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/test4.test
+++ b/attic/vendor/plugins/HTML5lib/testdata/tokenizer/test4.test
@ -0,0 +1,198 @@
+{"tests": [
+
+{"description":"< in attribute name",
+"input":"<z/0  <",
+"output":["ParseError", "ParseError", ["StartTag", "z", {"0": "", "<": ""}]]},
+
+{"description":"< in attribute value",
+"input":"<z x=<",
+"output":["ParseError", ["StartTag", "z", {"x": "<"}]]},
+
+{"description":"CR EOF after doctype name",
+"input":"<!doctype html \r",
+"output":["ParseError", ["DOCTYPE", "html", null, null, false]]},
+
+{"description":"CR EOF in tag name",
+"input":"<z\r",
+"output":["ParseError", ["StartTag", "z", {}]]},
+
+{"description":"Zero hex numeric entity",
+"input":"&#x0",
+"output":["ParseError", "ParseError", ["Character", "\uFFFD"]]},
+
+{"description":"Zero decimal numeric entity",
+"input":"&#0",
+"output":["ParseError", "ParseError", ["Character", "\uFFFD"]]},
+
+{"description":"Zero-prefixed hex numeric entity",
+"input":"&#x000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000041;",
+"output":[["Character", "A"]]},
+
+{"description":"Zero-prefixed decimal numeric entity",
+"input":"&#000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000065;",
+"output":[["Character", "A"]]},
+
+{"description":"Empty hex numeric entities",
+"input":"&#x &#X ",
+"output":["ParseError", ["Character", "&#x "], "ParseError", ["Character", "&#X "]]},
+
+{"description":"Empty decimal numeric entities",
+"input":"&# &#; ",
+"output":["ParseError", ["Character", "&# "], "ParseError", ["Character", "&#; "]]},
+
+{"description":"Non-BMP numeric entity",
+"input":"&#x10000;",
+"output":[["Character", "\uD800\uDC00"]]},
+
+{"description":"Maximum non-BMP numeric entity",
+"input":"&#X10FFFF;",
+"output":[["Character", "\uDBFF\uDFFF"]]},
+
+{"description":"Above maximum numeric entity",
+"input":"&#x110000;",
+"output":["ParseError", ["Character", "\uFFFD"]]},
+
+{"description":"32-bit hex numeric entity",
+"input":"&#x80000041;",
+"output":["ParseError", ["Character", "\uFFFD"]]},
+
+{"description":"33-bit hex numeric entity",
+"input":"&#x100000041;",
+"output":["ParseError", ["Character", "\uFFFD"]]},
+
+{"description":"33-bit decimal numeric entity",
+"input":"&#4294967361;",
+"output":["ParseError", ["Character", "\uFFFD"]]},
+
+{"description":"65-bit hex numeric entity",
+"input":"&#x10000000000000041;",
+"output":["ParseError", ["Character", "\uFFFD"]]},
+
+{"description":"65-bit decimal numeric entity",
+"input":"&#18446744073709551681;",
+"output":["ParseError", ["Character", "\uFFFD"]]},
+
+{"description":"Surrogate code point edge cases",
+"input":"&#xD7FF;&#xD800;&#xD801;&#xDFFE;&#xDFFF;&#xE000;",
+"output":[["Character", "\uD7FF"], "ParseError", ["Character", "\uFFFD"], "ParseError", ["Character", "\uFFFD"], "ParseError", ["Character", "\uFFFD"], "ParseError", ["Character", "\uFFFD\uE000"]]},
+
+{"description":"Uppercase start tag name",
+"input":"<X>",
+"output":[["StartTag", "x", {}]]},
+
+{"description":"Uppercase end tag name",
+"input":"</X>",
+"output":[["EndTag", "x"]]},
+
+{"description":"Uppercase attribute name",
+"input":"<x X>",
+"output":[["StartTag", "x", { "x":"" }]]},
+
+{"description":"Tag/attribute name case edge values",
