Fix Chromium issue 176 by treating byte-order marks as whitespace.

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@765 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
This commit is contained in:
kasperl@chromium.org 2008-11-17 06:56:28 +00:00
parent 7940adb1ec
commit d24556d1c5
2 changed files with 16 additions and 5 deletions

View File

@ -234,11 +234,25 @@ void Scanner::PushBack(uc32 ch) {
}
static inline bool IsByteOrderMark(uc32 c) {
// The Unicode value U+FFFE is guaranteed never to be assigned as a
// Unicode character; this implies that in a Unicode context the
// 0xFF, 0xFE byte pattern can only be interpreted as the U+FEFF
// character expressed in little-endian byte order (since it could
// not be a U+FFFE character expressed in big-endian byte
// order). Nevertheless, we check for it to be compatible with
// Spidermonkey.
return c == 0xFEFF || c == 0xFFFE;
}
void Scanner::SkipWhiteSpace(bool initial) {
has_line_terminator_before_next_ = initial;
while (true) {
while (kIsWhiteSpace.get(c0_)) {
// We treat byte-order marks (BOMs) as whitespace for better
// compatibility with Spidermonkey and other JavaScript engines.
while (kIsWhiteSpace.get(c0_) || IsByteOrderMark(c0_)) {
// IsWhiteSpace() includes line terminators!
if (kIsLineTerminator.get(c0_))
// Ignore line terminators, but remember them. This is necessary

View File

@ -570,10 +570,7 @@ js1_5/Regress/regress-306633: FAIL
js1_5/Regress/regress-303213: FAIL
# Bug 1193440: Ignore Unicode BOM characters when scanning.
ecma_3/extensions/regress-368516: FAIL
# Bug 1202592:New ecma_3/String/15.5.4.11 is failing.
# Bug 1202592: New ecma_3/String/15.5.4.11 is failing.
ecma_3/String/15.5.4.11: FAIL
# Bug 1202597: New js1_5/Expressions/regress-394673 is failing.