about summary refs log tree commit diff
path: root/third_party/git/contrib/mw-to-git/git-remote-mediawiki.perl
diff options
context:
space:
mode:
authorVincent Ambo <mail@tazj.in>2020-11-21T18·20+0100
committerVincent Ambo <mail@tazj.in>2020-11-21T18·45+0100
commitf4609b896fac842433bd495c166d5987852a6a73 (patch)
tree95511c465c54c4f5d27e5d39ce187e2a1dd82bd3 /third_party/git/contrib/mw-to-git/git-remote-mediawiki.perl
parent082c006c04343a78d87b6c6ab3608c25d6213c3f (diff)
merge(3p/git): Merge git subtree at v2.29.2 r/1890
This also bumps the stable nixpkgs to 20.09 as of 2020-11-21, because
there is some breakage in the git build related to the netrc
credentials helper which someone has taken care of in nixpkgs.

The stable channel is not used for anything other than git, so this
should be fine.

Change-Id: I3575a19dab09e1e9556cf8231d717de9890484fb
Diffstat (limited to 'third_party/git/contrib/mw-to-git/git-remote-mediawiki.perl')
-rwxr-xr-xthird_party/git/contrib/mw-to-git/git-remote-mediawiki.perl82
1 files changed, 49 insertions, 33 deletions
diff --git a/third_party/git/contrib/mw-to-git/git-remote-mediawiki.perl b/third_party/git/contrib/mw-to-git/git-remote-mediawiki.perl
index af9cbc9d0f7b..a5624413dc11 100755
--- a/third_party/git/contrib/mw-to-git/git-remote-mediawiki.perl
+++ b/third_party/git/contrib/mw-to-git/git-remote-mediawiki.perl
@@ -9,7 +9,7 @@
 # License: GPL v2 or later
 
 # Gateway between Git and MediaWiki.
-# Documentation & bugtracker: https://github.com/moy/Git-Mediawiki/
+# Documentation & bugtracker: https://github.com/Git-Mediawiki/Git-Mediawiki
 
 use strict;
 use MediaWiki::API;
@@ -56,38 +56,38 @@ 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.${remotename}.pages"));
+my @tracked_pages = split(/[ \n]/, run_git_quoted(["config", "--get-all", "remote.${remotename}.pages"]));
 chomp(@tracked_pages);
 
 # Just like @tracked_pages, but for MediaWiki categories.
-my @tracked_categories = split(/[ \n]/, run_git("config --get-all remote.${remotename}.categories"));
+my @tracked_categories = split(/[ \n]/, run_git_quoted(["config", "--get-all", "remote.${remotename}.categories"]));
 chomp(@tracked_categories);
 
 # Just like @tracked_categories, but for MediaWiki namespaces.
-my @tracked_namespaces = split(/[ \n]/, run_git("config --get-all remote.${remotename}.namespaces"));
+my @tracked_namespaces = split(/[ \n]/, run_git_quoted(["config", "--get-all", "remote.${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");
+my $import_media = run_git_quoted(["config", "--get", "--bool", "remote.${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");
+my $export_media = run_git_quoted(["config", "--get", "--bool", "remote.${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");
+my $wiki_login = run_git_quoted(["config", "--get", "remote.${remotename}.mwLogin"]);
+# Note: mwPassword is discouraged. Use the credential system instead.
+my $wiki_passwd = run_git_quoted(["config", "--get", "remote.${remotename}.mwPassword"]);
+my $wiki_domain = run_git_quoted(["config", "--get", "remote.${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");
+my $shallow_import = run_git_quoted(["config", "--get", "--bool", "remote.${remotename}.shallow"]);
 chomp($shallow_import);
 $shallow_import = ($shallow_import eq 'true');
 
@@ -97,9 +97,9 @@ $shallow_import = ($shallow_import eq 'true');
 # 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");
+my $fetch_strategy = run_git_quoted(["config", "--get", "remote.${remotename}.fetchStrategy"]);
 if (!$fetch_strategy) {
-	$fetch_strategy = run_git('config --get mediawiki.fetchStrategy');
+	$fetch_strategy = run_git_quoted(["config", "--get", "mediawiki.fetchStrategy"]);
 }
 chomp($fetch_strategy);
 if (!$fetch_strategy) {
@@ -123,9 +123,9 @@ my %basetimestamps;
 # 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");
+my $dumb_push = run_git_quoted(["config", "--get", "--bool", "remote.${remotename}.dumbPush"]);
 if (!$dumb_push) {
-	$dumb_push = run_git('config --get --bool mediawiki.dumbPush');
+	$dumb_push = run_git_quoted(["config", "--get", "--bool", "mediawiki.dumbPush"]);
 }
 chomp($dumb_push);
 $dumb_push = ($dumb_push eq 'true');
@@ -369,12 +369,14 @@ sub get_mw_pages {
 	return %pages;
 }
 
-# usage: $out = run_git("command args");
-#        $out = run_git("command args", "raw"); # don't interpret output as UTF-8.
-sub run_git {
+# usage: $out = run_git_quoted(["command", "args", ...]);
+#        $out = run_git_quoted(["command", "args", ...], "raw"); # don't interpret output as UTF-8.
+#        $out = run_git_quoted_nostderr(["command", "args", ...]); # discard stderr
+#        $out = run_git_quoted_nostderr(["command", "args", ...], "raw"); # ditto but raw instead of UTF-8 as above
+sub _run_git {
 	my $args = shift;
 	my $encoding = (shift || 'encoding(UTF-8)');
-	open(my $git, "-|:${encoding}", "git ${args}")
+	open(my $git, "-|:${encoding}", @$args)
 	    or die "Unable to fork: $!\n";
 	my $res = do {
 		local $/ = undef;
@@ -385,6 +387,13 @@ sub run_git {
 	return $res;
 }
 
