From b51fb4d3fbc38b61cfc7e6dd833973afbf8cd2bd Mon Sep 17 00:00:00 2001 From: Robin Ward Date: Mon, 21 Oct 2013 15:05:52 -0400 Subject: [PATCH] Sync up with markdown-js + our changes --- .../javascripts/discourse/dialects/dialect.js | 3 +- vendor/assets/javascripts/better_markdown.js | 2499 ++++++++--------- 2 files changed, 1249 insertions(+), 1253 deletions(-) diff --git a/app/assets/javascripts/discourse/dialects/dialect.js b/app/assets/javascripts/discourse/dialects/dialect.js index 2de07a741a4..71ab8a27dff 100644 --- a/app/assets/javascripts/discourse/dialects/dialect.js +++ b/app/assets/javascripts/discourse/dialects/dialect.js @@ -6,7 +6,8 @@ **/ var parser = window.BetterMarkdown, MD = parser.Markdown, - dialect = MD.dialects.Discourse = MD.subclassDialect( MD.dialects.Gruber ), + DialectHelpers = parser.DialectHelpers, + dialect = MD.dialects.Discourse = DialectHelpers.subclassDialect( MD.dialects.Gruber ), initialized = false, emitters = []; diff --git a/vendor/assets/javascripts/better_markdown.js b/vendor/assets/javascripts/better_markdown.js index 13513ac8afd..01f3d6c99ad 100644 --- a/vendor/assets/javascripts/better_markdown.js +++ b/vendor/assets/javascripts/better_markdown.js @@ -4,10 +4,14 @@ * We have replaced the strong/em handlers because we prefer them only to work on word boundaries. + * [MOD]: non-url is fixed + // Fix code within attrs if (prev && (typeof prev[0] === "string") && prev[0].match(/<[^>]+$/)) { return; } - // __RAW__ + // __RAW + + // if ( next_block.match(is_list_re) || (next_block.match(/^ /) && (!next_block.match(/^ *\>/))) ) { */ @@ -18,38 +22,116 @@ /*jshint browser:true, devel:true */ -(function( expose ) { +(function(expose) { -/** - * class Markdown - * - * Markdown processing in Javascript done right. We have very particular views - * on what constitutes 'right' which include: - * - * - produces well-formed HTML (this means that em and strong nesting is - * important) - * - * - has an intermediate representation to allow processing of parsed data (We - * in fact have two, both as [JsonML]: a markdown tree and an HTML tree). - * - * - is easily extensible to add new dialects without having to rewrite the - * entire parsing mechanics - * - * - has a good test suite - * - * This implementation fulfills all of these (except that the test suite could - * do with expanding to automatically run all the fixtures from other Markdown - * implementations.) - * - * ##### Intermediate Representation - * - * *TODO* Talk about this :) Its JsonML, but document the node names we use. - * - * [JsonML]: http://jsonml.org/ "JSON Markup Language" - **/ + var MarkdownHelpers = {}; -var Markdown = expose.Markdown = function(dialect) { - switch (typeof dialect) { + // For Spidermonkey based engines + function mk_block_toSource() { + return "Markdown.mk_block( " + + uneval(this.toString()) + + ", " + + uneval(this.trailing) + + ", " + + uneval(this.lineNumber) + + " )"; + } + + // node + function mk_block_inspect() { + var util = require("util"); + return "Markdown.mk_block( " + + util.inspect(this.toString()) + + ", " + + util.inspect(this.trailing) + + ", " + + util.inspect(this.lineNumber) + + " )"; + + } + + MarkdownHelpers.mk_block = function(block, trail, line) { + // Be helpful for default case in tests. + if ( arguments.length === 1 ) + trail = "\n\n"; + + // We actually need a String object, not a string primitive + /* jshint -W053 */ + var s = new String(block); + s.trailing = trail; + // To make it clear its not just a string + s.inspect = mk_block_inspect; + s.toSource = mk_block_toSource; + + if ( line !== undefined ) + s.lineNumber = line; + + return s; + }; + + var isArray = MarkdownHelpers.isArray = Array.isArray || function(obj) { + return Object.prototype.toString.call(obj) === "[object Array]"; + }; + + // Don't mess with Array.prototype. Its not friendly + if ( Array.prototype.forEach ) { + MarkdownHelpers.forEach = function forEach( arr, cb, thisp ) { + return arr.forEach( cb, thisp ); + }; + } + else { + MarkdownHelpers.forEach = function forEach(arr, cb, thisp) { + for (var i = 0; i < arr.length; i++) + cb.call(thisp || arr, arr[i], i, arr); + }; + } + + MarkdownHelpers.isEmpty = function isEmpty( obj ) { + for ( var key in obj ) { + if ( hasOwnProperty.call( obj, key ) ) + return false; + } + return true; + }; + + MarkdownHelpers.extract_attr = function extract_attr( jsonml ) { + return isArray(jsonml) + && jsonml.length > 1 + && typeof jsonml[ 1 ] === "object" + && !( isArray(jsonml[ 1 ]) ) + ? jsonml[ 1 ] + : undefined; + }; + + /** + * class Markdown + * + * Markdown processing in Javascript done right. We have very particular views + * on what constitutes 'right' which include: + * + * - produces well-formed HTML (this means that em and strong nesting is + * important) + * + * - has an intermediate representation to allow processing of parsed data (We + * in fact have two, both as [JsonML]: a markdown tree and an HTML tree). + * + * - is easily extensible to add new dialects without having to rewrite the + * entire parsing mechanics + * + * - has a good test suite + * + * This implementation fulfills all of these (except that the test suite could + * do with expanding to automatically run all the fixtures from other Markdown + * implementations.) + * + * ##### Intermediate Representation + * + * *TODO* Talk about this :) Its JsonML, but document the node names we use. + * + * [JsonML]: http://jsonml.org/ "JSON Markup Language" + **/ + var Markdown = function(dialect) { + switch (typeof dialect) { case "undefined": this.dialect = Markdown.dialects.Gruber; break; @@ -57,203 +139,100 @@ var Markdown = expose.Markdown = function(dialect) { this.dialect = dialect; break; default: - if ( dialect in Markdown.dialects ) { + if ( dialect in Markdown.dialects ) this.dialect = Markdown.dialects[dialect]; - } - else { + else throw new Error("Unknown Markdown dialect '" + String(dialect) + "'"); - } break; - } - this.em_state = []; - this.strong_state = []; - this.debug_indent = ""; -}; - -/** - * parse( markdown, [dialect] ) -> JsonML - * - markdown (String): markdown string to parse - * - dialect (String | Dialect): the dialect to use, defaults to gruber - * - * Parse `markdown` and return a markdown document as a Markdown.JsonML tree. - **/ -expose.parse = function( source, dialect ) { - // dialect will default if undefined - var md = new Markdown( dialect ); - return md.toTree( source ); -}; - -/** - * toHTML( markdown, [dialect] ) -> String - * toHTML( md_tree ) -> String - * - markdown (String): markdown string to parse - * - md_tree (Markdown.JsonML): parsed markdown tree - * - * Take markdown (either as a string or as a JsonML tree) and run it through - * [[toHTMLTree]] then turn it into a well-formated HTML fragment. - **/ -expose.toHTML = function toHTML( source , dialect , options ) { - var input = expose.toHTMLTree( source , dialect , options ); - - return expose.renderJsonML( input ); -}; - -/** - * toHTMLTree( markdown, [dialect] ) -> JsonML - * toHTMLTree( md_tree ) -> JsonML - * - markdown (String): markdown string to parse - * - dialect (String | Dialect): the dialect to use, defaults to gruber - * - md_tree (Markdown.JsonML): parsed markdown tree - * - * Turn markdown into HTML, represented as a JsonML tree. If a string is given - * to this function, it is first parsed into a markdown tree by calling - * [[parse]]. - **/ -expose.toHTMLTree = function toHTMLTree( input, dialect , options ) { - // convert string input to an MD tree - if ( typeof input ==="string" ) input = this.parse( input, dialect ); - - // Now convert the MD tree to an HTML tree - - // remove references from the tree - var attrs = extract_attr( input ), - refs = {}; - - if ( attrs && attrs.references ) { - refs = attrs.references; - } - - var html = convert_tree_to_html( input, refs , options ); - merge_text_nodes( html ); - return html; -}; - -// For Spidermonkey based engines -function mk_block_toSource() { - return "Markdown.mk_block( " + - uneval(this.toString()) + - ", " + - uneval(this.trailing) + - ", " + - uneval(this.lineNumber) + - " )"; -} - -// node -function mk_block_inspect() { - var util = require("util"); - return "Markdown.mk_block( " + - util.inspect(this.toString()) + - ", " + - util.inspect(this.trailing) + - ", " + - util.inspect(this.lineNumber) + - " )"; - -} - -var mk_block = Markdown.mk_block = function(block, trail, line) { - // Be helpful for default case in tests. - if ( arguments.length == 1 ) trail = "\n\n"; - - var s = new String(block); - s.trailing = trail; - // To make it clear its not just a string - s.inspect = mk_block_inspect; - s.toSource = mk_block_toSource; - - if ( line != undefined ) - s.lineNumber = line; - - return s; -}; - -function count_lines( str ) { - var n = 0, i = -1; - while ( ( i = str.indexOf("\n", i + 1) ) !== -1 ) n++; - return n; -} - -// Internal - split source into rough blocks -Markdown.prototype.split_blocks = function splitBlocks( input, startLine ) { - input = input.replace(/(\r\n|\n|\r)/g, "\n"); - // [\s\S] matches _anything_ (newline or space) - // [^] is equivalent but doesn't work in IEs. - var re = /([\s\S]+?)