[commonmark] make html comments, html inlines, html blocks and links compliant #1135
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -20,16 +20,25 @@ var block = { | |
| nptable: noop, | ||
| blockquote: /^( {0,3}> ?(paragraph|[^\n]*)(?:\n|$))+/, | ||
| list: /^( *)(bull) [\s\S]+?(?:hr|def|\n{2,}(?! )(?!\1bull )\n*|\s*$)/, | ||
| html: '^ {0,3}(?:' // optional indentation | ||
| + '<(script|pre|style)[\\s>][\\s\\S]*?(?:</\\1>[^\\n]*\\n+|$)' // (1) | ||
| + '|comment[^\\n]*(\\n+|$)' // (2) | ||
| + '|<\\?[\\s\\S]*?\\?>\\n*' // (3) | ||
| + '|<![A-Z][\\s\\S]*?>\\n*' // (4) | ||
| + '|<!\\[CDATA\\[[\\s\\S]*?\\]\\]>\\n*' // (5) | ||
| + '|</?(tag)(?: +|\\n|/?>)[\\s\\S]*?(?:\\n{2,}|$)' // (6) | ||
| + '|<(?!script|pre|style)([a-z][\\w-]*)(?:attribute)*? */?>(?=\\h*\\n)[\\s\\S]*?(?:\\n{2,}|$)' // (7) open tag | ||
| + '|</(?!script|pre|style)[a-z][\\w-]*\\s*>(?=\\h*\\n)[\\s\\S]*?(?:\\n{2,}|$)' // (7) closing tag | ||
| + ')', | ||
| def: /^ {0,3}\[(label)\]: *\n? *<?([^\s>]+)>?(?:(?: +\n? *| *\n *)(title))? *(?:\n+|$)/, | ||
| table: noop, | ||
| lheading: /^([^\n]+)\n *(=|-){2,} *(?:\n+|$)/, | ||
| paragraph: /^([^\n]+(?:\n(?!hr|heading|lheading| {0,3}>|<\/?(?:tag)(?: +|\\n|\/?>)|<(?:script|pre|style|!--))[^\n]+)+)/, | ||
| text: /^[^\n]+/ | ||
| }; | ||
|
|
||
| block._label = /(?!\s*\])(?:\\[\[\]]|[^\[\]])+/; | ||
| block._title = /(?:"(?:\\"?|[^"\\])*"|'[^'\n]*(?:\n[^'\n]+)*\n?'|\([^()]*\))/; | ||
|
|
||
| block.def = edit(block.def) | ||
| .replace('label', block._label) | ||
| .replace('title', block._title) | ||
|
|
@@ -47,23 +56,24 @@ block.list = edit(block.list) | |
| .replace('def', '\\n+(?=' + block.def.source + ')') | ||
| .getRegex(); | ||
|
|
||
| block._tag = 'address|article|aside|base|basefont|blockquote|body|caption' | ||
| + '|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption' | ||
| + '|figure|footer|form|frame|frameset|h[1-6]|head|header|hr|html|iframe' | ||
| + '|legend|li|link|main|menu|menuitem|meta|nav|noframes|ol|optgroup|option' | ||
| + '|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr' | ||
| + '|track|ul'; | ||
| block._comment = /<!--(?!-?>)[\s\S]*?-->/; | ||
| block.html = edit(block.html, 'i') | ||
| .replace('comment', block._comment) | ||
| .replace('tag', block._tag) | ||
| .replace('attribute', / +[a-zA-Z:_][\w.:-]*(?: *= *"[^"\n]*"| *= *'[^'\n]*'| *= *[^\s"'=<>`]+)?/) | ||
| .getRegex(); | ||
|
|
||
| block.paragraph = edit(block.paragraph) | ||
| .replace('hr', block.hr) | ||
| .replace('heading', block.heading) | ||
| .replace('lheading', block.lheading) | ||
| .replace('tag', block._tag) // pars can be interrupted by type (6) html blocks | ||
| .getRegex(); | ||
|
|
||
| block.blockquote = edit(block.blockquote) | ||
|
|
@@ -101,6 +111,24 @@ block.tables = merge({}, block.gfm, { | |
| table: /^ *\|(.+)\n *\|( *[-:]+[-| :]*)\n((?: *\|.*(?:\n|$))*)\n*/ | ||
| }); | ||
|
|
||
| /** | ||
| * Pedantic grammar | ||
| */ | ||
|
|
||
| block.pedantic = merge({}, block.normal, { | ||
| html: edit( | ||
| '^ *(?:comment *(?:\\n|\\s*$)' | ||
| + '|<(tag)[\\s\\S]+?</\\1> *(?:\\n{2,}|\\s*$)' // closed tag | ||
