RubyGems - html-to-markdown - Versions diffs - 2.24.6 → 2.25.0 - Mend

html-to-markdown 2.24.6 → 2.25.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (203) hide show

data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/pendingSpecChanges.test DELETED Viewed

@@ -1,9 +0,0 @@
-{"tests": [
-{"description":"<!---- >",
-"input":"<!---- >",
-"output":[["Comment","-- >"]],
-"errors":[
-    { "code": "eof-in-comment", "line": 1, "col": 9 }
-]}
-]}

data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/test1.test DELETED Viewed

@@ -1,353 +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":[["DOCTYPE", "html", null, null, false]],
-"errors":[
-    { "code": "eof-in-doctype", "line": 1, "col": 15 }
-]},
-{"description":"Truncated doctype start",
-"input":"<!DOC>",
-"output":[["Comment", "DOC"]],
-"errors":[
-    { "code": "incorrectly-opened-comment", "line": 1, "col": 3 }
-]},
-{"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":[],
-"errors":[
-    { "code": "missing-end-tag-name", "line": 1, "col": 3 }
-]},
-{"description":"Empty start tag",
-"input":"<>",
-"output":[["Character", "<>"]],
-"errors":[
-    { "code": "invalid-first-character-of-tag-name", "line": 1, "col": 2 }
-]},
-{"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", {}], ["EndTag", "h"]],
-"errors":[
-    { "code": "end-tag-with-attributes", "line": 1, "col": 13 }
-]},
-{"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":[["StartTag", "h", {"a":"b", "c":"d"}]],
-"errors":[
-    { "code": "missing-whitespace-between-attributes", "line": 1, "col": 9 }
-]},
-{"description":"Repeated attr",
- "input":"<h a='b' a='d'>",
- "output":[["StartTag", "h", {"a":"b"}]],
- "errors":[
-    { "code": "duplicate-attribute", "line": 1, "col": 11 }
-]},
-{"description":"Simple comment",
- "input":"<!--comment-->",
- "output":[["Comment", "comment"]]},
-{"description":"Comment, Central dash no space",
- "input":"<!----->",
- "output":[["Comment", "-"]]},
-{"description":"Comment, two central dashes",
-"input":"<!-- --comment -->",
-"output":[["Comment", " --comment "]]},
-{"description":"Comment, central less-than bang",
-"input":"<!--<!-->",
-"output":[["Comment", "<!"]]},
-{"description":"Unfinished comment",
-"input":"<!--comment",
-"output":[["Comment", "comment"]],
-"errors":[
-    { "code": "eof-in-comment", "line": 1, "col": 12 }
-]},
-{"description":"Unfinished comment after start of nested comment",
-"input":"<!-- <!--",
-"output":[["Comment", " <!"]],
-"errors":[
-    { "code": "eof-in-comment", "line": 1, "col": 10 }
-]},
-{"description":"Start of a comment",
-"input":"<!-",
-"output":[["Comment", "-"]],
-"errors":[
-    { "code": "incorrectly-opened-comment", "line": 1, "col": 3 }
-]},
-{"description":"Short comment",
-"input":"<!-->",
-"output":[["Comment", ""]],
-"errors":[
-    { "code": "abrupt-closing-of-empty-comment", "line": 1, "col": 5 }
-]},
-{"description":"Short comment two",
-"input":"<!--->",
-"output":[["Comment", ""]],
-"errors":[
-    { "code": "abrupt-closing-of-empty-comment", "line": 1, "col": 6 }
-]},
-{"description":"Short comment three",
- "input":"<!---->",
- "output":[["Comment", ""]]},
-{"description":"< in comment",
-"input":"<!-- <test-->",
-"output":[["Comment", " <test"]]},
-{"description":"<< in comment",
-"input":"<!--<<-->",
-"output":[["Comment", "<<"]]},
-{"description":"<! in comment",
-"input":"<!-- <!test-->",
-"output":[["Comment", " <!test"]]},
-{"description":"<!- in comment",
-"input":"<!-- <!-test-->",
-"output":[["Comment", " <!-test"]]},
-{"description":"Nested comment",
-"input":"<!-- <!--test-->",
-"output":[["Comment", " <!--test"]],
-"errors":[
-    { "code": "nested-comment", "line": 1, "col": 10 }