($|\n#|\n(?:\s*\n|$)+)/g, - blocks = [], - m; - - var line_no = 1; - - if ( ( m = /^(\s*\n)/.exec(input) ) != null ) { - // skip (but count) leading blank lines - line_no += count_lines( m[0] ); - re.lastIndex = m[0].length; - } - - while ( ( m = re.exec(input) ) !== null ) { - if (m[2] == "\n#") { - m[2] = "\n"; - re.lastIndex--; } - blocks.push( mk_block( m[1], m[2], line_no ) ); - line_no += count_lines( m[0] ); - } - - return blocks; -}; - -function create_attrs() { - if ( !extract_attr( this.tree ) ) { - this.tree.splice( 1, 0, {} ); - } - - var attrs = extract_attr( this.tree ); - - // make a references hash if it doesn't exist - if ( attrs.references === undefined ) { - attrs.references = {}; - } - - return attrs; -} - -function create_reference(attrs, m) { - if ( m[2] && m[2][0] == "<" && m[2][m[2].length-1] == ">" ) - m[2] = m[2].substring( 1, m[2].length - 1 ); - - var ref = attrs.references[ m[1].toLowerCase() ] = { - href: m[2] + this.em_state = []; + this.strong_state = []; + this.debug_indent = ""; }; - if ( m[4] !== undefined ) - ref.title = m[4]; - else if ( m[5] !== undefined ) - ref.title = m[5]; -} + /** + * Markdown.dialects + * + * Namespace of built-in dialects. + **/ + Markdown.dialects = {}; -/** - * Markdown#processBlock( block, next ) -> undefined | [ JsonML, ... ] - * - block (String): the block to process - * - next (Array): the following blocks - * - * Process `block` and return an array of JsonML nodes representing `block`. - * - * It does this by asking each block level function in the dialect to process - * the block until one can. Succesful handling is indicated by returning an - * array (with zero or more JsonML nodes), failure by a false value. - * - * Blocks handlers are responsible for calling [[Markdown#processInline]] - * themselves as appropriate. - * - * If the blocks were split incorrectly or adjacent blocks need collapsing you - * can adjust `next` in place using shift/splice etc. - * - * If any of this default behaviour is not right for the dialect, you can - * define a `__call__` method on the dialect that will get invoked to handle - * the block processing. - */ -Markdown.prototype.processBlock = function processBlock( block, next ) { + // Imported functions + var mk_block = Markdown.mk_block = MarkdownHelpers.mk_block, + isArray = MarkdownHelpers.isArray; + + /** + * parse( markdown, [dialect] ) -> JsonML + * - markdown (String): markdown string to parse + * - dialect (String | Dialect): the dialect to use, defaults to gruber + * + * Parse `markdown` and return a markdown document as a Markdown.JsonML tree. + **/ + Markdown.parse = function( source, dialect ) { + // dialect will default if undefined + var md = new Markdown( dialect ); + return md.toTree( source ); + }; + + function count_lines( str ) { + var n = 0, + i = -1; + while ( ( i = str.indexOf("\n", i + 1) ) !== -1 ) + n++; + return n; + } + + // Internal - split source into rough blocks + Markdown.prototype.split_blocks = function splitBlocks( input ) { + input = input.replace(/(\r\n|\n|\r)/g, "\n"); + // [\s\S] matches _anything_ (newline or space) + // [^] is equivalent but doesn't work in IEs. + var re = /([\s\S]+?)($|\n#|\n(?:\s*\n|$)+)/g, + blocks = [], + m; + + var line_no = 1; + + if ( ( m = /^(\s*\n)/.exec(input) ) !== null ) { + // skip (but count) leading blank lines + line_no += count_lines( m[0] ); + re.lastIndex = m[0].length; + } + + while ( ( m = re.exec(input) ) !== null ) { + if (m[2] === "\n#") { + m[2] = "\n"; + re.lastIndex--; + } + blocks.push( mk_block( m[1], m[2], line_no ) ); + line_no += count_lines( m[0] ); + } + + return blocks; + }; + + /** + * Markdown#processBlock( block, next ) -> undefined | [ JsonML, ... ] + * - block (String): the block to process + * - next (Array): the following blocks + * + * Process `block` and return an array of JsonML nodes representing `block`. + * + * It does this by asking each block level function in the dialect to process + * the block until one can. Succesful handling is indicated by returning an + * array (with zero or more JsonML nodes), failure by a false value. + * + * Blocks handlers are responsible for calling [[Markdown#processInline]] + * themselves as appropriate. + * + * If the blocks were split incorrectly or adjacent blocks need collapsing you + * can adjust `next` in place using shift/splice etc. + * + * If any of this default behaviour is not right for the dialect, you can + * define a `__call__` method on the dialect that will get invoked to handle + * the block processing. + */ + Markdown.prototype.processBlock = function processBlock( block, next ) { var cbs = this.dialect.block, ord = cbs.__order__; @@ -274,1028 +253,256 @@ Markdown.prototype.processBlock = function processBlock( block, next ) { // Uhoh! no match! Should we throw an error? return []; -}; + }; -Markdown.prototype.processInline = function processInline( block ) { - return this.dialect.inline.__call__.call( this, String( block ) ); -}; + Markdown.prototype.processInline = function processInline( block ) { + return this.dialect.inline.__call__.call( this, String( block ) ); + }; -/** - * Markdown#toTree( source ) -> JsonML - * - source (String): markdown source to parse - * - * Parse `source` into a JsonML tree representing the markdown document. - **/ -// custom_tree means set this.tree to `custom_tree` and restore old value on return -Markdown.prototype.toTree = function toTree( source, custom_root ) { - var blocks = source instanceof Array ? source : this.split_blocks( source ); + /** + * Markdown#toTree( source ) -> JsonML + * - source (String): markdown source to parse + * + * Parse `source` into a JsonML tree representing the markdown document. + **/ + // custom_tree means set this.tree to `custom_tree` and restore old value on return + Markdown.prototype.toTree = function toTree( source, custom_root ) { + var blocks = source instanceof Array ? source : this.split_blocks( source ); - // Make tree a member variable so its easier to mess with in extensions - var old_tree = this.tree; - try { - this.tree = custom_root || this.tree || [ "markdown" ]; + // Make tree a member variable so its easier to mess with in extensions + var old_tree = this.tree; + try { + this.tree = custom_root || this.tree || [ "markdown" ]; - blocks: - while ( blocks.length ) { - var b = this.processBlock( blocks.shift(), blocks ); + blocks_loop: + while ( blocks.length ) { + var b = this.processBlock( blocks.shift(), blocks ); - // Reference blocks and the like won't return any content - if ( !b.length ) continue blocks; + // Reference blocks and the like won't return any content + if ( !b.length ) + continue blocks_loop; - this.tree.push.apply( this.tree, b ); + this.tree.push.apply( this.tree, b ); + } + return this.tree; } - return this.tree; - } - finally { - if ( custom_root ) { - this.tree = old_tree; + finally { + if ( custom_root ) + this.tree = old_tree; } - } -}; + }; -// Noop by default -Markdown.prototype.debug = function () { - var args = Array.prototype.slice.call( arguments); - args.unshift(this.debug_indent); - if ( typeof print !== "undefined" ) + // Noop by default + Markdown.prototype.debug = function () { + var args = Array.prototype.slice.call( arguments); + args.unshift(this.debug_indent); + if ( typeof print !== "undefined" ) print.apply( print, args ); - if ( typeof console !== "undefined" && typeof console.log !== "undefined" ) + if ( typeof console !== "undefined" && typeof console.log !== "undefined" ) console.log.apply( null, args ); -} + }; -Markdown.prototype.loop_re_over_block = function( re, block, cb ) { - // Dont use /g regexps with this - var m, - b = block.valueOf(); + Markdown.prototype.loop_re_over_block = function( re, block, cb ) { + // Dont use /g regexps with this + var m, + b = block.valueOf(); - while ( b.length && (m = re.exec(b) ) != null ) { - b = b.substr( m[0].length ); - cb.call(this, m); - } - return b; -}; - -/** - * Markdown.dialects - * - * Namespace of built-in dialects. - **/ -Markdown.dialects = {}; - -/** - * Markdown.dialects.Gruber - * - * The default dialect that follows the rules set out by John Gruber's - * markdown.pl as closely as possible. Well actually we follow the behaviour of - * that script which in some places is not exactly what the syntax web page - * says. - **/ -Markdown.dialects.Gruber = { - block: { - atxHeader: function atxHeader( block, next ) { - var m = block.match( /^(#{1,6})\s*(.*?)\s*#*\s*(?:\n|$)/ ); - - if ( !m ) return undefined; - - var header = [ "header", { level: m[ 1 ].length } ]; - Array.prototype.push.apply(header, this.processInline(m[ 2 ])); - - if ( m[0].length < block.length ) - next.unshift( mk_block( block.substr( m[0].length ), block.trailing, block.lineNumber + 2 ) ); - - return [ header ]; - }, - - setextHeader: function setextHeader( block, next ) { - var m = block.match( /^(.*)\n([-=])\2\2+(?:\n|$)/ ); - - if ( !m ) return undefined; - - var level = ( m[ 2 ] === "=" ) ? 1 : 2; - var header = [ "header", { level : level } ].concat( this.processInline(m[ 1 ]) ); - - if ( m[0].length < block.length ) - next.unshift( mk_block( block.substr( m[0].length ), block.trailing, block.lineNumber + 2 ) ); - - return [ header ]; - }, - - code: function code( block, next ) { - // | Foo - // |bar - // should be a code block followed by a paragraph. Fun - // - // There might also be adjacent code block to merge. - - var ret = [], - re = /^(?: {0,3}\t| {4})(.