html-to-markdown 2.24.6 → 2.25.1

data/rust-vendor/markup5ever_rcdom/html5lib-tests/serializer/options.test

@@ -1,60 +0,0 @@
-{"tests":[
-
-{"description": "quote_char=\"'\"",
- "options": {"quote_char": "'"},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "span", [{"namespace": null, "name": "title", "value": "test 'with' quote_char"}]]],
- "expected": ["<span title='test &#39;with&#39; quote_char'>"]
-},
-
-{"description": "quote_attr_values=true",
- "options": {"quote_attr_values": true},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "button", [{"namespace": null, "name": "disabled", "value" :"disabled"}]]],
- "expected": ["<button disabled>"],
- "xhtml":    ["<button disabled=\"disabled\">"]
-},
-
-{"description": "quote_attr_values=true with irrelevant",
- "options": {"quote_attr_values": true},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "div", [{"namespace": null, "name": "irrelevant", "value" :"irrelevant"}]]],
- "expected": ["<div irrelevant>"],
- "xhtml":    ["<div irrelevant=\"irrelevant\">"]
-},
-
-{"description": "use_trailing_solidus=true with void element",
- "options": {"use_trailing_solidus": true},
- "input": [["EmptyTag", "img", {}]],
- "expected": ["<img />"]
-},
-
-{"description": "use_trailing_solidus=true with non-void element",
- "options": {"use_trailing_solidus": true},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "div", {}]],
- "expected": ["<div>"]
-},
-
-{"description": "minimize_boolean_attributes=false",
- "options": {"minimize_boolean_attributes": false},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "div", [{"namespace": null, "name": "irrelevant", "value" :"irrelevant"}]]],
- "expected": ["<div irrelevant=irrelevant>"],
- "xhtml":    ["<div irrelevant=\"irrelevant\">"]
-},
-
-{"description": "minimize_boolean_attributes=false with empty value",
- "options": {"minimize_boolean_attributes": false},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "div", [{"namespace": null, "name": "irrelevant", "value" :""}]]],
- "expected": ["<div irrelevant=\"\">"]
-},
-
-{"description": "escape less than signs in attribute values",
- "options": {"escape_lt_in_attrs": true},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "a", [{"namespace": null, "name": "title", "value": "a<b>c&d"}]]],
- "expected": ["<a title=\"a&lt;b>c&amp;d\">"]
-},
-
-{"description": "rcdata",
- "options": {"escape_rcdata": true},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "script", {}], ["Characters", "a<b>c&d"]],
- "expected": ["<script>a&lt;b&gt;c&amp;d"]
-}
-
-]}

data/rust-vendor/markup5ever_rcdom/html5lib-tests/serializer/whitespace.test

@@ -1,51 +0,0 @@
-{"tests": [
-
-{"description": "bare text with leading spaces",
- "options": {"strip_whitespace": true},
- "input": [["Characters", "\t\r\n\u000C foo"]],
- "expected": [" foo"]
-},
-
-{"description": "bare text with trailing spaces",
- "options": {"strip_whitespace": true},
- "input": [["Characters", "foo \t\r\n\u000C"]],
- "expected": ["foo "]
-},
-
-{"description": "bare text with inner spaces",
- "options": {"strip_whitespace": true},
- "input": [["Characters", "foo \t\r\n\u000C bar"]],
- "expected": ["foo bar"]
-},
-
-{"description": "text within <pre>",
- "options": {"strip_whitespace": true},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "pre", {}], ["Characters", "\t\r\n\u000C foo \t\r\n\u000C bar \t\r\n\u000C"], ["EndTag", "http://www.w3.org/1999/xhtml", "pre"]],
- "expected": ["<pre>\t\r\n\u000C foo \t\r\n\u000C bar \t\r\n\u000C</pre>"]
-},
-
-{"description": "text within <pre>, with inner markup",
- "options": {"strip_whitespace": true},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "pre", {}], ["Characters", "\t\r\n\u000C fo"], ["StartTag", "http://www.w3.org/1999/xhtml", "span", {}], ["Characters", "o \t\r\n\u000C b"], ["EndTag", "http://www.w3.org/1999/xhtml", "span"], ["Characters", "ar \t\r\n\u000C"], ["EndTag", "http://www.w3.org/1999/xhtml", "pre"]],
- "expected": ["<pre>\t\r\n\u000C fo<span>o \t\r\n\u000C b</span>ar \t\r\n\u000C</pre>"]
-},
-
-{"description": "text within <textarea>",
- "options": {"strip_whitespace": true},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "textarea", {}], ["Characters", "\t\r\n\u000C foo \t\r\n\u000C bar \t\r\n\u000C"], ["EndTag", "http://www.w3.org/1999/xhtml", "textarea"]],