-]},
-{"description":"Nested comment with extra <",
-"input":"<!-- <<!--test-->",
-"output":[["Comment", " <<!--test"]],
-"errors":[
-    { "code": "nested-comment", "line": 1, "col": 11 }
-]},
-{"description":"< in script data",
-"initialStates":["Script data state"],
-"input":"<test-->",
-"output":[["Character", "<test-->"]]},
-{"description":"<! in script data",
-"initialStates":["Script data state"],
-"input":"<!test-->",
-"output":[["Character", "<!test-->"]]},
-{"description":"<!- in script data",
-"initialStates":["Script data state"],
-"input":"<!-test-->",
-"output":[["Character", "<!-test-->"]]},
-{"description":"Escaped script data",
-"initialStates":["Script data state"],
-"input":"<!--test-->",
-"output":[["Character", "<!--test-->"]]},
-{"description":"< in script HTML comment",
-"initialStates":["Script data state"],
-"input":"<!-- < test -->",
-"output":[["Character", "<!-- < test -->"]]},
-{"description":"</ in script HTML comment",
-"initialStates":["Script data state"],
-"input":"<!-- </ test -->",
-"output":[["Character", "<!-- </ test -->"]]},
-{"description":"Start tag in script HTML comment",
-"initialStates":["Script data state"],
-"input":"<!-- <test> -->",
-"output":[["Character", "<!-- <test> -->"]]},
-{"description":"End tag in script HTML comment",
-"initialStates":["Script data state"],
-"input":"<!-- </test> -->",
-"output":[["Character", "<!-- </test> -->"]]},
-{"description":"- in script HTML comment double escaped",
-"initialStates":["Script data state"],
-"input":"<!--<script>-</script>-->",
-"output":[["Character", "<!--<script>-</script>-->"]]},
-{"description":"-- in script HTML comment double escaped",
-"initialStates":["Script data state"],
-"input":"<!--<script>--</script>-->",
-"output":[["Character", "<!--<script>--</script>-->"]]},
-{"description":"--- in script HTML comment double escaped",
-"initialStates":["Script data state"],
-"input":"<!--<script>---</script>-->",
-"output":[["Character", "<!--<script>---</script>-->"]]},
-{"description":"- spaced in script HTML comment double escaped",
-"initialStates":["Script data state"],
-"input":"<!--<script> - </script>-->",
-"output":[["Character", "<!--<script> - </script>-->"]]},
-{"description":"-- spaced in script HTML comment double escaped",
-"initialStates":["Script data state"],
-"input":"<!--<script> -- </script>-->",
-"output":[["Character", "<!--<script> -- </script>-->"]]},
-{"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":[["Character", "&#"]],
-"errors":[
-    { "code": "absence-of-digits-in-numeric-character-reference", "line": 1, "col": 3 }
-]},
-{"description":"Unfinished numeric entity",
-"input":"&#x",
-"output":[["Character", "&#x"]],
-"errors":[
-    { "code": "absence-of-digits-in-numeric-character-reference", "line": 1, "col": 4 }
-]},
-{"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 \u00ACit"]],
-"errors": [
-    {"code" : "missing-semicolon-after-character-reference", "line": 1, "col": 9 }
-]},
-{"description":"Entity without trailing semicolon (2)",
-"input":"I'm &notin",
-"output":[["Character","I'm \u00ACin"]],
-"errors": [
-    {"code" : "missing-semicolon-after-character-reference", "line": 1, "col": 9 }
-]},
-{"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":[["StartTag", "h", {"a":"\u00A9"}]],
-"errors": [
-    {"code" : "missing-semicolon-after-character-reference", "line": 1, "col": 12 }
-]},
-{"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":[["StartTag", "a", {"a":"f<"}]],
- "errors":[
-    { "code": "unexpected-character-in-unquoted-attribute-value", "line": 1, "col": 7 }
-]}
-]}

data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/test2.test DELETED Viewed