*)\n?/, - lines; - - // 4 spaces + content - if ( !block.match( re ) ) return undefined; - - block_search: - do { - // Now pull out the rest of the lines - var b = this.loop_re_over_block( - re, block.valueOf(), function( m ) { ret.push( m[1] ); } ); - - if ( b.length ) { - // Case alluded to in first comment. push it back on as a new block - next.unshift( mk_block(b, block.trailing) ); - break block_search; - } - else if ( next.length ) { - // Check the next block - it might be code too - if ( !next[0].match( re ) ) break block_search; - - // Pull how how many blanks lines follow - minus two to account for .join - ret.push ( block.trailing.replace(/[^\n]/g, "").substring(2) ); - - block = next.shift(); - } - else { - break block_search; - } - } while ( true ); - - return [ [ "code_block", ret.join("\n") ] ]; - }, - - horizRule: function horizRule( block, next ) { - // this needs to find any hr in the block to handle abutting blocks - var m = block.match( /^(?:([\s\S]*?)\n)?[ \t]*([-_*])(?:[ \t]*\2){2,}[ \t]*(?:\n([\s\S]*))?$/ ); - - if ( !m ) { - return undefined; - } - - var jsonml = [ [ "hr" ] ]; - - // if there's a leading abutting block, process it - if ( m[ 1 ] ) { - jsonml.unshift.apply( jsonml, this.processBlock( m[ 1 ], [] ) ); - } - - // if there's a trailing abutting block, stick it into next - if ( m[ 3 ] ) { - next.unshift( mk_block( m[ 3 ] ) ); - } - - return jsonml; - }, - - // There are two types of lists. Tight and loose. Tight lists have no whitespace - // between the items (and result in text just in the
  • ) and loose lists, - // which have an empty line between list items, resulting in (one or more) - // paragraphs inside the
  • . - // - // There are all sorts weird edge cases about the original markdown.pl's - // handling of lists: - // - // * Nested lists are supposed to be indented by four chars per level. But - // if they aren't, you can get a nested list by indenting by less than - // four so long as the indent doesn't match an indent of an existing list - // item in the 'nest stack'. - // - // * The type of the list (bullet or number) is controlled just by the - // first item at the indent. Subsequent changes are ignored unless they - // are for nested lists - // - lists: (function( ) { - // Use a closure to hide a few variables. - var any_list = "[*+-]|\\d+\\.", - bullet_list = /[*+-]/, - number_list = /\d+\./, - // Capture leading indent as it matters for determining nested lists. - is_list_re = new RegExp( "^( {0,3})(" + any_list + ")[ \t]+" ), - indent_re = "(?: {0,3}\\t| {4})"; - - // TODO: Cache this regexp for certain depths. - // Create a regexp suitable for matching an li for a given stack depth - function regex_for_depth( depth ) { - - return new RegExp( - // m[1] = indent, m[2] = list_type - "(?:^(" + indent_re + "{0," + depth + "} {0,3})(" + any_list + ")\\s+)|" + - // m[3] = cont - "(^" + indent_re + "{0," + (depth-1) + "}[ ]{0,4})" - ); - } - function expand_tab( input ) { - return input.replace( / {0,3}\t/g, " " ); - } - - // Add inline content `inline` to `li`. inline comes from processInline - // so is an array of content - function add(li, loose, inline, nl) { - if ( loose ) { - li.push( [ "para" ].concat(inline) ); - return; - } - // Hmmm, should this be any block level element or just paras? - var add_to = li[li.length -1] instanceof Array && li[li.length - 1][0] == "para" - ? li[li.length -1] - : li; - - // If there is already some content in this list, add the new line in - if ( nl && li.length > 1 ) inline.unshift(nl); - - for ( var i = 0; i < inline.length; i++ ) { - var what = inline[i], - is_str = typeof what == "string"; - if ( is_str && add_to.length > 1 && typeof add_to[add_to.length-1] == "string" ) { - add_to[ add_to.length-1 ] += what; - } - else { - add_to.push( what ); - } - } - } - - // contained means have an indent greater than the current one. On - // *every* line in the block - function get_contained_blocks( depth, blocks ) { - - var re = new RegExp( "^(" + indent_re + "{" + depth + "}.*?\\n?)*$" ), - replace = new RegExp("^" + indent_re + "{" + depth + "}", "gm"), - ret = []; - - while ( blocks.length > 0 ) { - if ( re.exec( blocks[0] ) ) { - var b = blocks.shift(), - // Now remove that indent - x = b.replace( replace, ""); - - ret.push( mk_block( x, b.trailing, b.lineNumber ) ); - } - else { - break; - } - } - return ret; - } - - // passed to stack.forEach to turn list items up the stack into paras - function paragraphify(s, i, stack) { - var list = s.list; - var last_li = list[list.length-1]; - - if ( last_li[1] instanceof Array && last_li[1][0] == "para" ) { - return; - } - - if ( i + 1 == stack.length ) { - // Last stack frame - // Keep the same array, but replace the contents - last_li.push( ["para"].concat( last_li.splice(1, last_li.length - 1) ) ); - } - else { - var sublist = last_li.pop(); - - last_li.push( ["para"].concat( last_li.splice(1, last_li.length - 1) ), sublist ); - } - } - - // The matcher function - return function( block, next ) { - - var m = block.match( is_list_re ); - if ( !m ) return undefined; - - function make_list( m ) { - var list = bullet_list.exec( m[2] ) - ? ["bulletlist"] - : ["numberlist"]; - - stack.push( { list: list, indent: m[1] } ); - return list; - } - - - var stack = [], // Stack of lists for nesting. - list = make_list( m ), - last_li, - loose = false, - ret = [ stack[0].list ], - i; - - // Loop to search over block looking for inner block elements and loose lists - loose_search: - while ( true ) { - // Split into lines preserving new lines at end of line - var lines = block.split( /(?=\n)/ ); - - // We have to grab all lines for a li and call processInline on them - // once as there are some inline things that can span lines. - var li_accumulate = ""; - - // Loop over the lines in this block looking for tight lists. - tight_search: - for ( var line_no = 0; line_no < lines.length; line_no++ ) { - var nl = "", - l = lines[line_no].replace(/^\n/, function(n) { nl = n; return ""; }); - - // TODO: really should cache this - var line_re = regex_for_depth( stack.length ); - - m = l.match( line_re ); - //print( "line:", uneval(l), "\nline match:", uneval(m) ); - - // We have a list item - if ( m[1] !== undefined ) { - // Process the previous list item, if any - if ( li_accumulate.length ) { - add( last_li, loose, this.processInline( li_accumulate ), nl ); - // Loose mode will have been dealt with. Reset it - loose = false; - li_accumulate = ""; - } - - m[1] = expand_tab( m[1] ); - var wanted_depth = Math.floor(m[1].length/4)+1; - //print( "want:", wanted_depth, "stack:", stack.length); - if ( wanted_depth > stack.length ) { - // Deep enough for a nested list outright - //print ( "new nested list" ); - list = make_list( m ); - last_li.push( list ); - last_li = list[1] = [ "listitem" ]; - } - else { - // We aren't deep enough to be strictly a new level. This is - // where Md.pl goes nuts. If the indent matches a level in the - // stack, put it there, else put it one deeper then the - // wanted_depth deserves. - var found = false; - for ( i = 0; i < stack.length; i++ ) { - if ( stack[ i ].indent != m[1] ) continue; - list = stack[ i ].list; - stack.splice( i+1, stack.length - (i+1) ); - found = true; - break; - } - - if (!found) { - //print("not found. l:", uneval(l)); - wanted_depth++; - if ( wanted_depth <= stack.length ) { - stack.splice(wanted_depth, stack.length - wanted_depth); - //print("Desired depth now", wanted_depth, "stack:", stack.length); - list = stack[wanted_depth-1].list; - //print("list:", uneval(list) ); - } - else { - //print ("made new stack for messy indent"); - list = make_list(m); - last_li.push(list); - } - } - - //print( uneval(list), "last", list === stack[stack.length-1].list ); - last_li = [ "listitem" ]; - list.push(last_li); - } // end depth of shenegains - nl = ""; - } - - // Add content - if ( l.length > m[0].length ) { - li_accumulate += nl + l.substr( m[0].length ); - } - } // tight_search - - if ( li_accumulate.length ) { - - add( last_li, loose, this.processInline( li_accumulate ), nl ); - - if(last_li[last_li.length-1] === "\n") { - last_li.pop(); - } - - // Loose mode will have been dealt with. Reset it - loose = false; - li_accumulate = ""; - } - - // Look at the next block - we might have a loose list. Or an extra - // paragraph for the current li - var contained = get_contained_blocks( stack.length, next ); - - // Deal with code blocks or properly nested lists - if ( contained.length > 0 ) { - // Make sure all listitems up the stack are paragraphs - forEach( stack, paragraphify, this); - - last_li.push.apply( last_li, this.toTree( contained, [] ) ); - } - - var next_block = next[0] && next[0].valueOf() || ""; - - - if ( next_block.match(is_list_re) || (next_block.match(/^ /) && (!next_block.match(/^ *\>/))) ) { - - block = next.shift(); - - // Check for an HR following a list: features/lists/hr_abutting - var hr = this.dialect.block.horizRule( block, next ); - - if ( hr ) { - ret.push.apply(ret, hr); - break; - } - - // Add paragraphs if the indentation level stays the same - if (stack[stack.length-1].indent === block.match(/^\s*/)[0]) { - forEach( stack, paragraphify, this); - } - - loose = true; - continue loose_search; - } - break; - } // loose_search - - return ret; - }; - })(), - - blockquote: function blockquote( block, next ) { - - var m = /(^|\n) +(\>[\s\S]*)/.exec(block); - if (m && m[2] && m[2].length) { - var blockContents = block.replace(/(^|\n) +\>/, "$1>"); - next.unshift(blockContents); - return []; - } - - if ( !block.match( /^>/m ) ) - return undefined; - - var jsonml = []; - - // separate out the leading abutting block, if any. I.e. in this case: - // - // a - // > b - // - if ( block[ 0 ] != ">" ) { - var lines = block.split( /\n/ ), - prev = [], - line_no = block.lineNumber; - - // keep shifting lines until you find a crotchet - while ( lines.length && lines[ 0 ][ 0 ] != ">" ) { - prev.push( lines.shift() ); - line_no++; - } - - var abutting = mk_block( prev.join( "\n" ), "\n", block.lineNumber ); - jsonml.push.apply( jsonml, this.processBlock( abutting, [] ) ); - // reassemble new block of just block quotes! - block = mk_block( lines.join( "\n" ), block.trailing, line_no ); - } - - - // if the next block is also a blockquote merge it in - while ( next.length && next[ 0 ][ 0 ] == ">" ) { - var b = next.shift(); - block = mk_block( block + block.trailing + b, b.trailing, block.lineNumber ); - } - - // Strip off the leading "> " and re-process as a block. - var input = block.replace( /^> ?