Merge branch 'remove-catchall' of https://github.com/layus/nix

3 files changed, 29 insertions, 13 deletions

diff --git a/src/libexpr/lexer.l b/src/libexpr/lexer.l
index 5b1ff0350cd1..40ca77258037 100644
--- a/src/libexpr/lexer.l
+++ b/src/libexpr/lexer.l
@@ -142,25 +142,34 @@ or          { return OR_KW; }
 \{                           { return '{'; }
 <INSIDE_DOLLAR_CURLY>\{      { PUSH_STATE(INSIDE_DOLLAR_CURLY); return '{'; }
 
-<INITIAL,INSIDE_DOLLAR_CURLY>\"          { PUSH_STATE(STRING); return '"'; }
+<INITIAL,INSIDE_DOLLAR_CURLY>\" {
+                PUSH_STATE(STRING); return '"';
+              }
 <STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)*\$/\" |
 <STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)+ {
-              /* It is impossible to match strings ending with '$' with one
-                 regex because trailing contexts are only valid at the end
-                 of a rule. (A sane but undocumented limitation.) */
-              yylval->e = unescapeStr(data->symbols, yytext);
-              return STR;
-            }
+                /* It is impossible to match strings ending with '$' with one
+                   regex because trailing contexts are only valid at the end
+                   of a rule. (A sane but undocumented limitation.) */
+                yylval->e = unescapeStr(data->symbols, yytext);
+                return STR;
+              }
 <STRING>\$\{  { PUSH_STATE(INSIDE_DOLLAR_CURLY); return DOLLAR_CURLY; }
-<STRING>\"  { POP_STATE(); return '"'; }
-<STRING>.   return yytext[0]; /* just in case: shouldn't be reached */
+<STRING>\"    { POP_STATE(); return '"'; }
+<STRING>\$|\\|\$\\ {
+                /* This can only occur when we reach EOF, otherwise the above
+                   (...|\$[^\{\"\\]|\\.|\$\\.)+ would have triggered.
+                   This is technically invalid, but we leave the problem to the
+                   parser who fails with exact location. */
+                return STR;
+              }
 
 <INITIAL,INSIDE_DOLLAR_CURLY>\'\'(\ *\n)?     { PUSH_STATE(IND_STRING); return IND_STRING_OPEN; }
 <IND_STRING>([^\$\']|\$[^\{\']|\'[^\'\$])+ {
                    yylval->e = new ExprIndStr(yytext);
                    return IND_STR;
                  }
-<IND_STRING>\'\'\$ {
+<IND_STRING>\'\'\$ |
+<IND_STRING>\$   {
                    yylval->e = new ExprIndStr("$");
                    return IND_STR;
                  }
@@ -178,7 +187,6 @@ or          { return OR_KW; }
                    yylval->e = new ExprIndStr("'");
                    return IND_STR;
                  }
-<IND_STRING>.    return yytext[0]; /* just in case: shouldn't be reached */
 
