[PATCH] D13641: clang-format: [JS] handle character classes in regexes.

[Martin Probst via cfe-commits]

mprobst created this revision.
mprobst added a reviewer: djasper.
mprobst added subscribers: cfe-commits, klimek.

Slashes in regular expressions do not need to be escaped and do not terminate
the regular expression even without a preceding backslash.

http://reviews.llvm.org/D13641

Files:
  lib/Format/Format.cpp
  unittests/Format/FormatTestJS.cpp

Index: unittests/Format/FormatTestJS.cpp
===================================================================
--- unittests/Format/FormatTestJS.cpp
+++ unittests/Format/FormatTestJS.cpp
@@ -617,9 +617,15 @@
   verifyFormat("var regex = /x|y/;");
   verifyFormat("var regex = /a{2}/;");
   verifyFormat("var regex = /a{1,3}/;");
+
   verifyFormat("var regex = /[abc]/;");
   verifyFormat("var regex = /[^abc]/;");
   verifyFormat("var regex = /[\\b]/;");
+  verifyFormat("var regex = /[/]/;");
+  verifyFormat("var regex = /[\\/]/;");
+  verifyFormat("var regex = /\\[/;");
+  verifyFormat("var regex = /\\\\[/]/;");
+
   verifyFormat("var regex = /\\b/;");
   verifyFormat("var regex = /\\B/;");
   verifyFormat("var regex = /\\d/;");
Index: lib/Format/Format.cpp
===================================================================
--- lib/Format/Format.cpp
+++ lib/Format/Format.cpp
@@ -876,12 +876,23 @@
       return false;
 
     unsigned TokenCount = 0;
+    auto InCharacterClass = false;
     for (auto I = Tokens.rbegin() + 1, E = Tokens.rend(); I != E; ++I) {
       ++TokenCount;
       auto Prev = I + 1;
       while (Prev != E && Prev[0]->is(tok::comment))
         ++Prev;
-      if (I[0]->isOneOf(tok::slash, tok::slashequal) &&
+      // Slashes in character classes (delimited by [ and ]) do not need
+      // escaping. Escaping of the squares themselves is already handled by
+      // \c tryMergeEscapeSequence(), a plain tok::r_square must be non-escaped.
+      if (I[0]->is(tok::r_square))
+        InCharacterClass = true;
+      if (I[0]->is(tok::l_square)) {
+        if (!InCharacterClass)
+          return false;
+        InCharacterClass = false;
+      }
+      if (!InCharacterClass && I[0]->isOneOf(tok::slash, tok::slashequal) &&
           (Prev == E ||
            ((Prev[0]->isOneOf(tok::l_paren, tok::semi, tok::l_brace,
                               tok::r_brace, tok::exclaim, tok::l_square,


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D13641.37072.patch
Type: text/x-patch
Size: 1932 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20151012/63456866/attachment.bin>