parse5 0.6.1 → 1.0.0

package/test/data/tokenizer/pendingSpecChanges.test

@@ -1,7 +0,0 @@
-{"tests": [
-
-{"description":"<!---- >",
-"input":"<!---- >",
-"output":["ParseError", "ParseError", ["Comment","-- >"]]}
-
-]}

package/test/data/tokenizer/test1.test

@@ -1,196 +0,0 @@
-{"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":"Correct Doctype case with EOF",
-"input":"<!DOCTYPE HtMl", 
-"output":["ParseError", ["DOCTYPE", "html", null, null, false]]},
-
-{"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":["ParseError", ["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 \u00ACit"]]},
-
-{"description":"Entity with trailing semicolon (2)",
-"input":"I'm &notin;",
-"output":[["Character","I'm \u2209"]]},
-
-{"description":"Entity without trailing semicolon (1)",
-"input":"I'm &notit",
-"output":[["Character","I'm "], "ParseError", ["Character", "\u00ACit"]]},
-
-{"description":"Entity without trailing semicolon (2)",
-"input":"I'm &notin",
-"output":[["Character","I'm "], "ParseError", ["Character", "\u00ACin"]]},
-
-{"description":"Partial entity match at end of file",
-"input":"I'm &no",
-"output":[["Character","I'm "], "ParseError", ["Character", "&no"]]},
-
-{"description":"Non-ASCII character reference name",
-"input":"&\u00AC;",
-"output":["ParseError", ["Character", "&\u00AC;"]]},
-
-{"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":"\u00A9"}]]},
-
-{"description":"Unquoted attribute ending in ampersand",
-"input":"<s o=& t>",
-"output":[["StartTag","s",{"o":"&","t":""}]]},
-
-{"description":"Unquoted attribute at end of tag with final character of &, with tag followed by characters",
-"input":"<a a=a&>foo",
-"output":[["StartTag", "a", {"a":"a&"}], ["Character", "foo"]]},
-
-{"description":"plaintext element",
- "input":"<plaintext>foobar",
- "output":[["StartTag","plaintext",{}], ["Character","foobar"]]},
-
-{"description":"Open angled bracket in unquoted attribute value state",
- "input":"<a a=f<>",
- "output":["ParseError", ["StartTag", "a", {"a":"f<"}]]}
-
-]}

package/test/data/tokenizer/test2.test

@@ -1,179 +0,0 @@
-{"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":"DOCTYPE with > in double-quoted publicId",
-"input":"<!DOCTYPE html PUBLIC \">x",
-"output":["ParseError", ["DOCTYPE", "html", "", null, false], ["Character", "x"]]},
-
-{"description":"DOCTYPE with > in single-quoted publicId",
-"input":"<!DOCTYPE html PUBLIC '>x",
-"output":["ParseError", ["DOCTYPE", "html", "", null, false], ["Character", "x"]]},
-
-{"description":"DOCTYPE with > in double-quoted systemId",
-"input":"<!DOCTYPE html PUBLIC \"foo\" \">x",
-"output":["ParseError", ["DOCTYPE", "html", "foo", "", false], ["Character", "x"]]},
-
-{"description":"DOCTYPE with > in single-quoted systemId",
-"input":"<!DOCTYPE html PUBLIC 'foo' '>x",
-"output":["ParseError", ["DOCTYPE", "html", "foo", "", false], ["Character", "x"]]},
-
-{"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":[["StartTag", "h", { "a":"&" }]]},
-
-{"description":"StartTag containing <",
-"input":"<a<b>",
-"output":[["StartTag", "a<b", { }]]},
-
-{"description":"Non-void element containing trailing /",
-"input":"<h/>",
-"output":[["StartTag","h",{},true]]},
-
-{"description":"Void element with permitted slash",
-"input":"<br/>",
-"output":[["StartTag","br",{},true]]},
-
-{"description":"Void element with permitted slash (with attribute)",
-"input":"<br foo='bar'/>",
-"output":[["StartTag","br",{"foo":"bar"},true]]},
-
-{"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", "\u0000"]]},
-
-{"description":"Comment with dash",
-"input":"<!---x",
-"output":["ParseError", ["Comment", "-x"]]},
-
-{"description":"Entity + newline",
-"input":"\nx\n&gt;\n",
-"output":[["Character","\nx\n>\n"]]},
-
-{"description":"Start tag with no attributes but space before the greater-than sign",
-"input":"<h >",
-"output":[["StartTag", "h", {}]]},
-
-{"description":"Empty attribute followed by uppercase attribute",
-"input":"<h a B=''>",
-"output":[["StartTag", "h", {"a":"", "b":""}]]},
-
-{"description":"Double-quote after attribute name",
-"input":"<h a \">",
-"output":["ParseError", ["StartTag", "h", {"a":"", "\"":""}]]},
-
-{"description":"Single-quote after attribute name",
-"input":"<h a '>",
-"output":["ParseError", ["StartTag", "h", {"a":"", "'":""}]]},
-
-{"description":"Empty end tag with following characters",
-"input":"a</>bc",
-"output":[["Character", "a"], "ParseError", ["Character", "bc"]]},
-
-{"description":"Empty end tag with following tag",
-"input":"a</><b>c",
-"output":[["Character", "a"], "ParseError", ["StartTag", "b", {}], ["Character", "c"]]},
-
-{"description":"Empty end tag with following comment",
-"input":"a</><!--b-->c",
-"output":[["Character", "a"], "ParseError", ["Comment", "b"], ["Character", "c"]]},
-
-{"description":"Empty end tag with following end tag",
-"input":"a</></b>c",
-"output":[["Character", "a"], "ParseError", ["EndTag", "b"], ["Character", "c"]]}
-
-]}