clang-format: [JS] Initial support for regex literals.

llvm-svn: 208281

3 files changed, 44 insertions, 7 deletions

diff --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp
index efb790b3592..c57993386f3 100644
--- a/clang/lib/Format/Format.cpp
+++ b/clang/lib/Format/Format.cpp
@@ -1215,10 +1215,13 @@ private:
       return;
 
     if (Style.Language == FormatStyle::LK_JavaScript) {
-      static tok::TokenKind JSIdentity[] = { tok::equalequal, tok::equal };
-      static tok::TokenKind JSNotIdentity[] = { tok::exclaimequal, tok::equal };
-      static tok::TokenKind JSShiftEqual[] = { tok::greater, tok::greater,
-                                               tok::greaterequal };
+      if (tryMergeJSRegexLiteral())
+        return;
+
+      static tok::TokenKind JSIdentity[] = {tok::equalequal, tok::equal};
+      static tok::TokenKind JSNotIdentity[] = {tok::exclaimequal, tok::equal};
+      static tok::TokenKind JSShiftEqual[] = {tok::greater, tok::greater,
+                                              tok::greaterequal};
       // FIXME: We probably need to change token type to mimic operator with the
       // correct priority.
       if (tryMergeTokens(JSIdentity))
@@ -1252,6 +1255,38 @@ private:
     return true;
   }
 
+  // Try to determine whether the current token ends a JavaScript regex literal.
+  // We heuristically assume that this is a regex literal if we find two
+  // unescaped slashes on a line and the token before the first slash is one of
+  // "(;,{}![:?" or a binary operator, as those cannot be followed by a
+  // division.
+  bool tryMergeJSRegexLiteral() {
+      if (Tokens.size() < 2 || Tokens.back()->isNot(tok::slash) ||
+          Tokens[Tokens.size() - 2]->is(tok::unknown))
+        return false;
+      unsigned TokenCount = 0;
+      unsigned LastColumn = Tokens.back()->OriginalColumn;
+      for (auto I = Tokens.rbegin() + 1, E = Tokens.rend(); I != E; ++I) {
+        ++TokenCount;
+        if (I[0]->is(tok::slash) && I + 1 != E &&
+            (I[1]->isOneOf(tok::l_paren, tok::semi, tok::l_brace,
+                           tok::r_brace, tok::exclaim, tok::l_square,
+                           tok::colon, tok::comma, tok::question) ||
+             I[1]->isBinaryOperator())) {
+          Tokens.resize(Tokens.size() - TokenCount);
+          Tokens.back()->Tok.setKind(tok::unknown);
+          Tokens.back()->Type = TT_RegexLiteral;
+          Tokens.back()->ColumnWidth += LastColumn - I[0]->OriginalColumn;
+          return true;
+        }
+
+        // There can't be a newline inside a regex literal.
+        if (I[0]->NewlinesBefore > 0)
+          return false;
+      }
+      return false;
+  }
+
   bool tryMerge_TMacro() {
     if (Tokens.size() < 4)
       return false;
diff --git a/clang/lib/Format/FormatToken.h b/clang/lib/Format/FormatToken.h
index 749dfcb3e46..056d4bdd1bb 100644
--- a/clang/lib/Format/FormatToken.h
+++ b/clang/lib/Format/FormatToken.h
@@ -60,6 +60,7 @@ enum TokenType {
   TT_PointerOrReference,
   TT_PureVirtualSpecifier,
   TT_RangeBasedForLoopColon,
+  TT_RegexLiteral,
   TT_StartOfName,
   TT_TemplateCloser,
   TT_TemplateOpener,
diff --git a/clang/lib/Format/TokenAnnotator.cpp b/clang/lib/Format/TokenAnnotator.cpp
index 21cec905a8e..2f8457c61b3 100644
--- a/clang/lib/Format/TokenAnnotator.cpp
+++ b/clang/lib/Format/TokenAnnotator.cpp
@@ -609,6 +609,7 @@ private:
     if (CurrentToken->Type != TT_LambdaLSquare &&
         CurrentToken->Type != TT_FunctionLBrace &&
         CurrentToken->Type != TT_ImplicitStringLiteral &&
+        CurrentToken->Type != TT_RegexLiteral &&
         CurrentToken->Type != TT_TrailingReturnArrow)
       CurrentToken->Type = TT_Unknown;
     if (CurrentToken->Role)
@@ -622,10 +623,8 @@ private:
       determineTokenType(*CurrentToken);
       CurrentToken->BindingStrength = Contexts.back().BindingStrength;
       CurrentToken->NestingLevel = Contexts.size() - 1;
-    }
-
-    if (CurrentToken != NULL)
       CurrentToken = CurrentToken->Next;
+    }
 
     resetTokenMetadata(CurrentToken);
   }
@@ -1555,6 +1554,8 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line,
     return true;
   if (Tok.Type == TT_TrailingUnaryOperator)
     return false;
+  if (Tok.Previous->Type == TT_RegexLiteral)
+    return false;
   return spaceRequiredBetween(Line, *Tok.Previous, Tok);
 }