- "expected": ["<textarea>\t\r\n\u000C foo \t\r\n\u000C bar \t\r\n\u000C</textarea>"]
-},
-
-{"description": "text within <script>",
- "options": {"strip_whitespace": true},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "script", {}], ["Characters", "\t\r\n\u000C foo \t\r\n\u000C bar \t\r\n\u000C"], ["EndTag", "http://www.w3.org/1999/xhtml", "script"]],
- "expected": ["<script>\t\r\n\u000C foo \t\r\n\u000C bar \t\r\n\u000C</script>"]
-},
-
-{"description": "text within <style>",
- "options": {"strip_whitespace": true},
- "input": [["StartTag", "http://www.w3.org/1999/xhtml", "style", {}], ["Characters", "\t\r\n\u000C foo \t\r\n\u000C bar \t\r\n\u000C"], ["EndTag", "http://www.w3.org/1999/xhtml", "style"]],
- "expected": ["<style>\t\r\n\u000C foo \t\r\n\u000C bar \t\r\n\u000C</style>"]
-}
-
-]}

data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/README.md

@@ -1,107 +0,0 @@
-Tokenizer tests
-===============
-
-The test format is [JSON](http://www.json.org/). This has the advantage
-that the syntax allows backward-compatible extensions to the tests and
-the disadvantage that it is relatively verbose.
-
-Basic Structure
----------------
-
-    {"tests": [
-        {"description": "Test description",
-        "input": "input_string",
-        "output": [expected_output_tokens],
-        "initialStates": [initial_states],
-        "lastStartTag": last_start_tag,
-        "errors": [parse_errors]
-        }
-    ]}
-
-Multiple tests per file are allowed simply by adding more objects to the
-"tests" list.
-
-Each parse error is an object that contains error `code` and one-based
-error location indices: `line` and `col`.
-
-`description`, `input` and `output` are always present. The other values
-are optional.
-
-### Test set-up
-
-`test.input` is a string containing the characters to pass to the
-tokenizer. Specifically, it represents the characters of the **input
-stream**, and so implementations are expected to perform the processing
-described in the spec's **Preprocessing the input stream** section
-before feeding the result to the tokenizer.
-
-If `test.doubleEscaped` is present and `true`, then `test.input` is not
-quite as described above. Instead, it must first be subjected to another
-round of unescaping (i.e., in addition to any unescaping involved in the
-JSON import), and the result of *that* represents the characters of the
-input stream. Currently, the only unescaping required by this option is
-to convert each sequence of the form \\uHHHH (where H is a hex digit)
-into the corresponding Unicode code point. (Note that this option also
-affects the interpretation of `test.output`.)
-
-`test.initialStates` is a list of strings, each being the name of a
-tokenizer state which can be one of the following:
-
--   `Data state`
--   `PLAINTEXT state`
--   `RCDATA state`
--   `RAWTEXT state`
--   `Script data state`
--   `CDATA section state`
-
- The test should be run once for each string, using it
-to set the tokenizer's initial state for that run. If
-`test.initialStates` is omitted, it defaults to `["Data state"]`.
-
-`test.lastStartTag` is a lowercase string that should be used as "the
-tag name of the last start tag to have been emitted from this
-tokenizer", referenced in the spec's definition of **appropriate end tag
-token**. If it is omitted, it is treated as if "no start tag has been
-emitted from this tokenizer".
-
-### Test results
-
-`test.output` is a list of tokens, ordered with the first produced by
-the tokenizer the first (leftmost) in the list. The list must mach the
-**complete** list of tokens that the tokenizer should produce. Valid
-tokens are:
-
-    ["DOCTYPE", name, public_id, system_id, correctness]
-    ["StartTag", name, {attributes}*, true*]
-    ["StartTag", name, {attributes}]
-    ["EndTag", name]
-    ["Comment", data]
-    ["Character", data]
-
-`public_id` and `system_id` are either strings or `null`. `correctness`
-is either `true` or `false`; `true` corresponds to the force-quirks flag
-being false, and vice-versa.
-
-When the self-closing flag is set, the `StartTag` array has `true` as
-its fourth entry. When the flag is not set, the array has only three
-entries for backwards compatibility.
-
-All adjacent character tokens are coalesced into a single
-`["Character", data]` token.
