified from git's credential.{h,c} + */ +struct credential { + char *protocol; + char *host; + unsigned short port; + char *path; + char *username; + char *password; +}; + +#define CREDENTIAL_INIT { NULL, NULL, 0, NULL, NULL, NULL } + +typedef int (*credential_op_cb)(struct credential *); + +struct credential_operation { + char *name; + credential_op_cb op; +}; + +#define CREDENTIAL_OP_END { NULL, NULL } + +/* ----------------- GNOME Keyring functions ----------------- */ + +/* create a special keyring option string, if path is given */ +static char *keyring_object(struct credential *c) +{ + if (!c->path) + return NULL; + + if (c->port) + return g_strdup_printf("%s:%hd/%s", c->host, c->port, c->path); + + return g_strdup_printf("%s/%s", c->host, c->path); +} + +static int keyring_get(struct credential *c) +{ + char *object = NULL; + GList *entries; + GnomeKeyringNetworkPasswordData *password_data; + GnomeKeyringResult result; + + if (!c->protocol || !(c->host || c->path)) + return EXIT_FAILURE; + + object = keyring_object(c); + + result = gnome_keyring_find_network_password_sync( + c->username, + NULL /* domain */, + c->host, + object, + c->protocol, + NULL /* authtype */, + c->port, + &entries); + + g_free(object); + + if (result == GNOME_KEYRING_RESULT_NO_MATCH) + return EXIT_SUCCESS; + + if (result == GNOME_KEYRING_RESULT_CANCELLED) + return EXIT_SUCCESS; + + if (result != GNOME_KEYRING_RESULT_OK) { + g_critical("%s", gnome_keyring_result_to_message(result)); + return EXIT_FAILURE; + } + + /* pick the first one from the list */ + password_data = (GnomeKeyringNetworkPasswordData *)entries->data; + + gnome_keyring_memory_free(c->password); + c->password = gnome_keyring_memory_strdup(password_data->password); + + if (!c->username) + c->username = g_strdup(password_data->user); + + gnome_keyring_network_password_list_free(entries); + + return EXIT_SUCCESS; +} + + +static int keyring_store(struct credential *c) +{ + guint32 item_id; + char *object = NULL; + GnomeKeyringResult result; + + /* + * Sanity check that what we are storing is actually sensible. + * In particular, we can't make a URL without a protocol field. + * Without either a host or pathname (depending on the scheme), + * we have no primary key. And without a username and password, + * we are not actually storing a credential. + */ + if (!c->protocol || !(c->host || c->path) || + !c->username || !c->password) + return EXIT_FAILURE; + + object = keyring_object(c); + + result = gnome_keyring_set_network_password_sync( + GNOME_KEYRING_DEFAULT, + c->username, + NULL /* domain */, + c->host, + object, + c->protocol, + NULL /* authtype */, + c->port, + c->password, + &item_id); + + g_free(object); + + if (result != GNOME_KEYRING_RESULT_OK && + result != GNOME_KEYRING_RESULT_CANCELLED) { + g_critical("%s", gnome_keyring_result_to_message(result)); + return EXIT_FAILURE; + } + + return EXIT_SUCCESS; +} + +static int keyring_erase(struct credential *c) +{ + char *object = NULL; + GList *entries; + GnomeKeyringNetworkPasswordData *password_data; + GnomeKeyringResult result; + + /* + * Sanity check that we actually have something to match + * against. The input we get is a restrictive pattern, + * so technically a blank credential means "erase everything". + * But it is too easy to accidentally send this, since it is equivalent + * to empty input. So explicitly disallow it, and require that the + * pattern have some actual content to match. + */ + if (!c->protocol && !c->host && !c->path && !c->username) + return EXIT_FAILURE; + + object = keyring_object(c); + + result = gnome_keyring_find_network_password_sync( + c->username, + NULL /* domain */, + c->host, + object, + c->protocol, + NULL /* authtype */, + c->port, + &entries); + + g_free(object); + + if (result == GNOME_KEYRING_RESULT_NO_MATCH) + return EXIT_SUCCESS; + + if (result == GNOME_KEYRING_RESULT_CANCELLED) + return EXIT_SUCCESS; + + if (result != GNOME_KEYRING_RESULT_OK) { + g_critical("%s", gnome_keyring_result_to_message(result)); + return EXIT_FAILURE; + } + + /* pick the first one from the list (delete all matches?) */ + password_data = (GnomeKeyringNetworkPasswordData *)entries->data; + + result = gnome_keyring_item_delete_sync( + password_data->keyring, password_data->item_id); + + gnome_keyring_network_password_list_free(entries); + + if (result != GNOME_KEYRING_RESULT_OK) { + g_critical("%s", gnome_keyring_result_to_message(result)); + return EXIT_FAILURE; + } + + return EXIT_SUCCESS; +} + +/* + * Table with helper operation callbacks, used by generic + * credential helper main function. + */ +static struct credential_operation const credential_helper_ops[] = { + { "get", keyring_get }, + { "store", keyring_store }, + { "erase", keyring_erase }, + CREDENTIAL_OP_END +}; + +/* ------------------ credential functions ------------------ */ + +static void credential_init(struct credential *c) +{ + memset(c, 0, sizeof(*c)); +} + +static void credential_clear(struct credential *c) +{ + g_free(c->protocol); + g_free(c->host); + g_free(c->path); + g_free(c->username); + gnome_keyring_memory_free(c->password); + + credential_init(c); +} + +static int credential_read(struct credential *c) +{ + char *buf; + size_t line_len; + char *key; + char *value; + + key = buf = gnome_keyring_memory_alloc(1024); + + while (fgets(buf, 1024, stdin)) { + line_len = strlen(buf); + + if (line_len && buf[line_len-1] == '\n') + buf[--line_len] = '\0'; + + if (!line_len) + break; + + value = strchr(buf, '='); + if (!value) { + g_warning("invalid credential line: %s", key); + gnome_keyring_memory_free(buf); + return -1; + } + *value++ = '\0'; + + if (!strcmp(key, "protocol")) { + g_free(c->protocol); + c->protocol = g_strdup(value); + } else if (!strcmp(key, "host")) { + g_free(c->host); + c->host = g_strdup(value); + value = strrchr(c->host, ':'); + if (value) { + *value++ = '\0'; + c->port = atoi(value); + } + } else if (!strcmp(key, "path")) { + g_free(c->path); + c->path = g_strdup(value); + } else if (!strcmp(key, "username")) { + g_free(c->username); + c->username = g_strdup(value); + } else if (!strcmp(key, "password")) { + gnome_keyring_memory_free(c->password); + c->password = gnome_keyring_memory_strdup(value); + while (*value) + *value++ = '\0'; + } + /* + * Ignore other lines; we don't know what they mean, but + * this future-proofs us when later versions of git do + * learn new lines, and the helpers are updated to match. + */ + } + + gnome_keyring_memory_free(buf); + + return 0; +} + +static void credential_write_item(FILE *fp, const char *key, const char *value) +{ + if (!value) + return; + fprintf(fp, "%s=%s\n", key, value); +} + +static void credential_write(const struct credential *c) +{ + /* only write username/password, if set */ + credential_write_item(stdout, "username", c->username); + credential_write_item(stdout, "password", c->password); +} + +static void usage(const char *name) +{ + struct credential_operation const *try_op = credential_helper_ops; + const char *basename = strrchr(name, '/'); + + basename = (basename) ? basename + 1 : name; + fprintf(stderr, "usage: %s <", basename); + while (try_op->name) { + fprintf(stderr, "%s", (try_op++)->name); + if (try_op->name) + fprintf(stderr, "%s", "|"); + } + fprintf(stderr, "%s", ">\n"); +} + +int main(int argc, char *argv[]) +{ + int ret = EXIT_SUCCESS; + + struct credential_operation const *try_op = credential_helper_ops; + struct credential cred = CREDENTIAL_INIT; + + if (!argv[1]) { + usage(argv[0]); + exit(EXIT_FAILURE); + } + + g_set_application_name("Git Credential Helper"); + + /* lookup operation callback */ + while (try_op->name && strcmp(argv[1], try_op->name)) + try_op++; + + /* unsupported operation given -- ignore silently */ + if (!try_op->name || !try_op->op) + goto out; + + ret = credential_read(&cred); + if (ret) + goto out; + + /* perform credential operation */ + ret = (*try_op->op)(&cred); + + credential_write(&cred); + +out: + credential_clear(&cred); + return ret; +} diff --git a/contrib/credential/libsecret/Makefile b/contrib/credential/libsecret/Makefile new file mode 100644 index 000000000000..3e67552cc5b5 --- /dev/null +++ b/contrib/credential/libsecret/Makefile @@ -0,0 +1,25 @@ +MAIN:=git-credential-libsecret +all:: $(MAIN) + +CC = gcc +RM = rm -f +CFLAGS = -g -O2 -Wall +PKG_CONFIG = pkg-config + +-include ../../../config.mak.autogen +-include ../../../config.mak + +INCS:=$(shell $(PKG_CONFIG) --cflags libsecret-1 glib-2.0) +LIBS:=$(shell $(PKG_CONFIG) --libs libsecret-1 glib-2.0) + +SRCS:=$(MAIN).c +OBJS:=$(SRCS:.c=.o) + +%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(INCS) -o $@ -c $< + +$(MAIN): $(OBJS) + $(CC) -o $@ $(LDFLAGS) $^ $(LIBS) + +clean: + @$(RM) $(MAIN) $(OBJS) diff --git a/contrib/credential/libsecret/git-credential-libsecret.c b/contrib/credential/libsecret/git-credential-libsecret.c new file mode 100644 index 000000000000..e6598b638339 --- /dev/null +++ b/contrib/credential/libsecret/git-credential-libsecret.c @@ -0,0 +1,369 @@ +/* + * Copyright (C) 2011 John Szakmeister <john@szakmeister.net> + * 2012 Philipp A. Hartmann <pah@qo.cx> + * 2016 Mantas Mikulėnas <grawity@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +/* + * Credits: + * - GNOME Keyring API handling originally written by John Szakmeister + * - ported to credential helper API by Philipp A. Hartmann + */ + +#include <stdio.h> +#include <string.h> +#include <stdlib.h> +#include <glib.h> +#include <libsecret/secret.h> + +/* + * This credential struct and API is simplified from git's credential.{h,c} + */ +struct credential { + char *protocol; + char *host; + unsigned short port; + char *path; + char *username; + char *password; +}; + +#define CREDENTIAL_INIT { NULL, NULL, 0, NULL, NULL, NULL } + +typedef int (*credential_op_cb)(struct credential *); + +struct credential_operation { + char *name; + credential_op_cb op; +}; + +#define CREDENTIAL_OP_END { NULL, NULL } + +/* ----------------- Secret Service functions ----------------- */ + +static char *make_label(struct credential *c) +{ + if (c->port) + return g_strdup_printf("Git: %s://%s:%hu/%s", + c->protocol, c->host, c->port, c->path ? c->path : ""); + else + return g_strdup_printf("Git: %s://%s/%s", + c->protocol, c->host, c->path ? c->path : ""); +} + +static GHashTable *make_attr_list(struct credential *c) +{ + GHashTable *al = g_hash_table_new_full(g_str_hash, g_str_equal, NULL, g_free); + + if (c->username) + g_hash_table_insert(al, "user", g_strdup(c->username)); + if (c->protocol) + g_hash_table_insert(al, "protocol", g_strdup(c->protocol)); + if (c->host) + g_hash_table_insert(al, "server", g_strdup(c->host)); + if (c->port) + g_hash_table_insert(al, "port", g_strdup_printf("%hu", c->port)); + if (c->path) + g_hash_table_insert(al, "object", g_strdup(c->path)); + + return al; +} + +static int keyring_get(struct credential *c) +{ + SecretService *service = NULL; + GHashTable *attributes = NULL; + GError *error = NULL; + GList *items = NULL; + + if (!c->protocol || !(c->host || c->path)) + return EXIT_FAILURE; + + service = secret_service_get_sync(0, NULL, &error); + if (error != NULL) { + g_critical("could not connect to Secret Service: %s", error->message); + g_error_free(error); + return EXIT_FAILURE; + } + + attributes = make_attr_list(c); + items = secret_service_search_sync(service, + SECRET_SCHEMA_COMPAT_NETWORK, + attributes, + SECRET_SEARCH_LOAD_SECRETS | SECRET_SEARCH_UNLOCK, + NULL, + &error); + g_hash_table_unref(attributes); + if (error != NULL) { + g_critical("lookup failed: %s", error->message); + g_error_free(error); + return EXIT_FAILURE; + } + + if (items != NULL) { + SecretItem *item; + SecretValue *secret; + const char *s; + + item = items->data; + secret = secret_item_get_secret(item); + attributes = secret_item_get_attributes(item); + + s = g_hash_table_lookup(attributes, "user"); + if (s) { + g_free(c->username); + c->username = g_strdup(s); + } + + s = secret_value_get_text(secret); + if (s) { + g_free(c->password); + c->password = g_strdup(s); + } + + g_hash_table_unref(attributes); + secret_value_unref(secret); + g_list_free_full(items, g_object_unref); + } + + return EXIT_SUCCESS; +} + + +static int keyring_store(struct credential *c) +{ + char *label = NULL; + GHashTable *attributes = NULL; + GError *error = NULL; + + /* + * Sanity check that what we are storing is actually sensible. + * In particular, we can't make a URL without a protocol field. + * Without either a host or pathname (depending on the scheme), + * we have no primary key. And without a username and password, + * we are not actually storing a credential. + */ + if (!c->protocol || !(c->host || c->path) || + !c->username || !c->password) + return EXIT_FAILURE; + + label = make_label(c); + attributes = make_attr_list(c); + secret_password_storev_sync(SECRET_SCHEMA_COMPAT_NETWORK, + attributes, + NULL, + label, + c->password, + NULL, + &error); + g_free(label); + g_hash_table_unref(attributes); + + if (error != NULL) { + g_critical("store failed: %s", error->message); + g_error_free(error); + return EXIT_FAILURE; + } + + return EXIT_SUCCESS; +} + +static int keyring_erase(struct credential *c) +{ + GHashTable *attributes = NULL; + GError *error = NULL; + + /* + * Sanity check that we actually have something to match + * against. The input we get is a restrictive pattern, + * so technically a blank credential means "erase everything". + * But it is too easy to accidentally send this, since it is equivalent + * to empty input. So explicitly disallow it, and require that the + * pattern have some actual content to match. + */ + if (!c->protocol && !c->host && !c->path && !c->username) + return EXIT_FAILURE; + + attributes = make_attr_list(c); + secret_password_clearv_sync(SECRET_SCHEMA_COMPAT_NETWORK, + attributes, + NULL, + &error); + g_hash_table_unref(attributes); + + if (error != NULL) { + g_critical("erase failed: %s", error->message); + g_error_free(error); + return EXIT_FAILURE; + } + + return EXIT_SUCCESS; +} + +/* + * Table with helper operation callbacks, used by generic + * credential helper main function. + */ +static struct credential_operation const credential_helper_ops[] = { + { "get", keyring_get }, + { "store", keyring_store }, + { "erase", keyring_erase }, + CREDENTIAL_OP_END +}; + +/* ------------------ credential functions ------------------ */ + +static void credential_init(struct credential *c) +{ + memset(c, 0, sizeof(*c)); +} + +static void credential_clear(struct credential *c) +{ + g_free(c->protocol); + g_free(c->host); + g_free(c->path); + g_free(c->username); + g_free(c->password); + + credential_init(c); +} + +static int credential_read(struct credential *c) +{ + char *buf; + size_t line_len; + char *key; + char *value; + + key = buf = g_malloc(1024); + + while (fgets(buf, 1024, stdin)) { + line_len = strlen(buf); + + if (line_len && buf[line_len-1] == '\n') + buf[--line_len] = '\0'; + + if (!line_len) + break; + + value = strchr(buf, '='); + if (!value) { + g_warning("invalid credential line: %s", key); + g_free(buf); + return -1; + } + *value++ = '\0'; + + if (!strcmp(key, "protocol")) { + g_free(c->protocol); + c->protocol = g_strdup(value); + } else if (!strcmp(key, "host")) { + g_free(c->host); + c->host = g_strdup(value); + value = strrchr(c->host, ':'); + if (value) { + *value++ = '\0'; + c->port = atoi(value); + } + } else if (!strcmp(key, "path")) { + g_free(c->path); + c->path = g_strdup(value); + } else if (!strcmp(key, "username")) { + g_free(c->username); + c->username = g_strdup(value); + } else if (!strcmp(key, "password")) { + g_free(c->password); + c->password = g_strdup(value); + while (*value) + *value++ = '\0'; + } + /* + * Ignore other lines; we don't know what they mean, but + * this future-proofs us when later versions of git do + * learn new lines, and the helpers are updated to match. + */ + } + + g_free(buf); + + return 0; +} + +static void credential_write_item(FILE *fp, const char *key, const char *value) +{ + if (!value) + return; + fprintf(fp, "%s=%s\n", key, value); +} + +static void credential_write(const struct credential *c) +{ + /* only write username/password, if set */ + credential_write_item(stdout, "username", c->username); + credential_write_item(stdout, "password", c->password); +} + +static void usage(const char *name) +{ + struct credential_operation const *try_op = credential_helper_ops; + const char *basename = strrchr(name, '/'); + + basename = (basename) ? basename + 1 : name; + fprintf(stderr, "usage: %s <", basename); + while (try_op->name) { + fprintf(stderr, "%s", (try_op++)->name); + if (try_op->name) + fprintf(stderr, "%s", "|"); + } + fprintf(stderr, "%s", ">\n"); +} + +int main(int argc, char *argv[]) +{ + int ret = EXIT_SUCCESS; + + struct credential_operation const *try_op = credential_helper_ops; + struct credential cred = CREDENTIAL_INIT; + + if (!argv[1]) { + usage(argv[0]); + exit(EXIT_FAILURE); + } + + g_set_application_name("Git Credential Helper"); + + /* lookup operation callback */ + while (try_op->name && strcmp(argv[1], try_op->name)) + try_op++; + + /* unsupported operation given -- ignore silently */ + if (!try_op->name || !try_op->op) + goto out; + + ret = credential_read(&cred); + if (ret) + goto out; + + /* perform credential operation */ + ret = (*try_op->op)(&cred); + + credential_write(&cred); + +out: + credential_clear(&cred); + return ret; +} diff --git a/contrib/credential/netrc/Makefile b/contrib/credential/netrc/Makefile new file mode 100644 index 000000000000..6174e3bb8382 --- /dev/null +++ b/contrib/credential/netrc/Makefile @@ -0,0 +1,8 @@ +# The default target of this Makefile is... +all:: + +test: + ./t-git-credential-netrc.sh + +testverbose: + ./t-git-credential-netrc.sh -d -v diff --git a/contrib/credential/netrc/git-credential-netrc b/contrib/credential/netrc/git-credential-netrc new file mode 100755 index 000000000000..ebfc123ec641 --- /dev/null +++ b/contrib/credential/netrc/git-credential-netrc @@ -0,0 +1,440 @@ +#!/usr/bin/perl + +use strict; +use warnings; + +use Getopt::Long; +use File::Basename; +use Git; + +my $VERSION = "0.2"; + +my %options = ( + help => 0, + debug => 0, + verbose => 0, + insecure => 0, + file => [], + + # identical token maps, e.g. host -> host, will be inserted later + tmap => { + port => 'protocol', + machine => 'host', + path => 'path', + login => 'username', + user => 'username', + password => 'password', + } + ); + +# Map each credential protocol token to itself on the netrc side. +foreach (values %{$options{tmap}}) { + $options{tmap}->{$_} = $_; +} + +# Now, $options{tmap} has a mapping from the netrc format to the Git credential +# helper protocol. + +# Next, we build the reverse token map. + +# When $rmap{foo} contains 'bar', that means that what the Git credential helper +# protocol calls 'bar' is found as 'foo' in the netrc/authinfo file. Keys in +# %rmap are what we expect to read from the netrc/authinfo file. + +my %rmap; +foreach my $k (keys %{$options{tmap}}) { + push @{$rmap{$options{tmap}->{$k}}}, $k; +} + +Getopt::Long::Configure("bundling"); + +# TODO: maybe allow the token map $options{tmap} to be configurable. +GetOptions(\%options, + "help|h", + "debug|d", + "insecure|k", + "verbose|v", + "file|f=s@", + 'gpg|g:s', + ); + +if ($options{help}) { + my $shortname = basename($0); + $shortname =~ s/git-credential-//; + + print <<EOHIPPUS; + +$0 [(-f <authfile>)...] [-g <program>] [-d] [-v] [-k] get + +Version $VERSION by tzz\@lifelogs.com. License: BSD. + +Options: + + -f|--file <authfile>: specify netrc-style files. Files with the .gpg + extension will be decrypted by GPG before parsing. + Multiple -f arguments are OK. They are processed in + order, and the first matching entry found is returned + via the credential helper protocol (see below). + + When no -f option is given, .authinfo.gpg, .netrc.gpg, + .authinfo, and .netrc files in your home directory are + used in this order. + + -g|--gpg <program> : specify the program for GPG. By default, this is the + value of gpg.program in the git repository or global + option or gpg. + + -k|--insecure : ignore bad file ownership or permissions + + -d|--debug : turn on debugging (developer info) + + -v|--verbose : be more verbose (show files and information found) + +To enable this credential helper: + + git config credential.helper '$shortname -f AUTHFILE1 -f AUTHFILE2' + +(Note that Git will prepend "git-credential-" to the helper name and look for it +in the path.) + +...and if you want lots of debugging info: + + git config credential.helper '$shortname -f AUTHFILE -d' + +...or to see the files opened and data found: + + git config credential.helper '$shortname -f AUTHFILE -v' + +Only "get" mode is supported by this credential helper. It opens every +<authfile> and looks for the first entry that matches the requested search +criteria: + + 'port|protocol': + The protocol that will be used (e.g., https). (protocol=X) + + 'machine|host': + The remote hostname for a network credential. (host=X) + + 'path': + The path with which the credential will be used. (path=X) + + 'login|user|username': + The credential’s username, if we already have one. (username=X) + +Thus, when we get this query on STDIN: + +host=github.com +protocol=https +username=tzz + +this credential helper will look for the first entry in every <authfile> that +matches + +machine github.com port https login tzz + +OR + +machine github.com protocol https login tzz + +OR... etc. acceptable tokens as listed above. Any unknown tokens are +simply ignored. + +Then, the helper will print out whatever tokens it got from the entry, including +"password" tokens, mapping back to Git's helper protocol; e.g. "port" is mapped +back to "protocol". Any redundant entry tokens (part of the original query) are +skipped. + +Again, note that only the first matching entry from all the <authfile>s, +processed in the sequence given on the command line, is used. + +Netrc/authinfo tokens can be quoted as 'STRING' or "STRING". + +No caching is performed by this credential helper. + +EOHIPPUS + + exit 0; +} + +my $mode = shift @ARGV; + +# Credentials must get a parameter, so die if it's missing. +die "Syntax: $0 [(-f <authfile>)...] [-d] get" unless defined $mode; + +# Only support 'get' mode; with any other unsupported ones we just exit. +exit 0 unless $mode eq 'get'; + +my $files = $options{file}; + +# if no files were given, use a predefined list. +# note that .gpg files come first +unless (scalar @$files) { + my @candidates = qw[ + ~/.authinfo.gpg + ~/.netrc.gpg + ~/.authinfo + ~/.netrc + ]; + + $files = $options{file} = [ map { glob $_ } @candidates ]; +} + +load_config(\%options); + +my $query = read_credential_data_from_stdin(); + +FILE: +foreach my $file (@$files) { + my $gpgmode = $file =~ m/\.gpg$/; + unless (-r $file) { + log_verbose("Unable to read $file; skipping it"); + next FILE; + } + + # the following check is copied from Net::Netrc, for non-GPG files + # OS/2 and Win32 do not handle stat in a way compatible with this check :-( + unless ($gpgmode || $options{insecure} || + $^O eq 'os2' + || $^O eq 'MSWin32' + || $^O eq 'MacOS' + || $^O =~ /^cygwin/) { + my @stat = stat($file); + + if (@stat) { + if ($stat[2] & 077) { + log_verbose("Insecure $file (mode=%04o); skipping it", + $stat[2] & 07777); + next FILE; + } + + if ($stat[4] != $<) { + log_verbose("Not owner of $file; skipping it"); + next FILE; + } + } + } + + my @entries = load_netrc($file, $gpgmode); + + unless (scalar @entries) { + if ($!) { + log_verbose("Unable to open $file: $!"); + } else { + log_verbose("No netrc entries found in $file"); + } + + next FILE; + } + + my $entry = find_netrc_entry($query, @entries); + if ($entry) { + print_credential_data($entry, $query); + # we're done! + last FILE; + } +} + +exit 0; + +sub load_netrc { + my $file = shift @_; + my $gpgmode = shift @_; + + my $io; + if ($gpgmode) { + my @cmd = ($options{'gpg'}, qw(--decrypt), $file); + log_verbose("Using GPG to open $file: [@cmd]"); + open $io, "-|", @cmd; + } else { + log_verbose("Opening $file..."); + open $io, '<', $file; + } + + # nothing to do if the open failed (we log the error later) + return unless $io; + + # Net::Netrc does this, but the functionality is merged with the file + # detection logic, so we have to extract just the part we need + my @netrc_entries = net_netrc_loader($io); + + # these entries will use the credential helper protocol token names + my @entries; + + foreach my $nentry (@netrc_entries) { + my %entry; + my $num_port; + + if (!defined $nentry->{machine}) { + next; + } + if (defined $nentry->{port} && $nentry->{port} =~ m/^\d+$/) { + $num_port = $nentry->{port}; + delete $nentry->{port}; + } + + # create the new entry for the credential helper protocol + $entry{$options{tmap}->{$_}} = $nentry->{$_} foreach keys %$nentry; + + # for "host X port Y" where Y is an integer (captured by + # $num_port above), set the host to "X:Y" + if (defined $entry{host} && defined $num_port) { + $entry{host} = join(':', $entry{host}, $num_port); + } + + push @entries, \%entry; + } + + return @entries; +} + +sub net_netrc_loader { + my $fh = shift @_; + my @entries; + my ($mach, $macdef, $tok, @tok); + + LINE: + while (<$fh>) { + undef $macdef if /\A\n\Z/; + + if ($macdef) { + next LINE; + } + + s/^\s*//; + chomp; + + while (length && s/^("((?:[^"]+|\\.)*)"|((?:[^\\\s]+|\\.)*))\s*//) { + (my $tok = $+) =~ s/\\(.)/$1/g; + push(@tok, $tok); + } + + TOKEN: + while (@tok) { + if ($tok[0] eq "default") { + shift(@tok); + $mach = { machine => undef }; + next TOKEN; + } + + $tok = shift(@tok); + + if ($tok eq "machine") { + my $host = shift @tok; + $mach = { machine => $host }; + push @entries, $mach; + } elsif (exists $options{tmap}->{$tok}) { + unless ($mach) { + log_debug("Skipping token $tok because no machine was given"); + next TOKEN; + } + + my $value = shift @tok; + unless (defined $value) { + log_debug("Token $tok had no value, skipping it."); + next TOKEN; + } + + # Following line added by rmerrell to remove '/' escape char in .netrc + $value =~ s/\/\\/\\/g; + $mach->{$tok} = $value; + } elsif ($tok eq "macdef") { # we ignore macros + next TOKEN unless $mach; + my $value = shift @tok; + $macdef = 1; + } + } + } + + return @entries; +} + +sub read_credential_data_from_stdin { + # the query: start with every token with no value + my %q = map { $_ => undef } values(%{$options{tmap}}); + + while (<STDIN>) { + next unless m/^([^=]+)=(.+)/; + + my ($token, $value) = ($1, $2); + die "Unknown search token $token" unless exists $q{$token}; + $q{$token} = $value; + log_debug("We were given search token $token and value $value"); + } + + foreach (sort keys %q) { + log_debug("Searching for %s = %s", $_, $q{$_} || '(any value)'); + } + + return \%q; +} + +# takes the search tokens and then a list of entries +# each entry is a hash reference +sub find_netrc_entry { + my $query = shift @_; + + ENTRY: + foreach my $entry (@_) + { + my $entry_text = join ', ', map { "$_=$entry->{$_}" } keys %$entry; + foreach my $check (sort keys %$query) { + if (!defined $entry->{$check}) { + log_debug("OK: entry has no $check token, so any value satisfies check $check"); + } elsif (defined $query->{$check}) { + log_debug("compare %s [%s] to [%s] (entry: %s)", + $check, + $entry->{$check}, + $query->{$check}, + $entry_text); + unless ($query->{$check} eq $entry->{$check}) { + next ENTRY; + } + } else { + log_debug("OK: any value satisfies check $check"); + } + } + + return $entry; + } + + # nothing was found + return; +} + +sub print_credential_data { + my $entry = shift @_; + my $query = shift @_; + + log_debug("entry has passed all the search checks"); + TOKEN: + foreach my $git_token (sort keys %$entry) { + log_debug("looking for useful token $git_token"); + # don't print unknown (to the credential helper protocol) tokens + next TOKEN unless exists $query->{$git_token}; + + # don't print things asked in the query (the entry matches them) + next TOKEN if defined $query->{$git_token}; + + log_debug("FOUND: $git_token=$entry->{$git_token}"); + printf "%s=%s\n", $git_token, $entry->{$git_token}; + } +} +sub load_config { + # load settings from git config + my $options = shift; + # set from command argument, gpg.program option, or default to gpg + $options->{'gpg'} //= Git->repository()->config('gpg.program') + // 'gpg'; + log_verbose("using $options{'gpg'} for GPG operations"); +} +sub log_verbose { + return unless $options{verbose}; + printf STDERR @_; + printf STDERR "\n"; +} + +sub log_debug { + return unless $options{debug}; + printf STDERR @_; + printf STDERR "\n"; +} diff --git a/contrib/credential/netrc/t-git-credential-netrc.sh b/contrib/credential/netrc/t-git-credential-netrc.sh new file mode 100755 index 000000000000..07227d022876 --- /dev/null +++ b/contrib/credential/netrc/t-git-credential-netrc.sh @@ -0,0 +1,32 @@ +#!/bin/sh +( + cd ../../../t + test_description='git-credential-netrc' + . ./test-lib.sh + + if ! test_have_prereq PERL; then + skip_all='skipping perl interface tests, perl not available' + test_done + fi + + perl -MTest::More -e 0 2>/dev/null || { + skip_all="Perl Test::More unavailable, skipping test" + test_done + } + + # set up test repository + + test_expect_success \ + 'set up test repository' \ + 'git config --add gpg.program test.git-config-gpg' + + # The external test will outputs its own plan + test_external_has_tap=1 + + export PERL5LIB="$GITPERLLIB" + test_external \ + 'git-credential-netrc' \ + perl "$GIT_BUILD_DIR"/contrib/credential/netrc/test.pl + + test_done +) diff --git a/contrib/credential/netrc/test.command-option-gpg b/contrib/credential/netrc/test.command-option-gpg new file mode 100755 index 000000000000..d8f1285d416d --- /dev/null +++ b/contrib/credential/netrc/test.command-option-gpg @@ -0,0 +1,2 @@ +#!/bin/sh +echo machine command-option-gpg login username password password diff --git a/contrib/credential/netrc/test.git-config-gpg b/contrib/credential/netrc/test.git-config-gpg new file mode 100755 index 000000000000..65cf594c2001 --- /dev/null +++ b/contrib/credential/netrc/test.git-config-gpg @@ -0,0 +1,2 @@ +#!/bin/sh +echo machine git-config-gpg login username password password diff --git a/contrib/credential/netrc/test.netrc b/contrib/credential/netrc/test.netrc new file mode 100644 index 000000000000..ba119a937f67 --- /dev/null +++ b/contrib/credential/netrc/test.netrc @@ -0,0 +1,13 @@ +machine imap login tzz@lifelogs.com port imaps password letmeknow +machine imap login bob port imaps password bobwillknow + +# comment test + +machine imap2 login tzz port 1099 password tzzknow +machine imap2 login bob password bobwillknow + +# another command + +machine github.com + multilinetoken anothervalue + login carol password carolknows diff --git a/contrib/credential/netrc/test.netrc.gpg b/contrib/credential/netrc/test.netrc.gpg new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/contrib/credential/netrc/test.netrc.gpg diff --git a/contrib/credential/netrc/test.pl b/contrib/credential/netrc/test.pl new file mode 100755 index 000000000000..c0fb3718b280 --- /dev/null +++ b/contrib/credential/netrc/test.pl @@ -0,0 +1,139 @@ +#!/usr/bin/perl + +use warnings; +use strict; +use Test::More qw(no_plan); +use File::Basename; +use File::Spec::Functions qw(:DEFAULT rel2abs); +use IPC::Open2; + +BEGIN { + # t-git-credential-netrc.sh kicks off our testing, so we have to go + # from there. + Test::More->builder->current_test(1); +} + +my @global_credential_args = @ARGV; +my $scriptDir = dirname rel2abs $0; +my ($netrc, $netrcGpg, $gcNetrc) = map { catfile $scriptDir, $_; } + qw(test.netrc + test.netrc.gpg + git-credential-netrc); +local $ENV{PATH} = join ':' + , $scriptDir + , $ENV{PATH} + ? $ENV{PATH} + : (); + +diag "Testing insecure file, nothing should be found\n"; +chmod 0644, $netrc; +my $cred = run_credential(['-f', $netrc, 'get'], + { host => 'github.com' }); + +ok(scalar keys %$cred == 0, "Got 0 keys from insecure file"); + +diag "Testing missing file, nothing should be found\n"; +chmod 0644, $netrc; +$cred = run_credential(['-f', '///nosuchfile///', 'get'], + { host => 'github.com' }); + +ok(scalar keys %$cred == 0, "Got 0 keys from missing file"); + +chmod 0600, $netrc; + +diag "Testing with invalid data\n"; +$cred = run_credential(['-f', $netrc, 'get'], + "bad data"); +ok(scalar keys %$cred == 4, "Got first found keys with bad data"); + +diag "Testing netrc file for a missing corovamilkbar entry\n"; +$cred = run_credential(['-f', $netrc, 'get'], + { host => 'corovamilkbar' }); + +ok(scalar keys %$cred == 0, "Got no corovamilkbar keys"); + +diag "Testing netrc file for a github.com entry\n"; +$cred = run_credential(['-f', $netrc, 'get'], + { host => 'github.com' }); + +ok(scalar keys %$cred == 2, "Got 2 Github keys"); + +is($cred->{password}, 'carolknows', "Got correct Github password"); +is($cred->{username}, 'carol', "Got correct Github username"); + +diag "Testing netrc file for a username-specific entry\n"; +$cred = run_credential(['-f', $netrc, 'get'], + { host => 'imap', username => 'bob' }); + +ok(scalar keys %$cred == 2, "Got 2 username-specific keys"); + +is($cred->{password}, 'bobwillknow', "Got correct user-specific password"); +is($cred->{protocol}, 'imaps', "Got correct user-specific protocol"); + +diag "Testing netrc file for a host:port-specific entry\n"; +$cred = run_credential(['-f', $netrc, 'get'], + { host => 'imap2:1099' }); + +ok(scalar keys %$cred == 2, "Got 2 host:port-specific keys"); + +is($cred->{password}, 'tzzknow', "Got correct host:port-specific password"); +is($cred->{username}, 'tzz', "Got correct host:port-specific username"); + +diag "Testing netrc file that 'host:port kills host' entry\n"; +$cred = run_credential(['-f', $netrc, 'get'], + { host => 'imap2' }); + +ok(scalar keys %$cred == 2, "Got 2 'host:port kills host' keys"); + +is($cred->{password}, 'bobwillknow', "Got correct 'host:port kills host' password"); +is($cred->{username}, 'bob', "Got correct 'host:port kills host' username"); + +diag 'Testing netrc file decryption by git config gpg.program setting\n'; +$cred = run_credential( ['-f', $netrcGpg, 'get'] + , { host => 'git-config-gpg' } + ); + +ok(scalar keys %$cred == 2, 'Got keys decrypted by git config option'); + +diag 'Testing netrc file decryption by gpg option\n'; +$cred = run_credential( ['-f', $netrcGpg, '-g', 'test.command-option-gpg', 'get'] + , { host => 'command-option-gpg' } + ); + +ok(scalar keys %$cred == 2, 'Got keys decrypted by command option'); + +my $is_passing = eval { Test::More->is_passing }; +exit($is_passing ? 0 : 1) unless $@ =~ /Can't locate object method/; + +sub run_credential +{ + my $args = shift @_; + my $data = shift @_; + my $pid = open2(my $chld_out, my $chld_in, + $gcNetrc, @global_credential_args, + @$args); + + die "Couldn't open pipe to netrc credential helper: $!" unless $pid; + + if (ref $data eq 'HASH') + { + print $chld_in "$_=$data->{$_}\n" foreach sort keys %$data; + } + else + { + print $chld_in "$data\n"; + } + + close $chld_in; + my %ret; + + while (<$chld_out>) + { + chomp; + next unless m/^([^=]+)=(.+)/; + + $ret{$1} = $2; + } + + return \%ret; +} diff --git a/contrib/credential/osxkeychain/.gitignore b/contrib/credential/osxkeychain/.gitignore new file mode 100644 index 000000000000..6c5b7026c53d --- /dev/null +++ b/contrib/credential/osxkeychain/.gitignore @@ -0,0 +1 @@ +git-credential-osxkeychain diff --git a/contrib/credential/osxkeychain/Makefile b/contrib/credential/osxkeychain/Makefile new file mode 100644 index 000000000000..4b3a08a2bac4 --- /dev/null +++ b/contrib/credential/osxkeychain/Makefile @@ -0,0 +1,17 @@ +all:: git-credential-osxkeychain + +CC = gcc +RM = rm -f +CFLAGS = -g -O2 -Wall + +-include ../../../config.mak.autogen +-include ../../../config.mak + +git-credential-osxkeychain: git-credential-osxkeychain.o + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) -Wl,-framework -Wl,Security + +git-credential-osxkeychain.o: git-credential-osxkeychain.c + $(CC) -c $(CFLAGS) $< + +clean: + $(RM) git-credential-osxkeychain git-credential-osxkeychain.o diff --git a/contrib/credential/osxkeychain/git-credential-osxkeychain.c b/contrib/credential/osxkeychain/git-credential-osxkeychain.c new file mode 100644 index 000000000000..bcd3f575a3e3 --- /dev/null +++ b/contrib/credential/osxkeychain/git-credential-osxkeychain.c @@ -0,0 +1,183 @@ +#include <stdio.h> +#include <string.h> +#include <stdlib.h> +#include <Security/Security.h> + +static SecProtocolType protocol; +static char *host; +static char *path; +static char *username; +static char *password; +static UInt16 port; + +static void die(const char *err, ...) +{ + char msg[4096]; + va_list params; + va_start(params, err); + vsnprintf(msg, sizeof(msg), err, params); + fprintf(stderr, "%s\n", msg); + va_end(params); + exit(1); +} + +static void *xstrdup(const char *s1) +{ + void *ret = strdup(s1); + if (!ret) + die("Out of memory"); + return ret; +} + +#define KEYCHAIN_ITEM(x) (x ? strlen(x) : 0), x +#define KEYCHAIN_ARGS \ + NULL, /* default keychain */ \ + KEYCHAIN_ITEM(host), \ + 0, NULL, /* account domain */ \ + KEYCHAIN_ITEM(username), \ + KEYCHAIN_ITEM(path), \ + port, \ + protocol, \ + kSecAuthenticationTypeDefault + +static void write_item(const char *what, const char *buf, int len) +{ + printf("%s=", what); + fwrite(buf, 1, len, stdout); + putchar('\n'); +} + +static void find_username_in_item(SecKeychainItemRef item) +{ + SecKeychainAttributeList list; + SecKeychainAttribute attr; + + list.count = 1; + list.attr = &attr; + attr.tag = kSecAccountItemAttr; + + if (SecKeychainItemCopyContent(item, NULL, &list, NULL, NULL)) + return; + + write_item("username", attr.data, attr.length); + SecKeychainItemFreeContent(&list, NULL); +} + +static void find_internet_password(void) +{ + void *buf; + UInt32 len; + SecKeychainItemRef item; + + if (SecKeychainFindInternetPassword(KEYCHAIN_ARGS, &len, &buf, &item)) + return; + + write_item("password", buf, len); + if (!username) + find_username_in_item(item); + + SecKeychainItemFreeContent(NULL, buf); +} + +static void delete_internet_password(void) +{ + SecKeychainItemRef item; + + /* + * Require at least a protocol and host for removal, which is what git + * will give us; if you want to do something more fancy, use the + * Keychain manager. + */ + if (!protocol || !host) + return; + + if (SecKeychainFindInternetPassword(KEYCHAIN_ARGS, 0, NULL, &item)) + return; + + SecKeychainItemDelete(item); +} + +static void add_internet_password(void) +{ + /* Only store complete credentials */ + if (!protocol || !host || !username || !password) + return; + + if (SecKeychainAddInternetPassword( + KEYCHAIN_ARGS, + KEYCHAIN_ITEM(password), + NULL)) + return; +} + +static void read_credential(void) +{ + char buf[1024]; + + while (fgets(buf, sizeof(buf), stdin)) { + char *v; + + if (!strcmp(buf, "\n")) + break; + buf[strlen(buf)-1] = '\0'; + + v = strchr(buf, '='); + if (!v) + die("bad input: %s", buf); + *v++ = '\0'; + + if (!strcmp(buf, "protocol")) { + if (!strcmp(v, "imap")) + protocol = kSecProtocolTypeIMAP; + else if (!strcmp(v, "imaps")) + protocol = kSecProtocolTypeIMAPS; + else if (!strcmp(v, "ftp")) + protocol = kSecProtocolTypeFTP; + else if (!strcmp(v, "ftps")) + protocol = kSecProtocolTypeFTPS; + else if (!strcmp(v, "https")) + protocol = kSecProtocolTypeHTTPS; + else if (!strcmp(v, "http")) + protocol = kSecProtocolTypeHTTP; + else if (!strcmp(v, "smtp")) + protocol = kSecProtocolTypeSMTP; + else /* we don't yet handle other protocols */ + exit(0); + } + else if (!strcmp(buf, "host")) { + char *colon = strchr(v, ':'); + if (colon) { + *colon++ = '\0'; + port = atoi(colon); + } + host = xstrdup(v); + } + else if (!strcmp(buf, "path")) + path = xstrdup(v); + else if (!strcmp(buf, "username")) + username = xstrdup(v); + else if (!strcmp(buf, "password")) + password = xstrdup(v); + } +} + +int main(int argc, const char **argv) +{ + const char *usage = + "usage: git credential-osxkeychain <get|store|erase>"; + + if (!argv[1]) + die(usage); + + read_credential(); + + if (!strcmp(argv[1], "get")) + find_internet_password(); + else if (!strcmp(argv[1], "store")) + add_internet_password(); + else if (!strcmp(argv[1], "erase")) + delete_internet_password(); + /* otherwise, ignore unknown action */ + + return 0; +} diff --git a/contrib/credential/wincred/Makefile b/contrib/credential/wincred/Makefile new file mode 100644 index 000000000000..6e992c08667d --- /dev/null +++ b/contrib/credential/wincred/Makefile @@ -0,0 +1,22 @@ +all: git-credential-wincred.exe + +-include ../../../config.mak.autogen +-include ../../../config.mak + +CC ?= gcc +RM ?= rm -f +CFLAGS ?= -O2 -Wall + +prefix ?= /usr/local +libexecdir ?= $(prefix)/libexec/git-core + +INSTALL ?= install + +git-credential-wincred.exe : git-credential-wincred.c + $(LINK.c) $^ $(LOADLIBES) $(LDLIBS) -o $@ + +install: git-credential-wincred.exe + $(INSTALL) -m 755 $^ $(libexecdir) + +clean: + $(RM) git-credential-wincred.exe diff --git a/contrib/credential/wincred/git-credential-wincred.c b/contrib/credential/wincred/git-credential-wincred.c new file mode 100644 index 000000000000..5bdad41de1f8 --- /dev/null +++ b/contrib/credential/wincred/git-credential-wincred.c @@ -0,0 +1,327 @@ +/* + * A git credential helper that interface with Windows' Credential Manager + * + */ +#include <windows.h> +#include <stdio.h> +#include <io.h> +#include <fcntl.h> + +/* common helpers */ + +#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0])) + +static void die(const char *err, ...) +{ + char msg[4096]; + va_list params; + va_start(params, err); + vsnprintf(msg, sizeof(msg), err, params); + fprintf(stderr, "%s\n", msg); + va_end(params); + exit(1); +} + +static void *xmalloc(size_t size) +{ + void *ret = malloc(size); + if (!ret && !size) + ret = malloc(1); + if (!ret) + die("Out of memory"); + return ret; +} + +/* MinGW doesn't have wincred.h, so we need to define stuff */ + +typedef struct _CREDENTIAL_ATTRIBUTEW { + LPWSTR Keyword; + DWORD Flags; + DWORD ValueSize; + LPBYTE Value; +} CREDENTIAL_ATTRIBUTEW, *PCREDENTIAL_ATTRIBUTEW; + +typedef struct _CREDENTIALW { + DWORD Flags; + DWORD Type; + LPWSTR TargetName; + LPWSTR Comment; + FILETIME LastWritten; + DWORD CredentialBlobSize; + LPBYTE CredentialBlob; + DWORD Persist; + DWORD AttributeCount; + PCREDENTIAL_ATTRIBUTEW Attributes; + LPWSTR TargetAlias; + LPWSTR UserName; +} CREDENTIALW, *PCREDENTIALW; + +#define CRED_TYPE_GENERIC 1 +#define CRED_PERSIST_LOCAL_MACHINE 2 +#define CRED_MAX_ATTRIBUTES 64 + +typedef BOOL (WINAPI *CredWriteWT)(PCREDENTIALW, DWORD); +typedef BOOL (WINAPI *CredEnumerateWT)(LPCWSTR, DWORD, DWORD *, + PCREDENTIALW **); +typedef VOID (WINAPI *CredFreeT)(PVOID); +typedef BOOL (WINAPI *CredDeleteWT)(LPCWSTR, DWORD, DWORD); + +static HMODULE advapi; +static CredWriteWT CredWriteW; +static CredEnumerateWT CredEnumerateW; +static CredFreeT CredFree; +static CredDeleteWT CredDeleteW; + +static void load_cred_funcs(void) +{ + /* load DLLs */ + advapi = LoadLibraryExA("advapi32.dll", NULL, + LOAD_LIBRARY_SEARCH_SYSTEM32); + if (!advapi) + die("failed to load advapi32.dll"); + + /* get function pointers */ + CredWriteW = (CredWriteWT)GetProcAddress(advapi, "CredWriteW"); + CredEnumerateW = (CredEnumerateWT)GetProcAddress(advapi, + "CredEnumerateW"); + CredFree = (CredFreeT)GetProcAddress(advapi, "CredFree"); + CredDeleteW = (CredDeleteWT)GetProcAddress(advapi, "CredDeleteW"); + if (!CredWriteW || !CredEnumerateW || !CredFree || !CredDeleteW) + die("failed to load functions"); +} + +static WCHAR *wusername, *password, *protocol, *host, *path, target[1024]; + +static void write_item(const char *what, LPCWSTR wbuf, int wlen) +{ + char *buf; + + if (!wbuf || !wlen) { + printf("%s=\n", what); + return; + } + + int len = WideCharToMultiByte(CP_UTF8, 0, wbuf, wlen, NULL, 0, NULL, + FALSE); + buf = xmalloc(len); + + if (!WideCharToMultiByte(CP_UTF8, 0, wbuf, wlen, buf, len, NULL, FALSE)) + die("WideCharToMultiByte failed!"); + + printf("%s=", what); + fwrite(buf, 1, len, stdout); + putchar('\n'); + free(buf); +} + +/* + * Match an (optional) expected string and a delimiter in the target string, + * consuming the matched text by updating the target pointer. + */ + +static LPCWSTR wcsstr_last(LPCWSTR str, LPCWSTR find) +{ + LPCWSTR res = NULL, pos; + for (pos = wcsstr(str, find); pos; pos = wcsstr(pos + 1, find)) + res = pos; + return res; +} + +static int match_part_with_last(LPCWSTR *ptarget, LPCWSTR want, LPCWSTR delim, int last) +{ + LPCWSTR delim_pos, start = *ptarget; + int len; + + /* find start of delimiter (or end-of-string if delim is empty) */ + if (*delim) + delim_pos = last ? wcsstr_last(start, delim) : wcsstr(start, delim); + else + delim_pos = start + wcslen(start); + + /* + * match text up to delimiter, or end of string (e.g. the '/' after + * host is optional if not followed by a path) + */ + if (delim_pos) + len = delim_pos - start; + else + len = wcslen(start); + + /* update ptarget if we either found a delimiter or need a match */ + if (delim_pos || want) + *ptarget = delim_pos ? delim_pos + wcslen(delim) : start + len; + + return !want || (!wcsncmp(want, start, len) && !want[len]); +} + +static int match_part(LPCWSTR *ptarget, LPCWSTR want, LPCWSTR delim) +{ + return match_part_with_last(ptarget, want, delim, 0); +} + +static int match_part_last(LPCWSTR *ptarget, LPCWSTR want, LPCWSTR delim) +{ + return match_part_with_last(ptarget, want, delim, 1); +} + +static int match_cred(const CREDENTIALW *cred) +{ + LPCWSTR target = cred->TargetName; + if (wusername && wcscmp(wusername, cred->UserName ? cred->UserName : L"")) + return 0; + + return match_part(&target, L"git", L":") && + match_part(&target, protocol, L"://") && + match_part_last(&target, wusername, L"@") && + match_part(&target, host, L"/") && + match_part(&target, path, L""); +} + +static void get_credential(void) +{ + CREDENTIALW **creds; + DWORD num_creds; + int i; + + if (!CredEnumerateW(L"git:*", 0, &num_creds, &creds)) + return; + + /* search for the first credential that matches username */ + for (i = 0; i < num_creds; ++i) + if (match_cred(creds[i])) { + write_item("username", creds[i]->UserName, + creds[i]->UserName ? wcslen(creds[i]->UserName) : 0); + write_item("password", + (LPCWSTR)creds[i]->CredentialBlob, + creds[i]->CredentialBlobSize / sizeof(WCHAR)); + break; + } + + CredFree(creds); +} + +static void store_credential(void) +{ + CREDENTIALW cred; + + if (!wusername || !password) + return; + + cred.Flags = 0; + cred.Type = CRED_TYPE_GENERIC; + cred.TargetName = target; + cred.Comment = L"saved by git-credential-wincred"; + cred.CredentialBlobSize = (wcslen(password)) * sizeof(WCHAR); + cred.CredentialBlob = (LPVOID)password; + cred.Persist = CRED_PERSIST_LOCAL_MACHINE; + cred.AttributeCount = 0; + cred.Attributes = NULL; + cred.TargetAlias = NULL; + cred.UserName = wusername; + + if (!CredWriteW(&cred, 0)) + die("CredWrite failed"); +} + +static void erase_credential(void) +{ + CREDENTIALW **creds; + DWORD num_creds; + int i; + + if (!CredEnumerateW(L"git:*", 0, &num_creds, &creds)) + return; + + for (i = 0; i < num_creds; ++i) { + if (match_cred(creds[i])) + CredDeleteW(creds[i]->TargetName, creds[i]->Type, 0); + } + + CredFree(creds); +} + +static WCHAR *utf8_to_utf16_dup(const char *str) +{ + int wlen = MultiByteToWideChar(CP_UTF8, 0, str, -1, NULL, 0); + WCHAR *wstr = xmalloc(sizeof(WCHAR) * wlen); + MultiByteToWideChar(CP_UTF8, 0, str, -1, wstr, wlen); + return wstr; +} + +static void read_credential(void) +{ + char buf[1024]; + + while (fgets(buf, sizeof(buf), stdin)) { + char *v; + int len = strlen(buf); + /* strip trailing CR / LF */ + while (len && strchr("\r\n", buf[len - 1])) + buf[--len] = 0; + + if (!*buf) + break; + + v = strchr(buf, '='); + if (!v) + die("bad input: %s", buf); + *v++ = '\0'; + + if (!strcmp(buf, "protocol")) + protocol = utf8_to_utf16_dup(v); + else if (!strcmp(buf, "host")) + host = utf8_to_utf16_dup(v); + else if (!strcmp(buf, "path")) + path = utf8_to_utf16_dup(v); + else if (!strcmp(buf, "username")) { + wusername = utf8_to_utf16_dup(v); + } else if (!strcmp(buf, "password")) + password = utf8_to_utf16_dup(v); + else + die("unrecognized input"); + } +} + +int main(int argc, char *argv[]) +{ + const char *usage = + "usage: git credential-wincred <get|store|erase>\n"; + + if (!argv[1]) + die(usage); + + /* git use binary pipes to avoid CRLF-issues */ + _setmode(_fileno(stdin), _O_BINARY); + _setmode(_fileno(stdout), _O_BINARY); + + read_credential(); + + load_cred_funcs(); + + if (!protocol || !(host || path)) + return 0; + + /* prepare 'target', the unique key for the credential */ + wcscpy(target, L"git:"); + wcsncat(target, protocol, ARRAY_SIZE(target)); + wcsncat(target, L"://", ARRAY_SIZE(target)); + if (wusername) { + wcsncat(target, wusername, ARRAY_SIZE(target)); + wcsncat(target, L"@", ARRAY_SIZE(target)); + } + if (host) + wcsncat(target, host, ARRAY_SIZE(target)); + if (path) { + wcsncat(target, L"/", ARRAY_SIZE(target)); + wcsncat(target, path, ARRAY_SIZE(target)); + } + + if (!strcmp(argv[1], "get")) + get_credential(); + else if (!strcmp(argv[1], "store")) + store_credential(); + else if (!strcmp(argv[1], "erase")) + erase_credential(); + /* otherwise, ignore unknown action */ + return 0; +} diff --git a/contrib/diff-highlight/.gitignore b/contrib/diff-highlight/.gitignore new file mode 100644 index 000000000000..c07454824e3a --- /dev/null +++ b/contrib/diff-highlight/.gitignore @@ -0,0 +1,2 @@ +shebang.perl +diff-highlight diff --git a/contrib/diff-highlight/DiffHighlight.pm b/contrib/diff-highlight/DiffHighlight.pm new file mode 100644 index 000000000000..7440aa1c4638 --- /dev/null +++ b/contrib/diff-highlight/DiffHighlight.pm @@ -0,0 +1,285 @@ +package DiffHighlight; + +use 5.008; +use warnings FATAL => 'all'; +use strict; + +# Use the correct value for both UNIX and Windows (/dev/null vs nul) +use File::Spec; + +my $NULL = File::Spec->devnull(); + +# Highlight by reversing foreground and background. You could do +# other things like bold or underline if you prefer. +my @OLD_HIGHLIGHT = ( + color_config('color.diff-highlight.oldnormal'), + color_config('color.diff-highlight.oldhighlight', "\x1b[7m"), + color_config('color.diff-highlight.oldreset', "\x1b[27m") +); +my @NEW_HIGHLIGHT = ( + color_config('color.diff-highlight.newnormal', $OLD_HIGHLIGHT[0]), + color_config('color.diff-highlight.newhighlight', $OLD_HIGHLIGHT[1]), + color_config('color.diff-highlight.newreset', $OLD_HIGHLIGHT[2]) +); + +my $RESET = "\x1b[m"; +my $COLOR = qr/\x1b\[[0-9;]*m/; +my $BORING = qr/$COLOR|\s/; + +my @removed; +my @added; +my $in_hunk; +my $graph_indent = 0; + +our $line_cb = sub { print @_ }; +our $flush_cb = sub { local $| = 1 }; + +# Count the visible width of a string, excluding any terminal color sequences. +sub visible_width { + local $_ = shift; + my $ret = 0; + while (length) { + if (s/^$COLOR//) { + # skip colors + } elsif (s/^.//) { + $ret++; + } + } + return $ret; +} + +# Return a substring of $str, omitting $len visible characters from the +# beginning, where terminal color sequences do not count as visible. +sub visible_substr { + my ($str, $len) = @_; + while ($len > 0) { + if ($str =~ s/^$COLOR//) { + next + } + $str =~ s/^.//; + $len--; + } + return $str; +} + +sub handle_line { + my $orig = shift; + local $_ = $orig; + + # match a graph line that begins a commit + if (/^(?:$COLOR?\|$COLOR?[ ])* # zero or more leading "|" with space + $COLOR?\*$COLOR?[ ] # a "*" with its trailing space + (?:$COLOR?\|$COLOR?[ ])* # zero or more trailing "|" + [ ]* # trailing whitespace for merges + /x) { + my $graph_prefix = $&; + + # We must flush before setting graph indent, since the + # new commit may be indented differently from what we + # queued. + flush(); + $graph_indent = visible_width($graph_prefix); + + } elsif ($graph_indent) { + if (length($_) < $graph_indent) { + $graph_indent = 0; + } else { + $_ = visible_substr($_, $graph_indent); + } + } + + if (!$in_hunk) { + $line_cb->($orig); + $in_hunk = /^$COLOR*\@\@ /; + } + elsif (/^$COLOR*-/) { + push @removed, $orig; + } + elsif (/^$COLOR*\+/) { + push @added, $orig; + } + else { + flush(); + $line_cb->($orig); + $in_hunk = /^$COLOR*[\@ ]/; + } + + # Most of the time there is enough output to keep things streaming, + # but for something like "git log -Sfoo", you can get one early + # commit and then many seconds of nothing. We want to show + # that one commit as soon as possible. + # + # Since we can receive arbitrary input, there's no optimal + # place to flush. Flushing on a blank line is a heuristic that + # happens to match git-log output. + if (!length) { + $flush_cb->(); + } +} + +sub flush { + # Flush any queued hunk (this can happen when there is no trailing + # context in the final diff of the input). + show_hunk(\@removed, \@added); + @removed = (); + @added = (); +} + +sub highlight_stdin { + while (<STDIN>) { + handle_line($_); + } + flush(); +} + +# Ideally we would feed the default as a human-readable color to +# git-config as the fallback value. But diff-highlight does +# not otherwise depend on git at all, and there are reports +# of it being used in other settings. Let's handle our own +# fallback, which means we will work even if git can't be run. +sub color_config { + my ($key, $default) = @_; + my $s = `git config --get-color $key 2>$NULL`; + return length($s) ? $s : $default; +} + +sub show_hunk { + my ($a, $b) = @_; + + # If one side is empty, then there is nothing to compare or highlight. + if (!@$a || !@$b) { + $line_cb->(@$a, @$b); + return; + } + + # If we have mismatched numbers of lines on each side, we could try to + # be clever and match up similar lines. But for now we are simple and + # stupid, and only handle multi-line hunks that remove and add the same + # number of lines. + if (@$a != @$b) { + $line_cb->(@$a, @$b); + return; + } + + my @queue; + for (my $i = 0; $i < @$a; $i++) { + my ($rm, $add) = highlight_pair($a->[$i], $b->[$i]); + $line_cb->($rm); + push @queue, $add; + } + $line_cb->(@queue); +} + +sub highlight_pair { + my @a = split_line(shift); + my @b = split_line(shift); + + # Find common prefix, taking care to skip any ansi + # color codes. + my $seen_plusminus; + my ($pa, $pb) = (0, 0); + while ($pa < @a && $pb < @b) { + if ($a[$pa] =~ /$COLOR/) { + $pa++; + } + elsif ($b[$pb] =~ /$COLOR/) { + $pb++; + } + elsif ($a[$pa] eq $b[$pb]) { + $pa++; + $pb++; + } + elsif (!$seen_plusminus && $a[$pa] eq '-' && $b[$pb] eq '+') { + $seen_plusminus = 1; + $pa++; + $pb++; + } + else { + last; + } + } + + # Find common suffix, ignoring colors. + my ($sa, $sb) = ($#a, $#b); + while ($sa >= $pa && $sb >= $pb) { + if ($a[$sa] =~ /$COLOR/) { + $sa--; + } + elsif ($b[$sb] =~ /$COLOR/) { + $sb--; + } + elsif ($a[$sa] eq $b[$sb]) { + $sa--; + $sb--; + } + else { + last; + } + } + + if (is_pair_interesting(\@a, $pa, $sa, \@b, $pb, $sb)) { + return highlight_line(\@a, $pa, $sa, \@OLD_HIGHLIGHT), + highlight_line(\@b, $pb, $sb, \@NEW_HIGHLIGHT); + } + else { + return join('', @a), + join('', @b); + } +} + +# we split either by $COLOR or by character. This has the side effect of +# leaving in graph cruft. It works because the graph cruft does not contain "-" +# or "+" +sub split_line { + local $_ = shift; + return utf8::decode($_) ? + map { utf8::encode($_); $_ } + map { /$COLOR/ ? $_ : (split //) } + split /($COLOR+)/ : + map { /$COLOR/ ? $_ : (split //) } + split /($COLOR+)/; +} + +sub highlight_line { + my ($line, $prefix, $suffix, $theme) = @_; + + my $start = join('', @{$line}[0..($prefix-1)]); + my $mid = join('', @{$line}[$prefix..$suffix]); + my $end = join('', @{$line}[($suffix+1)..$#$line]); + + # If we have a "normal" color specified, then take over the whole line. + # Otherwise, we try to just manipulate the highlighted bits. + if (defined $theme->[0]) { + s/$COLOR//g for ($start, $mid, $end); + chomp $end; + return join('', + $theme->[0], $start, $RESET, + $theme->[1], $mid, $RESET, + $theme->[0], $end, $RESET, + "\n" + ); + } else { + return join('', + $start, + $theme->[1], $mid, $theme->[2], + $end + ); + } +} + +# Pairs are interesting to highlight only if we are going to end up +# highlighting a subset (i.e., not the whole line). Otherwise, the highlighting +# is just useless noise. We can detect this by finding either a matching prefix +# or suffix (disregarding boring bits like whitespace and colorization). +sub is_pair_interesting { + my ($a, $pa, $sa, $b, $pb, $sb) = @_; + my $prefix_a = join('', @$a[0..($pa-1)]); + my $prefix_b = join('', @$b[0..($pb-1)]); + my $suffix_a = join('', @$a[($sa+1)..$#$a]); + my $suffix_b = join('', @$b[($sb+1)..$#$b]); + + return visible_substr($prefix_a, $graph_indent) !~ /^$COLOR*-$BORING*$/ || + visible_substr($prefix_b, $graph_indent) !~ /^$COLOR*\+$BORING*$/ || + $suffix_a !~ /^$BORING*$/ || + $suffix_b !~ /^$BORING*$/; +} diff --git a/contrib/diff-highlight/Makefile b/contrib/diff-highlight/Makefile new file mode 100644 index 000000000000..f2be7cc92437 --- /dev/null +++ b/contrib/diff-highlight/Makefile @@ -0,0 +1,23 @@ +all: diff-highlight + +PERL_PATH = /usr/bin/perl +-include ../../config.mak + +PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH)) + +diff-highlight: shebang.perl DiffHighlight.pm diff-highlight.perl + cat $^ >$@+ + chmod +x $@+ + mv $@+ $@ + +shebang.perl: FORCE + @echo '#!$(PERL_PATH_SQ)' >$@+ + @cmp $@+ $@ >/dev/null 2>/dev/null || mv $@+ $@ + +test: all + $(MAKE) -C t + +clean: + $(RM) diff-highlight + +.PHONY: FORCE diff --git a/contrib/diff-highlight/README b/contrib/diff-highlight/README new file mode 100644 index 000000000000..d4c234317520 --- /dev/null +++ b/contrib/diff-highlight/README @@ -0,0 +1,223 @@ +diff-highlight +============== + +Line oriented diffs are great for reviewing code, because for most +hunks, you want to see the old and the new segments of code next to each +other. Sometimes, though, when an old line and a new line are very +similar, it's hard to immediately see the difference. + +You can use "--color-words" to highlight only the changed portions of +lines. However, this can often be hard to read for code, as it loses +the line structure, and you end up with oddly formatted bits. + +Instead, this script post-processes the line-oriented diff, finds pairs +of lines, and highlights the differing segments. It's currently very +simple and stupid about doing these tasks. In particular: + + 1. It will only highlight hunks in which the number of removed and + added lines is the same, and it will pair lines within the hunk by + position (so the first removed line is compared to the first added + line, and so forth). This is simple and tends to work well in + practice. More complex changes don't highlight well, so we tend to + exclude them due to the "same number of removed and added lines" + restriction. Or even if we do try to highlight them, they end up + not highlighting because of our "don't highlight if the whole line + would be highlighted" rule. + + 2. It will find the common prefix and suffix of two lines, and + consider everything in the middle to be "different". It could + instead do a real diff of the characters between the two lines and + find common subsequences. However, the point of the highlight is to + call attention to a certain area. Even if some small subset of the + highlighted area actually didn't change, that's OK. In practice it + ends up being more readable to just have a single blob on the line + showing the interesting bit. + +The goal of the script is therefore not to be exact about highlighting +changes, but to call attention to areas of interest without being +visually distracting. Non-diff lines and existing diff coloration is +preserved; the intent is that the output should look exactly the same as +the input, except for the occasional highlight. + +Use +--- + +You can try out the diff-highlight program with: + +--------------------------------------------- +git log -p --color | /path/to/diff-highlight +--------------------------------------------- + +If you want to use it all the time, drop it in your $PATH and put the +following in your git configuration: + +--------------------------------------------- +[pager] + log = diff-highlight | less + show = diff-highlight | less + diff = diff-highlight | less +--------------------------------------------- + + +Color Config +------------ + +You can configure the highlight colors and attributes using git's +config. The colors for "old" and "new" lines can be specified +independently. There are two "modes" of configuration: + + 1. You can specify a "highlight" color and a matching "reset" color. + This will retain any existing colors in the diff, and apply the + "highlight" and "reset" colors before and after the highlighted + portion. + + 2. You can specify a "normal" color and a "highlight" color. In this + case, existing colors are dropped from that line. The non-highlighted + bits of the line get the "normal" color, and the highlights get the + "highlight" color. + +If no "new" colors are specified, they default to the "old" colors. If +no "old" colors are specified, the default is to reverse the foreground +and background for highlighted portions. + +Examples: + +--------------------------------------------- +# Underline highlighted portions +[color "diff-highlight"] +oldHighlight = ul +oldReset = noul +--------------------------------------------- + +--------------------------------------------- +# Varying background intensities +[color "diff-highlight"] +oldNormal = "black #f8cbcb" +oldHighlight = "black #ffaaaa" +newNormal = "black #cbeecb" +newHighlight = "black #aaffaa" +--------------------------------------------- + + +Using diff-highlight as a module +-------------------------------- + +If you want to pre- or post- process the highlighted lines as part of +another perl script, you can use the DiffHighlight module. You can +either "require" it or just cat the module together with your script (to +avoid run-time dependencies). + +Your script may set up one or more of the following variables: + + - $DiffHighlight::line_cb - this should point to a function which is + called whenever DiffHighlight has lines (which may contain + highlights) to output. The default function prints each line to + stdout. Note that the function may be called with multiple lines. + + - $DiffHighlight::flush_cb - this should point to a function which + flushes the output (because DiffHighlight believes it has completed + processing a logical chunk of input). The default function flushes + stdout. + +The script may then feed lines, one at a time, to DiffHighlight::handle_line(). +When lines are done processing, they will be fed to $line_cb. Note that +DiffHighlight may queue up many input lines (to analyze a whole hunk) +before calling $line_cb. After providing all lines, call +DiffHighlight::flush() to flush any unprocessed lines. + +If you just want to process stdin, DiffHighlight::highlight_stdin() +is a convenience helper which will loop and flush for you. + + +Bugs +---- + +Because diff-highlight relies on heuristics to guess which parts of +changes are important, there are some cases where the highlighting is +more distracting than useful. Fortunately, these cases are rare in +practice, and when they do occur, the worst case is simply a little +extra highlighting. This section documents some cases known to be +sub-optimal, in case somebody feels like working on improving the +heuristics. + +1. Two changes on the same line get highlighted in a blob. For example, + highlighting: + +---------------------------------------------- +-foo(buf, size); ++foo(obj->buf, obj->size); +---------------------------------------------- + + yields (where the inside of "+{}" would be highlighted): + +---------------------------------------------- +-foo(buf, size); ++foo(+{obj->buf, obj->}size); +---------------------------------------------- + + whereas a more semantically meaningful output would be: + +---------------------------------------------- +-foo(buf, size); ++foo(+{obj->}buf, +{obj->}size); +---------------------------------------------- + + Note that doing this right would probably involve a set of + content-specific boundary patterns, similar to word-diff. Otherwise + you get junk like: + +----------------------------------------------------- +-this line has some -{i}nt-{ere}sti-{ng} text on it ++this line has some +{fa}nt+{a}sti+{c} text on it +----------------------------------------------------- + + which is less readable than the current output. + +2. The multi-line matching assumes that lines in the pre- and post-image + match by position. This is often the case, but can be fooled when a + line is removed from the top and a new one added at the bottom (or + vice versa). Unless the lines in the middle are also changed, diffs + will show this as two hunks, and it will not get highlighted at all + (which is good). But if the lines in the middle are changed, the + highlighting can be misleading. Here's a pathological case: + +----------------------------------------------------- +-one +-two +-three +-four ++two 2 ++three 3 ++four 4 ++five 5 +----------------------------------------------------- + + which gets highlighted as: + +----------------------------------------------------- +-one +-t-{wo} +-three +-f-{our} ++two 2 ++t+{hree 3} ++four 4 ++f+{ive 5} +----------------------------------------------------- + + because it matches "two" to "three 3", and so forth. It would be + nicer as: + +----------------------------------------------------- +-one +-two +-three +-four ++two +{2} ++three +{3} ++four +{4} ++five 5 +----------------------------------------------------- + + which would probably involve pre-matching the lines into pairs + according to some heuristic. diff --git a/contrib/diff-highlight/diff-highlight.perl b/contrib/diff-highlight/diff-highlight.perl new file mode 100644 index 000000000000..9b3e9c1f4d7b --- /dev/null +++ b/contrib/diff-highlight/diff-highlight.perl @@ -0,0 +1,8 @@ +package main; + +# Some scripts may not realize that SIGPIPE is being ignored when launching the +# pager--for instance scripts written in Python. +$SIG{PIPE} = 'DEFAULT'; + +DiffHighlight::highlight_stdin(); +exit 0; diff --git a/contrib/diff-highlight/t/.gitignore b/contrib/diff-highlight/t/.gitignore new file mode 100644 index 000000000000..7dcbb232cd87 --- /dev/null +++ b/contrib/diff-highlight/t/.gitignore @@ -0,0 +1,2 @@ +/trash directory* +/test-results diff --git a/contrib/diff-highlight/t/Makefile b/contrib/diff-highlight/t/Makefile new file mode 100644 index 000000000000..5ff5275496c5 --- /dev/null +++ b/contrib/diff-highlight/t/Makefile @@ -0,0 +1,22 @@ +-include ../../../config.mak.autogen +-include ../../../config.mak + +# copied from ../../t/Makefile +SHELL_PATH ?= $(SHELL) +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) +T = $(wildcard t[0-9][0-9][0-9][0-9]-*.sh) + +all: test +test: $(T) + +.PHONY: help clean all test $(T) + +help: + @echo 'Run "$(MAKE) test" to launch test scripts' + @echo 'Run "$(MAKE) clean" to remove trash folders' + +$(T): + @echo "*** $@ ***"; '$(SHELL_PATH_SQ)' $@ $(GIT_TEST_OPTS) + +clean: + $(RM) -r 'trash directory'.* diff --git a/contrib/diff-highlight/t/t9400-diff-highlight.sh b/contrib/diff-highlight/t/t9400-diff-highlight.sh new file mode 100755 index 000000000000..f6f5195d00f6 --- /dev/null +++ b/contrib/diff-highlight/t/t9400-diff-highlight.sh @@ -0,0 +1,341 @@ +#!/bin/sh + +test_description='Test diff-highlight' + +CURR_DIR=$(pwd) +TEST_OUTPUT_DIRECTORY=$(pwd) +TEST_DIRECTORY="$CURR_DIR"/../../../t +DIFF_HIGHLIGHT="$CURR_DIR"/../diff-highlight + +CW="$(printf "\033[7m")" # white +CR="$(printf "\033[27m")" # reset + +. "$TEST_DIRECTORY"/test-lib.sh + +if ! test_have_prereq PERL +then + skip_all='skipping diff-highlight tests; perl not available' + test_done +fi + +# dh_test is a test helper function which takes 3 file names as parameters. The +# first 2 files are used to generate diff and commit output, which is then +# piped through diff-highlight. The 3rd file should contain the expected output +# of diff-highlight (minus the diff/commit header, ie. everything after and +# including the first @@ line). +dh_test () { + a="$1" b="$2" && + + cat >patch.exp && + + { + cat "$a" >file && + git add file && + git commit -m "Add a file" && + + cat "$b" >file && + git diff file >diff.raw && + git commit -a -m "Update a file" && + git show >commit.raw + } >/dev/null && + + "$DIFF_HIGHLIGHT" <diff.raw | test_strip_patch_header >diff.act && + "$DIFF_HIGHLIGHT" <commit.raw | test_strip_patch_header >commit.act && + test_cmp patch.exp diff.act && + test_cmp patch.exp commit.act +} + +test_strip_patch_header () { + sed -n '/^@@/,$p' $* +} + +# dh_test_setup_history generates a contrived graph such that we have at least +# 1 nesting (E) and 2 nestings (F). +# +# A---B master +# / +# D---E---F branch +# +# git log --all --graph +# * commit +# | B +# | * commit +# | | F +# * | commit +# | | A +# | * commit +# |/ +# | E +# * commit +# D +# +dh_test_setup_history () { + echo file1 >file && + git add file && + test_tick && + git commit -m "D" && + + git checkout -b branch && + echo file2 >file && + test_tick && + git commit -a -m "E" && + + git checkout master && + echo file2 >file && + test_tick && + git commit -a -m "A" && + + git checkout branch && + echo file3 >file && + test_tick && + git commit -a -m "F" && + + git checkout master && + echo file3 >file && + test_tick && + git commit -a -m "B" +} + +left_trim () { + "$PERL_PATH" -pe 's/^\s+//' +} + +trim_graph () { + # graphs start with * or | + # followed by a space or / or \ + "$PERL_PATH" -pe 's@^((\*|\|)( |/|\\))+@@' +} + +test_expect_success 'diff-highlight highlights the beginning of a line' ' + cat >a <<-\EOF && + aaa + bbb + ccc + EOF + + cat >b <<-\EOF && + aaa + 0bb + ccc + EOF + + dh_test a b <<-EOF + @@ -1,3 +1,3 @@ + aaa + -${CW}b${CR}bb + +${CW}0${CR}bb + ccc + EOF +' + +test_expect_success 'diff-highlight highlights the end of a line' ' + cat >a <<-\EOF && + aaa + bbb + ccc + EOF + + cat >b <<-\EOF && + aaa + bb0 + ccc + EOF + + dh_test a b <<-EOF + @@ -1,3 +1,3 @@ + aaa + -bb${CW}b${CR} + +bb${CW}0${CR} + ccc + EOF +' + +test_expect_success 'diff-highlight highlights the middle of a line' ' + cat >a <<-\EOF && + aaa + bbb + ccc + EOF + + cat >b <<-\EOF && + aaa + b0b + ccc + EOF + + dh_test a b <<-EOF + @@ -1,3 +1,3 @@ + aaa + -b${CW}b${CR}b + +b${CW}0${CR}b + ccc + EOF +' + +test_expect_success 'diff-highlight does not highlight whole line' ' + cat >a <<-\EOF && + aaa + bbb + ccc + EOF + + cat >b <<-\EOF && + aaa + 000 + ccc + EOF + + dh_test a b <<-EOF + @@ -1,3 +1,3 @@ + aaa + -bbb + +000 + ccc + EOF +' + +test_expect_failure 'diff-highlight highlights mismatched hunk size' ' + cat >a <<-\EOF && + aaa + bbb + EOF + + cat >b <<-\EOF && + aaa + b0b + ccc + EOF + + dh_test a b <<-EOF + @@ -1,3 +1,3 @@ + aaa + -b${CW}b${CR}b + +b${CW}0${CR}b + +ccc + EOF +' + +# These two code points share the same leading byte in UTF-8 representation; +# a naive byte-wise diff would highlight only the second byte. +# +# - U+00f3 ("o" with acute) +o_accent=$(printf '\303\263') +# - U+00f8 ("o" with stroke) +o_stroke=$(printf '\303\270') + +test_expect_success 'diff-highlight treats multibyte utf-8 as a unit' ' + echo "unic${o_accent}de" >a && + echo "unic${o_stroke}de" >b && + dh_test a b <<-EOF + @@ -1 +1 @@ + -unic${CW}${o_accent}${CR}de + +unic${CW}${o_stroke}${CR}de + EOF +' + +# Unlike the UTF-8 above, these are combining code points which are meant +# to modify the character preceding them: +# +# - U+0301 (combining acute accent) +combine_accent=$(printf '\314\201') +# - U+0302 (combining circumflex) +combine_circum=$(printf '\314\202') + +test_expect_failure 'diff-highlight treats combining code points as a unit' ' + echo "unico${combine_accent}de" >a && + echo "unico${combine_circum}de" >b && + dh_test a b <<-EOF + @@ -1 +1 @@ + -unic${CW}o${combine_accent}${CR}de + +unic${CW}o${combine_circum}${CR}de + EOF +' + +test_expect_success 'diff-highlight works with the --graph option' ' + dh_test_setup_history && + + # date-order so that the commits are interleaved for both + # trim graph elements so we can do a diff + # trim leading space because our trim_graph is not perfect + git log --branches -p --date-order | + "$DIFF_HIGHLIGHT" | left_trim >graph.exp && + git log --branches -p --date-order --graph | + "$DIFF_HIGHLIGHT" | trim_graph | left_trim >graph.act && + test_cmp graph.exp graph.act +' + +# Just reuse the previous graph test, but with --color. Our trimming +# doesn't know about color, so just sanity check that something got +# highlighted. +test_expect_success 'diff-highlight works with color graph' ' + git log --branches -p --date-order --graph --color | + "$DIFF_HIGHLIGHT" | trim_graph | left_trim >graph && + grep "\[7m" graph +' + +# Most combined diffs won't meet diff-highlight's line-number filter. So we +# create one here where one side drops a line and the other modifies it. That +# should result in a diff like: +# +# - modified content +# ++resolved content +# +# which naively looks like one side added "+resolved". +test_expect_success 'diff-highlight ignores combined diffs' ' + echo "content" >file && + git add file && + git commit -m base && + + >file && + git commit -am master && + + git checkout -b other HEAD^ && + echo "modified content" >file && + git commit -am other && + + test_must_fail git merge master && + echo "resolved content" >file && + git commit -am resolved && + + cat >expect <<-\EOF && + --- a/file + +++ b/file + @@@ -1,1 -1,0 +1,1 @@@ + - modified content + ++resolved content + EOF + + git show -c | "$DIFF_HIGHLIGHT" >actual.raw && + sed -n "/^---/,\$p" <actual.raw >actual && + test_cmp expect actual +' + +test_expect_success 'diff-highlight handles --graph with leading dash' ' + cat >file <<-\EOF && + before + the old line + -leading dash + EOF + git add file && + git commit -m before && + + sed s/old/new/ <file >file.tmp && + mv file.tmp file && + git add file && + git commit -m after && + + cat >expect <<-EOF && + --- a/file + +++ b/file + @@ -1,3 +1,3 @@ + before + -the ${CW}old${CR} line + +the ${CW}new${CR} line + -leading dash + EOF + git log --graph -p -1 | "$DIFF_HIGHLIGHT" >actual.raw && + trim_graph <actual.raw | sed -n "/^---/,\$p" >actual && + test_cmp expect actual +' + +test_done diff --git a/contrib/emacs/README b/contrib/emacs/README new file mode 100644 index 000000000000..977a16f1e339 --- /dev/null +++ b/contrib/emacs/README @@ -0,0 +1,33 @@ +This directory used to contain various modules for Emacs support. + +These were added shortly after Git was first released. Since then +Emacs's own support for Git got better than what was offered by these +modes. There are also popular 3rd-party Git modes such as Magit which +offer replacements for these. + +The following modules were available, and can be dug up from the Git +history: + +* git.el: + + Wrapper for "git status" that provided access to other git commands. + + Modern alternatives to this include Magit, and VC mode that ships + with Emacs. + +* git-blame.el: + + A wrapper for "git blame" written before Emacs's own vc-annotate + mode learned to invoke git-blame, which can be done via C-x v g. + +* vc-git.el: + + This file used to contain the VC-mode backend for git, but it is no + longer distributed with git. It is now maintained as part of Emacs + and included in standard Emacs distributions starting from version + 22.2. + + If you have an earlier Emacs version, upgrading to Emacs 22 is + recommended, since the VC mode in older Emacs is not generic enough + to be able to support git in a reasonable manner, and no attempt has + been made to backport vc-git.el. diff --git a/contrib/emacs/git-blame.el b/contrib/emacs/git-blame.el new file mode 100644 index 000000000000..6a8a2b8ff190 --- /dev/null +++ b/contrib/emacs/git-blame.el @@ -0,0 +1,6 @@ +(error "git-blame.el no longer ships with git. It's recommended +to replace its use with Emacs's own vc-annotate. See +contrib/emacs/README in git's +sources (https://github.com/git/git/blob/master/contrib/emacs/README) +for more info on suggested alternatives and for why this +happened.") diff --git a/contrib/emacs/git.el b/contrib/emacs/git.el new file mode 100644 index 000000000000..03f926281fb1 --- /dev/null +++ b/contrib/emacs/git.el @@ -0,0 +1,6 @@ +(error "git.el no longer ships with git. It's recommended to +replace its use with Magit, or simply delete references to git.el +in your initialization file(s). See contrib/emacs/README in git's +sources (https://github.com/git/git/blob/master/contrib/emacs/README) +for suggested alternatives and for why this happened. Emacs's own +VC mode and Magit are viable alternatives.") diff --git a/contrib/examples/README b/contrib/examples/README new file mode 100644 index 000000000000..18bc60b021be --- /dev/null +++ b/contrib/examples/README @@ -0,0 +1,20 @@ +This directory used to contain scripted implementations of builtins +that have since been rewritten in C. + +They have now been removed, but can be retrieved from an older commit +that removed them from this directory. + +They're interesting for their reference value to any aspiring plumbing +users who want to learn how pieces can be fit together, but in many +cases have drifted enough from the actual implementations Git uses to +be instructive. + +Other things that can be useful: + + * Some commands such as git-gc wrap other commands, and what they're + doing behind the scenes can be seen by running them under + GIT_TRACE=1 + + * Doing `git log` on paths matching '*--helper.c' will show + incremental effort in the direction of moving existing shell + scripts to C. diff --git a/contrib/fast-import/git-import.perl b/contrib/fast-import/git-import.perl new file mode 100755 index 000000000000..0891b9e36672 --- /dev/null +++ b/contrib/fast-import/git-import.perl @@ -0,0 +1,64 @@ +#!/usr/bin/perl +# +# Performs an initial import of a directory. This is the equivalent +# of doing 'git init; git add .; git commit'. It's a little slower, +# but is meant to be a simple fast-import example. + +use strict; +use File::Find; + +my $USAGE = 'usage: git-import branch import-message'; +my $branch = shift or die "$USAGE\n"; +my $message = shift or die "$USAGE\n"; + +chomp(my $username = `git config user.name`); +chomp(my $email = `git config user.email`); +die 'You need to set user name and email' + unless $username && $email; + +system('git init'); +open(my $fi, '|-', qw(git fast-import --date-format=now)) + or die "unable to spawn fast-import: $!"; + +print $fi <<EOF; +commit refs/heads/$branch +committer $username <$email> now +data <<MSGEOF +$message +MSGEOF + +EOF + +find( + sub { + if($File::Find::name eq './.git') { + $File::Find::prune = 1; + return; + } + return unless -f $_; + + my $fn = $File::Find::name; + $fn =~ s#^.\/##; + + open(my $in, '<', $_) + or die "unable to open $fn: $!"; + my @st = stat($in) + or die "unable to stat $fn: $!"; + my $len = $st[7]; + + print $fi "M 644 inline $fn\n"; + print $fi "data $len\n"; + while($len > 0) { + my $r = read($in, my $buf, $len < 4096 ? $len : 4096); + defined($r) or die "read error from $fn: $!"; + $r > 0 or die "premature EOF from $fn: $!"; + print $fi $buf; + $len -= $r; + } + print $fi "\n"; + + }, '.' +); + +close($fi); +exit $?; diff --git a/contrib/fast-import/git-import.sh b/contrib/fast-import/git-import.sh new file mode 100755 index 000000000000..f8d803c5e2be --- /dev/null +++ b/contrib/fast-import/git-import.sh @@ -0,0 +1,38 @@ +#!