| + '|<tag(?:"[^"]*"|\'[^\']*\'|\\s[^\'"/>\\s]*)*?/?> *(?:\\n{2,}|\\s*$))') | ||
|
|
||
| .replace('comment', block._comment) | ||
| .replace(/tag/g, '(?!(?:' | ||
| + 'a|em|strong|small|s|cite|q|dfn|abbr|data|time|code|var|samp|kbd|sub' | ||
| + '|sup|i|b|u|mark|ruby|rt|rp|bdi|bdo|span|br|wbr|ins|del|img)' | ||
| + '\\b)\\w+(?!:|[^\\w\\s@]*@)\\b') | ||
| .getRegex(), | ||
| def: /^ *\[([^\]]+)\]: *<?([^\s>]+)>?(?: +(["(][^\n]+[")]))? *(?:\n+|$)/ | ||
| }); | ||
|
|
||
| /** | ||
| * Block Lexer | ||
| */ | ||
|
|
@@ -111,7 +139,9 @@ function Lexer(options) { | |
| this.options = options || marked.defaults; | ||
| this.rules = block.normal; | ||
|
|
||
| if (this.options.pedantic) { | ||
| this.rules = block.pedantic; | ||
| } else if (this.options.gfm) { | ||
| if (this.options.tables) { | ||
| this.rules = block.tables; | ||
| } else { | ||
|
|
@@ -370,7 +400,7 @@ Lexer.prototype.token = function(src, top) { | |
| if (top && (cap = this.rules.def.exec(src))) { | ||
| src = src.substring(cap[0].length); | ||
| if (cap[3]) cap[3] = cap[3].substring(1, cap[3].length - 1); | ||
| tag = cap[1].toLowerCase().replace(/\s+/g, ' '); | ||
| if (!this.tokens.links[tag]) { | ||
| this.tokens.links[tag] = { | ||
| href: cap[2], | ||
|
|
@@ -461,13 +491,18 @@ Lexer.prototype.token = function(src, top) { | |
| */ | ||
|
|
||
| var inline = { | ||
| escape: /^\\([!"#$%&'()*+,\-./:;<=>?@\[\]\\^_`{|}~])/, | ||
| autolink: /^<(scheme:[^\s\x00-\x1f<>]*|email)>/, | ||
| url: noop, | ||
| tag: '^comment' | ||
| + '|^</[a-zA-Z][\\w:-]*\\s*>' // self-closing tag | ||
| + '|^<[a-zA-Z][\\w-]*(?:attribute)*?\\s*/?>' // open tag | ||
|
There was a problem hiding this comment. @davisjam same as above There was a problem hiding this comment. Could you print out There was a problem hiding this comment. Nevermind, I did it. This regex is safe. |
||
| + '|^<\\?[\\s\\S]*?\\?>' // processing instruction, e.g. <?php ?> | ||
| + '|^<![a-zA-Z]+\\s[\\s\\S]*?>' // declaration, e.g. <!DOCTYPE html> | ||
| + '|^<!\\[CDATA\\[[\\s\\S]*?\\]\\]>', // CDATA section | ||
| link: /^!?\[(label)\]\(href(?:\s+(title))?\s*\)/, | ||
|
There was a problem hiding this comment. @davisjam the commonmark spec is covered by this rule (and subrules at lines 530 and following). This is safe because the href part can't contain spaces, so the URI stops at the closing ) or at the first space. |
||
| reflink: /^!?\[(label)\]\[(?!\s*\])((?:\\[\[\]]?|[^\[\]\\])+)\]/, | ||
| nolink: /^!?\[(?!\s*\])((?:\[[^\[\]]*\]|\\[\[\]]|[^\[\]])*)\](?:\[\])?/, | ||
| strong: /^__([^\s][\s\S]*?[^\s])__(?!_)|^\*\*([^\s][\s\S]*?[^\s])\*\*(?!\*)|^__([^\s])__(?!_)|^\*\*([^\s])\*\*(?!\*)/, | ||
| em: /^_([^\s][\s\S]*?[^\s_])_(?!_)|^_([^\s_][\s\S]*?[^\s])_(?!_)|^\*([^\s][\s\S]*?[^\s*])\*(?!\*)|^\*([^\s*][\s\S]*?[^\s])\*(?!\*)|^_([^\s_])_(?!_)|^\*([^\s*])\*(?!\*)/, | ||
| code: /^(`+)\s*([\s\S]*?[^`]?)\s*\1(?!`)/, | ||
|
|
@@ -476,24 +511,34 @@ var inline = { | |
| text: /^[\s\S]+?(?=[\\<!\[`*]|\b_| {2,}\n|$)/ | ||
| }; | ||
|
|
||
| inline._escapes = /\\([!"#$%&'()*+,\-./:;<=>?@\[\]\\^_`{|}~])/g; | ||
|
|
||
