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

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@208281 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Format/Format.cpp b/lib/Format/Format.cpp
index efb790b3592312a5590fdea863cb18295eb49780..c57993386f30ae2b569d962d936d5ca2fcfb4521 100644 (file)
--- a/lib/Format/Format.cpp
+++ b/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/lib/Format/FormatToken.h b/lib/Format/FormatToken.h
index 749dfcb3e46ee92e27ff1afd8d2f3c70aa4c634a..056d4bdd1bbd04bc54a6bbad9f0082861c9f8e51 100644 (file)
--- a/lib/Format/FormatToken.h
+++ b/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/lib/Format/TokenAnnotator.cpp b/lib/Format/TokenAnnotator.cpp
index 21cec905a8e4c24b0a9f2aa47750bc60a231eb7e..2f8457c61b3afa21f7aaa947c1fa42a08a93758d 100644 (file)
--- a/lib/Format/TokenAnnotator.cpp
+++ b/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);
 }
 

diff --git a/unittests/Format/FormatTestJS.cpp b/unittests/Format/FormatTestJS.cpp
index a94ed4707db114b67e71f4ac7ab0ab7c31a0120d..52c85d3a9ac9c5dcfca270f03cfaffd946c2bdbe 100644 (file)
--- a/unittests/Format/FormatTestJS.cpp
+++ b/unittests/Format/FormatTestJS.cpp
@@ -111,5 +111,75 @@ TEST_F(FormatTestJS, ClosureStyleComments) {
   verifyFormat("var x = /** @type {foo} */ (bar);");
 }
 
+TEST_F(FormatTestJS, RegexLiteralClassification) {
+  // Regex literals.
+  verifyFormat("var regex = /abc/;");
+  verifyFormat("f(/abc/);");
+  verifyFormat("f(abc, /abc/);");
+  verifyFormat("some_map[/abc/];");
+  verifyFormat("var x = a ? /abc/ : /abc/;");
+  verifyFormat("for (var i = 0; /abc/.test(s[i]); i++) {\n}");
+  verifyFormat("var x = !/abc/.test(y);");
+  verifyFormat("var x = a && /abc/.test(y);");
+  verifyFormat("var x = a || /abc/.test(y);");
+  verifyFormat("var x = a + /abc/.search(y);");
+
+  // Not regex literals.
+  verifyFormat("var a = a / 2 + b / 3;");
+}
+
+TEST_F(FormatTestJS, RegexLiteralSpecialCharacters) {
+  verifyFormat("var regex = /a*/;");
+  verifyFormat("var regex = /a+/;");
+  verifyFormat("var regex = /a?/;");
+  verifyFormat("var regex = /.a./;");
+  verifyFormat("var regex = /a\\*/;");
+  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 = /\\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/;");
+  verifyFormat("var regex = /\\S/;");
+  verifyFormat("var regex = /\\t/;");
+  verifyFormat("var regex = /\\v/;");
+  verifyFormat("var regex = /\\w/;");
+  verifyFormat("var regex = /\\W/;");
+  verifyFormat("var regex = /a(a)\\1/;");
+  verifyFormat("var regex = /\\0/;");
+}
+
+TEST_F(FormatTestJS, RegexLiteralModifiers) {
+  verifyFormat("var regex = /abc/g;");
+  verifyFormat("var regex = /abc/i;");
+  verifyFormat("var regex = /abc/m;");
+  verifyFormat("var regex = /abc/y;");
+}
+
+TEST_F(FormatTestJS, RegexLiteralLength) {
+  verifyFormat("var regex = /aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/;",
+               getGoogleJSStyleWithColumns(60));
+  verifyFormat("var regex =\n"
+               "    /aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/;",
+               getGoogleJSStyleWithColumns(60));
+}
+
+TEST_F(FormatTestJS, RegexLiteralExamples) {
+  verifyFormat("var regex = search.match(/(?:\?|&)times=([^?&]+)/i);");
+}
+
 } // end namespace tooling
 } // end namespace clang