/bin/sh +# +# Performs an initial import of a directory. This is the equivalent +# of doing 'git init; git add .; git commit'. It's a lot slower, +# but is meant to be a simple fast-import example. + +if [ -z "$1" -o -z "$2" ]; then + echo "usage: git-import branch import-message" + exit 1 +fi + +USERNAME="$(git config user.name)" +EMAIL="$(git config user.email)" + +if [ -z "$USERNAME" -o -z "$EMAIL" ]; then + echo "You need to set user name and email" + exit 1 +fi + +git init + +( + cat <<EOF +commit refs/heads/$1 +committer $USERNAME <$EMAIL> now +data <<MSGEOF +$2 +MSGEOF + +EOF + find * -type f|while read i;do + echo "M 100644 inline $i" + echo data $(stat -c '%s' "$i") + cat "$i" + echo + done + echo +) | git fast-import --date-format=now diff --git a/contrib/fast-import/git-p4.README b/contrib/fast-import/git-p4.README new file mode 100644 index 000000000000..cec5ecfa7c78 --- /dev/null +++ b/contrib/fast-import/git-p4.README @@ -0,0 +1,12 @@ +The git-p4 script moved to the top-level of the git source directory. + +Invoke it as any other git command, like "git p4 clone", for instance. + +Note that the top-level git-p4.py script is now the source. It is +built using make to git-p4, which will be installed. + +Windows users can copy the git-p4.py source script directly, possibly +invoking it through a batch file called "git-p4.bat" in the same folder. +It should contain just one line: + + @python "%~d0%~p0git-p4.py" %* diff --git a/contrib/fast-import/import-directories.perl b/contrib/fast-import/import-directories.perl new file mode 100755 index 000000000000..a16f79cfdc46 --- /dev/null +++ b/contrib/fast-import/import-directories.perl @@ -0,0 +1,416 @@ +#!/usr/bin/perl +# +# Copyright 2008-2009 Peter Krefting <peter@softwolves.pp.se> +# +# ------------------------------------------------------------------------ +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, see <http://www.gnu.org/licenses/>. +# +# ------------------------------------------------------------------------ + +=pod + +=head1 NAME + +import-directories - Import bits and pieces to Git. + +=head1 SYNOPSIS + +B<import-directories.perl> F<configfile> F<outputfile> + +=head1 DESCRIPTION + +Script to import arbitrary projects version controlled by the "copy the +source directory to a new location and edit it there"-version controlled +projects into version control. Handles projects with arbitrary branching +and version trees, taking a file describing the inputs and generating a +file compatible with the L<git-fast-import(1)> format. + +=head1 CONFIGURATION FILE + +=head2 Format + +The configuration file is based on the standard I<.ini> format. + + ; Comments start with semi-colons + [section] + key=value + +Please see below for information on how to escape special characters. + +=head2 Global configuration + +Global configuration is done in the B<[config]> section, which should be +the first section in the file. Configuration can be changed by +repeating configuration sections later on. + + [config] + ; configure conversion of CRLFs. "convert" means that all CRLFs + ; should be converted into LFs (suitable for the core.autocrlf + ; setting set to true in Git). "none" means that all data is + ; treated as binary. + crlf=convert + +=head2 Revision configuration + +Each revision that is to be imported is described in three +sections. Revisions should be defined in topological order, so +that a revision's parent has always been defined when a new revision +is introduced. All the sections for one revision must be defined +before defining the next revision. + +Each revision is assigned a unique numerical identifier. The +numbers do not need to be consecutive, nor monotonically +increasing. + +For instance, if your configuration file contains only the two +revisions 4711 and 42, where 4711 is the initial commit, the +only requirement is that 4711 is completely defined before 42. + +=pod + +=head3 Revision description section + +A section whose section name is just an integer gives meta-data +about the revision. + + [3] + ; author sets the author of the revisions + author=Peter Krefting <peter@softwolves.pp.se> + ; branch sets the branch that the revision should be committed to + branch=master + ; parent describes the revision that is the parent of this commit + ; (optional) + parent=1 + ; merges describes a revision that is merged into this commit + ; (optional; can be repeated) + merges=2 + ; selects one file to take the timestamp from + ; (optional; if unspecified, the most recent file from the .files + ; section is used) + timestamp=3/source.c + +=head3 Revision contents section + +A section whose section name is an integer followed by B<.files> +describe all the files included in this revision. If a file that +was available previously is not included in this revision, it will +be removed. + +If an on-disk revision is incomplete, you can point to files from +a previous revision. There are no restrictions on where the source +files are located, nor on their names. + + [3.files] + ; the key is the path inside the repository, the value is the path + ; as seen from the importer script. + source.c=ver-3.00/source.c + source.h=ver-2.99/source.h + readme.txt=ver-3.00/introduction to the project.txt + +File names are treated as byte strings (but please see below on +quoting rules), and should be stored in the configuration file in +the encoding that should be used in the generated repository. + +=head3 Revision commit message section + +A section whose section name is an integer followed by B<.message> +gives the commit message. This section is read verbatim, up until +the beginning of the next section. As such, a commit message may not +contain a line that begins with an opening square bracket ("[") and +ends with a closing square bracket ("]"), unless they are surrounded +by whitespace or other characters. + + [3.message] + Implement foobar. + ; trailing blank lines are ignored. + +=cut + +# Globals +use strict; +use warnings; +use integer; +my $crlfmode = 0; +my @revs; +my (%revmap, %message, %files, %author, %branch, %parent, %merges, %time, %timesource); +my $sectiontype = 0; +my $rev = 0; +my $mark = 1; + +# Check command line +if ($#ARGV < 1 || $ARGV[0] =~ /^--?h/) +{ + exec('perldoc', $0); + exit 1; +} + +# Open configuration +my $config = $ARGV[0]; +open CFG, '<', $config or die "Cannot open configuration file \"$config\": "; + +# Open output +my $output = $ARGV[1]; +open OUT, '>', $output or die "Cannot create output file \"$output\": "; +binmode OUT; + +LINE: while (my $line = <CFG>) +{ + $line =~ s/\r?\n$//; + next LINE if $sectiontype != 4 && $line eq ''; + next LINE if $line =~ /^;/; + my $oldsectiontype = $sectiontype; + my $oldrev = $rev; + + # Sections + if ($line =~ m"^\[(config|(\d+)(|\.files|\.message))\]$") + { + if ($1 eq 'config') + { + $sectiontype = 1; + } + elsif ($3 eq '') + { + $sectiontype = 2; + $rev = $2; + # Create a new revision + die "Duplicate rev: $line\n " if defined $revmap{$rev}; + print "Reading revision $rev\n"; + push @revs, $rev; + $revmap{$rev} = $mark ++; + $time{$revmap{$rev}} = 0; + } + elsif ($3 eq '.files') + { + $sectiontype = 3; + $rev = $2; + die "Revision mismatch: $line\n " unless $rev == $oldrev; + } + elsif ($3 eq '.message') + { + $sectiontype = 4; + $rev = $2; + die "Revision mismatch: $line\n " unless $rev == $oldrev; + } + else + { + die "Internal parse error: $line\n "; + } + next LINE; + } + + # Parse data + if ($sectiontype != 4) + { + # Key and value + if ($line =~ m"^\s*([^\s].*=.*[^\s])\s*$") + { + my ($key, $value) = &parsekeyvaluepair($1); + # Global configuration + if (1 == $sectiontype) + { + if ($key eq 'crlf') + { + $crlfmode = 1, next LINE if $value eq 'convert'; + $crlfmode = 0, next LINE if $value eq 'none'; + } + die "Unknown configuration option: $line\n "; + } + # Revision specification + if (2 == $sectiontype) + { + my $current = $revmap{$rev}; + $author{$current} = $value, next LINE if $key eq 'author'; + $branch{$current} = $value, next LINE if $key eq 'branch'; + $parent{$current} = $value, next LINE if $key eq 'parent'; + $timesource{$current} = $value, next LINE if $key eq 'timestamp'; + push(@{$merges{$current}}, $value), next LINE if $key eq 'merges'; + die "Unknown revision option: $line\n "; + } + # Filespecs + if (3 == $sectiontype) + { + # Add the file and create a marker + die "File not found: $line\n " unless -f $value; + my $current = $revmap{$rev}; + ${$files{$current}}{$key} = $mark; + my $time = &fileblob($value, $crlfmode, $mark ++); + + # Update revision timestamp if more recent than other + # files seen, or if this is the file we have selected + # to take the time stamp from using the "timestamp" + # directive. + if ((defined $timesource{$current} && $timesource{$current} eq $value) + || $time > $time{$current}) + { + $time{$current} = $time; + } + } + } + else + { + die "Parse error: $line\n "; + } + } + else + { + # Commit message + my $current = $revmap{$rev}; + if (defined $message{$current}) + { + $message{$current} .= "\n"; + } + $message{$current} .= $line; + } +} +close CFG; + +# Start spewing out data for git-fast-import +foreach my $commit (@revs) +{ + # Progress + print OUT "progress Creating revision $commit\n"; + + # Create commit header + my $mark = $revmap{$commit}; + + # Branch and commit id + print OUT "commit refs/heads/", $branch{$mark}, "\nmark :", $mark, "\n"; + + # Author and timestamp + die "No timestamp defined for $commit (no files?)\n" unless defined $time{$mark}; + print OUT "committer ", $author{$mark}, " ", $time{$mark}, " +0100\n"; + + # Commit message + die "No message defined for $commit\n" unless defined $message{$mark}; + my $message = $message{$mark}; + $message =~ s/\n$//; # Kill trailing empty line + print OUT "data ", length($message), "\n", $message, "\n"; + + # Parent and any merges + print OUT "from :", $revmap{$parent{$mark}}, "\n" if defined $parent{$mark}; + if (defined $merges{$mark}) + { + foreach my $merge (@{$merges{$mark}}) + { + print OUT "merge :", $revmap{$merge}, "\n"; + } + } + + # Output file marks + print OUT "deleteall\n"; # start from scratch + foreach my $file (sort keys %{$files{$mark}}) + { + print OUT "M 644 :", ${$files{$mark}}{$file}, " $file\n"; + } + print OUT "\n"; +} + +# Create one file blob +sub fileblob +{ + my ($filename, $crlfmode, $mark) = @_; + + # Import the file + print OUT "progress Importing $filename\nblob\nmark :$mark\n"; + open FILE, '<', $filename or die "Cannot read $filename\n "; + binmode FILE; + my ($size, $mtime) = (stat(FILE))[7,9]; + my $file; + read FILE, $file, $size; + close FILE; + $file =~ s/\r\n/\n/g if $crlfmode; + print OUT "data ", length($file), "\n", $file, "\n"; + + return $mtime; +} + +# Parse a key=value pair +sub parsekeyvaluepair +{ +=pod + +=head2 Escaping special characters + +Key and value strings may be enclosed in quotes, in which case +whitespace inside the quotes is preserved. Additionally, an equal +sign may be included in the key by preceding it with a backslash. +For example: + + "key1 "=value1 + key2=" value2" + key\=3=value3 + key4=value=4 + "key5""=value5 + +Here the first key is "key1 " (note the trailing white-space) and the +second value is " value2" (note the leading white-space). The third +key contains an equal sign "key=3" and so does the fourth value, which +does not need to be escaped. The fifth key contains a trailing quote, +which does not need to be escaped since it is inside a surrounding +quote. + +=cut + my $pair = shift; + + # Separate key and value by the first non-quoted equal sign + my ($key, $value); + if ($pair =~ /^(.*[^\\])=(.*)$/) + { + ($key, $value) = ($1, $2) + } + else + { + die "Parse error: $pair\n "; + } + + # Unquote and unescape the key and value separately + return (&unescape($key), &unescape($value)); +} + +# Unquote and unescape +sub unescape +{ + my $string = shift; + + # First remove enclosing quotes. Backslash before the trailing + # quote leaves both. + if ($string =~ /^"(.*[^\\])"$/) + { + $string = $1; + } + + # Second remove any backslashes inside the unquoted string. + # For later: Handle special sequences like \t ? + $string =~ s/\\(.)/$1/g; + + return $string; +} + +__END__ + +=pod + +=head1 EXAMPLES + +B<import-directories.perl> F<project.import> + +=head1 AUTHOR + +Copyright 2008-2009 Peter Krefting E<lt>peter@softwolves.pp.se> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation. + +=cut diff --git a/contrib/fast-import/import-tars.perl b/contrib/fast-import/import-tars.perl new file mode 100755 index 000000000000..e800d9f5c9cf --- /dev/null +++ b/contrib/fast-import/import-tars.perl @@ -0,0 +1,225 @@ +#!/usr/bin/perl + +## tar archive frontend for git-fast-import +## +## For example: +## +## mkdir project; cd project; git init +## perl import-tars.perl *.tar.bz2 +## git whatchanged import-tars +## +## Use --metainfo to specify the extension for a meta data file, where +## import-tars can read the commit message and optionally author and +## committer information. +## +## echo 'This is the commit message' > myfile.tar.bz2.msg +## perl import-tars.perl --metainfo=msg myfile.tar.bz2 + +use strict; +use Getopt::Long; + +my $metaext = ''; + +die "usage: import-tars [--metainfo=extension] *.tar.{gz,bz2,lzma,xz,Z}\n" + unless GetOptions('metainfo=s' => \$metaext) && @ARGV; + +my $branch_name = 'import-tars'; +my $branch_ref = "refs/heads/$branch_name"; +my $author_name = $ENV{'GIT_AUTHOR_NAME'} || 'T Ar Creator'; +my $author_email = $ENV{'GIT_AUTHOR_EMAIL'} || 'tar@example.com'; +my $committer_name = $ENV{'GIT_COMMITTER_NAME'} || `git config --get user.name`; +my $committer_email = $ENV{'GIT_COMMITTER_EMAIL'} || `git config --get user.email`; + +chomp($committer_name, $committer_email); + +open(FI, '|-', 'git', 'fast-import', '--quiet') + or die "Unable to start git fast-import: $!\n"; +foreach my $tar_file (@ARGV) +{ + my $commit_time = time; + $tar_file =~ m,([^/]+)$,; + my $tar_name = $1; + + if ($tar_name =~ s/\.(tar\.gz|tgz)$//) { + open(I, '-|', 'gunzip', '-c', $tar_file) + or die "Unable to gunzip -c $tar_file: $!\n"; + } elsif ($tar_name =~ s/\.(tar\.bz2|tbz2)$//) { + open(I, '-|', 'bunzip2', '-c', $tar_file) + or die "Unable to bunzip2 -c $tar_file: $!\n"; + } elsif ($tar_name =~ s/\.tar\.Z$//) { + open(I, '-|', 'uncompress', '-c', $tar_file) + or die "Unable to uncompress -c $tar_file: $!\n"; + } elsif ($tar_name =~ s/\.(tar\.(lzma|xz)|(tlz|txz))$//) { + open(I, '-|', 'xz', '-dc', $tar_file) + or die "Unable to xz -dc $tar_file: $!\n"; + } elsif ($tar_name =~ s/\.tar$//) { + open(I, $tar_file) or die "Unable to open $tar_file: $!\n"; + } else { + die "Unrecognized compression format: $tar_file\n"; + } + + my $author_time = 0; + my $next_mark = 1; + my $have_top_dir = 1; + my ($top_dir, %files); + + my $next_path = ''; + + while (read(I, $_, 512) == 512) { + my ($name, $mode, $uid, $gid, $size, $mtime, + $chksum, $typeflag, $linkname, $magic, + $version, $uname, $gname, $devmajor, $devminor, + $prefix) = unpack 'Z100 Z8 Z8 Z8 Z12 Z12 + Z8 Z1 Z100 Z6 + Z2 Z32 Z32 Z8 Z8 Z*', $_; + + unless ($next_path eq '') { + # Recover name from previous extended header + $name = $next_path; + $next_path = ''; + } + + last unless length($name); + if ($name eq '././@LongLink') { + # GNU tar extension + if (read(I, $_, 512) != 512) { + die ('Short archive'); + } + $name = unpack 'Z257', $_; + next unless $name; + + my $dummy; + if (read(I, $_, 512) != 512) { + die ('Short archive'); + } + ($dummy, $mode, $uid, $gid, $size, $mtime, + $chksum, $typeflag, $linkname, $magic, + $version, $uname, $gname, $devmajor, $devminor, + $prefix) = unpack 'Z100 Z8 Z8 Z8 Z12 Z12 + Z8 Z1 Z100 Z6 + Z2 Z32 Z32 Z8 Z8 Z*', $_; + } + $mode = oct $mode; + $size = oct $size; + $mtime = oct $mtime; + next if $typeflag == 5; # directory + + if ($typeflag eq 'x') { # extended header + # If extended header, check for path + my $pax_header = ''; + while ($size > 0 && read(I, $_, 512) == 512) { + $pax_header = $pax_header . substr($_, 0, $size); + $size -= 512; + } + + my @lines = split /\n/, $pax_header; + foreach my $line (@lines) { + my ($len, $entry) = split / /, $line; + my ($key, $value) = split /=/, $entry; + if ($key eq 'path') { + $next_path = $value; + } + } + next; + } elsif ($name =~ m{/\z}) { # directory + next; + } elsif ($typeflag != 1) { # handle hard links later + print FI "blob\n", "mark :$next_mark\n"; + if ($typeflag == 2) { # symbolic link + print FI "data ", length($linkname), "\n", + $linkname; + $mode = 0120000; + } else { + print FI "data $size\n"; + while ($size > 0 && read(I, $_, 512) == 512) { + print FI substr($_, 0, $size); + $size -= 512; + } + } + print FI "\n"; + } + + my $path; + if ($prefix) { + $path = "$prefix/$name"; + } else { + $path = "$name"; + } + + if ($typeflag == 1) { # hard link + $linkname = "$prefix/$linkname" if $prefix; + $files{$path} = [ $files{$linkname}->[0], $mode ]; + } else { + $files{$path} = [$next_mark++, $mode]; + } + + $author_time = $mtime if $mtime > $author_time; + $path =~ m,^([^/]+)/,; + $top_dir = $1 unless $top_dir; + $have_top_dir = 0 if $top_dir ne $1; + } + + my $commit_msg = "Imported from $tar_file."; + my $this_committer_name = $committer_name; + my $this_committer_email = $committer_email; + my $this_author_name = $author_name; + my $this_author_email = $author_email; + if ($metaext ne '') { + # Optionally read a commit message from <filename.tar>.msg + # Add a line on the form "Committer: name <e-mail>" to override + # the committer and "Author: name <e-mail>" to override the + # author for this tar ball. + if (open MSG, '<', "${tar_file}.${metaext}") { + my $header_done = 0; + $commit_msg = ''; + while (<MSG>) { + if (!$header_done && /^Committer:\s+([^<>]*)\s+<(.*)>\s*$/i) { + $this_committer_name = $1; + $this_committer_email = $2; + } elsif (!$header_done && /^Author:\s+([^<>]*)\s+<(.*)>\s*$/i) { + $this_author_name = $1; + $this_author_email = $2; + } elsif (!$header_done && /^$/) { # empty line ends header. + $header_done = 1; + } else { + $commit_msg .= $_; + $header_done = 1; + } + } + close MSG; + } + } + + print FI <<EOF; +commit $branch_ref +author $this_author_name <$this_author_email> $author_time +0000 +committer $this_committer_name <$this_committer_email> $commit_time +0000 +data <<END_OF_COMMIT_MESSAGE +$commit_msg +END_OF_COMMIT_MESSAGE + +deleteall +EOF + + foreach my $path (keys %files) + { + my ($mark, $mode) = @{$files{$path}}; + $path =~ s,^([^/]+)/,, if $have_top_dir; + $mode = $mode & 0111 ? 0755 : 0644 unless $mode == 0120000; + printf FI "M %o :%i %s\n", $mode, $mark, $path; + } + print FI "\n"; + + print FI <<EOF; +tag $tar_name +from $branch_ref +tagger $author_name <$author_email> $author_time +0000 +data <<END_OF_TAG_MESSAGE +Package $tar_name +END_OF_TAG_MESSAGE + +EOF + + close I; +} +close FI; diff --git a/contrib/fast-import/import-zips.py b/contrib/fast-import/import-zips.py new file mode 100755 index 000000000000..d12c2962230b --- /dev/null +++ b/contrib/fast-import/import-zips.py @@ -0,0 +1,78 @@ +#!/usr/bin/env python + +## zip archive frontend for git-fast-import +## +## For example: +## +## mkdir project; cd project; git init +## python import-zips.py *.zip +## git log --stat import-zips + +from os import popen, path +from sys import argv, exit, hexversion, stderr +from time import mktime +from zipfile import ZipFile + +if hexversion < 0x01060000: + # The limiter is the zipfile module + stderr.write("import-zips.py: requires Python 1.6.0 or later.\n") + exit(1) + +if len(argv) < 2: + print 'usage:', argv[0], '<zipfile>...' + exit(1) + +branch_ref = 'refs/heads/import-zips' +committer_name = 'Z Ip Creator' +committer_email = 'zip@example.com' + +fast_import = popen('git fast-import --quiet', 'w') +def printlines(list): + for str in list: + fast_import.write(str + "\n") + +for zipfile in argv[1:]: + commit_time = 0 + next_mark = 1 + common_prefix = None + mark = dict() + + zip = ZipFile(zipfile, 'r') + for name in zip.namelist(): + if name.endswith('/'): + continue + info = zip.getinfo(name) + + if commit_time < info.date_time: + commit_time = info.date_time + if common_prefix == None: + common_prefix = name[:name.rfind('/') + 1] + else: + while not name.startswith(common_prefix): + last_slash = common_prefix[:-1].rfind('/') + 1 + common_prefix = common_prefix[:last_slash] + + mark[name] = ':' + str(next_mark) + next_mark += 1 + + printlines(('blob', 'mark ' + mark[name], \ + 'data ' + str(info.file_size))) + fast_import.write(zip.read(name) + "\n") + + committer = committer_name + ' <' + committer_email + '> %d +0000' % \ + mktime(commit_time + (0, 0, 0)) + + printlines(('commit ' + branch_ref, 'committer ' + committer, \ + 'data <<EOM', 'Imported from ' + zipfile + '.', 'EOM', \ + '', 'deleteall')) + + for name in mark.keys(): + fast_import.write('M 100644 ' + mark[name] + ' ' + + name[len(common_prefix):] + "\n") + + printlines(('', 'tag ' + path.basename(zipfile), \ + 'from ' + branch_ref, 'tagger ' + committer, \ + 'data <<EOM', 'Package ' + zipfile, 'EOM', '')) + +if fast_import.close(): + exit(1) diff --git a/contrib/git-jump/README b/contrib/git-jump/README new file mode 100644 index 000000000000..2f618a7f9788 --- /dev/null +++ b/contrib/git-jump/README @@ -0,0 +1,112 @@ +git-jump +======== + +Git-jump is a script for helping you jump to "interesting" parts of your +project in your editor. It works by outputting a set of interesting +spots in the "quickfix" format, which editors like vim can use as a +queue of places to visit (this feature is usually used to jump to errors +produced by a compiler). For example, given a diff like this: + +------------------------------------ +diff --git a/foo.c b/foo.c +index a655540..5a59044 100644 +--- a/foo.c ++++ b/foo.c +@@ -1,3 +1,3 @@ + int main(void) { +- printf("hello word!\n"); ++ printf("hello world!\n"); + } +----------------------------------- + +git-jump will feed this to the editor: + +----------------------------------- +foo.c:2: printf("hello word!\n"); +----------------------------------- + +Or, when running 'git jump grep', column numbers will also be emitted, +e.g. `git jump grep "hello"` would return: + +----------------------------------- +foo.c:2:9: printf("hello word!\n"); +----------------------------------- + +Obviously this trivial case isn't that interesting; you could just open +`foo.c` yourself. But when you have many changes scattered across a +project, you can use the editor's support to "jump" from point to point. + +Git-jump can generate four types of interesting lists: + + 1. The beginning of any diff hunks. + + 2. The beginning of any merge conflict markers. + + 3. Any grep matches, including the column of the first match on a + line. + + 4. Any whitespace errors detected by `git diff --check`. + + +Using git-jump +-------------- + +To use it, just drop git-jump in your PATH, and then invoke it like +this: + +-------------------------------------------------- +# jump to changes not yet staged for commit +git jump diff + +# jump to changes that are staged for commit; you can give +# arbitrary diff options +git jump diff --cached + +# jump to merge conflicts +git jump merge + +# jump to all instances of foo_bar +git jump grep foo_bar + +# same as above, but case-insensitive; you can give +# arbitrary grep options +git jump grep -i foo_bar + +# use the silver searcher for git jump grep +git config jump.grepCmd "ag --column" +-------------------------------------------------- + + +Related Programs +---------------- + +You can accomplish some of the same things with individual tools. For +example, you can use `git mergetool` to start vimdiff on each unmerged +file. `git jump merge` is for the vim-wielding luddite who just wants to +jump straight to the conflict text with no fanfare. + +As of git v1.7.2, `git grep` knows the `--open-files-in-pager` option, +which does something similar to `git jump grep`. However, it is limited +to positioning the cursor to the correct line in only the first file, +leaving you to locate subsequent hits in that file or other files using +the editor or pager. By contrast, git-jump provides the editor with a +complete list of files, lines, and a column number for each match. + + +Limitations +----------- + +This script was written and tested with vim. Given that the quickfix +format is the same as what gcc produces, I expect emacs users have a +similar feature for iterating through the list, but I know nothing about +how to activate it. + +The shell snippets to generate the quickfix lines will almost certainly +choke on filenames with exotic characters (like newlines). + +Contributing +------------ + +Bug fixes, bug reports, and feature requests should be discussed on the +Git mailing list <git@vger.kernel.org>, and cc'd to the git-jump +maintainer, Jeff King <peff@peff.net>. diff --git a/contrib/git-jump/git-jump b/contrib/git-jump/git-jump new file mode 100755 index 000000000000..931b0fe3a948 --- /dev/null +++ b/contrib/git-jump/git-jump @@ -0,0 +1,78 @@ +#!/bin/sh + +usage() { + cat <<\EOF +usage: git jump <mode> [<args>] + +Jump to interesting elements in an editor. +The <mode> parameter is one of: + +diff: elements are diff hunks. Arguments are given to diff. + +merge: elements are merge conflicts. Arguments are ignored. + +grep: elements are grep hits. Arguments are given to git grep or, if + configured, to the command in `jump.grepCmd`. + +ws: elements are whitespace errors. Arguments are given to diff --check. +EOF +} + +open_editor() { + editor=`git var GIT_EDITOR` + eval "$editor -q \$1" +} + +mode_diff() { + git diff --no-prefix --relative "$@" | + perl -ne ' + if (m{^\+\+\+ (.*)}) { $file = $1; next } + defined($file) or next; + if (m/^@@ .*?\+(\d+)/) { $line = $1; next } + defined($line) or next; + if (/^ /) { $line++; next } + if (/^[-+]\s*(.*)/) { + print "$file:$line: $1\n"; + $line = undef; + } + ' +} + +mode_merge() { + git ls-files -u | + perl -pe 's/^.*?\t//' | + sort -u | + while IFS= read fn; do + grep -Hn '^<<<<<<<' "$fn" + done +} + +# Grep -n generates nice quickfix-looking lines by itself, +# but let's clean up extra whitespace, so they look better if the +# editor shows them to us in the status bar. +mode_grep() { + cmd=$(git config jump.grepCmd) + test -n "$cmd" || cmd="git grep -n --column" + $cmd "$@" | + perl -pe ' + s/[ \t]+/ /g; + s/^ *//; + ' +} + +mode_ws() { + git diff --check "$@" +} + +if test $# -lt 1; then + usage >&2 + exit 1 +fi +mode=$1; shift + +trap 'rm -f "$tmp"' 0 1 2 3 15 +tmp=`mktemp -t git-jump.XXXXXX` || exit 1 +type "mode_$mode" >/dev/null 2>&1 || { usage >&2; exit 1; } +"mode_$mode" "$@" >"$tmp" +test -s "$tmp" || exit 0 +open_editor "$tmp" diff --git a/contrib/git-resurrect.sh b/contrib/git-resurrect.sh new file mode 100755 index 000000000000..8c171dd959f6 --- /dev/null +++ b/contrib/git-resurrect.sh @@ -0,0 +1,182 @@ +#!/bin/sh + +USAGE="[-a] [-r] [-m] [-t] [-n] [-b <newname>] <name>" +LONG_USAGE="git-resurrect attempts to find traces of a branch tip +called <name>, and tries to resurrect it. Currently, the reflog is +searched for checkout messages, and with -r also merge messages. With +-m and -t, the history of all refs is scanned for Merge <name> into +other/Merge <other> into <name> (respectively) commit subjects, which +is rather slow but allows you to resurrect other people's topic +branches." + +OPTIONS_KEEPDASHDASH= +OPTIONS_STUCKLONG= +OPTIONS_SPEC="\ +git resurrect $USAGE +-- +b,branch= save branch as <newname> instead of <name> +a,all same as -l -r -m -t +k,keep-going full rev-list scan (instead of first match) +l,reflog scan reflog for checkouts (enabled by default) +r,reflog-merges scan for merges recorded in reflog +m,merges scan for merges into other branches (slow) +t,merge-targets scan for merges of other branches into <name> +n,dry-run don't recreate the branch" + +. git-sh-setup + +search_reflog () { + sed -ne 's~^\([^ ]*\) .* checkout: moving from '"$1"' .*~\1~p' \ + < "$GIT_DIR"/logs/HEAD +} + +search_reflog_merges () { + git rev-parse $( + sed -ne 's~^[^ ]* \([^ ]*\) .* merge '"$1"':.*~\1^2~p' \ + < "$GIT_DIR"/logs/HEAD + ) +} + +_x40="[0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f]" +_x40="$_x40$_x40$_x40$_x40$_x40$_x40$_x40$_x40" + +search_merges () { + git rev-list --all --grep="Merge branch '$1'" \ + --pretty=tformat:"%P %s" | + sed -ne "/^$_x40 \($_x40\) Merge .*/ {s//\1/p;$early_exit}" +} + +search_merge_targets () { + git rev-list --all --grep="Merge branch '[^']*' into $branch\$" \ + --pretty=tformat:"%H %s" --all | + sed -ne "/^\($_x40\) Merge .*/ {s//\1/p;$early_exit} " +} + +dry_run= +early_exit=q +scan_reflog=t +scan_reflog_merges= +scan_merges= +scan_merge_targets= +new_name= + +while test "$#" != 0; do + case "$1" in + -b|--branch) + shift + new_name="$1" + ;; + -n|--dry-run) + dry_run=t + ;; + --no-dry-run) + dry_run= + ;; + -k|--keep-going) + early_exit= + ;; + --no-keep-going) + early_exit=q + ;; + -m|--merges) + scan_merges=t + ;; + --no-merges) + scan_merges= + ;; + -l|--reflog) + scan_reflog=t + ;; + --no-reflog) + scan_reflog= + ;; + -r|--reflog_merges) + scan_reflog_merges=t + ;; + --no-reflog_merges) + scan_reflog_merges= + ;; + -t|--merge-targets) + scan_merge_targets=t + ;; + --no-merge-targets) + scan_merge_targets= + ;; + -a|--all) + scan_reflog=t + scan_reflog_merges=t + scan_merges=t + scan_merge_targets=t + ;; + --) + shift + break + ;; + *) + usage + ;; + esac + shift +done + +test "$#" = 1 || usage + +all_strategies="$scan_reflog$scan_reflog_merges$scan_merges$scan_merge_targets" +if test -z "$all_strategies"; then + die "must enable at least one of -lrmt" +fi + +branch="$1" +test -z "$new_name" && new_name="$branch" + +if test ! -z "$scan_reflog"; then + if test -r "$GIT_DIR"/logs/HEAD; then + candidates="$(search_reflog $branch)" + else + die 'reflog scanning requested, but' \ + '$GIT_DIR/logs/HEAD not readable' + fi +fi +if test ! -z "$scan_reflog_merges"; then + if test -r "$GIT_DIR"/logs/HEAD; then + candidates="$candidates $(search_reflog_merges $branch)" + else + die 'reflog scanning requested, but' \ + '$GIT_DIR/logs/HEAD not readable' + fi +fi +if test ! -z "$scan_merges"; then + candidates="$candidates $(search_merges $branch)" +fi +if test ! -z "$scan_merge_targets"; then + candidates="$candidates $(search_merge_targets $branch)" +fi + +candidates="$(git rev-parse $candidates | sort -u)" + +if test -z "$candidates"; then + hint= + test "z$all_strategies" != "ztttt" \ + && hint=" (maybe try again with -a)" + die "no candidates for $branch found$hint" +fi + +echo "** Candidates for $branch **" +for cmt in $candidates; do + git --no-pager log --pretty=tformat:"%ct:%h [%cr] %s" --abbrev-commit -1 $cmt +done \ +| sort -n | cut -d: -f2- + +newest="$(git rev-list -1 $candidates)" +if test ! -z "$dry_run"; then + printf "** Most recent: " + git --no-pager log -1 --pretty=tformat:"%h %s" $newest +elif ! git rev-parse --verify --quiet $new_name >/dev/null; then + printf "** Restoring $new_name to " + git --no-pager log -1 --pretty=tformat:"%h %s" $newest + git branch $new_name $newest +else + printf "Most recent: " + git --no-pager log -1 --pretty=tformat:"%h %s" $newest + echo "** $new_name already exists, doing nothing" +fi diff --git a/contrib/git-shell-commands/README b/contrib/git-shell-commands/README new file mode 100644 index 000000000000..438463b16099 --- /dev/null +++ b/contrib/git-shell-commands/README @@ -0,0 +1,18 @@ +Sample programs callable through git-shell. Place a directory named +'git-shell-commands' in the home directory of a user whose shell is +git-shell. Then anyone logging in as that user will be able to run +executables in the 'git-shell-commands' directory. + +Provided commands: + +help: Prints out the names of available commands. When run +interactively, git-shell will automatically run 'help' on startup, +provided it exists. + +list: Displays any bare repository whose name ends with ".git" under +user's home directory. No other git repositories are visible, +although they might be clonable through git-shell. 'list' is designed +to minimize the number of calls to git that must be made in finding +available repositories; if your setup has additional repositories that +should be user-discoverable, you may wish to modify 'list' +accordingly. diff --git a/contrib/git-shell-commands/help b/contrib/git-shell-commands/help new file mode 100755 index 000000000000..535770c6ec19 --- /dev/null +++ b/contrib/git-shell-commands/help @@ -0,0 +1,18 @@ +#!/bin/sh + +if tty -s +then + echo "Run 'help' for help, or 'exit' to leave. Available commands:" +else + echo "Run 'help' for help. Available commands:" +fi + +cd "$(dirname "$0")" + +for cmd in * +do + case "$cmd" in + help) ;; + *) [ -f "$cmd" ] && [ -x "$cmd" ] && echo "$cmd" ;; + esac +done diff --git a/contrib/git-shell-commands/list b/contrib/git-shell-commands/list new file mode 100755 index 000000000000..6f8993882114 --- /dev/null +++ b/contrib/git-shell-commands/list @@ -0,0 +1,10 @@ +#!/bin/sh + +print_if_bare_repo=' + if "$(git --git-dir="$1" rev-parse --is-bare-repository)" = true + then + printf "%s\n" "${1#./}" + fi +' + +find -type d -name "*.git" -exec sh -c "$print_if_bare_repo" -- \{} \; -prune 2>/dev/null diff --git a/contrib/hg-to-git/hg-to-git.py b/contrib/hg-to-git/hg-to-git.py new file mode 100755 index 000000000000..de3f81667ed9 --- /dev/null +++ b/contrib/hg-to-git/hg-to-git.py @@ -0,0 +1,254 @@ +#!/usr/bin/env python + +""" hg-to-git.py - A Mercurial to GIT converter + + Copyright (C)2007 Stelian Pop <stelian@popies.net> + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, see <http://www.gnu.org/licenses/>. +""" + +import os, os.path, sys +import tempfile, pickle, getopt +import re + +if sys.hexversion < 0x02030000: + # The behavior of the pickle module changed significantly in 2.3 + sys.stderr.write("hg-to-git.py: requires Python 2.3 or later.\n") + sys.exit(1) + +# Maps hg version -> git version +hgvers = {} +# List of children for each hg revision +hgchildren = {} +# List of parents for each hg revision +hgparents = {} +# Current branch for each hg revision +hgbranch = {} +# Number of new changesets converted from hg +hgnewcsets = 0 + +#------------------------------------------------------------------------------ + +def usage(): + + print """\ +%s: [OPTIONS] <hgprj> + +options: + -s, --gitstate=FILE: name of the state to be saved/read + for incrementals + -n, --nrepack=INT: number of changesets that will trigger + a repack (default=0, -1 to deactivate) + -v, --verbose: be verbose + +required: + hgprj: name of the HG project to import (directory) +""" % sys.argv[0] + +#------------------------------------------------------------------------------ + +def getgitenv(user, date): + env = '' + elems = re.compile('(.*?)\s+<(.*)>').match(user) + if elems: + env += 'export GIT_AUTHOR_NAME="%s" ;' % elems.group(1) + env += 'export GIT_COMMITTER_NAME="%s" ;' % elems.group(1) + env += 'export GIT_AUTHOR_EMAIL="%s" ;' % elems.group(2) + env += 'export GIT_COMMITTER_EMAIL="%s" ;' % elems.group(2) + else: + env += 'export GIT_AUTHOR_NAME="%s" ;' % user + env += 'export GIT_COMMITTER_NAME="%s" ;' % user + env += 'export GIT_AUTHOR_EMAIL= ;' + env += 'export GIT_COMMITTER_EMAIL= ;' + + env += 'export GIT_AUTHOR_DATE="%s" ;' % date + env += 'export GIT_COMMITTER_DATE="%s" ;' % date + return env + +#------------------------------------------------------------------------------ + +state = '' +opt_nrepack = 0 +verbose = False + +try: + opts, args = getopt.getopt(sys.argv[1:], 's:t:n:v', ['gitstate=', 'tempdir=', 'nrepack=', 'verbose']) + for o, a in opts: + if o in ('-s', '--gitstate'): + state = a + state = os.path.abspath(state) + if o in ('-n', '--nrepack'): + opt_nrepack = int(a) + if o in ('-v', '--verbose'): + verbose = True + if len(args) != 1: + raise Exception('params') +except: + usage() + sys.exit(1) + +hgprj = args[0] +os.chdir(hgprj) + +if state: + if os.path.exists(state): + if verbose: + print 'State does exist, reading' + f = open(state, 'r') + hgvers = pickle.load(f) + else: + print 'State does not exist, first run' + +sock = os.popen('hg tip --template "{rev}"') +tip = sock.read() +if sock.close(): + sys.exit(1) +if verbose: + print 'tip is', tip + +# Calculate the branches +if verbose: + print 'analysing the branches...' +hgchildren["0"] = () +hgparents["0"] = (None, None) +hgbranch["0"] = "master" +for cset in range(1, int(tip) + 1): + hgchildren[str(cset)] = () + prnts = os.popen('hg log -r %d --template "{parents}"' % cset).read().strip().split(' ') + prnts = map(lambda x: x[:x.find(':')], prnts) + if prnts[0] != '': + parent = prnts[0].strip() + else: + parent = str(cset - 1) + hgchildren[parent] += ( str(cset), ) + if len(prnts) > 1: + mparent = prnts[1].strip() + hgchildren[mparent] += ( str(cset), ) + else: + mparent = None + + hgparents[str(cset)] = (parent, mparent) + + if mparent: + # For merge changesets, take either one, preferably the 'master' branch + if hgbranch[mparent] == 'master': + hgbranch[str(cset)] = 'master' + else: + hgbranch[str(cset)] = hgbranch[parent] + else: + # Normal changesets + # For first children, take the parent branch, for the others create a new branch + if hgchildren[parent][0] == str(cset): + hgbranch[str(cset)] = hgbranch[parent] + else: + hgbranch[str(cset)] = "branch-" + str(cset) + +if not hgvers.has_key("0"): + print 'creating repository' + os.system('git init') + +# loop through every hg changeset +for cset in range(int(tip) + 1): + + # incremental, already seen + if hgvers.has_key(str(cset)): + continue + hgnewcsets += 1 + + # get info + log_data = os.popen('hg log -r %d --template "{tags}\n{date|date}\n{author}\n"' % cset).readlines() + tag = log_data[0].strip() + date = log_data[1].strip() + user = log_data[2].strip() + parent = hgparents[str(cset)][0] + mparent = hgparents[str(cset)][1] + + #get comment + (fdcomment, filecomment) = tempfile.mkstemp() + csetcomment = os.popen('hg log -r %d --template "{desc}"' % cset).read().strip() + os.write(fdcomment, csetcomment) + os.close(fdcomment) + + print '-----------------------------------------' + print 'cset:', cset + print 'branch:', hgbranch[str(cset)] + print 'user:', user + print 'date:', date + print 'comment:', csetcomment + if parent: + print 'parent:', parent + if mparent: + print 'mparent:', mparent + if tag: + print 'tag:', tag + print '-----------------------------------------' + + # checkout the parent if necessary + if cset != 0: + if hgbranch[str(cset)] == "branch-" + str(cset): + print 'creating new branch', hgbranch[str(cset)] + os.system('git checkout -b %s %s' % (hgbranch[str(cset)], hgvers[parent])) + else: + print 'checking out branch', hgbranch[str(cset)] + os.system('git checkout %s' % hgbranch[str(cset)]) + + # merge + if mparent: + if hgbranch[parent] == hgbranch[str(cset)]: + otherbranch = hgbranch[mparent] + else: + otherbranch = hgbranch[parent] + print 'merging', otherbranch, 'into', hgbranch[str(cset)] + os.system(getgitenv(user, date) + 'git merge --no-commit -s ours "" %s %s' % (hgbranch[str(cset)], otherbranch)) + + # remove everything except .git and .hg directories + os.system('find . \( -path "./.hg" -o -path "./.git" \) -prune -o ! -name "." -print | xargs rm -rf') + + # repopulate with checkouted files + os.system('hg update -C %d' % cset) + + # add new files + os.system('git ls-files -x .hg --others | git update-index --add --stdin') + # delete removed files + os.system('git ls-files -x .hg --deleted | git update-index --remove --stdin') + + # commit + os.system(getgitenv(user, date) + 'git commit --allow-empty --allow-empty-message -a -F %s' % filecomment) + os.unlink(filecomment) + + # tag + if tag and tag != 'tip': + os.system(getgitenv(user, date) + 'git tag %s' % tag) + + # delete branch if not used anymore... + if mparent and len(hgchildren[str(cset)]): + print "Deleting unused branch:", otherbranch + os.system('git branch -d %s' % otherbranch) + + # retrieve and record the version + vvv = os.popen('git show --quiet --pretty=format:%H').read() + print 'record', cset, '->', vvv + hgvers[str(cset)] = vvv + +if hgnewcsets >= opt_nrepack and opt_nrepack != -1: + os.system('git repack -a -d') + +# write the state for incrementals +if state: + if verbose: + print 'Writing state' + f = open(state, 'w') + pickle.dump(hgvers, f) + +# vim: et ts=8 sw=4 sts=4 diff --git a/contrib/hg-to-git/hg-to-git.txt b/contrib/hg-to-git/hg-to-git.txt new file mode 100644 index 000000000000..91f8fe6410c0 --- /dev/null +++ b/contrib/hg-to-git/hg-to-git.txt @@ -0,0 +1,21 @@ +hg-to-git.py is able to convert a Mercurial repository into a git one, +and preserves the branches in the process (unlike tailor) + +hg-to-git.py can probably be greatly improved (it's a rather crude +combination of shell and python) but it does already work quite well for +me. Features: + - supports incremental conversion + (for keeping a git repo in sync with a hg one) + - supports hg branches + - converts hg tags + +Note that the git repository will be created 'in place' (at the same +location as the source hg repo). You will have to manually remove the +'.hg' directory after the conversion. + +Also note that the incremental conversion uses 'simple' hg changesets +identifiers (ordinals, as opposed to SHA-1 ids), and since these ids +are not stable across different repositories the hg-to-git.py state file +is forever tied to one hg repository. + +Stelian Pop <stelian@popies.net> diff --git a/contrib/hooks/multimail/CHANGES b/contrib/hooks/multimail/CHANGES new file mode 100644 index 000000000000..35791fd02c21 --- /dev/null +++ b/contrib/hooks/multimail/CHANGES @@ -0,0 +1,285 @@ +Release 1.5.0 +============= + +Backward-incompatible change +---------------------------- + +The name of classes for environment was misnamed as `*Environement`. +It is now `*Environment`. + +New features +------------ + +* A Thread-Index header is now added to each email sent (except for + combined emails where it would not make sense), so that MS Outlook + properly groups messages by threads even though they have a + different subject line. Unfortunately, even adding this header the + threading still seems to be unreliable, but it is unclear whether + this is an issue on our side or on MS Outlook's side (see discussion + here: https://github.com/git-multimail/git-multimail/pull/194). + +* A new variable multimailhook.ExcludeMergeRevisions was added to send + notification emails only for non-merge commits. + +* For gitolite environment, it is now possible to specify the mail map + in a separate file in addition to gitolite.conf, using the variable + multimailhook.MailaddressMap. + +Internal changes +---------------- + +* The testsuite now uses GIT_PRINT_SHA1_ELLIPSIS where needed for + compatibility with recent Git versions. Only tests are affected. + +* We don't try to install pyflakes in the continuous integration job + for old Python versions where it's no longer available. + +* Stop using the deprecated cgi.escape in Python 3. + +* New flake8 warnings have been fixed. + +* Python 3.6 is now tested against on Travis-CI. + +* A bunch of lgtm.com warnings have been fixed. + +Bug fixes +--------- + +* SMTPMailer logs in only once now. It used to re-login for each email + sent which triggered errors for some SMTP servers. + +* migrate-mailhook-config was broken by internal refactoring, it + should now work again. + +This version was tested with Python 2.6 to 3.7. It was tested with Git +1.7.10.406.gdc801, 2.15.1 and 2.20.1.98.gecbdaf0. + +Release 1.4.0 +============= + +New features to troubleshoot a git-multimail installation +--------------------------------------------------------- + +* One can now perform a basic check of git-multimail's setup by + running the hook with the environment variable + GIT_MULTIMAIL_CHECK_SETUP set to a non-empty string. See + doc/troubleshooting.rst for details. + +* A new log files system was added. See the multimailhook.logFile, + multimailhook.errorLogFile and multimailhook.debugLogFile variables. + +* git_multimail.py can now be made more verbose using + multimailhook.verbose. + +* A new option --check-ref-filter is now available to help debugging + the refFilter* options. + +Formatting emails +----------------- + +* Formatting of emails was made slightly more compact, to reduce the + odds of having long subject lines truncated or wrapped in short list + of commits. + +* multimailhook.emailPrefix may now use the '%(repo_shortname)s' + placeholder for the repository's short name. + +* A new option multimailhook.subjectMaxLength is available to truncate + overly long subject lines. + +Bug fixes and minor changes +--------------------------- + +* Options refFilterDoSendRegex and refFilterDontSendRegex were + essentially broken. They should work now. + +* The behavior when both refFilter{Do,Dont}SendRegex and + refFilter{Exclusion,Inclusion}Regex are set have been slightly + changed. Exclusion/Inclusion is now strictly stronger than + DoSend/DontSend. + +* The management of precedence when a setting can be computed in + multiple ways has been considerably refactored and modified. + multimailhook.from and multimailhook.reponame now have precedence + over the environment-specific settings ($GL_REPO/$GL_USER for + gitolite, --stash-user/repo for Stash, --submitter/--project for + Gerrit). + +* The coverage of the testsuite has been considerably improved. All + configuration variables now appear at least once in the testsuite. + +This version was tested with Python 2.6 to 3.5. It also mostly works +with Python 2.4, but there is one known breakage in the testsuite +related to non-ascii characters. It was tested with Git +1.7.10.406.gdc801, 1.8.5.6, 2.1.4, and 2.10.0.rc0.1.g07c9292. + +Release 1.3.1 (bugfix-only release) +=================================== + +* Generate links to commits in combined emails (it was done only for + commit emails in 1.3.0). + +* Fix broken links on PyPi. + +Release 1.3.0 +============= + +* New options multimailhook.htmlInIntro and multimailhook.htmlInFooter + now allow using HTML in the introduction and footer of emails (e.g. + for a more pleasant formatting or to insert a link to the commit on + a web interface). + +* A new option multimailhook.commitBrowseURL gives a simpler (and less + flexible) way to add a link to a web interface for commit emails + than multimailhook.htmlInIntro and multimailhook.htmlInFooter. + +* A new public function config.add_config_parameters was added to + allow custom hooks to set specific Git configuration variables + without modifying the configuration files. See an example in + post-receive.example. + +* Error handling for SMTP has been improved (we used to print Python + backtraces for legitimate errors). + +* The SMTP mailer can now check TLS certificates when the newly added + configuration variable multimailhook.smtpCACerts. + +* Python 3 portability has been improved. + +* The documentation's formatting has been improved. + +* The testsuite has been improved (we now use pyflakes to check for + errors in the code). + +This version has been tested with Python 2.4 and 2.6 to 3.5, and Git +v1.7.10-406-gdc801e7, 2.1.4 and 2.8.1.339.g3ad15fd. + +No change since 1.3 RC1. + +Release 1.2.0 +============= + +* It is now possible to exclude some refs (e.g. exclude some branches + or tags). See refFilterDoSendRegex, refFilterDontSendRegex, + refFilterInclusionRegex and refFilterExclusionRegex. + +* New commitEmailFormat option which can be set to "html" to generate + simple colorized diffs using HTML for the commit emails. + +* git-multimail can now be ran as a Gerrit ref-updated hook, or from + Atlassian BitBucket Server (formerly known as Atlassian Stash). + +* The From: field is now more customizeable. It can be set + independently for refchange emails and commit emails (see + fromCommit, fromRefChange). The special values pusher and author can + be used in these configuration variable. + +* A new command-line option, --version, was added. The version is also + available in the X-Git-Multimail-Version header of sent emails. + +* Set X-Git-NotificationType header to differentiate the various types + of notifications. Current values are: diff, ref_changed_plus_diff, + ref_changed. + +* Preliminary support for Python 3. The testsuite passes with Python 3, + but it has not received as much testing as the Python 2 version yet. + +* Several encoding-related fixes. UTF-8 characters work in more + situations (but non-ascii characters in email address are still not + supported). + +* The testsuite and its documentation has been greatly improved. + +Plus all the bugfixes from version 1.1.1. + +This version has been tested with Python 2.4 and 2.6 to 3.5, and Git +v1.7.10-406-gdc801e7, git-1.8.2.3 and 2.6.0. Git versions prior to +v1.7.10-406-gdc801e7 probably work, but cannot run the testsuite +properly. + +Release 1.1.1 (bugfix-only release) +=================================== + +* The SMTP mailer was not working with Python 2.4. + +Release 1.1.0 +============= + +* When a single commit is pushed, omit the reference changed email. + Set multimailhook.combineWhenSingleCommit to false to disable this + new feature. + +* In gitolite environments, the pusher's email address can be used as + the From address by creating a specially formatted comment block in + gitolite.conf (see multimailhook.from in README). + +* Support for SMTP authentication and SSL/TLS encryption was added, + see smtpUser, smtpPass, smtpEncryption in README. + +* A new option scanCommitForCc was added to allow git-multimail to + search the commit message for 'Cc: ...' lines, and add the + corresponding emails in Cc. + +* If $USER is not set, use the variable $USERNAME. This is needed on + Windows platform to recognize the pusher. + +* The emailPrefix variable can now be set to an empty string to remove + the prefix. + +* A short tutorial was added in doc/gitolite.rst to set up + git-multimail with gitolite. + +* The post-receive file was renamed to post-receive.example. It has + always been an example (the standard way to call git-multimail is to + call git_multimail.py), but it was unclear to many users. + +* A new refchangeShowGraph option was added to make it possible to + include both a graph and a log in the summary emails. The options + to control the graph formatting can be set via the new graphOpts + option. + +* New option --force-send was added to disable new commit detection + for update hook. One use-case is to run git_multimail.py after + running "git fetch" to send emails about commits that have just been + fetched (the detection of new commits was unreliable in this mode). + +* The testing infrastructure was considerably improved (continuous + integration with travis-ci, automatic check of PEP8 and RST syntax, + many improvements to the test scripts). + +This version has been tested with Python 2.4 to 2.7, and Git 1.7.1 to +2.4. + +Release 1.0.0 +============= + +* Fix encoding of non-ASCII email addresses in email headers. + +* Fix backwards-compatibility bugs for older Python 2.x versions. + +* Fix a backwards-compatibility bug for Git 1.7.1. + +* Add an option commitDiffOpts to customize logs for revisions. + +* Pass "-oi" to sendmail by default to prevent premature termination + on a line containing only ".". + +* Stagger email "Date:" values in an attempt to help mail clients + thread the emails in the right order. + +* If a mailing list setting is missing, just skip sending the + corresponding email (with a warning) instead of failing. + +* Add a X-Git-Host header that can be used for email filtering. + +* Allow the sender's fully-qualified domain name to be configured. + +* Minor documentation improvements. + +* Add this CHANGES file. + + +Release 0.9.0 +============= + +* Initial release. diff --git a/contrib/hooks/multimail/CONTRIBUTING.rst b/contrib/hooks/multimail/CONTRIBUTING.rst new file mode 100644 index 000000000000..de20a5428730 --- /dev/null +++ b/contrib/hooks/multimail/CONTRIBUTING.rst @@ -0,0 +1,60 @@ +Contributing +============ + +git-multimail is an open-source project, built by volunteers. We would +welcome your help! + +The current maintainers are `Matthieu Moy <http://matthieu-moy.fr>`__ and +`Michael Haggerty <https://github.com/mhagger>`__. + +Please note that although a copy of git-multimail is distributed in +the "contrib" section of the main Git project, development takes place +in a separate `git-multimail repository on GitHub`_. + +Whenever enough changes to git-multimail have accumulated, a new +code-drop of git-multimail will be submitted for inclusion in the Git +project. + +We use the GitHub issue tracker to keep track of bugs and feature +requests, and we use GitHub pull requests to exchange patches (though, +if you prefer, you can send patches via the Git mailing list with CC +to the maintainers). Please sign off your patches as per the `Git +project practice +<https://github.com/git/git/blob/master/Documentation/SubmittingPatches#L234>`__. + +Please vote for issues you would like to be addressed in priority +(click "add your reaction" and then the "+1" thumbs-up button on the +GitHub issue). + +General discussion of git-multimail can take place on the main `Git +mailing list`_. + +Please CC emails regarding git-multimail to the maintainers so that we +don't overlook them. + +Help needed: testers/maintainer for specific environments/OS +------------------------------------------------------------ + +The current maintainer uses and tests git-multimail on Linux with the +Generic environment. More testers, or better contributors are needed +to test git-multimail on other real-life setups: + +* Mac OS X, Windows: git-multimail is currently not supported on these + platforms. But since we have no external dependencies and try to + write code as portable as possible, it is possible that + git-multimail already runs there and if not, it is likely that it + could be ported easily. + + Patches to improve support for Windows and OS X are welcome. + Ideally, there would be a sub-maintainer for each OS who would test + at least once before each release (around twice a year). + +* Gerrit, Stash, Gitolite environments: although the testsuite + contains tests for these environments, a tester/maintainer for each + environment would be welcome to test and report failure (or success) + on real-life environments periodically (here also, feedback before + each release would be highly appreciated). + + +.. _`git-multimail repository on GitHub`: https://github.com/git-multimail/git-multimail +.. _`Git mailing list`: git@vger.kernel.org diff --git a/contrib/hooks/multimail/README.Git b/contrib/hooks/multimail/README.Git new file mode 100644 index 000000000000..044444245d09 --- /dev/null +++ b/contrib/hooks/multimail/README.Git @@ -0,0 +1,15 @@ +This copy of git-multimail is distributed as part of the "contrib" +section of the Git project as a convenience to Git users. +git-multimail is developed as an independent project at the following +website: + + https://github.com/git-multimail/git-multimail + +The version in this directory was obtained from the upstream project +on January 07 2019 and consists of the "git-multimail" subdirectory from +revision + + 04e80e6c40be465cc62b6c246f0fcb8fd2cfd454 refs/tags/1.5.0 + +Please see the README file in this directory for information about how +to report bugs or contribute to git-multimail. diff --git a/contrib/hooks/multimail/README.migrate-from-post-receive-email b/contrib/hooks/multimail/README.migrate-from-post-receive-email new file mode 100644 index 000000000000..1e6a976699aa --- /dev/null +++ b/contrib/hooks/multimail/README.migrate-from-post-receive-email @@ -0,0 +1,145 @@ +git-multimail is close to, but not exactly, a plug-in replacement for +the old Git project script contrib/hooks/post-receive-email. This +document describes the differences and explains how to configure +git-multimail to get behavior closest to that of post-receive-email. + +If you are in a hurry +===================== + +A script called migrate-mailhook-config is included with +git-multimail. If you run this script within a Git repository that is +configured to use post-receive-email, it will convert the +configuration settings into the approximate equivalent settings for +git-multimail. For more information, run + + migrate-mailhook-config --help + + +Configuration differences +========================= + +* The names of the config options for git-multimail are in namespace + "multimailhook.*" instead of "hooks.*". (Editorial comment: + post-receive-email should never have used such a generic top-level + namespace.) + +* In emails about new annotated tags, post-receive-email includes a + shortlog of all changes since the previous annotated tag. To get + this behavior with git-multimail, you need to set + multimailhook.announceshortlog to true: + + git config multimailhook.announceshortlog true + +* multimailhook.commitlist -- This is a new configuration variable. + Recipients listed here will receive a separate email for each new + commit. However, if this variable is *not* set, it defaults to the + value of multimailhook.mailinglist. Therefore, if you *don't* want + the members of multimailhook.mailinglist to receive one email per + commit, then set this value to the empty string: + + git config multimailhook.commitlist '' + +* multimailhook.emailprefix -- If this value is not set, then the + subjects of generated emails are prefixed with the short name of the + repository enclosed in square brackets; e.g., "[myrepo]". + post-receive-email defaults to prefix "[SCM]" if this option is not + set. So if you were using the old default and want to retain it + (for example, to avoid having to change your email filters), set + this variable explicitly to the old value: + + git config multimailhook.emailprefix "[SCM]" + +* The "multimailhook.showrev" configuration option is not supported. + Its main use is obsoleted by the one-email-per-commit feature of + git-multimail. + + +Other differences +================= + +This section describes other differences in the behavior of +git-multimail vs. post-receive-email. For full details, please refer +to the main README file: + +* One email per commit. For each reference change, the script first + outputs one email summarizing the reference change (including + one-line summaries of the new commits), then it outputs a separate + email for each new commit that was introduced, including patches. + These one-email-per-commit emails go to the addresses listed in + multimailhook.commitlist. post-receive-email sends only one email + for each *reference* that is changed, no matter how many commits + were added to the reference. + +* Better algorithm for detecting new commits. post-receive-email + processes one reference change at a time, which causes it to fail to + describe new commits that were included in multiple branches. For + example, if a single push adds the "*" commits in the diagram below, + then post-receive-email would never include the details of the two + commits that are common to "master" and "branch" in its + notifications. + + o---o---o---*---*---* <-- master + \ + *---* <-- branch + + git-multimail analyzes all reference modifications to determine + which commits were not present before the change, therefore avoiding + that error. + +* In reference change emails, git-multimail tells which commits have + been added to the reference vs. are entirely new to the repository, + and which commits that have been omitted from the reference + vs. entirely discarded from the repository. + +* The environment in which Git is running can be configured via an + "Environment" abstraction. + +* Built-in support for Gitolite-managed repositories. + +* Instead of using full SHA1 object names in emails, git-multimail + mostly uses abbreviated SHA1s, plus one-line log message summaries + where appropriate. + +* In the schematic diagrams that explain non-fast-forward commits, + git-multimail shows the names of the branches involved. + +* The emails generated by git-multimail include the name of the Git + repository that was modified; this is convenient for recipients who + are monitoring multiple repositories. + +* git-multimail allows the email "From" addresses to be configured. + +* The recipients lists (multimailhook.mailinglist, + multimailhook.refchangelist, multimailhook.announcelist, and + multimailhook.commitlist) can be comma-separated values and/or + multivalued settings in the config file; e.g., + + [multimailhook] + mailinglist = mr.brown@example.com, mr.black@example.com + announcelist = Him <him@example.com> + announcelist = Jim <jim@example.com> + announcelist = pop@example.com + + This might make it easier to maintain short recipients lists without + requiring full-fledged mailing list software. + +* By default, git-multimail sets email "Reply-To" headers to reply to + the pusher (for reference updates) and to the author (for commit + notifications). By default, the pusher's email address is + constructed by appending "multimailhook.emaildomain" to the pusher's + username. + +* The generated emails contain a configurable footer. By default, it + lists the name of the administrator who should be contacted to + unsubscribe from notification emails. + +* New option multimailhook.emailmaxlinelength to limit the length of + lines in the main part of the email body. The default limit is 500 + characters. + +* New option multimailhook.emailstrictutf8 to ensure that the main + part of the email body is valid UTF-8. Invalid characters are + turned into the Unicode replacement character, U+FFFD. By default + this option is turned on. + +* Written in Python. Easier to add new features. diff --git a/contrib/hooks/multimail/README.rst b/contrib/hooks/multimail/README.rst new file mode 100644 index 000000000000..7c0fc4a6ef00 --- /dev/null +++ b/contrib/hooks/multimail/README.rst @@ -0,0 +1,774 @@ +git-multimail version 1.5.0 +=========================== + +.. image:: https://travis-ci.org/git-multimail/git-multimail.svg?branch=master + :target: https://travis-ci.org/git-multimail/git-multimail + +git-multimail is a tool for sending notification emails on pushes to a +Git repository. It includes a Python module called ``git_multimail.py``, +which can either be used as a hook script directly or can be imported +as a Python module into another script. + +git-multimail is derived from the Git project's old +contrib/hooks/post-receive-email, and is mostly compatible with that +script. See README.migrate-from-post-receive-email for details about +the differences and for how to migrate from post-receive-email to +git-multimail. + +git-multimail, like the rest of the Git project, is licensed under +GPLv2 (see the COPYING file for details). + +Please note: although, as a convenience, git-multimail may be +distributed along with the main Git project, development of +git-multimail takes place in its own, separate project. Please, read +`<CONTRIBUTING.rst>`__ for more information. + + +By default, for each push received by the repository, git-multimail: + +1. Outputs one email summarizing each reference that was changed. + These "reference change" (called "refchange" below) emails describe + the nature of the change (e.g., was the reference created, deleted, + fast-forwarded, etc.) and include a one-line summary of each commit + that was added to the reference. + +2. Outputs one email for each new commit that was introduced by the + reference change. These "commit" emails include a list of the + files changed by the commit, followed by the diffs of files + modified by the commit. The commit emails are threaded to the + corresponding reference change email via "In-Reply-To". This style + (similar to the "git format-patch" style used on the Git mailing + list) makes it easy to scan through the emails, jump to patches + that need further attention, and write comments about specific + commits. Commits are handled in reverse topological order (i.e., + parents shown before children). For example:: + + [git] branch master updated + + [git] 01/08: doc: fix xref link from api docs to manual pages + + [git] 02/08: api-credentials.txt: show the big picture first + + [git] 03/08: api-credentials.txt: mention credential.helper explicitly + + [git] 04/08: api-credentials.txt: add "see also" section + + [git] 05/08: t3510 (cherry-pick-sequence): add missing '&&' + + [git] 06/08: Merge branch 'rr/maint-t3510-cascade-fix' + + [git] 07/08: Merge branch 'mm/api-credentials-doc' + + [git] 08/08: Git 1.7.11-rc2 + + By default, each commit appears in exactly one commit email, the + first time that it is pushed to the repository. If a commit is later + merged into another branch, then a one-line summary of the commit + is included in the reference change email (as usual), but no + additional commit email is generated. See + `multimailhook.refFilter(Inclusion|Exclusion|DoSend|DontSend)Regex` + below to configure which branches and tags are watched by the hook. + + By default, reference change emails have their "Reply-To" field set + to the person who pushed the change, and commit emails have their + "Reply-To" field set to the author of the commit. + +3. Output one "announce" mail for each new annotated tag, including + information about the tag and optionally a shortlog describing the + changes since the previous tag. Such emails might be useful if you + use annotated tags to mark releases of your project. + + +Requirements +------------ + +* Python 2.x, version 2.4 or later. No non-standard Python modules + are required. git-multimail has preliminary support for Python 3 + (but it has been better tested with Python 2). + +* The ``git`` command must be in your PATH. git-multimail is known to + work with Git versions back to 1.7.1. (Earlier versions have not + been tested; if you do so, please report your results.) + +* To send emails using the default configuration, a standard sendmail + program must be located at '/usr/sbin/sendmail' or + '/usr/lib/sendmail' and must be configured correctly to send emails. + If this is not the case, set multimailhook.sendmailCommand, or see + the multimailhook.mailer configuration variable below for how to + configure git-multimail to send emails via an SMTP server. + +* git-multimail is currently tested only on Linux. It may or may not + work on other platforms such as Windows and Mac OS. See + `<CONTRIBUTING.rst>`__ to improve the situation. + + +Invocation +---------- + +``git_multimail.py`` is designed to be used as a ``post-receive`` hook in a +Git repository (see githooks(5)). Link or copy it to +$GIT_DIR/hooks/post-receive within the repository for which email +notifications are desired. Usually it should be installed on the +central repository for a project, to which all commits are eventually +pushed. + +For use on pre-v1.5.1 Git servers, ``git_multimail.py`` can also work as +an ``update`` hook, taking its arguments on the command line. To use +this script in this manner, link or copy it to $GIT_DIR/hooks/update. +Please note that the script is not completely reliable in this mode +[1]_. + +Alternatively, ``git_multimail.py`` can be imported as a Python module +into your own Python post-receive script. This method is a bit more +work, but allows the behavior of the hook to be customized using +arbitrary Python code. For example, you can use a custom environment +(perhaps inheriting from GenericEnvironment or GitoliteEnvironment) to + +* change how the user who did the push is determined + +* read users' email addresses from an LDAP server or from a database + +* decide which users should be notified about which commits based on + the contents of the commits (e.g., for users who want to be notified + only about changes affecting particular files or subdirectories) + +Or you can change how emails are sent by writing your own Mailer +class. The ``post-receive`` script in this directory demonstrates how +to use ``git_multimail.py`` as a Python module. (If you make interesting +changes of this type, please consider sharing them with the +community.) + + +Troubleshooting/FAQ +------------------- + +Please read `<doc/troubleshooting.rst>`__ for frequently asked +questions and common issues with git-multimail. + + +Configuration +------------- + +By default, git-multimail mostly takes its configuration from the +following ``git config`` settings: + +multimailhook.environment + This describes the general environment of the repository. In most + cases, you do not need to specify a value for this variable: + `git-multimail` will autodetect which environment to use. + Currently supported values: + + generic + the username of the pusher is read from $USER or $USERNAME and + the repository name is derived from the repository's path. + + gitolite + Environment to use when ``git-multimail`` is ran as a gitolite_ + hook. + + The username of the pusher is read from $GL_USER, the repository + name is read from $GL_REPO, and the From: header value is + optionally read from gitolite.conf (see multimailhook.from). + + For more information about gitolite and git-multimail, read + `<doc/gitolite.rst>`__ + + stash + Environment to use when ``git-multimail`` is ran as an Atlassian + BitBucket Server (formerly known as Atlassian Stash) hook. + + **Warning:** this mode was provided by a third-party contributor + and never tested by the git-multimail maintainers. It is + provided as-is and may or may not work for you. + + This value is automatically assumed when the stash-specific + flags (``--stash-user`` and ``--stash-repo``) are specified on + the command line. When this environment is active, the username + and repo come from these two command line flags, which must be + specified. + + gerrit + Environment to use when ``git-multimail`` is ran as a + ``ref-updated`` Gerrit hook. + + This value is used when the gerrit-specific command line flags + (``--oldrev``, ``--newrev``, ``--refname``, ``--project``) for + gerrit's ref-updated hook are present. When this environment is + active, the username of the pusher is taken from the + ``--submitter`` argument if that command line option is passed, + otherwise 'Gerrit' is used. The repository name is taken from + the ``--project`` option on the command line, which must be passed. + + For more information about gerrit and git-multimail, read + `<doc/gerrit.rst>`__ + + If none of these environments is suitable for your setup, then you + can implement a Python class that inherits from Environment and + instantiate it via a script that looks like the example + post-receive script. + + The environment value can be specified on the command line using + the ``--environment`` option. If it is not specified on the + command line or by ``multimailhook.environment``, the value is + guessed as follows: + + * If stash-specific (respectively gerrit-specific) command flags + are present on the command-line, then ``stash`` (respectively + ``gerrit``) is used. + + * If the environment variables $GL_USER and $GL_REPO are set, then + ``gitolite`` is used. + + * If none of the above apply, then ``generic`` is used. + +multimailhook.repoName + A short name of this Git repository, to be used in various places + in the notification email text. The default is to use $GL_REPO + for gitolite repositories, or otherwise to derive this value from + the repository path name. + +multimailhook.mailingList + The list of email addresses to which notification emails should be + sent, as RFC 2822 email addresses separated by commas. This + configuration option can be multivalued. Leave it unset or set it + to the empty string to not send emails by default. The next few + settings can be used to configure specific address lists for + specific types of notification email. + +multimailhook.refchangeList + The list of email addresses to which summary emails about + reference changes should be sent, as RFC 2822 email addresses + separated by commas. This configuration option can be + multivalued. The default is the value in + multimailhook.mailingList. Set this value to "none" (or the empty + string) to prevent reference change emails from being sent even if + multimailhook.mailingList is set. + +multimailhook.announceList + The list of email addresses to which emails about new annotated + tags should be sent, as RFC 2822 email addresses separated by + commas. This configuration option can be multivalued. The + default is the value in multimailhook.refchangeList or + multimailhook.mailingList. Set this value to "none" (or the empty + string) to prevent annotated tag announcement emails from being sent + even if one of the other values is set. + +multimailhook.commitList + The list of email addresses to which emails about individual new + commits should be sent, as RFC 2822 email addresses separated by + commas. This configuration option can be multivalued. The + default is the value in multimailhook.mailingList. Set this value + to "none" (or the empty string) to prevent notification emails about + individual commits from being sent even if + multimailhook.mailingList is set. + +multimailhook.announceShortlog + If this option is set to true, then emails about changes to + annotated tags include a shortlog of changes since the previous + tag. This can be useful if the annotated tags represent releases; + then the shortlog will be a kind of rough summary of what has + happened since the last release. But if your tagging policy is + not so straightforward, then the shortlog might be confusing + rather than useful. Default is false. + +multimailhook.commitEmailFormat + The format of email messages for the individual commits, can be "text" or + "html". In the latter case, the emails will include diffs using colorized + HTML instead of plain text used by default. Note that this currently the + ref change emails are always sent in plain text. + + Note that when using "html", the formatting is done by parsing the + output of ``git log`` with ``-p``. When using + ``multimailhook.commitLogOpts`` to specify a ``--format`` for + ``git log``, one may get false positive (e.g. lines in the body of + the message starting with ``+++`` or ``---`` colored in red or + green). + + By default, all the message is HTML-escaped. See + ``multimailhook.htmlInIntro`` to change this behavior. + +multimailhook.commitBrowseURL + Used to generate a link to an online repository browser in commit + emails. This variable must be a string. Format directives like + ``%(<variable>)s`` will be expanded the same way as template + strings. In particular, ``%(id)s`` will be replaced by the full + Git commit identifier (40-chars hexadecimal). + + If the string does not contain any format directive, then + ``%(id)s`` will be automatically added to the string. If you don't + want ``%(id)s`` to be automatically added, use the empty format + directive ``%()s`` anywhere in the string. + + For example, a suitable value for the git-multimail project itself + would be + ``https://github.com/git-multimail/git-multimail/commit/%(id)s``. + +multimailhook.htmlInIntro, multimailhook.htmlInFooter + When generating an HTML message, git-multimail escapes any HTML + sequence by default. This means that if a template contains HTML + like ``<a href="foo">link</a>``, the reader will see the HTML + source code and not a proper link. + + Set ``multimailhook.htmlInIntro`` to true to allow writing HTML + formatting in introduction templates. Similarly, set + ``multimailhook.htmlInFooter`` for HTML in the footer. + + Variables expanded in the template are still escaped. For example, + if a repository's path contains a ``<``, it will be rendered as + such in the message. + + Read `<doc/customizing-emails.rst>`__ for more details and + examples. + +multimailhook.refchangeShowGraph + If this option is set to true, then summary emails about reference + changes will additionally include: + + * a graph of the added commits (if any) + + * a graph of the discarded commits (if any) + + The log is generated by running ``git log --graph`` with the options + specified in graphOpts. The default is false. + +multimailhook.refchangeShowLog + If this option is set to true, then summary emails about reference + changes will include a detailed log of the added commits in + addition to the one line summary. The log is generated by running + ``git log`` with the options specified in multimailhook.logOpts. + Default is false. + +multimailhook.mailer + This option changes the way emails are sent. Accepted values are: + + * **sendmail (the default)**: use the command ``/usr/sbin/sendmail`` or + ``/usr/lib/sendmail`` (or sendmailCommand, if configured). This + mode can be further customized via the following options: + + multimailhook.sendmailCommand + The command used by mailer ``sendmail`` to send emails. Shell + quoting is allowed in the value of this setting, but remember that + Git requires double-quotes to be escaped; e.g.:: + + git config multimailhook.sendmailcommand '/usr/sbin/sendmail -oi -t -F \"Git Repo\"' + + Default is '/usr/sbin/sendmail -oi -t' or + '/usr/lib/sendmail -oi -t' (depending on which file is + present and executable). + + multimailhook.envelopeSender + If set then pass this value to sendmail via the -f option to set + the envelope sender address. + + * **smtp**: use Python's smtplib. This is useful when the sendmail + command is not available on the system. This mode can be + further customized via the following options: + + multimailhook.smtpServer + The name of the SMTP server to connect to. The value can + also include a colon and a port number; e.g., + ``mail.example.com:25``. Default is 'localhost' using port 25. + + multimailhook.smtpUser, multimailhook.smtpPass + Server username and password. Required if smtpEncryption is 'ssl'. + Note that the username and password currently need to be + set cleartext in the configuration file, which is not + recommended. If you need to use this option, be sure your + configuration file is read-only. + + multimailhook.envelopeSender + The sender address to be passed to the SMTP server. If + unset, then the value of multimailhook.from is used. + + multimailhook.smtpServerTimeout + Timeout in seconds. Default is 10. + + multimailhook.smtpEncryption + Set the security type. Allowed values: ``none``, ``ssl``, ``tls`` (starttls). + Default is ``none``. + + multimailhook.smtpCACerts + Set the path to a list of trusted CA certificate to verify the + server certificate, only supported when ``smtpEncryption`` is + ``tls``. If unset or empty, the server certificate is not + verified. If it targets a file containing a list of trusted CA + certificates (PEM format) these CAs will be used to verify the + server certificate. For debian, you can set + ``/etc/ssl/certs/ca-certificates.crt`` for using the system + trusted CAs. For self-signed server, you can add your server + certificate to the system store:: + + cd /usr/local/share/ca-certificates/ + openssl s_client -starttls smtp \ + -connect mail.example.net:587 -showcerts \ + </dev/null 2>/dev/null \ + | openssl x509 -outform PEM >mail.example.net.crt + update-ca-certificates + + and used the updated ``/etc/ssl/certs/ca-certificates.crt``. Or + directly use your ``/path/to/mail.example.net.crt``. Default is + unset. + + multimailhook.smtpServerDebugLevel + Integer number. Set to greater than 0 to activate debugging. + +multimailhook.from, multimailhook.fromCommit, multimailhook.fromRefchange + If set, use this value in the From: field of generated emails. + ``fromCommit`` is used for commit emails, ``fromRefchange`` is + used for refchange emails, and ``from`` is used as fall-back in + all cases. + + The value for these variables can be either: + + - An email address, which will be used directly. + + - The value ``pusher``, in which case the pusher's address (if + available) will be used. + + - The value ``author`` (meaningful only for ``fromCommit``), in which + case the commit author's address will be used. + + If config values are unset, the value of the From: header is + determined as follows: + + 1. (gitolite environment only) + 1.a) If ``multimailhook.MailaddressMap`` is set, and is a path + to an existing file (if relative, it is considered relative to + the place where ``gitolite.conf`` is located), then this file + should contain lines like:: + + username Firstname Lastname <email@example.com> + + git-multimail will then look for a line where ``$GL_USER`` + matches the ``username`` part, and use the rest of the line for + the ``From:`` header. + + 1.b) Parse gitolite.conf, looking for a block of comments that + looks like this:: + + # BEGIN USER EMAILS + # username Firstname Lastname <email@example.com> + # END USER EMAILS + + If that block exists, and there is a line between the BEGIN + USER EMAILS and END USER EMAILS lines where the first field + matches the gitolite username ($GL_USER), use the rest of the + line for the From: header. + + 2. If the user.email configuration setting is set, use its value + (and the value of user.name, if set). + + 3. Use the value of multimailhook.envelopeSender. + +multimailhook.MailaddressMap + (gitolite environment only) + File to look for a ``From:`` address based on the user doing the + push. Defaults to unset. See ``multimailhook.from`` for details. + +multimailhook.administrator + The name and/or email address of the administrator of the Git + repository; used in FOOTER_TEMPLATE. Default is + multimailhook.envelopesender if it is set; otherwise a generic + string is used. + +multimailhook.emailPrefix + All emails have this string prepended to their subjects, to aid + email filtering (though filtering based on the X-Git-* email + headers is probably more robust). Default is the short name of + the repository in square brackets; e.g., ``[myrepo]``. Set this + value to the empty string to suppress the email prefix. You may + use the placeholder ``%(repo_shortname)s`` for the short name of + the repository. + +multimailhook.emailMaxLines + The maximum number of lines that should be included in the body of + a generated email. If not specified, there is no limit. Lines + beyond the limit are suppressed and counted, and a final line is + added indicating the number of suppressed lines. + +multimailhook.emailMaxLineLength + The maximum length of a line in the email body. Lines longer than + this limit are truncated to this length with a trailing ``[...]