/gm, "" ), - old_tree = this.tree, - processedBlock = this.toTree( input, [ "blockquote" ] ), - attr = extract_attr( processedBlock ); - - // If any link references were found get rid of them - if ( attr && attr.references ) { - delete attr.references; - // And then remove the attribute object if it's empty - if ( isEmpty( attr ) ) { - processedBlock.splice( 1, 1 ); - } - } - - jsonml.push( processedBlock ); - return jsonml; - }, - - referenceDefn: function referenceDefn( block, next) { - - var re = /^\s*\[(.*?)\]:\s*(\S+)(?:\s+(?:(['"])(.*)\3|\((.*?)\)))?\n?/; - // interesting matches are [ , ref_id, url, , title, title ] - - if ( !block.match(re) ) - return undefined; - - var attrs = create_attrs.call(this); - - var b = this.loop_re_over_block(re, block, function( m ) { - create_reference(attrs, m); - }); - - if ( b.length ) - next.unshift( mk_block( b, block.trailing ) ); - - return []; - }, - - para: function para( block, next ) { - // everything's a para! - return [ ["para"].concat( this.processInline( block ) ) ]; + while ( b.length && (m = re.exec(b) ) !== null ) { + b = b.substr( m[0].length ); + cb.call(this, m); } - } -}; + return b; + }; -Markdown.dialects.Gruber.inline = { + // Build default order from insertion order. + Markdown.buildBlockOrder = function(d) { + var ord = []; + for ( var i in d ) { + if ( i === "__order__" || i === "__call__" ) + continue; + ord.push( i ); + } + d.__order__ = ord; + }; - __oneElement__: function oneElement( text, patterns_or_re, previous_nodes ) { - var m, - res, - lastIndex = 0; + // Build patterns for inline matcher + Markdown.buildInlinePatterns = function(d) { + var patterns = []; - patterns_or_re = patterns_or_re || this.dialect.inline.__patterns__; - var re = new RegExp( "([\\s\\S]*?)(" + (patterns_or_re.source || patterns_or_re) + ")" ); + for ( var i in d ) { + // __foo__ is reserved and not a pattern + if ( i.match( /^__.*__$/) ) + continue; + var l = i.replace( /([\\.*+?|()\[\]{}])/g, "\\$1" ) + .replace( /\n/, "\\n" ); + patterns.push( i.length === 1 ? l : "(?:" + l + ")" ); + } - m = re.exec( text ); - if (!m) { - // Just boring text - return [ text.length, text ]; - } - else if ( m[1] ) { - // Some un-interesting text matched. Return that first - return [ m[1].length, m[1] ]; - } + patterns = patterns.join("|"); + d.__patterns__ = patterns; + //print("patterns:", uneval( patterns ) ); - var res; - if ( m[2] in this.dialect.inline ) { - res = this.dialect.inline[ m[2] ].call( - this, - text.substr( m.index ), m, previous_nodes || [] ); - } - // Default for now to make dev easier. just slurp special and output it. - res = res || [ m[2].length, m[2] ]; - return res; - }, - - __call__: function inline( text, patterns ) { - - var out = [], - res; - - function add(x) { - //D:self.debug(" adding output", uneval(x)); - if ( typeof x == "string" && typeof out[out.length-1] == "string" ) - out[ out.length-1 ] += x; - else - out.push(x); - } - - while ( text.length > 0 ) { - res = this.dialect.inline.__oneElement__.call(this, text, patterns, out ); - text = text.substr( res.shift() ); - forEach(res, add ) - } - - return out; - }, - - // These characters are intersting elsewhere, so have rules for them so that - // chunks of plain text blocks don't include them - "]": function () {}, - "}": function () {}, - - __escape__ : /^\\[\\`\*_\<\>{}\[\]()#\+.!\-]/, - - "\\": function escaped( text ) { - // [ length of input processed, node/children to add... ] - // Only esacape: \ ` * _ { } [ ] ( ) # * + - . ! - if ( this.dialect.inline.__escape__.exec( text ) ) - return [ 2, text.charAt( 1 ) ]; + var fn = d.__call__; + d.__call__ = function(text, pattern) { + if ( pattern !== undefined ) + return fn.call(this, text, pattern); else - // Not an esacpe - return [ 1, "\\" ]; - }, - - "![": function image( text ) { - - // Unlike images, alt text is plain text only. no other elements are - // allowed in there - - // ![Alt text](/path/to/img.jpg "Optional title") - // 1 2 3 4 <--- captures - // - // First attempt to use a strong URL regexp to catch things like parentheses. If it misses, use the - // old one. - var m = text.match( /^!\[(.*?)][ \t]*\(((?:https?:(?:\/{1,3}|[a-z0-9%])|www\d{0,3}[.])(?:[^\s()<>]+|\([^\s()<>]+\))+(?:\([^\s()<>]+\)|[^`!()\[\]{};:'".,<>?«»“”‘’\s]))\)([ \t])*(["'].*["'])?/ ) || - text.match( /^!\[(.*?)\][ \t]*\([ \t]*([^")]*?)(?:[ \t]+(["'])(.*?)\3)?[ \t]*\)/ ); - - if ( m ) { - if ( m[2] && m[2][0] == "<" && m[2][m[2].length-1] == ">" ) - m[2] = m[2].substring( 1, m[2].length - 1 ); - - m[2] = this.dialect.inline.__call__.call( this, m[2], /\\/ )[0]; - - var attrs = { alt: m[1], href: m[2] || "" }; - if ( m[4] !== undefined) - attrs.title = m[4]; - - return [ m[0].length, [ "img", attrs ] ]; - } - - // ![Alt text][id] - m = text.match( /^!\[(.*?)\][ \t]*\[(.*?)\]/ ); - - if ( m ) { - // We can't check if the reference is known here as it likely wont be - // found till after. Check it in md tree->hmtl tree conversion - return [ m[0].length, [ "img_ref", { alt: m[1], ref: m[2].toLowerCase(), original: m[0] } ] ]; - } - - // Just consume the '![' - return [ 2, "![" ]; - }, - - "[": function link( text ) { - - var orig = String(text); - - // Inline content is possible inside `link text` - var res = Markdown.DialectHelpers.inline_until_char.call( this, text.substr(1), "]" ); - - - // No closing ']' found. Just consume the [ - if ( !res ) return [ 1, "[" ]; - - var consumed = 1 + res[ 0 ], - children = res[ 1 ], - link, - attrs; - - // At this point the first [...] has been parsed. See what follows to find - // out which kind of link we are (reference or direct url) - text = text.substr( consumed ); - - // [link text](/path/to/img.jpg "Optional title") - // 1 2 3 <--- captures - // This will capture up to the last paren in the block. We then pull - // back based on if there a matching ones in the url - // ([here](/url/(test)) - // The parens have to be balanced - var m = text.match( /^\s*\([ \t]*([^"']*)(?:[ \t]+(["'])(.*?)\2)?[ \t]*\)/ ); - if ( m ) { - var url = m[1].replace(/ +$/, ''); - consumed += m[0].length; - - if ( url && url[0] == "<" && url[url.length-1] == ">" ) - url = url.substring( 1, url.length - 1 ); - - // If there is a title we don't have to worry about parens in the url - if ( !m[3] ) { - var open_parens = 1; // One open that isn't in the capture - for ( var len = 0; len < url.length; len++ ) { - switch ( url[len] ) { - case "(": - open_parens++; - break; - case ")": - if ( --open_parens == 0) { - consumed -= url.length - len; - url = url.substring(0, len); - } - break; - } - } - } - - // Process escapes only - url = this.dialect.inline.__call__.call( this, url, /\\/ )[0]; - - attrs = { href: url || "" }; - if ( m[3] !== undefined) - attrs.title = m[3]; - - link = [ "link", attrs ].concat( children ); - return [ consumed, link ]; - } - - // [Alt text][id] - // [Alt text] [id] - m = text.match( /^\s*\[(.*?)\]/ ); - - if ( m ) { - consumed += m[ 0 ].length; - - // [links][] uses links as its reference - attrs = { ref: ( m[ 1 ] || String(children) ).toLowerCase(), original: orig.substr( 0, consumed ) }; - - link = [ "link_ref", attrs ].concat( children ); - - // We can't check if the reference is known here as it likely wont be - // found till after. Check it in md tree->hmtl tree conversion. - // Store the original so that conversion can revert if the ref isn't found. - return [ consumed, link ]; - } - - m = orig.match(/^\s*\[(.*?)\]:\s*(\S+)(?:\s+(?:(['"])(.*?)\3|\((.*?)\)))?\n?/m); - if (m && - (/^(?:(?:https?|ftp):\/\/)(?:\S+(?::\S*)?@)?(?:(?!10(?:\.\d{1,3}){3})(?!127(?:\.\d{1,3}){3})(?!169\.254(?:\.\d{1,3}){2})(?!192\.168(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z\u00a1-\uffff0-9]+-?)*[a-z\u00a1-\uffff0-9]+)(?:\.(?:[a-z\u00a1-\uffff0-9]+-?)*[a-z\u00a1-\uffff0-9]+)*(?:\.(?:[a-z\u00a1-\uffff]{2,})))(?::\d{2,5})?(?:\/[^\s]*)?$/i.test(m[2]) || - /(\/[\w~,;\-\./?