deac/instiki
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Ruby 1.9 Compatibility

Browse source 
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.
This commit is contained in:
Jacques Distler 2009-11-30 16:28:18 -06:00
parent 79c8572053
commit a6429f8c22
142 changed files with 519 additions and 843 deletions
Download patch file Download diff file Expand all files Collapse all files

129
attic/vendor/plugins/HTML5lib/testdata/tokenizer/test2.test vendored Normal file
View file

@ -0,0 +1,129 @@
{"tests": [
{"description":"DOCTYPE without name",
"input":"<!DOCTYPE>",
"output":["ParseError", "ParseError", ["DOCTYPE", "", null, null, false]]},
{"description":"DOCTYPE without space before name",
"input":"<!DOCTYPEhtml>",
"output":["ParseError", ["DOCTYPE", "html", null, null, true]]},
{"description":"Incorrect DOCTYPE without a space before name",
"input":"<!DOCTYPEfoo>",
"output":["ParseError", ["DOCTYPE", "foo", null, null, true]]},
{"description":"DOCTYPE with publicId",
"input":"<!DOCTYPE html PUBLIC \"-//W3C//DTD HTML Transitional 4.01//EN\">",
"output":[["DOCTYPE", "html", "-//W3C//DTD HTML Transitional 4.01//EN", null, true]]},
{"description":"DOCTYPE with EOF after PUBLIC",
"input":"<!DOCTYPE html PUBLIC",
"output":["ParseError", ["DOCTYPE", "html", null, null, false]]},
{"description":"DOCTYPE with EOF after PUBLIC '",
"input":"<!DOCTYPE html PUBLIC '",
"output":["ParseError", ["DOCTYPE", "html", "", null, false]]},
{"description":"DOCTYPE with EOF after PUBLIC 'x",
"input":"<!DOCTYPE html PUBLIC 'x",
"output":["ParseError", ["DOCTYPE", "html", "x", null, false]]},
{"description":"DOCTYPE with systemId",
"input":"<!DOCTYPE html SYSTEM \"-//W3C//DTD HTML Transitional 4.01//EN\">",
"output":[["DOCTYPE", "html", null, "-//W3C//DTD HTML Transitional 4.01//EN", true]]},
{"description":"DOCTYPE with publicId and systemId",
"input":"<!DOCTYPE html PUBLIC \"-//W3C//DTD HTML Transitional 4.01//EN\" \"-//W3C//DTD HTML Transitional 4.01//EN\">",
"output":[["DOCTYPE", "html", "-//W3C//DTD HTML Transitional 4.01//EN", "-//W3C//DTD HTML Transitional 4.01//EN", true]]},
{"description":"Incomplete doctype",
"input":"<!DOCTYPE html ",
"output":["ParseError", ["DOCTYPE", "html", null, null, false]]},
{"description":"Numeric entity representing the NUL character",
"input":"&#0000;",
"output":["ParseError", ["Character", "\uFFFD"]]},
{"description":"Hexadecimal entity representing the NUL character",
"input":"&#x0000;",
"output":["ParseError", ["Character", "\uFFFD"]]},
{"description":"Numeric entity representing a codepoint after 1114111 (U+10FFFF)",
"input":"&#2225222;",
"output":["ParseError", ["Character", "\uFFFD"]]},
{"description":"Hexadecimal entity representing a codepoint after 1114111 (U+10FFFF)",
"input":"&#x1010FFFF;",
"output":["ParseError", ["Character", "\uFFFD"]]},
{"description":"Hexadecimal entity pair representing a surrogate pair",
"input":"&#xD869;&#xDED6;",
"output":["ParseError", ["Character", "\uFFFD"], "ParseError", ["Character", "\uFFFD"]]},
{"description":"Hexadecimal entity with mixed uppercase and lowercase",
"input":"&#xaBcD;",
"output":[["Character", "\uABCD"]]},
{"description":"Entity without a name",
"input":"&;",
"output":["ParseError", ["Character", "&;"]]},
{"description":"Unescaped ampersand in attribute value",
"input":"<h a='&'>",
"output":["ParseError", ["StartTag", "h", { "a":"&" }]]},
{"description":"StartTag containing <",
"input":"<a<b>",
"output":[["StartTag", "a<b", { }]]},
{"description":"Non-void element containing trailing /",
"input":"<h/>",
"output":["ParseError", ["StartTag", "h", { }]]},
{"description":"Void element with permitted slash",
"input":"<br/>",
"output":[["StartTag", "br", { }]]},
{"description":"StartTag containing /",
"input":"<h/a='b'>",
"output":["ParseError", ["StartTag", "h", { "a":"b" }]]},
{"description":"Double-quoted attribute value",
"input":"<h a=\"b\">",
"output":[["StartTag", "h", { "a":"b" }]]},
{"description":"Unescaped </",
"input":"</",
"output":["ParseError", ["Character", "</"]]},
{"description":"Illegal end tag name",
"input":"</1>",
"output":["ParseError", ["Comment", "1"]]},
{"description":"Simili processing instruction",
"input":"<?namespace>",
"output":["ParseError", ["Comment", "?namespace"]]},
{"description":"A bogus comment stops at >, even if preceeded by two dashes",
"input":"<?foo-->",
"output":["ParseError", ["Comment", "?foo--"]]},
{"description":"Unescaped <",
"input":"foo < bar",
"output":[["Character", "foo "], "ParseError", ["Character", "< bar"]]},
{"description":"Null Byte Replacement",
"input":"\u0000",
"output":["ParseError", ["Character", "\ufffd"]]},
{"description":"Comment with dash",
"input":"<!---x",
"output":["ParseError", ["Comment", "-x"]]},
{"description":"Entity + newline",
"input":"\nx\n&gt;\n",
"output":[["Character","\nx\n>\n"]]}
]}