`` + added to indicate the missing text. The default is 500, because + (a) diffs with longer lines are probably from binary files, for + which a diff is useless, and (b) even if a text file has such long + lines, the diffs are probably unreadable anyway. To disable line + truncation, set this option to 0. + +multimailhook.subjectMaxLength + The maximum length of the subject line (i.e. the ``oneline`` field + in templates, not including the prefix). Lines longer than this + limit are truncated to this length with a trailing ``[...]`` added + to indicate the missing text. This option The default is to use + ``multimailhook.emailMaxLineLength``. This option avoids sending + emails with overly long subject lines, but should not be needed if + the commit messages follow the Git convention (one short subject + line, then a blank line, then the message body). To disable line + truncation, set this option to 0. + +multimailhook.maxCommitEmails + The maximum number of commit emails to send for a given change. + When the number of patches is larger that this value, only the + summary refchange email is sent. This can avoid accidental + mailbombing, for example on an initial push. To disable commit + emails limit, set this option to 0. The default is 500. + +multimailhook.excludeMergeRevisions + When sending out revision emails, do not consider merge commits (the + functional equivalent of `rev-list --no-merges`). + The default is `false` (send merge commit emails). + +multimailhook.emailStrictUTF8 + If this boolean option is set to `true`, then the main part of the + email body is forced to be valid UTF-8. Any characters that are + not valid UTF-8 are converted to the Unicode replacement + character, U+FFFD. The default is `true`. + + This option is ineffective with Python 3, where non-UTF-8 + characters are unconditionally replaced. + +multimailhook.diffOpts + Options passed to ``git diff-tree`` when generating the summary + information for ReferenceChange emails. Default is ``--stat + --summary --find-copies-harder``. Add -p to those options to + include a unified diff of changes in addition to the usual summary + output. Shell quoting is allowed; see ``multimailhook.logOpts`` for + details. + +multimailhook.graphOpts + Options passed to ``git log --graph`` when generating graphs for the + reference change summary emails (used only if refchangeShowGraph + is true). The default is '--oneline --decorate'. + + Shell quoting is allowed; see logOpts for details. + +multimailhook.logOpts + Options passed to ``git log`` to generate additional info for + reference change emails (used only if refchangeShowLog is set). + For example, adding -p will show each commit's complete diff. The + default is empty. + + Shell quoting is allowed; for example, a log format that contains + spaces can be specified using something like:: + + git config multimailhook.logopts '--pretty=format:"%h %aN <%aE>%n%s%n%n%b%n"' + + If you want to set this by editing your configuration file + directly, remember that Git requires double-quotes to be escaped + (see git-config(1) for more information):: + + [multimailhook] + logopts = --pretty=format:\"%h %aN <%aE>%n%s%n%n%b%n\" + +multimailhook.commitLogOpts + Options passed to ``git log`` to generate additional info for + revision change emails. For example, adding --ignore-all-spaces + will suppress whitespace changes. The default options are ``-C + --stat -p --cc``. Shell quoting is allowed; see + multimailhook.logOpts for details. + +multimailhook.dateSubstitute + String to use as a substitute for ``Date:`` in the output of ``git + log`` while formatting commit messages. This is useful to avoid + emitting a line that can be interpreted by mailers as the start of + a cited message (Zimbra webmail in particular). Defaults to + ``CommitDate:``. Set to an empty string or ``none`` to deactivate + the behavior. + +multimailhook.emailDomain + Domain name appended to the username of the person doing the push + to convert it into an email address + (via ``"%s@%s" % (username, emaildomain)``). More complicated + schemes can be implemented by overriding Environment and + overriding its get_pusher_email() method. + +multimailhook.replyTo, multimailhook.replyToCommit, multimailhook.replyToRefchange + Addresses to use in the Reply-To: field for commit emails + (replyToCommit) and refchange emails (replyToRefchange). + multimailhook.replyTo is used as default when replyToCommit or + replyToRefchange is not set. The shortcuts ``pusher`` and + ``author`` are allowed with the same semantics as for + ``multimailhook.from``. In addition, the value ``none`` can be + used to omit the ``Reply-To:`` field. + + The default is ``pusher`` for refchange emails, and ``author`` for + commit emails. + +multimailhook.quiet + Do not output the list of email recipients from the hook + +multimailhook.stdout + For debugging, send emails to stdout rather than to the + mailer. Equivalent to the --stdout command line option + +multimailhook.scanCommitForCc + If this option is set to true, than recipients from lines in commit body + that starts with ``CC:`` will be added to CC list. + Default: false + +multimailhook.combineWhenSingleCommit + If this option is set to true and a single new commit is pushed to + a branch, combine the summary and commit email messages into a + single email. + Default: true + +multimailhook.refFilterInclusionRegex, multimailhook.refFilterExclusionRegex, multimailhook.refFilterDoSendRegex, multimailhook.refFilterDontSendRegex + **Warning:** these options are experimental. They should work, but + the user-interface is not stable yet (in particular, the option + names may change). If you want to participate in stabilizing the + feature, please contact the maintainers and/or send pull-requests. + If you are happy with the current shape of the feature, please + report it too. + + Regular expressions that can be used to limit refs for which email + updates will be sent. It is an error to specify both an inclusion + and an exclusion regex. If a ``refFilterInclusionRegex`` is + specified, emails will only be sent for refs which match this + regex. If a ``refFilterExclusionRegex`` regex is specified, + emails will be sent for all refs except those that match this + regex (or that match a predefined regex specific to the + environment, such as "^refs/notes" for most environments and + "^refs/notes|^refs/changes" for the gerrit environment). + + The expressions are matched against the complete refname, and is + considered to match if any substring matches. For example, to + filter-out all tags, set ``refFilterExclusionRegex`` to + ``^refs/tags/`` (note the leading ``^`` but no trailing ``$``). If + you set ``refFilterExclusionRegex`` to ``master``, then any ref + containing ``master`` will be excluded (the ``master`` branch, but + also ``refs/tags/master`` or ``refs/heads/foo-master-bar``). + + ``refFilterDoSendRegex`` and ``refFilterDontSendRegex`` are + analogous to ``refFilterInclusionRegex`` and + ``refFilterExclusionRegex`` with one difference: with + ``refFilterDoSendRegex`` and ``refFilterDontSendRegex``, commits + introduced by one excluded ref will not be considered as new when + they reach an included ref. Typically, if you add a branch ``foo`` + to ``refFilterDontSendRegex``, push commits to this branch, and + later merge branch ``foo`` into ``master``, then the notification + email for ``master`` will contain a commit email only for the + merge commit. If you include ``foo`` in + ``refFilterExclusionRegex``, then at the time of merge, you will + receive one commit email per commit in the branch. + + These variables can be multi-valued, like:: + + [multimailhook] + refFilterExclusionRegex = ^refs/tags/ + refFilterExclusionRegex = ^refs/heads/master$ + + You can also provide a whitespace-separated list like:: + + [multimailhook] + refFilterExclusionRegex = ^refs/tags/ ^refs/heads/master$ + + Both examples exclude tags and the master branch, and are + equivalent to:: + + [multimailhook] + refFilterExclusionRegex = ^refs/tags/|^refs/heads/master$ + + ``refFilterInclusionRegex`` and ``refFilterExclusionRegex`` are + strictly stronger than ``refFilterDoSendRegex`` and + ``refFilterDontSendRegex``. In other words, adding a ref to a + DoSend/DontSend regex has no effect if it is already excluded by a + Exclusion/Inclusion regex. + +multimailhook.logFile, multimailhook.errorLogFile, multimailhook.debugLogFile + + When set, these variable designate path to files where + git-multimail will log some messages. Normal messages and error + messages are sent to ``logFile``, and error messages are also sent + to ``errorLogFile``. Debug messages and all other messages are + sent to ``debugLogFile``. The recommended way is to set only one + of these variables, but it is also possible to set several of them + (part of the information is then duplicated in several log files, + for example errors are duplicated to all log files). + + Relative path are relative to the Git repository where the push is + done. + +multimailhook.verbose + + Verbosity level of git-multimail on its standard output. By + default, show only error and info messages. If set to true, show + also debug messages. + +Email filtering aids +-------------------- + +All emails include extra headers to enable fine tuned filtering and +give information for debugging. All emails include the headers +``X-Git-Host``, ``X-Git-Repo``, ``X-Git-Refname``, and ``X-Git-Reftype``. +ReferenceChange emails also include headers ``X-Git-Oldrev`` and ``X-Git-Newrev``; +Revision emails also include header ``X-Git-Rev``. + + +Customizing email contents +-------------------------- + +git-multimail mostly generates emails by expanding templates. The +templates can be customized. To avoid the need to edit +``git_multimail.py`` directly, the preferred way to change the templates +is to write a separate Python script that imports ``git_multimail.py`` as +a module, then replaces the templates in place. See the provided +post-receive script for an example of how this is done. + + +Customizing git-multimail for your environment +---------------------------------------------- + +git-multimail is mostly customized via an "environment" that describes +the local environment in which Git is running. Two types of +environment are built in: + +GenericEnvironment + a stand-alone Git repository. + +GitoliteEnvironment + a Git repository that is managed by gitolite_. For such + repositories, the identity of the pusher is read from + environment variable $GL_USER, the name of the repository is read + from $GL_REPO (if it is not overridden by multimailhook.reponame), + and the From: header value is optionally read from gitolite.conf + (see multimailhook.from). + +By default, git-multimail assumes GitoliteEnvironment if $GL_USER and +$GL_REPO are set, and otherwise assumes GenericEnvironment. +Alternatively, you can choose one of these two environments explicitly +by setting a ``multimailhook.environment`` config setting (which can +have the value `generic` or `gitolite`) or by passing an --environment +option to the script. + +If you need to customize the script in ways that are not supported by +the existing environments, you can define your own environment class +class using arbitrary Python code. To do so, you need to import +``git_multimail.py`` as a Python module, as demonstrated by the example +post-receive script. Then implement your environment class; it should +usually inherit from one of the existing Environment classes and +possibly one or more of the EnvironmentMixin classes. Then set the +``environment`` variable to an instance of your own environment class +and pass it to ``run_as_post_receive_hook()``. + +The standard environment classes, GenericEnvironment and +GitoliteEnvironment, are in fact themselves put together out of a +number of mixin classes, each of which handles one aspect of the +customization. For the finest control over your configuration, you +can specify exactly which mixin classes your own environment class +should inherit from, and override individual methods (or even add your +own mixin classes) to implement entirely new behaviors. If you +implement any mixins that might be useful to other people, please +consider sharing them with the community! + + +Getting involved +---------------- + +Please, read `<CONTRIBUTING.rst>`__ for instructions on how to +contribute to git-multimail. + + +Footnotes +--------- + +.. [1] Because of the way information is passed to update hooks, the + script's method of determining whether a commit has already + been seen does not work when it is used as an ``update`` script. + In particular, no notification email will be generated for a + new commit that is added to multiple references in the same + push. A workaround is to use --force-send to force sending the + emails. + +.. _gitolite: https://github.com/sitaramc/gitolite diff --git a/contrib/hooks/multimail/doc/customizing-emails.rst b/contrib/hooks/multimail/doc/customizing-emails.rst new file mode 100644 index 000000000000..3f5b67f768db --- /dev/null +++ b/contrib/hooks/multimail/doc/customizing-emails.rst @@ -0,0 +1,56 @@ +Customizing the content and formatting of emails +================================================ + +Overloading template strings +---------------------------- + +The content of emails is generated based on template strings defined +in ``git_multimail.py``. You can customize these template strings +without changing the script itself, by defining a Python wrapper +around it. The python wrapper should ``import git_multimail`` and then +override the ``git_multimail.*`` strings like this:: + + import sys # needed for sys.argv + + # Import and customize git_multimail: + import git_multimail + git_multimail.REVISION_INTRO_TEMPLATE = """...""" + git_multimail.COMBINED_INTRO_TEMPLATE = git_multimail.REVISION_INTRO_TEMPLATE + + # start git_multimail itself: + git_multimail.main(sys.argv[1:]) + +The template strings can use any value already used in the existing +templates (read the source code). + +Using HTML in template strings +------------------------------ + +If ``multimailhook.commitEmailFormat`` is set to HTML, then +git-multimail will generate HTML emails for commit notifications. The +log and diff will be formatted automatically by git-multimail. By +default, any HTML special character in the templates will be escaped. + +To use HTML formatting in the introduction of the email, set +``multimailhook.htmlInIntro`` to ``true``. Then, the template can +contain any HTML tags, that will be sent as-is in the email. For +example, to add some formatting and a link to the online commit, use +a format like:: + + git_multimail.REVISION_INTRO_TEMPLATE = """\ + <span style="color:#808080">This is an automated email from the git hooks/post-receive script.</span><br /><br /> + + <strong>%(pusher)s</strong> pushed a commit to %(refname_type)s %(short_refname)s + in repository %(repo_shortname)s.<br /> + + <a href="https://github.com/git-multimail/git-multimail/commit/%(newrev)s">View on GitHub</a>. + """ + +Note that the values expanded from ``%(variable)s`` in the format +strings will still be escaped. + +For a less flexible but easier to set up way to add a link to commit +emails, see ``multimailhook.commitBrowseURL``. + +Similarly, one can set ``multimailhook.htmlInFooter`` and override any +of the ``*_FOOTER*`` template strings. diff --git a/contrib/hooks/multimail/doc/gerrit.rst b/contrib/hooks/multimail/doc/gerrit.rst new file mode 100644 index 000000000000..8011d05dec03 --- /dev/null +++ b/contrib/hooks/multimail/doc/gerrit.rst @@ -0,0 +1,56 @@ +Setting up git-multimail on Gerrit +================================== + +Gerrit has its own email-sending system, but you may prefer using +``git-multimail`` instead. It supports Gerrit natively as a Gerrit +``ref-updated`` hook (Warning: `Gerrit hooks +<https://gerrit-review.googlesource.com/Documentation/config-hooks.html>`__ +are distinct from Git hooks). Setting up ``git-multimail`` on a Gerrit +installation can be done following the instructions below. + +The explanations show an easy way to set up ``git-multimail``, +but leave ``git-multimail`` installed and unconfigured for a while. If +you run Gerrit on a production server, it is advised that you +execute the step "Set up the hook" last to avoid confusing your users +in the meantime. + +Set up the hook +--------------- + +Create a directory ``$site_path/hooks/`` if it does not exist (if you +don't know what ``$site_path`` is, run ``gerrit.sh status`` and look +for a ``GERRIT_SITE`` line). Either copy ``git_multimail.py`` to +``$site_path/hooks/ref-updated`` or create a wrapper script like +this:: + + #! /bin/sh + exec /path/to/git_multimail.py "$@" + +In both cases, make sure the file is named exactly +``$site_path/hooks/ref-updated`` and is executable. + +(Alternatively, you may configure the ``[hooks]`` section of +gerrit.config) + +Configuration +------------- + +Log on the gerrit server and edit ``$site_path/git/$project/config`` +to configure ``git-multimail``. + +Troubleshooting +--------------- + +Warning: this will disable ``git-multimail`` during the debug, and +could confuse your users. Don't run on a production server. + +To debug configuration issues with ``git-multimail``, you can add the +``--stdout`` option when calling ``git_multimail.py`` like this:: + + #!/bin/sh + exec /path/to/git-multimail/git-multimail/git_multimail.py \ + --stdout "$@" >> /tmp/log.txt + +and try pushing from a test repository. You should see the source of +the email that would have been sent in the output of ``git push`` in +the file ``/tmp/log.txt``. diff --git a/contrib/hooks/multimail/doc/gitolite.rst b/contrib/hooks/multimail/doc/gitolite.rst new file mode 100644 index 000000000000..505483310552 --- /dev/null +++ b/contrib/hooks/multimail/doc/gitolite.rst @@ -0,0 +1,118 @@ +Setting up git-multimail on gitolite +==================================== + +``git-multimail`` supports gitolite 3 natively. +The explanations below show an easy way to set up ``git-multimail``, +but leave ``git-multimail`` installed and unconfigured for a while. If +you run gitolite on a production server, it is advised that you +execute the step "Set up the hook" last to avoid confusing your users +in the meantime. + +Set up the hook +--------------- + +Log in as your gitolite user. + +Create a file ``.gitolite/hooks/common/post-receive`` on your gitolite +account containing (adapt the path, obviously):: + + #!/bin/sh + exec /path/to/git-multimail/git-multimail/git_multimail.py "$@" + +Make sure it's executable (``chmod +x``). Record the hook in +gitolite:: + + gitolite setup + +Configuration +------------- + +First, you have to allow the admin to set Git configuration variables. + +As gitolite user, edit the line containing ``GIT_CONFIG_KEYS`` in file +``.gitolite.rc``, to make it look like:: + + GIT_CONFIG_KEYS => 'multimailhook\..*', + +You can now log out and return to your normal user. + +In the ``gitolite-admin`` clone, edit the file ``conf/gitolite.conf`` +and add:: + + repo @all + # Not strictly needed as git_multimail.py will chose gitolite if + # $GL_USER is set. + config multimailhook.environment = gitolite + config multimailhook.mailingList = # Where emails should be sent + config multimailhook.from = # From address to use + +Note that by default, gitolite forbids ``<`` and ``>`` in variable +values (for security/paranoia reasons, see +`compensating for UNSAFE_PATT +<http://gitolite.com/gitolite/git-config/index.html#compensating-for-unsafe95patt>`__ +in gitolite's documentation for explanations and a way to disable +this). As a consequence, you will not be able to use ``First Last +<First.Last@example.com>`` as recipient email, but specifying +``First.Last@example.com`` alone works. + +Obviously, you can customize all parameters on a per-repository basis by +adding these ``config multimailhook.*`` lines in the section +corresponding to a repository or set of repositories. + +To activate ``git-multimail`` on a per-repository basis, do not set +``multimailhook.mailingList`` in the ``@all`` section and set it only +for repositories for which you want ``git-multimail``. + +Alternatively, you can set up the ``From:`` field on a per-user basis +by adding a ``BEGIN USER EMAILS``/``END USER EMAILS`` section (see +``../README``). + +Specificities of Gitolite for Configuration +------------------------------------------- + +Empty configuration variables +............................. + +With gitolite, the syntax ``config multimailhook.commitList = ""`` +unsets the variable instead of setting it to an empty string (see +`here +<http://gitolite.com/gitolite/git-config.html#an-important-warning-about-deleting-a-config-line>`__). +As a result, there is no way to set a variable to the empty string. +In all most places where an empty value is required, git-multimail +now allows to specify special ``"none"`` value (case-sensitive) to +mean the same. + +Alternatively, one can use ``" "`` (a single space) instead of ``""``. +In most cases (in particular ``multimailhook.*List`` variables), this +will be equivalent to an empty string. + +If you have a use-case where ``"none"`` is not an acceptable value and +you need ``" "`` or ``""`` instead, please report it as a bug to +git-multimail. + +Allowing Regular Expressions in Configuration +............................................. + +gitolite has a mechanism to prevent unsafe configuration variable +values, which prevent characters like ``|`` commonly used in regular +expressions. If you do not need the safety feature of gitolite and +need to use regular expressions in your configuration (e.g. for +``multimailhook.refFilter*`` variables), set +`UNSAFE_PATT +<http://gitolite.com/gitolite/git-config.html#unsafe-patt>`__ to a +less restrictive value. + +Troubleshooting +--------------- + +Warning: this will disable ``git-multimail`` during the debug, and +could confuse your users. Don't run on a production server. + +To debug configuration issues with ``git-multimail``, you can add the +``--stdout`` option when calling ``git_multimail.py`` like this:: + + #!/bin/sh + exec /path/to/git-multimail/git-multimail/git_multimail.py --stdout "$@" + +and try pushing from a test repository. You should see the source of +the email that would have been sent in the output of ``git push``. diff --git a/contrib/hooks/multimail/doc/troubleshooting.rst b/contrib/hooks/multimail/doc/troubleshooting.rst new file mode 100644 index 000000000000..651b509ee66c --- /dev/null +++ b/contrib/hooks/multimail/doc/troubleshooting.rst @@ -0,0 +1,78 @@ +Troubleshooting issues with git-multimail: a FAQ +================================================ + +How to check that git-multimail is properly set up? +--------------------------------------------------- + +Since version 1.4.0, git-multimail allows a simple self-checking of +its configuration: run it with the environment variable +``GIT_MULTIMAIL_CHECK_SETUP`` set to a non-empty string. You should +get something like this:: + + $ GIT_MULTIMAIL_CHECK_SETUP=true /home/moy/dev/git-multimail/git-multimail/git_multimail.py + Environment values: + administrator : 'the administrator of this repository' + charset : 'utf-8' + emailprefix : '[git-multimail] ' + fqdn : 'anie' + projectdesc : 'UNNAMED PROJECT' + pusher : 'moy' + repo_path : '/home/moy/dev/git-multimail' + repo_shortname : 'git-multimail' + + Now, checking that git-multimail's standard input is properly set ... + Please type some text and then press Return + foo + You have just entered: + foo + git-multimail seems properly set up. + +If you forgot to set an important variable, you may get instead:: + + $ GIT_MULTIMAIL_CHECK_SETUP=true /home/moy/dev/git-multimail/git-multimail/git_multimail.py + No email recipients configured! + +Do not set ``$GIT_MULTIMAIL_CHECK_SETUP`` other than for testing your +configuration: it would disable the hook completely. + +Git is not using the right address in the From/To/Reply-To field +---------------------------------------------------------------- + +First, make sure that git-multimail actually uses what you think it is +using. A lot happens to your email (especially when posting to a +mailing-list) between the time `git_multimail.py` sends it and the +time it reaches your inbox. + +A simple test (to do on a test repository, do not use in production as +it would disable email sending): change your post-receive hook to call +`git_multimail.py` with the `--stdout` option, and try to push to the +repository. You should see something like:: + + Counting objects: 3, done. + Writing objects: 100% (3/3), 263 bytes | 0 bytes/s, done. + Total 3 (delta 0), reused 0 (delta 0) + remote: Sending notification emails to: foo.bar@example.com + remote: =========================================================================== + remote: Date: Mon, 25 Apr 2016 18:39:59 +0200 + remote: To: foo.bar@example.com + remote: Subject: [git] branch master updated: foo + remote: MIME-Version: 1.0 + remote: Content-Type: text/plain; charset=utf-8 + remote: Content-Transfer-Encoding: 8bit + remote: Message-ID: <20160425163959.2311.20498@anie> + remote: From: Auth Or <Foo.Bar@example.com> + remote: Reply-To: Auth Or <Foo.Bar@example.com> + remote: X-Git-Host: example + ... + remote: -- + remote: To stop receiving notification emails like this one, please contact + remote: the administrator of this repository. + remote: =========================================================================== + To /path/to/repo + 6278f04..e173f20 master -> master + +Note: this does not include the sender (Return-Path: header), as it is +not part of the message content but passed to the mailer. Some mailer +show the ``Sender:`` field instead of the ``From:`` field (for +example, Zimbra Webmail shows ``From: <sender-field> on behalf of +<from-field>``). diff --git a/contrib/hooks/multimail/git_multimail.py b/contrib/hooks/multimail/git_multimail.py new file mode 100755 index 000000000000..8823399e7522 --- /dev/null +++ b/contrib/hooks/multimail/git_multimail.py @@ -0,0 +1,4346 @@ +#! /usr/bin/env python + +__version__ = '1.5.0' + +# Copyright (c) 2015-2016 Matthieu Moy and others +# Copyright (c) 2012-2014 Michael Haggerty and others +# Derived from contrib/hooks/post-receive-email, which is +# Copyright (c) 2007 Andy Parkins +# and also includes contributions by other authors. +# +# This file is part of git-multimail. +# +# git-multimail is free software: you can redistribute it and/or +# modify it under the terms of the GNU General Public License version +# 2 as published by the Free Software Foundation. +# +# This program is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see +# <http://www.gnu.org/licenses/>. + +"""Generate notification emails for pushes to a git repository. + +This hook sends emails describing changes introduced by pushes to a +git repository. For each reference that was changed, it emits one +ReferenceChange email summarizing how the reference was changed, +followed by one Revision email for each new commit that was introduced +by the reference change. + +Each commit is announced in exactly one Revision email. If the same +commit is merged into another branch in the same or a later push, then +the ReferenceChange email will list the commit's SHA1 and its one-line +summary, but no new Revision email will be generated. + +This script is designed to be used as a "post-receive" hook in a git +repository (see githooks(5)). It can also be used as an "update" +script, but this usage is not completely reliable and is deprecated. + +To help with debugging, this script accepts a --stdout option, which +causes the emails to be written to standard output rather than sent +using sendmail. + +See the accompanying README file for the complete documentation. + +""" + +import sys +import os +import re +import bisect +import socket +import subprocess +import shlex +import optparse +import logging +import smtplib +try: + import ssl +except ImportError: + # Python < 2.6 do not have ssl, but that's OK if we don't use it. + pass +import time + +import uuid +import base64 + +PYTHON3 = sys.version_info >= (3, 0) + +if sys.version_info <= (2, 5): + def all(iterable): + for element in iterable: + if not element: + return False + return True + + +def is_ascii(s): + return all(ord(c) < 128 and ord(c) > 0 for c in s) + + +if PYTHON3: + def is_string(s): + return isinstance(s, str) + + def str_to_bytes(s): + return s.encode(ENCODING) + + def bytes_to_str(s, errors='strict'): + return s.decode(ENCODING, errors) + + unicode = str + + def write_str(f, msg): + # Try outputing with the default encoding. If it fails, + # try UTF-8. + try: + f.buffer.write(msg.encode(sys.getdefaultencoding())) + except UnicodeEncodeError: + f.buffer.write(msg.encode(ENCODING)) + + def read_line(f): + # Try reading with the default encoding. If it fails, + # try UTF-8. + out = f.buffer.readline() + try: + return out.decode(sys.getdefaultencoding()) + except UnicodeEncodeError: + return out.decode(ENCODING) + + import html + + def html_escape(s): + return html.escape(s) + +else: + def is_string(s): + try: + return isinstance(s, basestring) + except NameError: # Silence Pyflakes warning + raise + + def str_to_bytes(s): + return s + + def bytes_to_str(s, errors='strict'): + return s + + def write_str(f, msg): + f.write(msg) + + def read_line(f): + return f.readline() + + def next(it): + return it.next() + + import cgi + + def html_escape(s): + return cgi.escape(s, True) + +try: + from email.charset import Charset + from email.utils import make_msgid + from email.utils import getaddresses + from email.utils import formataddr + from email.utils import formatdate + from email.header import Header +except ImportError: + # Prior to Python 2.5, the email module used different names: + from email.Charset import Charset + from email.Utils import make_msgid + from email.Utils import getaddresses + from email.Utils import formataddr + from email.Utils import formatdate + from email.Header import Header + + +DEBUG = False + +ZEROS = '0' * 40 +LOGBEGIN = '- Log -----------------------------------------------------------------\n' +LOGEND = '-----------------------------------------------------------------------\n' + +ADDR_HEADERS = set(['from', 'to', 'cc', 'bcc', 'reply-to', 'sender']) + +# It is assumed in many places that the encoding is uniformly UTF-8, +# so changing these constants is unsupported. But define them here +# anyway, to make it easier to find (at least most of) the places +# where the encoding is important. +(ENCODING, CHARSET) = ('UTF-8', 'utf-8') + + +REF_CREATED_SUBJECT_TEMPLATE = ( + '%(emailprefix)s%(refname_type)s %(short_refname)s created' + ' (now %(newrev_short)s)' + ) +REF_UPDATED_SUBJECT_TEMPLATE = ( + '%(emailprefix)s%(refname_type)s %(short_refname)s updated' + ' (%(oldrev_short)s -> %(newrev_short)s)' + ) +REF_DELETED_SUBJECT_TEMPLATE = ( + '%(emailprefix)s%(refname_type)s %(short_refname)s deleted' + ' (was %(oldrev_short)s)' + ) + +COMBINED_REFCHANGE_REVISION_SUBJECT_TEMPLATE = ( + '%(emailprefix)s%(refname_type)s %(short_refname)s updated: %(oneline)s' + ) + +REFCHANGE_HEADER_TEMPLATE = """\ +Date: %(send_date)s +To: %(recipients)s +Subject: %(subject)s +MIME-Version: 1.0 +Content-Type: text/%(contenttype)s; charset=%(charset)s +Content-Transfer-Encoding: 8bit +Message-ID: %(msgid)s +From: %(fromaddr)s +Reply-To: %(reply_to)s +Thread-Index: %(thread_index)s +X-Git-Host: %(fqdn)s +X-Git-Repo: %(repo_shortname)s +X-Git-Refname: %(refname)s +X-Git-Reftype: %(refname_type)s +X-Git-Oldrev: %(oldrev)s +X-Git-Newrev: %(newrev)s +X-Git-NotificationType: ref_changed +X-Git-Multimail-Version: %(multimail_version)s +Auto-Submitted: auto-generated +""" + +REFCHANGE_INTRO_TEMPLATE = """\ +This is an automated email from the git hooks/post-receive script. + +%(pusher)s pushed a change to %(refname_type)s %(short_refname)s +in repository %(repo_shortname)s. + +""" + + +FOOTER_TEMPLATE = """\ + +-- \n\ +To stop receiving notification emails like this one, please contact +%(administrator)s. +""" + + +REWIND_ONLY_TEMPLATE = """\ +This update removed existing revisions from the reference, leaving the +reference pointing at a previous point in the repository history. + + * -- * -- N %(refname)s (%(newrev_short)s) + \\ + O -- O -- O (%(oldrev_short)s) + +Any revisions marked "omit" are not gone; other references still +refer to them. Any revisions marked "discard" are gone forever. +""" + + +NON_FF_TEMPLATE = """\ +This update added new revisions after undoing existing revisions. +That is to say, some revisions that were in the old version of the +%(refname_type)s are not in the new version. This situation occurs +when a user --force pushes a change and generates a repository +containing something like this: + + * -- * -- B -- O -- O -- O (%(oldrev_short)s) + \\ + N -- N -- N %(refname)s (%(newrev_short)s) + +You should already have received notification emails for all of the O +revisions, and so the following emails describe only the N revisions +from the common base, B. + +Any revisions marked "omit" are not gone; other references still +refer to them. Any revisions marked "discard" are gone forever. +""" + + +NO_NEW_REVISIONS_TEMPLATE = """\ +No new revisions were added by this update. +""" + + +DISCARDED_REVISIONS_TEMPLATE = """\ +This change permanently discards the following revisions: +""" + + +NO_DISCARDED_REVISIONS_TEMPLATE = """\ +The revisions that were on this %(refname_type)s are still contained in +other references; therefore, this change does not discard any commits +from the repository. +""" + + +NEW_REVISIONS_TEMPLATE = """\ +The %(tot)s revisions listed above as "new" are entirely new to this +repository and will be described in separate emails. The revisions +listed as "add" were already present in the repository and have only +been added to this reference. + +""" + + +TAG_CREATED_TEMPLATE = """\ + at %(newrev_short)-8s (%(newrev_type)s) +""" + + +TAG_UPDATED_TEMPLATE = """\ +*** WARNING: tag %(short_refname)s was modified! *** + + from %(oldrev_short)-8s (%(oldrev_type)s) + to %(newrev_short)-8s (%(newrev_type)s) +""" + + +TAG_DELETED_TEMPLATE = """\ +*** WARNING: tag %(short_refname)s was deleted! *** + +""" + + +# The template used in summary tables. It looks best if this uses the +# same alignment as TAG_CREATED_TEMPLATE and TAG_UPDATED_TEMPLATE. +BRIEF_SUMMARY_TEMPLATE = """\ +%(action)8s %(rev_short)-8s %(text)s +""" + + +NON_COMMIT_UPDATE_TEMPLATE = """\ +This is an unusual reference change because the reference did not +refer to a commit either before or after the change. We do not know +how to provide full information about this reference change. +""" + + +REVISION_HEADER_TEMPLATE = """\ +Date: %(send_date)s +To: %(recipients)s +Cc: %(cc_recipients)s +Subject: %(emailprefix)s%(num)02d/%(tot)02d: %(oneline)s +MIME-Version: 1.0 +Content-Type: text/%(contenttype)s; charset=%(charset)s +Content-Transfer-Encoding: 8bit +From: %(fromaddr)s +Reply-To: %(reply_to)s +In-Reply-To: %(reply_to_msgid)s +References: %(reply_to_msgid)s +Thread-Index: %(thread_index)s +X-Git-Host: %(fqdn)s +X-Git-Repo: %(repo_shortname)s +X-Git-Refname: %(refname)s +X-Git-Reftype: %(refname_type)s +X-Git-Rev: %(rev)s +X-Git-NotificationType: diff +X-Git-Multimail-Version: %(multimail_version)s +Auto-Submitted: auto-generated +""" + +REVISION_INTRO_TEMPLATE = """\ +This is an automated email from the git hooks/post-receive script. + +%(pusher)s pushed a commit to %(refname_type)s %(short_refname)s +in repository %(repo_shortname)s. + +""" + +LINK_TEXT_TEMPLATE = """\ +View the commit online: +%(browse_url)s + +""" + +LINK_HTML_TEMPLATE = """\ +<p><a href="%(browse_url)s">View the commit online</a>.</p> +""" + + +REVISION_FOOTER_TEMPLATE = FOOTER_TEMPLATE + + +# Combined, meaning refchange+revision email (for single-commit additions) +COMBINED_HEADER_TEMPLATE = """\ +Date: %(send_date)s +To: %(recipients)s +Subject: %(subject)s +MIME-Version: 1.0 +Content-Type: text/%(contenttype)s; charset=%(charset)s +Content-Transfer-Encoding: 8bit +Message-ID: %(msgid)s +From: %(fromaddr)s +Reply-To: %(reply_to)s +X-Git-Host: %(fqdn)s +X-Git-Repo: %(repo_shortname)s +X-Git-Refname: %(refname)s +X-Git-Reftype: %(refname_type)s +X-Git-Oldrev: %(oldrev)s +X-Git-Newrev: %(newrev)s +X-Git-Rev: %(rev)s +X-Git-NotificationType: ref_changed_plus_diff +X-Git-Multimail-Version: %(multimail_version)s +Auto-Submitted: auto-generated +""" + +COMBINED_INTRO_TEMPLATE = """\ +This is an automated email from the git hooks/post-receive script. + +%(pusher)s pushed a commit to %(refname_type)s %(short_refname)s +in repository %(repo_shortname)s. + +""" + +COMBINED_FOOTER_TEMPLATE = FOOTER_TEMPLATE + + +class CommandError(Exception): + def __init__(self, cmd, retcode): + self.cmd = cmd + self.retcode = retcode + Exception.__init__( + self, + 'Command "%s" failed with retcode %s' % (' '.join(cmd), retcode,) + ) + + +class ConfigurationException(Exception): + pass + + +# The "git" program (this could be changed to include a full path): +GIT_EXECUTABLE = 'git' + + +# How "git" should be invoked (including global arguments), as a list +# of words. This variable is usually initialized automatically by +# read_git_output() via choose_git_command(), but if a value is set +# here then it will be used unconditionally. +GIT_CMD = None + + +def choose_git_command(): + """Decide how to invoke git, and record the choice in GIT_CMD.""" + + global GIT_CMD + + if GIT_CMD is None: + try: + # Check to see whether the "-c" option is accepted (it was + # only added in Git 1.7.2). We don't actually use the + # output of "git --version", though if we needed more + # specific version information this would be the place to + # do it. + cmd = [GIT_EXECUTABLE, '-c', 'foo.bar=baz', '--version'] + read_output(cmd) + GIT_CMD = [GIT_EXECUTABLE, '-c', 'i18n.logoutputencoding=%s' % (ENCODING,)] + except CommandError: + GIT_CMD = [GIT_EXECUTABLE] + + +def read_git_output(args, input=None, keepends=False, **kw): + """Read the output of a Git command.""" + + if GIT_CMD is None: + choose_git_command() + + return read_output(GIT_CMD + args, input=input, keepends=keepends, **kw) + + +def read_output(cmd, input=None, keepends=False, **kw): + if input: + stdin = subprocess.PIPE + input = str_to_bytes(input) + else: + stdin = None + errors = 'strict' + if 'errors' in kw: + errors = kw['errors'] + del kw['errors'] + p = subprocess.Popen( + tuple(str_to_bytes(w) for w in cmd), + stdin=stdin, stdout=subprocess.PIPE, stderr=subprocess.PIPE, **kw + ) + (out, err) = p.communicate(input) + out = bytes_to_str(out, errors=errors) + retcode = p.wait() + if retcode: + raise CommandError(cmd, retcode) + if not keepends: + out = out.rstrip('\n\r') + return out + + +def read_git_lines(args, keepends=False, **kw): + """Return the lines output by Git command. + + Return as single lines, with newlines stripped off.""" + + return read_git_output(args, keepends=True, **kw).splitlines(keepends) + + +def git_rev_list_ish(cmd, spec, args=None, **kw): + """Common functionality for invoking a 'git rev-list'-like command. + + Parameters: + * cmd is the Git command to run, e.g., 'rev-list' or 'log'. + * spec is a list of revision arguments to pass to the named + command. If None, this function returns an empty list. + * args is a list of extra arguments passed to the named command. + * All other keyword arguments (if any) are passed to the + underlying read_git_lines() function. + + Return the output of the Git command in the form of a list, one + entry per output line. + """ + if spec is None: + return [] + if args is None: + args = [] + args = [cmd, '--stdin'] + args + spec_stdin = ''.join(s + '\n' for s in spec) + return read_git_lines(args, input=spec_stdin, **kw) + + +def git_rev_list(spec, **kw): + """Run 'git rev-list' with the given list of revision arguments. + + See git_rev_list_ish() for parameter and return value + documentation. + """ + return git_rev_list_ish('rev-list', spec, **kw) + + +def git_log(spec, **kw): + """Run 'git log' with the given list of revision arguments. + + See git_rev_list_ish() for parameter and return value + documentation. + """ + return git_rev_list_ish('log', spec, **kw) + + +def header_encode(text, header_name=None): + """Encode and line-wrap the value of an email header field.""" + + # Convert to unicode, if required. + if not isinstance(text, unicode): + text = unicode(text, 'utf-8') + + if is_ascii(text): + charset = 'ascii' + else: + charset = 'utf-8' + + return Header(text, header_name=header_name, charset=Charset(charset)).encode() + + +def addr_header_encode(text, header_name=None): + """Encode and line-wrap the value of an email header field containing + email addresses.""" + + # Convert to unicode, if required. + if not isinstance(text, unicode): + text = unicode(text, 'utf-8') + + text = ', '.join( + formataddr((header_encode(name), emailaddr)) + for name, emailaddr in getaddresses([text]) + ) + + if is_ascii(text): + charset = 'ascii' + else: + charset = 'utf-8' + + return Header(text, header_name=header_name, charset=Charset(charset)).encode() + + +class Config(object): + def __init__(self, section, git_config=None): + """Represent a section of the git configuration. + + If git_config is specified, it is passed to "git config" in + the GIT_CONFIG environment variable, meaning that "git config" + will read the specified path rather than the Git default + config paths.""" + + self.section = section + if git_config: + self.env = os.environ.copy() + self.env['GIT_CONFIG'] = git_config + else: + self.env = None + + @staticmethod + def _split(s): + """Split NUL-terminated values.""" + + words = s.split('\0') + assert words[-1] == '' + return words[:-1] + + @staticmethod + def add_config_parameters(c): + """Add configuration parameters to Git. + + c is either an str or a list of str, each element being of the + form 'var=val' or 'var', with the same syntax and meaning as + the argument of 'git -c var=val'. + """ + if isinstance(c, str): + c = (c,) + parameters = os.environ.get('GIT_CONFIG_PARAMETERS', '') + if parameters: + parameters += ' ' + # git expects GIT_CONFIG_PARAMETERS to be of the form + # "'name1=value1' 'name2=value2' 'name3=value3'" + # including everything inside the double quotes (but not the double + # quotes themselves). Spacing is critical. Also, if a value contains + # a literal single quote that quote must be represented using the + # four character sequence: '\'' + parameters += ' '.join("'" + x.replace("'", "'\\''") + "'" for x in c) + os.environ['GIT_CONFIG_PARAMETERS'] = parameters + + def get(self, name, default=None): + try: + values = self._split(read_git_output( + ['config', '--get', '--null', '%s.%s' % (self.section, name)], + env=self.env, keepends=True, + )) + assert len(values) == 1 + return values[0] + except CommandError: + return default + + def get_bool(self, name, default=None): + try: + value = read_git_output( + ['config', '--get', '--bool', '%s.%s' % (self.section, name)], + env=self.env, + ) + except CommandError: + return default + return value == 'true' + + def get_all(self, name, default=None): + """Read a (possibly multivalued) setting from the configuration. + + Return the result as a list of values, or default if the name + is unset.""" + + try: + return self._split(read_git_output( + ['config', '--get-all', '--null', '%s.%s' % (self.section, name)], + env=self.env, keepends=True, + )) + except CommandError: + t, e, traceback = sys.exc_info() + if e.retcode == 1: + # "the section or key is invalid"; i.e., there is no + # value for the specified key. + return default + else: + raise + + def set(self, name, value): + read_git_output( + ['config', '%s.%s' % (self.section, name), value], + env=self.env, + ) + + def add(self, name, value): + read_git_output( + ['config', '--add', '%s.%s' % (self.section, name), value], + env=self.env, + ) + + def __contains__(self, name): + return self.get_all(name, default=None) is not None + + # We don't use this method anymore internally, but keep it here in + # case somebody is calling it from their own code: + def has_key(self, name): + return name in self + + def unset_all(self, name): + try: + read_git_output( + ['config', '--unset-all', '%s.%s' % (self.section, name)], + env=self.env, + ) + except CommandError: + t, e, traceback = sys.exc_info() + if e.retcode == 5: + # The name doesn't exist, which is what we wanted anyway... + pass + else: + raise + + def set_recipients(self, name, value): + self.unset_all(name) + for pair in getaddresses([value]): + self.add(name, formataddr(pair)) + + +def generate_summaries(*log_args): + """Generate a brief summary for each revision requested. + + log_args are strings that will be passed directly to "git log" as + revision selectors. Iterate over (sha1_short, subject) for each + commit specified by log_args (subject is the first line of the + commit message as a string without EOLs).""" + + cmd = [ + 'log', '--abbrev', '--format=%h %s', + ] + list(log_args) + ['--'] + for line in read_git_lines(cmd): + yield tuple(line.split(' ', 1)) + + +def limit_lines(lines, max_lines): + for (index, line) in enumerate(lines): + if index < max_lines: + yield line + + if index >= max_lines: + yield '... %d lines suppressed ...\n' % (index + 1 - max_lines,) + + +def limit_linelength(lines, max_linelength): + for line in lines: + # Don't forget that lines always include a trailing newline. + if len(line) > max_linelength + 1: + line = line[:max_linelength - 7] + ' [...]\n' + yield line + + +class CommitSet(object): + """A (constant) set of object names. + + The set should be initialized with full SHA1 object names. The + __contains__() method returns True iff its argument is an + abbreviation of any the names in the set.""" + + def __init__(self, names): + self._names = sorted(names) + + def __len__(self): + return len(self._names) + + def __contains__(self, sha1_abbrev): + """Return True iff this set contains sha1_abbrev (which might be abbreviated).""" + + i = bisect.bisect_left(self._names, sha1_abbrev) + return i < len(self) and self._names[i].startswith(sha1_abbrev) + + +class GitObject(object): + def __init__(self, sha1, type=None): + if sha1 == ZEROS: + self.sha1 = self.type = self.commit_sha1 = None + else: + self.sha1 = sha1 + self.type = type or read_git_output(['cat-file', '-t', self.sha1]) + + if self.type == 'commit': + self.commit_sha1 = self.sha1 + elif self.type == 'tag': + try: + self.commit_sha1 = read_git_output( + ['rev-parse', '--verify', '%s^0' % (self.sha1,)] + ) + except CommandError: + # Cannot deref tag to determine commit_sha1 + self.commit_sha1 = None + else: + self.commit_sha1 = None + + self.short = read_git_output(['rev-parse', '--short', sha1]) + + def get_summary(self): + """Return (sha1_short, subject) for this commit.""" + + if not self.sha1: + raise ValueError('Empty commit has no summary') + + return next(iter(generate_summaries('--no-walk', self.sha1))) + + def __eq__(self, other): + return isinstance(other, GitObject) and self.sha1 == other.sha1 + + def __ne__(self, other): + return not self == other + + def __hash__(self): + return hash(self.sha1) + + def __nonzero__(self): + return bool(self.sha1) + + def __bool__(self): + """Python 2 backward compatibility""" + return self.__nonzero__() + + def __str__(self): + return self.sha1 or ZEROS + + +class Change(object): + """A Change that has been made to the Git repository. + + Abstract class from which both Revisions and ReferenceChanges are + derived. A Change knows how to generate a notification email + describing itself.""" + + def __init__(self, environment): + self.environment = environment + self._values = None + self._contains_html_diff = False + + def _contains_diff(self): + # We do contain a diff, should it be rendered in HTML? + if self.environment.commit_email_format == "html": + self._contains_html_diff = True + + def _compute_values(self): + """Return a dictionary {keyword: expansion} for this Change. + + Derived classes overload this method to add more entries to + the return value. This method is used internally by + get_values(). The return value should always be a new + dictionary.""" + + values = self.environment.get_values() + fromaddr = self.environment.get_fromaddr(change=self) + if fromaddr is not None: + values['fromaddr'] = fromaddr + values['multimail_version'] = get_version() + return values + + # Aliases usable in template strings. Tuple of pairs (destination, + # source). + VALUES_ALIAS = ( + ("id", "newrev"), + ) + + def get_values(self, **extra_values): + """Return a dictionary {keyword: expansion} for this Change. + + Return a dictionary mapping keywords to the values that they + should be expanded to for this Change (used when interpolating + template strings). If any keyword arguments are supplied, add + those to the return value as well. The return value is always + a new dictionary.""" + + if self._values is None: + self._values = self._compute_values() + + values = self._values.copy() + if extra_values: + values.update(extra_values) + + for alias, val in self.VALUES_ALIAS: + values[alias] = values[val] + return values + + def expand(self, template, **extra_values): + """Expand template. + + Expand the template (which should be a string) using string + interpolation of the values for this Change. If any keyword + arguments are provided, also include those in the keywords + available for interpolation.""" + + return template % self.get_values(**extra_values) + + def expand_lines(self, template, html_escape_val=False, **extra_values): + """Break template into lines and expand each line.""" + + values = self.get_values(**extra_values) + if html_escape_val: + for k in values: + if is_string(values[k]): + values[k] = html_escape(values[k]) + for line in template.splitlines(True): + yield line % values + + def expand_header_lines(self, template, **extra_values): + """Break template into lines and expand each line as an RFC 2822 header. + + Encode values and split up lines that are too long. Silently + skip lines that contain references to unknown variables.""" + + values = self.get_values(**extra_values) + if self._contains_html_diff: + self._content_type = 'html' + else: + self._content_type = 'plain' + values['contenttype'] = self._content_type + + for line in template.splitlines(): + (name, value) = line.split(': ', 1) + + try: + value = value % values + except KeyError: + t, e, traceback = sys.exc_info() + if DEBUG: + self.environment.log_warning( + 'Warning: unknown variable %r in the following line; line skipped:\n' + ' %s\n' + % (e.args[0], line,) + ) + else: + if name.lower() in ADDR_HEADERS: + value = addr_header_encode(value, name) + else: + value = header_encode(value, name) + for splitline in ('%s: %s\n' % (name, value)).splitlines(True): + yield splitline + + def generate_email_header(self): + """Generate the RFC 2822 email headers for this Change, a line at a time. + + The output should not include the trailing blank line.""" + + raise NotImplementedError() + + def generate_browse_link(self, base_url): + """Generate a link to an online repository browser.""" + return iter(()) + + def generate_email_intro(self, html_escape_val=False): + """Generate the email intro for this Change, a line at a time. + + The output will be used as the standard boilerplate at the top + of the email body.""" + + raise NotImplementedError() + + def generate_email_body(self, push): + """Generate the main part of the email body, a line at a time. + + The text in the body might be truncated after a specified + number of lines (see multimailhook.emailmaxlines).""" + + raise NotImplementedError() + + def generate_email_footer(self, html_escape_val): + """Generate the footer of the email, a line at a time. + + The footer is always included, irrespective of + multimailhook.emailmaxlines.""" + + raise NotImplementedError() + + def _wrap_for_html(self, lines): + """Wrap the lines in HTML <pre> tag when using HTML format. + + Escape special HTML characters and add <pre> and </pre> tags around + the given lines if we should be generating HTML as indicated by + self._contains_html_diff being set to true. + """ + if self._contains_html_diff: + yield "<pre style='margin:0'>\n" + + for line in lines: + yield html_escape(line) + + yield '</pre>\n' + else: + for line in lines: + yield line + + def generate_email(self, push, body_filter=None, extra_header_values={}): + """Generate an email describing this change. + + Iterate over the lines (including the header lines) of an + email describing this change. If body_filter is not None, + then use it to filter the lines that are intended for the + email body. + + The extra_header_values field is received as a dict and not as + **kwargs, to allow passing other keyword arguments in the + future (e.g. passing extra values to generate_email_intro()""" + + for line in self.generate_email_header(**extra_header_values): + yield line + yield '\n' + html_escape_val = (self.environment.html_in_intro and + self._contains_html_diff) + intro = self.generate_email_intro(html_escape_val) + if not self.environment.html_in_intro: + intro = self._wrap_for_html(intro) + for line in intro: + yield line + + if self.environment.commitBrowseURL: + for line in self.generate_browse_link(self.environment.commitBrowseURL): + yield line + + body = self.generate_email_body(push) + if body_filter is not None: + body = body_filter(body) + + diff_started = False + if self._contains_html_diff: + # "white-space: pre" is the default, but we need to + # specify it again in case the message is viewed in a + # webmail which wraps it in an element setting white-space + # to something else (Zimbra does this and sets + # white-space: pre-line). + yield '<pre style="white-space: pre; background: #F8F8F8">' + for line in body: + if self._contains_html_diff: + # This is very, very naive. It would be much better to really + # parse the diff, i.e. look at how many lines do we have in + # the hunk headers instead of blindly highlighting everything + # that looks like it might be part of a diff. + bgcolor = '' + fgcolor = '' + if line.startswith('--- a/'): + diff_started = True + bgcolor = 'e0e0ff' + elif line.startswith('diff ') or line.startswith('index '): + diff_started = True + fgcolor = '808080' + elif diff_started: + if line.startswith('+++ '): + bgcolor = 'e0e0ff' + elif line.startswith('@@'): + bgcolor = 'e0e0e0' + elif line.startswith('+'): + bgcolor = 'e0ffe0' + elif line.startswith('-'): + bgcolor = 'ffe0e0' + elif line.startswith('commit '): + fgcolor = '808000' + elif line.startswith(' '): + fgcolor = '404040' + + # Chop the trailing LF, we don't want it inside <pre>. + line = html_escape(line[:-1]) + + if bgcolor or fgcolor: + style = 'display:block; white-space:pre;' + if bgcolor: + style += 'background:#' + bgcolor + ';' + if fgcolor: + style += 'color:#' + fgcolor + ';' + # Use a <span style='display:block> to color the + # whole line. The newline must be inside the span + # to display properly both in Firefox and in + # text-based browser. + line = "<span style='%s'>%s\n</span>" % (style, line) + else: + line = line + '\n' + + yield line + if self._contains_html_diff: + yield '</pre>' + html_escape_val = (self.environment.html_in_footer and + self._contains_html_diff) + footer = self.generate_email_footer(html_escape_val) + if not self.environment.html_in_footer: + footer = self._wrap_for_html(footer) + for line in footer: + yield line + + def get_specific_fromaddr(self): + """For kinds of Changes which specify it, return the kind-specific + From address to use.""" + return None + + +class Revision(Change): + """A Change consisting of a single git commit.""" + + CC_RE = re.compile(r'^\s*C[Cc]:\s*(?P<to>[^#]+@[^\s#]*)\s*(#.*)?$') + + def __init__(self, reference_change, rev, num, tot): + Change.__init__(self, reference_change.environment) + self.reference_change = reference_change + self.rev = rev + self.change_type = self.reference_change.change_type + self.refname = self.reference_change.refname + self.num = num + self.tot = tot + self.author = read_git_output(['log', '--no-walk', '--format=%aN <%aE>', self.rev.sha1]) + self.recipients = self.environment.get_revision_recipients(self) + + # -s is short for --no-patch, but -s works on older git's (e.g. 1.7) + self.parents = read_git_lines(['show', '-s', '--format=%P', + self.rev.sha1])[0].split() + + self.cc_recipients = '' + if self.environment.get_scancommitforcc(): + self.cc_recipients = ', '.join(to.strip() for to in self._cc_recipients()) + if self.cc_recipients: + self.environment.log_msg( + 'Add %s to CC for %s' % (self.cc_recipients, self.rev.sha1)) + + def _cc_recipients(self): + cc_recipients = [] + message = read_git_output(['log', '--no-walk', '--format=%b', self.rev.sha1]) + lines = message.strip().split('\n') + for line in lines: + m = re.match(self.CC_RE, line) + if m: + cc_recipients.append(m.group('to')) + + return cc_recipients + + def _compute_values(self): + values = Change._compute_values(self) + + oneline = read_git_output( + ['log', '--format=%s', '--no-walk', self.rev.sha1] + ) + + max_subject_length = self.environment.get_max_subject_length() + if max_subject_length > 0 and len(oneline) > max_subject_length: + oneline = oneline[:max_subject_length - 6] + ' [...]' + + values['rev'] = self.rev.sha1 + values['parents'] = ' '.join(self.parents) + values['rev_short'] = self.rev.short + values['change_type'] = self.change_type + values['refname'] = self.refname + values['newrev'] = self.rev.sha1 + values['short_refname'] = self.reference_change.short_refname + values['refname_type'] = self.reference_change.refname_type + values['reply_to_msgid'] = self.reference_change.msgid + values['thread_index'] = self.reference_change.thread_index + values['num'] = self.num + values['tot'] = self.tot + values['recipients'] = self.recipients + if self.cc_recipients: + values['cc_recipients'] = self.cc_recipients + values['oneline'] = oneline + values['author'] = self.author + + reply_to = self.environment.get_reply_to_commit(self) + if reply_to: + values['reply_to'] = reply_to + + return values + + def generate_email_header(self, **extra_values): + for line in self.expand_header_lines( + REVISION_HEADER_TEMPLATE, **extra_values + ): + yield line + + def generate_browse_link(self, base_url): + if '%(' not in base_url: + base_url += '%(id)s' + url = "".join(self.expand_lines(base_url)) + if self._content_type == 'html': + for line in self.expand_lines(LINK_HTML_TEMPLATE, + html_escape_val=True, + browse_url=url): + yield line + elif self._content_type == 'plain': + for line in self.expand_lines(LINK_TEXT_TEMPLATE, + html_escape_val=False, + browse_url=url): + yield line + else: + raise NotImplementedError("Content-type %s unsupported. Please report it as a bug.") + + def generate_email_intro(self, html_escape_val=False): + for line in self.expand_lines(REVISION_INTRO_TEMPLATE, + html_escape_val=html_escape_val): + yield line + + def generate_email_body(self, push): + """Show this revision.""" + + for line in read_git_lines( + ['log'] + self.environment.commitlogopts + ['-1', self.rev.sha1], + keepends=True, + errors='replace'): + if line.startswith('Date: ') and self.environment.date_substitute: + yield self.environment.date_substitute + line[len('Date: '):] + else: + yield line + + def generate_email_footer(self, html_escape_val): + return self.expand_lines(REVISION_FOOTER_TEMPLATE, + html_escape_val=html_escape_val) + + def generate_email(self, push, body_filter=None, extra_header_values={}): + self._contains_diff() + return Change.generate_email(self, push, body_filter, extra_header_values) + + def get_specific_fromaddr(self): + return self.environment.from_commit + + +class ReferenceChange(Change): + """A Change to a Git reference. + + An abstract class representing a create, update, or delete of a + Git reference. Derived classes handle specific types of reference + (e.g., tags vs. branches). These classes generate the main + reference change email summarizing the reference change and + whether it caused any any commits to be added or removed. + + ReferenceChange objects are usually created using the static + create() method, which has the logic to decide which derived class + to instantiate.""" + + REF_RE = re.compile(r'^refs\/(?P<area>[^\/]+)\/(?P<shortname>.*)$') + + @staticmethod + def create(environment, oldrev, newrev, refname): + """Return a ReferenceChange object representing the change. + + Return an object that represents the type of change that is being + made. oldrev and newrev should be SHA1s or ZEROS.""" + + old = GitObject(oldrev) + new = GitObject(newrev) + rev = new or old + + # The revision type tells us what type the commit is, combined with + # the location of the ref we can decide between + # - working branch + # - tracking branch + # - unannotated tag + # - annotated tag + m = ReferenceChange.REF_RE.match(refname) + if m: + area = m.group('area') + short_refname = m.group('shortname') + else: + area = '' + short_refname = refname + + if rev.type == 'tag': + # Annotated tag: + klass = AnnotatedTagChange + elif rev.type == 'commit': + if area == 'tags': + # Non-annotated tag: + klass = NonAnnotatedTagChange + elif area == 'heads': + # Branch: + klass = BranchChange + elif area == 'remotes': + # Tracking branch: + environment.log_warning( + '*** Push-update of tracking branch %r\n' + '*** - incomplete email generated.' + % (refname,) + ) + klass = OtherReferenceChange + else: + # Some other reference namespace: + environment.log_warning( + '*** Push-update of strange reference %r\n' + '*** - incomplete email generated.' + % (refname,) + ) + klass = OtherReferenceChange + else: + # Anything else (is there anything else?) + environment.log_warning( + '*** Unknown type of update to %r (%s)\n' + '*** - incomplete email generated.' + % (refname, rev.type,) + ) + klass = OtherReferenceChange + + return klass( + environment, + refname=refname, short_refname=short_refname, + old=old, new=new, rev=rev, + ) + + @staticmethod + def make_thread_index(): + """Return a string appropriate for the Thread-Index header, + needed by MS Outlook to get threading right. + + The format is (base64-encoded): + - 1 byte must be 1 + - 5 bytes encode a date (hardcoded here) + - 16 bytes for a globally unique identifier + + FIXME: Unfortunately, even with the Thread-Index field, MS + Outlook doesn't seem to do the threading reliably (see + https://github.com/git-multimail/git-multimail/pull/194). + """ + thread_index = b'\x01\x00\x00\x12\x34\x56' + uuid.uuid4().bytes + return base64.standard_b64encode(thread_index).decode('ascii') + + def __init__(self, environment, refname, short_refname, old, new, rev): + Change.__init__(self, environment) + self.change_type = { + (False, True): 'create', + (True, True): 'update', + (True, False): 'delete', + }[bool(old), bool(new)] + self.refname = refname + self.short_refname = short_refname + self.old = old + self.new = new + self.rev = rev + self.msgid = make_msgid() + self.thread_index = self.make_thread_index() + self.diffopts = environment.diffopts + self.graphopts = environment.graphopts + self.logopts = environment.logopts + self.commitlogopts = environment.commitlogopts + self.showgraph = environment.refchange_showgraph + self.showlog = environment.refchange_showlog + + self.header_template = REFCHANGE_HEADER_TEMPLATE + self.intro_template = REFCHANGE_INTRO_TEMPLATE + self.footer_template = FOOTER_TEMPLATE + + def _compute_values(self): + values = Change._compute_values(self) + + values['change_type'] = self.change_type + values['refname_type'] = self.refname_type + values['refname'] = self.refname + values['short_refname'] = self.short_refname + values['msgid'] = self.msgid + values['thread_index'] = self.thread_index + values['recipients'] = self.recipients + values['oldrev'] = str(self.old) + values['oldrev_short'] = self.old.short + values['newrev'] = str(self.new) + values['newrev_short'] = self.new.short + + if self.old: + values['oldrev_type'] = self.old.type + if self.new: + values['newrev_type'] = self.new.type + + reply_to = self.environment.get_reply_to_refchange(self) + if reply_to: + values['reply_to'] = reply_to + + return values + + def send_single_combined_email(self, known_added_sha1s): + """Determine if a combined refchange/revision email should be sent + + If there is only a single new (non-merge) commit added by a + change, it is useful to combine the ReferenceChange and + Revision emails into one. In such a case, return the single + revision; otherwise, return None. + + This method is overridden in BranchChange.""" + + return None + + def generate_combined_email(self, push, revision, body_filter=None, extra_header_values={}): + """Generate an email describing this change AND specified revision. + + Iterate over the lines (including the header lines) of an + email describing this change. If body_filter is not None, + then use it to filter the lines that are intended for the + email body. + + The extra_header_values field is received as a dict and not as + **kwargs, to allow passing other keyword arguments in the + future (e.g. passing extra values to generate_email_intro() + + This method is overridden in BranchChange.""" + + raise NotImplementedError + + def get_subject(self): + template = { + 'create': REF_CREATED_SUBJECT_TEMPLATE, + 'update': REF_UPDATED_SUBJECT_TEMPLATE, + 'delete': REF_DELETED_SUBJECT_TEMPLATE, + }[self.change_type] + return self.expand(template) + + def generate_email_header(self, **extra_values): + if 'subject' not in extra_values: + extra_values['subject'] = self.get_subject() + + for line in self.expand_header_lines( + self.header_template, **extra_values + ): + yield line + + def generate_email_intro(self, html_escape_val=False): + for line in self.expand_lines(self.intro_template, + html_escape_val=html_escape_val): + yield line + + def generate_email_body(self, push): + """Call the appropriate body-generation routine. + + Call one of generate_create_summary() / + generate_update_summary() / generate_delete_summary().""" + + change_summary = { + 'create': self.generate_create_summary, + 'delete': self.generate_delete_summary, + 'update': self.generate_update_summary, + }[self.change_type](push) + for line in change_summary: + yield line + + for line in self.generate_revision_change_summary(push): + yield line + + def generate_email_footer(self, html_escape_val): + return self.expand_lines(self.footer_template, + html_escape_val=html_escape_val) + + def generate_revision_change_graph(self, push): + if self.showgraph: + args = ['--graph'] + self.graphopts + for newold in ('new', 'old'): + has_newold = False + spec = push.get_commits_spec(newold, self) + for line in git_log(spec, args=args, keepends=True): + if not has_newold: + has_newold = True + yield '\n' + yield 'Graph of %s commits:\n\n' % ( + {'new': 'new', 'old': 'discarded'}[newold],) + yield ' ' + line + if has_newold: + yield '\n' + + def generate_revision_change_log(self, new_commits_list): + if self.showlog: + yield '\n' + yield 'Detailed log of new commits:\n\n' + for line in read_git_lines( + ['log', '--no-walk'] + + self.logopts + + new_commits_list + + ['--'], + keepends=True, + ): + yield line + + def generate_new_revision_summary(self, tot, new_commits_list, push): + for line in self.expand_lines(NEW_REVISIONS_TEMPLATE, tot=tot): + yield line + for line in self.generate_revision_change_graph(push): + yield line + for line in self.generate_revision_change_log(new_commits_list): + yield line + + def generate_revision_change_summary(self, push): + """Generate a summary of the revisions added/removed by this change.""" + + if self.new.commit_sha1 and not self.old.commit_sha1: + # A new reference was created. List the new revisions + # brought by the new reference (i.e., those revisions that + # were not in the repository before this reference + # change). + sha1s = list(push.get_new_commits(self)) + sha1s.reverse() + tot = len(sha1s) + new_revisions = [ + Revision(self, GitObject(sha1), num=i + 1, tot=tot) + for (i, sha1) in enumerate(sha1s) + ] + + if new_revisions: + yield self.expand('This %(refname_type)s includes the following new commits:\n') + yield '\n' + for r in new_revisions: + (sha1, subject) = r.rev.get_summary() + yield r.expand( + BRIEF_SUMMARY_TEMPLATE, action='new', text=subject, + ) + yield '\n' + for line in self.generate_new_revision_summary( + tot, [r.rev.sha1 for r in new_revisions], push): + yield line + else: + for line in self.expand_lines(NO_NEW_REVISIONS_TEMPLATE): + yield line + + elif self.new.commit_sha1 and self.old.commit_sha1: + # A reference was changed to point at a different commit. + # List the revisions that were removed and/or added *from + # that reference* by this reference change, along with a + # diff between the trees for its old and new values. + + # List of the revisions that were added to the branch by + # this update. Note this list can include revisions that + # have already had notification emails; we want such + # revisions in the summary even though we will not send + # new notification emails for them. + adds = list(generate_summaries( + '--topo-order', '--reverse', '%s..%s' + % (self.old.commit_sha1, self.new.commit_sha1,) + )) + + # List of the revisions that were removed from the branch + # by this update. This will be empty except for + # non-fast-forward updates. + discards = list(generate_summaries( + '%s..%s' % (self.new.commit_sha1, self.old.commit_sha1,) + )) + + if adds: + new_commits_list = push.get_new_commits(self) + else: + new_commits_list = [] + new_commits = CommitSet(new_commits_list) + + if discards: + discarded_commits = CommitSet(push.get_discarded_commits(self)) + else: + discarded_commits = CommitSet([]) + + if discards and adds: + for (sha1, subject) in discards: + if sha1 in discarded_commits: + action = 'discard' + else: + action = 'omit' + yield self.expand( + BRIEF_SUMMARY_TEMPLATE, action=action, + rev_short=sha1, text=subject, + ) + for (sha1, subject) in adds: + if sha1 in new_commits: + action = 'new' + else: + action = 'add' + yield self.expand( + BRIEF_SUMMARY_TEMPLATE, action=action, + rev_short=sha1, text=subject, + ) + yield '\n' + for line in self.expand_lines(NON_FF_TEMPLATE): + yield line + + elif discards: + for (sha1, subject) in discards: + if sha1 in discarded_commits: + action = 'discard' + else: + action = 'omit' + yield self.expand( + BRIEF_SUMMARY_TEMPLATE, action=action, + rev_short=sha1, text=subject, + ) + yield '\n' + for line in self.expand_lines(REWIND_ONLY_TEMPLATE): + yield line + + elif adds: + (sha1, subject) = self.old.get_summary() + yield self.expand( + BRIEF_SUMMARY_TEMPLATE, action='from', + rev_short=sha1, text=subject, + ) + for (sha1, subject) in adds: + if sha1 in new_commits: + action = 'new' + else: + action = 'add' + yield self.expand( + BRIEF_SUMMARY_TEMPLATE, action=action, + rev_short=sha1, text=subject, + ) + + yield '\n' + + if new_commits: + for line in self.generate_new_revision_summary( + len(new_commits), new_commits_list, push): + yield line + else: + for line in self.expand_lines(NO_NEW_REVISIONS_TEMPLATE): + yield line + for line in self.generate_revision_change_graph(push): + yield line + + # The diffstat is shown from the old revision to the new + # revision. This is to show the truth of what happened in + # this change. There's no point showing the stat from the + # base to the new revision because the base is effectively a + # random revision at this point - the user will be interested + # in what this revision changed - including the undoing of + # previous revisions in the case of non-fast-forward updates. + yield '\n' + yield 'Summary of changes:\n' + for line in read_git_lines( + ['diff-tree'] + + self.diffopts + + ['%s..%s' % (self.old.commit_sha1, self.new.commit_sha1,)], + keepends=True, + ): + yield line + + elif self.old.commit_sha1 and not self.new.commit_sha1: + # A reference was deleted. List the revisions that were + # removed from the repository by this reference change. + + sha1s = list(push.get_discarded_commits(self)) + tot = len(sha1s) + discarded_revisions = [ + Revision(self, GitObject(sha1), num=i + 1, tot=tot) + for (i, sha1) in enumerate(sha1s) + ] + + if discarded_revisions: + for line in self.expand_lines(DISCARDED_REVISIONS_TEMPLATE): + yield line + yield '\n' + for r in discarded_revisions: + (sha1, subject) = r.rev.get_summary() + yield r.expand( + BRIEF_SUMMARY_TEMPLATE, action='discard', text=subject, + ) + for line in self.generate_revision_change_graph(push): + yield line + else: + for line in self.expand_lines(NO_DISCARDED_REVISIONS_TEMPLATE): + yield line + + elif not self.old.commit_sha1 and not self.new.commit_sha1: + for line in self.expand_lines(NON_COMMIT_UPDATE_TEMPLATE): + yield line + + def generate_create_summary(self, push): + """Called for the creation of a reference.""" + + # This is a new reference and so oldrev is not valid + (sha1, subject) = self.new.get_summary() + yield self.expand( + BRIEF_SUMMARY_TEMPLATE, action='at', + rev_short=sha1, text=subject, + ) + yield '\n' + + def generate_update_summary(self, push): + """Called for the change of a pre-existing branch.""" + + return iter([]) + + def generate_delete_summary(self, push): + """Called for the deletion of any type of reference.""" + + (sha1, subject) = self.old.get_summary() + yield self.expand( + BRIEF_SUMMARY_TEMPLATE, action='was', + rev_short=sha1, text=subject, + ) + yield '\n' + + def get_specific_fromaddr(self): + return self.environment.from_refchange + + +class BranchChange(ReferenceChange): + refname_type = 'branch' + + def __init__(self, environment, refname, short_refname, old, new, rev): + ReferenceChange.__init__( + self, environment, + refname=refname, short_refname=short_refname, + old=old, new=new, rev=rev, + ) + self.recipients = environment.get_refchange_recipients(self) + self._single_revision = None + + def send_single_combined_email(self, known_added_sha1s): + if not self.environment.combine_when_single_commit: + return None + + # In the sadly-all-too-frequent usecase of people pushing only + # one of their commits at a time to a repository, users feel + # the reference change summary emails are noise rather than + # important signal. This is because, in this particular + # usecase, there is a reference change summary email for each + # new commit, and all these summaries do is point out that + # there is one new commit (which can readily be inferred by + # the existence of the individual revision email that is also + # sent). In such cases, our users prefer there to be a combined + # reference change summary/new revision email. + # + # So, if the change is an update and it doesn't discard any + # commits, and it adds exactly one non-merge commit (gerrit + # forces a workflow where every commit is individually merged + # and the git-multimail hook fired off for just this one + # change), then we send a combined refchange/revision email. + try: + # If this change is a reference update that doesn't discard + # any commits... + if self.change_type != 'update': + return None + + if read_git_lines( + ['merge-base', self.old.sha1, self.new.sha1] + ) != [self.old.sha1]: + return None + + # Check if this update introduced exactly one non-merge + # commit: + + def split_line(line): + """Split line into (sha1, [parent,...]).""" + + words = line.split() + return (words[0], words[1:]) + + # Get the new commits introduced by the push as a list of + # (sha1, [parent,...]) + new_commits = [ + split_line(line) + for line in read_git_lines( + [ + 'log', '-3', '--format=%H %P', + '%s..