html-to-markdown 2.24.6 → 2.25.0

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

@@ -1,41 +0,0 @@
-{"tests" : [
-{"description": "Invalid Unicode character U+DFFF",
-"doubleEscaped":true,
-"input": "\\uDFFF",
-"output":[["Character", "\\uDFFF"]],
-"errors":[
-    { "code": "surrogate-in-input-stream", "line": 1, "col": 1 }
-]},
-
-{"description": "Invalid Unicode character U+D800",
-"doubleEscaped":true,
-"input": "\\uD800",
-"output":[["Character", "\\uD800"]],
-"errors":[
-    { "code": "surrogate-in-input-stream", "line": 1, "col": 1 }
-]},
-
-{"description": "Invalid Unicode character U+DFFF with valid preceding character",
-"doubleEscaped":true,
-"input": "a\\uDFFF",
-"output":[["Character", "a\\uDFFF"]],
-"errors":[
-    { "code": "surrogate-in-input-stream", "line": 1, "col": 2 }
-]},
-
-{"description": "Invalid Unicode character U+D800 with valid following character",
-"doubleEscaped":true,
-"input": "\\uD800a",
-"output":[["Character", "\\uD800a"]],
-"errors":[
-    { "code": "surrogate-in-input-stream", "line": 1, "col": 1 }
-]},
-
-{"description":"CR followed by U+0000",
-"input":"\r\u0000",
-"output":[["Character", "\n\u0000"]],
-"errors":[
-    { "code": "unexpected-null-character", "line": 2, "col": 1 }
-]}
-]
-}

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

@@ -1,20 +0,0 @@
-{"xmlViolationTests": [
-
-{"description":"Non-XML character",
-"input":"a\uFFFFb",
-"output":[["Character","a\uFFFDb"]]},
-
-{"description":"Non-XML space",
-"input":"a\u000Cb",
-"output":[["Character","a b"]]},
-
-{"description":"Double hyphen in comment",
-"input":"<!-- foo -- bar -->",
-"output":[["Comment"," foo - - bar "]]},
-
-{"description":"FF between attributes",
-"input":"<a b=''\u000Cc=''>",
-"output":[["StartTag","a",{"b":"","c":""}]]}
-]}
-
-

data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/README.md

@@ -1,108 +0,0 @@
-Tree Construction Tests
-=======================
-
-Each file containing tree construction tests consists of any number of
-tests separated by two newlines (LF) and a single newline before the end
-of the file. For instance:
-
-    [TEST]LF
-    LF
-    [TEST]LF
-    LF
-    [TEST]LF
-
-Where [TEST] is the following format:
-
-Each test must begin with a string "\#data" followed by a newline (LF).
-All subsequent lines until a line that says "\#errors" are the test data
-and must be passed to the system being tested unchanged, except with the
-final newline (on the last line) removed.
-
-Then there must be a line that says "\#errors". It must be followed by
-one line per parse error that a conformant checker would return. It
-doesn't matter what those lines are, although they can't be
-"\#new-errors", "\#document-fragment", "\#document", "\#script-off",
-"\#script-on", or empty, the only thing that matters is that there be
-the right number of parse errors.
-
-Then there \*may\* be a line that says "\#new-errors", which works like
-the "\#errors" section adding more errors to the expected number of
-errors.
-
-Then there \*may\* be a line that says "\#document-fragment", which must
-be followed by a newline (LF), followed by a string of characters that
-indicates the context element, followed by a newline (LF). If the string 
-of characters starts with "svg ", the context element is in the SVG
-namespace and the substring after "svg " is the local name. If the
-string of characters starts with "math ", the context element is in the
-MathML namespace and the substring after "math " is the local name.
-Otherwise, the context element is in the HTML namespace and the string
-is the local name. If this line is present the "\#data" must be parsed
-using the HTML fragment parsing algorithm with the context element as
-context.
-
-Then there \*may\* be a line that says "\#script-off" or
-"\#script-on". If a line that says "\#script-off" is present, the
-parser must set the scripting flag to disabled. If a line that says
-"\#script-on" is present, it must set it to enabled. Otherwise, the
-test should be run in both modes.
-
-Then there must be a line that says "\#document", which must be followed
-by a dump of the tree of the parsed DOM. Each node must be represented
-by a single line. Each line must start with "| ", followed by two spaces
-per parent node that the node has before the root document node.
-
--   Element nodes must be represented by a "`<`" then the *tag name
-    string* "`>`", and all the attributes must be given, sorted
-    lexicographically by UTF-16 code unit according to their *attribute
-    name string*, on subsequent lines, as if they were children of the
-    element node.
--   Attribute nodes must have the *attribute name string*, then an "="
-    sign, then the attribute value in double quotes (").
--   Text nodes must be the string, in double quotes. Newlines aren't
-    escaped.
--   Comments must be "`<`" then "`!-- `" then the data then "` -->`".
--   DOCTYPEs must be "`<!DOCTYPE `" then the name then if either of the
-    system id or public id is non-empty a space, public id in
-    double-quotes, another space an the system id in double-quotes, and
-    then in any case "`>`".
--   Processing instructions must be "`<?`", then the target, then a
-    space, then the data and then "`>`". (The HTML parser cannot emit
-    processing instructions, but scripts can, and the WebVTT to DOM
-    rules can emit them.)
--   Template contents are represented by the string "content" with the
-    children below it.
-
-The *tag name string* is the local name prefixed by a namespace
-designator. For the HTML namespace, the namespace designator is the
-empty string, i.e. there's no prefix. For the SVG namespace, the
-namespace designator is "svg ". For the MathML namespace, the namespace
-designator is "math ".
-
-The *attribute name string* is the local name prefixed by a namespace
-designator. For no namespace, the namespace designator is the empty
-string, i.e. there's no prefix. For the XLink namespace, the namespace
-designator is "xlink ". For the XML namespace, the namespace designator
-is "xml ". For the XMLNS namespace, the namespace designator is "xmlns
-". Note the difference between "xlink:href" which is an attribute in no
-namespace with the local name "xlink:href" and "xlink href" which is an
-attribute in the xlink namespace with the local name "href".
-
-If there is also a "\#document-fragment" the bit following "\#document"
-must be a representation of the HTML fragment serialization for the
-context element given by "\#document-fragment".
-
-For example:
-
-    #data
-    <p>One<p>Two
-    #errors
-    3: Missing document type declaration
-    #document
-    | <html>
-    |   <head>
-    |   <body>
-    |     <p>
-    |       "One"
-    |     <p>
-    |       "Two"

