Merge pull request #2716 from github/faster-string-tokenizer

Use negative lookbehind when tokenizing string literals
2025-10-29 17:50:22 +00:00 · 2015-11-05 08:40:34 -08:00
parent 04f981eeac fea8bb21a0
commit d24677adbb
1 changed files with 2 additions and 2 deletions
--- a/lib/linguist/tokenizer.rb
+++ b/lib/linguist/tokenizer.rb
@@ -86,13 +86,13 @@ module Linguist
          if s.peek(1) == "\""
            s.getch
          else
-            s.skip_until(/[^\\]"/)
+            s.skip_until(/(?<!\\)"/)
          end
        elsif s.scan(/'/)
          if s.peek(1) == "'"
            s.getch
          else
-            s.skip_until(/[^\\]'/)
+            s.skip_until(/(?<!\\)'/)
          end

        # Skip number literals