-
-If `test.doubleEscaped` is present and `true`, then every string within
-`test.output` must be further unescaped (as described above) before
-comparing with the tokenizer's output.
-
-xmlViolation tests
-------------------
-
-`tokenizer/xmlViolation.test` differs from the above in a couple of
-ways:
-
--   The name of the single member of the top-level JSON object is
-    "xmlViolationTests" instead of "tests".
--   Each test's expected output assumes that implementation is applying
-    the tweaks given in the spec's "Coercing an HTML DOM into an
-    infoset" section.
-

data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/contentModelFlags.test

@@ -1,93 +0,0 @@
-{"tests": [
-
-{"description":"PLAINTEXT content model flag",
-"initialStates":["PLAINTEXT state"],
-"lastStartTag":"plaintext",
-"input":"<head>&body;",
-"output":[["Character", "<head>&body;"]]},
-
-{"description":"PLAINTEXT with seeming close tag",
-"initialStates":["PLAINTEXT state"],
-"lastStartTag":"plaintext",
-"input":"</plaintext>&body;",
-"output":[["Character", "</plaintext>&body;"]]},
-
-{"description":"End tag closing RCDATA or RAWTEXT",
-"initialStates":["RCDATA state", "RAWTEXT state"],
-"lastStartTag":"xmp",
-"input":"foo</xmp>",
-"output":[["Character", "foo"], ["EndTag", "xmp"]]},
-
-{"description":"End tag closing RCDATA or RAWTEXT (case-insensitivity)",
-"initialStates":["RCDATA state", "RAWTEXT state"],
-"lastStartTag":"xmp",
-"input":"foo</xMp>",
-"output":[["Character", "foo"], ["EndTag", "xmp"]]},
-
-{"description":"End tag closing RCDATA or RAWTEXT (ending with space)",
-"initialStates":["RCDATA state", "RAWTEXT state"],
-"lastStartTag":"xmp",
-"input":"foo</xmp ",
-"output":[["Character", "foo"]],
-"errors":[
-    { "code": "eof-in-tag", "line": 1, "col": 10 }
-]},
-
-{"description":"End tag closing RCDATA or RAWTEXT (ending with EOF)",
-"initialStates":["RCDATA state", "RAWTEXT state"],
-"lastStartTag":"xmp",
-"input":"foo</xmp",
-"output":[["Character", "foo</xmp"]]},
-
-{"description":"End tag closing RCDATA or RAWTEXT (ending with slash)",
-"initialStates":["RCDATA state", "RAWTEXT state"],
-"lastStartTag":"xmp",
-"input":"foo</xmp/",
-"output":[["Character", "foo"]],
-"errors":[
-    { "code": "eof-in-tag", "line": 1, "col": 10 }
-]},
-
-{"description":"End tag not closing RCDATA or RAWTEXT (ending with left-angle-bracket)",
-"initialStates":["RCDATA state", "RAWTEXT state"],
-"lastStartTag":"xmp",
-"input":"foo</xmp<",
-"output":[["Character", "foo</xmp<"]]},
-
-{"description":"End tag with incorrect name in RCDATA or RAWTEXT",
-"initialStates":["RCDATA state", "RAWTEXT state"],
-"lastStartTag":"xmp",
-"input":"</foo>bar</xmp>",
-"output":[["Character", "</foo>bar"], ["EndTag", "xmp"]]},
-
-{"description":"Partial end tags leading straight into partial end tags",
-"initialStates":["RCDATA state", "RAWTEXT state"],
-"lastStartTag":"xmp",
-"input":"</xmp</xmp</xmp>",
-"output":[["Character", "</xmp</xmp"], ["EndTag", "xmp"]]},
-
-{"description":"End tag with incorrect name in RCDATA or RAWTEXT (starting like correct name)",
-"initialStates":["RCDATA state", "RAWTEXT state"],
-"lastStartTag":"xmp",
-"input":"</foo>bar</xmpaar>",
-"output":[["Character", "</foo>bar</xmpaar>"]]},
-
-{"description":"End tag closing RCDATA or RAWTEXT, switching back to PCDATA",
-"initialStates":["RCDATA state", "RAWTEXT state"],
-"lastStartTag":"xmp",
-"input":"foo</xmp></baz>",
-"output":[["Character", "foo"], ["EndTag", "xmp"], ["EndTag", "baz"]]},
-
-{"description":"RAWTEXT w/ something looking like an entity",
-"initialStates":["RAWTEXT state"],
-"lastStartTag":"xmp",
-"input":"&foo;",
-"output":[["Character", "&foo;"]]},
-
-{"description":"RCDATA w/ an entity",
-"initialStates":["RCDATA state"],
-"lastStartTag":"textarea",
-"input":"&lt;",
-"output":[["Character", "<"]]}
-
-]}

data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/domjs.test

@@ -1,335 +0,0 @@
-{
-    "tests": [
-        {
-            "description":"CR in bogus comment state",
-            "input":"<?\u000d",
-            "output":[["Comment", "?\u000a"]],
-            "errors":[
-                { "code": "unexpected-question-mark-instead-of-tag-name", "line": 1, "col": 2 }
-            ]
-        },
-        {
-            "description":"CRLF in bogus comment state",
-            "input":"<?\u000d\u000a",
-            "output":[["Comment", "?\u000a"]],
-            "errors":[