data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/adoption01.dat

@@ -1,354 +0,0 @@
-#data
-<a><p></a></p>
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,10): adoption-agency-1.3
-#document
-| <html>
-|   <head>
-|   <body>
-|     <a>
-|     <p>
-|       <a>
-
-#data
-<a>1<p>2</a>3</p>
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,12): adoption-agency-1.3
-#document
-| <html>
-|   <head>
-|   <body>
-|     <a>
-|       "1"
-|     <p>
-|       <a>
-|         "2"
-|       "3"
-
-#data
-<a>1<button>2</a>3</button>
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,17): adoption-agency-1.3
-#document
-| <html>
-|   <head>
-|   <body>
-|     <a>
-|       "1"
-|     <button>
-|       <a>
-|         "2"
-|       "3"
-
-#data
-<a>1<b>2</a>3</b>
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,12): adoption-agency-1.3
-#document
-| <html>
-|   <head>
-|   <body>
-|     <a>
-|       "1"
-|       <b>
-|         "2"
-|     <b>
-|       "3"
-
-#data
-<a>1<div>2<div>3</a>4</div>5</div>
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,20): adoption-agency-1.3
-(1,20): adoption-agency-1.3
-#document
-| <html>
-|   <head>
-|   <body>
-|     <a>
-|       "1"
-|     <div>
-|       <a>
-|         "2"
-|       <div>
-|         <a>
-|           "3"
-|         "4"
-|       "5"
-
-#data
-<table><a>1<p>2</a>3</p>
-#errors
-(1,7): expected-doctype-but-got-start-tag
-(1,10): unexpected-start-tag-implies-table-voodoo
-(1,11): unexpected-character-implies-table-voodoo
-(1,14): unexpected-start-tag-implies-table-voodoo
-(1,15): unexpected-character-implies-table-voodoo
-(1,19): unexpected-end-tag-implies-table-voodoo
-(1,19): adoption-agency-1.3
-(1,20): unexpected-character-implies-table-voodoo
-(1,24): unexpected-end-tag-implies-table-voodoo
-(1,24): eof-in-table
-#document
-| <html>
-|   <head>
-|   <body>
-|     <a>
-|       "1"
-|     <p>
-|       <a>
-|         "2"
-|       "3"
-|     <table>
-
-#data
-<b><b><a><p></a>
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,16): adoption-agency-1.3
-(1,16): expected-closing-tag-but-got-eof
-#document
-| <html>
-|   <head>
-|   <body>
-|     <b>
-|       <b>
-|         <a>
-|         <p>
-|           <a>
-
-#data
-<b><a><b><p></a>
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,16): adoption-agency-1.3
-(1,16): expected-closing-tag-but-got-eof
-#document
-| <html>
-|   <head>
-|   <body>
-|     <b>
-|       <a>
-|         <b>
-|       <b>
-|         <p>
-|           <a>
-
-#data
-<a><b><b><p></a>
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,16): adoption-agency-1.3
-(1,16): expected-closing-tag-but-got-eof
-#document
-| <html>
-|   <head>
-|   <body>
-|     <a>
-|       <b>
-|         <b>
-|     <b>
-|       <b>
-|         <p>
-|           <a>
-
-#data
-<p>1<s id="A">2<b id="B">3</p>4</s>5</b>
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,30): unexpected-end-tag
-(1,35): adoption-agency-1.3
-#document
-| <html>
-|   <head>
-|   <body>
-|     <p>
-|       "1"
-|       <s>
-|         id="A"
-|         "2"
-|         <b>
-|           id="B"
-|           "3"
-|     <s>
-|       id="A"
-|       <b>
-|         id="B"
-|         "4"
-|     <b>
-|       id="B"
-|       "5"
-
-#data
-<table><a>1<td>2</td>3</table>
-#errors
-(1,7): expected-doctype-but-got-start-tag
-(1,10): unexpected-start-tag-implies-table-voodoo
-(1,11): unexpected-character-implies-table-voodoo
-(1,15): unexpected-cell-in-table-body
-(1,30): unexpected-implied-end-tag-in-table-view
-#document
-| <html>
-|   <head>
-|   <body>
-|     <a>
-|       "1"
-|     <a>
-|       "3"
-|     <table>
-|       <tbody>
-|         <tr>
-|           <td>