%s' % (self.old.sha1, self.new.sha1), + ] + ) + ] + + if not new_commits: + return None + + # If the newest commit is a merge, save it for a later check + # but otherwise ignore it + merge = None + tot = len(new_commits) + if len(new_commits[0][1]) > 1: + merge = new_commits[0][0] + del new_commits[0] + + # Our primary check: we can't combine if more than one commit + # is introduced. We also currently only combine if the new + # commit is a non-merge commit, though it may make sense to + # combine if it is a merge as well. + if not ( + len(new_commits) == 1 and + len(new_commits[0][1]) == 1 and + new_commits[0][0] in known_added_sha1s + ): + return None + + # We do not want to combine revision and refchange emails if + # those go to separate locations. + rev = Revision(self, GitObject(new_commits[0][0]), 1, tot) + if rev.recipients != self.recipients: + return None + + # We ignored the newest commit if it was just a merge of the one + # commit being introduced. But we don't want to ignore that + # merge commit it it involved conflict resolutions. Check that. + if merge and merge != read_git_output(['diff-tree', '--cc', merge]): + return None + + # We can combine the refchange and one new revision emails + # into one. Return the Revision that a combined email should + # be sent about. + return rev + except CommandError: + # Cannot determine number of commits in old..new or new..old; + # don't combine reference/revision emails: + return None + + def generate_combined_email(self, push, revision, body_filter=None, extra_header_values={}): + values = revision.get_values() + if extra_header_values: + values.update(extra_header_values) + if 'subject' not in extra_header_values: + values['subject'] = self.expand(COMBINED_REFCHANGE_REVISION_SUBJECT_TEMPLATE, **values) + + self._single_revision = revision + self._contains_diff() + self.header_template = COMBINED_HEADER_TEMPLATE + self.intro_template = COMBINED_INTRO_TEMPLATE + self.footer_template = COMBINED_FOOTER_TEMPLATE + + def revision_gen_link(base_url): + # revision is used only to generate the body, and + # _content_type is set while generating headers. Get it + # from the BranchChange object. + revision._content_type = self._content_type + return revision.generate_browse_link(base_url) + self.generate_browse_link = revision_gen_link + for line in self.generate_email(push, body_filter, values): + yield line + + def generate_email_body(self, push): + '''Call the appropriate body generation routine. + + If this is a combined refchange/revision email, the special logic + for handling this combined email comes from this function. For + other cases, we just use the normal handling.''' + + # If self._single_revision isn't set; don't override + if not self._single_revision: + for line in super(BranchChange, self).generate_email_body(push): + yield line + return + + # This is a combined refchange/revision email; we first provide + # some info from the refchange portion, and then call the revision + # generate_email_body function to handle the revision portion. + adds = list(generate_summaries( + '--topo-order', '--reverse', '%s..%s' + % (self.old.commit_sha1, self.new.commit_sha1,) + )) + + yield self.expand("The following commit(s) were added to %(refname)s by this push:\n") + for (sha1, subject) in adds: + yield self.expand( + BRIEF_SUMMARY_TEMPLATE, action='new', + rev_short=sha1, text=subject, + ) + + yield self._single_revision.rev.short + " is described below\n" + yield '\n' + + for line in self._single_revision.generate_email_body(push): + yield line + + +class AnnotatedTagChange(ReferenceChange): + refname_type = 'annotated tag' + + def __init__(self, environment, refname, short_refname, old, new, rev): + ReferenceChange.__init__( + self, environment, + refname=refname, short_refname=short_refname, + old=old, new=new, rev=rev, + ) + self.recipients = environment.get_announce_recipients(self) + self.show_shortlog = environment.announce_show_shortlog + + ANNOTATED_TAG_FORMAT = ( + '%(*objectname)\n' + '%(*objecttype)\n' + '%(taggername)\n' + '%(taggerdate)' + ) + + def describe_tag(self, push): + """Describe the new value of an annotated tag.""" + + # Use git for-each-ref to pull out the individual fields from + # the tag + [tagobject, tagtype, tagger, tagged] = read_git_lines( + ['for-each-ref', '--format=%s' % (self.ANNOTATED_TAG_FORMAT,), self.refname], + ) + + yield self.expand( + BRIEF_SUMMARY_TEMPLATE, action='tagging', + rev_short=tagobject, text='(%s)' % (tagtype,), + ) + if tagtype == 'commit': + # If the tagged object is a commit, then we assume this is a + # release, and so we calculate which tag this tag is + # replacing + try: + prevtag = read_git_output(['describe', '--abbrev=0', '%s^' % (self.new,)]) + except CommandError: + prevtag = None + if prevtag: + yield ' replaces %s\n' % (prevtag,) + else: + prevtag = None + yield ' length %s bytes\n' % (read_git_output(['cat-file', '-s', tagobject]),) + + yield ' by %s\n' % (tagger,) + yield ' on %s\n' % (tagged,) + yield '\n' + + # Show the content of the tag message; this might contain a + # change log or release notes so is worth displaying. + yield LOGBEGIN + contents = list(read_git_lines(['cat-file', 'tag', self.new.sha1], keepends=True)) + contents = contents[contents.index('\n') + 1:] + if contents and contents[-1][-1:] != '\n': + contents.append('\n') + for line in contents: + yield line + + if self.show_shortlog and tagtype == 'commit': + # Only commit tags make sense to have rev-list operations + # performed on them + yield '\n' + if prevtag: + # Show changes since the previous release + revlist = read_git_output( + ['rev-list', '--pretty=short', '%s..%s' % (prevtag, self.new,)], + keepends=True, + ) + else: + # No previous tag, show all the changes since time + # began + revlist = read_git_output( + ['rev-list', '--pretty=short', '%s' % (self.new,)], + keepends=True, + ) + for line in read_git_lines(['shortlog'], input=revlist, keepends=True): + yield line + + yield LOGEND + yield '\n' + + def generate_create_summary(self, push): + """Called for the creation of an annotated tag.""" + + for line in self.expand_lines(TAG_CREATED_TEMPLATE): + yield line + + for line in self.describe_tag(push): + yield line + + def generate_update_summary(self, push): + """Called for the update of an annotated tag. + + This is probably a rare event and may not even be allowed.""" + + for line in self.expand_lines(TAG_UPDATED_TEMPLATE): + yield line + + for line in self.describe_tag(push): + yield line + + def generate_delete_summary(self, push): + """Called when a non-annotated reference is updated.""" + + for line in self.expand_lines(TAG_DELETED_TEMPLATE): + yield line + + yield self.expand(' tag was %(oldrev_short)s\n') + yield '\n' + + +class NonAnnotatedTagChange(ReferenceChange): + refname_type = 'tag' + + def __init__(self, environment, refname, short_refname, old, new, rev): + ReferenceChange.__init__( + self, environment, + refname=refname, short_refname=short_refname, + old=old, new=new, rev=rev, + ) + self.recipients = environment.get_refchange_recipients(self) + + def generate_create_summary(self, push): + """Called for the creation of an annotated tag.""" + + for line in self.expand_lines(TAG_CREATED_TEMPLATE): + yield line + + def generate_update_summary(self, push): + """Called when a non-annotated reference is updated.""" + + for line in self.expand_lines(TAG_UPDATED_TEMPLATE): + yield line + + def generate_delete_summary(self, push): + """Called when a non-annotated reference is updated.""" + + for line in self.expand_lines(TAG_DELETED_TEMPLATE): + yield line + + for line in ReferenceChange.generate_delete_summary(self, push): + yield line + + +class OtherReferenceChange(ReferenceChange): + refname_type = 'reference' + + def __init__(self, environment, refname, short_refname, old, new, rev): + # We use the full refname as short_refname, because otherwise + # the full name of the reference would not be obvious from the + # text of the email. + ReferenceChange.__init__( + self, environment, + refname=refname, short_refname=refname, + old=old, new=new, rev=rev, + ) + self.recipients = environment.get_refchange_recipients(self) + + +class Mailer(object): + """An object that can send emails.""" + + def __init__(self, environment): + self.environment = environment + + def close(self): + pass + + def send(self, lines, to_addrs): + """Send an email consisting of lines. + + lines must be an iterable over the lines constituting the + header and body of the email. to_addrs is a list of recipient + addresses (can be needed even if lines already contains a + "To:" field). It can be either a string (comma-separated list + of email addresses) or a Python list of individual email + addresses. + + """ + + raise NotImplementedError() + + +class SendMailer(Mailer): + """Send emails using 'sendmail -oi -t'.""" + + SENDMAIL_CANDIDATES = [ + '/usr/sbin/sendmail', + '/usr/lib/sendmail', + ] + + @staticmethod + def find_sendmail(): + for path in SendMailer.SENDMAIL_CANDIDATES: + if os.access(path, os.X_OK): + return path + else: + raise ConfigurationException( + 'No sendmail executable found. ' + 'Try setting multimailhook.sendmailCommand.' + ) + + def __init__(self, environment, command=None, envelopesender=None): + """Construct a SendMailer instance. + + command should be the command and arguments used to invoke + sendmail, as a list of strings. If an envelopesender is + provided, it will also be passed to the command, via '-f + envelopesender'.""" + super(SendMailer, self).__init__(environment) + if command: + self.command = command[:] + else: + self.command = [self.find_sendmail(), '-oi', '-t'] + + if envelopesender: + self.command.extend(['-f', envelopesender]) + + def send(self, lines, to_addrs): + try: + p = subprocess.Popen(self.command, stdin=subprocess.PIPE) + except OSError: + self.environment.get_logger().error( + '*** Cannot execute command: %s\n' % ' '.join(self.command) + + '*** %s\n' % sys.exc_info()[1] + + '*** Try setting multimailhook.mailer to "smtp"\n' + + '*** to send emails without using the sendmail command.\n' + ) + sys.exit(1) + try: + lines = (str_to_bytes(line) for line in lines) + p.stdin.writelines(lines) + except Exception: + self.environment.get_logger().error( + '*** Error while generating commit email\n' + '*** - mail sending aborted.\n' + ) + if hasattr(p, 'terminate'): + # subprocess.terminate() is not available in Python 2.4 + p.terminate() + else: + import signal + os.kill(p.pid, signal.SIGTERM) + raise + else: + p.stdin.close() + retcode = p.wait() + if retcode: + raise CommandError(self.command, retcode) + + +class SMTPMailer(Mailer): + """Send emails using Python's smtplib.""" + + def __init__(self, environment, + envelopesender, smtpserver, + smtpservertimeout=10.0, smtpserverdebuglevel=0, + smtpencryption='none', + smtpuser='', smtppass='', + smtpcacerts='' + ): + super(SMTPMailer, self).__init__(environment) + if not envelopesender: + self.environment.get_logger().error( + 'fatal: git_multimail: cannot use SMTPMailer without a sender address.\n' + 'please set either multimailhook.envelopeSender or user.email\n' + ) + sys.exit(1) + if smtpencryption == 'ssl' and not (smtpuser and smtppass): + raise ConfigurationException( + 'Cannot use SMTPMailer with security option ssl ' + 'without options username and password.' + ) + self.envelopesender = envelopesender + self.smtpserver = smtpserver + self.smtpservertimeout = smtpservertimeout + self.smtpserverdebuglevel = smtpserverdebuglevel + self.security = smtpencryption + self.username = smtpuser + self.password = smtppass + self.smtpcacerts = smtpcacerts + self.loggedin = False + try: + def call(klass, server, timeout): + try: + return klass(server, timeout=timeout) + except TypeError: + # Old Python versions do not have timeout= argument. + return klass(server) + if self.security == 'none': + self.smtp = call(smtplib.SMTP, self.smtpserver, timeout=self.smtpservertimeout) + elif self.security == 'ssl': + if self.smtpcacerts: + raise smtplib.SMTPException( + "Checking certificate is not supported for ssl, prefer starttls" + ) + self.smtp = call(smtplib.SMTP_SSL, self.smtpserver, timeout=self.smtpservertimeout) + elif self.security == 'tls': + if 'ssl' not in sys.modules: + self.environment.get_logger().error( + '*** Your Python version does not have the ssl library installed\n' + '*** smtpEncryption=tls is not available.\n' + '*** Either upgrade Python to 2.6 or later\n' + ' or use git_multimail.py version 1.2.\n') + if ':' not in self.smtpserver: + self.smtpserver += ':587' # default port for TLS + self.smtp = call(smtplib.SMTP, self.smtpserver, timeout=self.smtpservertimeout) + # start: ehlo + starttls + # equivalent to + # self.smtp.ehlo() + # self.smtp.starttls() + # with acces to the ssl layer + self.smtp.ehlo() + if not self.smtp.has_extn("starttls"): + raise smtplib.SMTPException("STARTTLS extension not supported by server") + resp, reply = self.smtp.docmd("STARTTLS") + if resp != 220: + raise smtplib.SMTPException("Wrong answer to the STARTTLS command") + if self.smtpcacerts: + self.smtp.sock = ssl.wrap_socket( + self.smtp.sock, + ca_certs=self.smtpcacerts, + cert_reqs=ssl.CERT_REQUIRED + ) + else: + self.smtp.sock = ssl.wrap_socket( + self.smtp.sock, + cert_reqs=ssl.CERT_NONE + ) + self.environment.get_logger().error( + '*** Warning, the server certificat is not verified (smtp) ***\n' + '*** set the option smtpCACerts ***\n' + ) + if not hasattr(self.smtp.sock, "read"): + # using httplib.FakeSocket with Python 2.5.x or earlier + self.smtp.sock.read = self.smtp.sock.recv + self.smtp.file = smtplib.SSLFakeFile(self.smtp.sock) + self.smtp.helo_resp = None + self.smtp.ehlo_resp = None + self.smtp.esmtp_features = {} + self.smtp.does_esmtp = 0 + # end: ehlo + starttls + self.smtp.ehlo() + else: + sys.stdout.write('*** Error: Control reached an invalid option. ***') + sys.exit(1) + if self.smtpserverdebuglevel > 0: + sys.stdout.write( + "*** Setting debug on for SMTP server connection (%s) ***\n" + % self.smtpserverdebuglevel) + self.smtp.set_debuglevel(self.smtpserverdebuglevel) + except Exception: + self.environment.get_logger().error( + '*** Error establishing SMTP connection to %s ***\n' + '*** %s\n' + % (self.smtpserver, sys.exc_info()[1])) + sys.exit(1) + + def close(self): + if hasattr(self, 'smtp'): + self.smtp.quit() + del self.smtp + + def __del__(self): + self.close() + + def send(self, lines, to_addrs): + try: + if self.username or self.password: + if not self.loggedin: + self.smtp.login(self.username, self.password) + self.loggedin = True + msg = ''.join(lines) + # turn comma-separated list into Python list if needed. + if is_string(to_addrs): + to_addrs = [email for (name, email) in getaddresses([to_addrs])] + self.smtp.sendmail(self.envelopesender, to_addrs, msg) + except socket.timeout: + self.environment.get_logger().error( + '*** Error sending email ***\n' + '*** SMTP server timed out (timeout is %s)\n' + % self.smtpservertimeout) + except smtplib.SMTPResponseException: + err = sys.exc_info()[1] + self.environment.get_logger().error( + '*** Error sending email ***\n' + '*** Error %d: %s\n' + % (err.smtp_code, bytes_to_str(err.smtp_error))) + try: + smtp = self.smtp + # delete the field before quit() so that in case of + # error, self.smtp is deleted anyway. + del self.smtp + smtp.quit() + except: + self.environment.get_logger().error( + '*** Error closing the SMTP connection ***\n' + '*** Exiting anyway ... ***\n' + '*** %s\n' % sys.exc_info()[1]) + sys.exit(1) + + +class OutputMailer(Mailer): + """Write emails to an output stream, bracketed by lines of '=' characters. + + This is intended for debugging purposes.""" + + SEPARATOR = '=' * 75 + '\n' + + def __init__(self, f, environment=None): + super(OutputMailer, self).__init__(environment=environment) + self.f = f + + def send(self, lines, to_addrs): + write_str(self.f, self.SEPARATOR) + for line in lines: + write_str(self.f, line) + write_str(self.f, self.SEPARATOR) + + +def get_git_dir(): + """Determine GIT_DIR. + + Determine GIT_DIR either from the GIT_DIR environment variable or + from the working directory, using Git's usual rules.""" + + try: + return read_git_output(['rev-parse', '--git-dir']) + except CommandError: + sys.stderr.write('fatal: git_multimail: not in a git directory\n') + sys.exit(1) + + +class Environment(object): + """Describes the environment in which the push is occurring. + + An Environment object encapsulates information about the local + environment. For example, it knows how to determine: + + * the name of the repository to which the push occurred + + * what user did the push + + * what users want to be informed about various types of changes. + + An Environment object is expected to have the following methods: + + get_repo_shortname() + + Return a short name for the repository, for display + purposes. + + get_repo_path() + + Return the absolute path to the Git repository. + + get_emailprefix() + + Return a string that will be prefixed to every email's + subject. + + get_pusher() + + Return the username of the person who pushed the changes. + This value is used in the email body to indicate who + pushed the change. + + get_pusher_email() (may return None) + + Return the email address of the person who pushed the + changes. The value should be a single RFC 2822 email + address as a string; e.g., "Joe User <user@example.com>" + if available, otherwise "user@example.com". If set, the + value is used as the Reply-To address for refchange + emails. If it is impossible to determine the pusher's + email, this attribute should be set to None (in which case + no Reply-To header will be output). + + get_sender() + + Return the address to be used as the 'From' email address + in the email envelope. + + get_fromaddr(change=None) + + Return the 'From' email address used in the email 'From:' + headers. If the change is known when this function is + called, it is passed in as the 'change' parameter. (May + be a full RFC 2822 email address like 'Joe User + <user@example.com>'.) + + get_administrator() + + Return the name and/or email of the repository + administrator. This value is used in the footer as the + person to whom requests to be removed from the + notification list should be sent. Ideally, it should + include a valid email address. + + get_reply_to_refchange() + get_reply_to_commit() + + Return the address to use in the email "Reply-To" header, + as a string. These can be an RFC 2822 email address, or + None to omit the "Reply-To" header. + get_reply_to_refchange() is used for refchange emails; + get_reply_to_commit() is used for individual commit + emails. + + get_ref_filter_regex() + + Return a tuple -- a compiled regex, and a boolean indicating + whether the regex picks refs to include (if False, the regex + matches on refs to exclude). + + get_default_ref_ignore_regex() + + Return a regex that should be ignored for both what emails + to send and when computing what commits are considered new + to the repository. Default is "^refs/notes/". + + get_max_subject_length() + + Return an int giving the maximal length for the subject + (git log --oneline). + + They should also define the following attributes: + + announce_show_shortlog (bool) + + True iff announce emails should include a shortlog. + + commit_email_format (string) + + If "html", generate commit emails in HTML instead of plain text + used by default. + + html_in_intro (bool) + html_in_footer (bool) + + When generating HTML emails, the introduction (respectively, + the footer) will be HTML-escaped iff html_in_intro (respectively, + the footer) is true. When false, only the values used to expand + the template are escaped. + + refchange_showgraph (bool) + + True iff refchanges emails should include a detailed graph. + + refchange_showlog (bool) + + True iff refchanges emails should include a detailed log. + + diffopts (list of strings) + + The options that should be passed to 'git diff' for the + summary email. The value should be a list of strings + representing words to be passed to the command. + + graphopts (list of strings) + + Analogous to diffopts, but contains options passed to + 'git log --graph' when generating the detailed graph for + a set of commits (see refchange_showgraph) + + logopts (list of strings) + + Analogous to diffopts, but contains options passed to + 'git log' when generating the detailed log for a set of + commits (see refchange_showlog) + + commitlogopts (list of strings) + + The options that should be passed to 'git log' for each + commit mail. The value should be a list of strings + representing words to be passed to the command. + + date_substitute (string) + + String to be used in substitution for 'Date:' at start of + line in the output of 'git log'. + + quiet (bool) + On success do not write to stderr + + stdout (bool) + Write email to stdout rather than emailing. Useful for debugging + + combine_when_single_commit (bool) + + True if a combined email should be produced when a single + new commit is pushed to a branch, False otherwise. + + from_refchange, from_commit (strings) + + Addresses to use for the From: field for refchange emails + and commit emails respectively. Set from + multimailhook.fromRefchange and multimailhook.fromCommit + by ConfigEnvironmentMixin. + + log_file, error_log_file, debug_log_file (string) + + Name of a file to which logs should be sent. + + verbose (int) + + How verbose the system should be. + - 0 (default): show info, errors, ... + - 1 : show basic debug info + """ + + REPO_NAME_RE = re.compile(r'^(?P<name>.+?)(?:\.git)$') + + def __init__(self, osenv=None): + self.osenv = osenv or os.environ + self.announce_show_shortlog = False + self.commit_email_format = "text" + self.html_in_intro = False + self.html_in_footer = False + self.commitBrowseURL = None + self.maxcommitemails = 500 + self.excludemergerevisions = False + self.diffopts = ['--stat', '--summary', '--find-copies-harder'] + self.graphopts = ['--oneline', '--decorate'] + self.logopts = [] + self.refchange_showgraph = False + self.refchange_showlog = False + self.commitlogopts = ['-C', '--stat', '-p', '--cc'] + self.date_substitute = 'AuthorDate: ' + self.quiet = False + self.stdout = False + self.combine_when_single_commit = True + self.logger = None + + self.COMPUTED_KEYS = [ + 'administrator', + 'charset', + 'emailprefix', + 'pusher', + 'pusher_email', + 'repo_path', + 'repo_shortname', + 'sender', + ] + + self._values = None + + def get_logger(self): + """Get (possibly creates) the logger associated to this environment.""" + if self.logger is None: + self.logger = Logger(self) + return self.logger + + def get_repo_shortname(self): + """Use the last part of the repo path, with ".git" stripped off if present.""" + + basename = os.path.basename(os.path.abspath(self.get_repo_path())) + m = self.REPO_NAME_RE.match(basename) + if m: + return m.group('name') + else: + return basename + + def get_pusher(self): + raise NotImplementedError() + + def get_pusher_email(self): + return None + + def get_fromaddr(self, change=None): + config = Config('user') + fromname = config.get('name', default='') + fromemail = config.get('email', default='') + if fromemail: + return formataddr([fromname, fromemail]) + return self.get_sender() + + def get_administrator(self): + return 'the administrator of this repository' + + def get_emailprefix(self): + return '' + + def get_repo_path(self): + if read_git_output(['rev-parse', '--is-bare-repository']) == 'true': + path = get_git_dir() + else: + path = read_git_output(['rev-parse', '--show-toplevel']) + return os.path.abspath(path) + + def get_charset(self): + return CHARSET + + def get_values(self): + """Return a dictionary {keyword: expansion} for this Environment. + + This method is called by Change._compute_values(). The keys + in the returned dictionary are available to be used in any of + the templates. The dictionary is created by calling + self.get_NAME() for each of the attributes named in + COMPUTED_KEYS and recording those that do not return None. + The return value is always a new dictionary.""" + + if self._values is None: + values = {'': ''} # %()s expands to the empty string. + + for key in self.COMPUTED_KEYS: + value = getattr(self, 'get_%s' % (key,))() + if value is not None: + values[key] = value + + self._values = values + + return self._values.copy() + + def get_refchange_recipients(self, refchange): + """Return the recipients for notifications about refchange. + + Return the list of email addresses to which notifications + about the specified ReferenceChange should be sent.""" + + raise NotImplementedError() + + def get_announce_recipients(self, annotated_tag_change): + """Return the recipients for notifications about annotated_tag_change. + + Return the list of email addresses to which notifications + about the specified AnnotatedTagChange should be sent.""" + + raise NotImplementedError() + + def get_reply_to_refchange(self, refchange): + return self.get_pusher_email() + + def get_revision_recipients(self, revision): + """Return the recipients for messages about revision. + + Return the list of email addresses to which notifications + about the specified Revision should be sent. This method + could be overridden, for example, to take into account the + contents of the revision when deciding whom to notify about + it. For example, there could be a scheme for users to express + interest in particular files or subdirectories, and only + receive notification emails for revisions that affecting those + files.""" + + raise NotImplementedError() + + def get_reply_to_commit(self, revision): + return revision.author + + def get_default_ref_ignore_regex(self): + # The commit messages of git notes are essentially meaningless + # and "filenames" in git notes commits are an implementational + # detail that might surprise users at first. As such, we + # would need a completely different method for handling emails + # of git notes in order for them to be of benefit for users, + # which we simply do not have right now. + return "^refs/notes/" + + def get_max_subject_length(self): + """Return the maximal subject line (git log --oneline) length. + Longer subject lines will be truncated.""" + raise NotImplementedError() + + def filter_body(self, lines): + """Filter the lines intended for an email body. + + lines is an iterable over the lines that would go into the + email body. Filter it (e.g., limit the number of lines, the + line length, character set, etc.), returning another iterable. + See FilterLinesEnvironmentMixin and MaxlinesEnvironmentMixin + for classes implementing this functionality.""" + + return lines + + def log_msg(self, msg): + """Write the string msg on a log file or on stderr. + + Sends the text to stderr by default, override to change the behavior.""" + self.get_logger().info(msg) + + def log_warning(self, msg): + """Write the string msg on a log file or on stderr. + + Sends the text to stderr by default, override to change the behavior.""" + self.get_logger().warning(msg) + + def log_error(self, msg): + """Write the string msg on a log file or on stderr. + + Sends the text to stderr by default, override to change the behavior.""" + self.get_logger().error(msg) + + def check(self): + pass + + +class ConfigEnvironmentMixin(Environment): + """A mixin that sets self.config to its constructor's config argument. + + This class's constructor consumes the "config" argument. + + Mixins that need to inspect the config should inherit from this + class (1) to make sure that "config" is still in the constructor + arguments with its own constructor runs and/or (2) to be sure that + self.config is set after construction.""" + + def __init__(self, config, **kw): + super(ConfigEnvironmentMixin, self).__init__(**kw) + self.config = config + + +class ConfigOptionsEnvironmentMixin(ConfigEnvironmentMixin): + """An Environment that reads most of its information from "git config".""" + + @staticmethod + def forbid_field_values(name, value, forbidden): + for forbidden_val in forbidden: + if value is not None and value.lower() == forbidden: + raise ConfigurationException( + '"%s" is not an allowed setting for %s' % (value, name) + ) + + def __init__(self, config, **kw): + super(ConfigOptionsEnvironmentMixin, self).__init__( + config=config, **kw + ) + + for var, cfg in ( + ('announce_show_shortlog', 'announceshortlog'), + ('refchange_showgraph', 'refchangeShowGraph'), + ('refchange_showlog', 'refchangeshowlog'), + ('quiet', 'quiet'), + ('stdout', 'stdout'), + ): + val = config.get_bool(cfg) + if val is not None: + setattr(self, var, val) + + commit_email_format = config.get('commitEmailFormat') + if commit_email_format is not None: + if commit_email_format != "html" and commit_email_format != "text": + self.log_warning( + '*** Unknown value for multimailhook.commitEmailFormat: %s\n' % + commit_email_format + + '*** Expected either "text" or "html". Ignoring.\n' + ) + else: + self.commit_email_format = commit_email_format + + html_in_intro = config.get_bool('htmlInIntro') + if html_in_intro is not None: + self.html_in_intro = html_in_intro + + html_in_footer = config.get_bool('htmlInFooter') + if html_in_footer is not None: + self.html_in_footer = html_in_footer + + self.commitBrowseURL = config.get('commitBrowseURL') + + self.excludemergerevisions = config.get('excludeMergeRevisions') + + maxcommitemails = config.get('maxcommitemails') + if maxcommitemails is not None: + try: + self.maxcommitemails = int(maxcommitemails) + except ValueError: + self.log_warning( + '*** Malformed value for multimailhook.maxCommitEmails: %s\n' + % maxcommitemails + + '*** Expected a number. Ignoring.\n' + ) + + diffopts = config.get('diffopts') + if diffopts is not None: + self.diffopts = shlex.split(diffopts) + + graphopts = config.get('graphOpts') + if graphopts is not None: + self.graphopts = shlex.split(graphopts) + + logopts = config.get('logopts') + if logopts is not None: + self.logopts = shlex.split(logopts) + + commitlogopts = config.get('commitlogopts') + if commitlogopts is not None: + self.commitlogopts = shlex.split(commitlogopts) + + date_substitute = config.get('dateSubstitute') + if date_substitute == 'none': + self.date_substitute = None + elif date_substitute is not None: + self.date_substitute = date_substitute + + reply_to = config.get('replyTo') + self.__reply_to_refchange = config.get('replyToRefchange', default=reply_to) + self.forbid_field_values('replyToRefchange', + self.__reply_to_refchange, + ['author']) + self.__reply_to_commit = config.get('replyToCommit', default=reply_to) + + self.from_refchange = config.get('fromRefchange') + self.forbid_field_values('fromRefchange', + self.from_refchange, + ['author', 'none']) + self.from_commit = config.get('fromCommit') + self.forbid_field_values('fromCommit', + self.from_commit, + ['none']) + + combine = config.get_bool('combineWhenSingleCommit') + if combine is not None: + self.combine_when_single_commit = combine + + self.log_file = config.get('logFile', default=None) + self.error_log_file = config.get('errorLogFile', default=None) + self.debug_log_file = config.get('debugLogFile', default=None) + if config.get_bool('Verbose', default=False): + self.verbose = 1 + else: + self.verbose = 0 + + def get_administrator(self): + return ( + self.config.get('administrator') or + self.get_sender() or + super(ConfigOptionsEnvironmentMixin, self).get_administrator() + ) + + def get_repo_shortname(self): + return ( + self.config.get('reponame') or + super(ConfigOptionsEnvironmentMixin, self).get_repo_shortname() + ) + + def get_emailprefix(self): + emailprefix = self.config.get('emailprefix') + if emailprefix is not None: + emailprefix = emailprefix.strip() + if emailprefix: + emailprefix += ' ' + else: + emailprefix = '[%(repo_shortname)s] ' + short_name = self.get_repo_shortname() + try: + return emailprefix % {'repo_shortname': short_name} + except: + self.get_logger().error( + '*** Invalid multimailhook.emailPrefix: %s\n' % emailprefix + + '*** %s\n' % sys.exc_info()[1] + + "*** Only the '%(repo_shortname)s' placeholder is allowed\n" + ) + raise ConfigurationException( + '"%s" is not an allowed setting for emailPrefix' % emailprefix + ) + + def get_sender(self): + return self.config.get('envelopesender') + + def process_addr(self, addr, change): + if addr.lower() == 'author': + if hasattr(change, 'author'): + return change.author + else: + return None + elif addr.lower() == 'pusher': + return self.get_pusher_email() + elif addr.lower() == 'none': + return None + else: + return addr + + def get_fromaddr(self, change=None): + fromaddr = self.config.get('from') + if change: + specific_fromaddr = change.get_specific_fromaddr() + if specific_fromaddr: + fromaddr = specific_fromaddr + if fromaddr: + fromaddr = self.process_addr(fromaddr, change) + if fromaddr: + return fromaddr + return super(ConfigOptionsEnvironmentMixin, self).get_fromaddr(change) + + def get_reply_to_refchange(self, refchange): + if self.__reply_to_refchange is None: + return super(ConfigOptionsEnvironmentMixin, self).get_reply_to_refchange(refchange) + else: + return self.process_addr(self.__reply_to_refchange, refchange) + + def get_reply_to_commit(self, revision): + if self.__reply_to_commit is None: + return super(ConfigOptionsEnvironmentMixin, self).get_reply_to_commit(revision) + else: + return self.process_addr(self.__reply_to_commit, revision) + + def get_scancommitforcc(self): + return self.config.get('scancommitforcc') + + +class FilterLinesEnvironmentMixin(Environment): + """Handle encoding and maximum line length of body lines. + + email_max_line_length (int or None) + + The maximum length of any single line in the email body. + Longer lines are truncated at that length with ' [...]' + appended. + + strict_utf8 (bool) + + If this field is set to True, then the email body text is + expected to be UTF-8. Any invalid characters are + converted to U+FFFD, the Unicode replacement character + (encoded as UTF-8, of course). + + """ + + def __init__(self, strict_utf8=True, + email_max_line_length=500, max_subject_length=500, + **kw): + super(FilterLinesEnvironmentMixin, self).__init__(**kw) + self.__strict_utf8 = strict_utf8 + self.__email_max_line_length = email_max_line_length + self.__max_subject_length = max_subject_length + + def filter_body(self, lines): + lines = super(FilterLinesEnvironmentMixin, self).filter_body(lines) + if self.__strict_utf8: + if not PYTHON3: + lines = (line.decode(ENCODING, 'replace') for line in lines) + # Limit the line length in Unicode-space to avoid + # splitting characters: + if self.__email_max_line_length > 0: + lines = limit_linelength(lines, self.__email_max_line_length) + if not PYTHON3: + lines = (line.encode(ENCODING, 'replace') for line in lines) + elif self.__email_max_line_length: + lines = limit_linelength(lines, self.__email_max_line_length) + + return lines + + def get_max_subject_length(self): + return self.__max_subject_length + + +class ConfigFilterLinesEnvironmentMixin( + ConfigEnvironmentMixin, + FilterLinesEnvironmentMixin, + ): + """Handle encoding and maximum line length based on config.""" + + def __init__(self, config, **kw): + strict_utf8 = config.get_bool('emailstrictutf8', default=None) + if strict_utf8 is not None: + kw['strict_utf8'] = strict_utf8 + + email_max_line_length = config.get('emailmaxlinelength') + if email_max_line_length is not None: + kw['email_max_line_length'] = int(email_max_line_length) + + max_subject_length = config.get('subjectMaxLength', default=email_max_line_length) + if max_subject_length is not None: + kw['max_subject_length'] = int(max_subject_length) + + super(ConfigFilterLinesEnvironmentMixin, self).__init__( + config=config, **kw + ) + + +class MaxlinesEnvironmentMixin(Environment): + """Limit the email body to a specified number of lines.""" + + def __init__(self, emailmaxlines, **kw): + super(MaxlinesEnvironmentMixin, self).__init__(**kw) + self.__emailmaxlines = emailmaxlines + + def filter_body(self, lines): + lines = super(MaxlinesEnvironmentMixin, self).filter_body(lines) + if self.__emailmaxlines > 0: + lines = limit_lines(lines, self.__emailmaxlines) + return lines + + +class ConfigMaxlinesEnvironmentMixin( + ConfigEnvironmentMixin, + MaxlinesEnvironmentMixin, + ): + """Limit the email body to the number of lines specified in config.""" + + def __init__(self, config, **kw): + emailmaxlines = int(config.get('emailmaxlines', default='0')) + super(ConfigMaxlinesEnvironmentMixin, self).__init__( + config=config, + emailmaxlines=emailmaxlines, + **kw + ) + + +class FQDNEnvironmentMixin(Environment): + """A mixin that sets the host's FQDN to its constructor argument.""" + + def __init__(self, fqdn, **kw): + super(FQDNEnvironmentMixin, self).__init__(**kw) + self.COMPUTED_KEYS += ['fqdn'] + self.__fqdn = fqdn + + def get_fqdn(self): + """Return the fully-qualified domain name for this host. + + Return None if it is unavailable or unwanted.""" + + return self.__fqdn + + +class ConfigFQDNEnvironmentMixin( + ConfigEnvironmentMixin, + FQDNEnvironmentMixin, + ): + """Read the FQDN from the config.""" + + def __init__(self, config, **kw): + fqdn = config.get('fqdn') + super(ConfigFQDNEnvironmentMixin, self).__init__( + config=config, + fqdn=fqdn, + **kw + ) + + +class ComputeFQDNEnvironmentMixin(FQDNEnvironmentMixin): + """Get the FQDN by calling socket.getfqdn().""" + + def __init__(self, **kw): + super(ComputeFQDNEnvironmentMixin, self).__init__( + fqdn=socket.getfqdn(), + **kw + ) + + +class PusherDomainEnvironmentMixin(ConfigEnvironmentMixin): + """Deduce pusher_email from pusher by appending an emaildomain.""" + + def __init__(self, **kw): + super(PusherDomainEnvironmentMixin, self).__init__(**kw) + self.__emaildomain = self.config.get('emaildomain') + + def get_pusher_email(self): + if self.__emaildomain: + # Derive the pusher's full email address in the default way: + return '%s@%s' % (self.get_pusher(), self.__emaildomain) + else: + return super(PusherDomainEnvironmentMixin, self).get_pusher_email() + + +class StaticRecipientsEnvironmentMixin(Environment): + """Set recipients statically based on constructor parameters.""" + + def __init__( + self, + refchange_recipients, announce_recipients, revision_recipients, scancommitforcc, + **kw + ): + super(StaticRecipientsEnvironmentMixin, self).__init__(**kw) + + # The recipients for various types of notification emails, as + # RFC 2822 email addresses separated by commas (or the empty + # string if no recipients are configured). Although there is + # a mechanism to choose the recipient lists based on on the + # actual *contents* of the change being reported, we only + # choose based on the *type* of the change. Therefore we can + # compute them once and for all: + self.__refchange_recipients = refchange_recipients + self.__announce_recipients = announce_recipients + self.__revision_recipients = revision_recipients + + def check(self): + if not (self.get_refchange_recipients(None) or + self.get_announce_recipients(None) or + self.get_revision_recipients(None) or + self.get_scancommitforcc()): + raise ConfigurationException('No email recipients configured!') + super(StaticRecipientsEnvironmentMixin, self).check() + + def get_refchange_recipients(self, refchange): + if self.__refchange_recipients is None: + return super(StaticRecipientsEnvironmentMixin, + self).get_refchange_recipients(refchange) + return self.__refchange_recipients + + def get_announce_recipients(self, annotated_tag_change): + if self.__announce_recipients is None: + return super(StaticRecipientsEnvironmentMixin, + self).get_refchange_recipients(annotated_tag_change) + return self.__announce_recipients + + def get_revision_recipients(self, revision): + if self.__revision_recipients is None: + return super(StaticRecipientsEnvironmentMixin, + self).get_refchange_recipients(revision) + return self.__revision_recipients + + +class CLIRecipientsEnvironmentMixin(Environment): + """Mixin storing recipients information coming from the + command-line.""" + + def __init__(self, cli_recipients=None, **kw): + super(CLIRecipientsEnvironmentMixin, self).__init__(**kw) + self.__cli_recipients = cli_recipients + + def get_refchange_recipients(self, refchange): + if self.__cli_recipients is None: + return super(CLIRecipientsEnvironmentMixin, + self).get_refchange_recipients(refchange) + return self.__cli_recipients + + def get_announce_recipients(self, annotated_tag_change): + if self.__cli_recipients is None: + return super(CLIRecipientsEnvironmentMixin, + self).get_announce_recipients(annotated_tag_change) + return self.__cli_recipients + + def get_revision_recipients(self, revision): + if self.__cli_recipients is None: + return super(CLIRecipientsEnvironmentMixin, + self).get_revision_recipients(revision) + return self.__cli_recipients + + +class ConfigRecipientsEnvironmentMixin( + ConfigEnvironmentMixin, + StaticRecipientsEnvironmentMixin + ): + """Determine recipients statically based on config.""" + + def __init__(self, config, **kw): + super(ConfigRecipientsEnvironmentMixin, self).__init__( + config=config, + refchange_recipients=self._get_recipients( + config, 'refchangelist', 'mailinglist', + ), + announce_recipients=self._get_recipients( + config, 'announcelist', 'refchangelist', 'mailinglist', + ), + revision_recipients=self._get_recipients( + config, 'commitlist', 'mailinglist', + ), + scancommitforcc=config.get('scancommitforcc'), + **kw + ) + + def _get_recipients(self, config, *names): + """Return the recipients for a particular type of message. + + Return the list of email addresses to which a particular type + of notification email should be sent, by looking at the config + value for "multimailhook.$name" for each of names. Use the + value from the first name that is configured. The return + value is a (possibly empty) string containing RFC 2822 email + addresses separated by commas. If no configuration could be + found, raise a ConfigurationException.""" + + for name in names: + lines = config.get_all(name) + if lines is not None: + lines = [line.strip() for line in lines] + # Single "none" is a special value equivalen to empty string. + if lines == ['none']: + lines = [''] + return ', '.join(lines) + else: + return '' + + +class StaticRefFilterEnvironmentMixin(Environment): + """Set branch filter statically based on constructor parameters.""" + + def __init__(self, ref_filter_incl_regex, ref_filter_excl_regex, + ref_filter_do_send_regex, ref_filter_dont_send_regex, + **kw): + super(StaticRefFilterEnvironmentMixin, self).__init__(**kw) + + if ref_filter_incl_regex and ref_filter_excl_regex: + raise ConfigurationException( + "Cannot specify both a ref inclusion and exclusion regex.") + self.__is_inclusion_filter = bool(ref_filter_incl_regex) + default_exclude = self.get_default_ref_ignore_regex() + if ref_filter_incl_regex: + ref_filter_regex = ref_filter_incl_regex + elif ref_filter_excl_regex: + ref_filter_regex = ref_filter_excl_regex + '|' + default_exclude + else: + ref_filter_regex = default_exclude + try: + self.__compiled_regex = re.compile(ref_filter_regex) + except Exception: + raise ConfigurationException( + 'Invalid Ref Filter Regex "%s": %s' % (ref_filter_regex, sys.exc_info()[1])) + + if ref_filter_do_send_regex and ref_filter_dont_send_regex: + raise ConfigurationException( + "Cannot specify both a ref doSend and dontSend regex.") + self.__is_do_send_filter = bool(ref_filter_do_send_regex) + if ref_filter_do_send_regex: + ref_filter_send_regex = ref_filter_do_send_regex + elif ref_filter_dont_send_regex: + ref_filter_send_regex = ref_filter_dont_send_regex + else: + ref_filter_send_regex = '.*' + self.__is_do_send_filter = True + try: + self.__send_compiled_regex = re.compile(ref_filter_send_regex) + except Exception: + raise ConfigurationException( + 'Invalid Ref Filter Regex "%s": %s' % + (ref_filter_send_regex, sys.exc_info()[1])) + + def get_ref_filter_regex(self, send_filter=False): + if send_filter: + return self.__send_compiled_regex, self.__is_do_send_filter + else: + return self.__compiled_regex, self.__is_inclusion_filter + + +class ConfigRefFilterEnvironmentMixin( + ConfigEnvironmentMixin, + StaticRefFilterEnvironmentMixin + ): + """Determine branch filtering statically based on config.""" + + def _get_regex(self, config, key): + """Get a list of whitespace-separated regex. The refFilter* config + variables are multivalued (hence the use of get_all), and we + allow each entry to be a whitespace-separated list (hence the + split on each line). The whole thing is glued into a single regex.""" + values = config.get_all(key) + if values is None: + return values + items = [] + for line in values: + for i in line.split(): + items.append(i) + if items == []: + return None + return '|'.join(items) + + def __init__(self, config, **kw): + super(ConfigRefFilterEnvironmentMixin, self).__init__( + config=config, + ref_filter_incl_regex=self._get_regex(config, 'refFilterInclusionRegex'), + ref_filter_excl_regex=self._get_regex(config, 'refFilterExclusionRegex'), + ref_filter_do_send_regex=self._get_regex(config, 'refFilterDoSendRegex'), + ref_filter_dont_send_regex=self._get_regex(config, 'refFilterDontSendRegex'), + **kw + ) + + +class ProjectdescEnvironmentMixin(Environment): + """Make a "projectdesc" value available for templates. + + By default, it is set to the first line of $GIT_DIR/description + (if that file is present and appears to be set meaningfully).""" + + def __init__(self, **kw): + super(ProjectdescEnvironmentMixin, self).__init__(**kw) + self.COMPUTED_KEYS += ['projectdesc'] + + def get_projectdesc(self): + """Return a one-line descripition of the project.""" + + git_dir = get_git_dir() + try: + projectdesc = open(os.path.join(git_dir, 'description')).readline().strip() + if projectdesc and not projectdesc.startswith('Unnamed repository'): + return projectdesc + except IOError: + pass + + return 'UNNAMED PROJECT' + + +class GenericEnvironmentMixin(Environment): + def get_pusher(self): + return self.osenv.get('USER', self.osenv.get('USERNAME', 'unknown user')) + + +class GitoliteEnvironmentHighPrecMixin(Environment): + def get_pusher(self): + return self.osenv.get('GL_USER', 'unknown user') + + +class GitoliteEnvironmentLowPrecMixin( + ConfigEnvironmentMixin, + Environment): + + def get_repo_shortname(self): + # The gitolite environment variable $GL_REPO is a pretty good + # repo_shortname (though it's probably not as good as a value + # the user might have explicitly put in his config). + return ( + self.osenv.get('GL_REPO', None) or + super(GitoliteEnvironmentLowPrecMixin, self).get_repo_shortname() + ) + + @staticmethod + def _compile_regex(re_template): + return ( + re.compile(re_template % x) + for x in ( + r'BEGIN\s+USER\s+EMAILS', + r'([^\s]+)\s+(.*)', + r'END\s+USER\s+EMAILS', + )) + + def get_fromaddr(self, change=None): + GL_USER = self.osenv.get('GL_USER') + if GL_USER is not None: + # Find the path to gitolite.conf. Note that gitolite v3 + # did away with the GL_ADMINDIR and GL_CONF environment + # variables (they are now hard-coded). + GL_ADMINDIR = self.osenv.get( + 'GL_ADMINDIR', + os.path.expanduser(os.path.join('~', '.gitolite'))) + GL_CONF = self.osenv.get( + 'GL_CONF', + os.path.join(GL_ADMINDIR, 'conf', 'gitolite.conf')) + + mailaddress_map = self.config.get('MailaddressMap') + # If relative, consider relative to GL_CONF: + if mailaddress_map: + mailaddress_map = os.path.join(os.path.dirname(GL_CONF), + mailaddress_map) + if os.path.isfile(mailaddress_map): + f = open(mailaddress_map, 'rU') + try: + # Leading '#' is optional + re_begin, re_user, re_end = self._compile_regex( + r'^(?:\s*#)?\s*%s\s*$') + for l in f: + l = l.rstrip('\n') + if re_begin.match(l) or re_end.match(l): + continue # Ignore these lines + m = re_user.match(l) + if m: + if m.group(1) == GL_USER: + return m.group(2) + else: + continue # Not this user, but not an error + raise ConfigurationException( + "Syntax error in mail address map.\n" + "Check file {}.\n" + "Line: {}".format(mailaddress_map, l)) + + finally: + f.close() + + if os.path.isfile(GL_CONF): + f = open(GL_CONF, 'rU') + try: + in_user_emails_section = False + re_begin, re_user, re_end = self._compile_regex( + r'^\s*#\s*%s\s*$') + for l in f: + l = l.rstrip('\n') + if not in_user_emails_section: + if re_begin.match(l): + in_user_emails_section = True + continue + if re_end.match(l): + break + m = re_user.match(l) + if m and m.group(1) == GL_USER: + return m.group(2) + finally: + f.close() + return super(GitoliteEnvironmentLowPrecMixin, self).get_fromaddr(change) + + +class IncrementalDateTime(object): + """Simple wrapper to give incremental date/times. + + Each call will result in a date/time a second later than the + previous call. This can be used to falsify email headers, to + increase the likelihood that email clients sort the emails + correctly.""" + + def __init__(self): + self.time = time.time() + self.next = self.__next__ # Python 2 backward compatibility + + def __next__(self): + formatted = formatdate(self.time, True) + self.time += 1 + return formatted + + +class StashEnvironmentHighPrecMixin(Environment): + def __init__(self, user=None, repo=None, **kw): + super(StashEnvironmentHighPrecMixin, + self).__init__(user=user, repo=repo, **kw) + self.__user = user + self.__repo = repo + + def get_pusher(self): + return re.match(r'(.*?)\s*<', self.__user).group(1) + + def get_pusher_email(self): + return self.__user + + +class StashEnvironmentLowPrecMixin(Environment): + def __init__(self, user=None, repo=None, **kw): + super(StashEnvironmentLowPrecMixin, self).__init__(**kw) + self.__repo = repo + self.__user = user + + def get_repo_shortname(self): + return self.__repo + + def get_fromaddr(self, change=None): + return self.__user + + +class GerritEnvironmentHighPrecMixin(Environment): + def __init__(self, project=None, submitter=None, update_method=None, **kw): + super(GerritEnvironmentHighPrecMixin, + self).__init__(submitter=submitter, project=project, **kw) + self.__project = project + self.__submitter = submitter + self.__update_method = update_method + "Make an 'update_method' value available for templates." + self.COMPUTED_KEYS += ['update_method'] + + def get_pusher(self): + if self.__submitter: + if self.__submitter.find('<') != -1: + # Submitter has a configured email, we transformed + # __submitter into an RFC 2822 string already. + return re.match(r'(.*?)\s*<', self.__submitter).group(1) + else: + # Submitter has no configured email, it's just his name. + return self.__submitter + else: + # If we arrive here, this means someone pushed "Submit" from + # the gerrit web UI for the CR (or used one of the programmatic + # APIs to do the same, such as gerrit review) and the + # merge/push was done by the Gerrit user. It was technically + # triggered by someone else, but sadly we have no way of + # determining who that someone else is at this point. + return 'Gerrit' # 'unknown user'? + + def get_pusher_email(self): + if self.__submitter: + return self.__submitter + else: + return super(GerritEnvironmentHighPrecMixin, self).get_pusher_email() + + def get_default_ref_ignore_regex(self): + default = super(GerritEnvironmentHighPrecMixin, self).get_default_ref_ignore_regex() + return default + '|^refs/changes/|^refs/cache-automerge/|^refs/meta/' + + def get_revision_recipients(self, revision): + # Merge commits created by Gerrit when users hit "Submit this patchset" + # in the Web UI (or do equivalently with REST APIs or the gerrit review + # command) are not something users want to see an individual email for. + # Filter them out. + committer = read_git_output(['log', '--no-walk', '--format=%cN', + revision.rev.sha1]) + if committer == 'Gerrit Code Review': + return [] + else: + return super(GerritEnvironmentHighPrecMixin, self).get_revision_recipients(revision) + + def get_update_method(self): + return self.__update_method + + +class GerritEnvironmentLowPrecMixin(Environment): + def __init__(self, project=None, submitter=None, **kw): + super(GerritEnvironmentLowPrecMixin, self).__init__(**kw) + self.__project = project + self.__submitter = submitter + + def get_repo_shortname(self): + return self.__project + + def get_fromaddr(self, change=None): + if self.__submitter and self.__submitter.find('<') != -1: + return self.__submitter + else: + return super(GerritEnvironmentLowPrecMixin, self).get_fromaddr(change) + + +class Push(object): + """Represent an entire push (i.e., a group of ReferenceChanges). + + It is easy to figure out what commits were added to a *branch* by + a Reference change: + + git rev-list change.old..change.new + + or removed from a *branch*: + + git rev-list change.new..change.old + + But it is not quite so trivial to determine which entirely new + commits were added to the *repository* by a push and which old + commits were discarded by a push. A big part of the job of this + class is to figure out these things, and to make sure that new + commits are only detailed once even if they were added to multiple + references. + + The first step is to determine the "other" references--those + unaffected by the current push. They are computed by listing all + references then removing any affected by this push. The results + are stored in Push._other_ref_sha1s. + + The commits contained in the repository before this push were + + git rev-list other1 other2 other3 ... change1.old change2.old ... + + Where "changeN.old" is the old value of one of the references + affected by this push. + + The commits contained in the repository after this push are + + git rev-list other1 other2 other3 ... change1.new change2.new ... + + The commits added by this push are the difference between these + two sets, which can be written + + git rev-list \ + ^other1 ^other2 ... \ + ^change1.old ^change2.old ... \ + change1.new change2.new ... + + The commits removed by this push can be computed by + + git rev-list \ + ^other1 ^other2 ... \ + ^change1.new ^change2.new ... \ + change1.old change2.old ... + + The last point is that it is possible that other pushes are + occurring simultaneously to this one, so reference values can + change at any time. It is impossible to eliminate all race + conditions, but we reduce the window of time during which problems + can occur by translating reference names to SHA1s as soon as + possible and working with SHA1s thereafter (because SHA1s are + immutable).""" + + # A map {(changeclass, changetype): integer} specifying the order + # that reference changes will be processed if multiple reference + # changes are included in a single push. The order is significant + # mostly because new commit notifications are threaded together + # with the first reference change that includes the commit. The + # following order thus causes commits to be grouped with branch + # changes (as opposed to tag changes) if possible. + SORT_ORDER = dict( + (value, i) for (i, value) in enumerate([ + (BranchChange, 'update'), + (BranchChange, 'create'), + (AnnotatedTagChange, 'update'), + (AnnotatedTagChange, 'create'), + (NonAnnotatedTagChange, 'update'), + (NonAnnotatedTagChange, 'create'), + (BranchChange, 'delete'), + (AnnotatedTagChange, 'delete'), + (NonAnnotatedTagChange, 'delete'), + (OtherReferenceChange, 'update'), + (OtherReferenceChange, 'create'), + (OtherReferenceChange, 'delete'), + ]) + ) + + def __init__(self, environment, changes, ignore_other_refs=False): + self.changes = sorted(changes, key=self._sort_key) + self.__other_ref_sha1s = None + self.__cached_commits_spec = {} + self.environment = environment + + if ignore_other_refs: + self.__other_ref_sha1s = set() + + @classmethod + def _sort_key(klass, change): + return (klass.SORT_ORDER[change.__class__, change.change_type], change.refname,) + + @property + def _other_ref_sha1s(self): + """The GitObjects referred to by references unaffected by this push. + """ + if self.__other_ref_sha1s is None: + # The refnames being changed by this push: + updated_refs = set( + change.refname + for change in self.changes + ) + + # The SHA-1s of commits referred to by all references in this + # repository *except* updated_refs: + sha1s = set() + fmt = ( + '%(objectname) %(objecttype) %(refname)\n' + '%(*objectname) %(*objecttype) %(refname)' + ) + ref_filter_regex, is_inclusion_filter = \ + self.environment.get_ref_filter_regex() + for line in read_git_lines( + ['for-each-ref', '--format=%s' % (fmt,)]): + (sha1, type, name) = line.split(' ', 2) + if (sha1 and type == 'commit' and + name not in updated_refs and + include_ref(name, ref_filter_regex, is_inclusion_filter)): + sha1s.add(sha1) + + self.__other_ref_sha1s = sha1s + + return self.__other_ref_sha1s + + def _get_commits_spec_incl(self, new_or_old, reference_change=None): + """Get new or old SHA-1 from one or each of the changed refs. + + Return a list of SHA-1 commit identifier strings suitable as + arguments to 'git rev-list' (or 'git log' or ...). The + returned identifiers are either the old or new values from one + or all of the changed references, depending on the values of + new_or_old and reference_change. + + new_or_old is either the string 'new' or the string 'old'. If + 'new', the returned SHA-1 identifiers are the new values from + each changed reference. If 'old', the SHA-1 identifiers are + the old values from each changed reference. + + If reference_change is specified and not None, only the new or + old reference from the specified reference is included in the + return value. + + This function returns None if there are no matching revisions + (e.g., because a branch was deleted and new_or_old is 'new'). + """ + + if not reference_change: + incl_spec = sorted( + getattr(change, new_or_old).sha1 + for change in self.changes + if getattr(change, new_or_old) + ) + if not incl_spec: + incl_spec = None + elif not getattr(reference_change, new_or_old).commit_sha1: + incl_spec = None + else: + incl_spec = [getattr(reference_change, new_or_old).commit_sha1] + return incl_spec + + def _get_commits_spec_excl(self, new_or_old): + """Get exclusion revisions for determining new or discarded commits. + + Return a list of strings suitable as arguments to 'git + rev-list' (or 'git log' or ...) that will exclude all + commits that, depending on the value of new_or_old, were + either previously in the repository (useful for determining + which commits are new to the repository) or currently in the + repository (useful for determining which commits were + discarded from the repository). + + new_or_old is either the string 'new' or the string 'old'. If + 'new', the commits to be excluded are those that were in the + repository before the push. If 'old', the commits to be + excluded are those that are currently in the repository. """ + + old_or_new = {'old': 'new', 'new': 'old'}[new_or_old] + excl_revs = self._other_ref_sha1s.union( + getattr(change, old_or_new).sha1 + for change in self.changes + if getattr(change, old_or_new).type in ['commit', 'tag'] + ) + return ['^' + sha1 for sha1 in sorted(excl_revs)] + + def get_commits_spec(self, new_or_old, reference_change=None): + """Get rev-list arguments for added or discarded commits. + + Return a list of strings suitable as arguments to 'git + rev-list' (or 'git log' or ...) that select those commits + that, depending on the value of new_or_old, are either new to + the repository or were discarded from the repository. + + new_or_old is either the string 'new' or the string 'old'. If + 'new', the returned list is used to select commits that are + new to the repository. If 'old', the returned value is used + to select the commits that have been discarded from the + repository. + + If reference_change is specified and not None, the new or + discarded commits are limited to those that are reachable from + the new or old value of the specified reference. + + This function returns None if there are no added (or discarded) + revisions. + """ + key = (new_or_old, reference_change) + if key not in self.__cached_commits_spec: + ret = self._get_commits_spec_incl(new_or_old, reference_change) + if ret is not None: + ret.extend(self._get_commits_spec_excl(new_or_old)) + self.__cached_commits_spec[key] = ret + return self.__cached_commits_spec[key] + + def get_new_commits(self, reference_change=None): + """Return a list of commits added by this push. + + Return a list of the object names of commits that were added + by the part of this push represented by reference_change. If + reference_change is None, then return a list of *all* commits + added by this push.""" + + spec = self.get_commits_spec('new', reference_change) + return git_rev_list(spec) + + def get_discarded_commits(self, reference_change): + """Return a list of commits discarded by this push. + + Return a list of the object names of commits that were + entirely discarded from the repository by the part of this + push represented by reference_change.""" + + spec = self.get_commits_spec('old', reference_change) + return git_rev_list(spec) + + def send_emails(self, mailer, body_filter=None): + """Use send all of the notification emails needed for this push. + + Use send all of the notification emails (including reference + change emails and commit emails) needed for this push. Send + the emails using mailer. If body_filter is not None, then use + it to filter the lines that are intended for the email + body.""" + + # The sha1s of commits that were introduced by this push. + # They will be removed from this set as they are processed, to + # guarantee that one (and only one) email is generated for + # each new commit. + unhandled_sha1s = set(self.get_new_commits()) + send_date = IncrementalDateTime() + for change in self.changes: + sha1s = [] + for sha1 in reversed(list(self.get_new_commits(change))): + if sha1 in unhandled_sha1s: + sha1s.append(sha1) + unhandled_sha1s.remove(sha1) + + # Check if we've got anyone to send to + if not change.recipients: + change.environment.log_warning( + '*** no recipients configured so no email will be sent\n' + '*** for %r update %s->%s' + % (change.refname, change.old.sha1, change.new.sha1,) + ) + else: + if not change.environment.quiet: + change.environment.log_msg( + 'Sending notification emails to: %s' % (change.recipients,)) + extra_values = {'send_date': next(send_date)} + + rev = change.send_single_combined_email(sha1s) + if rev: + mailer.send( + change.generate_combined_email(self, rev, body_filter, extra_values), + rev.recipients, + ) + # This change is now fully handled; no need to handle + # individual revisions any further. + continue + else: + mailer.send( + change.generate_email(self, body_filter, extra_values), + change.recipients, + ) + + max_emails = change.environment.maxcommitemails + if max_emails and len(sha1s) > max_emails: + change.environment.log_warning( + '*** Too many new commits (%d), not sending commit emails.\n' % len(sha1s) + + '*** Try setting multimailhook.maxCommitEmails to a greater value\n' + + '*** Currently, multimailhook.maxCommitEmails=%d' % max_emails + ) + return + + for (num, sha1) in enumerate(sha1s): + rev = Revision(change, GitObject(sha1), num=num + 1, tot=len(sha1s)) + if len(rev.parents) > 1 and change.environment.excludemergerevisions: + # skipping a merge commit + continue + if not rev.recipients and rev.cc_recipients: + change.environment.log_msg('*** Replacing Cc: with To:') + rev.recipients = rev.cc_recipients + rev.cc_recipients = None + if rev.recipients: + extra_values = {'send_date': next(send_date)} + mailer.send( + rev.generate_email(self, body_filter, extra_values), + rev.recipients, + ) + + # Consistency check: + if unhandled_sha1s: + change.environment.log_error( + 'ERROR: No emails were sent for the following new commits:\n' + ' %s' + % ('\n '.join(sorted(unhandled_sha1s)),) + ) + + +def include_ref(refname, ref_filter_regex, is_inclusion_filter): + does_match = bool(ref_filter_regex.search(refname)) + if is_inclusion_filter: + return does_match + else: # exclusion filter -- we include the ref if the regex doesn't match + return not does_match + + +def run_as_post_receive_hook(environment, mailer): + environment.check() + send_filter_regex, send_is_inclusion_filter = environment.get_ref_filter_regex(True) + ref_filter_regex, is_inclusion_filter = environment.get_ref_filter_regex(False) + changes = [] + while True: + line = read_line(sys.stdin) + if line == '': + break + (oldrev, newrev, refname) = line.strip().split(' ', 2) + environment.get_logger().debug( + "run_as_post_receive_hook: oldrev=%s, newrev=%s, refname=%s" % + (oldrev, newrev, refname)) + + if not include_ref(refname, ref_filter_regex, is_inclusion_filter): + continue + if not include_ref(refname, send_filter_regex, send_is_inclusion_filter): + continue + changes.append( + ReferenceChange.create(environment, oldrev, newrev, refname) + ) + if not changes: + mailer.close() + return + push = Push(environment, changes) + try: + push.send_emails(mailer, body_filter=environment.filter_body) + finally: + mailer.close() + + +def run_as_update_hook(environment, mailer, refname, oldrev, newrev, force_send=False): + environment.check() + send_filter_regex, send_is_inclusion_filter = environment.get_ref_filter_regex(True) + ref_filter_regex, is_inclusion_filter = environment.get_ref_filter_regex(False) + if not include_ref(refname, ref_filter_regex, is_inclusion_filter): + return + if not include_ref(refname, send_filter_regex, send_is_inclusion_filter): + return + changes = [ + ReferenceChange.create( + environment, + read_git_output(['rev-parse', '--verify', oldrev]), + read_git_output(['rev-parse', '--verify', newrev]), + refname, + ), + ] + if not changes: + mailer.close() + return + push = Push(environment, changes, force_send) + try: + push.send_emails(mailer, body_filter=environment.filter_body) + finally: + mailer.close() + + +def check_ref_filter(environment): + send_filter_regex, send_is_inclusion = environment.get_ref_filter_regex(True) + ref_filter_regex, ref_is_inclusion = environment.get_ref_filter_regex(False) + + def inc_exc_lusion(b): + if b: + return 'inclusion' + else: + return 'exclusion' + + if send_filter_regex: + sys.stdout.write("DoSend/DontSend filter regex (" + + (inc_exc_lusion(send_is_inclusion)) + + '): ' + send_filter_regex.pattern + + '\n') + if send_filter_regex: + sys.stdout.write("Include/Exclude filter regex (" + + (inc_exc_lusion(ref_is_inclusion)) + + '): ' + ref_filter_regex.pattern + + '\n') + sys.stdout.write(os.linesep) + + sys.stdout.write( + "Refs marked as EXCLUDE are excluded by either refFilterInclusionRegex\n" + "or refFilterExclusionRegex. No emails will be sent for commits included\n" + "in these refs.\n" + "Refs marked as DONT-SEND are excluded by either refFilterDoSendRegex or\n" + "refFilterDontSendRegex, but not by either refFilterInclusionRegex or\n" + "refFilterExclusionRegex. Emails will be sent for commits included in these\n" + "refs only when the commit reaches a ref which isn't excluded.\n" + "Refs marked as DO-SEND are not excluded by any filter. Emails will\n" + "be sent normally for commits included in these refs.\n") + + sys.stdout.write(os.linesep) + + for refname in read_git_lines(['for-each-ref', '--format', '%(refname)']): + sys.stdout.write(refname) + if not include_ref(refname, ref_filter_regex, ref_is_inclusion): + sys.stdout.write(' EXCLUDE') + elif not include_ref(refname, send_filter_regex, send_is_inclusion): + sys.stdout.write(' DONT-SEND') + else: + sys.stdout.write(' DO-SEND') + + sys.stdout.write(os.linesep) + + +def show_env(environment, out): + out.write('Environment values:\n') + for (k, v) in sorted(environment.get_values().items()): + if k: # Don't show the {'' : ''} pair. + out.write(' %s : %r\n' % (k, v)) + out.write('\n') + # Flush to avoid interleaving with further log output + out.flush() + + +def check_setup(environment): + environment.check() + show_env(environment, sys.stdout) + sys.stdout.write("Now, checking that git-multimail's standard input " + "is properly set ..." + os.linesep) + sys.stdout.write("Please type some text and then press Return" + os.linesep) + stdin = sys.stdin.readline() + sys.stdout.write("You have just entered:" + os.linesep) + sys.stdout.write(stdin) + sys.stdout.write("git-multimail seems properly set up." + os.linesep) + + +def choose_mailer(config, environment): + mailer = config.get('mailer', default='sendmail') + + if mailer == 'smtp': + smtpserver = config.get('smtpserver', default='localhost') + smtpservertimeout = float(config.get('smtpservertimeout', default=10.0)) + smtpserverdebuglevel = int(config.get('smtpserverdebuglevel', default=0)) + smtpencryption = config.get('smtpencryption', default='none') + smtpuser = config.get('smtpuser', default='') + smtppass = config.get('smtppass', default='') + smtpcacerts = config.get('smtpcacerts', default='') + mailer = SMTPMailer( + environment, + envelopesender=(environment.get_sender() or environment.get_fromaddr()), + smtpserver=smtpserver, smtpservertimeout=smtpservertimeout, + smtpserverdebuglevel=smtpserverdebuglevel, + smtpencryption=smtpencryption, + smtpuser=smtpuser, + smtppass=smtppass, + smtpcacerts=smtpcacerts + ) + elif mailer == 'sendmail': + command = config.get('sendmailcommand') + if command: + command = shlex.split(command) + mailer = SendMailer(environment, + command=command, envelopesender=environment.get_sender()) + else: + environment.log_error( + 'fatal: multimailhook.mailer is set to an incorrect value: "%s"\n' % mailer + + 'please use one of "smtp" or "sendmail".' + ) + sys.exit(1) + return mailer + + +KNOWN_ENVIRONMENTS = { + 'generic': {'highprec': GenericEnvironmentMixin}, + 'gitolite': {'highprec': GitoliteEnvironmentHighPrecMixin, + 'lowprec': GitoliteEnvironmentLowPrecMixin}, + 'stash': {'highprec': StashEnvironmentHighPrecMixin, + 'lowprec': StashEnvironmentLowPrecMixin}, + 'gerrit': {'highprec': GerritEnvironmentHighPrecMixin, + 'lowprec': GerritEnvironmentLowPrecMixin}, + } + + +def choose_environment(config, osenv=None, env=None, recipients=None, + hook_info=None): + env_name = choose_environment_name(config, env, osenv) + environment_klass = build_environment_klass(env_name) + env = build_environment(environment_klass, env_name, config, + osenv, recipients, hook_info) + return env + + +def choose_environment_name(config, env, osenv): + if not osenv: + osenv = os.environ + + if not env: + env = config.get('environment') + + if not env: + if 'GL_USER' in osenv and 'GL_REPO' in osenv: + env = 'gitolite' + else: + env = 'generic' + return env + + +COMMON_ENVIRONMENT_MIXINS = [ + ConfigRecipientsEnvironmentMixin, + CLIRecipientsEnvironmentMixin, + ConfigRefFilterEnvironmentMixin, + ProjectdescEnvironmentMixin, + ConfigMaxlinesEnvironmentMixin, + ComputeFQDNEnvironmentMixin, + ConfigFilterLinesEnvironmentMixin, + PusherDomainEnvironmentMixin, + ConfigOptionsEnvironmentMixin, + ] + + +def build_environment_klass(env_name): + if 'class' in KNOWN_ENVIRONMENTS[env_name]: + return KNOWN_ENVIRONMENTS[env_name]['class'] + + environment_mixins = [] + known_env = KNOWN_ENVIRONMENTS[env_name] + if 'highprec' in known_env: + high_prec_mixin = known_env['highprec'] + environment_mixins.append(high_prec_mixin) + environment_mixins = environment_mixins + COMMON_ENVIRONMENT_MIXINS + if 'lowprec' in known_env: + low_prec_mixin = known_env['lowprec'] + environment_mixins.append(low_prec_mixin) + environment_mixins.append(Environment) + klass_name = env_name.capitalize() + 'Environment' + environment_klass = type( + klass_name, + tuple(environment_mixins), + {}, + ) + KNOWN_ENVIRONMENTS[env_name]['class'] = environment_klass + return environment_klass + + +GerritEnvironment = build_environment_klass('gerrit') +StashEnvironment = build_environment_klass('stash') +GitoliteEnvironment = build_environment_klass('gitolite') +GenericEnvironment = build_environment_klass('generic') + + +def build_environment(environment_klass, env, config, + osenv, recipients, hook_info): + environment_kw = { + 'osenv': osenv, + 'config': config, + } + + if env == 'stash': + environment_kw['user'] = hook_info['stash_user'] + environment_kw['repo'] = hook_info['stash_repo'] + elif env == 'gerrit': + environment_kw['project'] = hook_info['project'] + environment_kw['submitter'] = hook_info['submitter'] + environment_kw['update_method'] = hook_info['update_method'] + + environment_kw['cli_recipients'] = recipients + + return environment_klass(**environment_kw) + + +def get_version(): + oldcwd = os.getcwd() + try: + try: + os.chdir(os.path.dirname(os.path.realpath(__file__))) + git_version = read_git_output(['describe', '--tags', 'HEAD']) + if git_version == __version__: + return git_version + else: + return '%s (%s)' % (__version__, git_version) + except: + pass + finally: + os.chdir(oldcwd) + return __version__ + + +def compute_gerrit_options(options, args, required_gerrit_options, + raw_refname): + if None in required_gerrit_options: + raise SystemExit("Error: Specify all of --oldrev, --newrev, --refname, " + "and --project; or none of them.") + + if options.environment not in (None, 'gerrit'): + raise SystemExit("Non-gerrit environments incompatible with --oldrev, " + "--newrev, --refname, and --project") + options.environment = 'gerrit' + + if args: + raise SystemExit("Error: Positional parameters not allowed with " + "--oldrev, --newrev, and --refname.") + + # Gerrit oddly omits 'refs/heads/' in the refname when calling + # ref-updated hook; put it back. + git_dir = get_git_dir() + if (not os.path.exists(os.path.join(git_dir, raw_refname)) and + os.path.exists(os.path.join(git_dir, 'refs', 'heads', + raw_refname))): + options.refname = 'refs/heads/' + options.refname + + # New revisions can appear in a gerrit repository either due to someone + # pushing directly (in which case options.submitter will be set), or they + # can press "Submit this patchset" in the web UI for some CR (in which + # case options.submitter will not be set and gerrit will not have provided + # us the information about who pressed the button). + # + # Note for the nit-picky: I'm lumping in REST API calls and the ssh + # gerrit review command in with "Submit this patchset" button, since they + # have the same effect. + if options.submitter: + update_method = 'pushed' + # The submitter argument is almost an RFC 2822 email address; change it + # from 'User Name (email@domain)' to 'User Name <email@domain>' so it is + options.submitter = options.submitter.replace('(', '<').replace(')', '>') + else: + update_method = 'submitted' + # Gerrit knew who submitted this patchset, but threw that information + # away when it invoked this hook. However, *IF* Gerrit created a + # merge to bring the patchset in (project 'Submit Type' is either + # "Always Merge", or is "Merge if Necessary" and happens to be + # necessary for this particular CR), then it will have the committer + # of that merge be 'Gerrit Code Review' and the author will be the + # person who requested the submission of the CR. Since this is fairly + # likely for most gerrit installations (of a reasonable size), it's + # worth the extra effort to try to determine the actual submitter. + rev_info = read_git_lines(['log', '--no-walk', '--merges', + '--format=%cN%n%aN <%aE>', options.newrev]) + if rev_info and rev_info[0] == 'Gerrit Code Review': + options.submitter = rev_info[1] + + # We pass back refname, oldrev, newrev as args because then the + # gerrit ref-updated hook is much like the git update hook + return (options, + [options.refname, options.oldrev, options.newrev], + {'project': options.project, 'submitter': options.submitter, + 'update_method': update_method}) + + +def check_hook_specific_args(options, args): + raw_refname = options.refname + # Convert each string option unicode for Python3. + if PYTHON3: + opts = ['environment', 'recipients', 'oldrev', 'newrev', 'refname', + 'project', 'submitter', 'stash_user', 'stash_repo'] + for opt in opts: + if not hasattr(options, opt): + continue + obj = getattr(options, opt) + if obj: + enc = obj.encode('utf-8', 'surrogateescape') + dec = enc.decode('utf-8', 'replace') + setattr(options, opt, dec) + + # First check for stash arguments + if (options.stash_user is None) != (options.stash_repo is None): + raise SystemExit("Error: Specify both of --stash-user and " + "--stash-repo or neither.") + if options.stash_user: + options.environment = 'stash' + return options, args, {'stash_user': options.stash_user, + 'stash_repo': options.stash_repo} + + # Finally, check for gerrit specific arguments + required_gerrit_options = (options.oldrev, options.newrev, options.refname, + options.project) + if required_gerrit_options != (None,) * 4: + return compute_gerrit_options(options, args, required_gerrit_options, + raw_refname) + + # No special options in use, just return what we started with + return options, args, {} + + +class Logger(object): + def parse_verbose(self, verbose): + if verbose > 0: + return logging.DEBUG + else: + return logging.INFO + + def create_log_file(self, environment, name, path, verbosity): + log_file = logging.getLogger(name) + file_handler = logging.FileHandler(path) + log_fmt = logging.Formatter("%(asctime)s [%(levelname)-5.5s] %(message)s") + file_handler.setFormatter(log_fmt) + log_file.addHandler(file_handler) + log_file.setLevel(verbosity) + return log_file + + def __init__(self, environment): + self.environment = environment + self.loggers = [] + stderr_log = logging.getLogger('git_multimail.stderr') + + class EncodedStderr(object): + def write(self, x): + write_str(sys.stderr, x) + + def flush(self): + sys.stderr.flush() + + stderr_handler = logging.StreamHandler(EncodedStderr()) + stderr_log.addHandler(stderr_handler) + stderr_log.setLevel(self.parse_verbose(environment.verbose)) + self.loggers.append(stderr_log) + + if environment.debug_log_file is not None: + debug_log_file = self.create_log_file( + environment, 'git_multimail.debug', environment.debug_log_file, logging.DEBUG) + self.loggers.append(debug_log_file) + + if environment.log_file is not None: + log_file = self.create_log_file( + environment, 'git_multimail.file', environment.log_file, logging.INFO) + self.loggers.append(log_file) + + if environment.error_log_file is not None: + error_log_file = self.create_log_file( + environment, 'git_multimail.error', environment.error_log_file, logging.ERROR) + self.loggers.append(error_log_file) + + def info(self, msg, *args, **kwargs): + for l in self.loggers: + l.info(msg, *args, **kwargs) + + def debug(self, msg, *args, **kwargs): + for l in self.loggers: + l.debug(msg, *args, **kwargs) + + def warning(self, msg, *args, **kwargs): + for l in self.loggers: + l.warning(msg, *args, **kwargs) + + def error(self, msg, *args, **kwargs): + for l in self.loggers: + l.error(msg, *args, **kwargs) + + +def main(args): + parser = optparse.OptionParser( + description=__doc__, + usage='%prog [OPTIONS]\n or: %prog [OPTIONS] REFNAME OLDREV NEWREV', + ) + + parser.add_option( + '--environment', '--env', action='store', type='choice', + choices=list(KNOWN_ENVIRONMENTS.keys()), default=None, + help=( + 'Choose type of environment is in use. Default is taken from ' + 'multimailhook.environment if set; otherwise "generic".' + ), + ) + parser.add_option( + '--stdout', action='store_true', default=False, + help='Output emails to stdout rather than sending them.', + ) + parser.add_option( + '--recipients', action='store', default=None, + help='Set list of email recipients for all types of emails.', + ) + parser.add_option( + '--show-env', action='store_true', default=False, + help=( + 'Write to stderr the values determined for the environment ' + '(intended for debugging purposes), then proceed normally.' + ), + ) + parser.add_option( + '--force-send', action='store_true', default=False, + help=( + 'Force sending refchange email when using as an update hook. ' + 'This is useful to work around the unreliable new commits ' + 'detection in this mode.' + ), + ) + parser.add_option( + '-c', metavar="<name>=<value>", action='append', + help=( + 'Pass a configuration parameter through to git. The value given ' + 'will override values from configuration files. See the -c option ' + 'of git(1) for more details. (Only works with git >= 1.7.3)' + ), + ) + parser.add_option( + '--version', '-v', action='store_true', default=False, + help=( + "Display git-multimail's version" + ), + ) + + parser.add_option( + '--python-version', action='store_true', default=False, + help=( + "Display the version of Python used by git-multimail" + ), + ) + + parser.add_option( + '--check-ref-filter', action='store_true', default=False, + help=( + 'List refs and show information on how git-multimail ' + 'will process them.' + ) + ) + + # The following options permit this script to be run as a gerrit + # ref-updated hook. See e.g. + # code.google.com/p/gerrit/source/browse/Documentation/config-hooks.txt + # We suppress help for these items, since these are specific to gerrit, + # and we don't want users directly using them any way other than how the + # gerrit ref-updated hook is called. + parser.add_option('--oldrev', action='store', help=optparse.SUPPRESS_HELP) + parser.add_option('--newrev', action='store', help=optparse.SUPPRESS_HELP) + parser.add_option('--refname', action='store', help=optparse.SUPPRESS_HELP) + parser.add_option('--project', action='store', help=optparse.SUPPRESS_HELP) + parser.add_option('--submitter', action='store', help=optparse.SUPPRESS_HELP) + + # The following allow this to be run as a stash asynchronous post-receive + # hook (almost identical to a git post-receive hook but triggered also for + # merges of pull requests from the UI). We suppress help for these items, + # since these are specific to stash. + parser.add_option('--stash-user', action='store', help=optparse.SUPPRESS_HELP) + parser.add_option('--stash-repo', action='store', help=optparse.SUPPRESS_HELP) + + (options, args) = parser.parse_args(args) + (options, args, hook_info) = check_hook_specific_args(options, args) + + if options.version: + sys.stdout.write('git-multimail version ' + get_version() + '\n') + return + + if options.python_version: + sys.stdout.write('Python version ' + sys.version + '\n') + return + + if options.c: + Config.add_config_parameters(options.c) + + config = Config('multimailhook') + + environment = None + try: + environment = choose_environment( + config, osenv=os.environ, + env=options.environment, + recipients=options.recipients, + hook_info=hook_info, + ) + + if options.show_env: + show_env(environment, sys.stderr) + + if options.stdout or environment.stdout: + mailer = OutputMailer(sys.stdout, environment) + else: + mailer = choose_mailer(config, environment) + + must_check_setup = os.environ.get('GIT_MULTIMAIL_CHECK_SETUP') + if must_check_setup == '': + must_check_setup = False + if options.check_ref_filter: + check_ref_filter(environment) + elif must_check_setup: + check_setup(environment) + # Dual mode: if arguments were specified on the command line, run + # like an update hook; otherwise, run as a post-receive hook. + elif args: + if len(args) != 3: + parser.error('Need zero or three non-option arguments') + (refname, oldrev, newrev) = args + environment.get_logger().debug( + "run_as_update_hook: refname=%s, oldrev=%s, newrev=%s, force_send=%s" % + (refname, oldrev, newrev, options.force_send)) + run_as_update_hook(environment, mailer, refname, oldrev, newrev, options.force_send) + else: + run_as_post_receive_hook(environment, mailer) + except ConfigurationException: + sys.exit(sys.exc_info()[1]) + except SystemExit: + raise + except Exception: + t, e, tb = sys.exc_info() + import traceback + sys.stderr.write('\n') # Avoid mixing message with previous output + msg = ( + 'Exception \'' + t.