%&+#=]*)/.test(m[2]))) { - var attrs = create_attrs.call(this); - create_reference(attrs, m); - - return [ m[0].length ] - } - - // [id] - // Only if id is plain (no formatting.) - if ( children.length == 1 && typeof children[0] == "string" ) { - - var normalized = children[0].toLowerCase().replace(/\n/, " ").replace(/\s+/, ' '); - attrs = { ref: normalized, original: orig.substr( 0, consumed ) }; - link = [ "link_ref", attrs, children[0] ]; - return [ consumed, link ]; - } - - // Just consume the "[" - return [ 1, "[" ]; - }, - - - "<": function autoLink( text ) { - var m; - - if ( ( m = text.match( /^<(?:((https?|ftp|mailto):[^>]+)|(.*?@.*?\.[a-zA-Z]+))>/ ) ) != null ) { - if ( m[3] ) { - return [ m[0].length, [ "link", { href: "mailto:" + m[3] }, m[3] ] ]; - - } - else if ( m[2] == "mailto" ) { - return [ m[0].length, [ "link", { href: m[1] }, m[1].substr("mailto:".length ) ] ]; - } - else - return [ m[0].length, [ "link", { href: m[1] }, m[1] ] ]; - } - - return [ 1, "<" ]; - }, - - "`": function inlineCode( text, match, prev ) { - - // If we're in a tag, don't do it. - if (prev && (typeof prev[0] === "string") && prev[0].match(/<[^>]+$/)) { return; } - - // Inline code block. as many backticks as you like to start it - // Always skip over the opening ticks. - var m = text.match( /(`+)(([\s\S]*?)\1)/ ); - - if ( m && m[2] ) - return [ m[1].length + m[2].length, [ "inlinecode", m[3] ] ]; - else { - // TODO: No matching end code found - warn! - return [ 1, "`" ]; - } - }, - - " \n": function lineBreak( text ) { - return [ 3, [ "linebreak" ] ]; - } - -}; - -// Build default order from insertion order. -Markdown.buildBlockOrder = function(d) { - var ord = []; - for ( var i in d ) { - if ( i == "__order__" || i == "__call__" ) continue; - ord.push( i ); - } - d.__order__ = ord; -}; - -// Build patterns for inline matcher -Markdown.buildInlinePatterns = function(d) { - var patterns = []; - - for ( var i in d ) { - // __foo__ is reserved and not a pattern - if ( i.match( /^__.*__$/) ) continue; - var l = i.replace( /([\\.*+?$|()\[\]{}])/g, "\\$1" ) - .replace( /\n/, "\\n" ); - patterns.push( i.length == 1 ? l : "(?:" + l + ")" ); - } - - patterns = patterns.join("|"); - d.__patterns__ = patterns; - //print("patterns:", uneval( patterns ) ); - - var fn = d.__call__; - d.__call__ = function(text, pattern) { - if ( pattern != undefined ) { - return fn.call(this, text, pattern); - } - else - { - return fn.call(this, text, patterns); - } + return fn.call(this, text, patterns); + }; }; -}; -Markdown.DialectHelpers = {}; -Markdown.DialectHelpers.inline_until_char = function( text, want ) { - var consumed = 0, - nodes = []; + var extract_attr = MarkdownHelpers.extract_attr; - while ( true ) { - if ( text.charAt( consumed ) == want ) { - // Found the character we were looking for - consumed++; - return [ consumed, nodes ]; + /** + * renderJsonML( jsonml[, options] ) -> String + * - jsonml (Array): JsonML array to render to XML + * - options (Object): options + * + * Converts the given JsonML into well-formed XML. + * + * The options currently understood are: + * + * - root (Boolean): wether or not the root node should be included in the + * output, or just its children. The default `false` is to not include the + * root itself. + */ + Markdown.renderJsonML = function( jsonml, options ) { + options = options || {}; + // include the root element in the rendered output? + options.root = options.root || false; + + var content = []; + + if ( options.root ) { + content.push( render_tree( jsonml ) ); + } + else { + jsonml.shift(); // get rid of the tag + if ( jsonml.length && typeof jsonml[ 0 ] === "object" && !( jsonml[ 0 ] instanceof Array ) ) + jsonml.shift(); // get rid of the attributes + + while ( jsonml.length ) + content.push( render_tree( jsonml.shift() ) ); } - if ( consumed >= text.length ) { - // No closing char found. Abort. - return null; - } - - var res = this.dialect.inline.__oneElement__.call(this, text.substr( consumed ) ); - consumed += res[ 0 ]; - // Add any returned nodes. - nodes.push.apply( nodes, res.slice( 1 ) ); - } -} - -// Helper function to make sub-classing a dialect easier -Markdown.subclassDialect = function( d ) { - function Block() {} - Block.prototype = d.block; - function Inline() {} - Inline.prototype = d.inline; - - return { block: new Block(), inline: new Inline() }; -}; - -Markdown.buildBlockOrder ( Markdown.dialects.Gruber.block ); -Markdown.buildInlinePatterns( Markdown.dialects.Gruber.inline ); - -var isArray = Array.isArray || function(obj) { - return Object.prototype.toString.call(obj) == "[object Array]"; -}; - -var forEach; -// Don't mess with Array.prototype. Its not friendly -if ( Array.prototype.forEach ) { - forEach = function( arr, cb, thisp ) { - return arr.forEach( cb, thisp ); + return content.join( "\n\n" ); }; -} -else { - forEach = function(arr, cb, thisp) { - for (var i = 0; i < arr.length; i++) { - cb.call(thisp || arr, arr[i], i, arr); - } - } -} -var isEmpty = function( obj ) { - for ( var key in obj ) { - if ( hasOwnProperty.call( obj, key ) ) { - return false; - } + /** + * toHTMLTree( markdown, [dialect] ) -> JsonML + * toHTMLTree( md_tree ) -> JsonML + * - markdown (String): markdown string to parse + * - dialect (String | Dialect): the dialect to use, defaults to gruber + * - md_tree (Markdown.JsonML): parsed markdown tree + * + * Turn markdown into HTML, represented as a JsonML tree. If a string is given + * to this function, it is first parsed into a markdown tree by calling + * [[parse]]. + **/ + Markdown.toHTMLTree = function toHTMLTree( input, dialect , options ) { + + // convert string input to an MD tree + if ( typeof input === "string" ) + input = this.parse( input, dialect ); + + // Now convert the MD tree to an HTML tree + + // remove references from the tree + var attrs = extract_attr( input ), + refs = {}; + + if ( attrs && attrs.references ) + refs = attrs.references; + + var html = convert_tree_to_html( input, refs , options ); + merge_text_nodes( html ); + return html; + }; + + /** + * toHTML( markdown, [dialect] ) -> String + * toHTML( md_tree ) -> String + * - markdown (String): markdown string to parse + * - md_tree (Markdown.JsonML): parsed markdown tree + * + * Take markdown (either as a string or as a JsonML tree) and run it through + * [[toHTMLTree]] then turn it into a well-formated HTML fragment. + **/ + Markdown.toHTML = function toHTML( source , dialect , options ) { + var input = this.toHTMLTree( source , dialect , options ); + + return this.renderJsonML( input ); + }; + + function escapeHTML( text ) { + return text.replace( /&/g, "&" ) + .replace( //g, ">" ) + .replace( /"/g, """ ) + .replace( /'/g, "'" ); } - return true; -} + function render_tree( jsonml ) { + // basic case + if ( typeof jsonml === "string" ) + return jsonml; -function extract_attr( jsonml ) { - return isArray(jsonml) - && jsonml.length > 1 - && typeof jsonml[ 1 ] === "object" - && !( isArray(jsonml[ 1 ]) ) - ? jsonml[ 1 ] - : undefined; -} - - - -/** - * renderJsonML( jsonml[, options] ) -> String - * - jsonml (Array): JsonML array to render to XML - * - options (Object): options - * - * Converts the given JsonML into well-formed XML. - * - * The options currently understood are: - * - * - root (Boolean): wether or not the root node should be included in the - * output, or just its children. The default `false` is to not include the - * root itself. - */ -expose.renderJsonML = function( jsonml, options ) { - options = options || {}; - // include the root element in the rendered output? - options.root = options.root || false; - - var content = []; - - if ( options.root ) { - content.push( render_tree( jsonml ) ); - } - else { - jsonml.shift(); // get rid of the tag - if ( jsonml.length && typeof jsonml[ 0 ] === "object" && !( jsonml[ 0 ] instanceof Array ) ) { - jsonml.shift(); // get rid of the attributes + if ( jsonml[0] == "__RAW" ) { + return jsonml[1]; } - while ( jsonml.length ) { + var tag = jsonml.shift(), + attributes = {}, + content = []; + + if ( jsonml.length && typeof jsonml[ 0 ] === "object" && !( jsonml[ 0 ] instanceof Array ) ) + attributes = jsonml.shift(); + + while ( jsonml.length ) content.push( render_tree( jsonml.shift() ) ); + + var tag_attrs = ""; + if (typeof attributes.src !== 'undefined') { + tag_attrs += ' src="' + escapeHTML( attributes.src ) + '"'; + delete attributes.src; } + + for ( var a in attributes ) + tag_attrs += " " + a + '="' + escapeHTML( attributes[ a ] ) + '"'; + + // be careful about adding whitespace here for inline elements + if ( tag === "img" || tag === "br" || tag === "hr" ) + return "<"+ tag + tag_attrs + "/>"; + else + return "<"+ tag + tag_attrs + ">" + content.join( "" ) + ""; } - return content.join( "\n\n" ); -}; + function convert_tree_to_html( tree, references, options ) { + var i; + options = options || {}; -function escapeHTML( text ) { - return text.replace( /&/g, "&" ) - .replace( //g, ">" ) - .replace( /"/g, """ ) - .replace( /'/g, "'" ); -} + // shallow clone + var jsonml = tree.slice( 0 ); -function render_tree( jsonml ) { - // basic case - if ( typeof jsonml === "string" ) { - return jsonml; - } - - if ( jsonml[0] == "__RAW" ) { - return jsonml[1]; - } - - var tag = jsonml.shift(), - attributes = {}, - content = []; - - if ( jsonml.length && typeof jsonml[ 0 ] === "object" && !