feat: tab support for indentation stripping

magistau · magistau · commit 01aaa078842e · 2024-06-13T14:17:06.000+03:00
diff --git a/src/libexpr/parser-state.hh b/src/libexpr/parser-state.hh
@@ -2,6 +2,7 @@
 ///@file
 
 #include "eval.hh"
+#include <limits>
 
 namespace nix {
 
@@ -173,16 +174,22 @@ inline Formals * ParserState::validateFormals(Formals * formals, PosIdx pos, Sym
     return formals;
 }
 
+enum IndentChar {
+    Tab = '\t',
+    Space = ' ',
+};
+
 inline Expr * ParserState::stripIndentation(const PosIdx pos,
     std::vector<std::pair<PosIdx, std::variant<Expr *, StringToken>>> && es)
 {
     if (es.empty()) return new ExprString("");
 
     /* Figure out the minimum indentation.  Note that by design
        whitespace-only final lines are not taken into account.  (So
-       the " " in "\n ''" is ignored, but the " " in "\n foo''" is.) */
+       the " " in "\n ''" is ignored, but the " " in "\n foo''" is not.) */
+    std::optional<IndentChar> indentChar = std::nullopt;
     bool atStartOfLine = true; /* = seen only whitespace in the current line */
-    size_t minIndent = 1000000;
+    size_t minIndent = std::numeric_limits<size_t>::max();
     size_t curIndent = 0;
     for (auto & [i_pos, i] : es) {
         auto * str = std::get_if<StringToken>(&i);
@@ -195,20 +202,26 @@ inline Expr * ParserState::stripIndentation(const PosIdx pos,
             continue;
         }
         for (size_t j = 0; j < str->l; ++j) {
-            if (atStartOfLine) {
-                if (str->p[j] == ' ')
-                    curIndent++;
-                else if (str->p[j] == '\n') {
-                    /* Empty line, doesn't influence minimum
-                       indentation. */
-                    curIndent = 0;
-                } else {
-                    atStartOfLine = false;
-                    if (curIndent < minIndent) minIndent = curIndent;
-                }
-            } else if (str->p[j] == '\n') {
+            auto cur = str->p[j];
+            if (!atStartOfLine) {
+                if (cur != '\n') continue;
                 atStartOfLine = true;
+                curIndent = true;
+            } else if (
+                indentChar == cur
+                || (!indentChar && (cur == ' ' || cur == '\t')) 
+            ) {
+                if (!indentChar) {
+                    indentChar = IndentChar(cur);
+                }
+                curIndent++;
+            } else if (cur == '\n') {
+                /* Empty line, doesn't influence minimum
+                   indentation. */
                 curIndent = 0;
+            } else {
+                atStartOfLine = false;
+                if (curIndent < minIndent) minIndent = curIndent;
             }
         }
     }
@@ -228,7 +241,7 @@ inline Expr * ParserState::stripIndentation(const PosIdx pos,
         std::string s2;
         for (size_t j = 0; j < t.l; ++j) {
             if (atStartOfLine) {
-                if (t.p[j] == ' ') {
+                if (t.p[j] == indentChar) {
                     if (curDropped++ >= minIndent)
                         s2 += t.p[j];
                 }