__name__ + + '\' raised. Please report this as a bug to\n' + 'https://github.com/git-multimail/git-multimail/issues\n' + 'with the information below:\n\n' + 'git-multimail version ' + get_version() + '\n' + 'Python version ' + sys.version + '\n' + + traceback.format_exc()) + try: + environment.get_logger().error(msg) + except: + sys.stderr.write(msg) + sys.exit(1) + + +if __name__ == '__main__': + main(sys.argv[1:]) diff --git a/contrib/hooks/multimail/migrate-mailhook-config b/contrib/hooks/multimail/migrate-mailhook-config new file mode 100755 index 000000000000..241ba22fa3c8 --- /dev/null +++ b/contrib/hooks/multimail/migrate-mailhook-config @@ -0,0 +1,274 @@ +#! /usr/bin/env python + +"""Migrate a post-receive-email configuration to be usable with git_multimail.py. + +See README.migrate-from-post-receive-email for more information. + +""" + +import sys +import optparse + +from git_multimail import CommandError +from git_multimail import Config +from git_multimail import read_output + + +OLD_NAMES = [ + 'mailinglist', + 'announcelist', + 'envelopesender', + 'emailprefix', + 'showrev', + 'emailmaxlines', + 'diffopts', + 'scancommitforcc', + ] + +NEW_NAMES = [ + 'environment', + 'reponame', + 'mailinglist', + 'refchangelist', + 'commitlist', + 'announcelist', + 'announceshortlog', + 'envelopesender', + 'administrator', + 'emailprefix', + 'emailmaxlines', + 'diffopts', + 'emaildomain', + 'scancommitforcc', + ] + + +INFO = """\ + +SUCCESS! + +Your post-receive-email configuration has been converted to +git-multimail format. Please see README and +README.migrate-from-post-receive-email to learn about other +git-multimail configuration possibilities. + +For example, git-multimail has the following new options with no +equivalent in post-receive-email. You might want to read about them +to see if they would be useful in your situation: + +""" + + +def _check_old_config_exists(old): + """Check that at least one old configuration value is set.""" + + for name in OLD_NAMES: + if name in old: + return True + + return False + + +def _check_new_config_clear(new): + """Check that none of the new configuration names are set.""" + + retval = True + for name in NEW_NAMES: + if name in new: + if retval: + sys.stderr.write('INFO: The following configuration values already exist:\n\n') + sys.stderr.write(' "%s.%s"\n' % (new.section, name)) + retval = False + + return retval + + +def erase_values(config, names): + for name in names: + if name in config: + try: + sys.stderr.write('...unsetting "%s.%s"\n' % (config.section, name)) + config.unset_all(name) + except CommandError: + sys.stderr.write( + '\nWARNING: could not unset "%s.%s". ' + 'Perhaps it is not set at the --local level?\n\n' + % (config.section, name) + ) + + +def is_section_empty(section, local): + """Return True iff the specified configuration section is empty. + + Iff local is True, use the --local option when invoking 'git + config'.""" + + if local: + local_option = ['--local'] + else: + local_option = [] + + try: + read_output( + ['git', 'config'] + + local_option + + ['--get-regexp', '^%s\.' % (section,)] + ) + except CommandError: + t, e, traceback = sys.exc_info() + if e.retcode == 1: + # This means that no settings were found. + return True + else: + raise + else: + return False + + +def remove_section_if_empty(section): + """If the specified configuration section is empty, delete it.""" + + try: + empty = is_section_empty(section, local=True) + except CommandError: + # Older versions of git do not support the --local option, so + # if the first attempt fails, try without --local. + try: + empty = is_section_empty(section, local=False) + except CommandError: + sys.stderr.write( + '\nINFO: If configuration section "%s.*" is empty, you might want ' + 'to delete it.\n\n' + % (section,) + ) + return + + if empty: + sys.stderr.write('...removing section "%s.*"\n' % (section,)) + read_output(['git', 'config', '--remove-section', section]) + else: + sys.stderr.write( + '\nINFO: Configuration section "%s.*" still has contents. ' + 'It will not be deleted.\n\n' + % (section,) + ) + + +def migrate_config(strict=False, retain=False, overwrite=False): + old = Config('hooks') + new = Config('multimailhook') + if not _check_old_config_exists(old): + sys.exit( + 'Your repository has no post-receive-email configuration. ' + 'Nothing to do.' + ) + if not _check_new_config_clear(new): + if overwrite: + sys.stderr.write('\nWARNING: Erasing the above values...\n\n') + erase_values(new, NEW_NAMES) + else: + sys.exit( + '\nERROR: Refusing to overwrite existing values. Use the --overwrite\n' + 'option to continue anyway.' + ) + + name = 'showrev' + if name in old: + msg = 'git-multimail does not support "%s.%s"' % (old.section, name,) + if strict: + sys.exit( + 'ERROR: %s.\n' + 'Please unset that value then try again, or run without --strict.' + % (msg,) + ) + else: + sys.stderr.write('\nWARNING: %s (ignoring).\n\n' % (msg,)) + + for name in ['mailinglist', 'announcelist']: + if name in old: + sys.stderr.write( + '...copying "%s.%s" to "%s.%s"\n' % (old.section, name, new.section, name) + ) + old_recipients = old.get_all(name, default=None) + old_recipients = ', '.join(o.strip() for o in old_recipients) + new.set_recipients(name, old_recipients) + + if strict: + sys.stderr.write( + '...setting "%s.commitlist" to the empty string\n' % (new.section,) + ) + new.set_recipients('commitlist', '') + sys.stderr.write( + '...setting "%s.announceshortlog" to "true"\n' % (new.section,) + ) + new.set('announceshortlog', 'true') + + for name in ['envelopesender', 'emailmaxlines', 'diffopts', 'scancommitforcc']: + if name in old: + sys.stderr.write( + '...copying "%s.%s" to "%s.%s"\n' % (old.section, name, new.section, name) + ) + new.set(name, old.get(name)) + + name = 'emailprefix' + if name in old: + sys.stderr.write( + '...copying "%s.%s" to "%s.%s"\n' % (old.section, name, new.section, name) + ) + new.set(name, old.get(name)) + elif strict: + sys.stderr.write( + '...setting "%s.%s" to "[SCM]" to preserve old subject lines\n' + % (new.section, name) + ) + new.set(name, '[SCM]') + + if not retain: + erase_values(old, OLD_NAMES) + remove_section_if_empty(old.section) + + sys.stderr.write(INFO) + for name in NEW_NAMES: + if name not in OLD_NAMES: + sys.stderr.write(' "%s.%s"\n' % (new.section, name,)) + sys.stderr.write('\n') + + +def main(args): + parser = optparse.OptionParser( + description=__doc__, + usage='%prog [OPTIONS]', + ) + + parser.add_option( + '--strict', action='store_true', default=False, + help=( + 'Slavishly configure git-multimail as closely as possible to ' + 'the post-receive-email configuration. Default is to turn ' + 'on some new features that have no equivalent in post-receive-email.' + ), + ) + parser.add_option( + '--retain', action='store_true', default=False, + help=( + 'Retain the post-receive-email configuration values. ' + 'Default is to delete them after the new values are set.' + ), + ) + parser.add_option( + '--overwrite', action='store_true', default=False, + help=( + 'Overwrite any existing git-multimail configuration settings. ' + 'Default is to abort if such settings already exist.' + ), + ) + + (options, args) = parser.parse_args(args) + + if args: + parser.error('Unexpected arguments: %s' % (' '.join(args),)) + + migrate_config(strict=options.strict, retain=options.retain, overwrite=options.overwrite) + + +main(sys.argv[1:]) diff --git a/contrib/hooks/multimail/post-receive.example b/contrib/hooks/multimail/post-receive.example new file mode 100755 index 000000000000..b9bb11834e1f --- /dev/null +++ b/contrib/hooks/multimail/post-receive.example @@ -0,0 +1,101 @@ +#! /usr/bin/env python + +"""Example post-receive hook based on git-multimail. + +The simplest way to use git-multimail is to use the script +git_multimail.py directly as a post-receive hook, and to configure it +using Git's configuration files and command-line parameters. You can +also write your own Python wrapper for more advanced configurability, +using git_multimail.py as a Python module. + +This script is a simple example of such a post-receive hook. It is +intended to be customized before use; see the comments in the script +to help you get started. + +Using git-multimail as a Python module as done here provides more +flexibility. It has the following advantages: + +* The tool's behavior can be customized using arbitrary Python code, + without having to edit git_multimail.py. + +* Configuration settings can be read from other sources; for example, + user names and email addresses could be read from LDAP or from a + database. Or the settings can even be hardcoded in the importing + Python script, if this is preferred. + +This script is a very basic example of how to use git_multimail.py as +a module. The comments below explain some of the points at which the +script's behavior could be changed or customized. + +""" + +import sys + +# If necessary, add the path to the directory containing +# git_multimail.py to the Python path as follows. (This is not +# necessary if git_multimail.py is in the same directory as this +# script): + +#LIBDIR = 'path/to/directory/containing/module' +#sys.path.insert(0, LIBDIR) + +import git_multimail + +# It is possible to modify the output templates here; e.g.: + +#git_multimail.FOOTER_TEMPLATE = """\ +# +#-- \n\ +#This email was generated by the wonderful git-multimail tool. +#""" + + +# Specify which "git config" section contains the configuration for +# git-multimail: +config = git_multimail.Config('multimailhook') + +# Set some Git configuration variables. Equivalent to passing var=val +# to "git -c var=val" each time git is called, or to adding the +# configuration in .git/config (must come before instanciating the +# environment) : +#git_multimail.Config.add_config_parameters('multimailhook.commitEmailFormat=html') +#git_multimail.Config.add_config_parameters(('user.name=foo', 'user.email=foo@example.com')) + +# Select the type of environment: +try: + environment = git_multimail.GenericEnvironment(config=config) + #environment = git_multimail.GitoliteEnvironment(config=config) +except git_multimail.ConfigurationException: + sys.stderr.write('*** %s\n' % sys.exc_info()[1]) + sys.exit(1) + + +# Choose the method of sending emails based on the git config: +mailer = git_multimail.choose_mailer(config, environment) + +# Alternatively, you may hardcode the mailer using code like one of +# the following: + +# Use "/usr/sbin/sendmail -oi -t" to send emails. The envelopesender +# argument is optional: +#mailer = git_multimail.SendMailer( +# command=['/usr/sbin/sendmail', '-oi', '-t'], +# envelopesender='git-repo@example.com', +# ) + +# Use Python's smtplib to send emails. Both arguments are required. +#mailer = git_multimail.SMTPMailer( +# environment=environment, +# envelopesender='git-repo@example.com', +# # The smtpserver argument can also include a port number; e.g., +# # smtpserver='mail.example.com:25' +# smtpserver='mail.example.com', +# ) + +# OutputMailer is intended only for testing; it writes the emails to +# the specified file stream. +#mailer = git_multimail.OutputMailer(sys.stdout) + + +# Read changes from stdin and send notification emails: +git_multimail.run_as_post_receive_hook(environment, mailer) diff --git a/contrib/hooks/post-receive-email b/contrib/hooks/post-receive-email new file mode 100755 index 000000000000..8747b84334f3 --- /dev/null +++ b/contrib/hooks/post-receive-email @@ -0,0 +1,759 @@ +#!/bin/sh +# +# Copyright (c) 2007 Andy Parkins +# +# An example hook script to mail out commit update information. +# +# NOTE: This script is no longer under active development. There +# is another script, git-multimail, which is more capable and +# configurable and is largely backwards-compatible with this script; +# please see "contrib/hooks/multimail/". For instructions on how to +# migrate from post-receive-email to git-multimail, please see +# "README.migrate-from-post-receive-email" in that directory. +# +# This hook sends emails listing new revisions to the repository +# introduced by the change being reported. The rule is that (for +# branch updates) each commit will appear on one email and one email +# only. +# +# This hook is stored in the contrib/hooks directory. Your distribution +# will have put this somewhere standard. You should make this script +# executable then link to it in the repository you would like to use it in. +# For example, on debian the hook is stored in +# /usr/share/git-core/contrib/hooks/post-receive-email: +# +# cd /path/to/your/repository.git +# ln -sf /usr/share/git-core/contrib/hooks/post-receive-email hooks/post-receive +# +# This hook script assumes it is enabled on the central repository of a +# project, with all users pushing only to it and not between each other. It +# will still work if you don't operate in that style, but it would become +# possible for the email to be from someone other than the person doing the +# push. +# +# To help with debugging and use on pre-v1.5.1 git servers, this script will +# also obey the interface of hooks/update, taking its arguments on the +# command line. Unfortunately, hooks/update is called once for each ref. +# To avoid firing one email per ref, this script just prints its output to +# the screen when used in this mode. The output can then be redirected if +# wanted. +# +# Config +# ------ +# hooks.mailinglist +# This is the list that all pushes will go to; leave it blank to not send +# emails for every ref update. +# hooks.announcelist +# This is the list that all pushes of annotated tags will go to. Leave it +# blank to default to the mailinglist field. The announce emails lists +# the short log summary of the changes since the last annotated tag. +# hooks.envelopesender +# If set then the -f option is passed to sendmail to allow the envelope +# sender address to be set +# hooks.emailprefix +# All emails have their subjects prefixed with this prefix, or "[SCM]" +# if emailprefix is unset, to aid filtering +# hooks.showrev +# The shell command used to format each revision in the email, with +# "%s" replaced with the commit id. Defaults to "git rev-list -1 +# --pretty %s", displaying the commit id, author, date and log +# message. To list full patches separated by a blank line, you +# could set this to "git show -C %s; echo". +# To list a gitweb/cgit URL *and* a full patch for each change set, use this: +# "t=%s; printf 'http://.../?id=%%s' \$t; echo;echo; git show -C \$t; echo" +# Be careful if "..." contains things that will be expanded by shell "eval" +# or printf. +# hooks.emailmaxlines +# The maximum number of lines that should be included in the generated +# email body. If not specified, there is no limit. +# Lines beyond the limit are suppressed and counted, and a final +# line is added indicating the number of suppressed lines. +# hooks.diffopts +# Alternate options for the git diff-tree invocation that shows changes. +# Default is "--stat --summary --find-copies-harder". Add -p to those +# options to include a unified diff of changes in addition to the usual +# summary output. +# +# Notes +# ----- +# All emails include the headers "X-Git-Refname", "X-Git-Oldrev", +# "X-Git-Newrev", and "X-Git-Reftype" to enable fine tuned filtering and +# give information for debugging. +# + +# ---------------------------- Functions + +# +# Function to prepare for email generation. This decides what type +# of update this is and whether an email should even be generated. +# +prep_for_email() +{ + # --- Arguments + oldrev=$(git rev-parse $1) + newrev=$(git rev-parse $2) + refname="$3" + + # --- Interpret + # 0000->1234 (create) + # 1234->2345 (update) + # 2345->0000 (delete) + if expr "$oldrev" : '0*$' >/dev/null + then + change_type="create" + else + if expr "$newrev" : '0*$' >/dev/null + then + change_type="delete" + else + change_type="update" + fi + fi + + # --- Get the revision types + newrev_type=$(git cat-file -t $newrev 2> /dev/null) + oldrev_type=$(git cat-file -t "$oldrev" 2> /dev/null) + case "$change_type" in + create|update) + rev="$newrev" + rev_type="$newrev_type" + ;; + delete) + rev="$oldrev" + rev_type="$oldrev_type" + ;; + esac + + # The revision type tells us what type the commit is, combined with + # the location of the ref we can decide between + # - working branch + # - tracking branch + # - unannoted tag + # - annotated tag + case "$refname","$rev_type" in + refs/tags/*,commit) + # un-annotated tag + refname_type="tag" + short_refname=${refname##refs/tags/} + ;; + refs/tags/*,tag) + # annotated tag + refname_type="annotated tag" + short_refname=${refname##refs/tags/} + # change recipients + if [ -n "$announcerecipients" ]; then + recipients="$announcerecipients" + fi + ;; + refs/heads/*,commit) + # branch + refname_type="branch" + short_refname=${refname##refs/heads/} + ;; + refs/remotes/*,commit) + # tracking branch + refname_type="tracking branch" + short_refname=${refname##refs/remotes/} + echo >&2 "*** Push-update of tracking branch, $refname" + echo >&2 "*** - no email generated." + return 1 + ;; + *) + # Anything else (is there anything else?) + echo >&2 "*** Unknown type of update to $refname ($rev_type)" + echo >&2 "*** - no email generated" + return 1 + ;; + esac + + # Check if we've got anyone to send to + if [ -z "$recipients" ]; then + case "$refname_type" in + "annotated tag") + config_name="hooks.announcelist" + ;; + *) + config_name="hooks.mailinglist" + ;; + esac + echo >&2 "*** $config_name is not set so no email will be sent" + echo >&2 "*** for $refname update $oldrev->$newrev" + return 1 + fi + + return 0 +} + +# +# Top level email generation function. This calls the appropriate +# body-generation routine after outputting the common header. +# +# Note this function doesn't actually generate any email output, that is +# taken care of by the functions it calls: +# - generate_email_header +# - generate_create_XXXX_email +# - generate_update_XXXX_email +# - generate_delete_XXXX_email +# - generate_email_footer +# +# Note also that this function cannot 'exit' from the script; when this +# function is running (in hook script mode), the send_mail() function +# is already executing in another process, connected via a pipe, and +# if this function exits without, whatever has been generated to that +# point will be sent as an email... even if nothing has been generated. +# +generate_email() +{ + # Email parameters + # The email subject will contain the best description of the ref + # that we can build from the parameters + describe=$(git describe $rev 2>/dev/null) + if [ -z "$describe" ]; then + describe=$rev + fi + + generate_email_header + + # Call the correct body generation function + fn_name=general + case "$refname_type" in + "tracking branch"|branch) + fn_name=branch + ;; + "annotated tag") + fn_name=atag + ;; + esac + + if [ -z "$maxlines" ]; then + generate_${change_type}_${fn_name}_email + else + generate_${change_type}_${fn_name}_email | limit_lines $maxlines + fi + + generate_email_footer +} + +generate_email_header() +{ + # --- Email (all stdout will be the email) + # Generate header + cat <<-EOF + To: $recipients + Subject: ${emailprefix}$projectdesc $refname_type $short_refname ${change_type}d. $describe + MIME-Version: 1.0 + Content-Type: text/plain; charset=utf-8 + Content-Transfer-Encoding: 8bit + X-Git-Refname: $refname + X-Git-Reftype: $refname_type + X-Git-Oldrev: $oldrev + X-Git-Newrev: $newrev + Auto-Submitted: auto-generated + + This is an automated email from the git hooks/post-receive script. It was + generated because a ref change was pushed to the repository containing + the project "$projectdesc". + + The $refname_type, $short_refname has been ${change_type}d + EOF +} + +generate_email_footer() +{ + SPACE=" " + cat <<-EOF + + + hooks/post-receive + --${SPACE} + $projectdesc + EOF +} + +# --------------- Branches + +# +# Called for the creation of a branch +# +generate_create_branch_email() +{ + # This is a new branch and so oldrev is not valid + echo " at $newrev ($newrev_type)" + echo "" + + echo $LOGBEGIN + show_new_revisions + echo $LOGEND +} + +# +# Called for the change of a pre-existing branch +# +generate_update_branch_email() +{ + # Consider this: + # 1 --- 2 --- O --- X --- 3 --- 4 --- N + # + # O is $oldrev for $refname + # N is $newrev for $refname + # X is a revision pointed to by some other ref, for which we may + # assume that an email has already been generated. + # In this case we want to issue an email containing only revisions + # 3, 4, and N. Given (almost) by + # + # git rev-list N ^O --not --all + # + # The reason for the "almost", is that the "--not --all" will take + # precedence over the "N", and effectively will translate to + # + # git rev-list N ^O ^X ^N + # + # So, we need to build up the list more carefully. git rev-parse + # will generate a list of revs that may be fed into git rev-list. + # We can get it to make the "--not --all" part and then filter out + # the "^N" with: + # + # git rev-parse --not --all | grep -v N + # + # Then, using the --stdin switch to git rev-list we have effectively + # manufactured + # + # git rev-list N ^O ^X + # + # This leaves a problem when someone else updates the repository + # while this script is running. Their new value of the ref we're + # working on would be included in the "--not --all" output; and as + # our $newrev would be an ancestor of that commit, it would exclude + # all of our commits. What we really want is to exclude the current + # value of $refname from the --not list, rather than N itself. So: + # + # git rev-parse --not --all | grep -v $(git rev-parse $refname) + # + # Get's us to something pretty safe (apart from the small time + # between refname being read, and git rev-parse running - for that, + # I give up) + # + # + # Next problem, consider this: + # * --- B --- * --- O ($oldrev) + # \ + # * --- X --- * --- N ($newrev) + # + # That is to say, there is no guarantee that oldrev is a strict + # subset of newrev (it would have required a --force, but that's + # allowed). So, we can't simply say rev-list $oldrev..$newrev. + # Instead we find the common base of the two revs and list from + # there. + # + # As above, we need to take into account the presence of X; if + # another branch is already in the repository and points at some of + # the revisions that we are about to output - we don't want them. + # The solution is as before: git rev-parse output filtered. + # + # Finally, tags: 1 --- 2 --- O --- T --- 3 --- 4 --- N + # + # Tags pushed into the repository generate nice shortlog emails that + # summarise the commits between them and the previous tag. However, + # those emails don't include the full commit messages that we output + # for a branch update. Therefore we still want to output revisions + # that have been output on a tag email. + # + # Luckily, git rev-parse includes just the tool. Instead of using + # "--all" we use "--branches"; this has the added benefit that + # "remotes/" will be ignored as well. + + # List all of the revisions that were removed by this update, in a + # fast-forward update, this list will be empty, because rev-list O + # ^N is empty. For a non-fast-forward, O ^N is the list of removed + # revisions + fast_forward="" + rev="" + for rev in $(git rev-list $newrev..$oldrev) + do + revtype=$(git cat-file -t "$rev") + echo " discards $rev ($revtype)" + done + if [ -z "$rev" ]; then + fast_forward=1 + fi + + # List all the revisions from baserev to newrev in a kind of + # "table-of-contents"; note this list can include revisions that + # have already had notification emails and is present to show the + # full detail of the change from rolling back the old revision to + # the base revision and then forward to the new revision + for rev in $(git rev-list $oldrev..$newrev) + do + revtype=$(git cat-file -t "$rev") + echo " via $rev ($revtype)" + done + + if [ "$fast_forward" ]; then + echo " from $oldrev ($oldrev_type)" + else + # 1. Existing revisions were removed. In this case newrev + # is a subset of oldrev - this is the reverse of a + # fast-forward, a rewind + # 2. New revisions were added on top of an old revision, + # this is a rewind and addition. + + # (1) certainly happened, (2) possibly. When (2) hasn't + # happened, we set a flag to indicate that no log printout + # is required. + + echo "" + + # Find the common ancestor of the old and new revisions and + # compare it with newrev + baserev=$(git merge-base $oldrev $newrev) + rewind_only="" + if [ "$baserev" = "$newrev" ]; then + echo "This update discarded existing revisions and left the branch pointing at" + echo "a previous point in the repository history." + echo "" + echo " * -- * -- N ($newrev)" + echo " \\" + echo " O -- O -- O ($oldrev)" + echo "" + echo "The removed revisions are not necessarily gone - if another reference" + echo "still refers to them they will stay in the repository." + rewind_only=1 + else + echo "This update added new revisions after undoing existing revisions. That is" + echo "to say, the old revision is not a strict subset of the new revision. This" + echo "situation occurs when you --force push a change and generate a repository" + echo "containing something like this:" + echo "" + echo " * -- * -- B -- O -- O -- O ($oldrev)" + echo " \\" + echo " N -- N -- N ($newrev)" + echo "" + echo "When this happens we assume that you've already had alert emails for all" + echo "of the O revisions, and so we here report only the revisions in the N" + echo "branch from the common base, B." + fi + fi + + echo "" + if [ -z "$rewind_only" ]; then + echo "Those revisions listed above that are new to this repository have" + echo "not appeared on any other notification email; so we list those" + echo "revisions in full, below." + + echo "" + echo $LOGBEGIN + show_new_revisions + + # XXX: Need a way of detecting whether git rev-list actually + # outputted anything, so that we can issue a "no new + # revisions added by this update" message + + echo $LOGEND + else + echo "No new revisions were added by this update." + fi + + # The diffstat is shown from the old revision to the new revision. + # This is to show the truth of what happened in this change. + # There's no point showing the stat from the base to the new + # revision because the base is effectively a random revision at this + # point - the user will be interested in what this revision changed + # - including the undoing of previous revisions in the case of + # non-fast-forward updates. + echo "" + echo "Summary of changes:" + git diff-tree $diffopts $oldrev..$newrev +} + +# +# Called for the deletion of a branch +# +generate_delete_branch_email() +{ + echo " was $oldrev" + echo "" + echo $LOGBEGIN + git diff-tree -s --always --encoding=UTF-8 --pretty=oneline $oldrev + echo $LOGEND +} + +# --------------- Annotated tags + +# +# Called for the creation of an annotated tag +# +generate_create_atag_email() +{ + echo " at $newrev ($newrev_type)" + + generate_atag_email +} + +# +# Called for the update of an annotated tag (this is probably a rare event +# and may not even be allowed) +# +generate_update_atag_email() +{ + echo " to $newrev ($newrev_type)" + echo " from $oldrev (which is now obsolete)" + + generate_atag_email +} + +# +# Called when an annotated tag is created or changed +# +generate_atag_email() +{ + # Use git for-each-ref to pull out the individual fields from the + # tag + eval $(git for-each-ref --shell --format=' + tagobject=%(*objectname) + tagtype=%(*objecttype) + tagger=%(taggername) + tagged=%(taggerdate)' $refname + ) + + echo " tagging $tagobject ($tagtype)" + case "$tagtype" in + commit) + + # If the tagged object is a commit, then we assume this is a + # release, and so we calculate which tag this tag is + # replacing + prevtag=$(git describe --abbrev=0 $newrev^ 2>/dev/null) + + if [ -n "$prevtag" ]; then + echo " replaces $prevtag" + fi + ;; + *) + echo " length $(git cat-file -s $tagobject) bytes" + ;; + esac + echo " tagged by $tagger" + echo " on $tagged" + + echo "" + echo $LOGBEGIN + + # Show the content of the tag message; this might contain a change + # log or release notes so is worth displaying. + git cat-file tag $newrev | sed -e '1,/^$/d' + + echo "" + case "$tagtype" in + commit) + # Only commit tags make sense to have rev-list operations + # performed on them + if [ -n "$prevtag" ]; then + # Show changes since the previous release + git shortlog "$prevtag..$newrev" + else + # No previous tag, show all the changes since time + # began + git shortlog $newrev + fi + ;; + *) + # XXX: Is there anything useful we can do for non-commit + # objects? + ;; + esac + + echo $LOGEND +} + +# +# Called for the deletion of an annotated tag +# +generate_delete_atag_email() +{ + echo " was $oldrev" + echo "" + echo $LOGBEGIN + git diff-tree -s --always --encoding=UTF-8 --pretty=oneline $oldrev + echo $LOGEND +} + +# --------------- General references + +# +# Called when any other type of reference is created (most likely a +# non-annotated tag) +# +generate_create_general_email() +{ + echo " at $newrev ($newrev_type)" + + generate_general_email +} + +# +# Called when any other type of reference is updated (most likely a +# non-annotated tag) +# +generate_update_general_email() +{ + echo " to $newrev ($newrev_type)" + echo " from $oldrev" + + generate_general_email +} + +# +# Called for creation or update of any other type of reference +# +generate_general_email() +{ + # Unannotated tags are more about marking a point than releasing a + # version; therefore we don't do the shortlog summary that we do for + # annotated tags above - we simply show that the point has been + # marked, and print the log message for the marked point for + # reference purposes + # + # Note this section also catches any other reference type (although + # there aren't any) and deals with them in the same way. + + echo "" + if [ "$newrev_type" = "commit" ]; then + echo $LOGBEGIN + git diff-tree -s --always --encoding=UTF-8 --pretty=medium $newrev + echo $LOGEND + else + # What can we do here? The tag marks an object that is not + # a commit, so there is no log for us to display. It's + # probably not wise to output git cat-file as it could be a + # binary blob. We'll just say how big it is + echo "$newrev is a $newrev_type, and is $(git cat-file -s $newrev) bytes long." + fi +} + +# +# Called for the deletion of any other type of reference +# +generate_delete_general_email() +{ + echo " was $oldrev" + echo "" + echo $LOGBEGIN + git diff-tree -s --always --encoding=UTF-8 --pretty=oneline $oldrev + echo $LOGEND +} + + +# --------------- Miscellaneous utilities + +# +# Show new revisions as the user would like to see them in the email. +# +show_new_revisions() +{ + # This shows all log entries that are not already covered by + # another ref - i.e. commits that are now accessible from this + # ref that were previously not accessible + # (see generate_update_branch_email for the explanation of this + # command) + + # Revision range passed to rev-list differs for new vs. updated + # branches. + if [ "$change_type" = create ] + then + # Show all revisions exclusive to this (new) branch. + revspec=$newrev + else + # Branch update; show revisions not part of $oldrev. + revspec=$oldrev..$newrev + fi + + other_branches=$(git for-each-ref --format='%(refname)' refs/heads/ | + grep -F -v $refname) + git rev-parse --not $other_branches | + if [ -z "$custom_showrev" ] + then + git rev-list --pretty --stdin $revspec + else + git rev-list --stdin $revspec | + while read onerev + do + eval $(printf "$custom_showrev" $onerev) + done + fi +} + + +limit_lines() +{ + lines=0 + skipped=0 + while IFS="" read -r line; do + lines=$((lines + 1)) + if [ $lines -gt $1 ]; then + skipped=$((skipped + 1)) + else + printf "%s\n" "$line" + fi + done + if [ $skipped -ne 0 ]; then + echo "... $skipped lines suppressed ..." + fi +} + + +send_mail() +{ + if [ -n "$envelopesender" ]; then + /usr/sbin/sendmail -t -f "$envelopesender" + else + /usr/sbin/sendmail -t + fi +} + +# ---------------------------- main() + +# --- Constants +LOGBEGIN="- Log -----------------------------------------------------------------" +LOGEND="-----------------------------------------------------------------------" + +# --- Config +# Set GIT_DIR either from the working directory, or from the environment +# variable. +GIT_DIR=$(git rev-parse --git-dir 2>/dev/null) +if [ -z "$GIT_DIR" ]; then + echo >&2 "fatal: post-receive: GIT_DIR not set" + exit 1 +fi + +projectdesc=$(sed -ne '1p' "$GIT_DIR/description" 2>/dev/null) +# Check if the description is unchanged from it's default, and shorten it to +# a more manageable length if it is +if expr "$projectdesc" : "Unnamed repository.*$" >/dev/null +then + projectdesc="UNNAMED PROJECT" +fi + +recipients=$(git config hooks.mailinglist) +announcerecipients=$(git config hooks.announcelist) +envelopesender=$(git config hooks.envelopesender) +emailprefix=$(git config hooks.emailprefix || echo '[SCM] ') +custom_showrev=$(git config hooks.showrev) +maxlines=$(git config hooks.emailmaxlines) +diffopts=$(git config hooks.diffopts) +: ${diffopts:="--stat --summary --find-copies-harder"} + +# --- Main loop +# Allow dual mode: run from the command line just like the update hook, or +# if no arguments are given then run as a hook script +if [ -n "$1" -a -n "$2" -a -n "$3" ]; then + # Output to the terminal in command line mode - if someone wanted to + # resend an email; they could redirect the output to sendmail + # themselves + prep_for_email $2 $3 $1 && PAGER= generate_email +else + while read oldrev newrev refname + do + prep_for_email $oldrev $newrev $refname || continue + generate_email $maxlines | send_mail + done +fi diff --git a/contrib/hooks/pre-auto-gc-battery b/contrib/hooks/pre-auto-gc-battery new file mode 100755 index 000000000000..7ba78c4dff68 --- /dev/null +++ b/contrib/hooks/pre-auto-gc-battery @@ -0,0 +1,42 @@ +#!/bin/sh +# +# An example hook script to verify if you are on battery, in case you +# are running Linux or OS X. Called by git-gc --auto with no arguments. +# The hook should exit with non-zero status after issuing an appropriate +# message if it wants to stop the auto repacking. +# +# This hook is stored in the contrib/hooks directory. Your distribution +# may have put this somewhere else. If you want to use this hook, you +# should make this script executable then link to it in the repository +# you would like to use it in. +# +# For example, if the hook is stored in +# /usr/share/git-core/contrib/hooks/pre-auto-gc-battery: +# +# cd /path/to/your/repository.git +# ln -sf /usr/share/git-core/contrib/hooks/pre-auto-gc-battery \ +# hooks/pre-auto-gc + +if test -x /sbin/on_ac_power && (/sbin/on_ac_power;test $? -ne 1) +then + exit 0 +elif test "$(cat /sys/class/power_supply/AC/online 2>/dev/null)" = 1 +then + exit 0 +elif grep -q 'on-line' /proc/acpi/ac_adapter/AC/state 2>/dev/null +then + exit 0 +elif grep -q '0x01$' /proc/apm 2>/dev/null +then + exit 0 +elif grep -q "AC Power \+: 1" /proc/pmu/info 2>/dev/null +then + exit 0 +elif test -x /usr/bin/pmset && /usr/bin/pmset -g batt | + grep -q "drawing from 'AC Power'" +then + exit 0 +fi + +echo "Auto packing deferred; not on AC" +exit 1 diff --git a/contrib/hooks/setgitperms.perl b/contrib/hooks/setgitperms.perl new file mode 100755 index 000000000000..2770a1b1d205 --- /dev/null +++ b/contrib/hooks/setgitperms.perl @@ -0,0 +1,214 @@ +#!/usr/bin/perl +# +# Copyright (c) 2006 Josh England +# +# This script can be used to save/restore full permissions and ownership data +# within a git working tree. +# +# To save permissions/ownership data, place this script in your .git/hooks +# directory and enable a `pre-commit` hook with the following lines: +# #!/bin/sh +# SUBDIRECTORY_OK=1 . git-sh-setup +# $GIT_DIR/hooks/setgitperms.perl -r +# +# To restore permissions/ownership data, place this script in your .git/hooks +# directory and enable a `post-merge` and `post-checkout` hook with the +# following lines: +# #!/bin/sh +# SUBDIRECTORY_OK=1 . git-sh-setup +# $GIT_DIR/hooks/setgitperms.perl -w +# +use strict; +use Getopt::Long; +use File::Find; +use File::Basename; + +my $usage = +"usage: setgitperms.perl [OPTION]... <--read|--write> +This program uses a file `.gitmeta` to store/restore permissions and uid/gid +info for all files/dirs tracked by git in the repository. + +---------------------------------Read Mode------------------------------------- +-r, --read Reads perms/etc from working dir into a .gitmeta file +-s, --stdout Output to stdout instead of .gitmeta +-d, --diff Show unified diff of perms file (XOR with --stdout) + +---------------------------------Write Mode------------------------------------ +-w, --write Modify perms/etc in working dir to match the .gitmeta file +-v, --verbose Be verbose + +\n"; + +my ($stdout, $showdiff, $verbose, $read_mode, $write_mode); + +if ((@ARGV < 0) || !GetOptions( + "stdout", \$stdout, + "diff", \$showdiff, + "read", \$read_mode, + "write", \$write_mode, + "verbose", \$verbose, + )) { die $usage; } +die $usage unless ($read_mode xor $write_mode); + +my $topdir = `git rev-parse --show-cdup` or die "\n"; chomp $topdir; +my $gitdir = $topdir . '.git'; +my $gitmeta = $topdir . '.gitmeta'; + +if ($write_mode) { + # Update the working dir permissions/ownership based on data from .gitmeta + open (IN, "<$gitmeta") or die "Could not open $gitmeta for reading: $!\n"; + while (defined ($_ = <IN>)) { + chomp; + if (/^(.*) mode=(\S+)\s+uid=(\d+)\s+gid=(\d+)/) { + # Compare recorded perms to actual perms in the working dir + my ($path, $mode, $uid, $gid) = ($1, $2, $3, $4); + my $fullpath = $topdir . $path; + my (undef,undef,$wmode,undef,$wuid,$wgid) = lstat($fullpath); + $wmode = sprintf "%04o", $wmode & 07777; + if ($mode ne $wmode) { + $verbose && print "Updating permissions on $path: old=$wmode, new=$mode\n"; + chmod oct($mode), $fullpath; + } + if ($uid != $wuid || $gid != $wgid) { + if ($verbose) { + # Print out user/group names instead of uid/gid + my $pwname = getpwuid($uid); + my $grpname = getgrgid($gid); + my $wpwname = getpwuid($wuid); + my $wgrpname = getgrgid($wgid); + $pwname = $uid if !defined $pwname; + $grpname = $gid if !defined $grpname; + $wpwname = $wuid if !defined $wpwname; + $wgrpname = $wgid if !defined $wgrpname; + + print "Updating uid/gid on $path: old=$wpwname/$wgrpname, new=$pwname/$grpname\n"; + } + chown $uid, $gid, $fullpath; + } + } + else { + warn "Invalid input format in $gitmeta:\n\t$_\n"; + } + } + close IN; +} +elsif ($read_mode) { + # Handle merge conflicts in the .gitperms file + if (-e "$gitdir/MERGE_MSG") { + if (`grep ====== $gitmeta`) { + # Conflict not resolved -- abort the commit + print "PERMISSIONS/OWNERSHIP CONFLICT\n"; + print " Resolve the conflict in the $gitmeta file and then run\n"; + print " `.git/hooks/setgitperms.perl --write` to reconcile.\n"; + exit 1; + } + elsif (`grep $gitmeta $gitdir/MERGE_MSG`) { + # A conflict in .gitmeta has been manually resolved. Verify that + # the working dir perms matches the current .gitmeta perms for + # each file/dir that conflicted. + # This is here because a `setgitperms.perl --write` was not + # performed due to a merge conflict, so permissions/ownership + # may not be consistent with the manually merged .gitmeta file. + my @conflict_diff = `git show \$(cat $gitdir/MERGE_HEAD)`; + my @conflict_files; + my $metadiff = 0; + + # Build a list of files that conflicted from the .gitmeta diff + foreach my $line (@conflict_diff) { + if ($line =~ m|^diff --git a/$gitmeta b/$gitmeta|) { + $metadiff = 1; + } + elsif ($line =~ /^diff --git/) { + $metadiff = 0; + } + elsif ($metadiff && $line =~ /^\+(.*) mode=/) { + push @conflict_files, $1; + } + } + + # Verify that each conflict file now has permissions consistent + # with the .gitmeta file + foreach my $file (@conflict_files) { + my $absfile = $topdir . $file; + my $gm_entry = `grep "^$file mode=" $gitmeta`; + if ($gm_entry =~ /mode=(\d+) uid=(\d+) gid=(\d+)/) { + my ($gm_mode, $gm_uid, $gm_gid) = ($1, $2, $3); + my (undef,undef,$mode,undef,$uid,$gid) = lstat("$absfile"); + $mode = sprintf("%04o", $mode & 07777); + if (($gm_mode ne $mode) || ($gm_uid != $uid) + || ($gm_gid != $gid)) { + print "PERMISSIONS/OWNERSHIP CONFLICT\n"; + print " Mismatch found for file: $file\n"; + print " Run `.git/hooks/setgitperms.perl --write` to reconcile.\n"; + exit 1; + } + } + else { + print "Warning! Permissions/ownership no longer being tracked for file: $file\n"; + } + } + } + } + + # No merge conflicts -- write out perms/ownership data to .gitmeta file + unless ($stdout) { + open (OUT, ">$gitmeta.tmp") or die "Could not open $gitmeta.tmp for writing: $!\n"; + } + + my @files = `git ls-files`; + my %dirs; + + foreach my $path (@files) { + chomp $path; + # We have to manually add stats for parent directories + my $parent = dirname($path); + while (!exists $dirs{$parent}) { + $dirs{$parent} = 1; + next if $parent eq '.'; + printstats($parent); + $parent = dirname($parent); + } + # Now the git-tracked file + printstats($path); + } + + # diff the temporary metadata file to see if anything has changed + # If no metadata has changed, don't overwrite the real file + # This is just so `git commit -a` doesn't try to commit a bogus update + unless ($stdout) { + if (! -e $gitmeta) { + rename "$gitmeta.tmp", $gitmeta; + } + else { + my $diff = `diff -U 0 $gitmeta $gitmeta.tmp`; + if ($diff ne '') { + rename "$gitmeta.tmp", $gitmeta; + } + else { + unlink "$gitmeta.tmp"; + } + if ($showdiff) { + print $diff; + } + } + close OUT; + } + # Make sure the .gitmeta file is tracked + system("git add $gitmeta"); +} + + +sub printstats { + my $path = $_[0]; + $path =~ s/@/\@/g; + my (undef,undef,$mode,undef,$uid,$gid) = lstat($path); + $path =~ s/%/\%/g; + if ($stdout) { + print $path; + printf " mode=%04o uid=$uid gid=$gid\n", $mode & 07777; + } + else { + print OUT $path; + printf OUT " mode=%04o uid=$uid gid=$gid\n", $mode & 07777; + } +} diff --git a/contrib/hooks/update-paranoid b/contrib/hooks/update-paranoid new file mode 100755 index 000000000000..d18b317b2f01 --- /dev/null +++ b/contrib/hooks/update-paranoid @@ -0,0 +1,421 @@ +#!/usr/bin/perl + +use strict; +use File::Spec; + +$ENV{PATH} = '/opt/git/bin'; +my $acl_git = '/vcs/acls.git'; +my $acl_branch = 'refs/heads/master'; +my $debug = 0; + +=doc +Invoked as: update refname old-sha1 new-sha1 + +This script is run by git-receive-pack once for each ref that the +client is trying to modify. If we exit with a non-zero exit value +then the update for that particular ref is denied, but updates for +other refs in the same run of receive-pack may still be allowed. + +We are run after the objects have been uploaded, but before the +ref is actually modified. We take advantage of that fact when we +look for "new" commits and tags (the new objects won't show up in +`rev-list --all`). + +This script loads and parses the content of the config file +"users/$this_user.acl" from the $acl_branch commit of $acl_git ODB. +The acl file is a git-config style file, but uses a slightly more +restricted syntax as the Perl parser contained within this script +is not nearly as permissive as git-config. + +Example: + + [user] + committer = John Doe <john.doe@example.com> + committer = John R. Doe <john.doe@example.com> + + [repository "acls"] + allow = heads/master + allow = CDUR for heads/jd/ + allow = C for ^tags/v\\d+$ + +For all new commit or tag objects the committer (or tagger) line +within the object must exactly match one of the user.committer +values listed in the acl file ("HEAD:users/$this_user.acl"). + +For a branch to be modified an allow line within the matching +repository section must be matched for both the refname and the +opcode. + +Repository sections are matched on the basename of the repository +(after removing the .git suffix). + +The opcode abbrevations are: + + C: create new ref + D: delete existing ref + U: fast-forward existing ref (no commit loss) + R: rewind/rebase existing ref (commit loss) + +if no opcodes are listed before the "for" keyword then "U" (for +fast-forward update only) is assumed as this is the most common +usage. + +Refnames are matched by always assuming a prefix of "refs/". +This hook forbids pushing or deleting anything not under "refs/". + +Refnames that start with ^ are Perl regular expressions, and the ^ +is kept as part of the regexp. \\ is needed to get just one \, so +\\d expands to \d in Perl. The 3rd allow line above is an example. + +Refnames that don't start with ^ but that end with / are prefix +matches (2nd allow line above); all other refnames are strict +equality matches (1st allow line). + +Anything pushed to "heads/" (ok, really "refs/heads/") must be +a commit. Tags are not permitted here. + +Anything pushed to "tags/" (err, really "refs/tags/") must be an +annotated tag. Commits, blobs, trees, etc. are not permitted here. +Annotated tag signatures aren't checked, nor are they required. + +The special subrepository of 'info/new-commit-check' can +be created and used to allow users to push new commits and +tags from another local repository to this one, even if they +aren't the committer/tagger of those objects. In a nut shell +the info/new-commit-check directory is a Git repository whose +objects/info/alternates file lists this repository and all other +possible sources, and whose refs subdirectory contains symlinks +to this repository's refs subdirectory, and to all other possible +sources refs subdirectories. Yes, this means that you cannot +use packed-refs in those repositories as they won't be resolved +correctly. + +=cut + +my $git_dir = $ENV{GIT_DIR}; +my $new_commit_check = "$git_dir/info/new-commit-check"; +my $ref = $ARGV[0]; +my $old = $ARGV[1]; +my $new = $ARGV[2]; +my $new_type; +my ($this_user) = getpwuid $<; # REAL_USER_ID +my $repository_name; +my %user_committer; +my @allow_rules; +my @path_rules; +my %diff_cache; + +sub deny ($) { + print STDERR "-Deny- $_[0]\n" if $debug; + print STDERR "\ndenied: $_[0]\n\n"; + exit 1; +} + +sub grant ($) { + print STDERR "-Grant- $_[0]\n" if $debug; + exit 0; +} + +sub info ($) { + print STDERR "-Info- $_[0]\n" if $debug; +} + +sub git_value (@) { + open(T,'-|','git',@_); local $_ = <T>; chop; close T; $_; +} + +sub match_string ($$) { + my ($acl_n, $ref) = @_; + ($acl_n eq $ref) + || ($acl_n =~ m,/$, && substr($ref,0,length $acl_n) eq $acl_n) + || ($acl_n =~ m,^\^, && $ref =~ m:$acl_n:); +} + +sub parse_config ($$$$) { + my $data = shift; + local $ENV{GIT_DIR} = shift; + my $br = shift; + my $fn = shift; + return unless git_value('rev-list','--max-count=1',$br,'--',$fn); + info "Loading $br:$fn"; + open(I,'-|','git','cat-file','blob',"$br:$fn"); + my $section = ''; + while (<I>) { + chomp; + if (/^\s*$/ || /^\s*#/) { + } elsif (/^\[([a-z]+)\]$/i) { + $section = lc $1; + } elsif (/^\[([a-z]+)\s+"(.*)"\]$/i) { + $section = join('.',lc $1,$2); + } elsif (/^\s*([a-z][a-z0-9]+)\s*=\s*(.*?)\s*$/i) { + push @{$data->{join('.',$section,lc $1)}}, $2; + } else { + deny "bad config file line $. in $br:$fn"; + } + } + close I; +} + +sub all_new_committers () { + local $ENV{GIT_DIR} = $git_dir; + $ENV{GIT_DIR} = $new_commit_check if -d $new_commit_check; + + info "Getting committers of new commits."; + my %used; + open(T,'-|','git','rev-list','--pretty=raw',$new,'--not','--all'); + while (<T>) { + next unless s/^committer //; + chop; + s/>.*$/>/; + info "Found $_." unless $used{$_}++; + } + close T; + info "No new commits." unless %used; + keys %used; +} + +sub all_new_taggers () { + my %exists; + open(T,'-|','git','for-each-ref','--format=%(objectname)','refs/tags'); + while (<T>) { + chop; + $exists{$_} = 1; + } + close T; + + info "Getting taggers of new tags."; + my %used; + my $obj = $new; + my $obj_type = $new_type; + while ($obj_type eq 'tag') { + last if $exists{$obj}; + $obj_type = ''; + open(T,'-|','git','cat-file','tag',$obj); + while (<T>) { + chop; + if (/^object ([a-z0-9]{40})$/) { + $obj = $1; + } elsif (/^type (.+)$/) { + $obj_type = $1; + } elsif (s/^tagger //) { + s/>.*$/>/; + info "Found $_." unless $used{$_}++; + last; + } + } + close T; + } + info "No new tags." unless %used; + keys %used; +} + +sub check_committers (@) { + my @bad; + foreach (@_) { push @bad, $_ unless $user_committer{$_}; } + if (@bad) { + print STDERR "\n"; + print STDERR "You are not $_.\n" foreach (sort @bad); + deny "You cannot push changes not committed by you."; + } +} + +sub load_diff ($) { + my $base = shift; + my $d = $diff_cache{$base}; + unless ($d) { + local $/ = "\0"; + my %this_diff; + if ($base =~ /^0{40}$/) { + # Don't load the diff at all; we are making the + # branch and have no base to compare to in this + # case. A file level ACL makes no sense in this + # context. Having an empty diff will allow the + # branch creation. + # + } else { + open(T,'-|','git','diff-tree', + '-r','--name-status','-z', + $base,$new) or return undef; + while (<T>) { + my $op = $_; + chop $op; + + my $path = <T>; + chop $path; + + $this_diff{$path} = $op; + } + close T or return undef; + } + $d = \%this_diff; + $diff_cache{$base} = $d; + } + return $d; +} + +deny "No GIT_DIR inherited from caller" unless $git_dir; +deny "Need a ref name" unless $ref; +deny "Refusing funny ref $ref" unless $ref =~ s,^refs/,,; +deny "Bad old value $old" unless $old =~ /^[a-z0-9]{40}$/; +deny "Bad new value $new" unless $new =~ /^[a-z0-9]{40}$/; +deny "Cannot determine who you are." unless $this_user; +grant "No change requested." if $old eq $new; + +$repository_name = File::Spec->rel2abs($git_dir); +$repository_name =~ m,/([^/]+)(?:\.git|/\.git)$,; +$repository_name = $1; +info "Updating in '$repository_name'."; + +my $op; +if ($old =~ /^0{40}$/) { $op = 'C'; } +elsif ($new =~ /^0{40}$/) { $op = 'D'; } +else { $op = 'R'; } + +# This is really an update (fast-forward) if the +# merge base of $old and $new is $old. +# +$op = 'U' if ($op eq 'R' + && $ref =~ m,^heads/, + && $old eq git_value('merge-base',$old,$new)); + +# Load the user's ACL file. Expand groups (user.memberof) one level. +{ + my %data = ('user.committer' => []); + parse_config(\%data,$acl_git,$acl_branch,"external/$repository_name.acl"); + + %data = ( + 'user.committer' => $data{'user.committer'}, + 'user.memberof' => [], + ); + parse_config(\%data,$acl_git,$acl_branch,"users/$this_user.acl"); + + %user_committer = map {$_ => $_} @{$data{'user.committer'}}; + my $rule_key = "repository.$repository_name.allow"; + my $rules = $data{$rule_key} || []; + + foreach my $group (@{$data{'user.memberof'}}) { + my %g; + parse_config(\%g,$acl_git,$acl_branch,"groups/$group.acl"); + my $group_rules = $g{$rule_key}; + push @$rules, @$group_rules if $group_rules; + } + +RULE: + foreach (@$rules) { + while (/\${user\.([a-z][a-zA-Z0-9]+)}/) { + my $k = lc $1; + my $v = $data{"user.$k"}; + next RULE unless defined $v; + next RULE if @$v != 1; + next RULE unless defined $v->[0]; + s/\${user\.$k}/$v->[0]/g; + } + + if (/^([AMD ]+)\s+of\s+([^\s]+)\s+for\s+([^\s]+)\s+diff\s+([^\s]+)$/) { + my ($ops, $pth, $ref, $bst) = ($1, $2, $3, $4); + $ops =~ s/ //g; + $pth =~ s/\\\\/\\/g; + $ref =~ s/\\\\/\\/g; + push @path_rules, [$ops, $pth, $ref, $bst]; + } elsif (/^([AMD ]+)\s+of\s+([^\s]+)\s+for\s+([^\s]+)$/) { + my ($ops, $pth, $ref) = ($1, $2, $3); + $ops =~ s/ //g; + $pth =~ s/\\\\/\\/g; + $ref =~ s/\\\\/\\/g; + push @path_rules, [$ops, $pth, $ref, $old]; + } elsif (/^([CDRU ]+)\s+for\s+([^\s]+)$/) { + my $ops = $1; + my $ref = $2; + $ops =~ s/ //g; + $ref =~ s/\\\\/\\/g; + push @allow_rules, [$ops, $ref]; + } elsif (/^for\s+([^\s]+)$/) { + # Mentioned, but nothing granted? + } elsif (/^[^\s]+$/) { + s/\\\\/\\/g; + push @allow_rules, ['U', $_]; + } + } +} + +if ($op ne 'D') { + $new_type = git_value('cat-file','-t',$new); + + if ($ref =~ m,^heads/,) { + deny "$ref must be a commit." unless $new_type eq 'commit'; + } elsif ($ref =~ m,^tags/,) { + deny "$ref must be an annotated tag." unless $new_type eq 'tag'; + } + + check_committers (all_new_committers); + check_committers (all_new_taggers) if $new_type eq 'tag'; +} + +info "$this_user wants $op for $ref"; +foreach my $acl_entry (@allow_rules) { + my ($acl_ops, $acl_n) = @$acl_entry; + next unless $acl_ops =~ /^[CDRU]+$/; # Uhh.... shouldn't happen. + next unless $acl_n; + next unless $op =~ /^[$acl_ops]$/; + next unless match_string $acl_n, $ref; + + # Don't test path rules on branch deletes. + # + grant "Allowed by: $acl_ops for $acl_n" if $op eq 'D'; + + # Aggregate matching path rules; allow if there aren't + # any matching this ref. + # + my %pr; + foreach my $p_entry (@path_rules) { + my ($p_ops, $p_n, $p_ref, $p_bst) = @$p_entry; + next unless $p_ref; + push @{$pr{$p_bst}}, $p_entry if match_string $p_ref, $ref; + } + grant "Allowed by: $acl_ops for $acl_n" unless %pr; + + # Allow only if all changes against a single base are + # allowed by file path rules. + # + my @bad; + foreach my $p_bst (keys %pr) { + my $diff_ref = load_diff $p_bst; + deny "Cannot difference trees." unless ref $diff_ref; + + my %fd = %$diff_ref; + foreach my $p_entry (@{$pr{$p_bst}}) { + my ($p_ops, $p_n, $p_ref, $p_bst) = @$p_entry; + next unless $p_ops =~ /^[AMD]+$/; + next unless $p_n; + + foreach my $f_n (keys %fd) { + my $f_op = $fd{$f_n}; + next unless $f_op; + next unless $f_op =~ /^[$p_ops]$/; + delete $fd{$f_n} if match_string $p_n, $f_n; + } + last unless %fd; + } + + if (%fd) { + push @bad, [$p_bst, \%fd]; + } else { + # All changes relative to $p_bst were allowed. + # + grant "Allowed by: $acl_ops for $acl_n diff $p_bst"; + } + } + + foreach my $bad_ref (@bad) { + my ($p_bst, $fd) = @$bad_ref; + print STDERR "\n"; + print STDERR "Not allowed to make the following changes:\n"; + print STDERR "(base: $p_bst)\n"; + foreach my $f_n (sort keys %$fd) { + print STDERR " $fd->{$f_n} $f_n\n"; + } + } + deny "You are not permitted to $op $ref"; +} +close A; +deny "You are not permitted to $op $ref"; diff --git a/contrib/long-running-filter/example.pl b/contrib/long-running-filter/example.pl new file mode 100755 index 000000000000..a677569ddd95 --- /dev/null +++ b/contrib/long-running-filter/example.pl @@ -0,0 +1,132 @@ +#!/usr/bin/perl +# +# Example implementation for the Git filter protocol version 2 +# See Documentation/gitattributes.txt, section "Filter Protocol" +# +# Please note, this pass-thru filter is a minimal skeleton. No proper +# error handling was implemented. +# + +use strict; +use warnings; + +my $MAX_PACKET_CONTENT_SIZE = 65516; + +sub packet_bin_read { + my $buffer; + my $bytes_read = read STDIN, $buffer, 4; + if ( $bytes_read == 0 ) { + + # EOF - Git stopped talking to us! + exit(); + } + elsif ( $bytes_read != 4 ) { + die "invalid packet: '$buffer'"; + } + my $pkt_size = hex($buffer); + if ( $pkt_size == 0 ) { + return ( 1, "" ); + } + elsif ( $pkt_size > 4 ) { + my $content_size = $pkt_size - 4; + $bytes_read = read STDIN, $buffer, $content_size; + if ( $bytes_read != $content_size ) { + die "invalid packet ($content_size bytes expected; $bytes_read bytes read)"; + } + return ( 0, $buffer ); + } + else { + die "invalid packet size: $pkt_size"; + } +} + +sub packet_txt_read { + my ( $res, $buf ) = packet_bin_read(); + unless ( $buf =~ s/\n$// ) { + die "A non-binary line MUST be terminated by an LF."; + } + return ( $res, $buf ); +} + +sub packet_bin_write { + my $buf = shift; + print STDOUT sprintf( "%04x", length($buf) + 4 ); + print STDOUT $buf; + STDOUT->flush(); +} + +sub packet_txt_write { + packet_bin_write( $_[0] . "\n" ); +} + +sub packet_flush { + print STDOUT sprintf( "%04x", 0 ); + STDOUT->flush(); +} + +( packet_txt_read() eq ( 0, "git-filter-client" ) ) || die "bad initialize"; +( packet_txt_read() eq ( 0, "version=2" ) ) || die "bad version"; +( packet_bin_read() eq ( 1, "" ) ) || die "bad version end"; + +packet_txt_write("git-filter-server"); +packet_txt_write("version=2"); +packet_flush(); + +( packet_txt_read() eq ( 0, "capability=clean" ) ) || die "bad capability"; +( packet_txt_read() eq ( 0, "capability=smudge" ) ) || die "bad capability"; +( packet_bin_read() eq ( 1, "" ) ) || die "bad capability end"; + +packet_txt_write("capability=clean"); +packet_txt_write("capability=smudge"); +packet_flush(); + +while (1) { + my ($command) = packet_txt_read() =~ /^command=(.+)$/; + my ($pathname) = packet_txt_read() =~ /^pathname=(.+)$/; + + if ( $pathname eq "" ) { + die "bad pathname '$pathname'"; + } + + packet_bin_read(); + + my $input = ""; + { + binmode(STDIN); + my $buffer; + my $done = 0; + while ( !$done ) { + ( $done, $buffer ) = packet_bin_read(); + $input .= $buffer; + } + } + + my $output; + if ( $command eq "clean" ) { + ### Perform clean here ### + $output = $input; + } + elsif ( $command eq "smudge" ) { + ### Perform smudge here ### + $output = $input; + } + else { + die "bad command '$command'"; + } + + packet_txt_write("status=success"); + packet_flush(); + while ( length($output) > 0 ) { + my $packet = substr( $output, 0, $MAX_PACKET_CONTENT_SIZE ); + packet_bin_write($packet); + if ( length($output) > $MAX_PACKET_CONTENT_SIZE ) { + $output = substr( $output, $MAX_PACKET_CONTENT_SIZE ); + } + else { + $output = ""; + } + } + packet_flush(); # flush content! + packet_flush(); # empty list, keep "status=success" unchanged! + +} diff --git a/contrib/mw-to-git/.gitignore b/contrib/mw-to-git/.gitignore new file mode 100644 index 000000000000..ae545b013dc8 --- /dev/null +++ b/contrib/mw-to-git/.gitignore @@ -0,0 +1,2 @@ +git-remote-mediawiki +git-mw diff --git a/contrib/mw-to-git/.perlcriticrc b/contrib/mw-to-git/.perlcriticrc new file mode 100644 index 000000000000..158958d36357 --- /dev/null +++ b/contrib/mw-to-git/.perlcriticrc @@ -0,0 +1,28 @@ +# These 3 rules demand to add the s, m and x flag to *every* regexp. This is +# overkill and would be harmful for readability. +[-RegularExpressions::RequireExtendedFormatting] +[-RegularExpressions::RequireDotMatchAnything] +[-RegularExpressions::RequireLineBoundaryMatching] + +# This rule says that builtin functions should not be called with parentheses +# e.g.: (taken from CPAN's documentation) +# open($handle, '>', $filename); #not ok +# open $handle, '>', $filename; #ok +# Applying such a rule would mean modifying a huge number of lines for a +# question of style. +[-CodeLayout::ProhibitParensWithBuiltins] + +# This rule states that each system call should have its return value checked +# The problem is that it includes the print call. Checking every print call's +# return value would be harmful to the code readabilty. +# This configuration keeps all default function but print. +[InputOutput::RequireCheckedSyscalls] +functions = open say close + +# This rule demands to add a dependency for the Readonly module. This is not +# wished. +[-ValuesAndExpressions::ProhibitConstantPragma] + +# This rule is not really useful (rather a question of style) and produces many +# warnings among the code. +[-ValuesAndExpressions::ProhibitNoisyQuotes] diff --git a/contrib/mw-to-git/Git/Mediawiki.pm b/contrib/mw-to-git/Git/Mediawiki.pm new file mode 100644 index 000000000000..917d9e2d3222 --- /dev/null +++ b/contrib/mw-to-git/Git/Mediawiki.pm @@ -0,0 +1,101 @@ +package Git::Mediawiki; + +use 5.008; +use strict; +use POSIX; +use Git; + +BEGIN { + +our ($VERSION, @ISA, @EXPORT, @EXPORT_OK); + +# Totally unstable API. +$VERSION = '0.01'; + +require Exporter; + +@ISA = qw(Exporter); + +@EXPORT = (); + +# Methods which can be called as standalone functions as well: +@EXPORT_OK = qw(clean_filename smudge_filename connect_maybe + EMPTY HTTP_CODE_OK HTTP_CODE_PAGE_NOT_FOUND); +} + +# Mediawiki filenames can contain forward slashes. This variable decides by which pattern they should be replaced +use constant SLASH_REPLACEMENT => '%2F'; + +# Used to test for empty strings +use constant EMPTY => q{}; + +# HTTP codes +use constant HTTP_CODE_OK => 200; +use constant HTTP_CODE_PAGE_NOT_FOUND => 404; + +sub clean_filename { + my $filename = shift; + $filename =~ s{@{[SLASH_REPLACEMENT]}}{/}g; + # [, ], |, {, and } are forbidden by MediaWiki, even URL-encoded. + # Do a variant of URL-encoding, i.e. looks like URL-encoding, + # but with _ added to prevent MediaWiki from thinking this is + # an actual special character. + $filename =~ s/[\[\]\{\}\|]/sprintf("_%%_%x", ord($&))/ge; + # If we use the uri escape before + # we should unescape here, before anything + + return $filename; +} + +sub smudge_filename { + my $filename = shift; + $filename =~ s{/}{@{[SLASH_REPLACEMENT]}}g; + $filename =~ s/ /_/g; + # Decode forbidden characters encoded in clean_filename + $filename =~ s/_%_([0-9a-fA-F][0-9a-fA-F])/sprintf('%c', hex($1))/ge; + return substr($filename, 0, NAME_MAX-length('.mw')); +} + +sub connect_maybe { + my $wiki = shift; + if ($wiki) { + return $wiki; + } + + my $remote_name = shift; + my $remote_url = shift; + my ($wiki_login, $wiki_password, $wiki_domain); + + $wiki_login = Git::config("remote.${remote_name}.mwLogin"); + $wiki_password = Git::config("remote.${remote_name}.mwPassword"); + $wiki_domain = Git::config("remote.${remote_name}.mwDomain"); + + $wiki = MediaWiki::API->new; + $wiki->{config}->{api_url} = "${remote_url}/api.php"; + if ($wiki_login) { + my %credential = ( + 'url' => $remote_url, + 'username' => $wiki_login, + 'password' => $wiki_password + ); + Git::credential(\%credential); + my $request = {lgname => $credential{username}, + lgpassword => $credential{password}, + lgdomain => $wiki_domain}; + if ($wiki->login($request)) { + Git::credential(\%credential, 'approve'); + print {*STDERR} qq(Logged in mediawiki user "$credential{username}".\n); + } else { + print {*STDERR} qq(Failed to log in mediawiki user "$credential{username}" on ${remote_url}\n); + print {*STDERR} ' (error ' . + $wiki->{error}->{code} . ': ' . + $wiki->{error}->{details} . ")\n"; + Git::credential(\%credential, 'reject'); + exit 1; + } + } + + return $wiki; +} + +1; # Famous last words diff --git a/contrib/mw-to-git/Makefile b/contrib/mw-to-git/Makefile new file mode 100644 index 000000000000..4e603512a39f --- /dev/null +++ b/contrib/mw-to-git/Makefile @@ -0,0 +1,58 @@ +# +# Copyright (C) 2013 +# Matthieu Moy <Matthieu.Moy@imag.fr> +# +# To build and test: +# +# make +# bin-wrapper/git mw preview Some_page.mw +# bin-wrapper/git clone mediawiki::http://example.com/wiki/ +# +# To install, run Git's toplevel 'make install' then run: +# +# make install + +GIT_MEDIAWIKI_PM=Git/Mediawiki.pm +SCRIPT_PERL=git-remote-mediawiki.perl +SCRIPT_PERL+=git-mw.perl +GIT_ROOT_DIR=../.. +HERE=contrib/mw-to-git/ + +INSTALL = install + +SCRIPT_PERL_FULL=$(patsubst %,$(HERE)/%,$(SCRIPT_PERL)) +INSTLIBDIR=$(shell $(MAKE) -C $(GIT_ROOT_DIR)/ \ + -s --no-print-directory prefix=$(prefix) \ + perllibdir=$(perllibdir) perllibdir) +DESTDIR_SQ = $(subst ','\'',$(DESTDIR)) +INSTLIBDIR_SQ = $(subst ','\'',$(INSTLIBDIR)) + +all: build + +test: all + $(MAKE) -C t + +check: perlcritic test + +install_pm: + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(INSTLIBDIR_SQ)/Git' + $(INSTALL) -m 644 $(GIT_MEDIAWIKI_PM) \ + '$(DESTDIR_SQ)$(INSTLIBDIR_SQ)/$(GIT_MEDIAWIKI_PM)' + +build: + $(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL="$(SCRIPT_PERL_FULL)" \ + build-perl-script + +install: install_pm + $(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL="$(SCRIPT_PERL_FULL)" \ + install-perl-script + +clean: + $(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL="$(SCRIPT_PERL_FULL)" \ + clean-perl-script + +perlcritic: + perlcritic -5 $(SCRIPT_PERL) + -perlcritic -2 $(SCRIPT_PERL) + +.PHONY: all test check install_pm install clean perlcritic diff --git a/contrib/mw-to-git/bin-wrapper/git b/contrib/mw-to-git/bin-wrapper/git new file mode 100755 index 000000000000..6663ae57e869 --- /dev/null +++ b/contrib/mw-to-git/bin-wrapper/git @@ -0,0 +1,14 @@ +#!/bin/sh + +# git executable wrapper script for Git-Mediawiki to run tests without +# installing all the scripts and perl packages. + +GIT_ROOT_DIR=../../.. +GIT_EXEC_PATH=$(cd "$(dirname "$0")" && cd ${GIT_ROOT_DIR} && pwd) + +GITPERLLIB="$GIT_EXEC_PATH"'/contrib/mw-to-git'"${GITPERLLIB:+:$GITPERLLIB}" +PATH="$GIT_EXEC_PATH"'/contrib/mw-to-git:'"$PATH" + +export GITPERLLIB PATH + +exec "${GIT_EXEC_PATH}/bin-wrappers/git" "$@" diff --git a/contrib/mw-to-git/git-mw.perl b/contrib/mw-to-git/git-mw.perl new file mode 100755 index 000000000000..28df3ee321ec --- /dev/null +++ b/contrib/mw-to-git/git-mw.perl @@ -0,0 +1,368 @@ +#!/usr/bin/perl + +# Copyright (C) 2013 +# Benoit Person <benoit.person@ensimag.imag.fr> +# Celestin Matte <celestin.matte@ensimag.imag.fr> +# License: GPL v2 or later + +# Set of tools for git repo with a mediawiki remote. +# Documentation & bugtracker: https://github.com/moy/Git-Mediawiki/ + +use strict; +use warnings; + +use Getopt::Long; +use URI::URL qw(url); +use LWP::UserAgent; +use HTML::TreeBuilder; + +use Git; +use MediaWiki::API; +use Git::Mediawiki qw(clean_filename connect_maybe + EMPTY HTTP_CODE_PAGE_NOT_FOUND); + +# By default, use UTF-8 to communicate with Git and the user +binmode STDERR, ':encoding(UTF-8)'; +binmode STDOUT, ':encoding(UTF-8)'; + +# Global parameters +my $verbose = 0; +sub v_print { + if ($verbose) { + return print {*STDERR} @_; + } + return; +} + +# Preview parameters +my $file_name = EMPTY; +my $remote_name = EMPTY; +my $preview_file_name = EMPTY; +my $autoload = 0; +sub file { + $file_name = shift; + return $file_name; +} + +my %commands = ( + 'help' => + [\&help, {}, \&help], + 'preview' => + [\&preview, { + '<>' => \&file, + 'output|o=s' => \$preview_file_name, + 'remote|r=s' => \$remote_name, + 'autoload|a' => \$autoload + }, \&preview_help] +); + +# Search for sub-command +my $cmd = $commands{'help'}; +for (0..@ARGV-1) { + if (defined $commands{$ARGV[$_]}) { + $cmd = $commands{$ARGV[$_]}; + splice @ARGV, $_, 1; + last; + } +}; +GetOptions( %{$cmd->[1]}, + 'help|h' => \&{$cmd->[2]}, + 'verbose|v' => \$verbose); + +# Launch command +&{$cmd->[0]}; + +############################# Preview Functions ################################ + +sub preview_help { + print {*STDOUT} <<'END'; +USAGE: git mw preview [--remote|-r <remote name>] [--autoload|-a] + [--output|-o <output filename>] [--verbose|-v] + <blob> | <filename> + +DESCRIPTION: +Preview is an utiliy to preview local content of a mediawiki repo as if it was +pushed on the remote. + +For that, preview searches for the remote name of the current branch's +upstream if --remote is not set. If that remote is not found or if it +is not a mediawiki, it lists all mediawiki remotes configured and asks +you to replay your command with the --remote option set properly. + +Then, it searches for a file named 'filename'. If it's not found in +the current dir, it will assume it's a blob. + +The content retrieved in the file (or in the blob) will then be parsed +by the remote mediawiki and combined with a template retrieved from +the mediawiki. + +Finally, preview will save the HTML result in a file. and autoload it +in your default web browser if the option --autoload is present. + +OPTIONS: + -r <remote name>, --remote <remote name> + If the remote is a mediawiki, the template and the parse engine + used for the preview will be those of that remote. + If not, a list of valid remotes will be shown. + + -a, --autoload + Try to load the HTML output in a new tab (or new window) of your + default web browser. + + -o <output filename>, --output <output filename> + Change the HTML output filename. Default filename is based on the + input filename with its extension replaced by '.html'. + + -v, --verbose + Show more information on what's going on under the hood. +END + exit; +} + +sub preview { + my $wiki; + my ($remote_url, $wiki_page_name); + my ($new_content, $template); + my $file_content; + + if ($file_name eq EMPTY) { + die "Missing file argument, see `git mw help`\n"; + } + + v_print("### Selecting remote\n"); + if ($remote_name eq EMPTY) { + $remote_name = find_upstream_remote_name(); + if ($remote_name) { + $remote_url = mediawiki_remote_url_maybe($remote_name); + } + + if (! $remote_url) { + my @valid_remotes = find_mediawiki_remotes(); + + if ($#valid_remotes == 0) { + print {*STDERR} "No mediawiki remote in this repo. \n"; + exit 1; + } else { + my $remotes_list = join("\n\t", @valid_remotes); + print {*STDERR} <<"MESSAGE"; +There are multiple mediawiki remotes, which of: + ${remotes_list} +do you want ? Use the -r option to specify the remote. +MESSAGE + } + + exit 1; + } + } else { + if (!is_valid_remote($remote_name)) { + die "${remote_name} is not a remote\n"; + } + + $remote_url = mediawiki_remote_url_maybe($remote_name); + if (! $remote_url) { + die "${remote_name} is not a mediawiki remote\n"; + } + } + v_print("selected remote:\n\tname: ${remote_name}\n\turl: ${remote_url}\n"); + + $wiki = connect_maybe($wiki, $remote_name, $remote_url); + + # Read file content + if (! -e $file_name) { + $file_content = git_cmd_try { + Git::command('cat-file', 'blob', $file_name); } + "%s failed w/ code %d"; + + if ($file_name =~ /(.+):(.+)/) { + $file_name = $2; + } + } else { + open my $read_fh, "<", $file_name + or die "could not open ${file_name}: $!\n"; + $file_content = do { local $/ = undef; <$read_fh> }; + close $read_fh + or die "unable to close: $!\n"; + } + + v_print("### Retrieving template\n"); + ($wiki_page_name = clean_filename($file_name)) =~ s/\.[^.]+$//; + $template = get_template($remote_url, $wiki_page_name); + + v_print("### Parsing local content\n"); + $new_content = $wiki->api({ + action => 'parse', + text => $file_content, + title => $wiki_page_name + }, { + skip_encoding => 1 + }) or die "No response from remote mediawiki\n"; + $new_content = $new_content->{'parse'}->{'text'}->{'*'}; + + v_print("### Merging contents\n"); + if ($preview_file_name eq EMPTY) { + ($preview_file_name = $file_name) =~ s/\.[^.]+$/.html/; + } + open(my $save_fh, '>:encoding(UTF-8)', $preview_file_name) + or die "Could not open: $!\n"; + print {$save_fh} merge_contents($template, $new_content, $remote_url); + close($save_fh) + or die "Could not close: $!\n"; + + v_print("### Results\n"); + if ($autoload) { + v_print("Launching browser w/ file: ${preview_file_name}"); + system('git', 'web--browse', $preview_file_name); + } else { + print {*STDERR} "Preview file saved as: ${preview_file_name}\n"; + } + + exit; +} + +# uses global scope variable: $remote_name +sub merge_contents { + my $template = shift; + my $content = shift; + my $remote_url = shift; + my ($content_tree, $html_tree, $mw_content_text); + my $template_content_id = 'bodyContent'; + + $html_tree = HTML::TreeBuilder->new; + $html_tree->parse($template); + + $content_tree = HTML::TreeBuilder->new; + $content_tree->parse($content); + + $template_content_id = Git::config("remote.${remote_name}.mwIDcontent") + || $template_content_id; + v_print("Using '${template_content_id}' as the content ID\n"); + + $mw_content_text = $html_tree->look_down('id', $template_content_id); + if (!defined $mw_content_text) { + print {*STDERR} <<"CONFIG"; +Could not combine the new content with the template. You might want to +configure `mediawiki.IDContent` in your config: + git config --add remote.${remote_name}.mwIDcontent <id> +and re-run the command afterward. +CONFIG + exit 1; + } + $mw_content_text->delete_content(); + $mw_content_text->push_content($content_tree); + + make_links_absolute($html_tree, $remote_url); + + return $html_tree->as_HTML; +} + +sub make_links_absolute { + my $html_tree = shift; + my $remote_url = shift; + for (@{ $html_tree->extract_links() }) { + my ($link, $element, $attr) = @{ $_ }; + my $url = url($link)->canonical; + if ($url !~ /#/) { + $element->attr($attr, URI->new_abs($url, $remote_url)); + } + } + return $html_tree; +} + +sub is_valid_remote { + my $remote = shift; + my @remotes = git_cmd_try { + Git::command('remote') } + "%s failed w/ code %d"; + my $found_remote = 0; + foreach my $remote (@remotes) { + if ($remote eq $remote) { + $found_remote = 1; + last; + } + } + return $found_remote; +} + +sub find_mediawiki_remotes { + my @remotes = git_cmd_try { + Git::command('remote'); } + "%s failed w/ code %d"; + my $remote_url; + my @valid_remotes = (); + foreach my $remote (@remotes) { + $remote_url = mediawiki_remote_url_maybe($remote); + if ($remote_url) { + push(@valid_remotes, $remote); + } + } + return @valid_remotes; +} + +sub find_upstream_remote_name { + my $current_branch = git_cmd_try { + Git::command_oneline('symbolic-ref', '--short', 'HEAD') } + "%s failed w/ code %d"; + return Git::config("branch.${current_branch}.remote"); +} + +sub mediawiki_remote_url_maybe { + my $remote = shift; + + # Find remote url + my $remote_url = Git::config("remote.${remote}.url"); + if ($remote_url =~ s/mediawiki::(.*)/$1/) { + return url($remote_url)->canonical; + } + + return; +} + +sub get_template { + my $url = shift; + my $page_name = shift; + my ($req, $res, $code, $url_after); + + $req = LWP::UserAgent->new; + if ($verbose) { + $req->show_progress(1); + } + + $res = $req->get("${url}/index.php?title=${page_name}"); + if (!$res->is_success) { + $code = $res->code; + $url_after = $res->request()->uri(); # resolve all redirections + if ($code == HTTP_CODE_PAGE_NOT_FOUND) { + if ($verbose) { + print {*STDERR} <<"WARNING"; +Warning: Failed to retrieve '$page_name'. Create it on the mediawiki if you want +all the links to work properly. +Trying to use the mediawiki homepage as a fallback template ... +WARNING + } + + # LWP automatically redirects GET request + $res = $req->get("${url}/index.php"); + if (!$res->is_success) { + $url_after = $res->request()->uri(); # resolve all redirections + die "Failed to get homepage @ ${url_after} w/ code ${code}\n"; + } + } else { + die "Failed to get '${page_name}' @ ${url_after} w/ code ${code}\n"; + } + } + + return $res->decoded_content; +} + +############################## Help Functions ################################## + +sub help { + print {*STDOUT} <<'END'; +usage: git mw <command> <args> + +git mw commands are: + help Display help information about git mw + preview Parse and render local file into HTML +END + exit; +} diff --git a/contrib/mw-to-git/git-remote-mediawiki.perl b/contrib/mw-to-git/git-remote-mediawiki.perl new file mode 100755 index 000000000000..af9cbc9d0f7b --- /dev/null +++ b/contrib/mw-to-git/git-remote-mediawiki.perl @@ -0,0 +1,1374 @@ +#! /usr/bin/perl + +# Copyright (C) 2011 +# Jérémie Nikaes <jeremie.nikaes@ensimag.imag.fr> +# Arnaud Lacurie <arnaud.lacurie@ensimag.imag.fr> +# Claire Fousse <claire.fousse@ensimag.imag.fr> +# David Amouyal <david.amouyal@ensimag.imag.fr> +# Matthieu Moy <matthieu.moy@grenoble-inp.fr> +# License: GPL v2 or later + +# Gateway between Git and MediaWiki. +# Documentation & bugtracker: https://github.com/moy/Git-Mediawiki/ + +use strict; +use MediaWiki::API; +use Git; +use Git::Mediawiki qw(clean_filename smudge_filename connect_maybe + EMPTY HTTP_CODE_OK); +use DateTime::Format::ISO8601; +use warnings; + +# By default, use UTF-8 to communicate with Git and the user +binmode STDERR, ':encoding(UTF-8)'; +binmode STDOUT, ':encoding(UTF-8)'; + +use URI::Escape; + +# It's not always possible to delete pages (may require some +# privileges). Deleted pages are replaced with this content. +use constant DELETED_CONTENT => "[[Category:Deleted]]\n"; + +# It's not possible to create empty pages. New empty files in Git are +# sent with this content instead. +use constant EMPTY_CONTENT => "<!