 <INITIAL,INSIDE_DOLLAR_CURLY>{
 
diff --git a/tests/lang/eval-okay-ind-string.exp b/tests/lang/eval-okay-ind-string.exp
index 886219dcf652..9cf4bd2ee78a 100644
--- a/tests/lang/eval-okay-ind-string.exp
+++ b/tests/lang/eval-okay-ind-string.exp
@@ -1 +1 @@
-"This is an indented multi-line string\nliteral.  An amount of whitespace at\nthe start of each line matching the minimum\nindentation of all lines in the string\nliteral together will be removed.  Thus,\nin this case four spaces will be\nstripped from each line, even though\n  THIS LINE is indented six spaces.\n\nAlso, empty lines don't count in the\ndetermination of the indentation level (the\nprevious empty line has indentation 0, but\nit doesn't matter).\nIf the string starts with whitespace\n  followed by a newline, it's stripped, but\n  that's not the case here. Two spaces are\n  stripped because of the \"  \" at the start. \nThis line is indented\na bit further.\nAnti-quotations, like so, are\nalso allowed.\n  The \\ is not special here.\n' can be followed by any character except another ', e.g. 'x'.\nLikewise for $, e.g. $$ or $varName.\nBut ' followed by ' is special, as is $ followed by {.\nIf you want them, use anti-quotations: '', ${.\n   Tabs are not interpreted as whitespace (since we can't guess\n   what tab settings are intended), so don't use them.\n\tThis line starts with a space and a tab, so only one\n   space will be stripped from each line.\nAlso note that if the last line (just before the closing ' ')\nconsists only of whitespace, it's ignored.  But here there is\nsome non-whitespace stuff, so the line isn't removed. \nThis shows a hacky way to preserve an empty line after the start.\nBut there's no reason to do so: you could just repeat the empty\nline.\n  Similarly you can force an indentation level,\n  in this case to 2 spaces.  This works because the anti-quote\n  is significant (not whitespace).\nstart on network-interfaces\n\nstart script\n\n  rm -f /var/run/opengl-driver\n  ln -sf 123 /var/run/opengl-driver\n\n  rm -f /var/log/slim.log\n   \nend script\n\nenv SLIM_CFGFILE=abc\nenv SLIM_THEMESDIR=def\nenv FONTCONFIG_FILE=/etc/fonts/fonts.conf  \t\t\t\t# !!! cleanup\nenv XKB_BINDIR=foo/bin         \t\t\t\t# Needed for the Xkb extension.\nenv LD_LIBRARY_PATH=libX11/lib:libXext/lib:/usr/lib/          # related to xorg-sys-opengl - needed to load libglx for (AI)GLX support (for compiz)\n\nenv XORG_DRI_DRIVER_PATH=nvidiaDrivers/X11R6/lib/modules/drivers/ \n\nexec slim/bin/slim\nEscaping of ' followed by ': ''\nEscaping of $ followed by {: ${\nAnd finally to interpret \\n etc. as in a string: \n, \r, \t.\nfoo\n'bla'\nbar\n"
+"This is an indented multi-line string\nliteral.  An amount of whitespace at\nthe start of each line matching the minimum\nindentation of all lines in the string\nliteral together will be removed.  Thus,\nin this case four spaces will be\nstripped from each line, even though\n  THIS LINE is indented six spaces.\n\nAlso, empty lines don't count in the\ndetermination of the indentation level (the\nprevious empty line has indentation 0, but\nit doesn't matter).\nIf the string starts with whitespace\n  followed by a newline, it's stripped, but\n  that's not the case here. Two spaces are\n  stripped because of the \"  \" at the start. \nThis line is indented\na bit further.\nAnti-quotations, like so, are\nalso allowed.\n  The \\ is not special here.\n' can be followed by any character except another ', e.g. 'x'.\nLikewise for $, e.g. $$ or $varName.\nBut ' followed by ' is special, as is $ followed by {.\nIf you want them, use anti-quotations: '', ${.\n   Tabs are not interpreted as whitespace (since we can't guess\n   what tab settings are intended), so don't use them.\n\tThis line starts with a space and a tab, so only one\n   space will be stripped from each line.\nAlso note that if the last line (just before the closing ' ')\nconsists only of whitespace, it's ignored.  But here there is\nsome non-whitespace stuff, so the line isn't removed. \nThis shows a hacky way to preserve an empty line after the start.\nBut there's no reason to do so: you could just repeat the empty\nline.\n  Similarly you can force an indentation level,\n  in this case to 2 spaces.  This works because the anti-quote\n  is significant (not whitespace).\nstart on network-interfaces\n\nstart script\n\n  rm -f /var/run/opengl-driver\n  ln -sf 123 /var/run/opengl-driver\n\n  rm -f /var/log/slim.log\n   \nend script\n\nenv SLIM_CFGFILE=abc\nenv SLIM_THEMESDIR=def\nenv FONTCONFIG_FILE=/etc/fonts/fonts.conf  \t\t\t\t# !!! cleanup\nenv XKB_BINDIR=foo/bin         \t\t\t\t# Needed for the Xkb extension.\nenv LD_LIBRARY_PATH=libX11/lib:libXext/lib:/usr/lib/          # related to xorg-sys-opengl - needed to load libglx for (AI)GLX support (for compiz)\n\nenv XORG_DRI_DRIVER_PATH=nvidiaDrivers/X11R6/lib/modules/drivers/ \n\nexec slim/bin/slim\nEscaping of ' followed by ': ''\nEscaping of $ followed by {: ${\nAnd finally to interpret \\n etc. as in a string: \n, \r, \t.\nfoo\n'bla'\nbar\ncut -d $'\\t' -f 1\nending dollar $$\n"
diff --git a/tests/lang/eval-okay-ind-string.nix b/tests/lang/eval-okay-ind-string.nix
index 1556aae9f54f..1669dc0648ea 100644
--- a/tests/lang/eval-okay-ind-string.nix
+++ b/tests/lang/eval-okay-ind-string.nix
@@ -117,4 +117,12 @@ let
     bar
   '';
 
-in s1 + s2 + s3 + s4 + s5 + s6 + s7 + s8 + s9 + s10 + s11 + s12 + s13 + s14 + s15
+  # Regression test: accept $'.
+  s16 = ''
+    cut -d $'\t' -f 1
+  '';
+
+  # Accept dollars at end of strings 
+  s17 = ''ending dollar $'' + ''$'' + "\n";
+
+in s1 + s2 + s3 + s4 + s5 + s6 + s7 + s8 + s9 + s10 + s11 + s12 + s13 + s14 + s15 + s16 + s17