-                { "code": "unexpected-question-mark-instead-of-tag-name", "line": 1, "col": 2 }
-            ]
-        },
-        {
-            "description":"CRLFLF in bogus comment state",
-            "input":"<?\u000d\u000a\u000a",
-            "output":[["Comment", "?\u000a\u000a"]],
-            "errors":[
-                { "code": "unexpected-question-mark-instead-of-tag-name", "line": 1, "col": 2 }
-            ]
-        },
-        {
-            "description":"Raw NUL replacement",
-            "doubleEscaped":true,
-            "initialStates":["RCDATA state", "RAWTEXT state", "PLAINTEXT state", "Script data state"],
-            "input":"\\u0000",
-            "output":[["Character", "\\uFFFD"]],
-            "errors":[
-                { "code": "unexpected-null-character", "line": 1, "col": 1 }
-            ]
-        },
-        {
-            "description":"NUL in CDATA section",
-            "doubleEscaped":true,
-            "initialStates":["CDATA section state"],
-            "input":"\\u0000]]>",
-            "output":[["Character", "\\u0000"]]
-        },
-        {
-           "description":"NUL in script HTML comment",
-           "doubleEscaped":true,
-           "initialStates":["Script data state"],
-           "input":"<!--test\\u0000--><!--test-\\u0000--><!--test--\\u0000-->",
-           "output":[["Character", "<!--test\\uFFFD--><!--test-\\uFFFD--><!--test--\\uFFFD-->"]],
-           "errors":[
-               { "code": "unexpected-null-character", "line": 1, "col": 9 },
-               { "code": "unexpected-null-character", "line": 1, "col": 22 },
-               { "code": "unexpected-null-character", "line": 1, "col": 36 }
-           ]
-        },
-        {
-           "description":"NUL in script HTML comment - double escaped",
-           "doubleEscaped":true,
-           "initialStates":["Script data state"],
-           "input":"<!--<script>\\u0000--><!--<script>-\\u0000--><!--<script>--\\u0000-->",
-           "output":[["Character", "<!--<script>\\uFFFD--><!--<script>-\\uFFFD--><!--<script>--\\uFFFD-->"]],
-           "errors":[
-                { "code": "unexpected-null-character", "line": 1, "col": 13 },
-                { "code": "unexpected-null-character", "line": 1, "col": 30 },
-                { "code": "unexpected-null-character", "line": 1, "col": 48 }
-           ]
-        },
-        {
-           "description":"EOF in script HTML comment",
-           "initialStates":["Script data state"],
-           "input":"<!--test",
-           "output":[["Character", "<!--test"]],
-           "errors":[
-               { "code": "eof-in-script-html-comment-like-text", "line": 1, "col": 9 }
-           ]
-        },
-        {
-           "description":"EOF in script HTML comment after dash",
-           "initialStates":["Script data state"],
-           "input":"<!--test-",
-           "output":[["Character", "<!--test-"]],
-           "errors":[
-               { "code": "eof-in-script-html-comment-like-text", "line": 1, "col": 10 }
-           ]
-        },
-        {
-           "description":"EOF in script HTML comment after dash dash",
-           "initialStates":["Script data state"],
-           "input":"<!--test--",
-           "output":[["Character", "<!--test--"]],
-           "errors":[
-               { "code": "eof-in-script-html-comment-like-text", "line": 1, "col": 11 }
-           ]
-        },
-        {
-           "description":"EOF in script HTML comment double escaped after dash",
-           "initialStates":["Script data state"],
-           "input":"<!--<script>-",
-           "output":[["Character", "<!--<script>-"]],
-           "errors":[
-               { "code": "eof-in-script-html-comment-like-text", "line": 1, "col": 14 }
-           ]
-        },
-        {
-           "description":"EOF in script HTML comment double escaped after dash dash",
-           "initialStates":["Script data state"],
-           "input":"<!--<script>--",
-           "output":[["Character", "<!--<script>--"]],
-           "errors":[
-               { "code": "eof-in-script-html-comment-like-text", "line": 1, "col": 15 }
-           ]
-        },
-        {
-           "description":"EOF in script HTML comment - double escaped",
-           "initialStates":["Script data state"],
-           "input":"<!--<script>",
-           "output":[["Character", "<!--<script>"]],
-           "errors":[