| inline._scheme = /[a-zA-Z][a-zA-Z0-9+.-]{1,31}/; | ||
| inline._email = /[a-zA-Z0-9.!#$%&'*+/=?^_`{|}~-]+(@)[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)+(?![-_])/; | ||
| inline.autolink = edit(inline.autolink) | ||
| .replace('scheme', inline._scheme) | ||
| .replace('email', inline._email) | ||
| .getRegex(); | ||
|
|
||
| inline._attribute = /\s+[a-zA-Z:_][\w.:-]*(?:\s*=\s*"[^"]*"|\s*=\s*'[^']*'|\s*=\s*[^\s"'=<>`]+)?/; | ||
|
|
||
|
|
||
| inline.tag = edit(inline.tag) | ||
| .replace('comment', block._comment) | ||
| .replace('attribute', inline._attribute) | ||
| .getRegex(); | ||
|
|
||
| inline._label = /(?:\[[^\[\]]*\]|\\[\[\]]?|`[^`]*`|[^\[\]\\])*?/; | ||
| inline._href = /\s*(<(?:\\[<>]?|[^\s<>\\])*>|(?:\\[()]?|\([^\s\x00-\x1f()\\]*\)|[^\s\x00-\x1f()\\])*?)/; | ||
| inline._title = /"(?:\\"?|[^"\\])*"|'(?:\\'?|[^'\\])*'|\((?:\\\)?|[^)\\])*\)/; | ||
|
There was a problem hiding this comment. @davisjam check these 3 |
||
|
|
||
| inline.link = edit(inline.link) | ||
| .replace('label', inline._label) | ||
| .replace('href', inline._href) | ||
| .replace('title', inline._title) | ||
| .getRegex(); | ||
|
|
||
| inline.reflink = edit(inline.reflink) | ||
| .replace('label', inline._label) | ||
| .getRegex(); | ||
|
|
||
| /** | ||
|
|
@@ -508,7 +553,13 @@ inline.normal = merge({}, inline); | |
|
|
||
| inline.pedantic = merge({}, inline.normal, { | ||
| strong: /^__(?=\S)([\s\S]*?\S)__(?!_)|^\*\*(?=\S)([\s\S]*?\S)\*\*(?!\*)/, | ||
| em: /^_(?=\S)([\s\S]*?\S)_(?!_)|^\*(?=\S)([\s\S]*?\S)\*(?!\*)/, | ||
| link: edit(/^!?\[(label)\]\(\s*<?([\s\S]*?)>?(?:\s+(['"][\s\S]*?['"]))?\s*\)/) | ||
|
There was a problem hiding this comment. A static scan of the tree on @Feder1co5oave's PR says: (JSON-encoded). Checking the ones requested individually... There was a problem hiding this comment. I'm pretty sure this is the "old" link regex, I didn't change it. The double ?, maybe? I'm kinda lost. There was a problem hiding this comment. This is what The issue is the use of There was a problem hiding this comment. Ok I see where we're getting at... I'm not sure what that output means, can you translate that into some example input that triggers the quadratic behavior? There was a problem hiding this comment. wrapping the URI in angular parenthesis is optional. There was a problem hiding this comment. It doesn't sound like this can be done cleanly (and safely) in a single regex. Can you provide a link to the spec for this rule? There was a problem hiding this comment. This is the "legacy" link rule of marked, it's been like this for a long time. I didn't change it. It doesn't follow any clear spec, it just tries its best. We should come up with a different rule that doesn't break compatibility. There was a problem hiding this comment. OK. Since you didn't change it, it shouldn't prevent the PR from being merged. |
||
| .replace('label', inline._label) | ||
| .getRegex(), | ||
| reflink: edit(/^!?\[(label)\]\s*\[([^\]]*)\]/) | ||
| .replace('label', inline._label) | ||
| .getRegex() | ||
| }); | ||
|
|
||
| /** | ||
|
|
@@ -552,14 +603,14 @@ function InlineLexer(links, options) { | |