@@ -1,275 +0,0 @@
-{"tests": [
-{"description":"DOCTYPE without name",
-"input":"<!DOCTYPE>",
-"output":[["DOCTYPE", null, null, null, false]],
-"errors":[
-    { "code": "missing-doctype-name", "line": 1, "col": 10 }
-]},
-{"description":"DOCTYPE without space before name",
-"input":"<!DOCTYPEhtml>",
-"output":[["DOCTYPE", "html", null, null, true]],
-"errors":[
-    { "code": "missing-whitespace-before-doctype-name", "line": 1, "col": 10 }
-]},
-{"description":"Incorrect DOCTYPE without a space before name",
-"input":"<!DOCTYPEfoo>",
-"output":[["DOCTYPE", "foo", null, null, true]],
-"errors":[
-    { "code": "missing-whitespace-before-doctype-name", "line": 1, "col": 10 }
-]},
-{"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":[["DOCTYPE", "html", null, null, false]],
-"errors": [
-    { "code": "eof-in-doctype", "col": 22, "line": 1 }
-]},
-{"description":"DOCTYPE with EOF after PUBLIC '",
-"input":"<!DOCTYPE html PUBLIC '",
-"output":[["DOCTYPE", "html", "", null, false]],
-"errors": [
-    { "code": "eof-in-doctype", "col": 24, "line": 1 }
-]},
-{"description":"DOCTYPE with EOF after PUBLIC 'x",
-"input":"<!DOCTYPE html PUBLIC 'x",
-"output":[["DOCTYPE", "html", "x", null, false]],
-"errors": [
-    { "code": "eof-in-doctype", "col": 25, "line": 1 }
-]},
-{"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 single-quoted 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":[["DOCTYPE", "html", "", null, false], ["Character", "x"]],
-"errors": [
-    { "code": "abrupt-doctype-public-identifier", "col": 24, "line": 1 }
-]},
-{"description":"DOCTYPE with > in single-quoted publicId",
-"input":"<!DOCTYPE html PUBLIC '>x",
-"output":[["DOCTYPE", "html", "", null, false], ["Character", "x"]],
-"errors": [
-    { "code": "abrupt-doctype-public-identifier", "col": 24, "line": 1 }
-]},
-{"description":"DOCTYPE with > in double-quoted systemId",
-"input":"<!DOCTYPE html PUBLIC \"foo\" \">x",
-"output":[["DOCTYPE", "html", "foo", "", false], ["Character", "x"]],
-"errors": [
-    { "code": "abrupt-doctype-system-identifier", "col": 30, "line": 1 }
-]},
-{"description":"DOCTYPE with > in single-quoted systemId",
-"input":"<!DOCTYPE html PUBLIC 'foo' '>x",
-"output":[["DOCTYPE", "html", "foo", "", false], ["Character", "x"]],
-"errors": [
-    { "code": "abrupt-doctype-system-identifier", "col": 30, "line": 1 }
-]},
-{"description":"Incomplete doctype",
-"input":"<!DOCTYPE html ",
-"output":[["DOCTYPE", "html", null, null, false]],
-"errors":[
-    { "code": "eof-in-doctype", "line": 1, "col": 16 }
-]},
-{"description":"Numeric entity representing the NUL character",
-"input":"&#0000;",
-"output":[["Character", "\uFFFD"]],
-"errors":[
-    { "code": "null-character-reference", "line": 1, "col": 8 }
-]},
-{"description":"Hexadecimal entity representing the NUL character",
-"input":"&#x0000;",
-"output":[["Character", "\uFFFD"]],
-"errors":[
-    { "code": "null-character-reference", "line": 1, "col": 9 }
-]},
-{"description":"Numeric entity representing a codepoint after 1114111 (U+10FFFF)",
-"input":"&#2225222;",
-"output":[["Character", "\uFFFD"]],
-"errors":[
-    { "code": "character-reference-outside-unicode-range", "line": 1, "col": 11 }
-]},
-{"description":"Hexadecimal entity representing a codepoint after 1114111 (U+10FFFF)",
-"input":"&#x1010FFFF;",
-"output":[["Character", "\uFFFD"]],
-"errors":[
-    { "code": "character-reference-outside-unicode-range", "line": 1, "col": 13 }
