From 7692c69e500284e9ace13b486af8d5e6f1f4a9de Mon Sep 17 00:00:00 2001 From: Rupinder Singh Khokhar Date: Fri, 20 Jun 2014 22:14:13 +0530 Subject: Handling LF after CR in bogus comment state & changing few tests to make it in accordance with the tester interface --- src/tokeniser/tokeniser.c | 5 +++-- test/data/tokeniser2/INDEX | 2 +- test/data/tokeniser2/domjs.test | 11 ++++------- 3 files changed, 8 insertions(+), 10 deletions(-) diff --git a/src/tokeniser/tokeniser.c b/src/tokeniser/tokeniser.c index 7a54df9..ca13366 100644 --- a/src/tokeniser/tokeniser.c +++ b/src/tokeniser/tokeniser.c @@ -1790,11 +1790,12 @@ hubbub_error hubbub_tokeniser_handle_bogus_comment(hubbub_tokeniser *tokeniser) tokeniser->context.pending += len; } else if (c == '\r') { + size_t next_len; error = parserutils_inputstream_peek( tokeniser->input, - tokeniser->context.pending, + tokeniser->context.pending + len, &cptr, - &len); + &next_len); if (error != PARSERUTILS_OK && error != PARSERUTILS_EOF) { return hubbub_error_from_parserutils_error(error); diff --git a/test/data/tokeniser2/INDEX b/test/data/tokeniser2/INDEX index fe2b6e6..cedb81f 100644 --- a/test/data/tokeniser2/INDEX +++ b/test/data/tokeniser2/INDEX @@ -13,7 +13,7 @@ numericEntities.test html5lib numeric entities tests unicodeChars.test html5lib unicode character tests cdata.test CDATA section tests regression.test Regression tests -#domjs.test NA +domjs.test html5lib parsing in tokeniser tests namedEntities.test html5lib named entities tests pendingSpecChanges.test NA unicodeCharsProblematic.test html5lib unicode exceptions tests diff --git a/test/data/tokeniser2/domjs.test b/test/data/tokeniser2/domjs.test index b9e650c..afb17bc 100644 --- a/test/data/tokeniser2/domjs.test +++ b/test/data/tokeniser2/domjs.test @@ -12,14 +12,12 @@ }, { "description":"NUL in RCDATA and RAWTEXT", - "doubleEscaped":true, "initialStates":["RCDATA state", "RAWTEXT state"], - "input":"\\u0000", - "output":["ParseError", ["Character", "\\uFFFD"]] + "input":"\u0000", + "output":["ParseError", ["Character", "\uFFFD"]] }, { "description":"leading U+FEFF must pass through", - "doubleEscaped":true, "input":"\\uFEFFfoo\\uFEFFbar", "output":[["Character", "\\uFEFFfoo\\uFEFFbar"]] }, @@ -77,9 +75,8 @@ }, { "description":"--!NUL in comment ", - "doubleEscaped":true, - "input":"", - "output":["ParseError", "ParseError", ["Comment", "--!\\uFFFD"]] + "input":"", + "output":["ParseError", "ParseError", ["Comment", "--!\uFFFD"]] }, { "description":"space EOF after doctype ", -- cgit v1.2.3