diff options
-rw-r--r-- | src/tokeniser/tokeniser.c | 20 | ||||
-rw-r--r-- | test/data/tokeniser2/test1.test | 6 |
2 files changed, 15 insertions, 11 deletions
diff --git a/src/tokeniser/tokeniser.c b/src/tokeniser/tokeniser.c index 1f1ae40..54ad118 100644 --- a/src/tokeniser/tokeniser.c +++ b/src/tokeniser/tokeniser.c @@ -2811,17 +2811,25 @@ bool hubbub_tokeniser_handle_named_entity(hubbub_tokeniser *tokeniser) return false; cptr = parserutils_inputstream_peek(tokeniser->input, - ctx->match_entity.offset + ctx->match_entity.length - 1, + ctx->match_entity.offset + ctx->match_entity.length, &len); c = CHAR(cptr); if ((tokeniser->context.match_entity.return_state == STATE_CHARACTER_REFERENCE_IN_ATTRIBUTE_VALUE) && - (c != ';') && - ((0x0030 <= c && c <= 0x0039) || - (0x0041 <= c && c <= 0x005A) || - (0x0061 <= c && c <= 0x007A))) { - ctx->match_entity.codepoint = 0; + (c != ';')) { + + cptr = parserutils_inputstream_peek(tokeniser->input, + ctx->match_entity.offset + + ctx->match_entity.length, + &len); + c = CHAR(cptr); + + if ((0x0030 <= c && c <= 0x0039) || + (0x0041 <= c && c <= 0x005A) || + (0x0061 <= c && c <= 0x007A)) { + ctx->match_entity.codepoint = 0; + } } /* Flag completion */ diff --git a/test/data/tokeniser2/test1.test b/test/data/tokeniser2/test1.test index e40e5f8..46ad7ca 100644 --- a/test/data/tokeniser2/test1.test +++ b/test/data/tokeniser2/test1.test @@ -169,12 +169,8 @@ "input":"<h a='¬i'>", "output":["ParseError", ["StartTag", "h", {"a":"¬i"}]]}, -{"description":"Entity in attribute with semicolon", -"input":"<h a='©'>", -"output":["ParseError", ["StartTag", "h", {"a":"\u00A9"}]]}, - {"description":"Entity in attribute without semicolon", "input":"<h a='©'>", -"output":["ParseError", ["StartTag", "h", {"a":"©"}]]} +"output":["ParseError", ["StartTag", "h", {"a":"\u00A9"}]]} ]} |