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

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

Patch by Martin Probst. Thank you.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@250009 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Format/Format.cpp b/lib/Format/Format.cpp
index 6bfd9cb5ceca114001d6d3192726546ff32cc92b..0afa9aa9ce2db02f29cdff555c6439f3f037c408 100644 (file)
--- a/lib/Format/Format.cpp
+++ b/lib/Format/Format.cpp
@@ -876,12 +876,23 @@ private:
       return false;
 
     unsigned TokenCount = 0;
+    bool 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,

diff --git a/unittests/Format/FormatTestJS.cpp b/unittests/Format/FormatTestJS.cpp
index f09df28142942d16b522cb36d83c541fe9741966..d63a24d805636a01967b3e587c5983275ede18bc 100644 (file)
--- a/unittests/Format/FormatTestJS.cpp
+++ b/unittests/Format/FormatTestJS.cpp
@@ -617,9 +617,15 @@ TEST_F(FormatTestJS, RegexLiteralSpecialCharacters) {
   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/;");