Sync with latest HTML5lib and latest Maruku

This commit is contained in:
Jacques Distler 2007-07-04 17:36:59 -05:00
parent 8e92e4a3ab
commit 8ccaad85a5
71 changed files with 1974 additions and 1621 deletions

View file

@ -135,7 +135,7 @@
{"description":"Entity without trailing semicolon (2)",
"input":"I'm &notin",
"output":[["Character","I'm "], "ParseError", ["Character", ""]]},
"output":[["Character","I'm "], "ParseError", ["Character", "¬in"]]},
{"description":"Partial entity match at end of file",
"input":"I'm &no",
@ -151,6 +151,18 @@
{"description":"Hexadecimal entity in attribute",
"input":"<h a='&#x3f;'></h>",
"output":[["StartTag", "h", {"a":"?"}], ["EndTag", "h"]]}
"output":[["StartTag", "h", {"a":"?"}], ["EndTag", "h"]]},
{"description":"Entity in attribute without semicolon ending in x",
"input":"<h a='&notx'>",
"output":["ParseError", ["StartTag", "h", {"a":"&notx"}]]},
{"description":"Entity in attribute without semicolon ending in 1",
"input":"<h a='&not1'>",
"output":["ParseError", ["StartTag", "h", {"a":"&not1"}]]},
{"description":"Entity in attribute without semicolon",
"input":"<h a='&COPY'>",
"output":["ParseError", ["StartTag", "h", {"a":"©"}]]}
]}

View file

@ -42,19 +42,23 @@
{"description":"Numeric entity representing the NUL character",
"input":"&#0000;",
"output":[["Character", "\uFFFD"]]},
"output":["ParseError", ["Character", "\uFFFD"]]},
{"description":"Hexadecimal entity representing the NUL character",
"input":"&#x0000;",
"output":[["Character", "\uFFFD"]]},
"output":["ParseError", ["Character", "\uFFFD"]]},
{"description":"Numeric entity representing a codepoint after 1114111 (U+10FFFF)",
"input":"&#2225222;",
"output":[["Character", "\uFFFD"]]},
"output":["ParseError", ["Character", "\uFFFD"]]},
{"description":"Hexadecimal entity representing a codepoint after 1114111 (U+10FFFF)",
"input":"&#x1010FFFF;",
"output":[["Character", "\uFFFD"]]},
"output":["ParseError", ["Character", "\uFFFD"]]},
{"description":"Hexadecimal entity pair representing a surrogate pair",
"input":"&#xD869;&#xDED6;",
"output":["ParseError", ["Character", "\uFFFD"], "ParseError", ["Character", "\uFFFD"]]},
{"description":"Numeric entity representing a Windows-1252 'codepoint'",
"input":"&#137;",
@ -118,7 +122,7 @@
{"description":"Null Byte Replacement",
"input":"\u0000",
"output":[["Character", "\ufffd"]]}
"output":["ParseError", ["Character", "\ufffd"]]}
]}