( jsonml[ 0 ] instanceof Array ) ) { - attributes = jsonml.shift(); - } - - while ( jsonml.length ) { - content.push( render_tree( jsonml.shift() ) ); - } - - var tag_attrs = ""; - - // MDTest has src attributes first - if (typeof attributes.src !== 'undefined') { - tag_attrs += ' src="' + escapeHTML( attributes.src ) + '"'; - delete attributes.src; - } - - for ( var a in attributes ) { - tag_attrs += " " + a + '="' + escapeHTML( attributes[ a ] ) + '"'; - } - - // be careful about adding whitespace here for inline elements - if ( tag == "img" || tag == "br" || tag == "hr" ) { - return "<"+ tag + tag_attrs + "/>"; - } - else { - return "<"+ tag + tag_attrs + ">" + content.join( "" ) + ""; - } -} - -function convert_tree_to_html( tree, references, options ) { - var i; - options = options || {}; - - // shallow clone - var jsonml = tree.slice( 0 ); - - if ( typeof options.preprocessTreeNode === "function" ) { + if ( typeof options.preprocessTreeNode === "function" ) jsonml = options.preprocessTreeNode(jsonml, references); - } - // Clone attributes if they exist - var attrs = extract_attr( jsonml ); - if ( attrs ) { - jsonml[ 1 ] = {}; - for ( i in attrs ) { - jsonml[ 1 ][ i ] = attrs[ i ]; + // Clone attributes if they exist + var attrs = extract_attr( jsonml ); + if ( attrs ) { + jsonml[ 1 ] = {}; + for ( i in attrs ) { + jsonml[ 1 ][ i ] = attrs[ i ]; + } + attrs = jsonml[ 1 ]; } - attrs = jsonml[ 1 ]; - } - // basic case - if ( typeof jsonml === "string" ) { - return jsonml; - } + // basic case + if ( typeof jsonml === "string" ) + return jsonml; - // convert this node - switch ( jsonml[ 0 ] ) { + // convert this node + switch ( jsonml[ 0 ] ) { case "header": jsonml[ 0 ] = "h" + jsonml[ 1 ].level; delete jsonml[ 1 ].level; @@ -1314,7 +521,8 @@ function convert_tree_to_html( tree, references, options ) { break; case "markdown": jsonml[ 0 ] = "html"; - if ( attrs ) delete attrs.references; + if ( attrs ) + delete attrs.references; break; case "code_block": jsonml[ 0 ] = "pre"; @@ -1332,7 +540,7 @@ function convert_tree_to_html( tree, references, options ) { break; case "linebreak": jsonml[ 0 ] = "br"; - break; + break; case "link": jsonml[ 0 ] = "a"; break; @@ -1348,9 +556,8 @@ function convert_tree_to_html( tree, references, options ) { // add in the href and title, if present attrs.href = ref.href; - if ( ref.title ) { + if ( ref.title ) attrs.title = ref.title; - } // get rid of the unneeded original text delete attrs.original; @@ -1372,9 +579,8 @@ function convert_tree_to_html( tree, references, options ) { // add in the href and title, if present attrs.src = ref.href; - if ( ref.title ) { + if ( ref.title ) attrs.title = ref.title; - } // get rid of the unneeded original text delete attrs.original; @@ -1384,62 +590,851 @@ function convert_tree_to_html( tree, references, options ) { return attrs.original; } break; - } + } - // convert all the children - i = 1; + // convert all the children + i = 1; - // deal with the attribute node, if it exists - if ( attrs ) { - // if there are keys, skip over it - for ( var key in jsonml[ 1 ] ) { + // deal with the attribute node, if it exists + if ( attrs ) { + // if there are keys, skip over it + for ( var key in jsonml[ 1 ] ) { i = 2; break; - } - // if there aren't, remove it - if ( i === 1 ) { - jsonml.splice( i, 1 ); - } - } - - for ( ; i < jsonml.length; ++i ) { - jsonml[ i ] = convert_tree_to_html( jsonml[ i ], references, options ); - } - - return jsonml; -} - - -// merges adjacent text nodes into a single node -function merge_text_nodes( jsonml ) { - // skip the tag name and attribute hash - var i = extract_attr( jsonml ) ? 2 : 1; - - while ( i < jsonml.length ) { - // if it's a string check the next item too - if ( typeof jsonml[ i ] === "string" ) { - if ( i + 1 < jsonml.length && typeof jsonml[ i + 1 ] === "string" ) { - // merge the second string into the first and remove it - jsonml[ i ] += jsonml.splice( i + 1, 1 )[ 0 ]; } + // if there aren't, remove it + if ( i === 1 ) + jsonml.splice( i, 1 ); + } + + for ( ; i < jsonml.length; ++i ) { + jsonml[ i ] = convert_tree_to_html( jsonml[ i ], references, options ); + } + + return jsonml; + } + + // merges adjacent text nodes into a single node + function merge_text_nodes( jsonml ) { + // skip the tag name and attribute hash + var i = extract_attr( jsonml ) ? 2 : 1; + + while ( i < jsonml.length ) { + // if it's a string check the next item too + if ( typeof jsonml[ i ] === "string" ) { + if ( i + 1 < jsonml.length && typeof jsonml[ i + 1 ] === "string" ) { + // merge the second string into the first and remove it + jsonml[ i ] += jsonml.splice( i + 1, 1 )[ 0 ]; + } + else { + ++i; + } + } + // if it's not a string recurse else { + merge_text_nodes( jsonml[ i ] ); ++i; } } - // if it's not a string recurse - else { - merge_text_nodes( jsonml[ i ] ); - ++i; - } } -} -} )( (function() { - if ( typeof exports === "undefined" ) { - window.BetterMarkdown = {}; - return window.BetterMarkdown; + var DialectHelpers = {}; + DialectHelpers.inline_until_char = function( text, want ) { + var consumed = 0, + nodes = []; + + while ( true ) { + if ( text.charAt( consumed ) === want ) { + // Found the character we were looking for + consumed++; + return [ consumed, nodes ]; + } + + if ( consumed >= text.length ) { + // No closing char found. Abort. + return null; + } + + var res = this.dialect.inline.__oneElement__.call(this, text.substr( consumed ) ); + consumed += res[ 0 ]; + // Add any returned nodes. + nodes.push.apply( nodes, res.slice( 1 ) ); + } + }; + + // Helper function to make sub-classing a dialect easier + DialectHelpers.subclassDialect = function( d ) { + function Block() {} + Block.prototype = d.block; + function Inline() {} + Inline.prototype = d.inline; + + return { block: new Block(), inline: new Inline() }; + }; + + var forEach = MarkdownHelpers.forEach, + extract_attr = MarkdownHelpers.extract_attr, + mk_block = MarkdownHelpers.mk_block, + isEmpty = MarkdownHelpers.isEmpty, + inline_until_char = DialectHelpers.inline_until_char; + + /** + * Gruber dialect + * + * The default dialect that follows the rules set out by John Gruber's + * markdown.pl as closely as possible. Well actually we follow the behaviour of + * that script which in some places is not exactly what the syntax web page + * says. + **/ + var Gruber = { + block: { + atxHeader: function atxHeader( block, next ) { + var m = block.match( /^(#{1,6})\s*(.*?)\s*#*\s*(?:\n|$)/ ); + + if ( !m ) + return undefined; + + var header = [ "header", { level: m[ 1 ].length } ]; + Array.prototype.push.apply(header, this.processInline(m[ 2 ])); + + if ( m[0].length < block.length ) + next.unshift( mk_block( block.substr( m[0].length ), block.trailing, block.lineNumber + 2 ) ); + + return [ header ]; + }, + + setextHeader: function setextHeader( block, next ) { + var m = block.match( /^(.*)\n([-=])\2\2+(?:\n|$)/ ); + + if ( !m ) + return undefined; + + var level = ( m[ 2 ] === "=" ) ? 1 : 2, + header = [ "header", { level : level } ].concat( this.processInline(m[ 1 ]) ); + + if ( m[0].length < block.length ) + next.unshift( mk_block( block.substr( m[0].length ), block.trailing, block.lineNumber + 2 ) ); + + return [ header ]; + }, + + code: function code( block, next ) { + // | Foo + // |bar + // should be a code block followed by a paragraph. Fun + // + // There might also be adjacent code block to merge. + + var ret = [], + re = /^(?: {0,3}\t| {4})(.*)\n?/; + + // 4 spaces + content + if ( !block.match( re ) ) + return undefined; + + block_search: + do { + // Now pull out the rest of the lines + var b = this.loop_re_over_block( + re, block.valueOf(), function( m ) { ret.push( m[1] ); } ); + + if ( b.length ) { + // Case alluded to in first comment. push it back on as a new block + next.unshift( mk_block(b, block.trailing) ); + break block_search; + } + else if ( next.length ) { + // Check the next block - it might be code too + if ( !next[0].match( re ) ) + break block_search; + + // Pull how how many blanks lines follow - minus two to account for .join + ret.push ( block.trailing.replace(/[^\n]/g, "").substring(2) ); + + block = next.shift(); + } + else { + break block_search; + } + } while ( true ); + + return [ [ "code_block", ret.join("\n") ] ]; + }, + + horizRule: function horizRule( block, next ) { + // this needs to find any hr in the block to handle abutting blocks + var m = block.match( /^(?:([\s\S]*?)\n)?[ \t]*([-_*])(?:[ \t]*\2){2,}[ \t]*(?:\n([\s\S]*))?$/ ); + + if ( !m ) + return undefined; + + var jsonml = [ [ "hr" ] ]; + + // if there's a leading abutting block, process it + if ( m[ 1 ] ) { + var contained = mk_block( m[ 1 ], "", block.lineNumber ); + jsonml.unshift.apply( jsonml, this.toTree( contained, [] ) ); + } + + // if there's a trailing abutting block, stick it into next + if ( m[ 3 ] ) + next.unshift( mk_block( m[ 3 ], block.trailing, block.lineNumber + 1 ) ); + + return jsonml; + }, + + // There are two types of lists. Tight and loose. Tight lists have no whitespace + // between the items (and result in text just in the
  • ) and loose lists, + // which have an empty line between list items, resulting in (one or more) + // paragraphs inside the