diff --git a/tests/functional/lang/eval-okay-ind-string.exp b/tests/functional/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. $$ or $varName.\nBut ' followed by ' is special, as is $ followed by {.\nIf you want them, use anti-quotations: '', \${.\n   Tabs are not interpreted as whitespace (since we can't guess\n   what tab settings are intended), so don't use them.\n\tThis line starts with a space and a tab, so only one\n   space will be stripped from each line.\nAlso note that if the last line (just before the closing ' ')\nconsists only of whitespace, it's ignored.  But here there is\nsome non-whitespace stuff, so the line isn't removed. \nThis shows a hacky way to preserve an empty line after the start.\nBut there's no reason to do so: you could just repeat the empty\nline.\n  Similarly you can force an indentation level,\n  in this case to 2 spaces.  This works because the anti-quote\n  is significant (not whitespace).\nstart on network-interfaces\n\nstart script\n\n  rm -f /var/run/opengl-driver\n  ln -sf 123 /var/run/opengl-driver\n\n  rm -f /var/log/slim.log\n   \nend script\n\nenv SLIM_CFGFILE=abc\nenv SLIM_THEMESDIR=def\nenv FONTCONFIG_FILE=/etc/fonts/fonts.conf  \t\t\t\t# !!! cleanup\nenv XKB_BINDIR=foo/bin         \t\t\t\t# Needed for the Xkb extension.\nenv LD_LIBRARY_PATH=libX11/lib:libXext/lib:/usr/lib/          # related to xorg-sys-opengl - needed to load libglx for (AI)GLX support (for compiz)\n\nenv XORG_DRI_DRIVER_PATH=nvidiaDrivers/X11R6/lib/modules/drivers/ \n\nexec slim/bin/slim\nEscaping of ' followed by ': ''\nEscaping of $ followed by {: \${\nAnd finally to interpret \\n etc. as in a string: \n, \r, \t.\nfoo\n'bla'\nbar\ncut -d $'\\t' -f 1\nending dollar $$\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. $$ or $varName.\nBut ' followed by ' is special, as is $ followed by {.\nIf you want them, use anti-quotations: '', \${.\n   Tabs are not interpreted as whitespace (since we can't guess\n   what tab settings are intended), so don't use them.\n\tThis line starts with a space and a tab, so only one\n   space will be stripped from each line.\nAlso note that if the last line (just before the closing ' ')\nconsists only of whitespace, it's ignored.  But here there is\nsome non-whitespace stuff, so the line isn't removed. \nThis shows a hacky way to preserve an empty line after the start.\nBut there's no reason to do so: you could just repeat the empty\nline.\n  Similarly you can force an indentation level,\n  in this case to 2 spaces.  This works because the anti-quote\n  is significant (not whitespace).\nstart on network-interfaces\n\nstart script\n\n  rm -f /var/run/opengl-driver\n  ln -sf 123 /var/run/opengl-driver\n\n  rm -f /var/log/slim.log\n   \nend script\n\nenv SLIM_CFGFILE=abc\nenv SLIM_THEMESDIR=def\nenv FONTCONFIG_FILE=/etc/fonts/fonts.conf  \t\t\t\t# !!! cleanup\nenv XKB_BINDIR=foo/bin         \t\t\t\t# Needed for the Xkb extension.\nenv LD_LIBRARY_PATH=libX11/lib:libXext/lib:/usr/lib/          # related to xorg-sys-opengl - needed to load libglx for (AI)GLX support (for compiz)\n\nenv XORG_DRI_DRIVER_PATH=nvidiaDrivers/X11R6/lib/modules/drivers/ \n\nexec slim/bin/slim\nEscaping of ' followed by ': ''\nEscaping of $ followed by {: \${\nAnd finally to interpret \\n etc. as in a string: \n, \r, \t.\nfoo\n'bla'\nbar\ncut -d $'\\t' -f 1\nending dollar $$\nThis text uses\n\ttabs\nfor indentation\nAnd this text uses\n  spaces\nbut is indented with tabs\n  \tThis text uses\n\t  both spaces and tabs\n\t\tso nothing is stripped\n\t"
diff --git a/tests/functional/lang/eval-okay-ind-string.nix b/tests/functional/lang/eval-okay-ind-string.nix
@@ -125,4 +125,22 @@ let
   # 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
+  s18 = ''
+    This text uses
+    	tabs
+    for indentation
+  '';
+
+	s19 = ''
+		And this text uses
+		  spaces
+		but is indented with tabs
+	'';
+
+  s20 = ''
+  	This text uses
+	  both spaces and tabs
+		so nothing is stripped
+	'';
+
+in s1 + s2 + s3 + s4 + s5 + s6 + s7 + s8 + s9 + s10 + s11 + s12 + s13 + s14 + s15 + s16 + s17 + s18 + s19 + s20