-- empty page -->\n"; + +# used to reflect file creation or deletion in diff. +use constant NULL_SHA1 => '0000000000000000000000000000000000000000'; + +# Used on Git's side to reflect empty edit messages on the wiki +use constant EMPTY_MESSAGE => '*Empty MediaWiki Message*'; + +# Number of pages taken into account at once in submodule get_mw_page_list +use constant SLICE_SIZE => 50; + +# Number of linked mediafile to get at once in get_linked_mediafiles +# The query is split in small batches because of the MW API limit of +# the number of links to be returned (500 links max). +use constant BATCH_SIZE => 10; + +if (@ARGV != 2) { + exit_error_usage(); +} + +my $remotename = $ARGV[0]; +my $url = $ARGV[1]; + +# Accept both space-separated and multiple keys in config file. +# Spaces should be written as _ anyway because we'll use chomp. +my @tracked_pages = split(/[ \n]/, run_git("config --get-all remote.${remotename}.pages")); +chomp(@tracked_pages); + +# Just like @tracked_pages, but for MediaWiki categories. +my @tracked_categories = split(/[ \n]/, run_git("config --get-all remote.${remotename}.categories")); +chomp(@tracked_categories); + +# Just like @tracked_categories, but for MediaWiki namespaces. +my @tracked_namespaces = split(/[ \n]/, run_git("config --get-all remote.${remotename}.namespaces")); +for (@tracked_namespaces) { s/_/ /g; } +chomp(@tracked_namespaces); + +# Import media files on pull +my $import_media = run_git("config --get --bool remote.${remotename}.mediaimport"); +chomp($import_media); +$import_media = ($import_media eq 'true'); + +# Export media files on push +my $export_media = run_git("config --get --bool remote.${remotename}.mediaexport"); +chomp($export_media); +$export_media = !($export_media eq 'false'); + +my $wiki_login = run_git("config --get remote.${remotename}.mwLogin"); +# Note: mwPassword is discourraged. Use the credential system instead. +my $wiki_passwd = run_git("config --get remote.${remotename}.mwPassword"); +my $wiki_domain = run_git("config --get remote.${remotename}.mwDomain"); +chomp($wiki_login); +chomp($wiki_passwd); +chomp($wiki_domain); + +# Import only last revisions (both for clone and fetch) +my $shallow_import = run_git("config --get --bool remote.${remotename}.shallow"); +chomp($shallow_import); +$shallow_import = ($shallow_import eq 'true'); + +# Fetch (clone and pull) by revisions instead of by pages. This behavior +# is more efficient when we have a wiki with lots of pages and we fetch +# the revisions quite often so that they concern only few pages. +# Possible values: +# - by_rev: perform one query per new revision on the remote wiki +# - by_page: query each tracked page for new revision +my $fetch_strategy = run_git("config --get remote.${remotename}.fetchStrategy"); +if (!$fetch_strategy) { + $fetch_strategy = run_git('config --get mediawiki.fetchStrategy'); +} +chomp($fetch_strategy); +if (!$fetch_strategy) { + $fetch_strategy = 'by_page'; +} + +# Remember the timestamp corresponding to a revision id. +my %basetimestamps; + +# Dumb push: don't update notes and mediawiki ref to reflect the last push. +# +# Configurable with mediawiki.dumbPush, or per-remote with +# remote.<remotename>.dumbPush. +# +# This means the user will have to re-import the just-pushed +# revisions. On the other hand, this means that the Git revisions +# corresponding to MediaWiki revisions are all imported from the wiki, +# regardless of whether they were initially created in Git or from the +# web interface, hence all users will get the same history (i.e. if +# the push from Git to MediaWiki loses some information, everybody +# will get the history with information lost). If the import is +# deterministic, this means everybody gets the same sha1 for each +# MediaWiki revision. +my $dumb_push = run_git("config --get --bool remote.${remotename}.dumbPush"); +if (!$dumb_push) { + $dumb_push = run_git('config --get --bool mediawiki.dumbPush'); +} +chomp($dumb_push); +$dumb_push = ($dumb_push eq 'true'); + +my $wiki_name = $url; +$wiki_name =~ s{[^/]*://}{}; +# If URL is like http://user:password@example.com/, we clearly don't +# want the password in $wiki_name. While we're there, also remove user +# and '@' sign, to avoid author like MWUser@HTTPUser@host.com +$wiki_name =~ s/^.*@//; + +# Commands parser +while (<STDIN>) { + chomp; + + if (!parse_command($_)) { + last; + } + + BEGIN { $| = 1 } # flush STDOUT, to make sure the previous + # command is fully processed. +} + +########################## Functions ############################## + +## error handling +sub exit_error_usage { + die "ERROR: git-remote-mediawiki module was not called with a correct number of\n" . + "parameters\n" . + "You may obtain this error because you attempted to run the git-remote-mediawiki\n" . + "module directly.\n" . + "This module can be used the following way:\n" . + "\tgit clone mediawiki://<address of a mediawiki>\n" . + "Then, use git commit, push and pull as with every normal git repository.\n"; +} + +sub parse_command { + my ($line) = @_; + my @cmd = split(/ /, $line); + if (!defined $cmd[0]) { + return 0; + } + if ($cmd[0] eq 'capabilities') { + die("Too many arguments for capabilities\n") + if (defined($cmd[1])); + mw_capabilities(); + } elsif ($cmd[0] eq 'list') { + die("Too many arguments for list\n") if (defined($cmd[2])); + mw_list($cmd[1]); + } elsif ($cmd[0] eq 'import') { + die("Invalid argument for import\n") + if ($cmd[1] eq EMPTY); + die("Too many arguments for import\n") + if (defined($cmd[2])); + mw_import($cmd[1]); + } elsif ($cmd[0] eq 'option') { + die("Invalid arguments for option\n") + if ($cmd[1] eq EMPTY || $cmd[2] eq EMPTY); + die("Too many arguments for option\n") + if (defined($cmd[3])); + mw_option($cmd[1],$cmd[2]); + } elsif ($cmd[0] eq 'push') { + mw_push($cmd[1]); + } else { + print {*STDERR} "Unknown command. Aborting...\n"; + return 0; + } + return 1; +} + +# MediaWiki API instance, created lazily. +my $mediawiki; + +sub fatal_mw_error { + my $action = shift; + print STDERR "fatal: could not $action.\n"; + print STDERR "fatal: '$url' does not appear to be a mediawiki\n"; + if ($url =~ /^https/) { + print STDERR "fatal: make sure '$url/api.php' is a valid page\n"; + print STDERR "fatal: and the SSL certificate is correct.\n"; + } else { + print STDERR "fatal: make sure '$url/api.php' is a valid page.\n"; + } + print STDERR "fatal: (error " . + $mediawiki->{error}->{code} . ': ' . + $mediawiki->{error}->{details} . ")\n"; + exit 1; +} + +## Functions for listing pages on the remote wiki +sub get_mw_tracked_pages { + my $pages = shift; + get_mw_page_list(\@tracked_pages, $pages); + return; +} + +sub get_mw_page_list { + my $page_list = shift; + my $pages = shift; + my @some_pages = @{$page_list}; + while (@some_pages) { + my $last_page = SLICE_SIZE; + if ($#some_pages < $last_page) { + $last_page = $#some_pages; + } + my @slice = @some_pages[0..$last_page]; + get_mw_first_pages(\@slice, $pages); + @some_pages = @some_pages[(SLICE_SIZE + 1)..$#some_pages]; + } + return; +} + +sub get_mw_tracked_categories { + my $pages = shift; + foreach my $category (@tracked_categories) { + if (index($category, ':') < 0) { + # Mediawiki requires the Category + # prefix, but let's not force the user + # to specify it. + $category = "Category:${category}"; + } + my $mw_pages = $mediawiki->list( { + action => 'query', + list => 'categorymembers', + cmtitle => $category, + cmlimit => 'max' } ) + || die $mediawiki->{error}->{code} . ': ' + . $mediawiki->{error}->{details} . "\n"; + foreach my $page (@{$mw_pages}) { + $pages->{$page->{title}} = $page; + } + } + return; +} + +sub get_mw_tracked_namespaces { + my $pages = shift; + foreach my $local_namespace (sort @tracked_namespaces) { + my $namespace_id; + if ($local_namespace eq "(Main)") { + $namespace_id = 0; + } else { + $namespace_id = get_mw_namespace_id($local_namespace); + } + # virtual namespaces don't support allpages + next if !defined($namespace_id) || $namespace_id < 0; + my $mw_pages = $mediawiki->list( { + action => 'query', + list => 'allpages', + apnamespace => $namespace_id, + aplimit => 'max' } ) + || die $mediawiki->{error}->{code} . ': ' + . $mediawiki->{error}->{details} . "\n"; + print {*STDERR} "$#{$mw_pages} found in namespace $local_namespace ($namespace_id)\n"; + foreach my $page (@{$mw_pages}) { + $pages->{$page->{title}} = $page; + } + } + return; +} + +sub get_mw_all_pages { + my $pages = shift; + # No user-provided list, get the list of pages from the API. + my $mw_pages = $mediawiki->list({ + action => 'query', + list => 'allpages', + aplimit => 'max' + }); + if (!defined($mw_pages)) { + fatal_mw_error("get the list of wiki pages"); + } + foreach my $page (@{$mw_pages}) { + $pages->{$page->{title}} = $page; + } + return; +} + +# queries the wiki for a set of pages. Meant to be used within a loop +# querying the wiki for slices of page list. +sub get_mw_first_pages { + my $some_pages = shift; + my @some_pages = @{$some_pages}; + + my $pages = shift; + + # pattern 'page1|page2|...' required by the API + my $titles = join('|', @some_pages); + + my $mw_pages = $mediawiki->api({ + action => 'query', + titles => $titles, + }); + if (!defined($mw_pages)) { + fatal_mw_error("query the list of wiki pages"); + } + while (my ($id, $page) = each(%{$mw_pages->{query}->{pages}})) { + if ($id < 0) { + print {*STDERR} "Warning: page $page->{title} not found on wiki\n"; + } else { + $pages->{$page->{title}} = $page; + } + } + return; +} + +# Get the list of pages to be fetched according to configuration. +sub get_mw_pages { + $mediawiki = connect_maybe($mediawiki, $remotename, $url); + + print {*STDERR} "Listing pages on remote wiki...\n"; + + my %pages; # hash on page titles to avoid duplicates + my $user_defined; + if (@tracked_pages) { + $user_defined = 1; + # The user provided a list of pages titles, but we + # still need to query the API to get the page IDs. + get_mw_tracked_pages(\%pages); + } + if (@tracked_categories) { + $user_defined = 1; + get_mw_tracked_categories(\%pages); + } + if (@tracked_namespaces) { + $user_defined = 1; + get_mw_tracked_namespaces(\%pages); + } + if (!$user_defined) { + get_mw_all_pages(\%pages); + } + if ($import_media) { + print {*STDERR} "Getting media files for selected pages...\n"; + if ($user_defined) { + get_linked_mediafiles(\%pages); + } else { + get_all_mediafiles(\%pages); + } + } + print {*STDERR} (scalar keys %pages) . " pages found.\n"; + return %pages; +} + +# usage: $out = run_git("command args"); +# $out = run_git("command args", "raw"); # don't interpret output as UTF-8. +sub run_git { + my $args = shift; + my $encoding = (shift || 'encoding(UTF-8)'); + open(my $git, "-|:${encoding}", "git ${args}") + or die "Unable to fork: $!\n"; + my $res = do { + local $/ = undef; + <$git> + }; + close($git); + + return $res; +} + + +sub get_all_mediafiles { + my $pages = shift; + # Attach list of all pages for media files from the API, + # they are in a different namespace, only one namespace + # can be queried at the same moment + my $mw_pages = $mediawiki->list({ + action => 'query', + list => 'allpages', + apnamespace => get_mw_namespace_id('File'), + aplimit => 'max' + }); + if (!defined($mw_pages)) { + print {*STDERR} "fatal: could not get the list of pages for media files.\n"; + print {*STDERR} "fatal: '$url' does not appear to be a mediawiki\n"; + print {*STDERR} "fatal: make sure '$url/api.php' is a valid page.\n"; + exit 1; + } + foreach my $page (@{$mw_pages}) { + $pages->{$page->{title}} = $page; + } + return; +} + +sub get_linked_mediafiles { + my $pages = shift; + my @titles = map { $_->{title} } values(%{$pages}); + + my $batch = BATCH_SIZE; + while (@titles) { + if ($#titles < $batch) { + $batch = $#titles; + } + my @slice = @titles[0..$batch]; + + # pattern 'page1|page2|...' required by the API + my $mw_titles = join('|', @slice); + + # Media files could be included or linked from + # a page, get all related + my $query = { + action => 'query', + prop => 'links|images', + titles => $mw_titles, + plnamespace => get_mw_namespace_id('File'), + pllimit => 'max' + }; + my $result = $mediawiki->api($query); + + while (my ($id, $page) = each(%{$result->{query}->{pages}})) { + my @media_titles; + if (defined($page->{links})) { + my @link_titles + = map { $_->{title} } @{$page->{links}}; + push(@media_titles, @link_titles); + } + if (defined($page->{images})) { + my @image_titles + = map { $_->{title} } @{$page->{images}}; + push(@media_titles, @image_titles); + } + if (@media_titles) { + get_mw_page_list(\@media_titles, $pages); + } + } + + @titles = @titles[($batch+1)..$#titles]; + } + return; +} + +sub get_mw_mediafile_for_page_revision { + # Name of the file on Wiki, with the prefix. + my $filename = shift; + my $timestamp = shift; + my %mediafile; + + # Search if on a media file with given timestamp exists on + # MediaWiki. In that case download the file. + my $query = { + action => 'query', + prop => 'imageinfo', + titles => "File:${filename}", + iistart => $timestamp, + iiend => $timestamp, + iiprop => 'timestamp|archivename|url', + iilimit => 1 + }; + my $result = $mediawiki->api($query); + + my ($fileid, $file) = each( %{$result->{query}->{pages}} ); + # If not defined it means there is no revision of the file for + # given timestamp. + if (defined($file->{imageinfo})) { + $mediafile{title} = $filename; + + my $fileinfo = pop(@{$file->{imageinfo}}); + $mediafile{timestamp} = $fileinfo->{timestamp}; + # Mediawiki::API's download function doesn't support https URLs + # and can't download old versions of files. + print {*STDERR} "\tDownloading file $mediafile{title}, version $mediafile{timestamp}\n"; + $mediafile{content} = download_mw_mediafile($fileinfo->{url}); + } + return %mediafile; +} + +sub download_mw_mediafile { + my $download_url = shift; + + my $response = $mediawiki->{ua}->get($download_url); + if ($response->code == HTTP_CODE_OK) { + # It is tempting to return + # $response->decoded_content({charset => "none"}), but + # when doing so, utf8::downgrade($content) fails with + # "Wide character in subroutine entry". + $response->decode(); + return $response->content(); + } else { + print {*STDERR} "Error downloading mediafile from :\n"; + print {*STDERR} "URL: ${download_url}\n"; + print {*STDERR} 'Server response: ' . $response->code . q{ } . $response->message . "\n"; + exit 1; + } +} + +sub get_last_local_revision { + # Get note regarding last mediawiki revision + my $note = run_git("notes --ref=${remotename}/mediawiki show refs/mediawiki/${remotename}/master 2>/dev/null"); + my @note_info = split(/ /, $note); + + my $lastrevision_number; + if (!(defined($note_info[0]) && $note_info[0] eq 'mediawiki_revision:')) { + print {*STDERR} 'No previous mediawiki revision found'; + $lastrevision_number = 0; + } else { + # Notes are formatted : mediawiki_revision: #number + $lastrevision_number = $note_info[1]; + chomp($lastrevision_number); + print {*STDERR} "Last local mediawiki revision found is ${lastrevision_number}"; + } + return $lastrevision_number; +} + +# Get the last remote revision without taking in account which pages are +# tracked or not. This function makes a single request to the wiki thus +# avoid a loop onto all tracked pages. This is useful for the fetch-by-rev +# option. +sub get_last_global_remote_rev { + $mediawiki = connect_maybe($mediawiki, $remotename, $url); + + my $query = { + action => 'query', + list => 'recentchanges', + prop => 'revisions', + rclimit => '1', + rcdir => 'older', + }; + my $result = $mediawiki->api($query); + return $result->{query}->{recentchanges}[0]->{revid}; +} + +# Get the last remote revision concerning the tracked pages and the tracked +# categories. +sub get_last_remote_revision { + $mediawiki = connect_maybe($mediawiki, $remotename, $url); + + my %pages_hash = get_mw_pages(); + my @pages = values(%pages_hash); + + my $max_rev_num = 0; + + print {*STDERR} "Getting last revision id on tracked pages...\n"; + + foreach my $page (@pages) { + my $id = $page->{pageid}; + + my $query = { + action => 'query', + prop => 'revisions', + rvprop => 'ids|timestamp', + pageids => $id, + }; + + my $result = $mediawiki->api($query); + + my $lastrev = pop(@{$result->{query}->{pages}->{$id}->{revisions}}); + + $basetimestamps{$lastrev->{revid}} = $lastrev->{timestamp}; + + $max_rev_num = ($lastrev->{revid} > $max_rev_num ? $lastrev->{revid} : $max_rev_num); + } + + print {*STDERR} "Last remote revision found is $max_rev_num.\n"; + return $max_rev_num; +} + +# Clean content before sending it to MediaWiki +sub mediawiki_clean { + my $string = shift; + my $page_created = shift; + # Mediawiki does not allow blank space at the end of a page and ends with a single \n. + # This function right trims a string and adds a \n at the end to follow this rule + $string =~ s/\s+$//; + if ($string eq EMPTY && $page_created) { + # Creating empty pages is forbidden. + $string = EMPTY_CONTENT; + } + return $string."\n"; +} + +# Filter applied on MediaWiki data before adding them to Git +sub mediawiki_smudge { + my $string = shift; + if ($string eq EMPTY_CONTENT) { + $string = EMPTY; + } + # This \n is important. This is due to mediawiki's way to handle end of files. + return "${string}\n"; +} + +sub literal_data { + my ($content) = @_; + print {*STDOUT} 'data ', bytes::length($content), "\n", $content; + return; +} + +sub literal_data_raw { + # Output possibly binary content. + my ($content) = @_; + # Avoid confusion between size in bytes and in characters + utf8::downgrade($content); + binmode STDOUT, ':raw'; + print {*STDOUT} 'data ', bytes::length($content), "\n", $content; + binmode STDOUT, ':encoding(UTF-8)'; + return; +} + +sub mw_capabilities { + # Revisions are imported to the private namespace + # refs/mediawiki/$remotename/ by the helper and fetched into + # refs/remotes/$remotename later by fetch. + print {*STDOUT} "refspec refs/heads/*:refs/mediawiki/${remotename}/*\n"; + print {*STDOUT} "import\n"; + print {*STDOUT} "list\n"; + print {*STDOUT} "push\n"; + if ($dumb_push) { + print {*STDOUT} "no-private-update\n"; + } + print {*STDOUT} "\n"; + return; +} + +sub mw_list { + # MediaWiki do not have branches, we consider one branch arbitrarily + # called master, and HEAD pointing to it. + print {*STDOUT} "? refs/heads/master\n"; + print {*STDOUT} "\@refs/heads/master HEAD\n"; + print {*STDOUT} "\n"; + return; +} + +sub mw_option { + print {*STDERR} "remote-helper command 'option $_[0]' not yet implemented\n"; + print {*STDOUT} "unsupported\n"; + return; +} + +sub fetch_mw_revisions_for_page { + my $page = shift; + my $id = shift; + my $fetch_from = shift; + my @page_revs = (); + my $query = { + action => 'query', + prop => 'revisions', + rvprop => 'ids', + rvdir => 'newer', + rvstartid => $fetch_from, + rvlimit => 500, + pageids => $id, + + # Let MediaWiki know that we support the latest API. + continue => '', + }; + + my $revnum = 0; + # Get 500 revisions at a time due to the mediawiki api limit + while (1) { + my $result = $mediawiki->api($query); + + # Parse each of those 500 revisions + foreach my $revision (@{$result->{query}->{pages}->{$id}->{revisions}}) { + my $page_rev_ids; + $page_rev_ids->{pageid} = $page->{pageid}; + $page_rev_ids->{revid} = $revision->{revid}; + push(@page_revs, $page_rev_ids); + $revnum++; + } + + if ($result->{'query-continue'}) { # For legacy APIs + $query->{rvstartid} = $result->{'query-continue'}->{revisions}->{rvstartid}; + } elsif ($result->{continue}) { # For newer APIs + $query->{rvstartid} = $result->{continue}->{rvcontinue}; + $query->{continue} = $result->{continue}->{continue}; + } else { + last; + } + } + if ($shallow_import && @page_revs) { + print {*STDERR} " Found 1 revision (shallow import).\n"; + @page_revs = sort {$b->{revid} <=> $a->{revid}} (@page_revs); + return $page_revs[0]; + } + print {*STDERR} " Found ${revnum} revision(s).\n"; + return @page_revs; +} + +sub fetch_mw_revisions { + my $pages = shift; my @pages = @{$pages}; + my $fetch_from = shift; + + my @revisions = (); + my $n = 1; + foreach my $page (@pages) { + my $id = $page->{pageid}; + print {*STDERR} "page ${n}/", scalar(@pages), ': ', $page->{title}, "\n"; + $n++; + my @page_revs = fetch_mw_revisions_for_page($page, $id, $fetch_from); + @revisions = (@page_revs, @revisions); + } + + return ($n, @revisions); +} + +sub fe_escape_path { + my $path = shift; + $path =~ s/\\/\\\\/g; + $path =~ s/"/\\"/g; + $path =~ s/\n/\\n/g; + return qq("${path}"); +} + +sub import_file_revision { + my $commit = shift; + my %commit = %{$commit}; + my $full_import = shift; + my $n = shift; + my $mediafile = shift; + my %mediafile; + if ($mediafile) { + %mediafile = %{$mediafile}; + } + + my $title = $commit{title}; + my $comment = $commit{comment}; + my $content = $commit{content}; + my $author = $commit{author}; + my $date = $commit{date}; + + print {*STDOUT} "commit refs/mediawiki/${remotename}/master\n"; + print {*STDOUT} "mark :${n}\n"; + print {*STDOUT} "committer ${author} <${author}\@${wiki_name}> " . $date->epoch . " +0000\n"; + literal_data($comment); + + # If it's not a clone, we need to know where to start from + if (!$full_import && $n == 1) { + print {*STDOUT} "from refs/mediawiki/${remotename}/master^0\n"; + } + if ($content ne DELETED_CONTENT) { + print {*STDOUT} 'M 644 inline ' . + fe_escape_path("${title}.mw") . "\n"; + literal_data($content); + if (%mediafile) { + print {*STDOUT} 'M 644 inline ' + . fe_escape_path($mediafile{title}) . "\n"; + literal_data_raw($mediafile{content}); + } + print {*STDOUT} "\n\n"; + } else { + print {*STDOUT} 'D ' . fe_escape_path("${title}.mw") . "\n"; + } + + # mediawiki revision number in the git note + if ($full_import && $n == 1) { + print {*STDOUT} "reset refs/notes/${remotename}/mediawiki\n"; + } + print {*STDOUT} "commit refs/notes/${remotename}/mediawiki\n"; + print {*STDOUT} "committer ${author} <${author}\@${wiki_name}> " . $date->epoch . " +0000\n"; + literal_data('Note added by git-mediawiki during import'); + if (!$full_import && $n == 1) { + print {*STDOUT} "from refs/notes/${remotename}/mediawiki^0\n"; + } + print {*STDOUT} "N inline :${n}\n"; + literal_data("mediawiki_revision: $commit{mw_revision}"); + print {*STDOUT} "\n\n"; + return; +} + +# parse a sequence of +# <cmd> <arg1> +# <cmd> <arg2> +# \n +# (like batch sequence of import and sequence of push statements) +sub get_more_refs { + my $cmd = shift; + my @refs; + while (1) { + my $line = <STDIN>; + if ($line =~ /^$cmd (.*)$/) { + push(@refs, $1); + } elsif ($line eq "\n") { + return @refs; + } else { + die("Invalid command in a '$cmd' batch: $_\n"); + } + } + return; +} + +sub mw_import { + # multiple import commands can follow each other. + my @refs = (shift, get_more_refs('import')); + foreach my $ref (@refs) { + mw_import_ref($ref); + } + print {*STDOUT} "done\n"; + return; +} + +sub mw_import_ref { + my $ref = shift; + # The remote helper will call "import HEAD" and + # "import refs/heads/master". + # Since HEAD is a symbolic ref to master (by convention, + # followed by the output of the command "list" that we gave), + # we don't need to do anything in this case. + if ($ref eq 'HEAD') { + return; + } + + $mediawiki = connect_maybe($mediawiki, $remotename, $url); + + print {*STDERR} "Searching revisions...\n"; + my $last_local = get_last_local_revision(); + my $fetch_from = $last_local + 1; + if ($fetch_from == 1) { + print {*STDERR} ", fetching from beginning.\n"; + } else { + print {*STDERR} ", fetching from here.\n"; + } + + my $n = 0; + if ($fetch_strategy eq 'by_rev') { + print {*STDERR} "Fetching & writing export data by revs...\n"; + $n = mw_import_ref_by_revs($fetch_from); + } elsif ($fetch_strategy eq 'by_page') { + print {*STDERR} "Fetching & writing export data by pages...\n"; + $n = mw_import_ref_by_pages($fetch_from); + } else { + print {*STDERR} qq(fatal: invalid fetch strategy "${fetch_strategy}".\n); + print {*STDERR} "Check your configuration variables remote.${remotename}.fetchStrategy and mediawiki.fetchStrategy\n"; + exit 1; + } + + if ($fetch_from == 1 && $n == 0) { + print {*STDERR} "You appear to have cloned an empty MediaWiki.\n"; + # Something has to be done remote-helper side. If nothing is done, an error is + # thrown saying that HEAD is referring to unknown object 0000000000000000000 + # and the clone fails. + } + return; +} + +sub mw_import_ref_by_pages { + + my $fetch_from = shift; + my %pages_hash = get_mw_pages(); + my @pages = values(%pages_hash); + + my ($n, @revisions) = fetch_mw_revisions(\@pages, $fetch_from); + + @revisions = sort {$a->{revid} <=> $b->{revid}} @revisions; + my @revision_ids = map { $_->{revid} } @revisions; + + return mw_import_revids($fetch_from, \@revision_ids, \%pages_hash); +} + +sub mw_import_ref_by_revs { + + my $fetch_from = shift; + my %pages_hash = get_mw_pages(); + + my $last_remote = get_last_global_remote_rev(); + my @revision_ids = $fetch_from..$last_remote; + return mw_import_revids($fetch_from, \@revision_ids, \%pages_hash); +} + +# Import revisions given in second argument (array of integers). +# Only pages appearing in the third argument (hash indexed by page titles) +# will be imported. +sub mw_import_revids { + my $fetch_from = shift; + my $revision_ids = shift; + my $pages = shift; + + my $n = 0; + my $n_actual = 0; + my $last_timestamp = 0; # Placeholder in case $rev->timestamp is undefined + + foreach my $pagerevid (@{$revision_ids}) { + # Count page even if we skip it, since we display + # $n/$total and $total includes skipped pages. + $n++; + + # fetch the content of the pages + my $query = { + action => 'query', + prop => 'revisions', + rvprop => 'content|timestamp|comment|user|ids', + revids => $pagerevid, + }; + + my $result = $mediawiki->api($query); + + if (!$result) { + die "Failed to retrieve modified page for revision $pagerevid\n"; + } + + if (defined($result->{query}->{badrevids}->{$pagerevid})) { + # The revision id does not exist on the remote wiki. + next; + } + + if (!defined($result->{query}->{pages})) { + die "Invalid revision ${pagerevid}.\n"; + } + + my @result_pages = values(%{$result->{query}->{pages}}); + my $result_page = $result_pages[0]; + my $rev = $result_pages[0]->{revisions}->[0]; + + my $page_title = $result_page->{title}; + + if (!exists($pages->{$page_title})) { + print {*STDERR} "${n}/", scalar(@{$revision_ids}), + ": Skipping revision #$rev->{revid} of ${page_title}\n"; + next; + } + + $n_actual++; + + my %commit; + $commit{author} = $rev->{user} || 'Anonymous'; + $commit{comment} = $rev->{comment} || EMPTY_MESSAGE; + $commit{title} = smudge_filename($page_title); + $commit{mw_revision} = $rev->{revid}; + $commit{content} = mediawiki_smudge($rev->{'*'}); + + if (!defined($rev->{timestamp})) { + $last_timestamp++; + } else { + $last_timestamp = $rev->{timestamp}; + } + $commit{date} = DateTime::Format::ISO8601->parse_datetime($last_timestamp); + + # Differentiates classic pages and media files. + my ($namespace, $filename) = $page_title =~ /^([^:]*):(.*)$/; + my %mediafile; + if ($namespace) { + my $id = get_mw_namespace_id($namespace); + if ($id && $id == get_mw_namespace_id('File')) { + %mediafile = get_mw_mediafile_for_page_revision($filename, $rev->{timestamp}); + } + } + # If this is a revision of the media page for new version + # of a file do one common commit for both file and media page. + # Else do commit only for that page. + print {*STDERR} "${n}/", scalar(@{$revision_ids}), ": Revision #$rev->{revid} of $commit{title}\n"; + import_file_revision(\%commit, ($fetch_from == 1), $n_actual, \%mediafile); + } + + return $n_actual; +} + +sub error_non_fast_forward { + my $advice = run_git('config --bool advice.pushNonFastForward'); + chomp($advice); + if ($advice ne 'false') { + # Native git-push would show this after the summary. + # We can't ask it to display it cleanly, so print it + # ourselves before. + print {*STDERR} "To prevent you from losing history, non-fast-forward updates were rejected\n"; + print {*STDERR} "Merge the remote changes (e.g. 'git pull') before pushing again. See the\n"; + print {*STDERR} "'Note about fast-forwards' section of 'git push --help' for details.\n"; + } + print {*STDOUT} qq(error $_[0] "non-fast-forward"\n); + return 0; +} + +sub mw_upload_file { + my $complete_file_name = shift; + my $new_sha1 = shift; + my $extension = shift; + my $file_deleted = shift; + my $summary = shift; + my $newrevid; + my $path = "File:${complete_file_name}"; + my %hashFiles = get_allowed_file_extensions(); + if (!exists($hashFiles{$extension})) { + print {*STDERR} "${complete_file_name} is not a permitted file on this wiki.\n"; + print {*STDERR} "Check the configuration of file uploads in your mediawiki.\n"; + return $newrevid; + } + # Deleting and uploading a file requires a privileged user + if ($file_deleted) { + $mediawiki = connect_maybe($mediawiki, $remotename, $url); + my $query = { + action => 'delete', + title => $path, + reason => $summary + }; + if (!$mediawiki->edit($query)) { + print {*STDERR} "Failed to delete file on remote wiki\n"; + print {*STDERR} "Check your permissions on the remote site. Error code:\n"; + print {*STDERR} $mediawiki->{error}->{code} . ':' . $mediawiki->{error}->{details}; + exit 1; + } + } else { + # Don't let perl try to interpret file content as UTF-8 => use "raw" + my $content = run_git("cat-file blob ${new_sha1}", 'raw'); + if ($content ne EMPTY) { + $mediawiki = connect_maybe($mediawiki, $remotename, $url); + $mediawiki->{config}->{upload_url} = + "${url}/index.php/Special:Upload"; + $mediawiki->edit({ + action => 'upload', + filename => $complete_file_name, + comment => $summary, + file => [undef, + $complete_file_name, + Content => $content], + ignorewarnings => 1, + }, { + skip_encoding => 1 + } ) || die $mediawiki->{error}->{code} . ':' + . $mediawiki->{error}->{details} . "\n"; + my $last_file_page = $mediawiki->get_page({title => $path}); + $newrevid = $last_file_page->{revid}; + print {*STDERR} "Pushed file: ${new_sha1} - ${complete_file_name}.\n"; + } else { + print {*STDERR} "Empty file ${complete_file_name} not pushed.\n"; + } + } + return $newrevid; +} + +sub mw_push_file { + my $diff_info = shift; + # $diff_info contains a string in this format: + # 100644 100644 <sha1_of_blob_before_commit> <sha1_of_blob_now> <status> + my @diff_info_split = split(/[ \t]/, $diff_info); + + # Filename, including .mw extension + my $complete_file_name = shift; + # Commit message + my $summary = shift; + # MediaWiki revision number. Keep the previous one by default, + # in case there's no edit to perform. + my $oldrevid = shift; + my $newrevid; + + if ($summary eq EMPTY_MESSAGE) { + $summary = EMPTY; + } + + my $new_sha1 = $diff_info_split[3]; + my $old_sha1 = $diff_info_split[2]; + my $page_created = ($old_sha1 eq NULL_SHA1); + my $page_deleted = ($new_sha1 eq NULL_SHA1); + $complete_file_name = clean_filename($complete_file_name); + + my ($title, $extension) = $complete_file_name =~ /^(.*)\.([^\.]*)$/; + if (!defined($extension)) { + $extension = EMPTY; + } + if ($extension eq 'mw') { + my $ns = get_mw_namespace_id_for_page($complete_file_name); + if ($ns && $ns == get_mw_namespace_id('File') && (!$export_media)) { + print {*STDERR} "Ignoring media file related page: ${complete_file_name}\n"; + return ($oldrevid, 'ok'); + } + my $file_content; + if ($page_deleted) { + # Deleting a page usually requires + # special privileges. A common + # convention is to replace the page + # with this content instead: + $file_content = DELETED_CONTENT; + } else { + $file_content = run_git("cat-file blob ${new_sha1}"); + } + + $mediawiki = connect_maybe($mediawiki, $remotename, $url); + + my $result = $mediawiki->edit( { + action => 'edit', + summary => $summary, + title => $title, + basetimestamp => $basetimestamps{$oldrevid}, + text => mediawiki_clean($file_content, $page_created), + }, { + skip_encoding => 1 # Helps with names with accentuated characters + }); + if (!$result) { + if ($mediawiki->{error}->{code} == 3) { + # edit conflicts, considered as non-fast-forward + print {*STDERR} 'Warning: Error ' . + $mediawiki->{error}->{code} . + ' from mediawiki: ' . $mediawiki->{error}->{details} . + ".\n"; + return ($oldrevid, 'non-fast-forward'); + } else { + # Other errors. Shouldn't happen => just die() + die 'Fatal: Error ' . + $mediawiki->{error}->{code} . + ' from mediawiki: ' . $mediawiki->{error}->{details} . "\n"; + } + } + $newrevid = $result->{edit}->{newrevid}; + print {*STDERR} "Pushed file: ${new_sha1} - ${title}\n"; + } elsif ($export_media) { + $newrevid = mw_upload_file($complete_file_name, $new_sha1, + $extension, $page_deleted, + $summary); + } else { + print {*STDERR} "Ignoring media file ${title}\n"; + } + $newrevid = ($newrevid or $oldrevid); + return ($newrevid, 'ok'); +} + +sub mw_push { + # multiple push statements can follow each other + my @refsspecs = (shift, get_more_refs('push')); + my $pushed; + for my $refspec (@refsspecs) { + my ($force, $local, $remote) = $refspec =~ /^(\+)?([^:]*):([^:]*)$/ + or die("Invalid refspec for push. Expected <src>:<dst> or +<src>:<dst>\n"); + if ($force) { + print {*STDERR} "Warning: forced push not allowed on a MediaWiki.\n"; + } + if ($local eq EMPTY) { + print {*STDERR} "Cannot delete remote branch on a MediaWiki\n"; + print {*STDOUT} "error ${remote} cannot delete\n"; + next; + } + if ($remote ne 'refs/heads/master') { + print {*STDERR} "Only push to the branch 'master' is supported on a MediaWiki\n"; + print {*STDOUT} "error ${remote} only master allowed\n"; + next; + } + if (mw_push_revision($local, $remote)) { + $pushed = 1; + } + } + + # Notify Git that the push is done + print {*STDOUT} "\n"; + + if ($pushed && $dumb_push) { + print {*STDERR} "Just pushed some revisions to MediaWiki.\n"; + print {*STDERR} "The pushed revisions now have to be re-imported, and your current branch\n"; + print {*STDERR} "needs to be updated with these re-imported commits. You can do this with\n"; + print {*STDERR} "\n"; + print {*STDERR} " git pull --rebase\n"; + print {*STDERR} "\n"; + } + return; +} + +sub mw_push_revision { + my $local = shift; + my $remote = shift; # actually, this has to be "refs/heads/master" at this point. + my $last_local_revid = get_last_local_revision(); + print {*STDERR} ".\n"; # Finish sentence started by get_last_local_revision() + my $last_remote_revid = get_last_remote_revision(); + my $mw_revision = $last_remote_revid; + + # Get sha1 of commit pointed by local HEAD + my $HEAD_sha1 = run_git("rev-parse ${local} 2>/dev/null"); + chomp($HEAD_sha1); + # Get sha1 of commit pointed by remotes/$remotename/master + my $remoteorigin_sha1 = run_git("rev-parse refs/remotes/${remotename}/master 2>/dev/null"); + chomp($remoteorigin_sha1); + + if ($last_local_revid > 0 && + $last_local_revid < $last_remote_revid) { + return error_non_fast_forward($remote); + } + + if ($HEAD_sha1 eq $remoteorigin_sha1) { + # nothing to push + return 0; + } + + # Get every commit in between HEAD and refs/remotes/origin/master, + # including HEAD and refs/remotes/origin/master + my @commit_pairs = (); + if ($last_local_revid > 0) { + my $parsed_sha1 = $remoteorigin_sha1; + # Find a path from last MediaWiki commit to pushed commit + print {*STDERR} "Computing path from local to remote ...\n"; + my @local_ancestry = split(/\n/, run_git("rev-list --boundary --parents ${local} ^${parsed_sha1}")); + my %local_ancestry; + foreach my $line (@local_ancestry) { + if (my ($child, $parents) = $line =~ /^-?([a-f0-9]+) ([a-f0-9 ]+)/) { + foreach my $parent (split(/ /, $parents)) { + $local_ancestry{$parent} = $child; + } + } elsif (!$line =~ /^([a-f0-9]+)/) { + die "Unexpected output from git rev-list: ${line}\n"; + } + } + while ($parsed_sha1 ne $HEAD_sha1) { + my $child = $local_ancestry{$parsed_sha1}; + if (!$child) { + print {*STDERR} "Cannot find a path in history from remote commit to last commit\n"; + return error_non_fast_forward($remote); + } + push(@commit_pairs, [$parsed_sha1, $child]); + $parsed_sha1 = $child; + } + } else { + # No remote mediawiki revision. Export the whole + # history (linearized with --first-parent) + print {*STDERR} "Warning: no common ancestor, pushing complete history\n"; + my $history = run_git("rev-list --first-parent --children ${local}"); + my @history = split(/\n/, $history); + @history = @history[1..$#history]; + foreach my $line (reverse @history) { + my @commit_info_split = split(/[ \n]/, $line); + push(@commit_pairs, \@commit_info_split); + } + } + + foreach my $commit_info_split (@commit_pairs) { + my $sha1_child = @{$commit_info_split}[0]; + my $sha1_commit = @{$commit_info_split}[1]; + my $diff_infos = run_git("diff-tree -r --raw -z ${sha1_child} ${sha1_commit}"); + # TODO: we could detect rename, and encode them with a #redirect on the wiki. + # TODO: for now, it's just a delete+add + my @diff_info_list = split(/\0/, $diff_infos); + # Keep the subject line of the commit message as mediawiki comment for the revision + my $commit_msg = run_git(qq(log --no-walk --format="%s" ${sha1_commit})); + chomp($commit_msg); + # Push every blob + while (@diff_info_list) { + my $status; + # git diff-tree -z gives an output like + # <metadata>\0<filename1>\0 + # <metadata>\0<filename2>\0 + # and we've split on \0. + my $info = shift(@diff_info_list); + my $file = shift(@diff_info_list); + ($mw_revision, $status) = mw_push_file($info, $file, $commit_msg, $mw_revision); + if ($status eq 'non-fast-forward') { + # we may already have sent part of the + # commit to MediaWiki, but it's too + # late to cancel it. Stop the push in + # the middle, but still give an + # accurate error message. + return error_non_fast_forward($remote); + } + if ($status ne 'ok') { + die("Unknown error from mw_push_file()\n"); + } + } + if (!$dumb_push) { + run_git(qq(notes --ref=${remotename}/mediawiki add -f -m "mediawiki_revision: ${mw_revision}" ${sha1_commit})); + } + } + + print {*STDOUT} "ok ${remote}\n"; + return 1; +} + +sub get_allowed_file_extensions { + $mediawiki = connect_maybe($mediawiki, $remotename, $url); + + my $query = { + action => 'query', + meta => 'siteinfo', + siprop => 'fileextensions' + }; + my $result = $mediawiki->api($query); + my @file_extensions = map { $_->{ext}} @{$result->{query}->{fileextensions}}; + my %hashFile = map { $_ => 1 } @file_extensions; + + return %hashFile; +} + +# In memory cache for MediaWiki namespace ids. +my %namespace_id; + +# Namespaces whose id is cached in the configuration file +# (to avoid duplicates) +my %cached_mw_namespace_id; + +# Return MediaWiki id for a canonical namespace name. +# Ex.: "File", "Project". +sub get_mw_namespace_id { + $mediawiki = connect_maybe($mediawiki, $remotename, $url); + my $name = shift; + + if (!exists $namespace_id{$name}) { + # Look at configuration file, if the record for that namespace is + # already cached. Namespaces are stored in form: + # "Name_of_namespace:Id_namespace", ex.: "File:6". + my @temp = split(/\n/, + run_git("config --get-all remote.${remotename}.namespaceCache")); + chomp(@temp); + foreach my $ns (@temp) { + my ($n, $id) = split(/:/, $ns); + if ($id eq 'notANameSpace') { + $namespace_id{$n} = {is_namespace => 0}; + } else { + $namespace_id{$n} = {is_namespace => 1, id => $id}; + } + $cached_mw_namespace_id{$n} = 1; + } + } + + if (!exists $namespace_id{$name}) { + print {*STDERR} "Namespace ${name} not found in cache, querying the wiki ...\n"; + # NS not found => get namespace id from MW and store it in + # configuration file. + my $query = { + action => 'query', + meta => 'siteinfo', + siprop => 'namespaces' + }; + my $result = $mediawiki->api($query); + + while (my ($id, $ns) = each(%{$result->{query}->{namespaces}})) { + if (defined($ns->{id}) && defined($ns->{canonical})) { + $namespace_id{$ns->{canonical}} = {is_namespace => 1, id => $ns->{id}}; + if ($ns->{'*'}) { + # alias (e.g. french Fichier: as alias for canonical File:) + $namespace_id{$ns->{'*'}} = {is_namespace => 1, id => $ns->{id}}; + } + } + } + } + + my $ns = $namespace_id{$name}; + my $id; + + if (!defined $ns) { + my @namespaces = map { s/ /_/g; $_; } sort keys %namespace_id; + print {*STDERR} "No such namespace ${name} on MediaWiki, known namespaces: @namespaces\n"; + $ns = {is_namespace => 0}; + $namespace_id{$name} = $ns; + } + + if ($ns->{is_namespace}) { + $id = $ns->{id}; + } + + # Store "notANameSpace" as special value for inexisting namespaces + my $store_id = ($id || 'notANameSpace'); + + # Store explicitly requested namespaces on disk + if (!exists $cached_mw_namespace_id{$name}) { + run_git(qq(config --add remote.${remotename}.namespaceCache "${name}:${store_id}")); + $cached_mw_namespace_id{$name} = 1; + } + return $id; +} + +sub get_mw_namespace_id_for_page { + my $namespace = shift; + if ($namespace =~ /^([^:]*):/) { + return get_mw_namespace_id($namespace); + } else { + return; + } +} diff --git a/contrib/mw-to-git/git-remote-mediawiki.txt b/contrib/mw-to-git/git-remote-mediawiki.txt new file mode 100644 index 000000000000..23b7ef9f6208 --- /dev/null +++ b/contrib/mw-to-git/git-remote-mediawiki.txt @@ -0,0 +1,7 @@ +Git-Mediawiki is a project which aims the creation of a gate +between git and mediawiki, allowing git users to push and pull +objects from mediawiki just as one would do with a classic git +repository thanks to remote-helpers. + +For more information, visit the wiki at +https://github.com/moy/Git-Mediawiki/wiki diff --git a/contrib/mw-to-git/t/.gitignore b/contrib/mw-to-git/t/.gitignore new file mode 100644 index 000000000000..a7a40b49644f --- /dev/null +++ b/contrib/mw-to-git/t/.gitignore @@ -0,0 +1,4 @@ +WEB/ +wiki/ +trash directory.t*/ +test-results/ diff --git a/contrib/mw-to-git/t/Makefile b/contrib/mw-to-git/t/Makefile new file mode 100644 index 000000000000..f422203fa069 --- /dev/null +++ b/contrib/mw-to-git/t/Makefile @@ -0,0 +1,31 @@ +# +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# +## Test git-remote-mediawiki + +all: test + +-include ../../../config.mak.autogen +-include ../../../config.mak + +T = $(wildcard t[0-9][0-9][0-9][0-9]-*.sh) + +.PHONY: help test clean all + +help: + @echo 'Run "$(MAKE) test" to launch test scripts' + @echo 'Run "$(MAKE) clean" to remove trash folders' + +test: + @for t in $(T); do \ + echo "$$t"; \ + "./$$t" || exit 1; \ + done + +clean: + $(RM) -r 'trash directory'.* diff --git a/contrib/mw-to-git/t/README b/contrib/mw-to-git/t/README new file mode 100644 index 000000000000..2ee34be7e491 --- /dev/null +++ b/contrib/mw-to-git/t/README @@ -0,0 +1,124 @@ +Tests for Mediawiki-to-Git +========================== + +Introduction +------------ +This manual describes how to install the git-remote-mediawiki test +environment on a machine with git installed on it. + +Prerequisite +------------ + +In order to run this test environment correctly, you will need to +install the following packages (Debian/Ubuntu names, may need to be +adapted for another distribution): + +* lighttpd +* php5 +* php5-cgi +* php5-cli +* php5-curl +* php5-sqlite + +Principles and Technical Choices +-------------------------------- + +The test environment makes it easy to install and manipulate one or +several MediaWiki instances. To allow developers to run the testsuite +easily, the environment does not require root privilege (except to +install the required packages if needed). It starts a webserver +instance on the user's account (using lighttpd greatly helps for +that), and does not need a separate database daemon (thanks to the use +of sqlite). + +Run the test environment +------------------------ + +Install a new wiki +~~~~~~~~~~~~~~~~~~ + +Once you have all the prerequisite, you need to install a MediaWiki +instance on your machine. If you already have one, it is still +strongly recommended to install one with the script provided. Here's +how to work it: + +a. change directory to contrib/mw-to-git/t/ +b. if needed, edit test.config to choose your installation parameters +c. run `./install-wiki.sh install` +d. check on your favourite web browser if your wiki is correctly + installed. + +Remove an existing wiki +~~~~~~~~~~~~~~~~~~~~~~~ + +Edit the file test.config to fit the wiki you want to delete, and then +execute the command `./install-wiki.sh delete` from the +contrib/mw-to-git/t directory. + +Run the existing tests +~~~~~~~~~~~~~~~~~~~~~~ + +The provided tests are currently in the `contrib/mw-to-git/t` directory. +The files are all the t936[0-9]-*.sh shell scripts. + +a. Run all tests: +To do so, run "make test" from the contrib/mw-to-git/ directory. + +b. Run a specific test: +To run a given test <test_name>, run ./<test_name> from the +contrib/mw-to-git/t directory. + +How to create new tests +----------------------- + +Available functions +~~~~~~~~~~~~~~~~~~~ + +The test environment of git-remote-mediawiki provides some functions +useful to test its behaviour. for more details about the functions' +parameters, please refer to the `test-gitmw-lib.sh` and +`test-gitmw.pl` files. + +** `test_check_wiki_precond`: +Check if the tests must be skipped or not. Please use this function +at the beginning of each new test file. + +** `wiki_getpage`: +Fetch a given page from the wiki and puts its content in the +directory in parameter. + +** `wiki_delete_page`: +Delete a given page from the wiki. + +** `wiki_edit_page`: +Create or modify a given page in the wiki. You can specify several +parameters like a summary for the page edition, or add the page to a +given category. +See test-gitmw.pl for more details. + +** `wiki_getallpage`: +Fetch all pages from the wiki into a given directory. The directory +is created if it does not exists. + +** `test_diff_directories`: +Compare the content of two directories. The content must be the same. +Use this function to compare the content of a git directory and a wiki +one created by wiki_getallpage. + +** `test_contains_N_files`: +Check if the given directory contains a given number of file. + +** `wiki_page_exists`: +Tests if a given page exists on the wiki. + +** `wiki_reset`: +Reset the wiki, i.e. flush the database. Use this function at the +beginning of each new test, except if the test re-uses the same wiki +(and history) as the previous test. + +How to write a new test +~~~~~~~~~~~~~~~~~~~~~~~ + +Please, follow the standards given by git. See git/t/README. +New file should be named as t936[0-9]-*.sh. +Be sure to reset your wiki regularly with the function `wiki_reset`. diff --git a/contrib/mw-to-git/t/install-wiki.sh b/contrib/mw-to-git/t/install-wiki.sh new file mode 100755 index 000000000000..c215213c4bfd --- /dev/null +++ b/contrib/mw-to-git/t/install-wiki.sh @@ -0,0 +1,55 @@ +#!/bin/sh + +# This script installs or deletes a MediaWiki on your computer. +# It requires a web server with PHP and SQLite running. In addition, if you +# do not have MediaWiki sources on your computer, the option 'install' +# downloads them for you. +# Please set the CONFIGURATION VARIABLES in ./test-gitmw-lib.sh + +WIKI_TEST_DIR=$(cd "$(dirname "$0")" && pwd) + +if test -z "$WIKI_TEST_DIR" +then + WIKI_TEST_DIR=. +fi + +. "$WIKI_TEST_DIR"/test-gitmw-lib.sh +usage () { + echo "usage: " + echo " ./install-wiki.sh <install | delete | --help>" + echo " install | -i : Install a wiki on your computer." + echo " delete | -d : Delete the wiki and all its pages and " + echo " content." + echo " start | -s : Start the previously configured lighttpd daemon" + echo " stop : Stop lighttpd daemon." +} + + +# Argument: install, delete, --help | -h +case "$1" in + "install" | "-i") + wiki_install + exit 0 + ;; + "delete" | "-d") + wiki_delete + exit 0 + ;; + "start" | "-s") + start_lighttpd + exit + ;; + "stop") + stop_lighttpd + exit + ;; + "--help" | "-h") + usage + exit 0 + ;; + *) + echo "Invalid argument: $1" + usage + exit 1 + ;; +esac diff --git a/contrib/mw-to-git/t/install-wiki/.gitignore b/contrib/mw-to-git/t/install-wiki/.gitignore new file mode 100644 index 000000000000..b5a2a4408c59 --- /dev/null +++ b/contrib/mw-to-git/t/install-wiki/.gitignore @@ -0,0 +1 @@ +wikidb.sqlite diff --git a/contrib/mw-to-git/t/install-wiki/LocalSettings.php b/contrib/mw-to-git/t/install-wiki/LocalSettings.php new file mode 100644 index 000000000000..745e47e88173 --- /dev/null +++ b/contrib/mw-to-git/t/install-wiki/LocalSettings.php @@ -0,0 +1,129 @@ +<?php +# This file was automatically generated by the MediaWiki 1.19.0 +# installer. If you make manual changes, please keep track in case you +# need to recreate them later. +# +# See includes/DefaultSettings.php for all configurable settings +# and their default values, but don't forget to make changes in _this_ +# file, not there. +# +# Further documentation for configuration settings may be found at: +# http://www.mediawiki.org/wiki/Manual:Configuration_settings + +# Protect against web entry +if ( !defined( 'MEDIAWIKI' ) ) { + exit; +} + +## Uncomment this to disable output compression +# $wgDisableOutputCompression = true; + +$wgSitename = "Git-MediaWiki-Test"; +$wgMetaNamespace = "Git-MediaWiki-Test"; + +## The URL base path to the directory containing the wiki; +## defaults for all runtime URL paths are based off of this. +## For more information on customizing the URLs please see: +## http://www.mediawiki.org/wiki/Manual:Short_URL +$wgScriptPath = "@WG_SCRIPT_PATH@"; +$wgScriptExtension = ".php"; + +## The protocol and server name to use in fully-qualified URLs +$wgServer = "@WG_SERVER@"; + +## The relative URL path to the skins directory +$wgStylePath = "$wgScriptPath/skins"; + +## The relative URL path to the logo. Make sure you change this from the default, +## or else you'll overwrite your logo when you upgrade! +$wgLogo = "$wgStylePath/common/images/wiki.png"; + +## UPO means: this is also a user preference option + +$wgEnableEmail = true; +$wgEnableUserEmail = true; # UPO + +$wgEmergencyContact = "apache@localhost"; +$wgPasswordSender = "apache@localhost"; + +$wgEnotifUserTalk = false; # UPO +$wgEnotifWatchlist = false; # UPO +$wgEmailAuthentication = true; + +## Database settings +$wgDBtype = "sqlite"; +$wgDBserver = ""; +$wgDBname = "@WG_SQLITE_DATAFILE@"; +$wgDBuser = ""; +$wgDBpassword = ""; + +# SQLite-specific settings +$wgSQLiteDataDir = "@WG_SQLITE_DATADIR@"; + + +## Shared memory settings +$wgMainCacheType = CACHE_NONE; +$wgMemCachedServers = array(); + +## To enable image uploads, make sure the 'images' directory +## is writable, then set this to true: +$wgEnableUploads = true; +$wgUseImageMagick = true; +$wgImageMagickConvertCommand ="@CONVERT@"; +$wgFileExtensions[] = 'txt'; + +# InstantCommons allows wiki to use images from http://commons.wikimedia.org +$wgUseInstantCommons = false; + +## If you use ImageMagick (or any other shell command) on a +## Linux server, this will need to be set to the name of an +## available UTF-8 locale +$wgShellLocale = "en_US.utf8"; + +## If you want to use image uploads under safe mode, +## create the directories images/archive, images/thumb and +## images/temp, and make them all writable. Then uncomment +## this, if it's not already uncommented: +#$wgHashedUploadDirectory = false; + +## Set $wgCacheDirectory to a writable directory on the web server +## to make your wiki go slightly faster. The directory should not +## be publicly accessible from the web. +#$wgCacheDirectory = "$IP/cache"; + +# Site language code, should be one of the list in ./languages/Names.php +$wgLanguageCode = "en"; + +$wgSecretKey = "1c912bfe3519fb70f5dc523ecc698111cd43d81a11c585b3eefb28f29c2699b7"; +#$wgSecretKey = "@SECRETKEY@"; + + +# Site upgrade key. Must be set to a string (default provided) to turn on the +# web installer while LocalSettings.php is in place +$wgUpgradeKey = "ddae7dc87cd0a645"; + +## Default skin: you can change the default skin. Use the internal symbolic +## names, ie 'standard', 'nostalgia', 'cologneblue', 'monobook', 'vector': +$wgDefaultSkin = "vector"; + +## For attaching licensing metadata to pages, and displaying an +## appropriate copyright notice / icon. GNU Free Documentation +## License and Creative Commons licenses are supported so far. +$wgRightsPage = ""; # Set to the title of a wiki page that describes your license/copyright +$wgRightsUrl = ""; +$wgRightsText = ""; +$wgRightsIcon = ""; + +# Path to the GNU diff3 utility. Used for conflict resolution. +$wgDiff3 = "/usr/bin/diff3"; + +# Query string length limit for ResourceLoader. You should only set this if +# your web server has a query string length limit (then set it to that limit), +# or if you have suhosin.get.max_value_length set in php.ini (then set it to +# that value) +$wgResourceLoaderMaxQueryLength = -1; + + + +# End of automatically generated settings. +# Add more configuration options below. diff --git a/contrib/mw-to-git/t/install-wiki/db_install.php b/contrib/mw-to-git/t/install-wiki/db_install.php new file mode 100644 index 000000000000..0f3f4e018a05 --- /dev/null +++ b/contrib/mw-to-git/t/install-wiki/db_install.php @@ -0,0 +1,120 @@ +<?php +/** + * This script generates a SQLite database for a MediaWiki version 1.19.0 + * You must specify the login of the admin (argument 1) and its + * password (argument 2) and the folder where the database file + * is located (absolute path in argument 3). + * It is used by the script install-wiki.sh in order to make easy the + * installation of a MediaWiki. + * + * In order to generate a SQLite database file, MediaWiki ask the user + * to submit some forms in its web browser. This script simulates this + * behavior though the functions <get> and <submit> + * + */ +$argc = $_SERVER['argc']; +$argv = $_SERVER['argv']; + +$login = $argv[2]; +$pass = $argv[3]; +$tmp = $argv[4]; +$port = $argv[5]; + +$url = 'http://localhost:'.$port.'/wiki/mw-config/index.php'; +$db_dir = urlencode($tmp); +$tmp_cookie = tempnam($tmp, "COOKIE_"); +/* + * Fetchs a page with cURL. + */ +function get($page_name = "") { + $curl = curl_init(); + $page_name_add = ""; + if ($page_name != "") { + $page_name_add = '?page='.$page_name; + } + $url = $GLOBALS['url'].$page_name_add; + $tmp_cookie = $GLOBALS['tmp_cookie']; + curl_setopt($curl, CURLOPT_COOKIEJAR, $tmp_cookie); + curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); + curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true); + curl_setopt($curl, CURLOPT_COOKIEFILE, $tmp_cookie); + curl_setopt($curl, CURLOPT_HEADER, true); + curl_setopt($curl, CURLOPT_URL, $url); + + $page = curl_exec($curl); + if (!$page) { + die("Could not get page: $url\n"); + } + curl_close($curl); + return $page; +} + +/* + * Submits a form with cURL. + */ +function submit($page_name, $option = "") { + $curl = curl_init(); + $datapost = 'submit-continue=Continue+%E2%86%92'; + if ($option != "") { + $datapost = $option.'&'.$datapost; + } + $url = $GLOBALS['url'].'?page='.$page_name; + $tmp_cookie = $GLOBALS['tmp_cookie']; + curl_setopt($curl, CURLOPT_URL, $url); + curl_setopt($curl, CURLOPT_POST, true); + curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true); + curl_setopt($curl, CURLOPT_POSTFIELDS, $datapost); + curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); + curl_setopt($curl, CURLOPT_COOKIEJAR, $tmp_cookie); + curl_setopt($curl, CURLOPT_COOKIEFILE, $tmp_cookie); + + $page = curl_exec($curl); + if (!$page) { + die("Could not get page: $url\n"); + } + curl_close($curl); + return "$page"; +} + +/* + * Here starts this script: simulates the behavior of the user + * submitting forms to generates the database file. + * Note this simulation was made for the MediaWiki version 1.19.0, + * we can't assume it works with other versions. + * + */ + +$page = get(); +if (!preg_match('/input type="hidden" value="([0-9]+)" name="LanguageRequestTime"/', + $page, $matches)) { + echo "Unexpected content for page downloaded:\n"; + echo "$page"; + die; +}; +$timestamp = $matches[1]; +$language = "LanguageRequestTime=$timestamp&uselang=en&ContLang=en"; +$page = submit('Language', $language); + +submit('Welcome'); + +$db_config = 'DBType=sqlite'; +$db_config = $db_config.'&sqlite_wgSQLiteDataDir='.$db_dir; +$db_config = $db_config.'&sqlite_wgDBname='.$argv[1]; +submit('DBConnect', $db_config); + +$wiki_config = 'config_wgSitename=TEST'; +$wiki_config = $wiki_config.'&config__NamespaceType=site-name'; +$wiki_config = $wiki_config.'&config_wgMetaNamespace=MyWiki'; +$wiki_config = $wiki_config.'&config__AdminName='.$login; + +$wiki_config = $wiki_config.'&config__AdminPassword='.$pass; +$wiki_config = $wiki_config.'&config__AdminPassword2='.$pass; + +$wiki_config = $wiki_config.'&wiki__configEmail=email%40email.org'; +$wiki_config = $wiki_config.'&config__SkipOptional=skip'; +submit('Name', $wiki_config); +submit('Install'); +submit('Install'); + +unlink($tmp_cookie); +?> diff --git a/contrib/mw-to-git/t/push-pull-tests.sh b/contrib/mw-to-git/t/push-pull-tests.sh new file mode 100644 index 000000000000..9da2dc5ff036 --- /dev/null +++ b/contrib/mw-to-git/t/push-pull-tests.sh @@ -0,0 +1,144 @@ +test_push_pull () { + + test_expect_success 'Git pull works after adding a new wiki page' ' + wiki_reset && + + git clone mediawiki::'"$WIKI_URL"' mw_dir_1 && + wiki_editpage Foo "page created after the git clone" false && + + ( + cd mw_dir_1 && + git pull + ) && + + wiki_getallpage ref_page_1 && + test_diff_directories mw_dir_1 ref_page_1 + ' + + test_expect_success 'Git pull works after editing a wiki page' ' + wiki_reset && + + wiki_editpage Foo "page created before the git clone" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_2 && + wiki_editpage Foo "new line added on the wiki" true && + + ( + cd mw_dir_2 && + git pull + ) && + + wiki_getallpage ref_page_2 && + test_diff_directories mw_dir_2 ref_page_2 + ' + + test_expect_success 'git pull works on conflict handled by auto-merge' ' + wiki_reset && + + wiki_editpage Foo "1 init +3 +5 + " false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_3 && + + wiki_editpage Foo "1 init +2 content added on wiki after clone +3 +5 + " false && + + ( + cd mw_dir_3 && + echo "1 init +3 +4 content added on git after clone +5 +" >Foo.mw && + git commit -am "conflicting change on foo" && + git pull && + git push + ) + ' + + test_expect_success 'Git push works after adding a file .mw' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_4 && + wiki_getallpage ref_page_4 && + ( + cd mw_dir_4 && + test_path_is_missing Foo.mw && + touch Foo.mw && + echo "hello world" >>Foo.mw && + git add Foo.mw && + git commit -m "Foo" && + git push + ) && + wiki_getallpage ref_page_4 && + test_diff_directories mw_dir_4 ref_page_4 + ' + + test_expect_success 'Git push works after editing a file .mw' ' + wiki_reset && + wiki_editpage "Foo" "page created before the git clone" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_5 && + + ( + cd mw_dir_5 && + echo "new line added in the file Foo.mw" >>Foo.mw && + git commit -am "edit file Foo.mw" && + git push + ) && + + wiki_getallpage ref_page_5 && + test_diff_directories mw_dir_5 ref_page_5 + ' + + test_expect_failure 'Git push works after deleting a file' ' + wiki_reset && + wiki_editpage Foo "wiki page added before git clone" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_6 && + + ( + cd mw_dir_6 && + git rm Foo.mw && + git commit -am "page Foo.mw deleted" && + git push + ) && + + test_must_fail wiki_page_exist Foo + ' + + test_expect_success 'Merge conflict expected and solving it' ' + wiki_reset && + + git clone mediawiki::'"$WIKI_URL"' mw_dir_7 && + wiki_editpage Foo "1 conflict +3 wiki +4" false && + + ( + cd mw_dir_7 && + echo "1 conflict +2 git +4" >Foo.mw && + git add Foo.mw && + git commit -m "conflict created" && + test_must_fail git pull && + "$PERL_PATH" -pi -e "s/[<=>].*//g" Foo.mw && + git commit -am "merge conflict solved" && + git push + ) + ' + + test_expect_failure 'git pull works after deleting a wiki page' ' + wiki_reset && + wiki_editpage Foo "wiki page added before the git clone" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_8 && + + wiki_delete_page Foo && + ( + cd mw_dir_8 && + git pull && + test_path_is_missing Foo.mw + ) + ' +} diff --git a/contrib/mw-to-git/t/t9360-mw-to-git-clone.sh b/contrib/mw-to-git/t/t9360-mw-to-git-clone.sh new file mode 100755 index 000000000000..cfbfe7ddf622 --- /dev/null +++ b/contrib/mw-to-git/t/t9360-mw-to-git-clone.sh @@ -0,0 +1,257 @@ +#!/bin/sh +# +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# +# License: GPL v2 or later + + +test_description='Test the Git Mediawiki remote helper: git clone' + +. ./test-gitmw-lib.sh +. $TEST_DIRECTORY/test-lib.sh + + +test_check_precond + + +test_expect_success 'Git clone creates the expected git log with one file' ' + wiki_reset && + wiki_editpage foo "this is not important" false -c cat -s "this must be the same" && + git clone mediawiki::'"$WIKI_URL"' mw_dir_1 && + ( + cd mw_dir_1 && + git log --format=%s HEAD^..HEAD >log.tmp + ) && + echo "this must be the same" >msg.tmp && + diff -b mw_dir_1/log.tmp msg.tmp +' + + +test_expect_success 'Git clone creates the expected git log with multiple files' ' + wiki_reset && + wiki_editpage daddy "this is not important" false -s="this must be the same" && + wiki_editpage daddy "neither is this" true -s="this must also be the same" && + wiki_editpage daddy "neither is this" true -s="same same same" && + wiki_editpage dj "dont care" false -s="identical" && + wiki_editpage dj "dont care either" true -s="identical too" && + git clone mediawiki::'"$WIKI_URL"' mw_dir_2 && + ( + cd mw_dir_2 && + git log --format=%s Daddy.mw >logDaddy.tmp && + git log --format=%s Dj.mw >logDj.tmp + ) && + echo "same same same" >msgDaddy.tmp && + echo "this must also be the same" >>msgDaddy.tmp && + echo "this must be the same" >>msgDaddy.tmp && + echo "identical too" >msgDj.tmp && + echo "identical" >>msgDj.tmp && + diff -b mw_dir_2/logDaddy.tmp msgDaddy.tmp && + diff -b mw_dir_2/logDj.tmp msgDj.tmp +' + + +test_expect_success 'Git clone creates only Main_Page.mw with an empty wiki' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_3 && + test_contains_N_files mw_dir_3 1 && + test_path_is_file mw_dir_3/Main_Page.mw +' + +test_expect_success 'Git clone does not fetch a deleted page' ' + wiki_reset && + wiki_editpage foo "this page must be deleted before the clone" false && + wiki_delete_page foo && + git clone mediawiki::'"$WIKI_URL"' mw_dir_4 && + test_contains_N_files mw_dir_4 1 && + test_path_is_file mw_dir_4/Main_Page.mw && + test_path_is_missing mw_dir_4/Foo.mw +' + +test_expect_success 'Git clone works with page added' ' + wiki_reset && + wiki_editpage foo " I will be cloned" false && + wiki_editpage bar "I will be cloned" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_5 && + wiki_getallpage ref_page_5 && + test_diff_directories mw_dir_5 ref_page_5 && + wiki_delete_page foo && + wiki_delete_page bar +' + +test_expect_success 'Git clone works with an edited page ' ' + wiki_reset && + wiki_editpage foo "this page will be edited" \ + false -s "first edition of page foo"&& + wiki_editpage foo "this page has been edited and must be on the clone " true && + git clone mediawiki::'"$WIKI_URL"' mw_dir_6 && + test_path_is_file mw_dir_6/Foo.mw && + test_path_is_file mw_dir_6/Main_Page.mw && + wiki_getallpage mw_dir_6/page_ref_6 && + test_diff_directories mw_dir_6 mw_dir_6/page_ref_6 && + ( + cd mw_dir_6 && + git log --format=%s HEAD^ Foo.mw > ../Foo.log + ) && + echo "first edition of page foo" > FooExpect.log && + diff FooExpect.log Foo.log +' + + +test_expect_success 'Git clone works with several pages and some deleted ' ' + wiki_reset && + wiki_editpage foo "this page will not be deleted" false && + wiki_editpage bar "I must not be erased" false && + wiki_editpage namnam "I will not be there at the end" false && + wiki_editpage nyancat "nyan nyan nyan delete me" false && + wiki_delete_page namnam && + wiki_delete_page nyancat && + git clone mediawiki::'"$WIKI_URL"' mw_dir_7 && + test_path_is_file mw_dir_7/Foo.mw && + test_path_is_file mw_dir_7/Bar.mw && + test_path_is_missing mw_dir_7/Namnam.mw && + test_path_is_missing mw_dir_7/Nyancat.mw && + wiki_getallpage mw_dir_7/page_ref_7 && + test_diff_directories mw_dir_7 mw_dir_7/page_ref_7 +' + + +test_expect_success 'Git clone works with one specific page cloned ' ' + wiki_reset && + wiki_editpage foo "I will not be cloned" false && + wiki_editpage bar "Do not clone me" false && + wiki_editpage namnam "I will be cloned :)" false -s="this log must stay" && + wiki_editpage nyancat "nyan nyan nyan you cant clone me" false && + git clone -c remote.origin.pages=namnam \ + mediawiki::'"$WIKI_URL"' mw_dir_8 && + test_contains_N_files mw_dir_8 1 && + test_path_is_file mw_dir_8/Namnam.mw && + test_path_is_missing mw_dir_8/Main_Page.mw && + ( + cd mw_dir_8 && + echo "this log must stay" >msg.tmp && + git log --format=%s >log.tmp && + diff -b msg.tmp log.tmp + ) && + wiki_check_content mw_dir_8/Namnam.mw Namnam +' + +test_expect_success 'Git clone works with multiple specific page cloned ' ' + wiki_reset && + wiki_editpage foo "I will be there" false && + wiki_editpage bar "I will not disapear" false && + wiki_editpage namnam "I be erased" false && + wiki_editpage nyancat "nyan nyan nyan you will not erase me" false && + wiki_delete_page namnam && + git clone -c remote.origin.pages="foo bar nyancat namnam" \ + mediawiki::'"$WIKI_URL"' mw_dir_9 && + test_contains_N_files mw_dir_9 3 && + test_path_is_missing mw_dir_9/Namnam.mw && + test_path_is_file mw_dir_9/Foo.mw && + test_path_is_file mw_dir_9/Nyancat.mw && + test_path_is_file mw_dir_9/Bar.mw && + wiki_check_content mw_dir_9/Foo.mw Foo && + wiki_check_content mw_dir_9/Bar.mw Bar && + wiki_check_content mw_dir_9/Nyancat.mw Nyancat +' + +test_expect_success 'Mediawiki-clone of several specific pages on wiki' ' + wiki_reset && + wiki_editpage foo "foo 1" false && + wiki_editpage bar "bar 1" false && + wiki_editpage dummy "dummy 1" false && + wiki_editpage cloned_1 "cloned_1 1" false && + wiki_editpage cloned_2 "cloned_2 2" false && + wiki_editpage cloned_3 "cloned_3 3" false && + mkdir -p ref_page_10 && + wiki_getpage cloned_1 ref_page_10 && + wiki_getpage cloned_2 ref_page_10 && + wiki_getpage cloned_3 ref_page_10 && + git clone -c remote.origin.pages="cloned_1 cloned_2 cloned_3" \ + mediawiki::'"$WIKI_URL"' mw_dir_10 && + test_diff_directories mw_dir_10 ref_page_10 +' + +test_expect_success 'Git clone works with the shallow option' ' + wiki_reset && + wiki_editpage foo "1st revision, should be cloned" false && + wiki_editpage bar "1st revision, should be cloned" false && + wiki_editpage nyan "1st revision, should not be cloned" false && + wiki_editpage nyan "2nd revision, should be cloned" false && + git -c remote.origin.shallow=true clone \ + mediawiki::'"$WIKI_URL"' mw_dir_11 && + test_contains_N_files mw_dir_11 4 && + test_path_is_file mw_dir_11/Nyan.mw && + test_path_is_file mw_dir_11/Foo.mw && + test_path_is_file mw_dir_11/Bar.mw && + test_path_is_file mw_dir_11/Main_Page.mw && + ( + cd mw_dir_11 && + test $(git log --oneline Nyan.mw | wc -l) -eq 1 && + test $(git log --oneline Foo.mw | wc -l) -eq 1 && + test $(git log --oneline Bar.mw | wc -l) -eq 1 && + test $(git log --oneline Main_Page.mw | wc -l ) -eq 1 + ) && + wiki_check_content mw_dir_11/Nyan.mw Nyan && + wiki_check_content mw_dir_11/Foo.mw Foo && + wiki_check_content mw_dir_11/Bar.mw Bar && + wiki_check_content mw_dir_11/Main_Page.mw Main_Page +' + +test_expect_success 'Git clone works with the shallow option with a delete page' ' + wiki_reset && + wiki_editpage foo "1st revision, will be deleted" false && + wiki_editpage bar "1st revision, should be cloned" false && + wiki_editpage nyan "1st revision, should not be cloned" false && + wiki_editpage nyan "2nd revision, should be cloned" false && + wiki_delete_page foo && + git -c remote.origin.shallow=true clone \ + mediawiki::'"$WIKI_URL"' mw_dir_12 && + test_contains_N_files mw_dir_12 3 && + test_path_is_file mw_dir_12/Nyan.mw && + test_path_is_missing mw_dir_12/Foo.mw && + test_path_is_file mw_dir_12/Bar.mw && + test_path_is_file mw_dir_12/Main_Page.mw && + ( + cd mw_dir_12 && + test $(git log --oneline Nyan.mw | wc -l) -eq 1 && + test $(git log --oneline Bar.mw | wc -l) -eq 1 && + test $(git log --oneline Main_Page.mw | wc -l ) -eq 1 + ) && + wiki_check_content mw_dir_12/Nyan.mw Nyan && + wiki_check_content mw_dir_12/Bar.mw Bar && + wiki_check_content mw_dir_12/Main_Page.mw Main_Page +' + +test_expect_success 'Test of fetching a category' ' + wiki_reset && + wiki_editpage Foo "I will be cloned" false -c=Category && + wiki_editpage Bar "Meet me on the repository" false -c=Category && + wiki_editpage Dummy "I will not come" false && + wiki_editpage BarWrong "I will stay online only" false -c=NotCategory && + git clone -c remote.origin.categories="Category" \ + mediawiki::'"$WIKI_URL"' mw_dir_13 && + wiki_getallpage ref_page_13 Category && + test_diff_directories mw_dir_13 ref_page_13 +' + +test_expect_success 'Test of resistance to modification of category on wiki for clone' ' + wiki_reset && + wiki_editpage Tobedeleted "this page will be deleted" false -c=Catone && + wiki_editpage Tobeedited "this page will be modified" false -c=Catone && + wiki_editpage Normalone "this page wont be modified and will be on git" false -c=Catone && + wiki_editpage Notconsidered "this page will not appear on local" false && + wiki_editpage Othercategory "this page will not appear on local" false -c=Cattwo && + wiki_editpage Tobeedited "this page have been modified" true -c=Catone && + wiki_delete_page Tobedeleted && + git clone -c remote.origin.categories="Catone" \ + mediawiki::'"$WIKI_URL"' mw_dir_14 && + wiki_getallpage ref_page_14 Catone && + test_diff_directories mw_dir_14 ref_page_14 +' + +test_done diff --git a/contrib/mw-to-git/t/t9361-mw-to-git-push-pull.sh b/contrib/mw-to-git/t/t9361-mw-to-git-push-pull.sh new file mode 100755 index 000000000000..9ea201459b53 --- /dev/null +++ b/contrib/mw-to-git/t/t9361-mw-to-git-push-pull.sh @@ -0,0 +1,24 @@ +#!/bin/sh +# +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# +# License: GPL v2 or later + +# tests for git-remote-mediawiki + +test_description='Test the Git Mediawiki remote helper: git push and git pull simple test cases' + +. ./test-gitmw-lib.sh +. ./push-pull-tests.sh +. $TEST_DIRECTORY/test-lib.sh + +test_check_precond + +test_push_pull + +test_done diff --git a/contrib/mw-to-git/t/t9362-mw-to-git-utf8.sh b/contrib/mw-to-git/t/t9362-mw-to-git-utf8.sh new file mode 100755 index 000000000000..6b0dbdac4d35 --- /dev/null +++ b/contrib/mw-to-git/t/t9362-mw-to-git-utf8.sh @@ -0,0 +1,347 @@ +#!/bin/sh +# +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# +# License: GPL v2 or later + +# tests for git-remote-mediawiki + +test_description='Test git-mediawiki with special characters in filenames' + +. ./test-gitmw-lib.sh +. $TEST_DIRECTORY/test-lib.sh + + +test_check_precond + + +test_expect_success 'Git clone works for a wiki with accents in the page names' ' + wiki_reset && + wiki_editpage féé "This page must be délétéd before clone" false && + wiki_editpage kèè "This page must be deleted before clone" false && + wiki_editpage hàà "This page must be deleted before clone" false && + wiki_editpage kîî "This page must be deleted before clone" false && + wiki_editpage foo "This page must be deleted before clone" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_1 && + wiki_getallpage ref_page_1 && + test_diff_directories mw_dir_1 ref_page_1 +' + + +test_expect_success 'Git pull works with a wiki with accents in the pages names' ' + wiki_reset && + wiki_editpage kîî "this page must be cloned" false && + wiki_editpage foo "this page must be cloned" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_2 && + wiki_editpage éàîôû "This page must be pulled" false && + ( + cd mw_dir_2 && + git pull + ) && + wiki_getallpage ref_page_2 && + test_diff_directories mw_dir_2 ref_page_2 +' + + +test_expect_success 'Cloning a chosen page works with accents' ' + wiki_reset && + wiki_editpage kîî "this page must be cloned" false && + git clone -c remote.origin.pages=kîî \ + mediawiki::'"$WIKI_URL"' mw_dir_3 && + wiki_check_content mw_dir_3/Kîî.mw Kîî && + test_path_is_file mw_dir_3/Kîî.mw && + rm -rf mw_dir_3 +' + + +test_expect_success 'The shallow option works with accents' ' + wiki_reset && + wiki_editpage néoà "1st revision, should not be cloned" false && + wiki_editpage néoà "2nd revision, should be cloned" false && + git -c remote.origin.shallow=true clone \ + mediawiki::'"$WIKI_URL"' mw_dir_4 && + test_contains_N_files mw_dir_4 2 && + test_path_is_file mw_dir_4/Néoà.mw && + test_path_is_file mw_dir_4/Main_Page.mw && + ( + cd mw_dir_4 && + test $(git log --oneline Néoà.mw | wc -l) -eq 1 && + test $(git log --oneline Main_Page.mw | wc -l ) -eq 1 + ) && + wiki_check_content mw_dir_4/Néoà.mw Néoà && + wiki_check_content mw_dir_4/Main_Page.mw Main_Page +' + + +test_expect_success 'Cloning works when page name first letter has an accent' ' + wiki_reset && + wiki_editpage îî "this page must be cloned" false && + git clone -c remote.origin.pages=îî \ + mediawiki::'"$WIKI_URL"' mw_dir_5 && + test_path_is_file mw_dir_5/Îî.mw && + wiki_check_content mw_dir_5/Îî.mw Îî +' + + +test_expect_success 'Git push works with a wiki with accents' ' + wiki_reset && + wiki_editpage féé "lots of accents : éèàÖ" false && + wiki_editpage foo "this page must be cloned" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_6 && + ( + cd mw_dir_6 && + echo "A wild Pîkächû appears on the wiki" >Pîkächû.mw && + git add Pîkächû.mw && + git commit -m "A new page appears" && + git push + ) && + wiki_getallpage ref_page_6 && + test_diff_directories mw_dir_6 ref_page_6 +' + +test_expect_success 'Git clone works with accentsand spaces' ' + wiki_reset && + wiki_editpage "é à î" "this page must be délété before the clone" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_7 && + wiki_getallpage ref_page_7 && + test_diff_directories mw_dir_7 ref_page_7 +' + +test_expect_success 'character $ in page name (mw -> git)' ' + wiki_reset && + wiki_editpage file_\$_foo "expect to be called file_$_foo" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_8 && + test_path_is_file mw_dir_8/File_\$_foo.mw && + wiki_getallpage ref_page_8 && + test_diff_directories mw_dir_8 ref_page_8 +' + + + +test_expect_success 'character $ in file name (git -> mw) ' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_9 && + ( + cd mw_dir_9 && + echo "this file is called File_\$_foo.mw" >File_\$_foo.mw && + git add . && + git commit -am "file File_\$_foo.mw" && + git pull && + git push + ) && + wiki_getallpage ref_page_9 && + test_diff_directories mw_dir_9 ref_page_9 +' + + +test_expect_failure 'capital at the beginning of file names' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_10 && + ( + cd mw_dir_10 && + echo "my new file foo" >foo.mw && + echo "my new file Foo... Finger crossed" >Foo.mw && + git add . && + git commit -am "file foo.mw" && + git pull && + git push + ) && + wiki_getallpage ref_page_10 && + test_diff_directories mw_dir_10 ref_page_10 +' + + +test_expect_failure 'special character at the beginning of file name from mw to git' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_11 && + wiki_editpage {char_1 "expect to be renamed {char_1" false && + wiki_editpage [char_2 "expect to be renamed [char_2" false && + ( + cd mw_dir_11 && + git pull + ) && + test_path_is_file mw_dir_11/{char_1 && + test_path_is_file mw_dir_11/[char_2 +' + +test_expect_success 'Pull page with title containing ":" other than namespace separator' ' + wiki_editpage Foo:Bar content false && + ( + cd mw_dir_11 && + git pull + ) && + test_path_is_file mw_dir_11/Foo:Bar.mw +' + +test_expect_success 'Push page with title containing ":" other than namespace separator' ' + ( + cd mw_dir_11 && + echo content >NotANameSpace:Page.mw && + git add NotANameSpace:Page.mw && + git commit -m "add page with colon" && + git push + ) && + wiki_page_exist NotANameSpace:Page +' + +test_expect_success 'test of correct formatting for file name from mw to git' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_12 && + wiki_editpage char_%_7b_1 "expect to be renamed char{_1" false && + wiki_editpage char_%_5b_2 "expect to be renamed char{_2" false && + ( + cd mw_dir_12 && + git pull + ) && + test_path_is_file mw_dir_12/Char\{_1.mw && + test_path_is_file mw_dir_12/Char\[_2.mw && + wiki_getallpage ref_page_12 && + mv ref_page_12/Char_%_7b_1.mw ref_page_12/Char\{_1.mw && + mv ref_page_12/Char_%_5b_2.mw ref_page_12/Char\[_2.mw && + test_diff_directories mw_dir_12 ref_page_12 +' + + +test_expect_failure 'test of correct formatting for file name beginning with special character' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_13 && + ( + cd mw_dir_13 && + echo "my new file {char_1" >\{char_1.mw && + echo "my new file [char_2" >\[char_2.mw && + git add . && + git commit -am "committing some exotic file name..." && + git push && + git pull + ) && + wiki_getallpage ref_page_13 && + test_path_is_file ref_page_13/{char_1.mw && + test_path_is_file ref_page_13/[char_2.mw && + test_diff_directories mw_dir_13 ref_page_13 +' + + +test_expect_success 'test of correct formatting for file name from git to mw' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_14 && + ( + cd mw_dir_14 && + echo "my new file char{_1" >Char\{_1.mw && + echo "my new file char[_2" >Char\[_2.mw && + git add . && + git commit -m "committing some exotic file name..." && + git push + ) && + wiki_getallpage ref_page_14 && + mv mw_dir_14/Char\{_1.mw mw_dir_14/Char_%_7b_1.mw && + mv mw_dir_14/Char\[_2.mw mw_dir_14/Char_%_5b_2.mw && + test_diff_directories mw_dir_14 ref_page_14 +' + + +test_expect_success 'git clone with /' ' + wiki_reset && + wiki_editpage \/fo\/o "this is not important" false -c=Deleted && + git clone mediawiki::'"$WIKI_URL"' mw_dir_15 && + test_path_is_file mw_dir_15/%2Ffo%2Fo.mw && + wiki_check_content mw_dir_15/%2Ffo%2Fo.mw \/fo\/o +' + + +test_expect_success 'git push with /' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_16 && + echo "I will be on the wiki" >mw_dir_16/%2Ffo%2Fo.mw && + ( + cd mw_dir_16 && + git add %2Ffo%2Fo.mw && + git commit -m " %2Ffo%2Fo added" && + git push + ) && + wiki_page_exist \/fo\/o && + wiki_check_content mw_dir_16/%2Ffo%2Fo.mw \/fo\/o + +' + + +test_expect_success 'git clone with \' ' + wiki_reset && + wiki_editpage \\ko\\o "this is not important" false -c=Deleted && + git clone mediawiki::'"$WIKI_URL"' mw_dir_17 && + test_path_is_file mw_dir_17/\\ko\\o.mw && + wiki_check_content mw_dir_17/\\ko\\o.mw \\ko\\o +' + + +test_expect_success 'git push with \' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_18 && + echo "I will be on the wiki" >mw_dir_18/\\ko\\o.mw && + ( + cd mw_dir_18 && + git add \\ko\\o.mw && + git commit -m " \\ko\\o added" && + git push + )&& + wiki_page_exist \\ko\\o && + wiki_check_content mw_dir_18/\\ko\\o.mw \\ko\\o + +' + +test_expect_success 'git clone with \ in format control' ' + wiki_reset && + wiki_editpage \\no\\o "this is not important" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_19 && + test_path_is_file mw_dir_19/\\no\\o.mw && + wiki_check_content mw_dir_19/\\no\\o.mw \\no\\o +' + + +test_expect_success 'git push with \ in format control' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_20 && + echo "I will be on the wiki" >mw_dir_20/\\fo\\o.mw && + ( + cd mw_dir_20 && + git add \\fo\\o.mw && + git commit -m " \\fo\\o added" && + git push + )&& + wiki_page_exist \\fo\\o && + wiki_check_content mw_dir_20/\\fo\\o.mw \\fo\\o + +' + + +test_expect_success 'fast-import meta-characters in page name (mw -> git)' ' + wiki_reset && + wiki_editpage \"file\"_\\_foo "expect to be called \"file\"_\\_foo" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_21 && + test_path_is_file mw_dir_21/\"file\"_\\_foo.mw && + wiki_getallpage ref_page_21 && + test_diff_directories mw_dir_21 ref_page_21 +' + + +test_expect_success 'fast-import meta-characters in page name (git -> mw) ' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_22 && + ( + cd mw_dir_22 && + echo "this file is called \"file\"_\\_foo.mw" >\"file\"_\\_foo && + git add . && + git commit -am "file \"file\"_\\_foo" && + git pull && + git push + ) && + wiki_getallpage ref_page_22 && + test_diff_directories mw_dir_22 ref_page_22 +' + + +test_done diff --git a/contrib/mw-to-git/t/t9363-mw-to-git-export-import.sh b/contrib/mw-to-git/t/t9363-mw-to-git-export-import.sh new file mode 100755 index 000000000000..3ff3a095670e --- /dev/null +++ b/contrib/mw-to-git/t/t9363-mw-to-git-export-import.sh @@ -0,0 +1,217 @@ +#!