Reviewers: Erik Corry,
Description:
Convert Unicode code points outside the basic multilingual plane to the
replacement character.
Previous behavior was to silently truncate the value to 16 bits.
Please review this at http://codereview.chromium.org/2832050/show
Affected files:
M src/heap.cc
Index: src/heap.cc
diff --git a/src/heap.cc b/src/heap.cc
index
6ae46f2a6ee743e4bac99446ca61e08288657b91..fa6344556fbcc43e633a1d9c5c67eb7cca7ae3a7
100644
--- a/src/heap.cc
+++ b/src/heap.cc
@@ -2866,6 +2866,8 @@ Object* Heap::AllocateStringFromAscii(Vector<const
char> string,
Object* Heap::AllocateStringFromUtf8(Vector<const char> string,
PretenureFlag pretenure) {
+ // V8 only supports characters in the Basic Multilingual Plane.
+ const uc32 kMaxSupportedChar = 0xFFFF;
// Count the number of characters in the UTF-8 string and check if
// it is an ASCII string.
Access<Scanner::Utf8Decoder> decoder(Scanner::utf8_decoder());
@@ -2890,6 +2892,7 @@ Object* Heap::AllocateStringFromUtf8(Vector<const
char> string,
decoder->Reset(string.start(), string.length());
for (int i = 0; i < chars; i++) {
uc32 r = decoder->GetNext();
+ if (r > kMaxSupportedChar) { r = unibrow::Utf8::kBadChar; }
string_result->Set(i, r);
}
return result;
--
v8-dev mailing list
[email protected]
http://groups.google.com/group/v8-dev
