Implement ES6 unicode escapes.

src/scanner.cc

 // Copyright 2011 the V8 project authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 // Features shared by parsing and pre-parsing scanners.
 
 #include <stdint.h>
 
 #include <cmath>
 
@@ skipping 676 matching lines @@
   switch (c) {
     case '\'':  // fall through
     case '"' :  // fall through
     case '\\': break;
     case 'b' : c = '\b'; break;
     case 'f' : c = '\f'; break;
     case 'n' : c = '\n'; break;
     case 'r' : c = '\r'; break;
     case 't' : c = '\t'; break;
     case 'u' : {
-      c = ScanHexNumber(4);
+      c = ScanUnicodeEscape();
       if (c < 0) return false;
       break;
     }
     case 'v' : c = '\v'; break;
     case 'x' : {
       c = ScanHexNumber(2);
       if (c < 0) return false;
       break;
     }
     case '0' :  // fall through
@@ skipping 172 matching lines @@
   literal.Complete();
 
   return Token::NUMBER;
 }
 
 
 uc32 Scanner::ScanIdentifierUnicodeEscape() {
   Advance();
   if (c0_ != 'u') return -1;
   Advance();
-  return ScanHexNumber(4);
+  return ScanUnicodeEscape();
 }
 
 
+uc32 Scanner::ScanUnicodeEscape() {
+  // Accept both \uxxxx and \u{xxxx}. \ and u have already been read.
+  bool has_brace = false;
+  if (c0_ == '{') {
+    has_brace = true;
+    Advance();
+  }
+  uc32 c = ScanHexNumber(4);

[arv (Not doing code reviews), 2014/11/07 16:23:20]

In case of u{ then there is no upper limit for the number of hex digits.

[caitp (gmail), 2014/11/07 16:23:55]

If `has_brace` is true, we want the HexDigits non-terminal, which is not limited
to 4 digits (as I'm reading it) --- as opposed to `Hex4Digits` non-terminal
which should be exactly 4 digits.

I guess arv beat me to it :>

[marja, 2014/11/13 11:53:20]

Done.

+  if (c < 0) {
+    return c;
+  }
+  if (has_brace) {
+    if (c0_ != '}') {
+      return 1;

[caitp (gmail), 2014/11/07 16:50:39]

shouldn't this return -1 so that the scanner knows it's a bad token? otherwise
it looks the same as \u{1}

[marja, 2014/11/13 11:53:20]

Done.

+    }
+    Advance();
+  }
+  return c;
+}
+
+
 // ----------------------------------------------------------------------------
 // Keyword Matcher
 
 #define KEYWORDS(KEYWORD_GROUP, KEYWORD)                                     \
   KEYWORD_GROUP('b')                                                         \
   KEYWORD("break", Token::BREAK)                                             \
   KEYWORD_GROUP('c')                                                         \
   KEYWORD("case", Token::CASE)                                               \
   KEYWORD("catch", Token::CATCH)                                             \
   KEYWORD("class",                                                           \
@@ skipping 422 matching lines @@
     }
     backing_store_.Add(static_cast<uint8_t>((one_byte_length >> 7) | 0x80u));
   }
   backing_store_.Add(static_cast<uint8_t>(one_byte_length & 0x7f));
 
   backing_store_.AddBlock(bytes);
   return backing_store_.EndSequence().start();
 }
 
 } }  // namespace v8::internal