-]},
-{"description":"Hexadecimal entity pair representing a surrogate pair",
-"input":"&#xD869;&#xDED6;",
-"output":[["Character", "\uFFFD\uFFFD"]],
-"errors":[
-    { "code": "surrogate-character-reference", "line": 1, "col": 9 },
-    { "code": "surrogate-character-reference", "line": 1, "col": 17 }
-]},
-{"description":"Hexadecimal entity with mixed uppercase and lowercase",
-"input":"&#xaBcD;",
-"output":[["Character", "\uABCD"]]},
-{"description":"Entity without a name",
-"input":"&;",
-"output":[["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":[["StartTag", "h", { "a":"b" }]],
-"errors":[
-    { "code": "unexpected-solidus-in-tag", "line": 1, "col": 4 }
-]},
-{"description":"Double-quoted attribute value",
-"input":"<h a=\"b\">",
-"output":[["StartTag", "h", { "a":"b" }]]},
-{"description":"Unescaped </",
-"input":"</",
-"output":[["Character", "</"]],
-"errors":[
-    { "code": "eof-before-tag-name", "line": 1, "col": 3 }
-]},
-{"description":"Illegal end tag name",
-"input":"</1>",
-"output":[["Comment", "1"]],
-"errors":[
-    { "code": "invalid-first-character-of-tag-name", "line": 1, "col": 3 }
-]},
-{"description":"Simili processing instruction",
-"input":"<?namespace>",
-"output":[["Comment", "?namespace"]],
-"errors":[
-    { "code": "unexpected-question-mark-instead-of-tag-name", "line": 1, "col": 2 }
-]},
-{"description":"A bogus comment stops at >, even if preceded by two dashes",
-"input":"<?foo-->",
-"output":[["Comment", "?foo--"]],
-"errors":[
-    { "code": "unexpected-question-mark-instead-of-tag-name", "line": 1, "col": 2 }
-]},
-{"description":"Unescaped <",
-"input":"foo < bar",
-"output":[["Character", "foo < bar"]],
-"errors":[
-    { "code": "invalid-first-character-of-tag-name", "line": 1, "col": 6 }
-]},
-{"description":"Null Byte Replacement",
-"input":"\u0000",
-"output":[["Character", "\u0000"]],
-"errors":[
-    { "code": "unexpected-null-character", "line": 1, "col": 1 }
-]},
-{"description":"Comment with dash",
-"input":"<!---x",
-"output":[["Comment", "-x"]],
-"errors":[
-    { "code": "eof-in-comment", "line": 1, "col": 7 }
-]},
-{"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":[["StartTag", "h", {"a":"", "\"":""}]],
-"errors":[
-    { "code": "unexpected-character-in-attribute-name", "line": 1, "col": 6 }
-]},
-{"description":"Single-quote after attribute name",
-"input":"<h a '>",
-"output":[["StartTag", "h", {"a":"", "'":""}]],
-"errors":[
-    { "code": "unexpected-character-in-attribute-name", "line": 1, "col": 6 }
-]},
-{"description":"Empty end tag with following characters",
-"input":"a</>bc",
-"output":[["Character", "abc"]],
-"errors":[
-    { "code": "missing-end-tag-name", "line": 1, "col": 4 }
-]},
-{"description":"Empty end tag with following tag",
-"input":"a</><b>c",
-"output":[["Character", "a"], ["StartTag", "b", {}], ["Character", "c"]],
-"errors":[
-    { "code": "missing-end-tag-name", "line": 1, "col": 4 }
-]},
-{"description":"Empty end tag with following comment",
-"input":"a</><!--b-->c",
-"output":[["Character", "a"], ["Comment", "b"], ["Character", "c"]],
-"errors":[
-    { "code": "missing-end-tag-name", "line": 1, "col": 4 }
-]},
-{"description":"Empty end tag with following end tag",
-"input":"a</></b>c",
-"output":[["Character", "a"], ["EndTag", "b"], ["Character", "c"]],
-"errors":[
-    { "code": "missing-end-tag-name", "line": 1, "col": 4 }
-]}
-]}