  • . + // + // There are all sorts weird edge cases about the original markdown.pl's + // handling of lists: + // + // * Nested lists are supposed to be indented by four chars per level. But + // if they aren't, you can get a nested list by indenting by less than + // four so long as the indent doesn't match an indent of an existing list + // item in the 'nest stack'. + // + // * The type of the list (bullet or number) is controlled just by the + // first item at the indent. Subsequent changes are ignored unless they + // are for nested lists + // + lists: (function( ) { + // Use a closure to hide a few variables. + var any_list = "[*+-]|\\d+\\.", + bullet_list = /[*+-]/, + // Capture leading indent as it matters for determining nested lists. + is_list_re = new RegExp( "^( {0,3})(" + any_list + ")[ \t]+" ), + indent_re = "(?: {0,3}\\t| {4})"; + + // TODO: Cache this regexp for certain depths. + // Create a regexp suitable for matching an li for a given stack depth + function regex_for_depth( depth ) { + + return new RegExp( + // m[1] = indent, m[2] = list_type + "(?:^(" + indent_re + "{0," + depth + "} {0,3})(" + any_list + ")\\s+)|" + + // m[3] = cont + "(^" + indent_re + "{0," + (depth-1) + "}[ ]{0,4})" + ); + } + function expand_tab( input ) { + return input.replace( / {0,3}\t/g, " " ); + } + + // Add inline content `inline` to `li`. inline comes from processInline + // so is an array of content + function add(li, loose, inline, nl) { + if ( loose ) { + li.push( [ "para" ].concat(inline) ); + return; + } + // Hmmm, should this be any block level element or just paras? + var add_to = li[li.length -1] instanceof Array && li[li.length - 1][0] === "para" + ? li[li.length -1] + : li; + + // If there is already some content in this list, add the new line in + if ( nl && li.length > 1 ) + inline.unshift(nl); + + for ( var i = 0; i < inline.length; i++ ) { + var what = inline[i], + is_str = typeof what === "string"; + if ( is_str && add_to.length > 1 && typeof add_to[add_to.length-1] === "string" ) + add_to[ add_to.length-1 ] += what; + else + add_to.push( what ); + } + } + + // contained means have an indent greater than the current one. On + // *every* line in the block + function get_contained_blocks( depth, blocks ) { + + var re = new RegExp( "^(" + indent_re + "{" + depth + "}.*?\\n?)*$" ), + replace = new RegExp("^" + indent_re + "{" + depth + "}", "gm"), + ret = []; + + while ( blocks.length > 0 ) { + if ( re.exec( blocks[0] ) ) { + var b = blocks.shift(), + // Now remove that indent + x = b.replace( replace, ""); + + ret.push( mk_block( x, b.trailing, b.lineNumber ) ); + } + else + break; + } + return ret; + } + + // passed to stack.forEach to turn list items up the stack into paras + function paragraphify(s, i, stack) { + var list = s.list; + var last_li = list[list.length-1]; + + if ( last_li[1] instanceof Array && last_li[1][0] === "para" ) + return; + + if ( i + 1 === stack.length ) { + // Last stack frame + // Keep the same array, but replace the contents + last_li.push( ["para"].concat( last_li.splice(1, last_li.length - 1) ) ); + } + else { + var sublist = last_li.pop(); + last_li.push( ["para"].concat( last_li.splice(1, last_li.length - 1) ), sublist ); + } + } + + // The matcher function + return function( block, next ) { + var m = block.match( is_list_re ); + if ( !m ) + return undefined; + + function make_list( m ) { + var list = bullet_list.exec( m[2] ) + ? ["bulletlist"] + : ["numberlist"]; + + stack.push( { list: list, indent: m[1] } ); + return list; + } + + var stack = [], // Stack of lists for nesting. + list = make_list( m ), + last_li, + loose = false, + ret = [ stack[0].list ], + i; + + // Loop to search over block looking for inner block elements and loose lists + loose_search: + while ( true ) { + // Split into lines preserving new lines at end of line + var lines = block.split( /(?=\n)/ ); + + // We have to grab all lines for a li and call processInline on them + // once as there are some inline things that can span lines. + var li_accumulate = "", nl = ""; + + // Loop over the lines in this block looking for tight lists. + tight_search: + for ( var line_no = 0; line_no < lines.length; line_no++ ) { + nl = ""; + var l = lines[line_no].replace(/^\n/, function(n) { nl = n; return ""; }); + + // TODO: really should cache this + var line_re = regex_for_depth( stack.length ); + + m = l.match( line_re ); + //print( "line:", uneval(l), "\nline match:", uneval(m) ); + + // We have a list item + if ( m[1] !== undefined ) { + // Process the previous list item, if any + if ( li_accumulate.length ) { + add( last_li, loose, this.processInline( li_accumulate ), nl ); + // Loose mode will have been dealt with. Reset it + loose = false; + li_accumulate = ""; + } + + m[1] = expand_tab( m[1] ); + var wanted_depth = Math.floor(m[1].length/4)+1; + //print( "want:", wanted_depth, "stack:", stack.length); + if ( wanted_depth > stack.length ) { + // Deep enough for a nested list outright + //print ( "new nested list" ); + list = make_list( m ); + last_li.push( list ); + last_li = list[1] = [ "listitem" ]; + } + else { + // We aren't deep enough to be strictly a new level. This is + // where Md.pl goes nuts. If the indent matches a level in the + // stack, put it there, else put it one deeper then the + // wanted_depth deserves. + var found = false; + for ( i = 0; i < stack.length; i++ ) { + if ( stack[ i ].indent !== m[1] ) + continue; + + list = stack[ i ].list; + stack.splice( i+1, stack.length - (i+1) ); + found = true; + break; + } + + if (!found) { + //print("not found. l:", uneval(l)); + wanted_depth++; + if ( wanted_depth <= stack.length ) { + stack.splice(wanted_depth, stack.length - wanted_depth); + //print("Desired depth now", wanted_depth, "stack:", stack.length); + list = stack[wanted_depth-1].list; + //print("list:", uneval(list) ); + } + else { + //print ("made new stack for messy indent"); + list = make_list(m); + last_li.push(list); + } + } + + //print( uneval(list), "last", list === stack[stack.length-1].list ); + last_li = [ "listitem" ]; + list.push(last_li); + } // end depth of shenegains + nl = ""; + } + + // Add content + if ( l.length > m[0].length ) + li_accumulate += nl + l.substr( m[0].length ); + } // tight_search + + if ( li_accumulate.length ) { + add( last_li, loose, this.processInline( li_accumulate ), nl ); + + // Let's not creating a trailing \n after content in the li + if(last_li[last_li.length-1] === "\n") { + last_li.pop(); + } + + // Loose mode will have been dealt with. Reset it + loose = false; + li_accumulate = ""; + } + + // Look at the next block - we might have a loose list. Or an extra + // paragraph for the current li + var contained = get_contained_blocks( stack.length, next ); + + // Deal with code blocks or properly nested lists + if ( contained.length > 0 ) { + // Make sure all listitems up the stack are paragraphs + forEach( stack, paragraphify, this); + + last_li.push.apply( last_li, this.toTree( contained, [] ) ); + } + + var next_block = next[0] && next[0].valueOf() || ""; + + if ( next_block.match(is_list_re) || (next_block.match(/^ /) && (!next_block.match(/^ *\>/))) ) { + block = next.shift(); + + // Check for an HR following a list: features/lists/hr_abutting + var hr = this.dialect.block.horizRule( block, next ); + + if ( hr ) { + ret.push.apply(ret, hr); + break; + } + + // Add paragraphs if the indentation level stays the same + if (stack[stack.length-1].indent === block.match(/^\s*/)[0]) { + forEach( stack, paragraphify, this); + } + + loose = true; + continue loose_search; + } + break; + } // loose_search + + return ret; + }; + })(), + + blockquote: function blockquote( block, next ) { + + // Handle quotes that have spaces before them + var m = /(^|\n) +(\>[\s\S]*)/.exec(block); + if (m && m[2] && m[2].length) { + var blockContents = block.replace(/(^|\n) +\>/, "$1>"); + next.unshift(blockContents); + return []; + } + + if ( !block.match( /^>/m ) ) + return undefined; + + var jsonml = []; + + // separate out the leading abutting block, if any. I.e. in this case: + // + // a + // > b + // + if ( block[ 0 ] !== ">" ) { + var lines = block.split( /\n/ ), + prev = [], + line_no = block.lineNumber; + + // keep shifting lines until you find a crotchet + while ( lines.length && lines[ 0 ][ 0 ] !== ">" ) { + prev.push( lines.shift() ); + line_no++; + } + + var abutting = mk_block( prev.join( "\n" ), "\n", block.lineNumber ); + jsonml.push.apply( jsonml, this.processBlock( abutting, [] ) ); + // reassemble new block of just block quotes! + block = mk_block( lines.join( "\n" ), block.trailing, line_no ); + } + + // if the next block is also a blockquote merge it in + while ( next.length && next[ 0 ][ 0 ] === ">" ) { + var b = next.shift(); + block = mk_block( block + block.trailing + b, b.trailing, block.lineNumber ); + } + + // Strip off the leading "> " and re-process as a block. + var input = block.replace( /^> ?/gm, "" ), + old_tree = this.tree, + processedBlock = this.toTree( input, [ "blockquote" ] ), + attr = extract_attr( processedBlock ); + + // If any link references were found get rid of them + if ( attr && attr.references ) { + delete attr.references; + // And then remove the attribute object if it's empty + if ( isEmpty( attr ) ) + processedBlock.splice( 1, 1 ); + } + + jsonml.push( processedBlock ); + return jsonml; + }, + + referenceDefn: function referenceDefn( block, next) { + var re = /^\s*\[(.