/bin/sh +# +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# +# License: GPL v2 or later + +# tests for git-remote-mediawiki + +test_description='Test the Git Mediawiki remote helper: git push and git pull simple test cases' + +. ./test-gitmw-lib.sh +. $TEST_DIRECTORY/test-lib.sh + + +test_check_precond + + +test_git_reimport () { + git -c remote.origin.dumbPush=true push && + git -c remote.origin.mediaImport=true pull --rebase +} + +# Don't bother with permissions, be administrator by default +test_expect_success 'setup config' ' + git config --global remote.origin.mwLogin WikiAdmin && + git config --global remote.origin.mwPassword AdminPass && + test_might_fail git config --global --unset remote.origin.mediaImport +' + +test_expect_success 'git push can upload media (File:) files' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + ( + cd mw_dir && + echo "hello world" >Foo.txt && + git add Foo.txt && + git commit -m "add a text file" && + git push && + "$PERL_PATH" -e "print STDOUT \"binary content: \".chr(255);" >Foo.txt && + git add Foo.txt && + git commit -m "add a text file with binary content" && + git push + ) +' + +test_expect_success 'git clone works on previously created wiki with media files' ' + test_when_finished "rm -rf mw_dir mw_dir_clone" && + git clone -c remote.origin.mediaimport=true \ + mediawiki::'"$WIKI_URL"' mw_dir_clone && + test_cmp mw_dir_clone/Foo.txt mw_dir/Foo.txt && + (cd mw_dir_clone && git checkout HEAD^) && + (cd mw_dir && git checkout HEAD^) && + test_cmp mw_dir_clone/Foo.txt mw_dir/Foo.txt +' + +test_expect_success 'git push can upload media (File:) files containing valid UTF-8' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + ( + cd mw_dir && + "$PERL_PATH" -e "print STDOUT \"UTF-8 content: éèàéê€.\";" >Bar.txt && + git add Bar.txt && + git commit -m "add a text file with UTF-8 content" && + git push + ) +' + +test_expect_success 'git clone works on previously created wiki with media files containing valid UTF-8' ' + test_when_finished "rm -rf mw_dir mw_dir_clone" && + git clone -c remote.origin.mediaimport=true \ + mediawiki::'"$WIKI_URL"' mw_dir_clone && + test_cmp mw_dir_clone/Bar.txt mw_dir/Bar.txt +' + +test_expect_success 'git push & pull work with locally renamed media files' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + test_when_finished "rm -fr mw_dir" && + ( + cd mw_dir && + echo "A File" >Foo.txt && + git add Foo.txt && + git commit -m "add a file" && + git mv Foo.txt Bar.txt && + git commit -m "Rename a file" && + test_git_reimport && + echo "A File" >expect && + test_cmp expect Bar.txt && + test_path_is_missing Foo.txt + ) +' + +test_expect_success 'git push can propagate local page deletion' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + test_when_finished "rm -fr mw_dir" && + ( + cd mw_dir && + test_path_is_missing Foo.mw && + echo "hello world" >Foo.mw && + git add Foo.mw && + git commit -m "Add the page Foo" && + git push && + rm -f Foo.mw && + git commit -am "Delete the page Foo" && + test_git_reimport && + test_path_is_missing Foo.mw + ) +' + +test_expect_success 'git push can propagate local media file deletion' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + test_when_finished "rm -fr mw_dir" && + ( + cd mw_dir && + echo "hello world" >Foo.txt && + git add Foo.txt && + git commit -m "Add the text file Foo" && + git rm Foo.txt && + git commit -m "Delete the file Foo" && + test_git_reimport && + test_path_is_missing Foo.txt + ) +' + +# test failure: the file is correctly uploaded, and then deleted but +# as no page link to it, the import (which looks at page revisions) +# doesn't notice the file deletion on the wiki. We fetch the list of +# files from the wiki, but as the file is deleted, it doesn't appear. +test_expect_failure 'git pull correctly imports media file deletion when no page link to it' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + test_when_finished "rm -fr mw_dir" && + ( + cd mw_dir && + echo "hello world" >Foo.txt && + git add Foo.txt && + git commit -m "Add the text file Foo" && + git push && + git rm Foo.txt && + git commit -m "Delete the file Foo" && + test_git_reimport && + test_path_is_missing Foo.txt + ) +' + +test_expect_success 'git push properly warns about insufficient permissions' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + test_when_finished "rm -fr mw_dir" && + ( + cd mw_dir && + echo "A File" >foo.forbidden && + git add foo.forbidden && + git commit -m "add a file" && + git push 2>actual && + test_i18ngrep "foo.forbidden is not a permitted file" actual + ) +' + +test_expect_success 'setup a repository with media files' ' + wiki_reset && + wiki_editpage testpage "I am linking a file [[File:File.txt]]" false && + echo "File content" >File.txt && + wiki_upload_file File.txt && + echo "Another file content" >AnotherFile.txt && + wiki_upload_file AnotherFile.txt +' + +test_expect_success 'git clone works with one specific page cloned and mediaimport=true' ' + git clone -c remote.origin.pages=testpage \ + -c remote.origin.mediaimport=true \ + mediawiki::'"$WIKI_URL"' mw_dir_15 && + test_when_finished "rm -rf mw_dir_15" && + test_contains_N_files mw_dir_15 3 && + test_path_is_file mw_dir_15/Testpage.mw && + test_path_is_file mw_dir_15/File:File.txt.mw && + test_path_is_file mw_dir_15/File.txt && + test_path_is_missing mw_dir_15/Main_Page.mw && + test_path_is_missing mw_dir_15/File:AnotherFile.txt.mw && + test_path_is_missing mw_dir_15/AnothetFile.txt && + wiki_check_content mw_dir_15/Testpage.mw Testpage && + test_cmp mw_dir_15/File.txt File.txt +' + +test_expect_success 'git clone works with one specific page cloned and mediaimport=false' ' + test_when_finished "rm -rf mw_dir_16" && + git clone -c remote.origin.pages=testpage \ + mediawiki::'"$WIKI_URL"' mw_dir_16 && + test_contains_N_files mw_dir_16 1 && + test_path_is_file mw_dir_16/Testpage.mw && + test_path_is_missing mw_dir_16/File:File.txt.mw && + test_path_is_missing mw_dir_16/File.txt && + test_path_is_missing mw_dir_16/Main_Page.mw && + wiki_check_content mw_dir_16/Testpage.mw Testpage +' + +# should behave like mediaimport=false +test_expect_success 'git clone works with one specific page cloned and mediaimport unset' ' + test_when_finished "rm -fr mw_dir_17" && + git clone -c remote.origin.pages=testpage \ + mediawiki::'"$WIKI_URL"' mw_dir_17 && + test_contains_N_files mw_dir_17 1 && + test_path_is_file mw_dir_17/Testpage.mw && + test_path_is_missing mw_dir_17/File:File.txt.mw && + test_path_is_missing mw_dir_17/File.txt && + test_path_is_missing mw_dir_17/Main_Page.mw && + wiki_check_content mw_dir_17/Testpage.mw Testpage +' + +test_done diff --git a/contrib/mw-to-git/t/t9364-pull-by-rev.sh b/contrib/mw-to-git/t/t9364-pull-by-rev.sh new file mode 100755 index 000000000000..5c22457a0b6a --- /dev/null +++ b/contrib/mw-to-git/t/t9364-pull-by-rev.sh @@ -0,0 +1,17 @@ +#!/bin/sh + +test_description='Test the Git Mediawiki remote helper: git pull by revision' + +. ./test-gitmw-lib.sh +. ./push-pull-tests.sh +. $TEST_DIRECTORY/test-lib.sh + +test_check_precond + +test_expect_success 'configuration' ' + git config --global mediawiki.fetchStrategy by_rev +' + +test_push_pull + +test_done diff --git a/contrib/mw-to-git/t/t9365-continuing-queries.sh b/contrib/mw-to-git/t/t9365-continuing-queries.sh new file mode 100755 index 000000000000..016454749f8d --- /dev/null +++ b/contrib/mw-to-git/t/t9365-continuing-queries.sh @@ -0,0 +1,23 @@ +#!/bin/sh + +test_description='Test the Git Mediawiki remote helper: queries w/ more than 500 results' + +. ./test-gitmw-lib.sh +. $TEST_DIRECTORY/test-lib.sh + +test_check_precond + +test_expect_success 'creating page w/ >500 revisions' ' + wiki_reset && + for i in $(test_seq 501) + do + echo "creating revision $i" && + wiki_editpage foo "revision $i<br/>" true + done +' + +test_expect_success 'cloning page w/ >500 revisions' ' + git clone mediawiki::'"$WIKI_URL"' mw_dir +' + +test_done diff --git a/contrib/mw-to-git/t/test-gitmw-lib.sh b/contrib/mw-to-git/t/test-gitmw-lib.sh new file mode 100755 index 000000000000..6546294f159e --- /dev/null +++ b/contrib/mw-to-git/t/test-gitmw-lib.sh @@ -0,0 +1,432 @@ +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# License: GPL v2 or later + +# +# CONFIGURATION VARIABLES +# You might want to change these ones +# + +. ./test.config + +WIKI_URL=http://"$SERVER_ADDR:$PORT/$WIKI_DIR_NAME" +CURR_DIR=$(pwd) +TEST_OUTPUT_DIRECTORY=$(pwd) +TEST_DIRECTORY="$CURR_DIR"/../../../t + +export TEST_OUTPUT_DIRECTORY TEST_DIRECTORY CURR_DIR + +if test "$LIGHTTPD" = "false" ; then + PORT=80 +else + WIKI_DIR_INST="$CURR_DIR/$WEB_WWW" +fi + +wiki_upload_file () { + "$CURR_DIR"/test-gitmw.pl upload_file "$@" +} + +wiki_getpage () { + "$CURR_DIR"/test-gitmw.pl get_page "$@" +} + +wiki_delete_page () { + "$CURR_DIR"/test-gitmw.pl delete_page "$@" +} + +wiki_editpage () { + "$CURR_DIR"/test-gitmw.pl edit_page "$@" +} + +die () { + die_with_status 1 "$@" +} + +die_with_status () { + status=$1 + shift + echo >&2 "$*" + exit "$status" +} + + +# Check the preconditions to run git-remote-mediawiki's tests +test_check_precond () { + if ! test_have_prereq PERL + then + skip_all='skipping gateway git-mw tests, perl not available' + test_done + fi + + GIT_EXEC_PATH=$(cd "$(dirname "$0")" && cd "../.." && pwd) + PATH="$GIT_EXEC_PATH"'/bin-wrapper:'"$PATH" + + if [ ! -d "$WIKI_DIR_INST/$WIKI_DIR_NAME" ]; + then + skip_all='skipping gateway git-mw tests, no mediawiki found' + test_done + fi +} + +# test_diff_directories <dir_git> <dir_wiki> +# +# Compare the contents of directories <dir_git> and <dir_wiki> with diff +# and errors if they do not match. The program will +# not look into .git in the process. +# Warning: the first argument MUST be the directory containing the git data +test_diff_directories () { + rm -rf "$1_tmp" + mkdir -p "$1_tmp" + cp "$1"/*.mw "$1_tmp" + diff -r -b "$1_tmp" "$2" +} + +# $1=<dir> +# $2=<N> +# +# Check that <dir> contains exactly <N> files +test_contains_N_files () { + if test $(ls -- "$1" | wc -l) -ne "$2"; then + echo "directory $1 should contain $2 files" + echo "it contains these files:" + ls "$1" + false + fi +} + + +# wiki_check_content <file_name> <page_name> +# +# Compares the contents of the file <file_name> and the wiki page +# <page_name> and exits with error 1 if they do not match. +wiki_check_content () { + mkdir -p wiki_tmp + wiki_getpage "$2" wiki_tmp + # replacement of forbidden character in file name + page_name=$(printf "%s\n" "$2" | sed -e "s/\//%2F/g") + + diff -b "$1" wiki_tmp/"$page_name".mw + if test $? -ne 0 + then + rm -rf wiki_tmp + error "ERROR: file $2 not found on wiki" + fi + rm -rf wiki_tmp +} + +# wiki_page_exist <page_name> +# +# Check the existence of the page <page_name> on the wiki and exits +# with error if it is absent from it. +wiki_page_exist () { + mkdir -p wiki_tmp + wiki_getpage "$1" wiki_tmp + page_name=$(printf "%s\n" "$1" | sed "s/\//%2F/g") + if test -f wiki_tmp/"$page_name".mw ; then + rm -rf wiki_tmp + else + rm -rf wiki_tmp + error "test failed: file $1 not found on wiki" + fi +} + +# wiki_getallpagename +# +# Fetch the name of each page on the wiki. +wiki_getallpagename () { + "$CURR_DIR"/test-gitmw.pl getallpagename +} + +# wiki_getallpagecategory <category> +# +# Fetch the name of each page belonging to <category> on the wiki. +wiki_getallpagecategory () { + "$CURR_DIR"/test-gitmw.pl getallpagename "$@" +} + +# wiki_getallpage <dest_dir> [<category>] +# +# Fetch all the pages from the wiki and place them in the directory +# <dest_dir>. +# If <category> is define, then wiki_getallpage fetch the pages included +# in <category>. +wiki_getallpage () { + if test -z "$2"; + then + wiki_getallpagename + else + wiki_getallpagecategory "$2" + fi + mkdir -p "$1" + while read -r line; do + wiki_getpage "$line" $1; + done < all.txt +} + +# ================= Install part ================= + +error () { + echo "$@" >&2 + exit 1 +} + +# config_lighttpd +# +# Create the configuration files and the folders necessary to start lighttpd. +# Overwrite any existing file. +config_lighttpd () { + mkdir -p $WEB + mkdir -p $WEB_TMP + mkdir -p $WEB_WWW + cat > $WEB/lighttpd.conf <<EOF + server.document-root = "$CURR_DIR/$WEB_WWW" + server.port = $PORT + server.pid-file = "$CURR_DIR/$WEB_TMP/pid" + + server.modules = ( + "mod_rewrite", + "mod_redirect", + "mod_access", + "mod_accesslog", + "mod_fastcgi" + ) + + index-file.names = ("index.php" , "index.html") + + mimetype.assign = ( + ".pdf" => "application/pdf", + ".sig" => "application/pgp-signature", + ".spl" => "application/futuresplash", + ".class" => "application/octet-stream", + ".ps" => "application/postscript", + ".torrent" => "application/x-bittorrent", + ".dvi" => "application/x-dvi", + ".gz" => "application/x-gzip", + ".pac" => "application/x-ns-proxy-autoconfig", + ".swf" => "application/x-shockwave-flash", + ".tar.gz" => "application/x-tgz", + ".tgz" => "application/x-tgz", + ".tar" => "application/x-tar", + ".zip" => "application/zip", + ".mp3" => "audio/mpeg", + ".m3u" => "audio/x-mpegurl", + ".wma" => "audio/x-ms-wma", + ".wax" => "audio/x-ms-wax", + ".ogg" => "application/ogg", + ".wav" => "audio/x-wav", + ".gif" => "image/gif", + ".jpg" => "image/jpeg", + ".jpeg" => "image/jpeg", + ".png" => "image/png", + ".xbm" => "image/x-xbitmap", + ".xpm" => "image/x-xpixmap", + ".xwd" => "image/x-xwindowdump", + ".css" => "text/css", + ".html" => "text/html", + ".htm" => "text/html", + ".js" => "text/javascript", + ".asc" => "text/plain", + ".c" => "text/plain", + ".cpp" => "text/plain", + ".log" => "text/plain", + ".conf" => "text/plain", + ".text" => "text/plain", + ".txt" => "text/plain", + ".dtd" => "text/xml", + ".xml" => "text/xml", + ".mpeg" => "video/mpeg", + ".mpg" => "video/mpeg", + ".mov" => "video/quicktime", + ".qt" => "video/quicktime", + ".avi" => "video/x-msvideo", + ".asf" => "video/x-ms-asf", + ".asx" => "video/x-ms-asf", + ".wmv" => "video/x-ms-wmv", + ".bz2" => "application/x-bzip", + ".tbz" => "application/x-bzip-compressed-tar", + ".tar.bz2" => "application/x-bzip-compressed-tar", + "" => "text/plain" + ) + + fastcgi.server = ( ".php" => + ("localhost" => + ( "socket" => "$CURR_DIR/$WEB_TMP/php.socket", + "bin-path" => "$PHP_DIR/php-cgi -c $CURR_DIR/$WEB/php.ini" + + ) + ) + ) +EOF + + cat > $WEB/php.ini <<EOF + session.save_path ='$CURR_DIR/$WEB_TMP' +EOF +} + +# start_lighttpd +# +# Start or restart daemon lighttpd. If restart, rewrite configuration files. +start_lighttpd () { + if test -f "$WEB_TMP/pid"; then + echo "Instance already running. Restarting..." + stop_lighttpd + fi + config_lighttpd + "$LIGHTTPD_DIR"/lighttpd -f "$WEB"/lighttpd.conf + + if test $? -ne 0 ; then + echo "Could not execute http deamon lighttpd" + exit 1 + fi +} + +# stop_lighttpd +# +# Kill daemon lighttpd and removes files and folders associated. +stop_lighttpd () { + test -f "$WEB_TMP/pid" && kill $(cat "$WEB_TMP/pid") +} + +# Create the SQLite database of the MediaWiki. If the database file already +# exists, it will be deleted. +# This script should be runned from the directory where $FILES_FOLDER is +# located. +create_db () { + rm -f "$TMP/$DB_FILE" + + echo "Generating the SQLite database file. It can take some time ..." + # Run the php script to generate the SQLite database file + # with cURL calls. + php "$FILES_FOLDER/$DB_INSTALL_SCRIPT" $(basename "$DB_FILE" .sqlite) \ + "$WIKI_ADMIN" "$WIKI_PASSW" "$TMP" "$PORT" + + if [ ! -f "$TMP/$DB_FILE" ] ; then + error "Can't create database file $TMP/$DB_FILE. Try to run ./install-wiki.sh delete first." + fi + + # Copy the generated database file into the directory the + # user indicated. + cp "$TMP/$DB_FILE" "$FILES_FOLDER" || + error "Unable to copy $TMP/$DB_FILE to $FILES_FOLDER" +} + +# Install a wiki in your web server directory. +wiki_install () { + if test $LIGHTTPD = "true" ; then + start_lighttpd + fi + + SERVER_ADDR=$SERVER_ADDR:$PORT + # In this part, we change directory to $TMP in order to download, + # unpack and copy the files of MediaWiki + ( + mkdir -p "$WIKI_DIR_INST/$WIKI_DIR_NAME" + if [ ! -d "$WIKI_DIR_INST/$WIKI_DIR_NAME" ] ; then + error "Folder $WIKI_DIR_INST/$WIKI_DIR_NAME doesn't exist. + Please create it and launch the script again." + fi + + # Fetch MediaWiki's archive if not already present in the TMP directory + MW_FILENAME="mediawiki-$MW_VERSION_MAJOR.$MW_VERSION_MINOR.tar.gz" + cd "$TMP" + if [ ! -f $MW_FILENAME ] ; then + echo "Downloading $MW_VERSION_MAJOR.$MW_VERSION_MINOR sources ..." + wget "http://download.wikimedia.org/mediawiki/$MW_VERSION_MAJOR/$MW_FILENAME" || + error "Unable to download "\ + "http://download.wikimedia.org/mediawiki/$MW_VERSION_MAJOR/"\ + "$MW_FILENAME. "\ + "Please fix your connection and launch the script again." + echo "$MW_FILENAME downloaded in $(pwd). "\ + "You can delete it later if you want." + else + echo "Reusing existing $MW_FILENAME downloaded in $(pwd)." + fi + archive_abs_path=$(pwd)/$MW_FILENAME + cd "$WIKI_DIR_INST/$WIKI_DIR_NAME/" || + error "can't cd to $WIKI_DIR_INST/$WIKI_DIR_NAME/" + tar xzf "$archive_abs_path" --strip-components=1 || + error "Unable to extract WikiMedia's files from $archive_abs_path to "\ + "$WIKI_DIR_INST/$WIKI_DIR_NAME" + ) || exit 1 + + create_db + + # Copy the generic LocalSettings.php in the web server's directory + # And modify parameters according to the ones set at the top + # of this script. + # Note that LocalSettings.php is never modified. + if [ ! -f "$FILES_FOLDER/LocalSettings.php" ] ; then + error "Can't find $FILES_FOLDER/LocalSettings.php " \ + "in the current folder. "\ + "Please run the script inside its folder." + fi + cp "$FILES_FOLDER/LocalSettings.php" \ + "$FILES_FOLDER/LocalSettings-tmp.php" || + error "Unable to copy $FILES_FOLDER/LocalSettings.php " \ + "to $FILES_FOLDER/LocalSettings-tmp.php" + + # Parse and set the LocalSettings file of the user according to the + # CONFIGURATION VARIABLES section at the beginning of this script + file_swap="$FILES_FOLDER/LocalSettings-swap.php" + sed "s,@WG_SCRIPT_PATH@,/$WIKI_DIR_NAME," \ + "$FILES_FOLDER/LocalSettings-tmp.php" > "$file_swap" + mv "$file_swap" "$FILES_FOLDER/LocalSettings-tmp.php" + sed "s,@WG_SERVER@,http://$SERVER_ADDR," \ + "$FILES_FOLDER/LocalSettings-tmp.php" > "$file_swap" + mv "$file_swap" "$FILES_FOLDER/LocalSettings-tmp.php" + sed "s,@WG_SQLITE_DATADIR@,$TMP," \ + "$FILES_FOLDER/LocalSettings-tmp.php" > "$file_swap" + mv "$file_swap" "$FILES_FOLDER/LocalSettings-tmp.php" + sed "s,@WG_SQLITE_DATAFILE@,$( basename $DB_FILE .sqlite)," \ + "$FILES_FOLDER/LocalSettings-tmp.php" > "$file_swap" + mv "$file_swap" "$FILES_FOLDER/LocalSettings-tmp.php" + + mv "$FILES_FOLDER/LocalSettings-tmp.php" \ + "$WIKI_DIR_INST/$WIKI_DIR_NAME/LocalSettings.php" || + error "Unable to move $FILES_FOLDER/LocalSettings-tmp.php" \ + "in $WIKI_DIR_INST/$WIKI_DIR_NAME" + echo "File $FILES_FOLDER/LocalSettings.php is set in" \ + " $WIKI_DIR_INST/$WIKI_DIR_NAME" + + echo "Your wiki has been installed. You can check it at + http://$SERVER_ADDR/$WIKI_DIR_NAME" +} + +# Reset the database of the wiki and the password of the admin +# +# Warning: This function must be called only in a subdirectory of t/ directory +wiki_reset () { + # Copy initial database of the wiki + if [ ! -f "../$FILES_FOLDER/$DB_FILE" ] ; then + error "Can't find ../$FILES_FOLDER/$DB_FILE in the current folder." + fi + cp "../$FILES_FOLDER/$DB_FILE" "$TMP" || + error "Can't copy ../$FILES_FOLDER/$DB_FILE in $TMP" + echo "File $FILES_FOLDER/$DB_FILE is set in $TMP" +} + +# Delete the wiki created in the web server's directory and all its content +# saved in the database. +wiki_delete () { + if test $LIGHTTPD = "true"; then + stop_lighttpd + rm -fr "$WEB" + else + # Delete the wiki's directory. + rm -rf "$WIKI_DIR_INST/$WIKI_DIR_NAME" || + error "Wiki's directory $WIKI_DIR_INST/" \ + "$WIKI_DIR_NAME could not be deleted" + # Delete the wiki's SQLite database. + rm -f "$TMP/$DB_FILE" || + error "Database $TMP/$DB_FILE could not be deleted." + fi + + # Delete the wiki's SQLite database + rm -f "$TMP/$DB_FILE" || error "Database $TMP/$DB_FILE could not be deleted." + rm -f "$FILES_FOLDER/$DB_FILE" + rm -rf "$TMP/mediawiki-$MW_VERSION_MAJOR.$MW_VERSION_MINOR.tar.gz" +} diff --git a/contrib/mw-to-git/t/test-gitmw.pl b/contrib/mw-to-git/t/test-gitmw.pl new file mode 100755 index 000000000000..0ff76259faa6 --- /dev/null +++ b/contrib/mw-to-git/t/test-gitmw.pl @@ -0,0 +1,225 @@ +#!/usr/bin/perl -w -s +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# License: GPL v2 or later + +# Usage: +# ./test-gitmw.pl <command> [argument]* +# Execute in terminal using the name of the function to call as first +# parameter, and the function's arguments as following parameters +# +# Example: +# ./test-gitmw.pl "get_page" foo . +# will call <wiki_getpage> with arguments <foo> and <.> +# +# Available functions are: +# "get_page" +# "delete_page" +# "edit_page" +# "getallpagename" + +use MediaWiki::API; +use Getopt::Long; +use encoding 'utf8'; +use DateTime::Format::ISO8601; +use open ':encoding(utf8)'; +use constant SLASH_REPLACEMENT => "%2F"; + +#Parsing of the config file + +my $configfile = "$ENV{'CURR_DIR'}/test.config"; +my %config; +open my $CONFIG, "<", $configfile or die "can't open $configfile: $!"; +while (<$CONFIG>) +{ + chomp; + s/#.*//; + s/^\s+//; + s/\s+$//; + next unless length; + my ($key, $value) = split (/\s*=\s*/,$_, 2); + $config{$key} = $value; + last if ($key eq 'LIGHTTPD' and $value eq 'false'); + last if ($key eq 'PORT'); +} +close $CONFIG or die "can't close $configfile: $!"; + +my $wiki_address = "http://$config{'SERVER_ADDR'}".":"."$config{'PORT'}"; +my $wiki_url = "$wiki_address/$config{'WIKI_DIR_NAME'}/api.php"; +my $wiki_admin = "$config{'WIKI_ADMIN'}"; +my $wiki_admin_pass = "$config{'WIKI_PASSW'}"; +my $mw = MediaWiki::API->new; +$mw->{config}->{api_url} = $wiki_url; + + +# wiki_login <name> <password> +# +# Logs the user with <name> and <password> in the global variable +# of the mediawiki $mw +sub wiki_login { + $mw->login( { lgname => "$_[0]",lgpassword => "$_[1]" } ) + || die "getpage: login failed"; +} + +# wiki_getpage <wiki_page> <dest_path> +# +# fetch a page <wiki_page> from the wiki referenced in the global variable +# $mw and copies its content in directory dest_path +sub wiki_getpage { + my $pagename = $_[0]; + my $destdir = $_[1]; + + my $page = $mw->get_page( { title => $pagename } ); + if (!defined($page)) { + die "getpage: wiki does not exist"; + } + + my $content = $page->{'*'}; + if (!defined($content)) { + die "getpage: page does not exist"; + } + + $pagename=$page->{'title'}; + # Replace spaces by underscore in the page name + $pagename =~ s/ /_/g; + $pagename =~ s/\//%2F/g; + open(my $file, ">$destdir/$pagename.mw"); + print $file "$content"; + close ($file); + +} + +# wiki_delete_page <page_name> +# +# delete the page with name <page_name> from the wiki referenced +# in the global variable $mw +sub wiki_delete_page { + my $pagename = $_[0]; + + my $exist=$mw->get_page({title => $pagename}); + + if (defined($exist->{'*'})){ + $mw->edit({ action => 'delete', + title => $pagename}) + || die $mw->{error}->{code} . ": " . $mw->{error}->{details}; + } else { + die "no page with such name found: $pagename\n"; + } +} + +# wiki_editpage <wiki_page> <wiki_content> <wiki_append> [-c=<category>] [-s=<summary>] +# +# Edit a page named <wiki_page> with content <wiki_content> on the wiki +# referenced with the global variable $mw +# If <wiki_append> == true : append <wiki_content> at the end of the actual +# content of the page <wiki_page> +# If <wik_page> doesn't exist, that page is created with the <wiki_content> +sub wiki_editpage { + my $wiki_page = $_[0]; + my $wiki_content = $_[1]; + my $wiki_append = $_[2]; + my $summary = ""; + my ($summ, $cat) = (); + GetOptions('s=s' => \$summ, 'c=s' => \$cat); + + my $append = 0; + if (defined($wiki_append) && $wiki_append eq 'true') { + $append=1; + } + + my $previous_text =""; + + if ($append) { + my $ref = $mw->get_page( { title => $wiki_page } ); + $previous_text = $ref->{'*'}; + } + + my $text = $wiki_content; + if (defined($previous_text)) { + $text="$previous_text$text"; + } + + # Eventually, add this page to a category. + if (defined($cat)) { + my $category_name="[[Category:$cat]]"; + $text="$text\n $category_name"; + } + if(defined($summ)){ + $summary=$summ; + } + + $mw->edit( { action => 'edit', title => $wiki_page, summary => $summary, text => "$text"} ); +} + +# wiki_getallpagename [<category>] +# +# Fetch all pages of the wiki referenced by the global variable $mw +# and print the names of each one in the file all.txt with a new line +# ("\n") between these. +# If the argument <category> is defined, then this function get only the pages +# belonging to <category>. +sub wiki_getallpagename { + # fetch the pages of the wiki + if (defined($_[0])) { + my $mw_pages = $mw->list ( { action => 'query', + list => 'categorymembers', + cmtitle => "Category:$_[0]", + cmnamespace => 0, + cmlimit => 500 }, + ) + || die $mw->{error}->{code}.": ".$mw->{error}->{details}; + open(my $file, ">all.txt"); + foreach my $page (@{$mw_pages}) { + print $file "$page->{title}\n"; + } + close ($file); + + } else { + my $mw_pages = $mw->list({ + action => 'query', + list => 'allpages', + aplimit => 500, + }) + || die $mw->{error}->{code}.": ".$mw->{error}->{details}; + open(my $file, ">all.txt"); + foreach my $page (@{$mw_pages}) { + print $file "$page->{title}\n"; + } + close ($file); + } +} + +sub wiki_upload_file { + my $file_name = $_[0]; + my $resultat = $mw->edit ( { + action => 'upload', + filename => $file_name, + comment => 'upload a file', + file => [ $file_name ], + ignorewarnings=>1, + }, { + skip_encoding => 1 + } ) || die $mw->{error}->{code} . ' : ' . $mw->{error}->{details}; +} + + + +# Main part of this script: parse the command line arguments +# and select which function to execute +my $fct_to_call = shift; + +wiki_login($wiki_admin, $wiki_admin_pass); + +my %functions_to_call = qw( + upload_file wiki_upload_file + get_page wiki_getpage + delete_page wiki_delete_page + edit_page wiki_editpage + getallpagename wiki_getallpagename +); +die "$0 ERROR: wrong argument" unless exists $functions_to_call{$fct_to_call}; +&{$functions_to_call{$fct_to_call}}(@ARGV); diff --git a/contrib/mw-to-git/t/test.config b/contrib/mw-to-git/t/test.config new file mode 100644 index 000000000000..5ba068416247 --- /dev/null +++ b/contrib/mw-to-git/t/test.config @@ -0,0 +1,37 @@ +# Name of the web server's directory dedicated to the wiki is WIKI_DIR_NAME +WIKI_DIR_NAME=wiki + +# Login and password of the wiki's admin +WIKI_ADMIN=WikiAdmin +WIKI_PASSW=AdminPass + +# Address of the web server +SERVER_ADDR=localhost + +# SQLite database of the wiki, named DB_FILE, is located in TMP +TMP=/tmp +DB_FILE=wikidb.sqlite + +# If LIGHTTPD is not set to true, the script will use the default +# web server running in WIKI_DIR_INST. +WIKI_DIR_INST=/var/www + +# If LIGHTTPD is set to true, the script will use Lighttpd to run +# the wiki. +LIGHTTPD=true + +# The variables below are useful only if LIGHTTPD is set to true. +PORT=1234 +PHP_DIR=/usr/bin +LIGHTTPD_DIR=/usr/sbin +WEB=WEB +WEB_TMP=$WEB/tmp +WEB_WWW=$WEB/www + +# The variables below are used by the script to install a wiki. +# You should not modify these unless you are modifying the script itself. +# tested versions: 1.19.X -> 1.21.1 +MW_VERSION_MAJOR=1.21 +MW_VERSION_MINOR=1 +FILES_FOLDER=install-wiki +DB_INSTALL_SCRIPT=db_install.php diff --git a/contrib/persistent-https/LICENSE b/contrib/persistent-https/LICENSE new file mode 100644 index 000000000000..d64569567334 --- /dev/null +++ b/contrib/persistent-https/LICENSE @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. diff --git a/contrib/persistent-https/Makefile b/contrib/persistent-https/Makefile new file mode 100644 index 000000000000..52b84ba3d439 --- /dev/null +++ b/contrib/persistent-https/Makefile @@ -0,0 +1,40 @@ +# Copyright 2012 Google Inc. All Rights Reserved. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +BUILD_LABEL=$(shell cut -d" " -f3 ../../GIT-VERSION-FILE) +TAR_OUT=$(shell go env GOOS)_$(shell go env GOARCH).tar.gz + +all: git-remote-persistent-https git-remote-persistent-https--proxy \ + git-remote-persistent-http + +git-remote-persistent-https--proxy: git-remote-persistent-https + ln -f -s git-remote-persistent-https git-remote-persistent-https--proxy + +git-remote-persistent-http: git-remote-persistent-https + ln -f -s git-remote-persistent-https git-remote-persistent-http + +git-remote-persistent-https: + case $$(go version) in \ + "go version go"1.[0-5].*) EQ=" " ;; *) EQ="=" ;; esac && \ + go build -o git-remote-persistent-https \ + -ldflags "-X main._BUILD_EMBED_LABEL$${EQ}$(BUILD_LABEL)" + +clean: + rm -f git-remote-persistent-http* *.tar.gz + +tar: clean all + @chmod 555 git-remote-persistent-https + @tar -czf $(TAR_OUT) git-remote-persistent-http* README LICENSE + @echo + @echo "Created $(TAR_OUT)" diff --git a/contrib/persistent-https/README b/contrib/persistent-https/README new file mode 100644 index 000000000000..7c4cd8d257da --- /dev/null +++ b/contrib/persistent-https/README @@ -0,0 +1,72 @@ +git-remote-persistent-https + +The git-remote-persistent-https binary speeds up SSL operations +by running a daemon job (git-remote-persistent-https--proxy) that +keeps a connection open to a server. + + +PRE-BUILT BINARIES + +Darwin amd64: +https://commondatastorage.googleapis.com/git-remote-persistent-https/darwin_amd64.tar.gz + +Linux amd64: +https://commondatastorage.googleapis.com/git-remote-persistent-https/linux_amd64.tar.gz + + +INSTALLING + +Move all of the git-remote-persistent-http* binaries to a directory +in PATH. + + +USAGE + +HTTPS requests can be delegated to the proxy by using the +"persistent-https" scheme, e.g. + +git clone persistent-https://kernel.googlesource.com/pub/scm/git/git + +Likewise, .gitconfig can be updated as follows to rewrite https urls +to use persistent-https: + +[url "persistent-https"] + insteadof = https +[url "persistent-http"] + insteadof = http + +You may also want to allow the use of the persistent-https helper for +submodule URLs (since any https URLs pointing to submodules will be +rewritten, and Git's out-of-the-box defaults forbid submodules from +using unknown remote helpers): + +[protocol "persistent-https"] + allow = always +[protocol "persistent-http"] + allow = always + + +##################################################################### +# BUILDING FROM SOURCE +##################################################################### + +LOCATION + +The source is available in the contrib/persistent-https directory of +the Git source repository. The Git source repository is available at +git://git.kernel.org/pub/scm/git/git.git/ +https://kernel.googlesource.com/pub/scm/git/git + + +PREREQUISITES + +The code is written in Go (http://golang.org/) and the Go compiler is +required. Currently, the compiler must be built and installed from tip +of source, in order to include a fix in the reverse http proxy: +http://code.google.com/p/go/source/detail?r=a615b796570a2cd8591884767a7d67ede74f6648 + + +BUILDING + +Run "make" to build the binaries. See the section on +INSTALLING above. diff --git a/contrib/persistent-https/client.go b/contrib/persistent-https/client.go new file mode 100644 index 000000000000..71125b5832d3 --- /dev/null +++ b/contrib/persistent-https/client.go @@ -0,0 +1,189 @@ +// Copyright 2012 Google Inc. All Rights Reserved. +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +package main + +import ( + "bufio" + "errors" + "fmt" + "net" + "net/url" + "os" + "os/exec" + "strings" + "syscall" + "time" +) + +type Client struct { + ProxyBin string + Args []string + + insecure bool +} + +func (c *Client) Run() error { + if err := c.resolveArgs(); err != nil { + return fmt.Errorf("resolveArgs() got error: %v", err) + } + + // Connect to the proxy. + uconn, hconn, addr, err := c.connect() + if err != nil { + return fmt.Errorf("connect() got error: %v", err) + } + // Keep the unix socket connection open for the duration of the request. + defer uconn.Close() + // Keep a connection to the HTTP server open, so no other user can + // bind on the same address so long as the process is running. + defer hconn.Close() + + // Start the git-remote-http subprocess. + cargs := []string{"-c", fmt.Sprintf("http.proxy=%v", addr), "remote-http"} + cargs = append(cargs, c.Args...) + cmd := exec.Command("git", cargs...) + + for _, v := range os.Environ() { + if !strings.HasPrefix(v, "GIT_PERSISTENT_HTTPS_SECURE=") { + cmd.Env = append(cmd.Env, v) + } + } + // Set the GIT_PERSISTENT_HTTPS_SECURE environment variable when + // the proxy is using a SSL connection. This allows credential helpers + // to identify secure proxy connections, despite being passed an HTTP + // scheme. + if !c.insecure { + cmd.Env = append(cmd.Env, "GIT_PERSISTENT_HTTPS_SECURE=1") + } + + cmd.Stdin = os.Stdin + cmd.Stdout = os.Stdout + cmd.Stderr = os.Stderr + if err := cmd.Run(); err != nil { + if eerr, ok := err.(*exec.ExitError); ok { + if stat, ok := eerr.ProcessState.Sys().(syscall.WaitStatus); ok && stat.ExitStatus() != 0 { + os.Exit(stat.ExitStatus()) + } + } + return fmt.Errorf("git-remote-http subprocess got error: %v", err) + } + return nil +} + +func (c *Client) connect() (uconn net.Conn, hconn net.Conn, addr string, err error) { + uconn, err = DefaultSocket.Dial() + if err != nil { + if e, ok := err.(*net.OpError); ok && (os.IsNotExist(e.Err) || e.Err == syscall.ECONNREFUSED) { + if err = c.startProxy(); err == nil { + uconn, err = DefaultSocket.Dial() + } + } + if err != nil { + return + } + } + + if addr, err = c.readAddr(uconn); err != nil { + return + } + + // Open a tcp connection to the proxy. + if hconn, err = net.Dial("tcp", addr); err != nil { + return + } + + // Verify the address hasn't changed ownership. + var addr2 string + if addr2, err = c.readAddr(uconn); err != nil { + return + } else if addr != addr2 { + err = fmt.Errorf("address changed after connect. got %q, want %q", addr2, addr) + return + } + return +} + +func (c *Client) readAddr(conn net.Conn) (string, error) { + conn.SetDeadline(time.Now().Add(5 * time.Second)) + data := make([]byte, 100) + n, err := conn.Read(data) + if err != nil { + return "", fmt.Errorf("error reading unix socket: %v", err) + } else if n == 0 { + return "", errors.New("empty data response") + } + conn.Write([]byte{1}) // Ack + + var addr string + if addrs := strings.Split(string(data[:n]), "\n"); len(addrs) != 2 { + return "", fmt.Errorf("got %q, wanted 2 addresses", data[:n]) + } else if c.insecure { + addr = addrs[1] + } else { + addr = addrs[0] + } + return addr, nil +} + +func (c *Client) startProxy() error { + cmd := exec.Command(c.ProxyBin) + cmd.SysProcAttr = &syscall.SysProcAttr{Setpgid: true} + stdout, err := cmd.StdoutPipe() + if err != nil { + return err + } + defer stdout.Close() + if err := cmd.Start(); err != nil { + return err + } + result := make(chan error) + go func() { + bytes, _, err := bufio.NewReader(stdout).ReadLine() + if line := string(bytes); err == nil && line != "OK" { + err = fmt.Errorf("proxy returned %q, want \"OK\"", line) + } + result <- err + }() + select { + case err := <-result: + return err + case <-time.After(5 * time.Second): + return errors.New("timeout waiting for proxy to start") + } + panic("not reachable") +} + +func (c *Client) resolveArgs() error { + if nargs := len(c.Args); nargs == 0 { + return errors.New("remote needed") + } else if nargs > 2 { + return fmt.Errorf("want at most 2 args, got %v", c.Args) + } + + // Rewrite the url scheme to be http. + idx := len(c.Args) - 1 + rawurl := c.Args[idx] + rurl, err := url.Parse(rawurl) + if err != nil { + return fmt.Errorf("invalid remote: %v", err) + } + c.insecure = rurl.Scheme == "persistent-http" + rurl.Scheme = "http" + c.Args[idx] = rurl.String() + if idx != 0 && c.Args[0] == rawurl { + c.Args[0] = c.Args[idx] + } + return nil +} diff --git a/contrib/persistent-https/main.go b/contrib/persistent-https/main.go new file mode 100644 index 000000000000..fd1b1077439b --- /dev/null +++ b/contrib/persistent-https/main.go @@ -0,0 +1,82 @@ +// Copyright 2012 Google Inc. All Rights Reserved. +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +// The git-remote-persistent-https binary speeds up SSL operations by running +// a daemon job that keeps a connection open to a Git server. This ensures the +// git-remote-persistent-https--proxy is running and delegating execution +// to the git-remote-http binary with the http_proxy set to the daemon job. +// A unix socket is used to authenticate the proxy and discover the +// HTTP address. Note, both the client and proxy are included in the same +// binary. +package main + +import ( + "flag" + "fmt" + "log" + "os" + "strings" + "time" +) + +var ( + forceProxy = flag.Bool("proxy", false, "Whether to start the binary in proxy mode") + proxyBin = flag.String("proxy_bin", "git-remote-persistent-https--proxy", "Path to the proxy binary") + printLabel = flag.Bool("print_label", false, "Prints the build label for the binary") + + // Variable that should be defined through the -X linker flag. + _BUILD_EMBED_LABEL string +) + +const ( + defaultMaxIdleDuration = 24 * time.Hour + defaultPollUpdateInterval = 15 * time.Minute +) + +func main() { + flag.Parse() + if *printLabel { + // Short circuit execution to print the build label + fmt.Println(buildLabel()) + return + } + + var err error + if *forceProxy || strings.HasSuffix(os.Args[0], "--proxy") { + log.SetPrefix("git-remote-persistent-https--proxy: ") + proxy := &Proxy{ + BuildLabel: buildLabel(), + MaxIdleDuration: defaultMaxIdleDuration, + PollUpdateInterval: defaultPollUpdateInterval, + } + err = proxy.Run() + } else { + log.SetPrefix("git-remote-persistent-https: ") + client := &Client{ + ProxyBin: *proxyBin, + Args: flag.Args(), + } + err = client.Run() + } + if err != nil { + log.Fatalln(err) + } +} + +func buildLabel() string { + if _BUILD_EMBED_LABEL == "" { + log.Println(`unlabeled build; build with "make" to label`) + } + return _BUILD_EMBED_LABEL +} diff --git a/contrib/persistent-https/proxy.go b/contrib/persistent-https/proxy.go new file mode 100644 index 000000000000..bb0cdba3864c --- /dev/null +++ b/contrib/persistent-https/proxy.go @@ -0,0 +1,190 @@ +// Copyright 2012 Google Inc. All Rights Reserved. +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +package main + +import ( + "fmt" + "log" + "net" + "net/http" + "net/http/httputil" + "os" + "os/exec" + "os/signal" + "sync" + "syscall" + "time" +) + +type Proxy struct { + BuildLabel string + MaxIdleDuration time.Duration + PollUpdateInterval time.Duration + + ul net.Listener + httpAddr string + httpsAddr string +} + +func (p *Proxy) Run() error { + hl, err := net.Listen("tcp", "127.0.0.1:0") + if err != nil { + return fmt.Errorf("http listen failed: %v", err) + } + defer hl.Close() + + hsl, err := net.Listen("tcp", "127.0.0.1:0") + if err != nil { + return fmt.Errorf("https listen failed: %v", err) + } + defer hsl.Close() + + p.ul, err = DefaultSocket.Listen() + if err != nil { + c, derr := DefaultSocket.Dial() + if derr == nil { + c.Close() + fmt.Println("OK\nA proxy is already running... exiting") + return nil + } else if e, ok := derr.(*net.OpError); ok && e.Err == syscall.ECONNREFUSED { + // Nothing is listening on the socket, unlink it and try again. + syscall.Unlink(DefaultSocket.Path()) + p.ul, err = DefaultSocket.Listen() + } + if err != nil { + return fmt.Errorf("unix listen failed on %v: %v", DefaultSocket.Path(), err) + } + } + defer p.ul.Close() + go p.closeOnSignal() + go p.closeOnUpdate() + + p.httpAddr = hl.Addr().String() + p.httpsAddr = hsl.Addr().String() + fmt.Printf("OK\nListening on unix socket=%v http=%v https=%v\n", + p.ul.Addr(), p.httpAddr, p.httpsAddr) + + result := make(chan error, 2) + go p.serveUnix(result) + go func() { + result <- http.Serve(hl, &httputil.ReverseProxy{ + FlushInterval: 500 * time.Millisecond, + Director: func(r *http.Request) {}, + }) + }() + go func() { + result <- http.Serve(hsl, &httputil.ReverseProxy{ + FlushInterval: 500 * time.Millisecond, + Director: func(r *http.Request) { + r.URL.Scheme = "https" + }, + }) + }() + return <-result +} + +type socketContext struct { + sync.WaitGroup + mutex sync.Mutex + last time.Time +} + +func (sc *socketContext) Done() { + sc.mutex.Lock() + defer sc.mutex.Unlock() + sc.last = time.Now() + sc.WaitGroup.Done() +} + +func (p *Proxy) serveUnix(result chan<- error) { + sockCtx := &socketContext{} + go p.closeOnIdle(sockCtx) + + var err error + for { + var uconn net.Conn + uconn, err = p.ul.Accept() + if err != nil { + err = fmt.Errorf("accept failed: %v", err) + break + } + sockCtx.Add(1) + go p.handleUnixConn(sockCtx, uconn) + } + sockCtx.Wait() + result <- err +} + +func (p *Proxy) handleUnixConn(sockCtx *socketContext, uconn net.Conn) { + defer sockCtx.Done() + defer uconn.Close() + data := []byte(fmt.Sprintf("%v\n%v", p.httpsAddr, p.httpAddr)) + uconn.SetDeadline(time.Now().Add(5 * time.Second)) + for i := 0; i < 2; i++ { + if n, err := uconn.Write(data); err != nil { + log.Printf("error sending http addresses: %+v\n", err) + return + } else if n != len(data) { + log.Printf("sent %d data bytes, wanted %d\n", n, len(data)) + return + } + if _, err := uconn.Read([]byte{0, 0, 0, 0}); err != nil { + log.Printf("error waiting for Ack: %+v\n", err) + return + } + } + // Wait without a deadline for the client to finish via EOF + uconn.SetDeadline(time.Time{}) + uconn.Read([]byte{0, 0, 0, 0}) +} + +func (p *Proxy) closeOnIdle(sockCtx *socketContext) { + for d := p.MaxIdleDuration; d > 0; { + time.Sleep(d) + sockCtx.Wait() + sockCtx.mutex.Lock() + if d = sockCtx.last.Add(p.MaxIdleDuration).Sub(time.Now()); d <= 0 { + log.Println("graceful shutdown from idle timeout") + p.ul.Close() + } + sockCtx.mutex.Unlock() + } +} + +func (p *Proxy) closeOnUpdate() { + for { + time.Sleep(p.PollUpdateInterval) + if out, err := exec.Command(os.Args[0], "--print_label").Output(); err != nil { + log.Printf("error polling for updated binary: %v\n", err) + } else if s := string(out[:len(out)-1]); p.BuildLabel != s { + log.Printf("graceful shutdown from updated binary: %q --> %q\n", p.BuildLabel, s) + p.ul.Close() + break + } + } +} + +func (p *Proxy) closeOnSignal() { + ch := make(chan os.Signal, 10) + signal.Notify(ch, os.Interrupt, os.Kill, os.Signal(syscall.SIGTERM), os.Signal(syscall.SIGHUP)) + sig := <-ch + p.ul.Close() + switch sig { + case os.Signal(syscall.SIGHUP): + log.Printf("graceful shutdown from signal: %v\n", sig) + default: + log.Fatalf("exiting from signal: %v\n", sig) + } +} diff --git a/contrib/persistent-https/socket.go b/contrib/persistent-https/socket.go new file mode 100644 index 000000000000..193b911dd13a --- /dev/null +++ b/contrib/persistent-https/socket.go @@ -0,0 +1,97 @@ +// Copyright 2012 Google Inc. All Rights Reserved. +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +package main + +import ( + "fmt" + "log" + "net" + "os" + "path/filepath" + "syscall" +) + +// A Socket is a wrapper around a Unix socket that verifies directory +// permissions. +type Socket struct { + Dir string +} + +func defaultDir() string { + sockPath := ".git-credential-cache" + if home := os.Getenv("HOME"); home != "" { + return filepath.Join(home, sockPath) + } + log.Printf("socket: cannot find HOME path. using relative directory %q for socket", sockPath) + return sockPath +} + +// DefaultSocket is a Socket in the $HOME/.git-credential-cache directory. +var DefaultSocket = Socket{Dir: defaultDir()} + +// Listen announces the local network address of the unix socket. The +// permissions on the socket directory are verified before attempting +// the actual listen. +func (s Socket) Listen() (net.Listener, error) { + network, addr := "unix", s.Path() + if err := s.mkdir(); err != nil { + return nil, &net.OpError{Op: "listen", Net: network, Addr: &net.UnixAddr{Name: addr, Net: network}, Err: err} + } + return net.Listen(network, addr) +} + +// Dial connects to the unix socket. The permissions on the socket directory +// are verified before attempting the actual dial. +func (s Socket) Dial() (net.Conn, error) { + network, addr := "unix", s.Path() + if err := s.checkPermissions(); err != nil { + return nil, &net.OpError{Op: "dial", Net: network, Addr: &net.UnixAddr{Name: addr, Net: network}, Err: err} + } + return net.Dial(network, addr) +} + +// Path returns the fully specified file name of the unix socket. +func (s Socket) Path() string { + return filepath.Join(s.Dir, "persistent-https-proxy-socket") +} + +func (s Socket) mkdir() error { + if err := s.checkPermissions(); err == nil { + return nil + } else if !os.IsNotExist(err) { + return err + } + if err := os.MkdirAll(s.Dir, 0700); err != nil { + return err + } + return s.checkPermissions() +} + +func (s Socket) checkPermissions() error { + fi, err := os.Stat(s.Dir) + if err != nil { + return err + } + if !fi.IsDir() { + return fmt.Errorf("socket: got file, want directory for %q", s.Dir) + } + if fi.Mode().Perm() != 0700 { + return fmt.Errorf("socket: got perm %o, want 700 for %q", fi.Mode().Perm(), s.Dir) + } + if st := fi.Sys().(*syscall.Stat_t); int(st.Uid) != os.Getuid() { + return fmt.Errorf("socket: got uid %d, want %d for %q", st.Uid, os.Getuid(), s.Dir) + } + return nil +} diff --git a/contrib/remote-helpers/README b/contrib/remote-helpers/README new file mode 100644 index 000000000000..ac72332517a5 --- /dev/null +++ b/contrib/remote-helpers/README @@ -0,0 +1,15 @@ +The remote-helper bridges to access data stored in Mercurial and +Bazaar are maintained outside the git.git tree in the repositories +of their primary author: + + https://github.com/felipec/git-remote-hg (for Mercurial) + https://github.com/felipec/git-remote-bzr (for Bazaar) + +You can pick a directory on your $PATH and download them from these +repositories, e.g.: + + $ wget -O $HOME/bin/git-remote-hg \ + https://raw.github.com/felipec/git-remote-hg/master/git-remote-hg + $ wget -O $HOME/bin/git-remote-bzr \ + https://raw.github.com/felipec/git-remote-bzr/master/git-remote-bzr + $ chmod +x $HOME/bin/git-remote-hg $HOME/bin/git-remote-bzr diff --git a/contrib/remote-helpers/git-remote-bzr b/contrib/remote-helpers/git-remote-bzr new file mode 100755 index 000000000000..1c3d87f8619e --- /dev/null +++ b/contrib/remote-helpers/git-remote-bzr @@ -0,0 +1,11 @@ +#!/bin/sh + +cat >&2 <<'EOT' +WARNING: git-remote-bzr is now maintained independently. +WARNING: For more information visit https://github.com/felipec/git-remote-bzr +WARNING: +WARNING: You can pick a directory on your $PATH and download it, e.g.: +WARNING: $ wget -O $HOME/bin/git-remote-bzr \ +WARNING: https://raw.github.com/felipec/git-remote-bzr/master/git-remote-bzr +WARNING: $ chmod +x $HOME/bin/git-remote-bzr +EOT diff --git a/contrib/remote-helpers/git-remote-hg b/contrib/remote-helpers/git-remote-hg new file mode 100755 index 000000000000..8e9188364c6f --- /dev/null +++ b/contrib/remote-helpers/git-remote-hg @@ -0,0 +1,11 @@ +#!/bin/sh + +cat >&2 <<'EOT' +WARNING: git-remote-hg is now maintained independently. +WARNING: For more information visit https://github.com/felipec/git-remote-hg +WARNING: +WARNING: You can pick a directory on your $PATH and download it, e.g.: +WARNING: $ wget -O $HOME/bin/git-remote-hg \ +WARNING: https://raw.github.com/felipec/git-remote-hg/master/git-remote-hg +WARNING: $ chmod +x $HOME/bin/git-remote-hg +EOT diff --git a/contrib/remotes2config.sh b/contrib/remotes2config.sh new file mode 100755 index 000000000000..1cda19f66af9 --- /dev/null +++ b/contrib/remotes2config.sh @@ -0,0 +1,33 @@ +#!/bin/sh + +# Use this tool to rewrite your .git/remotes/ files into the config. + +. git-sh-setup + +if [ -d "$GIT_DIR"/remotes ]; then + echo "Rewriting $GIT_DIR/remotes" >&2 + error=0 + # rewrite into config + { + cd "$GIT_DIR"/remotes + ls | while read f; do + name=$(printf "$f" | tr -c "A-Za-z0-9-" ".") + sed -n \ + -e "s/^URL:[ ]*\(.*\)$/remote.$name.url \1 ./p" \ + -e "s/^Pull:[ ]*\(.*\)$/remote.$name.fetch \1 ^$ /p" \ + -e "s/^Push:[ ]*\(.*\)$/remote.$name.push \1 ^$ /p" \ + < "$f" + done + echo done + } | while read key value regex; do + case $key in + done) + if [ $error = 0 ]; then + mv "$GIT_DIR"/remotes "$GIT_DIR"/remotes.old + fi ;; + *) + echo "git config $key "$value" $regex" + git config $key "$value" $regex || error=1 ;; + esac + done +fi diff --git a/contrib/rerere-train.sh b/contrib/rerere-train.sh new file mode 100755 index 000000000000..eeee45dd341b --- /dev/null +++ b/contrib/rerere-train.sh @@ -0,0 +1,102 @@ +#!/bin/sh +# Copyright (c) 2008, Nanako Shiraishi +# Prime rerere database from existing merge commits + +me=rerere-train +USAGE=$(cat <<-EOF +usage: $me [--overwrite] <rev-list-args> + + -h, --help show the help + -o, --overwrite overwrite any existing rerere cache +EOF +) + +SUBDIRECTORY_OK=Yes + +overwrite=0 + +while test $# -gt 0 +do + opt="$1" + case "$opt" in + -h|--help) + echo "$USAGE" + exit 0 + ;; + -o|--overwrite) + overwrite=1 + shift + break + ;; + --) + shift + break + ;; + *) + break + ;; + esac +done + +# Overwrite or help options are not valid except as first arg +for opt in "$@" +do + case "$opt" in + -h|--help) + echo "$USAGE" + exit 0 + ;; + -o|--overwrite) + echo "$USAGE" + exit 0 + ;; + esac +done + +. "$(git --exec-path)/git-sh-setup" +require_work_tree +cd_to_toplevel + +# Remember original branch +branch=$(git symbolic-ref -q HEAD) || +original_HEAD=$(git rev-parse --verify HEAD) || { + echo >&2 "Not on any branch and no commit yet?" + exit 1 +} + +mkdir -p "$GIT_DIR/rr-cache" || exit + +git rev-list --parents "$@" | +while read commit parent1 other_parents +do + if test -z "$other_parents" + then + # Skip non-merges + continue + fi + git checkout -q "$parent1^0" + if git merge $other_parents >/dev/null 2>&1 + then + # Cleanly merges + continue + fi + if test $overwrite = 1 + then + git rerere forget . + fi + if test -s "$GIT_DIR/MERGE_RR" + then + git show -s --pretty=format:"Learning from %h %s" "$commit" + git rerere + git checkout -q $commit -- . + git rerere + fi + git reset -q --hard +done + +if test -z "$branch" +then + git checkout "$original_HEAD" +else + git checkout "${branch#refs/heads/}" +fi diff --git a/contrib/stats/git-common-hash b/contrib/stats/git-common-hash new file mode 100755 index 000000000000..e27fd088be1b --- /dev/null +++ b/contrib/stats/git-common-hash @@ -0,0 +1,26 @@ +#!/bin/sh + +# This script displays the distribution of longest common hash prefixes. +# This can be used to determine the minimum prefix length to use +# for object names to be unique. + +git rev-list --objects --all | sort | perl -lne ' + substr($_, 40) = ""; + # uncomment next line for a distribution of bits instead of hex chars + # $_ = unpack("B*",pack("H*",$_)); + if (defined $p) { + ($p ^ $_) =~ /^(\0*)/; + $common = length $1; + if (defined $pcommon) { + $count[$pcommon > $common ? $pcommon : $common]++; + } else { + $count[$common]++; # first item + } + } + $p = $_; + $pcommon = $common; + END { + $count[$common]++; # last item + print "$_: $count[$_]" for 0..$#count; + } +' diff --git a/contrib/stats/mailmap.pl b/contrib/stats/mailmap.pl new file mode 100755 index 000000000000..9513f5e35b44 --- /dev/null +++ b/contrib/stats/mailmap.pl @@ -0,0 +1,70 @@ +#!/usr/bin/perl + +use warnings 'all'; +use strict; +use Getopt::Long; + +my $match_emails; +my $match_names; +my $order_by = 'count'; +Getopt::Long::Configure(qw(bundling)); +GetOptions( + 'emails|e!' => \$match_emails, + 'names|n!' => \$match_names, + 'count|c' => sub { $order_by = 'count' }, + 'time|t' => sub { $order_by = 'stamp' }, +) or exit 1; +$match_emails = 1 unless $match_names; + +my $email = {}; +my $name = {}; + +open(my $fh, '-|', "git log --format='%at <%aE> %aN'"); +while(<$fh>) { + my ($t, $e, $n) = /(\S+) <(\S+)> (.*)/; + mark($email, $e, $n, $t); + mark($name, $n, $e, $t); +} +close($fh); + +if ($match_emails) { + foreach my $e (dups($email)) { + foreach my $n (vals($email->{$e})) { + show($n, $e, $email->{$e}->{$n}); + } + print "\n"; + } +} +if ($match_names) { + foreach my $n (dups($name)) { + foreach my $e (vals($name->{$n})) { + show($n, $e, $name->{$n}->{$e}); + } + print "\n"; + } +} +exit 0; + +sub mark { + my ($h, $k, $v, $t) = @_; + my $e = $h->{$k}->{$v} ||= { count => 0, stamp => 0 }; + $e->{count}++; + $e->{stamp} = $t unless $t < $e->{stamp}; +} + +sub dups { + my $h = shift; + return grep { keys($h->{$_}) > 1 } keys($h); +} + +sub vals { + my $h = shift; + return sort { + $h->{$b}->{$order_by} <=> $h->{$a}->{$order_by} + } keys($h); +} + +sub show { + my ($n, $e, $h) = @_; + print "$n <$e> ($h->{$order_by})\n"; +} diff --git a/contrib/stats/packinfo.pl b/contrib/stats/packinfo.pl new file mode 100755 index 000000000000..be188c0f11db --- /dev/null +++ b/contrib/stats/packinfo.pl @@ -0,0 +1,212 @@ +#!/usr/bin/perl +# +# This tool will print vaguely pretty information about a pack. It +# expects the output of "git verify-pack -v" as input on stdin. +# +# $ git verify-pack -v | packinfo.pl +# +# This prints some full-pack statistics; currently "all sizes", "all +# path sizes", "tree sizes", "tree path sizes", and "depths". +# +# * "all sizes" stats are across every object size in the file; +# full sizes for base objects, and delta size for deltas. +# * "all path sizes" stats are across all object's "path sizes". +# A path size is the sum of the size of the delta chain, including the +# base object. In other words, it's how many bytes need be read to +# reassemble the file from deltas. +# * "tree sizes" are object sizes grouped into delta trees. +# * "tree path sizes" are path sizes grouped into delta trees. +# * "depths" should be obvious. +# +# When run as: +# +# $ git verify-pack -v | packinfo.pl -tree +# +# the trees of objects are output along with the stats. This looks +# like: +# +# 0 commit 031321c6... 803 803 +# +# 0 blob 03156f21... 1767 1767 +# 1 blob f52a9d7f... 10 1777 +# 2 blob a8cc5739... 51 1828 +# 3 blob 660e90b1... 15 1843 +# 4 blob 0cb8e3bb... 33 1876 +# 2 blob e48607f0... 311 2088 +# size: count 6 total 2187 min 10 max 1767 mean 364.50 median 51 std_dev 635.85 +# path size: count 6 total 11179 min 1767 max 2088 mean 1863.17 median 1843 std_dev 107.26 +# +# The first number after the sha1 is the object size, the second +# number is the path size. The statistics are across all objects in +# the previous delta tree. Obviously they are omitted for trees of +# one object. +# +# When run as: +# +# $ git verify-pack -v | packinfo.pl -tree -filenames +# +# it adds filenames to the tree. Getting this information is slow: +# +# 0 blob 03156f21... 1767 1767 Documentation/git-lost-found.txt @ tags/v1.2.0~142 +# 1 blob f52a9d7f... 10 1777 Documentation/git-lost-found.txt @ tags/v1.5.0-rc1~74 +# 2 blob a8cc5739... 51 1828 Documentation/git-lost+found.txt @ tags/v0.99.9h^0 +# 3 blob 660e90b1... 15 1843 Documentation/git-lost+found.txt @ master~3222^2~2 +# 4 blob 0cb8e3bb... 33 1876 Documentation/git-lost+found.txt @ master~3222^2~3 +# 2 blob e48607f0... 311 2088 Documentation/git-lost-found.txt @ tags/v1.5.2-rc3~4 +# size: count 6 total 2187 min 10 max 1767 mean 364.50 median 51 std_dev 635.85 +# path size: count 6 total 11179 min 1767 max 2088 mean 1863.17 median 1843 std_dev 107.26 +# +# When run as: +# +# $ git verify-pack -v | packinfo.pl -dump +# +# it prints out "sha1 size pathsize depth" for each sha1 in lexical +# order. +# +# 000079a2eaef17b7eae70e1f0f635557ea67b644 30 472 7 +# 00013cafe6980411aa6fdd940784917b5ff50f0a 44 1542 4 +# 000182eacf99cde27d5916aa415921924b82972c 499 499 0 +# ... +# +# This is handy for comparing two packs. Adding "-filenames" will add +# filenames, as per "-tree -filenames" above. + +use strict; +use Getopt::Long; + +my $filenames = 0; +my $tree = 0; +my $dump = 0; +GetOptions("tree" => \$tree, + "filenames" => \$filenames, + "dump" => \$dump); + +my %parents; +my %children; +my %sizes; +my @roots; +my %paths; +my %types; +my @commits; +my %names; +my %depths; +my @depths; + +while (<STDIN>) { + my ($sha1, $type, $size, $space, $offset, $depth, $parent) = split(/\s+/, $_); + next unless ($sha1 =~ /^[0-9a-f]{40}$/); + $depths{$sha1} = $depth || 0; + push(@depths, $depth || 0); + push(@commits, $sha1) if ($type eq 'commit'); + push(@roots, $sha1) unless $parent; + $parents{$sha1} = $parent; + $types{$sha1} = $type; + push(@{$children{$parent}}, $sha1); + $sizes{$sha1} = $size; +} + +if ($filenames && ($tree || $dump)) { + open(NAMES, "git name-rev --all|"); + while (<NAMES>) { + if (/^(\S+)\s+(.*)$/) { + my ($sha1, $name) = ($1, $2); + $names{$sha1} = $name; + } + } + close NAMES; + + for my $commit (@commits) { + my $name = $names{$commit}; + open(TREE, "git ls-tree -t -r $commit|"); + print STDERR "Plumbing tree $name\n"; + while (<TREE>) { + if (/^(\S+)\s+(\S+)\s+(\S+)\s+(.*)$/) { + my ($mode, $type, $sha1, $path) = ($1, $2, $3, $4); + $paths{$sha1} = "$path @ $name"; + } + } + close TREE; + } +} + +sub stats { + my @data = sort {$a <=> $b} @_; + my $min = $data[0]; + my $max = $data[$#data]; + my $total = 0; + my $count = scalar @data; + for my $datum (@data) { + $total += $datum; + } + my $mean = $total / $count; + my $median = $data[int(@data / 2)]; + my $diff_sum = 0; + for my $datum (@data) { + $diff_sum += ($datum - $mean)**2; + } + my $std_dev = sqrt($diff_sum / $count); + return ($count, $total, $min, $max, $mean, $median, $std_dev); +} + +sub print_stats { + my $name = shift; + my ($count, $total, $min, $max, $mean, $median, $std_dev) = stats(@_); + printf("%s: count %s total %s min %s max %s mean %.2f median %s std_dev %.2f\n", + $name, $count, $total, $min, $max, $mean, $median, $std_dev); +} + +my @sizes; +my @path_sizes; +my @all_sizes; +my @all_path_sizes; +my %path_sizes; + +sub dig { + my ($sha1, $depth, $path_size) = @_; + $path_size += $sizes{$sha1}; + push(@sizes, $sizes{$sha1}); + push(@all_sizes, $sizes{$sha1}); + push(@path_sizes, $path_size); + push(@all_path_sizes, $path_size); + $path_sizes{$sha1} = $path_size; + if ($tree) { + printf("%3d%s %6s %s %8d %8d %s\n", + $depth, (" " x $depth), $types{$sha1}, + $sha1, $sizes{$sha1}, $path_size, $paths{$sha1}); + } + for my $child (@{$children{$sha1}}) { + dig($child, $depth + 1, $path_size); + } +} + +my @tree_sizes; +my @tree_path_sizes; + +for my $root (@roots) { + undef @sizes; + undef @path_sizes; + dig($root, 0, 0); + my ($aa, $sz_total) = stats(@sizes); + my ($bb, $psz_total) = stats(@path_sizes); + push(@tree_sizes, $sz_total); + push(@tree_path_sizes, $psz_total); + if ($tree) { + if (@sizes > 1) { + print_stats(" size", @sizes); + print_stats("path size", @path_sizes); + } + print "\n"; + } +} + +if ($dump) { + for my $sha1 (sort keys %sizes) { + print "$sha1 $sizes{$sha1} $path_sizes{$sha1} $depths{$sha1} $paths{$sha1}\n"; + } +} else { + print_stats(" all sizes", @all_sizes); + print_stats(" all path sizes", @all_path_sizes); + print_stats(" tree sizes", @tree_sizes); + print_stats("tree path sizes", @tree_path_sizes); + print_stats(" depths", @depths); +} diff --git a/contrib/subtree/.gitignore b/contrib/subtree/.gitignore new file mode 100644 index 000000000000..0b9381abcad3 --- /dev/null +++ b/contrib/subtree/.gitignore @@ -0,0 +1,7 @@ +*~ +git-subtree +git-subtree.1 +git-subtree.html +git-subtree.xml +mainline +subproj diff --git a/contrib/subtree/COPYING b/contrib/subtree/COPYING new file mode 100644 index 000000000000..d511905c1647 --- /dev/null +++ b/contrib/subtree/COPYING @@ -0,0 +1,339 @@ + GNU GENERAL PUBLIC LICENSE + Version 2, June 1991 + + Copyright (C) 1989, 1991 Free Software Foundation, Inc., + 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +License is intended to guarantee your freedom to share and change free +software--to make sure the software is free for all its users. This +General Public License applies to most of the Free Software +Foundation's software and to any other program whose authors commit to +using it. (Some other Free Software Foundation software is covered by +the GNU Lesser General Public License instead.) You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +this service if you wish), that you receive source code or can get it +if you want it, that you can change the software or use pieces of it +in new free programs; and that you know you can do these things. + + To protect your rights, we need to make restrictions that forbid +anyone to deny you these rights or to ask you to surrender the rights. +These restrictions translate to certain responsibilities for you if you +distribute copies of the software, or if you modify it. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must give the recipients all the rights that +you have. You must make sure that they, too, receive or can get the +source code. And you must show them these terms so they know their +rights. + + We protect your rights with two steps: (1) copyright the software, and +(2) offer you this license which gives you legal permission to copy, +distribute and/or modify the software. + + Also, for each author's protection and ours, we want to make certain +that everyone understands that there is no warranty for this free +software. If the software is modified by someone else and passed on, we +want its recipients to know that what they have is not the original, so +that any problems introduced by others will not reflect on the original +authors' reputations. + + Finally, any free program is threatened constantly by software +patents. We wish to avoid the danger that redistributors of a free +program will individually obtain patent licenses, in effect making the +program proprietary. To prevent this, we have made it clear that any +patent must be licensed for everyone's free use or not licensed at all. + + The precise terms and conditions for copying, distribution and +modification follow. + + GNU GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License applies to any program or other work which contains +a notice placed by the copyright holder saying it may be distributed +under the terms of this General Public License. The "Program", below, +refers to any such program or work, and a "work based on the Program" +means either the Program or any derivative work under copyright law: +that is to say, a work containing the Program or a portion of it, +either verbatim or with modifications and/or translated into another +language. (Hereinafter, translation is included without limitation in +the term "modification".) Each licensee is addressed as "you". + +Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running the Program is not restricted, and the output from the Program +is covered only if its contents constitute a work based on the +Program (independent of having been made by running the Program). +Whether that is true depends on what the Program does. + + 1. You may copy and distribute verbatim copies of the Program's +source code as you receive it, in any medium, provided that you +conspicuously and appropriately publish on each copy an appropriate +copyright notice and disclaimer of warranty; keep intact all the +notices that refer to this License and to the absence of any warranty; +and give any other recipients of the Program a copy of this License +along with the Program. + +You may charge a fee for the physical act of transferring a copy, and +you may at your option offer warranty protection in exchange for a fee. + + 2. You may modify your copy or copies of the Program or any portion +of it, thus forming a work based on the Program, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) You must cause the modified files to carry prominent notices + stating that you changed the files and the date of any change. + + b) You must cause any work that you distribute or publish, that in + whole or in part contains or is derived from the Program or any + part thereof, to be licensed as a whole at no charge to all third + parties under the terms of this License. + + c) If the modified program normally reads commands interactively + when run, you must cause it, when started running for such + interactive use in the most ordinary way, to print or display an + announcement including an appropriate copyright notice and a + notice that there is no warranty (or else, saying that you provide + a warranty) and that users may redistribute the program under + these conditions, and telling the user how to view a copy of this + License. (Exception: if the Program itself is interactive but + does not normally print such an announcement, your work based on + the Program is not required to print an announcement.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Program, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Program, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Program. + +In addition, mere aggregation of another work not based on the Program +with the Program (or with a work based on the Program) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may copy and distribute the Program (or a work based on it, +under Section 2) in object code or executable form under the terms of +Sections 1 and 2 above provided that you also do one of the following: + + a) Accompany it with the complete corresponding machine-readable + source code, which must be distributed under the terms of Sections + 1 and 2 above on a medium customarily used for software interchange; or, + + b) Accompany it with a written offer, valid for at least three + years, to give any third party, for a charge no more than your + cost of physically performing source distribution, a complete + machine-readable copy of the corresponding source code, to be + distributed under the terms of Sections 1 and 2 above on a medium + customarily used for software interchange; or, + + c) Accompany it with the information you received as to the offer + to distribute corresponding source code. (This alternative is + allowed only for noncommercial distribution and only if you + received the program in object code or executable form with such + an offer, in accord with Subsection b above.) + +The source code for a work means the preferred form of the work for +making modifications to it. For an executable work, complete source +code means all the source code for all modules it contains, plus any +associated interface definition files, plus the scripts used to +control compilation and installation of the executable. However, as a +special exception, the source code distributed need not include +anything that is normally distributed (in either source or binary +form) with the major components (compiler, kernel, and so on) of the +operating system on which the executable runs, unless that component +itself accompanies the executable. + +If distribution of executable or object code is made by offering +access to copy from a designated place, then offering equivalent +access to copy the source code from the same place counts as +distribution of the source code, even though third parties are not +compelled to copy the source along with the object code. + + 4. You may not copy, modify, sublicense, or distribute the Program +except as expressly provided under this License. Any attempt +otherwise to copy, modify, sublicense or distribute the Program is +void, and will automatically terminate your rights under this License. +However, parties who have received copies, or rights, from you under +this License will not have their licenses terminated so long as such +parties remain in full compliance. + + 5. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Program or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Program (or any work based on the +Program), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Program or works based on it. + + 6. Each time you redistribute the Program (or any work based on the +Program), the recipient automatically receives a license from the +original licensor to copy, distribute or modify the Program subject to +these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties to +this License. + + 7. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Program at all. For example, if a patent +license would not permit royalty-free redistribution of the Program by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Program. + +If any portion of this section is held invalid or unenforceable under +any particular circumstance, the balance of the section is intended to +apply and the section as a whole is intended to apply in other +circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system, which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 8. If the distribution and/or use of the Program is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Program under this License +may add an explicit geographical distribution limitation excluding +those countries, so that distribution is permitted only in or among +countries not thus excluded. In such case, this License incorporates +the limitation as if written in the body of this License. + + 9. The Free Software Foundation may publish revised and/or new versions +of the General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + +Each version is given a distinguishing version number. If the Program +specifies a version number of this License which applies to it and "any +later version", you have the option of following the terms and conditions +either of that version or of any later version published by the Free +Software Foundation. If the Program does not specify a version number of +this License, you may choose any version ever published by the Free Software +Foundation. + + 10. If you wish to incorporate parts of the Program into other free +programs whose distribution conditions are different, write to the author +to ask for permission. For software which is copyrighted by the Free +Software Foundation, write to the Free Software Foundation; we sometimes +make exceptions for this. Our decision will be guided by the two goals +of preserving the free status of all derivatives of our free software and +of promoting the sharing and reuse of software generally. + + NO WARRANTY + + 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY +FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN +OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES +PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED +OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS +TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE +PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, +REPAIR OR CORRECTION. + + 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR +REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, +INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING +OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED +TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY +YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER +PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE +POSSIBILITY OF SUCH DAMAGES. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +convey the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + <one line to give the program's name and a brief idea of what it does.> + Copyright (C) <year> <name of author> + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License along + with this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + +Also add information on how to contact you by electronic and paper mail. + +If the program is interactive, make it output a short notice like this +when it starts in an interactive mode: + + Gnomovision version 69, Copyright (C) year name of author + Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, the commands you use may +be called something other than `show w' and `show c'; they could even be +mouse-clicks or menu items--whatever suits your program. + +You should also get your employer (if you work as a programmer) or your +school, if any, to sign a "copyright disclaimer" for the program, if +necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the program + `Gnomovision' (which makes passes at compilers) written by James Hacker. + + <signature of Ty Coon>, 1 April 1989 + Ty Coon, President of Vice + +This General Public License does not permit incorporating your program into +proprietary programs. If your program is a subroutine library, you may +consider it more useful to permit linking proprietary applications with the +library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. diff --git a/contrib/subtree/INSTALL b/contrib/subtree/INSTALL new file mode 100644 index 000000000000..7ab0cf450967 --- /dev/null +++ b/contrib/subtree/INSTALL @@ -0,0 +1,28 @@ +HOW TO INSTALL git-subtree +========================== + +First, build from the top source directory. + +Then, in contrib/subtree, run: + + make + make install + make install-doc + +If you used configure to do the main build the git-subtree build will +pick up those settings. If not, you will likely have to provide a +value for prefix: + + make prefix=<some dir> + make prefix=<some dir> install + make prefix=<some dir> install-doc + +To run tests first copy git-subtree to the main build area so the +newly-built git can find it: + + cp git-subtree ../.. + +Then: + + make test + diff --git a/contrib/subtree/Makefile b/contrib/subtree/Makefile new file mode 100644 index 000000000000..6906aae44147 --- /dev/null +++ b/contrib/subtree/Makefile @@ -0,0 +1,101 @@ +# The default target of this Makefile is... +all:: + +-include ../../config.mak.autogen +-include ../../config.mak + +prefix ?= /usr/local +gitexecdir ?= $(prefix)/libexec/git-core +mandir ?= $(prefix)/share/man +man1dir ?= $(mandir)/man1 +htmldir ?= $(prefix)/share/doc/git-doc + +../../GIT-VERSION-FILE: FORCE + $(MAKE) -C ../../ GIT-VERSION-FILE + +-include ../../GIT-VERSION-FILE + +# this should be set to a 'standard' bsd-type install program +INSTALL ?= install +RM ?= rm -f + +ASCIIDOC = asciidoc +ASCIIDOC_CONF = -f ../../Documentation/asciidoc.conf +ASCIIDOC_HTML = xhtml11 +ASCIIDOC_DOCBOOK = docbook +ASCIIDOC_EXTRA = +XMLTO = xmlto + +ifdef USE_ASCIIDOCTOR +ASCIIDOC = asciidoctor +ASCIIDOC_CONF = +ASCIIDOC_HTML = xhtml5 +ASCIIDOC_DOCBOOK = docbook45 +ASCIIDOC_EXTRA += -I../../Documentation -rasciidoctor-extensions +ASCIIDOC_EXTRA += -alitdd='&\#x2d;&\#x2d;' +endif + +ifndef SHELL_PATH + SHELL_PATH = /bin/sh +endif +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) + +MANPAGE_XSL = ../../Documentation/manpage-normal.xsl + +GIT_SUBTREE_SH := git-subtree.sh +GIT_SUBTREE := git-subtree + +GIT_SUBTREE_DOC := git-subtree.1 +GIT_SUBTREE_XML := git-subtree.xml +GIT_SUBTREE_TXT := git-subtree.txt +GIT_SUBTREE_HTML := git-subtree.html +GIT_SUBTREE_TEST := ../../git-subtree + +all:: $(GIT_SUBTREE) + +$(GIT_SUBTREE): $(GIT_SUBTREE_SH) + sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' $< >$@ + chmod +x $@ + +doc: $(GIT_SUBTREE_DOC) $(GIT_SUBTREE_HTML) + +man: $(GIT_SUBTREE_DOC) + +html: $(GIT_SUBTREE_HTML) + +install: $(GIT_SUBTREE) + $(INSTALL) -d -m 755 $(DESTDIR)$(gitexecdir) + $(INSTALL) -m 755 $(GIT_SUBTREE) $(DESTDIR)$(gitexecdir) + +install-doc: install-man install-html + +install-man: $(GIT_SUBTREE_DOC) + $(INSTALL) -d -m 755 $(DESTDIR)$(man1dir) + $(INSTALL) -m 644 $^ $(DESTDIR)$(man1dir) + +install-html: $(GIT_SUBTREE_HTML) + $(INSTALL) -d -m 755 $(DESTDIR)$(htmldir) + $(INSTALL) -m 644 $^ $(DESTDIR)$(htmldir) + +$(GIT_SUBTREE_DOC): $(GIT_SUBTREE_XML) + $(XMLTO) -m $(MANPAGE_XSL) man $^ + +$(GIT_SUBTREE_XML): $(GIT_SUBTREE_TXT) + $(ASCIIDOC) -b $(ASCIIDOC_DOCBOOK) -d manpage $(ASCIIDOC_CONF) \ + -agit_version=$(GIT_VERSION) $(ASCIIDOC_EXTRA) $^ + +$(GIT_SUBTREE_HTML): $(GIT_SUBTREE_TXT) + $(ASCIIDOC) -b $(ASCIIDOC_HTML) -d manpage $(ASCIIDOC_CONF) \ + -agit_version=$(GIT_VERSION) $(ASCIIDOC_EXTRA) $^ + +$(GIT_SUBTREE_TEST): $(GIT_SUBTREE) + cp $< $@ + +test: $(GIT_SUBTREE_TEST) + $(MAKE) -C t/ test + +clean: + $(RM) $(GIT_SUBTREE) + $(RM) *.xml *.html *.1 + +.PHONY: FORCE diff --git a/contrib/subtree/README b/contrib/subtree/README new file mode 100644 index 000000000000..c686b4a69b12 --- /dev/null +++ b/contrib/subtree/README @@ -0,0 +1,8 @@ + +Please read git-subtree.txt for documentation. + +Please don't contact me using github mail; it's slow, ugly, and worst of +all, redundant. Email me instead at apenwarr@gmail.com and I'll be happy to +help. + +Avery diff --git a/contrib/subtree/git-subtree.sh b/contrib/subtree/git-subtree.sh new file mode 100755 index 000000000000..868e18b9a1ab --- /dev/null +++ b/contrib/subtree/git-subtree.sh @@ -0,0 +1,901 @@ +#!