+"input":"<x@AZ[`az{ @AZ[`az{>",
+"output":[["StartTag", "x@az[`az{", { "@az[`az{":"" }]]},
+
+{"description":"Duplicate different-case attributes",
+"input":"<x x=1 x=2 X=3>",
+"output":["ParseError", "ParseError", ["StartTag", "x", { "x":"1" }]]},
+
+{"description":"Uppercase close tag attributes",
+"input":"</x X>",
+"output":["ParseError", ["EndTag", "x"]]},
+
+{"description":"Duplicate close tag attributes",
+"input":"</x x x>",
+"output":["ParseError", "ParseError", ["EndTag", "x"]]},
+
+{"description":"Permitted slash",
+"input":"<br/>",
+"output":[["StartTag", "br", {}]]},
+
+{"description":"Non-permitted slash",
+"input":"<xr/>",
+"output":["ParseError", ["StartTag", "xr", {}]]},
+
+{"description":"Permitted slash but in close tag",
+"input":"</br/>",
+"output":["ParseError", ["EndTag", "br"]]},
+
+{"description":"Doctype public case-sensitivity (1)",
+"input":"<!DoCtYpE HtMl PuBlIc \"AbC\" \"XyZ\">",
+"output":[["DOCTYPE", "HtMl", "AbC", "XyZ", true]]},
+
+{"description":"Doctype public case-sensitivity (2)",
+"input":"<!dOcTyPe hTmL pUbLiC \"aBc\" \"xYz\">",
+"output":[["DOCTYPE", "hTmL", "aBc", "xYz", true]]},
+
+{"description":"Doctype system case-sensitivity (1)",
+"input":"<!DoCtYpE HtMl SyStEm \"XyZ\">",
+"output":[["DOCTYPE", "HtMl", null, "XyZ", true]]},
+
+{"description":"Doctype system case-sensitivity (2)",
+"input":"<!dOcTyPe hTmL sYsTeM \"xYz\">",
+"output":[["DOCTYPE", "hTmL", null, "xYz", true]]},
+
+{"description":"U+0000 in lookahead region after non-matching character",
+"input":"<!doc>\u0000",
+"output":["ParseError", ["Comment", "doc"], "ParseError", ["Character", "\uFFFD"]],
+"ignoreErrorOrder":true},
+
+{"description":"U+0000 in lookahead region",
+"input":"<!doc\u0000",
+"output":["ParseError", "ParseError", ["Comment", "doc\uFFFD"]],
+"ignoreErrorOrder":true},
+
+{"description":"CR followed by U+0000",
+"input":"\r\u0000",
+"output":["ParseError", ["Character", "\n\uFFFD"]],
+"ignoreErrorOrder":true},
+
+{"description":"CR followed by non-LF",
+"input":"\r?",
+"output":[["Character", "\n?"]]},
+
+{"description":"CR at EOF",
+"input":"\r",
+"output":[["Character", "\n"]]},
+
+{"description":"LF at EOF",
+"input":"\n",
+"output":[["Character", "\n"]]},
+
+{"description":"CR LF",
+"input":"\r\n",
+"output":[["Character", "\n"]]},
+
+{"description":"CR CR",
+"input":"\r\r",
+"output":[["Character", "\n\n"]]},
+
+{"description":"LF LF",
+"input":"\n\n",
+"output":[["Character", "\n\n"]]},
+
+{"description":"LF CR",
+"input":"\n\r",
+"output":[["Character", "\n\n"]]},
+
+{"description":"text CR CR CR text",
+"input":"text\r\r\rtext",
+"output":[["Character", "text\n\n\ntext"]]},
+
+{"description":"Doctype publik",
+"input":"<!DOCTYPE html PUBLIK \"AbC\" \"XyZ\">",
+"output":["ParseError", ["DOCTYPE", "html", null, null, false]]},
+
+{"description":"Doctype publi",
+"input":"<!DOCTYPE html PUBLI",
+"output":["ParseError", "ParseError", ["DOCTYPE", "html", null, null, false]]},
+
+{"description":"Doctype sistem",
+"input":"<!DOCTYPE html SISTEM \"AbC\">",
+"output":["ParseError", ["DOCTYPE", "html", null, null, false]]},
+
+{"description":"Doctype sys",
+"input":"<!DOCTYPE html SYS",
+"output":["ParseError", "ParseError", ["DOCTYPE", "html", null, null, false]]}
+
+]}