ES6 unicode extensions, part 1.

src/scanner.cc

Index: src/scanner.cc
diff --git a/src/scanner.cc b/src/scanner.cc
index ddcd937584d50fc45fa921a25e2a5d21fcf5697e..97aced924d47ba3f188875ec79e7d24fae0bbe7a 100644
--- a/src/scanner.cc
+++ b/src/scanner.cc
@@ -38,7 +38,8 @@ Scanner::Scanner(UnicodeCache* unicode_cache)
       harmony_scoping_(false),
       harmony_modules_(false),
       harmony_numeric_literals_(false),
-      harmony_classes_(false) { }
+      harmony_classes_(false),
+      harmony_unicode_(false) {}
 
 
 void Scanner::Initialize(Utf16CharacterStream* source) {
@@ -71,6 +72,22 @@ uc32 Scanner::ScanHexNumber(int expected_length) {
 }
 
 
+uc32 Scanner::ScanUnlimitedLengthHexNumber(int max_value) {
+  uc32 x = 0;
+  int d = HexValue(c0_);
+  if (d < 0) {
+    return -1;
+  }
+  while (d >= 0) {
+    x = x * 16 + d;
+    if (x > max_value) return -1;

[caitp (gmail), 2014/11/13 15:09:18]

I don't think this should block landing this, but I think it would be an
improvement if this error condition were handled in the parser, so that an error
could be reported (like "SyntaxError: Unicode escape sequences cannot have a
value exceeding U+10FFFF" or something).

So you'd want to make sure the value doesn't overflow, but max_value checking
could be verified in the parser. Again though, not a blocker, I just think that
would be easier on people. SpiderMonkey outputs some pretty nice static errors
for a lot of these, but V8 is just saying "Unexpected token ____" which is not
that great.

Not a blocker but something to think about

[rossberg, 2014/11/14 09:59:08]

Alternatively, we should enable the scanner to give proper error messages.

+    Advance();
+    d = HexValue(c0_);
+  }
+  return x;
+}
+
+
 // Ensure that tokens can be stored in a byte.
 STATIC_ASSERT(Token::NUM_TOKENS <= 0x100);
 
@@ -694,7 +711,7 @@ bool Scanner::ScanEscape() {
     case 'r' : c = '\r'; break;
     case 't' : c = '\t'; break;
     case 'u' : {
-      c = ScanHexNumber(4);
+      c = ScanUnicodeEscape();
       if (c < 0) return false;
       break;
     }
@@ -887,6 +904,26 @@ uc32 Scanner::ScanIdentifierUnicodeEscape() {
   Advance();
   if (c0_ != 'u') return -1;
   Advance();
+  return ScanUnicodeEscape();
+}
+
+
+uc32 Scanner::ScanUnicodeEscape() {
+  // Accept both \uxxxx and \u{xxxxxx} (if harmony unicode escapes are
+  // allowed). In the latter case, the number of hex digits between { } is
+  // arbitrary. \ and u have already been read.
+  if (c0_ == '{' && HarmonyUnicode()) {
+    Advance();
+    uc32 cp = ScanUnlimitedLengthHexNumber(0x10ffff);
+    if (cp < 0) {
+      return -1;
+    }
+    if (c0_ != '}') {
+      return -1;
+    }
+    Advance();
+    return cp;
+  }
   return ScanHexNumber(4);
 }