Original file line number	Diff line number	Diff line change
`@@ -1 +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. $$ or $varName.\nBut ' followed by ' is special, as is $ followed by {.\nIf you want them, use anti-quotations: '', \${.\n Tabs are not interpreted as whitespace (since we can't guess\n what tab settings are intended), so don't use them.\n\tThis line starts with a space and a tab, so only one\n space will be stripped from each line.\nAlso note that if the last line (just before the closing ' ')\nconsists only of whitespace, it's ignored. But here there is\nsome non-whitespace stuff, so the line isn't removed. \nThis shows a hacky way to preserve an empty line after the start.\nBut there's no reason to do so: you could just repeat the empty\nline.\n Similarly you can force an indentation level,\n in this case to 2 spaces. This works because the anti-quote\n is significant (not whitespace).\nstart on network-interfaces\n\nstart script\n\n rm -f /var/run/opengl-driver\n ln -sf 123 /var/run/opengl-driver\n\n rm -f /var/log/slim.log\n \nend script\n\nenv SLIM_CFGFILE=abc\nenv SLIM_THEMESDIR=def\nenv FONTCONFIG_FILE=/etc/fonts/fonts.conf \t\t\t\t# !!! cleanup\nenv XKB_BINDIR=foo/bin \t\t\t\t# Needed for the Xkb extension.\nenv LD_LIBRARY_PATH=libX11/lib:libXext/lib:/usr/lib/ # related to xorg-sys-opengl - needed to load libglx for (AI)GLX support (for compiz)\n\nenv XORG_DRI_DRIVER_PATH=nvidiaDrivers/X11R6/lib/modules/drivers/ \n\nexec slim/bin/slim\nEscaping of ' followed by ': ''\nEscaping of $ followed by {: \${\nAnd finally to interpret \\n etc. as in a string: \n, \r, \t.\nfoo\n'bla'\nbar\ncut -d $'\\t' -f 1\nending dollar $$\n"
	`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. $$ or $varName.\nBut ' followed by ' is special, as is $ followed by {.\nIf you want them, use anti-quotations: '', \${.\n Tabs are not interpreted as whitespace (since we can't guess\n what tab settings are intended), so don't use them.\n\tThis line starts with a space and a tab, so only one\n space will be stripped from each line.\nAlso note that if the last line (just before the closing ' ')\nconsists only of whitespace, it's ignored. But here there is\nsome non-whitespace stuff, so the line isn't removed. \nThis shows a hacky way to preserve an empty line after the start.\nBut there's no reason to do so: you could just repeat the empty\nline.\n Similarly you can force an indentation level,\n in this case to 2 spaces. This works because the anti-quote\n is significant (not whitespace).\nstart on network-interfaces\n\nstart script\n\n rm -f /var/run/opengl-driver\n ln -sf 123 /var/run/opengl-driver\n\n rm -f /var/log/slim.log\n \nend script\n\nenv SLIM_CFGFILE=abc\nenv SLIM_THEMESDIR=def\nenv FONTCONFIG_FILE=/etc/fonts/fonts.conf \t\t\t\t# !!! cleanup\nenv XKB_BINDIR=foo/bin \t\t\t\t# Needed for the Xkb extension.\nenv LD_LIBRARY_PATH=libX11/lib:libXext/lib:/usr/lib/ # related to xorg-sys-opengl - needed to load libglx for (AI)GLX support (for compiz)\n\nenv XORG_DRI_DRIVER_PATH=nvidiaDrivers/X11R6/lib/modules/drivers/ \n\nexec slim/bin/slim\nEscaping of ' followed by ': ''\nEscaping of $ followed by {: \${\nAnd finally to interpret \\n etc. as in a string: \n, \r, \t.\nfoo\n'bla'\nbar\ncut -d $'\\t' -f 1\nending dollar $$\nThis text uses\n\ttabs\nfor indentation\nAnd this text uses\n spaces\nbut is indented with tabs\n \tThis text uses\n\t both spaces and tabs\n\t\tso nothing is stripped\n\t"