/bin/sh +# +# git-subtree.sh: split/join git repositories in subdirectories of this one +# +# Copyright (C) 2009 Avery Pennarun <apenwarr@gmail.com> +# +if test $# -eq 0 +then + set -- -h +fi +OPTS_SPEC="\ +git subtree add --prefix=<prefix> <commit> +git subtree add --prefix=<prefix> <repository> <ref> +git subtree merge --prefix=<prefix> <commit> +git subtree pull --prefix=<prefix> <repository> <ref> +git subtree push --prefix=<prefix> <repository> <ref> +git subtree split --prefix=<prefix> <commit> +-- +h,help show the help +q quiet +d show debug messages +P,prefix= the name of the subdir to split out +m,message= use the given message as the commit message for the merge commit + options for 'split' +annotate= add a prefix to commit message of new commits +b,branch= create a new branch from the split subtree +ignore-joins ignore prior --rejoin commits +onto= try connecting new tree to an existing one +rejoin merge the new branch back into HEAD + options for 'add', 'merge', and 'pull' +squash merge subtree changes as a single commit +" +eval "$(echo "$OPTS_SPEC" | git rev-parse --parseopt -- "$@" || echo exit $?)" + +PATH=$PATH:$(git --exec-path) +. git-sh-setup + +require_work_tree + +quiet= +branch= +debug= +command= +onto= +rejoin= +ignore_joins= +annotate= +squash= +message= +prefix= + +debug () { + if test -n "$debug" + then + printf "%s\n" "$*" >&2 + fi +} + +say () { + if test -z "$quiet" + then + printf "%s\n" "$*" >&2 + fi +} + +progress () { + if test -z "$quiet" + then + printf "%s\r" "$*" >&2 + fi +} + +assert () { + if ! "$@" + then + die "assertion failed: " "$@" + fi +} + +ensure_single_rev () { + if test $# -ne 1 + then + die "You must provide exactly one revision. Got: '$@'" + fi +} + +while test $# -gt 0 +do + opt="$1" + shift + + case "$opt" in + -q) + quiet=1 + ;; + -d) + debug=1 + ;; + --annotate) + annotate="$1" + shift + ;; + --no-annotate) + annotate= + ;; + -b) + branch="$1" + shift + ;; + -P) + prefix="${1%/}" + shift + ;; + -m) + message="$1" + shift + ;; + --no-prefix) + prefix= + ;; + --onto) + onto="$1" + shift + ;; + --no-onto) + onto= + ;; + --rejoin) + rejoin=1 + ;; + --no-rejoin) + rejoin= + ;; + --ignore-joins) + ignore_joins=1 + ;; + --no-ignore-joins) + ignore_joins= + ;; + --squash) + squash=1 + ;; + --no-squash) + squash= + ;; + --) + break + ;; + *) + die "Unexpected option: $opt" + ;; + esac +done + +command="$1" +shift + +case "$command" in +add|merge|pull) + default= + ;; +split|push) + default="--default HEAD" + ;; +*) + die "Unknown command '$command'" + ;; +esac + +if test -z "$prefix" +then + die "You must provide the --prefix option." +fi + +case "$command" in +add) + test -e "$prefix" && + die "prefix '$prefix' already exists." + ;; +*) + test -e "$prefix" || + die "'$prefix' does not exist; use 'git subtree add'" + ;; +esac + +dir="$(dirname "$prefix/.")" + +if test "$command" != "pull" && + test "$command" != "add" && + test "$command" != "push" +then + revs=$(git rev-parse $default --revs-only "$@") || exit $? + dirs=$(git rev-parse --no-revs --no-flags "$@") || exit $? + ensure_single_rev $revs + if test -n "$dirs" + then + die "Error: Use --prefix instead of bare filenames." + fi +fi + +debug "command: {$command}" +debug "quiet: {$quiet}" +debug "revs: {$revs}" +debug "dir: {$dir}" +debug "opts: {$*}" +debug + +cache_setup () { + cachedir="$GIT_DIR/subtree-cache/$$" + rm -rf "$cachedir" || + die "Can't delete old cachedir: $cachedir" + mkdir -p "$cachedir" || + die "Can't create new cachedir: $cachedir" + mkdir -p "$cachedir/notree" || + die "Can't create new cachedir: $cachedir/notree" + debug "Using cachedir: $cachedir" >&2 +} + +cache_get () { + for oldrev in "$@" + do + if test -r "$cachedir/$oldrev" + then + read newrev <"$cachedir/$oldrev" + echo $newrev + fi + done +} + +cache_miss () { + for oldrev in "$@" + do + if ! test -r "$cachedir/$oldrev" + then + echo $oldrev + fi + done +} + +check_parents () { + missed=$(cache_miss "$1") + local indent=$(($2 + 1)) + for miss in $missed + do + if ! test -r "$cachedir/notree/$miss" + then + debug " incorrect order: $miss" + process_split_commit "$miss" "" "$indent" + fi + done +} + +set_notree () { + echo "1" > "$cachedir/notree/$1" +} + +cache_set () { + oldrev="$1" + newrev="$2" + if test "$oldrev" != "latest_old" && + test "$oldrev" != "latest_new" && + test -e "$cachedir/$oldrev" + then + die "cache for $oldrev already exists!" + fi + echo "$newrev" >"$cachedir/$oldrev" +} + +rev_exists () { + if git rev-parse "$1" >/dev/null 2>&1 + then + return 0 + else + return 1 + fi +} + +rev_is_descendant_of_branch () { + newrev="$1" + branch="$2" + branch_hash=$(git rev-parse "$branch") + match=$(git rev-list -1 "$branch_hash" "^$newrev") + + if test -z "$match" + then + return 0 + else + return 1 + fi +} + +# if a commit doesn't have a parent, this might not work. But we only want +# to remove the parent from the rev-list, and since it doesn't exist, it won't +# be there anyway, so do nothing in that case. +try_remove_previous () { + if rev_exists "$1^" + then + echo "^$1^" + fi +} + +find_latest_squash () { + debug "Looking for latest squash ($dir)..." + dir="$1" + sq= + main= + sub= + git log --grep="^git-subtree-dir: $dir/*\$" \ + --no-show-signature --pretty=format:'START %H%n%s%n%n%b%nEND%n' HEAD | + while read a b junk + do + debug "$a $b $junk" + debug "{{$sq/$main/$sub}}" + case "$a" in + START) + sq="$b" + ;; + git-subtree-mainline:) + main="$b" + ;; + git-subtree-split:) + sub="$(git rev-parse "$b^0")" || + die "could not rev-parse split hash $b from commit $sq" + ;; + END) + if test -n "$sub" + then + if test -n "$main" + then + # a rejoin commit? + # Pretend its sub was a squash. + sq="$sub" + fi + debug "Squash found: $sq $sub" + echo "$sq" "$sub" + break + fi + sq= + main= + sub= + ;; + esac + done +} + +find_existing_splits () { + debug "Looking for prior splits..." + dir="$1" + revs="$2" + main= + sub= + local grep_format="^git-subtree-dir: $dir/*\$" + if test -n "$ignore_joins" + then + grep_format="^Add '$dir/' from commit '" + fi + git log --grep="$grep_format" \ + --no-show-signature --pretty=format:'START %H%n%s%n%n%b%nEND%n' $revs | + while read a b junk + do + case "$a" in + START) + sq="$b" + ;; + git-subtree-mainline:) + main="$b" + ;; + git-subtree-split:) + sub="$(git rev-parse "$b^0")" || + die "could not rev-parse split hash $b from commit $sq" + ;; + END) + debug " Main is: '$main'" + if test -z "$main" -a -n "$sub" + then + # squash commits refer to a subtree + debug " Squash: $sq from $sub" + cache_set "$sq" "$sub" + fi + if test -n "$main" -a -n "$sub" + then + debug " Prior: $main -> $sub" + cache_set $main $sub + cache_set $sub $sub + try_remove_previous "$main" + try_remove_previous "$sub" + fi + main= + sub= + ;; + esac + done +} + +copy_commit () { + # We're going to set some environment vars here, so + # do it in a subshell to get rid of them safely later + debug copy_commit "{$1}" "{$2}" "{$3}" + git log -1 --no-show-signature --pretty=format:'%an%n%ae%n%aD%n%cn%n%ce%n%cD%n%B' "$1" | + ( + read GIT_AUTHOR_NAME + read GIT_AUTHOR_EMAIL + read GIT_AUTHOR_DATE + read GIT_COMMITTER_NAME + read GIT_COMMITTER_EMAIL + read GIT_COMMITTER_DATE + export GIT_AUTHOR_NAME \ + GIT_AUTHOR_EMAIL \ + GIT_AUTHOR_DATE \ + GIT_COMMITTER_NAME \ + GIT_COMMITTER_EMAIL \ + GIT_COMMITTER_DATE + ( + printf "%s" "$annotate" + cat + ) | + git commit-tree "$2" $3 # reads the rest of stdin + ) || die "Can't copy commit $1" +} + +add_msg () { + dir="$1" + latest_old="$2" + latest_new="$3" + if test -n "$message" + then + commit_message="$message" + else + commit_message="Add '$dir/' from commit '$latest_new'" + fi + cat <<-EOF + $commit_message + + git-subtree-dir: $dir + git-subtree-mainline: $latest_old + git-subtree-split: $latest_new + EOF +} + +add_squashed_msg () { + if test -n "$message" + then + echo "$message" + else + echo "Merge commit '$1' as '$2'" + fi +} + +rejoin_msg () { + dir="$1" + latest_old="$2" + latest_new="$3" + if test -n "$message" + then + commit_message="$message" + else + commit_message="Split '$dir/' into commit '$latest_new'" + fi + cat <<-EOF + $commit_message + + git-subtree-dir: $dir + git-subtree-mainline: $latest_old + git-subtree-split: $latest_new + EOF +} + +squash_msg () { + dir="$1" + oldsub="$2" + newsub="$3" + newsub_short=$(git rev-parse --short "$newsub") + + if test -n "$oldsub" + then + oldsub_short=$(git rev-parse --short "$oldsub") + echo "Squashed '$dir/' changes from $oldsub_short..$newsub_short" + echo + git log --no-show-signature --pretty=tformat:'%h %s' "$oldsub..$newsub" + git log --no-show-signature --pretty=tformat:'REVERT: %h %s' "$newsub..$oldsub" + else + echo "Squashed '$dir/' content from commit $newsub_short" + fi + + echo + echo "git-subtree-dir: $dir" + echo "git-subtree-split: $newsub" +} + +toptree_for_commit () { + commit="$1" + git rev-parse --verify "$commit^{tree}" || exit $? +} + +subtree_for_commit () { + commit="$1" + dir="$2" + git ls-tree "$commit" -- "$dir" | + while read mode type tree name + do + assert test "$name" = "$dir" + assert test "$type" = "tree" -o "$type" = "commit" + test "$type" = "commit" && continue # ignore submodules + echo $tree + break + done +} + +tree_changed () { + tree=$1 + shift + if test $# -ne 1 + then + return 0 # weird parents, consider it changed + else + ptree=$(toptree_for_commit $1) + if test "$ptree" != "$tree" + then + return 0 # changed + else + return 1 # not changed + fi + fi +} + +new_squash_commit () { + old="$1" + oldsub="$2" + newsub="$3" + tree=$(toptree_for_commit $newsub) || exit $? + if test -n "$old" + then + squash_msg "$dir" "$oldsub" "$newsub" | + git commit-tree "$tree" -p "$old" || exit $? + else + squash_msg "$dir" "" "$newsub" | + git commit-tree "$tree" || exit $? + fi +} + +copy_or_skip () { + rev="$1" + tree="$2" + newparents="$3" + assert test -n "$tree" + + identical= + nonidentical= + p= + gotparents= + copycommit= + for parent in $newparents + do + ptree=$(toptree_for_commit $parent) || exit $? + test -z "$ptree" && continue + if test "$ptree" = "$tree" + then + # an identical parent could be used in place of this rev. + if test -n "$identical" + then + # if a previous identical parent was found, check whether + # one is already an ancestor of the other + mergebase=$(git merge-base $identical $parent) + if test "$identical" = "$mergebase" + then + # current identical commit is an ancestor of parent + identical="$parent" + elif test "$parent" != "$mergebase" + then + # no common history; commit must be copied + copycommit=1 + fi + else + # first identical parent detected + identical="$parent" + fi + else + nonidentical="$parent" + fi + + # sometimes both old parents map to the same newparent; + # eliminate duplicates + is_new=1 + for gp in $gotparents + do + if test "$gp" = "$parent" + then + is_new= + break + fi + done + if test -n "$is_new" + then + gotparents="$gotparents $parent" + p="$p -p $parent" + fi + done + + if test -n "$identical" && test -n "$nonidentical" + then + extras=$(git rev-list --count $identical..$nonidentical) + if test "$extras" -ne 0 + then + # we need to preserve history along the other branch + copycommit=1 + fi + fi + if test -n "$identical" && test -z "$copycommit" + then + echo $identical + else + copy_commit "$rev" "$tree" "$p" || exit $? + fi +} + +ensure_clean () { + if ! git diff-index HEAD --exit-code --quiet 2>&1 + then + die "Working tree has modifications. Cannot add." + fi + if ! git diff-index --cached HEAD --exit-code --quiet 2>&1 + then + die "Index has modifications. Cannot add." + fi +} + +ensure_valid_ref_format () { + git check-ref-format "refs/heads/$1" || + die "'$1' does not look like a ref" +} + +process_split_commit () { + local rev="$1" + local parents="$2" + local indent=$3 + + if test $indent -eq 0 + then + revcount=$(($revcount + 1)) + else + # processing commit without normal parent information; + # fetch from repo + parents=$(git rev-parse "$rev^@") + extracount=$(($extracount + 1)) + fi + + progress "$revcount/$revmax ($createcount) [$extracount]" + + debug "Processing commit: $rev" + exists=$(cache_get "$rev") + if test -n "$exists" + then + debug " prior: $exists" + return + fi + createcount=$(($createcount + 1)) + debug " parents: $parents" + check_parents "$parents" "$indent" + newparents=$(cache_get $parents) + debug " newparents: $newparents" + + tree=$(subtree_for_commit "$rev" "$dir") + debug " tree is: $tree" + + # ugly. is there no better way to tell if this is a subtree + # vs. a mainline commit? Does it matter? + if test -z "$tree" + then + set_notree "$rev" + if test -n "$newparents" + then + cache_set "$rev" "$rev" + fi + return + fi + + newrev=$(copy_or_skip "$rev" "$tree" "$newparents") || exit $? + debug " newrev is: $newrev" + cache_set "$rev" "$newrev" + cache_set latest_new "$newrev" + cache_set latest_old "$rev" +} + +cmd_add () { + if test -e "$dir" + then + die "'$dir' already exists. Cannot add." + fi + + ensure_clean + + if test $# -eq 1 + then + git rev-parse -q --verify "$1^{commit}" >/dev/null || + die "'$1' does not refer to a commit" + + cmd_add_commit "$@" + + elif test $# -eq 2 + then + # Technically we could accept a refspec here but we're + # just going to turn around and add FETCH_HEAD under the + # specified directory. Allowing a refspec might be + # misleading because we won't do anything with any other + # branches fetched via the refspec. + ensure_valid_ref_format "$2" + + cmd_add_repository "$@" + else + say "error: parameters were '$@'" + die "Provide either a commit or a repository and commit." + fi +} + +cmd_add_repository () { + echo "git fetch" "$@" + repository=$1 + refspec=$2 + git fetch "$@" || exit $? + revs=FETCH_HEAD + set -- $revs + cmd_add_commit "$@" +} + +cmd_add_commit () { + rev=$(git rev-parse $default --revs-only "$@") || exit $? + ensure_single_rev $rev + + debug "Adding $dir as '$rev'..." + git read-tree --prefix="$dir" $rev || exit $? + git checkout -- "$dir" || exit $? + tree=$(git write-tree) || exit $? + + headrev=$(git rev-parse HEAD) || exit $? + if test -n "$headrev" && test "$headrev" != "$rev" + then + headp="-p $headrev" + else + headp= + fi + + if test -n "$squash" + then + rev=$(new_squash_commit "" "" "$rev") || exit $? + commit=$(add_squashed_msg "$rev" "$dir" | + git commit-tree "$tree" $headp -p "$rev") || exit $? + else + revp=$(peel_committish "$rev") && + commit=$(add_msg "$dir" $headrev "$rev" | + git commit-tree "$tree" $headp -p "$revp") || exit $? + fi + git reset "$commit" || exit $? + + say "Added dir '$dir'" +} + +cmd_split () { + debug "Splitting $dir..." + cache_setup || exit $? + + if test -n "$onto" + then + debug "Reading history for --onto=$onto..." + git rev-list $onto | + while read rev + do + # the 'onto' history is already just the subdir, so + # any parent we find there can be used verbatim + debug " cache: $rev" + cache_set "$rev" "$rev" + done + fi + + unrevs="$(find_existing_splits "$dir" "$revs")" + + # We can't restrict rev-list to only $dir here, because some of our + # parents have the $dir contents the root, and those won't match. + # (and rev-list --follow doesn't seem to solve this) + grl='git rev-list --topo-order --reverse --parents $revs $unrevs' + revmax=$(eval "$grl" | wc -l) + revcount=0 + createcount=0 + extracount=0 + eval "$grl" | + while read rev parents + do + process_split_commit "$rev" "$parents" 0 + done || exit $? + + latest_new=$(cache_get latest_new) + if test -z "$latest_new" + then + die "No new revisions were found" + fi + + if test -n "$rejoin" + then + debug "Merging split branch into HEAD..." + latest_old=$(cache_get latest_old) + git merge -s ours \ + --allow-unrelated-histories \ + -m "$(rejoin_msg "$dir" "$latest_old" "$latest_new")" \ + "$latest_new" >&2 || exit $? + fi + if test -n "$branch" + then + if rev_exists "refs/heads/$branch" + then + if ! rev_is_descendant_of_branch "$latest_new" "$branch" + then + die "Branch '$branch' is not an ancestor of commit '$latest_new'." + fi + action='Updated' + else + action='Created' + fi + git update-ref -m 'subtree split' \ + "refs/heads/$branch" "$latest_new" || exit $? + say "$action branch '$branch'" + fi + echo "$latest_new" + exit 0 +} + +cmd_merge () { + rev=$(git rev-parse $default --revs-only "$@") || exit $? + ensure_single_rev $rev + ensure_clean + + if test -n "$squash" + then + first_split="$(find_latest_squash "$dir")" + if test -z "$first_split" + then + die "Can't squash-merge: '$dir' was never added." + fi + set $first_split + old=$1 + sub=$2 + if test "$sub" = "$rev" + then + say "Subtree is already at commit $rev." + exit 0 + fi + new=$(new_squash_commit "$old" "$sub" "$rev") || exit $? + debug "New squash commit: $new" + rev="$new" + fi + + version=$(git version) + if test "$version" \< "git version 1.7" + then + if test -n "$message" + then + git merge -s subtree --message="$message" "$rev" + else + git merge -s subtree "$rev" + fi + else + if test -n "$message" + then + git merge -Xsubtree="$prefix" \ + --message="$message" "$rev" + else + git merge -Xsubtree="$prefix" $rev + fi + fi +} + +cmd_pull () { + if test $# -ne 2 + then + die "You must provide <repository> <ref>" + fi + ensure_clean + ensure_valid_ref_format "$2" + git fetch "$@" || exit $? + revs=FETCH_HEAD + set -- $revs + cmd_merge "$@" +} + +cmd_push () { + if test $# -ne 2 + then + die "You must provide <repository> <ref>" + fi + ensure_valid_ref_format "$2" + if test -e "$dir" + then + repository=$1 + refspec=$2 + echo "git push using: " "$repository" "$refspec" + localrev=$(git subtree split --prefix="$prefix") || die + git push "$repository" "$localrev":"refs/heads/$refspec" + else + die "'$dir' must already exist. Try 'git subtree add'." + fi +} + +"cmd_$command" "$@" diff --git a/contrib/subtree/git-subtree.txt b/contrib/subtree/git-subtree.txt new file mode 100644 index 000000000000..352deda69dcf --- /dev/null +++ b/contrib/subtree/git-subtree.txt @@ -0,0 +1,351 @@ +git-subtree(1) +============== + +NAME +---- +git-subtree - Merge subtrees together and split repository into subtrees + + +SYNOPSIS +-------- +[verse] +'git subtree' add -P <prefix> <commit> +'git subtree' add -P <prefix> <repository> <ref> +'git subtree' pull -P <prefix> <repository> <ref> +'git subtree' push -P <prefix> <repository> <ref> +'git subtree' merge -P <prefix> <commit> +'git subtree' split -P <prefix> [OPTIONS] [<commit>] + + +DESCRIPTION +----------- +Subtrees allow subprojects to be included within a subdirectory +of the main project, optionally including the subproject's +entire history. + +For example, you could include the source code for a library +as a subdirectory of your application. + +Subtrees are not to be confused with submodules, which are meant for +the same task. Unlike submodules, subtrees do not need any special +constructions (like .gitmodules files or gitlinks) be present in +your repository, and do not force end-users of your +repository to do anything special or to understand how subtrees +work. A subtree is just a subdirectory that can be +committed to, branched, and merged along with your project in +any way you want. + +They are also not to be confused with using the subtree merge +strategy. The main difference is that, besides merging +the other project as a subdirectory, you can also extract the +entire history of a subdirectory from your project and make it +into a standalone project. Unlike the subtree merge strategy +you can alternate back and forth between these +two operations. If the standalone library gets updated, you can +automatically merge the changes into your project; if you +update the library inside your project, you can "split" the +changes back out again and merge them back into the library +project. + +For example, if a library you made for one application ends up being +useful elsewhere, you can extract its entire history and publish +that as its own git repository, without accidentally +intermingling the history of your application project. + +[TIP] +In order to keep your commit messages clean, we recommend that +people split their commits between the subtrees and the main +project as much as possible. That is, if you make a change that +affects both the library and the main application, commit it in +two pieces. That way, when you split the library commits out +later, their descriptions will still make sense. But if this +isn't important to you, it's not *necessary*. git subtree will +simply leave out the non-library-related parts of the commit +when it splits it out into the subproject later. + + +COMMANDS +-------- +add:: + Create the <prefix> subtree by importing its contents + from the given <commit> or <repository> and remote <ref>. + A new commit is created automatically, joining the imported + project's history with your own. With '--squash', imports + only a single commit from the subproject, rather than its + entire history. + +merge:: + Merge recent changes up to <commit> into the <prefix> + subtree. As with normal 'git merge', this doesn't + remove your own local changes; it just merges those + changes into the latest <commit>. With '--squash', + creates only one commit that contains all the changes, + rather than merging in the entire history. ++ +If you use '--squash', the merge direction doesn't always have to be +forward; you can use this command to go back in time from v2.5 to v2.4, +for example. If your merge introduces a conflict, you can resolve it in +the usual ways. + +pull:: + Exactly like 'merge', but parallels 'git pull' in that + it fetches the given ref from the specified remote + repository. + +push:: + Does a 'split' (see below) using the <prefix> supplied + and then does a 'git push' to push the result to the + repository and ref. This can be used to push your + subtree to different branches of the remote repository. + +split:: + Extract a new, synthetic project history from the + history of the <prefix> subtree. The new history + includes only the commits (including merges) that + affected <prefix>, and each of those commits now has the + contents of <prefix> at the root of the project instead + of in a subdirectory. Thus, the newly created history + is suitable for export as a separate git repository. ++ +After splitting successfully, a single commit id is printed to stdout. +This corresponds to the HEAD of the newly created tree, which you can +manipulate however you want. ++ +Repeated splits of exactly the same history are guaranteed to be +identical (i.e. to produce the same commit ids). Because of this, if +you add new commits and then re-split, the new commits will be attached +as commits on top of the history you generated last time, so 'git merge' +and friends will work as expected. ++ +Note that if you use '--squash' when you merge, you should usually not +just '--rejoin' when you split. + + +OPTIONS +------- +-q:: +--quiet:: + Suppress unnecessary output messages on stderr. + +-d:: +--debug:: + Produce even more unnecessary output messages on stderr. + +-P <prefix>:: +--prefix=<prefix>:: + Specify the path in the repository to the subtree you + want to manipulate. This option is mandatory + for all commands. + +-m <message>:: +--message=<message>:: + This option is only valid for add, merge and pull (unsure). + Specify <message> as the commit message for the merge commit. + + +OPTIONS FOR add, merge, push, pull +---------------------------------- +--squash:: + This option is only valid for add, merge, and pull + commands. ++ +Instead of merging the entire history from the subtree project, produce +only a single commit that contains all the differences you want to +merge, and then merge that new commit into your project. ++ +Using this option helps to reduce log clutter. People rarely want to see +every change that happened between v1.0 and v1.1 of the library they're +using, since none of the interim versions were ever included in their +application. ++ +Using '--squash' also helps avoid problems when the same subproject is +included multiple times in the same project, or is removed and then +re-added. In such a case, it doesn't make sense to combine the +histories anyway, since it's unclear which part of the history belongs +to which subtree. ++ +Furthermore, with '--squash', you can switch back and forth between +different versions of a subtree, rather than strictly forward. 'git +subtree merge --squash' always adjusts the subtree to match the exactly +specified commit, even if getting to that commit would require undoing +some changes that were added earlier. ++ +Whether or not you use '--squash', changes made in your local repository +remain intact and can be later split and send upstream to the +subproject. + + +OPTIONS FOR split +----------------- +--annotate=<annotation>:: + This option is only valid for the split command. ++ +When generating synthetic history, add <annotation> as a prefix to each +commit message. Since we're creating new commits with the same commit +message, but possibly different content, from the original commits, this +can help to differentiate them and avoid confusion. ++ +Whenever you split, you need to use the same <annotation>, or else you +don't have a guarantee that the new re-created history will be identical +to the old one. That will prevent merging from working correctly. git +subtree tries to make it work anyway, particularly if you use --rejoin, +but it may not always be effective. + +-b <branch>:: +--branch=<branch>:: + This option is only valid for the split command. ++ +After generating the synthetic history, create a new branch called +<branch> that contains the new history. This is suitable for immediate +pushing upstream. <branch> must not already exist. + +--ignore-joins:: + This option is only valid for the split command. ++ +If you use '--rejoin', git subtree attempts to optimize its history +reconstruction to generate only the new commits since the last +'--rejoin'. '--ignore-join' disables this behaviour, forcing it to +regenerate the entire history. In a large project, this can take a long +time. + +--onto=<onto>:: + This option is only valid for the split command. ++ +If your subtree was originally imported using something other than git +subtree, its history may not match what git subtree is expecting. In +that case, you can specify the commit id <onto> that corresponds to the +first revision of the subproject's history that was imported into your +project, and git subtree will attempt to build its history from there. ++ +If you used 'git subtree add', you should never need this option. + +--rejoin:: + This option is only valid for the split command. ++ +After splitting, merge the newly created synthetic history back into +your main project. That way, future splits can search only the part of +history that has been added since the most recent --rejoin. ++ +If your split commits end up merged into the upstream subproject, and +then you want to get the latest upstream version, this will allow git's +merge algorithm to more intelligently avoid conflicts (since it knows +these synthetic commits are already part of the upstream repository). ++ +Unfortunately, using this option results in 'git log' showing an extra +copy of every new commit that was created (the original, and the +synthetic one). ++ +If you do all your merges with '--squash', don't use '--rejoin' when you +split, because you don't want the subproject's history to be part of +your project anyway. + + +EXAMPLE 1. Add command +---------------------- +Let's assume that you have a local repository that you would like +to add an external vendor library to. In this case we will add the +git-subtree repository as a subdirectory of your already existing +git-extensions repository in ~/git-extensions/: + + $ git subtree add --prefix=git-subtree --squash \ + git://github.com/apenwarr/git-subtree.git master + +'master' needs to be a valid remote ref and can be a different branch +name + +You can omit the --squash flag, but doing so will increase the number +of commits that are included in your local repository. + +We now have a ~/git-extensions/git-subtree directory containing code +from the master branch of git://github.com/apenwarr/git-subtree.git +in our git-extensions repository. + +EXAMPLE 2. Extract a subtree using commit, merge and pull +--------------------------------------------------------- +Let's use the repository for the git source code as an example. +First, get your own copy of the git.git repository: + + $ git clone git://git.kernel.org/pub/scm/git/git.git test-git + $ cd test-git + +gitweb (commit 1130ef3) was merged into git as of commit +0a8f4f0, after which it was no longer maintained separately. +But imagine it had been maintained separately, and we wanted to +extract git's changes to gitweb since that time, to share with +the upstream. You could do this: + + $ git subtree split --prefix=gitweb --annotate='(split) ' \ + 0a8f4f0^.. --onto=1130ef3 --rejoin \ + --branch gitweb-latest + $ gitk gitweb-latest + $ git push git@github.com:whatever/gitweb.git gitweb-latest:master + +(We use '0a8f4f0^..' because that means "all the changes from +0a8f4f0 to the current version, including 0a8f4f0 itself.") + +If gitweb had originally been merged using 'git subtree add' (or +a previous split had already been done with --rejoin specified) +then you can do all your splits without having to remember any +weird commit ids: + + $ git subtree split --prefix=gitweb --annotate='(split) ' --rejoin \ + --branch gitweb-latest2 + +And you can merge changes back in from the upstream project just +as easily: + + $ git subtree pull --prefix=gitweb \ + git@github.com:whatever/gitweb.git master + +Or, using '--squash', you can actually rewind to an earlier +version of gitweb: + + $ git subtree merge --prefix=gitweb --squash gitweb-latest~10 + +Then make some changes: + + $ date >gitweb/myfile + $ git add gitweb/myfile + $ git commit -m 'created myfile' + +And fast forward again: + + $ git subtree merge --prefix=gitweb --squash gitweb-latest + +And notice that your change is still intact: + + $ ls -l gitweb/myfile + +And you can split it out and look at your changes versus +the standard gitweb: + + git log gitweb-latest..$(git subtree split --prefix=gitweb) + +EXAMPLE 3. Extract a subtree using branch +----------------------------------------- +Suppose you have a source directory with many files and +subdirectories, and you want to extract the lib directory to its own +git project. Here's a short way to do it: + +First, make the new repository wherever you want: + + $ <go to the new location> + $ git init --bare + +Back in your original directory: + + $ git subtree split --prefix=lib --annotate="(split)" -b split + +Then push the new branch onto the new empty repository: + + $ git push <new-repo> split:master + + +AUTHOR +------ +Written by Avery Pennarun <apenwarr@gmail.com> + + +GIT +--- +Part of the linkgit:git[1] suite diff --git a/contrib/subtree/t/Makefile b/contrib/subtree/t/Makefile new file mode 100644 index 000000000000..276898eb6bd7 --- /dev/null +++ b/contrib/subtree/t/Makefile @@ -0,0 +1,86 @@ +# Run tests +# +# Copyright (c) 2005 Junio C Hamano +# + +-include ../../../config.mak.autogen +-include ../../../config.mak + +#GIT_TEST_OPTS=--verbose --debug +SHELL_PATH ?= $(SHELL) +PERL_PATH ?= /usr/bin/perl +TAR ?= $(TAR) +RM ?= rm -f +PROVE ?= prove +DEFAULT_TEST_TARGET ?= test +TEST_LINT ?= test-lint + +ifdef TEST_OUTPUT_DIRECTORY +TEST_RESULTS_DIRECTORY = $(TEST_OUTPUT_DIRECTORY)/test-results +else +TEST_RESULTS_DIRECTORY = ../../../t/test-results +endif + +# Shell quote; +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) +PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH)) +TEST_RESULTS_DIRECTORY_SQ = $(subst ','\'',$(TEST_RESULTS_DIRECTORY)) + +T = $(sort $(wildcard t[0-9][0-9][0-9][0-9]-*.sh)) +TSVN = $(sort $(wildcard t91[0-9][0-9]-*.sh)) +TGITWEB = $(sort $(wildcard t95[0-9][0-9]-*.sh)) +THELPERS = $(sort $(filter-out $(T),$(wildcard *.sh))) + +all: $(DEFAULT_TEST_TARGET) + +test: pre-clean $(TEST_LINT) + $(MAKE) aggregate-results-and-cleanup + +prove: pre-clean $(TEST_LINT) + @echo "*** prove ***"; GIT_CONFIG=.git/config $(PROVE) --exec '$(SHELL_PATH_SQ)' $(GIT_PROVE_OPTS) $(T) :: $(GIT_TEST_OPTS) + $(MAKE) clean-except-prove-cache + +$(T): + @echo "*** $@ ***"; GIT_CONFIG=.git/config '$(SHELL_PATH_SQ)' $@ $(GIT_TEST_OPTS) + +pre-clean: + $(RM) -r '$(TEST_RESULTS_DIRECTORY_SQ)' + +clean-except-prove-cache: + $(RM) -r 'trash directory'.* '$(TEST_RESULTS_DIRECTORY_SQ)' + $(RM) -r valgrind/bin + +clean: clean-except-prove-cache + $(RM) .prove + +test-lint: test-lint-duplicates test-lint-executable test-lint-shell-syntax + +test-lint-duplicates: + @dups=`echo $(T) | tr ' ' '\n' | sed 's/-.*//' | sort | uniq -d` && \ + test -z "$$dups" || { \ + echo >&2 "duplicate test numbers:" $$dups; exit 1; } + +test-lint-executable: + @bad=`for i in $(T); do test -x "$$i" || echo $$i; done` && \ + test -z "$$bad" || { \ + echo >&2 "non-executable tests:" $$bad; exit 1; } + +test-lint-shell-syntax: + @'$(PERL_PATH_SQ)' ../../../t/check-non-portable-shell.pl $(T) $(THELPERS) + +aggregate-results-and-cleanup: $(T) + $(MAKE) aggregate-results + $(MAKE) clean + +aggregate-results: + for f in '$(TEST_RESULTS_DIRECTORY_SQ)'/t*-*.counts; do \ + echo "$$f"; \ + done | '$(SHELL_PATH_SQ)' ../../../t/aggregate-results.sh + +valgrind: + $(MAKE) GIT_TEST_OPTS="$(GIT_TEST_OPTS) --valgrind" + +test-results: + mkdir -p test-results + +.PHONY: pre-clean $(T) aggregate-results clean valgrind diff --git a/contrib/subtree/t/t7900-subtree.sh b/contrib/subtree/t/t7900-subtree.sh new file mode 100755 index 000000000000..57ff4b25c17e --- /dev/null +++ b/contrib/subtree/t/t7900-subtree.sh @@ -0,0 +1,1034 @@ +#!/bin/sh +# +# Copyright (c) 2012 Avery Pennaraum +# Copyright (c) 2015 Alexey Shumkin +# +test_description='Basic porcelain support for subtrees + +This test verifies the basic operation of the add, pull, merge +and split subcommands of git subtree. +' + +TEST_DIRECTORY=$(pwd)/../../../t +export TEST_DIRECTORY + +. ../../../t/test-lib.sh + +subtree_test_create_repo() +{ + test_create_repo "$1" && + ( + cd "$1" && + git config log.date relative + ) +} + +create() +{ + echo "$1" >"$1" && + git add "$1" +} + +check_equal() +{ + test_debug 'echo' + test_debug "echo \"check a:\" \"{$1}\"" + test_debug "echo \" b:\" \"{$2}\"" + if [ "$1" = "$2" ]; then + return 0 + else + return 1 + fi +} + +undo() +{ + git reset --hard HEAD~ +} + +# Make sure no patch changes more than one file. +# The original set of commits changed only one file each. +# A multi-file change would imply that we pruned commits +# too aggressively. +join_commits() +{ + commit= + all= + while read x y; do + if [ -z "$x" ]; then + continue + elif [ "$x" = "commit:" ]; then + if [ -n "$commit" ]; then + echo "$commit $all" + all= + fi + commit="$y" + else + all="$all $y" + fi + done + echo "$commit $all" +} + +test_create_commit() ( + repo=$1 && + commit=$2 && + cd "$repo" && + mkdir -p "$(dirname "$commit")" \ + || error "Could not create directory for commit" + echo "$commit" >"$commit" && + git add "$commit" || error "Could not add commit" + git commit -m "$commit" || error "Could not commit" +) + +last_commit_message() +{ + git log --pretty=format:%s -1 +} + +subtree_test_count=0 +next_test() { + subtree_test_count=$(($subtree_test_count+1)) +} + +# +# Tests for 'git subtree add' +# + +next_test +test_expect_success 'no merge from non-existent subtree' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + test_must_fail git subtree merge --prefix="sub dir" FETCH_HEAD + ) +' + +next_test +test_expect_success 'no pull from non-existent subtree' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + test_must_fail git subtree pull --prefix="sub dir" ./"sub proj" master + )' + +next_test +test_expect_success 'add subproj as subtree into sub dir/ with --prefix' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD && + check_equal "$(last_commit_message)" "Add '\''sub dir/'\'' from commit '\''$(git rev-parse FETCH_HEAD)'\''" + ) +' + +next_test +test_expect_success 'add subproj as subtree into sub dir/ with --prefix and --message' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" --message="Added subproject" FETCH_HEAD && + check_equal "$(last_commit_message)" "Added subproject" + ) +' + +next_test +test_expect_success 'add subproj as subtree into sub dir/ with --prefix as -P and --message as -m' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add -P "sub dir" -m "Added subproject" FETCH_HEAD && + check_equal "$(last_commit_message)" "Added subproject" + ) +' + +next_test +test_expect_success 'add subproj as subtree into sub dir/ with --squash and --prefix and --message' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" --message="Added subproject with squash" --squash FETCH_HEAD && + check_equal "$(last_commit_message)" "Added subproject with squash" + ) +' + +# +# Tests for 'git subtree merge' +# + +next_test +test_expect_success 'merge new subproj history into sub dir/ with --prefix' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count/sub proj" sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + check_equal "$(last_commit_message)" "Merge commit '\''$(git rev-parse FETCH_HEAD)'\''" + ) +' + +next_test +test_expect_success 'merge new subproj history into sub dir/ with --prefix and --message' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count/sub proj" sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" --message="Merged changes from subproject" FETCH_HEAD && + check_equal "$(last_commit_message)" "Merged changes from subproject" + ) +' + +next_test +test_expect_success 'merge new subproj history into sub dir/ with --squash and --prefix and --message' ' + subtree_test_create_repo "$subtree_test_count/sub proj" && + subtree_test_create_repo "$subtree_test_count" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count/sub proj" sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" --message="Merged changes from subproject using squash" --squash FETCH_HEAD && + check_equal "$(last_commit_message)" "Merged changes from subproject using squash" + ) +' + +next_test +test_expect_success 'merge the added subproj again, should do nothing' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD && + # this shouldn not actually do anything, since FETCH_HEAD + # is already a parent + result=$(git merge -s ours -m "merge -s -ours" FETCH_HEAD) && + check_equal "${result}" "Already up to date." + ) +' + +next_test +test_expect_success 'merge new subproj history into subdir/ with a slash appended to the argument of --prefix' ' + test_create_repo "$test_count" && + test_create_repo "$test_count/subproj" && + test_create_commit "$test_count" main1 && + test_create_commit "$test_count/subproj" sub1 && + ( + cd "$test_count" && + git fetch ./subproj master && + git subtree add --prefix=subdir/ FETCH_HEAD + ) && + test_create_commit "$test_count/subproj" sub2 && + ( + cd "$test_count" && + git fetch ./subproj master && + git subtree merge --prefix=subdir/ FETCH_HEAD && + check_equal "$(last_commit_message)" "Merge commit '\''$(git rev-parse FETCH_HEAD)'\''" + ) +' + +# +# Tests for 'git subtree split' +# + +next_test +test_expect_success 'split requires option --prefix' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD && + echo "You must provide the --prefix option." > expected && + test_must_fail git subtree split > actual 2>&1 && + test_debug "printf '"expected: "'" && + test_debug "cat expected" && + test_debug "printf '"actual: "'" && + test_debug "cat actual" && + test_cmp expected actual + ) +' + +next_test +test_expect_success 'split requires path given by option --prefix must exist' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD && + echo "'\''non-existent-directory'\'' does not exist; use '\''git subtree add'\''" > expected && + test_must_fail git subtree split --prefix=non-existent-directory > actual 2>&1 && + test_debug "printf '"expected: "'" && + test_debug "cat expected" && + test_debug "printf '"actual: "'" && + test_debug "cat actual" && + test_cmp expected actual + ) +' + +next_test +test_expect_success 'split sub dir/ with --rejoin' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + split_hash=$(git subtree split --prefix="sub dir" --annotate="*") && + git subtree split --prefix="sub dir" --annotate="*" --rejoin && + check_equal "$(last_commit_message)" "Split '\''sub dir/'\'' into commit '\''$split_hash'\''" + ) + ' + +next_test +test_expect_success 'split sub dir/ with --rejoin from scratch' ' + subtree_test_create_repo "$subtree_test_count" && + test_create_commit "$subtree_test_count" main1 && + ( + cd "$subtree_test_count" && + mkdir "sub dir" && + echo file >"sub dir"/file && + git add "sub dir/file" && + git commit -m"sub dir file" && + split_hash=$(git subtree split --prefix="sub dir" --rejoin) && + git subtree split --prefix="sub dir" --rejoin && + check_equal "$(last_commit_message)" "Split '\''sub dir/'\'' into commit '\''$split_hash'\''" + ) + ' + +next_test +test_expect_success 'split sub dir/ with --rejoin and --message' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + git subtree split --prefix="sub dir" --message="Split & rejoin" --annotate="*" --rejoin && + check_equal "$(last_commit_message)" "Split & rejoin" + ) +' + +next_test +test_expect_success 'split "sub dir"/ with --branch' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + split_hash=$(git subtree split --prefix="sub dir" --annotate="*") && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br && + check_equal "$(git rev-parse subproj-br)" "$split_hash" + ) +' + +next_test +test_expect_success 'check hash of split' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + split_hash=$(git subtree split --prefix="sub dir" --annotate="*") && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br && + check_equal "$(git rev-parse subproj-br)" "$split_hash" && + # Check hash of split + new_hash=$(git rev-parse subproj-br^2) && + ( + cd ./"sub proj" && + subdir_hash=$(git rev-parse HEAD) && + check_equal ''"$new_hash"'' "$subdir_hash" + ) + ) +' + +next_test +test_expect_success 'split "sub dir"/ with --branch for an existing branch' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git branch subproj-br FETCH_HEAD && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + split_hash=$(git subtree split --prefix="sub dir" --annotate="*") && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br && + check_equal "$(git rev-parse subproj-br)" "$split_hash" + ) +' + +next_test +test_expect_success 'split "sub dir"/ with --branch for an incompatible branch' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git branch init HEAD && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + test_must_fail git subtree split --prefix="sub dir" --branch init + ) +' + +# +# Validity checking +# + +next_test +test_expect_success 'make sure exactly the right set of files ends up in the subproj' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + test_create_commit "$subtree_test_count/sub proj" sub3 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub3 && + ( + cd "$subtree_test_count/sub proj" && + git fetch .. subproj-br && + git merge FETCH_HEAD + ) && + test_create_commit "$subtree_test_count/sub proj" sub4 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub4 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + ( + cd "$subtree_test_count/sub proj" && + git fetch .. subproj-br && + git merge FETCH_HEAD && + + test_write_lines main-sub1 main-sub2 main-sub3 main-sub4 \ + sub1 sub2 sub3 sub4 >expect && + git ls-files >actual && + test_cmp expect actual + ) +' + +next_test +test_expect_success 'make sure the subproj *only* contains commits that affect the "sub dir"' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + test_create_commit "$subtree_test_count/sub proj" sub3 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub3 && + ( + cd "$subtree_test_count/sub proj" && + git fetch .. subproj-br && + git merge FETCH_HEAD + ) && + test_create_commit "$subtree_test_count/sub proj" sub4 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub4 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + ( + cd "$subtree_test_count/sub proj" && + git fetch .. subproj-br && + git merge FETCH_HEAD && + + test_write_lines main-sub1 main-sub2 main-sub3 main-sub4 \ + sub1 sub2 sub3 sub4 >expect && + git log --name-only --pretty=format:"" >log && + sort <log | sed "/^\$/ d" >actual && + test_cmp expect actual + ) +' + +next_test +test_expect_success 'make sure exactly the right set of files ends up in the mainline' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + test_create_commit "$subtree_test_count/sub proj" sub3 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub3 && + ( + cd "$subtree_test_count/sub proj" && + git fetch .. subproj-br && + git merge FETCH_HEAD + ) && + test_create_commit "$subtree_test_count/sub proj" sub4 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub4 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + ( + cd "$subtree_test_count/sub proj" && + git fetch .. subproj-br && + git merge FETCH_HEAD + ) && + ( + cd "$subtree_test_count" && + git subtree pull --prefix="sub dir" ./"sub proj" master && + + test_write_lines main1 main2 >chkm && + test_write_lines main-sub1 main-sub2 main-sub3 main-sub4 >chkms && + sed "s,^,sub dir/," chkms >chkms_sub && + test_write_lines sub1 sub2 sub3 sub4 >chks && + sed "s,^,sub dir/," chks >chks_sub && + + cat chkm chkms_sub chks_sub >expect && + git ls-files >actual && + test_cmp expect actual + ) +' + +next_test +test_expect_success 'make sure each filename changed exactly once in the entire history' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git config log.date relative && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + test_create_commit "$subtree_test_count/sub proj" sub3 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub3 && + ( + cd "$subtree_test_count/sub proj" && + git fetch .. subproj-br && + git merge FETCH_HEAD + ) && + test_create_commit "$subtree_test_count/sub proj" sub4 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub4 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + ( + cd "$subtree_test_count/sub proj" && + git fetch .. subproj-br && + git merge FETCH_HEAD + ) && + ( + cd "$subtree_test_count" && + git subtree pull --prefix="sub dir" ./"sub proj" master && + + test_write_lines main1 main2 >chkm && + test_write_lines sub1 sub2 sub3 sub4 >chks && + test_write_lines main-sub1 main-sub2 main-sub3 main-sub4 >chkms && + sed "s,^,sub dir/," chkms >chkms_sub && + + # main-sub?? and /"sub dir"/main-sub?? both change, because those are the + # changes that were split into their own history. And "sub dir"/sub?? never + # change, since they were *only* changed in the subtree branch. + git log --name-only --pretty=format:"" >log && + sort <log >sorted-log && + sed "/^$/ d" sorted-log >actual && + + cat chkms chkm chks chkms_sub >expect-unsorted && + sort expect-unsorted >expect && + test_cmp expect actual + ) +' + +next_test +test_expect_success 'make sure the --rejoin commits never make it into subproj' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + test_create_commit "$subtree_test_count/sub proj" sub3 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub3 && + ( + cd "$subtree_test_count/sub proj" && + git fetch .. subproj-br && + git merge FETCH_HEAD + ) && + test_create_commit "$subtree_test_count/sub proj" sub4 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub4 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + ( + cd "$subtree_test_count/sub proj" && + git fetch .. subproj-br && + git merge FETCH_HEAD + ) && + ( + cd "$subtree_test_count" && + git subtree pull --prefix="sub dir" ./"sub proj" master && + check_equal "$(git log --pretty=format:"%s" HEAD^2 | grep -i split)" "" + ) +' + +next_test +test_expect_success 'make sure no "git subtree" tagged commits make it into subproj' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + test_create_commit "$subtree_test_count/sub proj" sub3 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub3 && + ( + cd "$subtree_test_count/sub proj" && + git fetch .. subproj-br && + git merge FETCH_HEAD + ) && + test_create_commit "$subtree_test_count/sub proj" sub4 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub4 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --annotate="*" --branch subproj-br --rejoin + ) && + ( + cd "$subtree_test_count/sub proj" && + git fetch .. subproj-br && + git merge FETCH_HEAD + ) && + ( + cd "$subtree_test_count" && + git subtree pull --prefix="sub dir" ./"sub proj" master && + + # They are meaningless to subproj since one side of the merge refers to the mainline + check_equal "$(git log --pretty=format:"%s%n%b" HEAD^2 | grep "git-subtree.*:")" "" + ) +' + +# +# A new set of tests +# + +next_test +test_expect_success 'make sure "git subtree split" find the correct parent' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count/sub proj" sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git branch subproj-ref FETCH_HEAD && + git subtree merge --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --branch subproj-br && + + # at this point, the new commit parent should be subproj-ref, if it is + # not, something went wrong (the "newparent" of "master~" commit should + # have been sub2, but it was not, because its cache was not set to + # itself) + check_equal "$(git log --pretty=format:%P -1 subproj-br)" "$(git rev-parse subproj-ref)" + ) +' + +next_test +test_expect_success 'split a new subtree without --onto option' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count/sub proj" sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --branch subproj-br + ) && + mkdir "$subtree_test_count"/"sub dir2" && + test_create_commit "$subtree_test_count" "sub dir2"/main-sub2 && + ( + cd "$subtree_test_count" && + + # also test that we still can split out an entirely new subtree + # if the parent of the first commit in the tree is not empty, + # then the new subtree has accidentally been attached to something + git subtree split --prefix="sub dir2" --branch subproj2-br && + check_equal "$(git log --pretty=format:%P -1 subproj2-br)" "" + ) +' + +next_test +test_expect_success 'verify one file change per commit' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git branch sub1 FETCH_HEAD && + git subtree add --prefix="sub dir" sub1 + ) && + test_create_commit "$subtree_test_count/sub proj" sub2 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir" --branch subproj-br + ) && + mkdir "$subtree_test_count"/"sub dir2" && + test_create_commit "$subtree_test_count" "sub dir2"/main-sub2 && + ( + cd "$subtree_test_count" && + git subtree split --prefix="sub dir2" --branch subproj2-br && + + x= && + git log --pretty=format:"commit: %H" | join_commits | + ( + while read commit a b; do + test_debug "echo Verifying commit $commit" + test_debug "echo a: $a" + test_debug "echo b: $b" + check_equal "$b" "" + x=1 + done + check_equal "$x" 1 + ) + ) +' + +next_test +test_expect_success 'push split to subproj' ' + subtree_test_create_repo "$subtree_test_count" && + subtree_test_create_repo "$subtree_test_count/sub proj" && + test_create_commit "$subtree_test_count" main1 && + test_create_commit "$subtree_test_count/sub proj" sub1 && + ( + cd "$subtree_test_count" && + git fetch ./"sub proj" master && + git subtree add --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub1 && + test_create_commit "$subtree_test_count" main2 && + test_create_commit "$subtree_test_count/sub proj" sub2 && + test_create_commit "$subtree_test_count" "sub dir"/main-sub2 && + ( + cd $subtree_test_count/"sub proj" && + git branch sub-branch-1 && + cd .. && + git fetch ./"sub proj" master && + git subtree merge --prefix="sub dir" FETCH_HEAD + ) && + test_create_commit "$subtree_test_count" "sub dir"/main-sub3 && + ( + cd "$subtree_test_count" && + git subtree push ./"sub proj" --prefix "sub dir" sub-branch-1 && + cd ./"sub proj" && + git checkout sub-branch-1 && + check_equal "$(last_commit_message)" "sub dir/main-sub3" + ) +' + +# +# This test covers 2 cases in subtree split copy_or_skip code +# 1) Merges where one parent is a superset of the changes of the other +# parent regarding changes to the subtree, in this case the merge +# commit should be copied +# 2) Merges where only one parent operate on the subtree, and the merge +# commit should be skipped +# +# (1) is checked by ensuring subtree_tip is a descendent of subtree_branch +# (2) should have a check added (not_a_subtree_change shouldn't be present +# on the produced subtree) +# +# Other related cases which are not tested (or currently handled correctly) +# - Case (1) where there are more than 2 parents, it will sometimes correctly copy +# the merge, and sometimes not +# - Merge commit where both parents have same tree as the merge, currently +# will always be skipped, even if they reached that state via different +# set of commits. +# + +next_test +test_expect_success 'subtree descendant check' ' + subtree_test_create_repo "$subtree_test_count" && + test_create_commit "$subtree_test_count" folder_subtree/a && + ( + cd "$subtree_test_count" && + git branch branch + ) && + test_create_commit "$subtree_test_count" folder_subtree/0 && + test_create_commit "$subtree_test_count" folder_subtree/b && + cherry=$(cd "$subtree_test_count"; git rev-parse HEAD) && + ( + cd "$subtree_test_count" && + git checkout branch + ) && + test_create_commit "$subtree_test_count" commit_on_branch && + ( + cd "$subtree_test_count" && + git cherry-pick $cherry && + git checkout master && + git merge -m "merge should be kept on subtree" branch && + git branch no_subtree_work_branch + ) && + test_create_commit "$subtree_test_count" folder_subtree/d && + ( + cd "$subtree_test_count" && + git checkout no_subtree_work_branch + ) && + test_create_commit "$subtree_test_count" not_a_subtree_change && + ( + cd "$subtree_test_count" && + git checkout master && + git merge -m "merge should be skipped on subtree" no_subtree_work_branch && + + git subtree split --prefix folder_subtree/ --branch subtree_tip master && + git subtree split --prefix folder_subtree/ --branch subtree_branch branch && + check_equal $(git rev-list --count subtree_tip..subtree_branch) 0 + ) +' + +test_done diff --git a/contrib/subtree/todo b/contrib/subtree/todo new file mode 100644 index 000000000000..0d0e77765175 --- /dev/null +++ b/contrib/subtree/todo @@ -0,0 +1,48 @@ + + delete tempdir + + 'git subtree rejoin' option to do the same as --rejoin, eg. after a + rebase + + --prefix doesn't force the subtree correctly in merge/pull: + "-s subtree" should be given an explicit subtree option? + There doesn't seem to be a way to do this. We'd have to + patch git-merge-subtree. Ugh. + (but we could avoid this problem by generating squashes with + exactly the right subtree structure, rather than using + subtree merge...) + + add a 'log' subcommand to see what's new in a subtree? + + add to-submodule and from-submodule commands + + automated tests for --squash stuff + + "add" command non-obviously requires a commitid; would be easier if + it had a "pull" sort of mode instead + + "pull" and "merge" commands should fail if you've never merged + that --prefix before + + docs should provide an example of "add" + + note that the initial split doesn't *have* to have a commitid + specified... that's just an optimization + + if you try to add (or maybe merge?) with an invalid commitid, you + get a misleading "prefix must end with /" message from + one of the other git tools that git-subtree calls. Should + detect this situation and print the *real* problem. + + "pull --squash" should do fetch-synthesize-merge, but instead just + does "pull" directly, which doesn't work at all. + + make a 'force-update' that does what 'add' does even if the subtree + already exists. That way we can help people who imported + subtrees "incorrectly" (eg. by just copying in the files) in + the past. + + guess --prefix automatically if possible based on pwd + + make a 'git subtree grafts' that automatically expands --squash'd + commits so you can see the full history if you want it. diff --git a/contrib/svn-fe/.gitignore b/contrib/svn-fe/.gitignore new file mode 100644 index 000000000000..02a779158572 --- /dev/null +++ b/contrib/svn-fe/.gitignore @@ -0,0 +1,4 @@ +/*.xml +/*.1 +/*.html +/svn-fe diff --git a/contrib/svn-fe/Makefile b/contrib/svn-fe/Makefile new file mode 100644 index 000000000000..e8651aaf4b53 --- /dev/null +++ b/contrib/svn-fe/Makefile @@ -0,0 +1,105 @@ +all:: svn-fe$X + +CC = cc +RM = rm -f +MV = mv + +CFLAGS = -g -O2 -Wall +LDFLAGS = +EXTLIBS = -lz + +include ../../config.mak.uname +-include ../../config.mak.autogen +-include ../../config.mak + +ifeq ($(uname_S),Darwin) + ifndef NO_FINK + ifeq ($(shell test -d /sw/lib && echo y),y) + CFLAGS += -I/sw/include + LDFLAGS += -L/sw/lib + endif + endif + ifndef NO_DARWIN_PORTS + ifeq ($(shell test -d /opt/local/lib && echo y),y) + CFLAGS += -I/opt/local/include + LDFLAGS += -L/opt/local/lib + endif + endif +endif + +ifndef NO_OPENSSL + EXTLIBS += -lssl + ifdef NEEDS_CRYPTO_WITH_SSL + EXTLIBS += -lcrypto + endif +endif + +ifndef NO_PTHREADS + CFLAGS += $(PTHREADS_CFLAGS) + EXTLIBS += $(PTHREAD_LIBS) +endif + +ifdef HAVE_CLOCK_GETTIME + CFLAGS += -DHAVE_CLOCK_GETTIME + EXTLIBS += -lrt +endif + +ifdef NEEDS_LIBICONV + EXTLIBS += -liconv +endif + +GIT_LIB = ../../libgit.a +VCSSVN_LIB = ../../vcs-svn/lib.a +XDIFF_LIB = ../../xdiff/lib.a + +LIBS = $(VCSSVN_LIB) $(GIT_LIB) $(XDIFF_LIB) + +QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir +QUIET_SUBDIR1 = + +ifneq ($(findstring $(MAKEFLAGS),w),w) +PRINT_DIR = --no-print-directory +else # "make -w" +NO_SUBDIR = : +endif + +ifneq ($(findstring $(MAKEFLAGS),s),s) +ifndef V + QUIET_CC = @echo ' ' CC $@; + QUIET_LINK = @echo ' ' LINK $@; + QUIET_SUBDIR0 = +@subdir= + QUIET_SUBDIR1 = ;$(NO_SUBDIR) echo ' ' SUBDIR $$subdir; \ + $(MAKE) $(PRINT_DIR) -C $$subdir +endif +endif + +svn-fe$X: svn-fe.o $(VCSSVN_LIB) $(XDIFF_LIB) $(GIT_LIB) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(EXTLIBS) -o $@ svn-fe.o $(LIBS) + +svn-fe.o: svn-fe.c ../../vcs-svn/svndump.h + $(QUIET_CC)$(CC) $(CFLAGS) -I../../vcs-svn -o $*.o -c $< + +svn-fe.html: svn-fe.txt + $(QUIET_SUBDIR0)../../Documentation $(QUIET_SUBDIR1) \ + MAN_TXT=../contrib/svn-fe/svn-fe.txt \ + ../contrib/svn-fe/$@ + +svn-fe.1: svn-fe.txt + $(QUIET_SUBDIR0)../../Documentation $(QUIET_SUBDIR1) \ + MAN_TXT=../contrib/svn-fe/svn-fe.txt \ + ../contrib/svn-fe/$@ + $(MV) ../../Documentation/svn-fe.1 . + +../../vcs-svn/lib.a: FORCE + $(QUIET_SUBDIR0)../.. $(QUIET_SUBDIR1) vcs-svn/lib.a + +../../xdiff/lib.a: FORCE + $(QUIET_SUBDIR0)../.. $(QUIET_SUBDIR1) xdiff/lib.a + +../../libgit.a: FORCE + $(QUIET_SUBDIR0)../.. $(QUIET_SUBDIR1) libgit.a + +clean: + $(RM) svn-fe$X svn-fe.o svn-fe.html svn-fe.xml svn-fe.1 + +.PHONY: all clean FORCE diff --git a/contrib/svn-fe/svn-fe.c b/contrib/svn-fe/svn-fe.c new file mode 100644 index 000000000000..f363505abb27 --- /dev/null +++ b/contrib/svn-fe/svn-fe.c @@ -0,0 +1,18 @@ +/* + * This file is in the public domain. + * You may freely use, modify, distribute, and relicense it. + */ + +#include <stdlib.h> +#include "svndump.h" + +int main(int argc, char **argv) +{ + if (svndump_init(NULL)) + return 1; + svndump_read((argc > 1) ? argv[1] : NULL, "refs/heads/master", + "refs/notes/svn/revs"); + svndump_deinit(); + svndump_reset(); + return 0; +} diff --git a/contrib/svn-fe/svn-fe.txt b/contrib/svn-fe/svn-fe.txt new file mode 100644 index 000000000000..a3425f4770c5 --- /dev/null +++ b/contrib/svn-fe/svn-fe.txt @@ -0,0 +1,71 @@ +svn-fe(1) +========= + +NAME +---- +svn-fe - convert an SVN "dumpfile" to a fast-import stream + +SYNOPSIS +-------- +[verse] +mkfifo backchannel && +svnadmin dump --deltas REPO | + svn-fe [url] 3<backchannel | + git fast-import --cat-blob-fd=3 3>backchannel + +DESCRIPTION +----------- + +Converts a Subversion dumpfile into input suitable for +git-fast-import(1) and similar importers. REPO is a path to a +Subversion repository mirrored on the local disk. Remote Subversion +repositories can be mirrored on local disk using the `svnsync` +command. + +Note: this tool is very young. The details of its commandline +interface may change in backward incompatible ways. + +INPUT FORMAT +------------ +Subversion's repository dump format is documented in full in +`notes/dump-load-format.txt` from the Subversion source tree. +Files in this format can be generated using the 'svnadmin dump' or +'svk admin dump' command. + +OUTPUT FORMAT +------------- +The fast-import format is documented by the git-fast-import(1) +manual page. + +NOTES +----- +Subversion dumps do not record a separate author and committer for +each revision, nor do they record a separate display name and email +address for each author. Like git-svn(1), 'svn-fe' will use the name + +--------- +user <user@UUID> +--------- + +as committer, where 'user' is the value of the `svn:author` property +and 'UUID' the repository's identifier. + +To support incremental imports, 'svn-fe' puts a `git-svn-id` line at +the end of each commit log message if passed a URL on the command +line. This line has the form `git-svn-id: URL@REVNO UUID`. + +The resulting repository will generally require further processing +to put each project in its own repository and to separate the history +of each branch. The 'git filter-branch --subdirectory-filter' command +may be useful for this purpose. + +BUGS +---- +Empty directories and unknown properties are silently discarded. + +The exit status does not reflect whether an error was detected. + +SEE ALSO +-------- +git-svn(1), svn2git(1), svk(1), git-filter-branch(1), git-fast-import(1), +https://svn.apache.org/repos/asf/subversion/trunk/notes/dump-load-format.txt diff --git a/contrib/svn-fe/svnrdump_sim.py b/contrib/svn-fe/svnrdump_sim.py new file mode 100755 index 000000000000..11ac6f692733 --- /dev/null +++ b/contrib/svn-fe/svnrdump_sim.py @@ -0,0 +1,68 @@ +#!/usr/bin/python +""" +Simulates svnrdump by replaying an existing dump from a file, taking care +of the specified revision range. +To simulate incremental imports the environment variable SVNRMAX can be set +to the highest revision that should be available. +""" +import sys +import os + +if sys.hexversion < 0x02040000: + # The limiter is the ValueError() calls. This may be too conservative + sys.stderr.write("svnrdump-sim.py: requires Python 2.4 or later.\n") + sys.exit(1) + + +def getrevlimit(): + var = 'SVNRMAX' + if var in os.environ: + return os.environ[var] + return None + + +def writedump(url, lower, upper): + if url.startswith('sim://'): + filename = url[6:] + if filename[-1] == '/': + filename = filename[:-1] # remove terminating slash + else: + raise ValueError('sim:// url required') + f = open(filename, 'r') + state = 'header' + wroterev = False + while(True): + l = f.readline() + if l == '': + break + if state == 'header' and l.startswith('Revision-number: '): + state = 'prefix' + if state == 'prefix' and l == 'Revision-number: %s\n' % lower: + state = 'selection' + if not upper == 'HEAD' and state == 'selection' and \ + l == 'Revision-number: %s\n' % upper: + break + + if state == 'header' or state == 'selection': + if state == 'selection': + wroterev = True + sys.stdout.write(l) + return wroterev + +if __name__ == "__main__": + if not (len(sys.argv) in (3, 4, 5)): + print("usage: %s dump URL -rLOWER:UPPER") + sys.exit(1) + if not sys.argv[1] == 'dump': + raise NotImplementedError('only "dump" is suppported.') + url = sys.argv[2] + r = ('0', 'HEAD') + if len(sys.argv) == 4 and sys.argv[3][0:2] == '-r': + r = sys.argv[3][2:].lstrip().split(':') + if not getrevlimit() is None: + r[1] = getrevlimit() + if writedump(url, r[0], r[1]): + ret = 0 + else: + ret = 1 + sys.exit(ret) diff --git a/contrib/thunderbird-patch-inline/README b/contrib/thunderbird-patch-inline/README new file mode 100644 index 000000000000..000147bbe4a0 --- /dev/null +++ b/contrib/thunderbird-patch-inline/README @@ -0,0 +1,20 @@ +appp.sh is a script that is supposed to be used together with ExternalEditor +for Mozilla Thunderbird. It will let you include patches inline in e-mails +in an easy way. + +Usage: +- Generate the patch with git format-patch. +- Start writing a new e-mail in Thunderbird. +- Press the external editor button (or Ctrl-E) to run appp.sh +- Select the previously generated patch file. +- Finish editing the e-mail. + +Any text that is entered into the message editor before appp.sh is called +will be moved to the section between the --- and the diffstat. + +All S-O-B:s and Cc:s in the patch will be added to the CC list. + +To set it up, just install External Editor and tell it to use appp.sh as the +editor. + +Zenity is a required dependency. diff --git a/contrib/thunderbird-patch-inline/appp.sh b/contrib/thunderbird-patch-inline/appp.sh new file mode 100755 index 000000000000..1053872eea90 --- /dev/null +++ b/contrib/thunderbird-patch-inline/appp.sh @@ -0,0 +1,55 @@ +#!/bin/sh +# Copyright 2008 Lukas Sandström <luksan@gmail.com> +# +# AppendPatch - A script to be used together with ExternalEditor +# for Mozilla Thunderbird to properly include patches inline in e-mails. + +# ExternalEditor can be downloaded at http://globs.org/articles.php?lng=en&pg=2 + +CONFFILE=~/.appprc + +SEP="-=-=-=-=-=-=-=-=-=# Don't remove this line #=-=-=-=-=-=-=-=-=-" +if [ -e "$CONFFILE" ] ; then + LAST_DIR=$(grep -m 1 "^LAST_DIR=" "${CONFFILE}"|sed -e 's/^LAST_DIR=//') + cd "${LAST_DIR}" +else + cd > /dev/null +fi + +PATCH=$(zenity --file-selection) + +if [ "$?" != "0" ] ; then + #zenity --error --text "No patchfile given." + exit 1 +fi + +cd - > /dev/null + +SUBJECT=$(sed -n -e '/^Subject: /p' "${PATCH}") +HEADERS=$(sed -e '/^'"${SEP}"'$/,$d' $1) +BODY=$(sed -e "1,/${SEP}/d" $1) +CMT_MSG=$(sed -e '1,/^$/d' -e '/^---$/,$d' "${PATCH}") +DIFF=$(sed -e '1,/^---$/d' "${PATCH}") + +CCS=$(echo -e "$CMT_MSG\n$HEADERS" | sed -n -e 's/^Cc: \(.*\)$/\1,/gp' \ + -e 's/^Signed-off-by: \(.*\)/\1,/gp') + +echo "$SUBJECT" > $1 +echo "Cc: $CCS" >> $1 +echo "$HEADERS" | sed -e '/^Subject: /d' -e '/^Cc: /d' >> $1 +echo "$SEP" >> $1 + +echo "$CMT_MSG" >> $1 +echo "---" >> $1 +if [ "x${BODY}x" != "xx" ] ; then + echo >> $1 + echo "$BODY" >> $1 + echo >> $1 +fi +echo "$DIFF" >> $1 + +LAST_DIR=$(dirname "${PATCH}") + +grep -v "^LAST_DIR=" "${CONFFILE}" > "${CONFFILE}_" +echo "LAST_DIR=${LAST_DIR}" >> "${CONFFILE}_" +mv "${CONFFILE}_" "${CONFFILE}" diff --git a/contrib/update-unicode/.gitignore b/contrib/update-unicode/.gitignore new file mode 100644 index 000000000000..b0ebc6aad214 --- /dev/null +++ b/contrib/update-unicode/.gitignore @@ -0,0 +1,3 @@ +uniset/ +UnicodeData.txt +EastAsianWidth.txt diff --git a/contrib/update-unicode/README b/contrib/update-unicode/README new file mode 100644 index 000000000000..151a1970419f --- /dev/null +++ b/contrib/update-unicode/README @@ -0,0 +1,20 @@ +TL;DR: Run update_unicode.sh after the publication of a new Unicode +standard and commit the resulting unicode-widths.h file. + +The long version +================ + +The Git source code ships the file unicode-widths.h which contains +tables of zero and double width Unicode code points, respectively. +These tables are generated using update_unicode.sh in this directory. +update_unicode.sh itself uses a third-party tool, uniset, to query two +Unicode data files for the interesting code points. + +On first run, update_unicode.sh clones uniset from Github and builds it. +This requires a current-ish version of autoconf (2.69 works per December +2016). + +On each run, update_unicode.sh checks whether more recent Unicode data +files are available from the Unicode consortium, and rebuilds the header +unicode-widths.h with the new data. The new header can then be +committed. diff --git a/contrib/update-unicode/update_unicode.sh b/contrib/update-unicode/update_unicode.sh new file mode 100755 index 000000000000..aa90865befa4 --- /dev/null +++ b/contrib/update-unicode/update_unicode.sh @@ -0,0 +1,33 @@ +#!/bin/sh +#See http://www.unicode.org/reports/tr44/ +# +#Me Enclosing_Mark an enclosing combining mark +#Mn Nonspacing_Mark a nonspacing combining mark (zero advance width) +#Cf Format a format control character +# +cd "$(dirname "$0")" +UNICODEWIDTH_H=$(git rev-parse --show-toplevel)/unicode-width.h + +wget -N http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt \ + http://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt && +if ! test -d uniset; then + git clone https://github.com/depp/uniset.git && + ( cd uniset && git checkout 4b186196dd ) +fi && +( + cd uniset && + if ! test -x uniset; then + autoreconf -i && + ./configure --enable-warnings=-Werror CFLAGS='-O0 -ggdb' + fi && + make +) && +UNICODE_DIR=. && export UNICODE_DIR && +cat >$UNICODEWIDTH_H <<-EOF +static const struct interval zero_width[] = { + $(uniset/uniset --32 cat:Me,Mn,Cf + U+1160..U+11FF - U+00AD) +}; +static const struct interval double_width[] = { + $(uniset/uniset --32 eaw:F,W) +}; +EOF diff --git a/contrib/vscode/.gitattributes b/contrib/vscode/.gitattributes new file mode 100644 index 000000000000..e89f2236efea --- /dev/null +++ b/contrib/vscode/.gitattributes @@ -0,0 +1 @@ +init.sh whitespace=-indent-with-non-tab diff --git a/contrib/vscode/README.md b/contrib/vscode/README.md new file mode 100644 index 000000000000..8202d62035f9 --- /dev/null +++ b/contrib/vscode/README.md @@ -0,0 +1,14 @@ +Configuration for VS Code +========================= + +[VS Code](https://code.visualstudio.com/) is a lightweight but powerful source +code editor which runs on your desktop and is available for +[Windows](https://code.visualstudio.com/docs/setup/windows), +[macOS](https://code.visualstudio.com/docs/setup/mac) and +[Linux](https://code.visualstudio.com/docs/setup/linux). Among other languages, +it has [support for C/C++ via an extension](https://github.com/Microsoft/vscode-cpptools). + +To start developing Git with VS Code, simply run the Unix shell script called +`init.sh` in this directory, which creates the configuration files in +`.vscode/` that VS Code consumes. `init.sh` needs access to `make` and `gcc`, +so run the script in a Git SDK shell if you are using Windows. diff --git a/contrib/vscode/init.sh b/contrib/vscode/init.sh new file mode 100755 index 000000000000..27de94994b5d --- /dev/null +++ b/contrib/vscode/init.sh @@ -0,0 +1,375 @@ +#!/bin/sh + +die () { + echo "$*" >&2 + exit 1 +} + +cd "$(dirname "$0")"/../.. || +die "Could not cd to top-level directory" + +mkdir -p .vscode || +die "Could not create .vscode/" + +# General settings + +cat >.vscode/settings.json.new <<\EOF || +{ + "C_Cpp.intelliSenseEngine": "Default", + "C_Cpp.intelliSenseEngineFallback": "Disabled", + "[git-commit]": { + "editor.wordWrap": "wordWrapColumn", + "editor.wordWrapColumn": 72 + }, + "[c]": { + "editor.detectIndentation": false, + "editor.insertSpaces": false, + "editor.tabSize": 8, + "editor.wordWrap": "wordWrapColumn", + "editor.wordWrapColumn": 80, + "files.trimTrailingWhitespace": true + }, + "files.associations": { + "*.h": "c", + "*.c": "c" + }, + "cSpell.ignorePaths": [ + ], + "cSpell.words": [ + "DATAW", + "DBCACHED", + "DFCHECK", + "DTYPE", + "Hamano", + "HCAST", + "HEXSZ", + "HKEY", + "HKLM", + "IFGITLINK", + "IFINVALID", + "ISBROKEN", + "ISGITLINK", + "ISSYMREF", + "Junio", + "LPDWORD", + "LPPROC", + "LPWSTR", + "MSVCRT", + "NOARG", + "NOCOMPLETE", + "NOINHERIT", + "RENORMALIZE", + "STARTF", + "STARTUPINFOEXW", + "Schindelin", + "UCRT", + "YESNO", + "argcp", + "beginthreadex", + "committish", + "contentp", + "cpath", + "cpidx", + "ctim", + "dequote", + "envw", + "ewah", + "fdata", + "fherr", + "fhin", + "fhout", + "fragp", + "fsmonitor", + "hnsec", + "idents", + "includeif", + "interpr", + "iprog", + "isexe", + "iskeychar", + "kompare", + "mksnpath", + "mktag", + "mktree", + "mmblob", + "mmbuffer", + "mmfile", + "noenv", + "nparents", + "ntpath", + "ondisk", + "ooid", + "oplen", + "osdl", + "pnew", + "pold", + "ppinfo", + "pushf", + "pushv", + "rawsz", + "rebasing", + "reencode", + "repo", + "rerere", + "scld", + "sharedrepo", + "spawnv", + "spawnve", + "spawnvpe", + "strdup'ing", + "submodule", + "submodules", + "topath", + "topo", + "tpatch", + "unexecutable", + "unhide", + "unkc", + "unkv", + "unmark", + "unmatch", + "unsets", + "unshown", + "untracked", + "untrackedcache", + "unuse", + "upos", + "uval", + "vreportf", + "wargs", + "wargv", + "wbuffer", + "wcmd", + "wcsnicmp", + "wcstoutfdup", + "wdeltaenv", + "wdir", + "wenv", + "wenvblk", + "wenvcmp", + "wenviron", + "wenvpos", + "wenvsz", + "wfile", + "wfilename", + "wfopen", + "wfreopen", + "wfullpath", + "which'll", + "wlink", + "wmain", + "wmkdir", + "wmktemp", + "wnewpath", + "wotype", + "wpath", + "wpathname", + "wpgmptr", + "wpnew", + "wpointer", + "wpold", + "wpos", + "wputenv", + "wrmdir", + "wship", + "wtarget", + "wtemplate", + "wunlink", + "xcalloc", + "xgetcwd", + "xmallocz", + "xmemdupz", + "xmmap", + "xopts", + "xrealloc", + "xsnprintf", + "xutftowcs", + "xutftowcsn", + "xwcstoutf" + ], + "cSpell.ignoreRegExpList": [ + "\\\"(DIRC|FSMN|REUC|UNTR)\\\"", + "\\\\u[0-9a-fA-Fx]{4}\\b", + "\\b(filfre|frotz|xyzzy)\\b", + "\\bCMIT_FMT_DEFAULT\\b", + "\\bde-munge\\b", + "\\bGET_OID_DISAMBIGUATORS\\b", + "\\bHASH_RENORMALIZE\\b", + "\\bTREESAMEness\\b", + "\\bUSE_STDEV\\b", + "\\Wchar *\\*\\W*utfs\\W", + "cURL's", + "nedmalloc'ed", + "ntifs\\.h", + ], +} +EOF +die "Could not write settings.json" + +# Infer some setup-specific locations/names + +GCCPATH="$(which gcc)" +GDBPATH="$(which gdb)" +MAKECOMMAND="make -j5 DEVELOPER=1" +OSNAME= +X= +case "$(uname -s)" in +MINGW*) + GCCPATH="$(cygpath -am "$GCCPATH")" + GDBPATH="$(cygpath -am "$GDBPATH")" + MAKE_BASH="$(cygpath -am /git-cmd.exe) --command=usr\\\\bin\\\\bash.exe" + MAKECOMMAND="$MAKE_BASH -lc \\\"$MAKECOMMAND\\\"" + OSNAME=Win32 + X=.exe + ;; +Linux) + OSNAME=Linux + ;; +Darwin) + OSNAME=macOS + ;; +esac + +# Default build task + +cat >.vscode/tasks.json.new <<EOF || +{ + // See https://go.microsoft.com/fwlink/?LinkId=733558 + // for the documentation about the tasks.json format + "version": "2.0.0", + "tasks": [ + { + "label": "make", + "type": "shell", + "command": "$MAKECOMMAND", + "group": { + "kind": "build", + "isDefault": true + } + } + ] +} +EOF +die "Could not install default build task" + +# Debugger settings + +cat >.vscode/launch.json.new <<EOF || +{ + // Use IntelliSense to learn about possible attributes. + // Hover to view descriptions of existing attributes. + // For more information, visit: + // https://go.microsoft.com/fwlink/?linkid=830387 + "version": "0.2.0", + "configurations": [ + { + "name": "(gdb) Launch", + "type": "cppdbg", + "request": "launch", + "program": "\${workspaceFolder}/git$X", + "args": [], + "stopAtEntry": false, + "cwd": "\${workspaceFolder}", + "environment": [], + "externalConsole": true, + "MIMode": "gdb", + "miDebuggerPath": "$GDBPATH", + "setupCommands": [ + { + "description": "Enable pretty-printing for gdb", + "text": "-enable-pretty-printing", + "ignoreFailures": true + } + ] + } + ] +} +EOF +die "Could not write launch configuration" + +# C/C++ extension settings + +make -f - OSNAME=$OSNAME GCCPATH="$GCCPATH" vscode-init \ + >.vscode/c_cpp_properties.json <<\EOF || +include Makefile + +vscode-init: + @mkdir -p .vscode && \ + incs= && defs= && \ + for e in $(ALL_CFLAGS) \ + '-DGIT_EXEC_PATH="$(gitexecdir_SQ)"' \ + '-DGIT_LOCALE_PATH="$(localedir_relative_SQ)"' \ + '-DBINDIR="$(bindir_relative_SQ)"' \ + '-DFALLBACK_RUNTIME_PREFIX="$(prefix_SQ)"' \ + '-DDEFAULT_GIT_TEMPLATE_DIR="$(template_dir_SQ)"' \ + '-DETC_GITCONFIG="$(ETC_GITCONFIG_SQ)"' \ + '-DETC_GITATTRIBUTES="$(ETC_GITATTRIBUTES_SQ)"' \ + '-DGIT_LOCALE_PATH="$(localedir_relative_SQ)"' \ + '-DCURL_DISABLE_TYPECHECK', \ + '-DGIT_HTML_PATH="$(htmldir_relative_SQ)"' \ + '-DGIT_MAN_PATH="$(mandir_relative_SQ)"' \ + '-DGIT_INFO_PATH="$(infodir_relative_SQ)"'; do \ + case "$$e" in \ + -I.) \ + incs="$$(printf '% 16s"$${workspaceRoot}",\n%s' \ + "" "$$incs")" \ + ;; \ + -I/*) \ + incs="$$(printf '% 16s"%s",\n%s' \ + "" "$${e#-I}" "$$incs")" \ + ;; \ + -I*) \ + incs="$$(printf '% 16s"$${workspaceRoot}/%s",\n%s' \ + "" "$${e#-I}" "$$incs")" \ + ;; \ + -D*) \ + defs="$$(printf '% 16s"%s",\n%s' \ + "" "$$(echo "$${e#-D}" | sed 's/"/\\&/g')" \ + "$$defs")" \ + ;; \ + esac; \ + done && \ + echo '{' && \ + echo ' "configurations": [' && \ + echo ' {' && \ + echo ' "name": "$(OSNAME)",' && \ + echo ' "intelliSenseMode": "clang-x64",' && \ + echo ' "includePath": [' && \ + echo "$$incs" | sort | sed '$$s/,$$//' && \ + echo ' ],' && \ + echo ' "defines": [' && \ + echo "$$defs" | sort | sed '$$s/,$$//' && \ + echo ' ],' && \ + echo ' "browse": {' && \ + echo ' "limitSymbolsToIncludedHeaders": true,' && \ + echo ' "databaseFilename": "",' && \ + echo ' "path": [' && \ + echo ' "$${workspaceRoot}"' && \ + echo ' ]' && \ + echo ' },' && \ + echo ' "cStandard": "c11",' && \ + echo ' "cppStandard": "c++17",' && \ + echo ' "compilerPath": "$(GCCPATH)"' && \ + echo ' }' && \ + echo ' ],' && \ + echo ' "version": 4' && \ + echo '}' +EOF +die "Could not write settings for the C/C++ extension" + +for file in .vscode/settings.json .vscode/tasks.json .vscode/launch.json +do + if test -f $file + then + if git diff --no-index --quiet --exit-code $file $file.new + then + rm $file.new + else + printf "The file $file.new has these changes:\n\n" + git --no-pager diff --no-index $file $file.new + printf "\n\nMaybe \`mv $file.new $file\`?\n\n" + fi + else + mv $file.new $file + fi +done diff --git a/contrib/workdir/.gitattributes b/contrib/workdir/.gitattributes new file mode 100644 index 000000000000..1f78c5d1bd30 --- /dev/null +++ b/contrib/workdir/.gitattributes @@ -0,0 +1 @@ +/git-new-workdir eol=lf diff --git a/contrib/workdir/git-new-workdir b/contrib/workdir/git-new-workdir new file mode 100755 index 000000000000..888c34a52152 --- /dev/null +++ b/contrib/workdir/git-new-workdir @@ -0,0 +1,105 @@ +#!/bin/sh + +usage () { + echo "usage:" $@ + exit 127 +} + +die () { + echo $@ + exit 128 +} + +failed () { + die "unable to create new workdir '$new_workdir'!" +} + +if test $# -lt 2 || test $# -gt 3 +then + usage "$0 <repository> <new_workdir> [<branch>]" +fi + +orig_git=$1 +new_workdir=$2 +branch=$3 + +# want to make sure that what is pointed to has a .git directory ... +git_dir=$(cd "$orig_git" 2>/dev/null && + git rev-parse --git-dir 2>/dev/null) || + die "Not a git repository: \"$orig_git\"" + +case "$git_dir" in +.git) + git_dir="$orig_git/.git" + ;; +.) + git_dir=$orig_git + ;; +esac + +# don't link to a configured bare repository +isbare=$(git --git-dir="$git_dir" config --bool --get core.bare) +if test ztrue = "z$isbare" +then + die "\"$git_dir\" has core.bare set to true," \ + " remove from \"$git_dir/config\" to use $0" +fi + +# don't link to a workdir +if test -h "$git_dir/config" +then + die "\"$orig_git\" is a working directory only, please specify" \ + "a complete repository." +fi + +# make sure the links in the workdir have full paths to the original repo +git_dir=$(cd "$git_dir" && pwd) || exit 1 + +# don't recreate a workdir over an existing directory, unless it's empty +if test -d "$new_workdir" +then + if test $(ls -a1 "$new_workdir/." | wc -l) -ne 2 + then + die "destination directory '$new_workdir' is not empty." + fi + cleandir="$new_workdir/.git" +else + cleandir="$new_workdir" +fi + +mkdir -p "$new_workdir/.git" || failed +cleandir=$(cd "$cleandir" && pwd) || failed + +cleanup () { + rm -rf "$cleandir" +} +siglist="0 1 2 15" +trap cleanup $siglist + +# create the links to the original repo. explicitly exclude index, HEAD and +# logs/HEAD from the list since they are purely related to the current working +# directory, and should not be shared. +for x in config refs logs/refs objects info hooks packed-refs remotes rr-cache svn +do + # create a containing directory if needed + case $x in + */*) + mkdir -p "$new_workdir/.git/${x%/*}" + ;; + esac + + ln -s "$git_dir/$x" "$new_workdir/.git/$x" || failed +done + +# commands below this are run in the context of the new workdir +cd "$new_workdir" || failed + +# copy the HEAD from the original repository as a default branch +cp "$git_dir/HEAD" .git/HEAD || failed + +# the workdir is set up. if the checkout fails, the user can fix it. +trap - $siglist + +# checkout the branch (either the same as HEAD from the original repository, +# or the one that was asked for) +git checkout -f $branch |