+sub run_git_quoted {
+    _run_git(["git", @{$_[0]}], $_[1]);
+}
+
+sub run_git_quoted_nostderr {
+    _run_git(['sh', '-c', 'git "$@" 2>/dev/null', '--', @{$_[0]}], $_[1]);
+}
 
 sub get_all_mediafiles {
 	my $pages = shift;
@@ -511,8 +520,9 @@ sub download_mw_mediafile {
 }
 
 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");
+	# Get note regarding last mediawiki revision.
+	my $note = run_git_quoted_nostderr(["notes", "--ref=${remotename}/mediawiki",
+					    "show", "refs/mediawiki/${remotename}/master"]);
 	my @note_info = split(/ /, $note);
 
 	my $lastrevision_number;
@@ -807,7 +817,10 @@ sub get_more_refs {
 sub mw_import {
 	# multiple import commands can follow each other.
 	my @refs = (shift, get_more_refs('import'));
+	my $processedRefs;
 	foreach my $ref (@refs) {
+		next if $processedRefs->{$ref}; # skip duplicates: "import refs/heads/master" being issued twice; TODO: why?
+		$processedRefs->{$ref} = 1;
 		mw_import_ref($ref);
 	}
 	print {*STDOUT} "done\n";
@@ -970,7 +983,7 @@ sub mw_import_revids {
 }
 
 sub error_non_fast_forward {
-	my $advice = run_git('config --bool advice.pushNonFastForward');
+	my $advice = run_git_quoted(["config", "--bool", "advice.pushNonFastForward"]);
 	chomp($advice);
 	if ($advice ne 'false') {
 		# Native git-push would show this after the summary.
@@ -1014,7 +1027,7 @@ sub mw_upload_file {
 		}
 	} 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');
+		my $content = run_git_quoted(["cat-file", "blob", $new_sha1], 'raw');
 		if ($content ne EMPTY) {
 			$mediawiki = connect_maybe($mediawiki, $remotename, $url);
 			$mediawiki->{config}->{upload_url} =
@@ -1084,7 +1097,7 @@ sub mw_push_file {
 			# with this content instead:
 			$file_content = DELETED_CONTENT;
 		} else {
-			$file_content = run_git("cat-file blob ${new_sha1}");
+			$file_content = run_git_quoted(["cat-file", "blob", $new_sha1]);
 		}
 
 		$mediawiki = connect_maybe($mediawiki, $remotename, $url);
@@ -1174,10 +1187,10 @@ sub mw_push_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");
+	my $HEAD_sha1 = run_git_quoted_nostderr(["rev-parse", $local]);
 	chomp($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");
+	my $remoteorigin_sha1 = run_git_quoted_nostderr(["rev-parse", "refs/remotes/${remotename}/master"]);
 	chomp($remoteorigin_sha1);
 
 	if ($last_local_revid > 0 &&
@@ -1197,7 +1210,7 @@ sub mw_push_revision {
 		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 = split(/\n/, run_git_quoted(["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 ]+)/) {
@@ -1221,7 +1234,7 @@ sub mw_push_revision {
 		# 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 = run_git_quoted(["rev-list", "--first-parent", "--children", $local]);
 		my @history = split(/\n/, $history);
 		@history = @history[1..$#history];
 		foreach my $line (reverse @history) {
@@ -1233,12 +1246,12 @@ sub mw_push_revision {
 	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}");
+		my $diff_infos = run_git_quoted(["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}));
+		my $commit_msg = run_git_quoted(["log", "--no-walk", '--format="%s"', $sha1_commit]);
 		chomp($commit_msg);
 		# Push every blob
 		while (@diff_info_list) {
@@ -1263,7 +1276,10 @@ sub mw_push_revision {
 			}
 		}
 		if (!$dumb_push) {
-			run_git(qq(notes --ref=${remotename}/mediawiki add -f -m "mediawiki_revision: ${mw_revision}" ${sha1_commit}));
+			run_git_quoted(["notes", "--ref=${remotename}/mediawiki",
+					"add", "-f", "-m",
+					"mediawiki_revision: ${mw_revision}",
+					$sha1_commit]);
 		}
 	}
 
@@ -1304,7 +1320,7 @@ sub get_mw_namespace_id {
 		# 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.${remotename}.namespaceCache"));
+				 run_git_quoted(["config", "--get-all", "remote.${remotename}.namespaceCache"]));
 		chomp(@temp);
 		foreach my $ns (@temp) {
 			my ($n, $id) = split(/:/, $ns);
@@ -1358,7 +1374,7 @@ sub get_mw_namespace_id {
 
 	# Store explicitly requested namespaces on disk
 	if (!exists $cached_mw_namespace_id{$name}) {
-		run_git(qq(config --add remote.${remotename}.namespaceCache "${name}:${store_id}"));
+		run_git_quoted(["config", "--add", "remote.${remotename}.namespaceCache", "${name}:${store_id}"]);
 		$cached_mw_namespace_id{$name} = 1;
 	}
 	return $id;