-|             "2"
-
-#data
-<table>A<td>B</td>C</table>
-#errors
-(1,7): expected-doctype-but-got-start-tag
-(1,8): unexpected-character-implies-table-voodoo
-(1,12): unexpected-cell-in-table-body
-(1,22): unexpected-character-implies-table-voodoo
-#document
-| <html>
-|   <head>
-|   <body>
-|     "AC"
-|     <table>
-|       <tbody>
-|         <tr>
-|           <td>
-|             "B"
-
-#data
-<a><svg><tr><input></a>
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,23): unexpected-end-tag
-(1,23): adoption-agency-1.3
-#document
-| <html>
-|   <head>
-|   <body>
-|     <a>
-|       <svg svg>
-|         <svg tr>
-|           <svg input>
-
-#data
-<div><a><b><div><div><div><div><div><div><div><div><div><div></a>
-#errors
-(1,5): expected-doctype-but-got-start-tag
-(1,65): adoption-agency-1.3
-(1,65): adoption-agency-1.3
-(1,65): adoption-agency-1.3
-(1,65): adoption-agency-1.3
-(1,65): adoption-agency-1.3
-(1,65): adoption-agency-1.3
-(1,65): adoption-agency-1.3
-(1,65): adoption-agency-1.3
-(1,65): expected-closing-tag-but-got-eof
-#document
-| <html>
-|   <head>
-|   <body>
-|     <div>
-|       <a>
-|         <b>
-|       <b>
-|         <div>
-|           <a>
-|           <div>
-|             <a>
-|             <div>
-|               <a>
-|               <div>
-|                 <a>
-|                 <div>
-|                   <a>
-|                   <div>
-|                     <a>
-|                     <div>
-|                       <a>
-|                       <div>
-|                         <a>
-|                           <div>
-|                             <div>
-
-#data
-<div><a><b><u><i><code><div></a>
-#errors
-(1,5): expected-doctype-but-got-start-tag
-(1,32): adoption-agency-1.3
-(1,32): expected-closing-tag-but-got-eof
-#document
-| <html>
-|   <head>
-|   <body>
-|     <div>
-|       <a>
-|         <b>
-|           <u>
-|             <i>
-|               <code>
-|       <u>
-|         <i>
-|           <code>
-|             <div>
-|               <a>
-
-#data
-<b><b><b><b>x</b></b></b></b>y
-#errors
-(1,3): expected-doctype-but-got-start-tag
-#document
-| <html>
-|   <head>
-|   <body>
-|     <b>
-|       <b>
-|         <b>
-|           <b>
-|             "x"
-|     "y"
-
-#data
-<p><b><b><b><b><p>x
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,18): unexpected-end-tag
-(1,19): expected-closing-tag-but-got-eof
-#document
-| <html>
-|   <head>
-|   <body>
-|     <p>
-|       <b>
-|         <b>
-|           <b>
-|             <b>
-|     <p>
-|       <b>
-|         <b>
-|           <b>
-|             "x"
-
-#data
-<b><em><foo><foob><fooc><aside></b></em>
-#errors
-(1,35): adoption-agency-1.3
-(1,40): adoption-agency-1.3
-(1,40): expected-closing-tag-but-got-eof
-#document-fragment
-div
-#document
-| <b>
-|   <em>
-|     <foo>
-|       <foob>
-|         <fooc>
-| <aside>
-|   <b>

data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/adoption02.dat

@@ -1,39 +0,0 @@
-#data
-<b>1<i>2<p>3</b>4
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,16): adoption-agency-1.3
-(1,17): expected-closing-tag-but-got-eof
-#document
-| <html>
-|   <head>
-|   <body>
-|     <b>
-|       "1"
-|       <i>
-|         "2"
-|     <i>
-|       <p>
-|         <b>
-|           "3"
-|         "4"
-
-#data
-<a><div><style></style><address><a>
-#errors
-(1,3): expected-doctype-but-got-start-tag
-(1,35): unexpected-start-tag-implies-end-tag
-(1,35): adoption-agency-1.3
-(1,35): adoption-agency-1.3
-(1,35): expected-closing-tag-but-got-eof
-#document
-| <html>
-|   <head>
-|   <body>
-|     <a>
-|     <div>
-|       <a>
-|         <style>
-|       <address>
-|         <a>
-|         <a>