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

[mprobst]

Summary

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

[djasper]

looks good

lib/Format/Format.cpp

879

I think, we should just use bool here.

[djasper]

Submitted as r250009.

lib/Format/Format.cpp

bool MightEndWithEscapedSlash =
         Tokens[Tokens.size() - 2]->TokenText == "\\";
     if (!MightEndWithEscapedSlash && SlashInStringPos == StringRef::npos &&
         (Tokens.back()->isNot(tok::slash) ||
          (Tokens[Tokens.size() - 2]->is(tok::unknown) &&
           Tokens[Tokens.size() - 2]->TokenText == "\\")))
       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,
                               tok::colon, tok::comma, tok::question,
                               tok::kw_return) ||
              Prev[0]->isBinaryOperator())))) {
         unsigned LastColumn = Tokens.back()->OriginalColumn;
         SourceLocation Loc = Tokens.back()->Tok.getLocation();

unittests/Format/FormatTestJS.cpp

TEST_F(FormatTestJS, RegexLiteralSpecialCharacters) {
   verifyFormat("var regex = /^a$/;");
   verifyFormat("var regex = /\\/a/;");
   verifyFormat("var regex = /(?:x)/;");
   verifyFormat("var regex = /x(?=y)/;");
   verifyFormat("var regex = /x(?!y)/;");
   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/;");
   verifyFormat("var regex = /\\D/;");
   verifyFormat("var regex = /\\f/;");
   verifyFormat("var regex = /\\n/;");
   verifyFormat("var regex = /\\r/;");
   verifyFormat("var regex = /\\s/;");