| throw new Error('Tokens array requires a `links` property.'); | ||
| } | ||
|
|
||
| if (this.options.pedantic) { | ||
| this.rules = inline.pedantic; | ||
| } else if (this.options.gfm) { | ||
| if (this.options.breaks) { | ||
| this.rules = inline.breaks; | ||
| } else { | ||
| this.rules = inline.gfm; | ||
| } | ||
| } | ||
| } | ||
|
|
||
|
|
@@ -587,6 +638,7 @@ InlineLexer.prototype.output = function(src) { | |
| link, | ||
| text, | ||
| href, | ||
| title, | ||
| cap; | ||
|
|
||
| while (src) { | ||
|
|
@@ -650,9 +702,12 @@ InlineLexer.prototype.output = function(src) { | |
| if (cap = this.rules.link.exec(src)) { | ||
| src = src.substring(cap[0].length); | ||
| this.inLink = true; | ||
| href = cap[2]; | ||
| href = href[0] === '<' ? href.substring(1, href.length - 1) : href; | ||
| title = cap[3] ? cap[3].substring(1, cap[3].length - 1) : cap[3]; | ||
| out += this.outputLink(cap, { | ||
| href: InlineLexer.escapes(href), | ||
| title: InlineLexer.escapes(title) | ||
| }); | ||
| this.inLink = false; | ||
| continue; | ||
|
|
@@ -725,12 +780,16 @@ InlineLexer.prototype.output = function(src) { | |
| return out; | ||
| }; | ||
|
|
||
| InlineLexer.escapes = function(text) { | ||
| return text ? text.replace(InlineLexer.rules._escapes, '$1') : text; | ||
| } | ||
|
|
||
| /** | ||
| * Compile Link | ||
| */ | ||
|
|
||
| InlineLexer.prototype.outputLink = function(cap, link) { | ||
| var href = link.href, | ||
| title = link.title ? escape(link.title) : null; | ||
|
|
||
| return cap[0].charAt(0) !== '!' | ||
|
|
@@ -917,7 +976,12 @@ Renderer.prototype.link = function(href, title, text) { | |
| if (this.options.baseUrl && !originIndependentUrl.test(href)) { | ||
| href = resolveUrl(this.options.baseUrl, href); | ||
| } | ||
| try { | ||
| href = encodeURI(href).replace(/%25/g, '%'); | ||
| } catch (e) { | ||
| return text; | ||
| } | ||
| var out = '<a href="' + escape(href) + '"'; | ||
| if (title) { | ||
| out += ' title="' + title + '"'; | ||
| } | ||
|
|
@@ -1137,10 +1201,8 @@ Parser.prototype.tok = function() { | |
| return this.renderer.listitem(body); | ||
| } | ||
| case 'html': { | ||
| // TODO parse inline content if parameter markdown=1 | ||
| return this.renderer.html(this.token.text); | ||
| } | ||
| case 'paragraph': { | ||
| return this.renderer.paragraph(this.inline.output(this.token.text)); | ||
|
|
@@ -1179,7 +1241,7 @@ function unescape(html) { | |
| } | ||
|
|
||
| function edit(regex, opt) { | ||
| regex = regex.source || regex; | ||
| opt = opt || ''; | ||
| return { | ||
| replace: function(name, val) { | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
File renamed without changes.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@davisjam it this safe?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Could you print out
html.source?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nevermind, I did it. Safe.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@Feder1co5oave what is the
\\h*for in(?=\\h*\\n)?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
it that supposed to be
\\n*?