-               { "code": "eof-in-script-html-comment-like-text", "line": 1, "col": 13 }
-           ]
-        },
-        {
-            "description":"Dash in script HTML comment",
-            "initialStates":["Script data state"],
-            "input":"<!-- - -->",
-            "output":[["Character", "<!-- - -->"]]
-        },
-        {
-            "description":"Dash less-than in script HTML comment",
-            "initialStates":["Script data state"],
-            "input":"<!-- -< -->",
-            "output":[["Character", "<!-- -< -->"]]
-        },
-        {
-            "description":"Dash at end of script HTML comment",
-            "initialStates":["Script data state"],
-            "input":"<!--test--->",
-            "output":[["Character", "<!--test--->"]]
-        },
-        {
-            "description":"</script> in script HTML comment",
-            "initialStates":["Script data state"],
-            "lastStartTag":"script",
-            "input":"<!-- </script> --></script>",
-            "output":[["Character", "<!-- "], ["EndTag", "script"], ["Character", " -->"], ["EndTag", "script"]]
-        },
-        {
-            "description":"</script> in script HTML comment - double escaped",
-            "initialStates":["Script data state"],
-            "lastStartTag":"script",
-            "input":"<!-- <script></script> --></script>",
-            "output":[["Character", "<!-- <script></script> -->"], ["EndTag", "script"]]
-        },
-        {
-            "description":"</script> in script HTML comment - double escaped with nested <script>",
-            "initialStates":["Script data state"],
-            "lastStartTag":"script",
-            "input":"<!-- <script><script></script></script> --></script>",
-            "output":[["Character", "<!-- <script><script></script>"], ["EndTag", "script"], ["Character", " -->"], ["EndTag", "script"]]
-        },
-        {
-            "description":"</script> in script HTML comment - double escaped with abrupt end",
-            "initialStates":["Script data state"],
-            "lastStartTag":"script",
-            "input":"<!-- <script>--></script> --></script>",
-            "output":[["Character", "<!-- <script>-->"], ["EndTag", "script"], ["Character", " -->"], ["EndTag", "script"]]
-        },
-        {
-            "description":"Incomplete start tag in script HTML comment double escaped",
-            "initialStates":["Script data state"],
-            "lastStartTag":"script",
-            "input":"<!--<scrip></script>-->",
-            "output":[["Character", "<!--<scrip>"], ["EndTag", "script"], ["Character", "-->"]]
-        },
-        {
-            "description":"Unclosed start tag in script HTML comment double escaped",
-            "initialStates":["Script data state"],
-            "lastStartTag":"script",
-            "input":"<!--<script</script>-->",
-            "output":[["Character", "<!--<script"], ["EndTag", "script"], ["Character", "-->"]]
-        },
-        {
-            "description":"Incomplete end tag in script HTML comment double escaped",
-            "initialStates":["Script data state"],
-            "lastStartTag":"script",
-            "input":"<!--<script></scrip>-->",
-            "output":[["Character", "<!--<script></scrip>-->"]]
-        },
-        {
-            "description":"Unclosed end tag in script HTML comment double escaped",
-            "initialStates":["Script data state"],
-            "lastStartTag":"script",
-            "input":"<!--<script></script-->",
-            "output":[["Character", "<!--<script></script-->"]]
-        },
-        {
-            "description":"leading U+FEFF must pass through",
-            "initialStates":["Data state", "RCDATA state", "RAWTEXT state", "Script data state"],
-            "doubleEscaped":true,
-            "input":"\\uFEFFfoo\\uFEFFbar",
-            "output":[["Character", "\\uFEFFfoo\\uFEFFbar"]]
-        },
-        {
-            "description":"Non BMP-charref in RCDATA",
-            "initialStates":["RCDATA state"],
-            "input":"&NotEqualTilde;",
-            "output":[["Character", "\u2242\u0338"]]
-        },
-        {
-            "description":"Bad charref in RCDATA",
-            "initialStates":["RCDATA state"],
-            "input":"&NotEqualTild;",
-            "output":[["Character", "&NotEqualTild;"]],
-            "errors":[