*?)\]:\s*(\S+)(?:\s+(?:(['"])(.*)\3|\((.*?)\)))?\n?/; + // interesting matches are [ , ref_id, url, , title, title ] + + if ( !block.match(re) ) + return undefined; + + var attrs = create_attrs.call( this ); + + var b = this.loop_re_over_block(re, block, function( m ) { + create_reference(attrs, m); + } ); + + if ( b.length ) + next.unshift( mk_block( b, block.trailing ) ); + + return []; + }, + + para: function para( block ) { + // everything's a para! + return [ ["para"].concat( this.processInline( block ) ) ]; + } + }, + + inline: { + + __oneElement__: function oneElement( text, patterns_or_re, previous_nodes ) { + var m, + res; + + patterns_or_re = patterns_or_re || this.dialect.inline.__patterns__; + var re = new RegExp( "([\\s\\S]*?)(" + (patterns_or_re.source || patterns_or_re) + ")" ); + + m = re.exec( text ); + if (!m) { + // Just boring text + return [ text.length, text ]; + } + else if ( m[1] ) { + // Some un-interesting text matched. Return that first + return [ m[1].length, m[1] ]; + } + + var res; + if ( m[2] in this.dialect.inline ) { + res = this.dialect.inline[ m[2] ].call( + this, + text.substr( m.index ), m, previous_nodes || [] ); + } + // Default for now to make dev easier. just slurp special and output it. + res = res || [ m[2].length, m[2] ]; + return res; + }, + + __call__: function inline( text, patterns ) { + + var out = [], + res; + + function add(x) { + //D:self.debug(" adding output", uneval(x)); + if ( typeof x === "string" && typeof out[out.length-1] === "string" ) + out[ out.length-1 ] += x; + else + out.push(x); + } + + while ( text.length > 0 ) { + res = this.dialect.inline.__oneElement__.call(this, text, patterns, out ); + text = text.substr( res.shift() ); + forEach(res, add ); + } + + return out; + }, + + // These characters are intersting elsewhere, so have rules for them so that + // chunks of plain text blocks don't include them + "]": function () {}, + "}": function () {}, + + __escape__ : /^\\[\\`\*_{}<>\[\]()#\+.!\-]/, + + "\\": function escaped( text ) { + // [ length of input processed, node/children to add... ] + // Only esacape: \ ` * _ { } [ ] ( ) # * + - . ! + if ( this.dialect.inline.__escape__.exec( text ) ) + return [ 2, text.charAt( 1 ) ]; + else + // Not an esacpe + return [ 1, "\\" ]; + }, + + "![": function image( text ) { + + // Unlike images, alt text is plain text only. no other elements are + // allowed in there + + // ![Alt text](/path/to/img.jpg "Optional title") + // 1 2 3 4 <--- captures + // + // First attempt to use a strong URL regexp to catch things like parentheses. If it misses, use the + // old one. + var m = text.match( /^!\[(.*?)][ \t]*\(((?:https?:(?:\/{1,3}|[a-z0-9%])|www\d{0,3}[.])(?:[^\s()<>]+|\([^\s()<>]+\))+(?:\([^\s()<>]+\)|[^`!()\[\]{};:'".,<>?«»“”‘’\s]))\)([ \t])*(["'].*["'])?/ ) || + text.match( /^!\[(.*?)\][ \t]*\([ \t]*([^")]*?)(?:[ \t]+(["'])(.*?)\3)?[ \t]*\)/ ); + + if ( m ) { + if ( m[2] && m[2][0] === "<" && m[2][m[2].length-1] === ">" ) + m[2] = m[2].substring( 1, m[2].length - 1 ); + + m[2] = this.dialect.inline.__call__.call( this, m[2], /\\/ )[0]; + + var attrs = { alt: m[1], href: m[2] || "" }; + if ( m[4] !== undefined) + attrs.title = m[4]; + + return [ m[0].length, [ "img", attrs ] ]; + } + + // ![Alt text][id] + m = text.match( /^!\[(.*?)\][ \t]*\[(.*?)\]/ ); + + if ( m ) { + // We can't check if the reference is known here as it likely wont be + // found till after. Check it in md tree->hmtl tree conversion + return [ m[0].length, [ "img_ref", { alt: m[1], ref: m[2].toLowerCase(), original: m[0] } ] ]; + } + + // Just consume the '![' + return [ 2, "![" ]; + }, + + "[": function link( text ) { + + var orig = String(text); + // Inline content is possible inside `link text` + var res = inline_until_char.call( this, text.substr(1), "]" ); + + // No closing ']' found. Just consume the [ + if ( !res ) + return [ 1, "[" ]; + + var consumed = 1 + res[ 0 ], + children = res[ 1 ], + link, + attrs; + + // At this point the first [...] has been parsed. See what follows to find + // out which kind of link we are (reference or direct url) + text = text.substr( consumed ); + + // [link text](/path/to/img.jpg "Optional title") + // 1 2 3 <--- captures + // This will capture up to the last paren in the block. We then pull + // back based on if there a matching ones in the url + // ([here](/url/(test)) + // The parens have to be balanced + var m = text.match( /^\s*\([ \t]*([^"']*)(?:[ \t]+(["'])(.*?)\2)?[ \t]*\)/ ); + if ( m ) { + var url = m[1].replace(/\s+$/, ''); + consumed += m[0].length; + + if ( url && url[0] === "<" && url[url.length-1] === ">" ) + url = url.substring( 1, url.length - 1 ); + + // If there is a title we don't have to worry about parens in the url + if ( !m[3] ) { + var open_parens = 1; // One open that isn't in the capture + for ( var len = 0; len < url.length; len++ ) { + switch ( url[len] ) { + case "(": + open_parens++; + break; + case ")": + if ( --open_parens === 0) { + consumed -= url.length - len; + url = url.substring(0, len); + } + break; + } + } + } + + // Process escapes only + url = this.dialect.inline.__call__.call( this, url, /\\/ )[0]; + + attrs = { href: url || "" }; + if ( m[3] !== undefined) + attrs.title = m[3]; + + link = [ "link", attrs ].concat( children ); + return [ consumed, link ]; + } + + // [Alt text][id] + // [Alt text] [id] + m = text.match( /^\s*\[(.*?)\]/ ); + + if ( m ) { + + consumed += m[ 0 ].length; + + // [links][] uses links as its reference + attrs = { ref: ( m[ 1 ] || String(children) ).toLowerCase(), original: orig.substr( 0, consumed ) }; + + link = [ "link_ref", attrs ].concat( children ); + + // We can't check if the reference is known here as it likely wont be + // found till after. Check it in md tree->hmtl tree conversion. + // Store the original so that conversion can revert if the ref isn't found. + return [ consumed, link ]; + } + + // Another check for references + m = orig.match(/^\s*\[(.*?)\]:\s*(\S+)(?:\s+(?:(['"])(.*?)\3|\((.*?)\)))?\n?/); + if (m && + (/^(?:(?:https?|ftp):\/\/)(?:\S+(?::\S*)?@)?(?:(?!10(?:\.\d{1,3}){3})(?!127(?:\.\d{1,3}){3})(?!169\.254(?:\.\d{1,3}){2})(?!192\.168(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z\u00a1-\uffff0-9]+-?)*[a-z\u00a1-\uffff0-9]+)(?:\.(?:[a-z\u00a1-\uffff0-9]+-?)*[a-z\u00a1-\uffff0-9]+)*(?:\.(?:[a-z\u00a1-\uffff]{2,})))(?::\d{2,5})?(?:\/[^\s]*)?$/i.test(m[2]) || + /(\/[\w~,;\-\./?%&+#=]*)/.test(m[2]))) { + var attrs = create_attrs.call(this); + create_reference(attrs, m); + + return [ m[0].length ] + } + + // [id] + // Only if id is plain (no formatting.) + if ( children.length === 1 && typeof children[0] === "string" ) { + + var normalized = children[0].toLowerCase().replace(/\s+/, ' '); + attrs = { ref: normalized, original: orig.substr( 0, consumed ) }; + link = [ "link_ref", attrs, children[0] ]; + return [ consumed, link ]; + } + + // Just consume the "[" + return [ 1, "[" ]; + }, + + "<": function autoLink( text ) { + var m; + + if ( ( m = text.match( /^<(?:((https?|ftp|mailto):[^>]+)|(.*?@.*?\.[a-zA-Z]+))>/ ) ) !== null ) { + if ( m[3] ) + return [ m[0].length, [ "link", { href: "mailto:" + m[3] }, m[3] ] ]; + else if ( m[2] === "mailto" ) + return [ m[0].length, [ "link", { href: m[1] }, m[1].substr("mailto:".length ) ] ]; + else + return [ m[0].length, [ "link", { href: m[1] }, m[1] ] ]; + } + + return [ 1, "<" ]; + }, + + "`": function inlineCode( text, match, prev ) { + + // If we're in a tag, don't do it. + if (prev && (typeof prev[0] === "string") && prev[0].match(/<[^>]+$/)) { return; } + + // Inline code block. as many backticks as you like to start it + // Always skip over the opening ticks. + var m = text.match( /(`+)(([\s\S]*?)\1)/ ); + + if ( m && m[2] ) + return [ m[1].length + m[2].length, [ "inlinecode", m[3] ] ]; + else { + // TODO: No matching end code found - warn! + return [ 1, "`" ]; + } + }, + + " \n": function lineBreak() { + return [ 3, [ "linebreak" ] ]; + } + + } + }; + + // A helper function to create attributes + function create_attrs() { + if ( !extract_attr( this.tree ) ) { + this.tree.splice( 1, 0, {} ); + } + + var attrs = extract_attr( this.tree ); + + // make a references hash if it doesn't exist + if ( attrs.references === undefined ) { + attrs.references = {}; + } + + return attrs; } - else { - return exports; + + // Create references for attributes + function create_reference(attrs, m) { + if ( m[2] && m[2][0] === "<" && m[2][m[2].length-1] === ">" ) + m[2] = m[2].substring( 1, m[2].length - 1 ); + + var ref = attrs.references[ m[1].toLowerCase() ] = { + href: m[2] + }; + + if ( m[4] !== undefined ) + ref.title = m[4]; + else if ( m[5] !== undefined ) + ref.title = m[5]; } -} )() ); + + Markdown.dialects.Gruber = Gruber; + Markdown.buildBlockOrder ( Markdown.dialects.Gruber.block ); + Markdown.buildInlinePatterns( Markdown.dialects.Gruber.inline ); + +// Include all our dependencies and return the resulting library. + + expose.Markdown = Markdown; + expose.parse = Markdown.parse; + expose.toHTML = Markdown.toHTML; + expose.toHTMLTree = Markdown.toHTMLTree; + expose.renderJsonML = Markdown.renderJsonML; + expose.DialectHelpers = DialectHelpers; + +})(function() { + window.BetterMarkdown = {}; + return window.BetterMarkdown; +}());