bazarr/libs/html5lib/tests/testdata/tokenizer/test1.test

197 lines
5.5 KiB
Plaintext

{"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":[["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 &no"]]},
{"description":"Non-ASCII character reference name",
"input":"&\u00AC;",
"output":[["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":[["StartTag", "h", {"a":"&notx"}]]},
{"description":"Entity in attribute without semicolon ending in 1",
"input":"<h a='&not1'>",
"output":[["StartTag", "h", {"a":"&not1"}]]},
{"description":"Entity in attribute without semicolon ending in i",
"input":"<h a='&noti'>",
"output":[["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<"}]]}
]}