-               { "code": "unknown-named-character-reference", "line": 1, "col": 14 }
-            ]
-        },
-        {
-            "description":"lowercase endtags",
-            "initialStates":["RCDATA state", "RAWTEXT state", "Script data state"],
-            "lastStartTag":"xmp",
-            "input":"</XMP>",
-            "output":[["EndTag","xmp"]]
-        },
-        {
-            "description":"bad endtag (space before name)",
-            "initialStates":["RCDATA state", "RAWTEXT state", "Script data state"],
-            "lastStartTag":"xmp",
-            "input":"</ XMP>",
-            "output":[["Character","</ XMP>"]]
-        },
-        {
-            "description":"bad endtag (not matching last start tag)",
-            "initialStates":["RCDATA state", "RAWTEXT state", "Script data state"],
-            "lastStartTag":"xmp",
-            "input":"</xm>",
-            "output":[["Character","</xm>"]]
-        },
-        {
-            "description":"bad endtag (without close bracket)",
-            "initialStates":["RCDATA state", "RAWTEXT state", "Script data state"],
-            "lastStartTag":"xmp",
-            "input":"</xm ",
-            "output":[["Character","</xm "]]
-        },
-        {
-            "description":"bad endtag (trailing solidus)",
-            "initialStates":["RCDATA state", "RAWTEXT state", "Script data state"],
-            "lastStartTag":"xmp",
-            "input":"</xm/",
-            "output":[["Character","</xm/"]]
-        },
-        {
-            "description":"Non BMP-charref in attribute",
-            "input":"<p id=\"&NotEqualTilde;\">",
-            "output":[["StartTag", "p", {"id":"\u2242\u0338"}]]
-        },
-        {
-            "description":"--!NUL in comment ",
-            "doubleEscaped":true,
-            "input":"<!----!\\u0000-->",
-            "output":[["Comment", "--!\\uFFFD"]],
-            "errors":[
-                { "code": "unexpected-null-character", "line": 1, "col": 8 }
-            ]
-        },
-        {
-            "description":"space EOF after doctype ",
-            "input":"<!DOCTYPE html ",
-            "output":[["DOCTYPE", "html", null, null , false]],
-            "errors":[
-                { "code": "eof-in-doctype", "line": 1, "col": 16 }
-            ]
-        },
-        {
-            "description":"CDATA in HTML content",
-            "input":"<![CDATA[foo]]>",
-            "output":[["Comment", "[CDATA[foo]]"]],
-            "errors":[
-                { "code": "cdata-in-html-content", "line": 1, "col": 9 }
-            ]
-        },
-        {
-            "description":"CDATA content",
-            "input":"foo&#32;]]>",
-            "initialStates":["CDATA section state"],
-            "output":[["Character", "foo&#32;"]]
-        },
-        {
-            "description":"CDATA followed by HTML content",
-            "input":"foo&#32;]]>&#32;",
-            "initialStates":["CDATA section state"],
-            "output":[["Character", "foo&#32; "]]
-        },
-        {
-            "description":"CDATA with extra bracket",
-            "input":"foo]]]>",
-            "initialStates":["CDATA section state"],
-            "output":[["Character", "foo]"]]
-        },
-        {
-            "description":"CDATA without end marker",
-            "input":"foo",
-            "initialStates":["CDATA section state"],
-            "output":[["Character", "foo"]],
-            "errors":[
-                { "code": "eof-in-cdata", "line": 1, "col": 4 }
-            ]
-        },
-        {
-            "description":"CDATA with single bracket ending",
-            "input":"foo]",
-            "initialStates":["CDATA section state"],
-            "output":[["Character", "foo]"]],
-            "errors":[
-                { "code": "eof-in-cdata", "line": 1, "col": 5 }
-            ]
-        },
-        {
-            "description":"CDATA with two brackets ending",
-            "input":"foo]]",
-            "initialStates":["CDATA section state"],
-            "output":[["Character", "foo]]"]],
-            "errors":[
-                { "code": "eof-in-cdata", "line": 1, "col": 6 }
-            ]
-        },
-        {
-            "description": "HTML tag in script data",
-            "input": "<b>hello world</b>",
-            "initialStates": ["Script data state"],
-            "output": [["Character", "<b>hello world</b>"]]
-        }
-    ]
-}