Ruby 1.9 Compatibility

Completely removed the html5lib sanitizer. Fixed the string-handling to work in both Ruby 1.8.x and 1.9.2. There are still, inexplicably, two functional tests that fail. But the rest seems to work quite well.
2009-11-30 16:28:18 -06:00 · 2009-11-30 16:28:18 -06:00 · a6429f8c22
commit a6429f8c22
parent 79c8572053
142 changed files with 519 additions and 843 deletions
--- a/attic/vendor/plugins/HTML5lib/testdata/tokenizer/test1.test
+++ b/attic/vendor/plugins/HTML5lib/testdata/tokenizer/test1.test
@ -0,0 +1,172 @@
+{"tests": [
+
+{"description":"Correct Doctype lowercase",
+"input":"<!DOCTYPE html>",
+"output":[["DOCTYPE", "html", null, null, true]]},
+
+{"description":"Correct Doctype uppercase",
+"input":"<!DOCTYPE HTML>",
+"output":[["DOCTYPE", "HTML", null, null, true]]},
+
+{"description":"Correct Doctype mixed case",
+"input":"<!DOCTYPE HtMl>", 
+"output":[["DOCTYPE", "HtMl", null, null, true]]},
+
+{"description":"Truncated doctype start",
+"input":"<!DOC>", 
+"output":["ParseError", ["Comment", "DOC"]]},
+
+{"description":"Doctype in error",
+"input":"<!DOCTYPE foo>", 
+"output":[["DOCTYPE", "foo", null, null, true]]},
+
+{"description":"Single Start Tag",
+"input":"<h>",
+"output":[["StartTag", "h", {}]]},
+
+{"description":"Empty end tag",
+"input":"</>",
+"output":["ParseError"]},
+
+{"description":"Empty start tag",
+"input":"<>",
+"output":["ParseError", ["Character", "<>"]]},
+
+{"description":"Start Tag w/attribute",
+"input":"<h a='b'>",
+"output":[["StartTag", "h", {"a":"b"}]]},
+
+{"description":"Start Tag w/attribute no quotes",
+"input":"<h a=b>",
+"output":[["StartTag", "h", {"a":"b"}]]},
+
+{"description":"Start/End Tag",
+"input":"<h></h>",
+"output":[["StartTag", "h", {}], ["EndTag", "h"]]},
+
+{"description":"Two unclosed start tags",
+"input":"<p>One<p>Two",
+"output":[["StartTag", "p", {}], ["Character", "One"], ["StartTag", "p", {}], ["Character", "Two"]]},
+
+{"description":"End Tag w/attribute",
+"input":"<h></h a='b'>",
+"output":[["StartTag", "h", {}], "ParseError", ["EndTag", "h"]]},
+
+{"description":"Multiple atts",
+"input":"<h a='b' c='d'>",
+"output":[["StartTag", "h", {"a":"b", "c":"d"}]]},
+
+{"description":"Multiple atts no space",
+"input":"<h a='b'c='d'>",
+"output":[["StartTag", "h", {"a":"b", "c":"d"}]]},
+
+{"description":"Repeated attr",
+ "input":"<h a='b' a='d'>",
+ "output":["ParseError", ["StartTag", "h", {"a":"b"}]]},
+
+{"description":"Simple comment",
+ "input":"<!--comment-->",
+ "output":[["Comment", "comment"]]},
+
+{"description":"Comment, Central dash no space",
+ "input":"<!----->",
+ "output":["ParseError", ["Comment", "-"]]},
+
+{"description":"Comment, two central dashes",
+"input":"<!-- --comment -->",
+"output":["ParseError", ["Comment", " --comment "]]},
+
+{"description":"Unfinished comment",
+"input":"<!--comment",
+"output":["ParseError", ["Comment", "comment"]]},
+
+{"description":"Start of a comment",
+"input":"<!-",
+"output":["ParseError", ["Comment", "-"]]},
+
+{"description":"Short comment",
+ "input":"<!-->",
+ "output":["ParseError", ["Comment", ""]]},
+
+{"description":"Short comment two",
+ "input":"<!--->",
+ "output":["ParseError", ["Comment", ""]]},
+
+{"description":"Short comment three",
+ "input":"<!---->",
+ "output":[["Comment", ""]]},
+
+
+{"description":"Ampersand EOF",
+"input":"&",
+"output":[["Character", "&"]]},
+
+{"description":"Ampersand ampersand EOF",
+"input":"&&",
+"output":[["Character", "&&"]]},
+
+{"description":"Ampersand space EOF",
+"input":"& ",
+"output":[["Character", "& "]]},
+
+{"description":"Unfinished entity",
+"input":"&f",
+"output":["ParseError", ["Character", "&f"]]},
+
+{"description":"Ampersand, number sign",
+"input":"&#",
+"output":["ParseError", ["Character", "&#"]]},
+
+{"description":"Unfinished numeric entity",
+"input":"&#x",
+"output":["ParseError", ["Character", "&#x"]]},
+
+{"description":"Entity with trailing semicolon (1)",
+"input":"I'm &not;it",
+"output":[["Character","I'm ¬it"]]},
+
+{"description":"Entity with trailing semicolon (2)",
+"input":"I'm &notin;",
+"output":[["Character","I'm ∉"]]},
+
+{"description":"Entity without trailing semicolon (1)",
+"input":"I'm &notit",
+"output":[["Character","I'm "], "ParseError", ["Character", "¬it"]]},
+
+{"description":"Entity without trailing semicolon (2)",
+"input":"I'm &notin",
+"output":[["Character","I'm "], "ParseError", ["Character", "¬in"]]},
+
+{"description":"Partial entity match at end of file",
+"input":"I'm &no",
+"output":[["Character","I'm "], "ParseError", ["Character", "&no"]]},
+
+{"description":"ASCII decimal entity",
+"input":"&#0036;",
+"output":[["Character","$"]]},
+
+{"description":"ASCII hexadecimal entity",
+"input":"&#x3f;",
+"output":[["Character","?"]]},
+
+{"description":"Hexadecimal entity in attribute",
+"input":"<h a='&#x3f;'></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 ending in i",
+"input":"<h a='&noti'>",
+"output":["ParseError", ["StartTag", "h", {"a":"&noti"}]]},
+
+{"description":"Entity in attribute without semicolon",
+"input":"<h a='&COPY'>",
+"output":["ParseError", ["StartTag", "h", {"a":"©"}]]}
+
+]}