diff --git a/index.html b/index.html index f5da412b..76b456f6 100644 --- a/index.html +++ b/index.html @@ -56,257 +56,30 @@
-

alt text

-

INSTALL

+ - +
-

Prerequisites:

- - - -

Installing on Debian/Ubuntu:

- -

Before Ubuntu 14.04:

- -

sudo apt-get install libcurl4-gnutls-dev libopenssl-ruby libxml2 libxml2-dev libxslt1-dev ruby-dev

- -

From Ubuntu 14.04:

- -

sudo apt-get install libcurl4-gnutls-dev libxml2 libxml2-dev libxslt1-dev ruby-dev

- -

git clone https://github.com/wpscanteam/wpscan.git

- -

cd wpscan

- -

sudo gem install bundler && bundle install --without test development

- -

Installing on Fedora:

- -

sudo yum install gcc ruby-devel libxml2 libxml2-devel libxslt libxslt-devel libcurl-devel

- -

git clone https://github.com/wpscanteam/wpscan.git

- -

cd wpscan

- -

sudo gem install bundler && bundle install --without test development

- -

Installing on Archlinux:

- -

pacman -Syu ruby

-

pacman -Syu libyaml

- -

git clone https://github.com/wpscanteam/wpscan.git

- -

cd wpscan

- -

sudo gem install bundler && bundle install --without test development

- -

gem install typhoeus

- -

gem install nokogiri

- -

Installing on Mac OSX:

- -

git clone https://github.com/wpscanteam/wpscan.git

- -

cd wpscan

- -

sudo gem install bundler && bundle install --without test development

- -

Installing with RVM:

- -

cd ~

- -

curl -sSL https://get.rvm.io | bash -s stable

- -

source ~/.rvm/scripts/rvm

- -

echo "source ~/.rvm/scripts/rvm" >> ~/.bashrc

- -

rvm install 2.1.2

- -

rvm use 2.1.2 --default

- -

echo "gem: --no-ri --no-rdoc" > ~/.gemrc

- -

git clone https://github.com/wpscanteam/wpscan.git

- -

cd wpscan

- -

gem install bundler

- -

bundle install --without test

- - -

KNOWN ISSUES

- - - -

WPSCAN ARGUMENTS

- -
--url   | -u <target url>  The WordPress URL/domain to scan.
-
---force | -f Forces WPScan to not check if the remote site is running WordPress.
-
---enumerate | -e [option(s)]  Enumeration.
-  option :
-    u        usernames from id 1 to 10
-    u[10-20] usernames from id 10 to 20 (you must write [] chars)
-    p        plugins
-    vp       only vulnerable plugins
-    ap       all plugins (can take a long time)
-    tt       timthumbs
-    t        themes
-    vt       only vulnerable themes
-    at       all themes (can take a long time)
-  Multiple values are allowed : '-e tt,p' will enumerate timthumbs and plugins
-  If no option is supplied, the default is 'vt,tt,u,vp'
-
---exclude-content-based '<regexp or string>'  Used with the enumeration option, will exclude all occurence based on the regexp or string supplied
-                                                    You do not need to provide the regexp delimiters, but you must write the quotes (simple or double)
-
---config-file | -c <config file> Use the specified config file
-
---follow-redirection  If the target url has a redirection, it will be followed without asking if you wanted to do so or not
-
---proxy <[protocol://]host:port>  Supply a proxy (will override the one from conf/browser.conf.json).
-                                        HTTP, SOCKS4 SOCKS4A and SOCKS5 are supported. If no protocol is given (format host:port), HTTP will be used
-
---proxy-auth <username:password>  Supply the proxy login credentials (will override the one from conf/browser.conf.json).
-
---basic-auth <username:password>  Set the HTTP basic authentification
-
---wordlist | -w <wordlist>  Supply a wordlist for the password bruter and do the brute.
-
---threads  | -t <number of threads>  The number of threads to use when multi-threading requests. (will override the value from conf/browser.conf.json)
-
---username | -U <username>  Only brute force the supplied username.
-
---help     | -h This help screen.
-
---verbose  | -v Verbose output.
-
- -

WPSCAN EXAMPLES

- -

Do 'non-intrusive' checks...

- -

ruby wpscan.rb --url www.example.com

- -

Do wordlist password brute force on enumerated users using 50 threads...

- -

ruby wpscan.rb --url www.example.com --wordlist darkc0de.lst --threads 50

- -

Do wordlist password brute force on the 'admin' username only...

- -

ruby wpscan.rb --url www.example.com --wordlist darkc0de.lst --username admin

- -

Enumerate installed plugins...

- -

ruby wpscan.rb --url www.example.com --enumerate p

- -

Run all enumeration tools...

- -

ruby wpscan.rb --url www.example.com --enumerate

- -

Update WPScan...

- -

ruby wpscan.rb --update

- -

WPSTOOLS ARGUMENTS

- -
--help    | -h   This help screen.
---Verbose | -v   Verbose output.
---update  | -u   Update to the latest revision.
---generate_plugin_list [number of pages]  Generate a new data/plugins.txt file. (supply number of *pages* to parse, default : 150)
---gpl  Alias for --generate_plugin_list
-
- -

WPSTOOLS EXAMPLES

- -

Generate a new 'most popular' plugin list, up to 150 pages...

- -

ruby wpstools.rb --generate_plugin_list 150

- -

PROJECT HOME

- -

www.wpscan.org

- -

GIT REPOSITORY

- -

https://github.com/wpscanteam/wpscan

- -

ISSUES

- -

https://github.com/wpscanteam/wpscan/issues

- -

SPONSOR

- -

WPScan is sponsored by the RandomStorm Open Source Initiative.

- -
+ + diff --git a/javascripts/markdown-browser-0.6.0-beta1/markdown.js b/javascripts/markdown-browser-0.6.0-beta1/markdown.js new file mode 100644 index 00000000..65b04e46 --- /dev/null +++ b/javascripts/markdown-browser-0.6.0-beta1/markdown.js @@ -0,0 +1,1740 @@ +// Released under MIT license +// Copyright (c) 2009-2010 Dominic Baggott +// Copyright (c) 2009-2010 Ash Berlin +// Copyright (c) 2011 Christoph Dorn (http://www.christophdorn.com) +// Date: 2013-09-15T16:12Z + +(function(expose) { + + + + + var MarkdownHelpers = {}; + + // 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; + case "object": + this.dialect = dialect; + break; + default: + if ( dialect in Markdown.dialects ) + this.dialect = Markdown.dialects[dialect]; + else + throw new Error("Unknown Markdown dialect '" + String(dialect) + "'"); + break; + } + this.em_state = []; + this.strong_state = []; + this.debug_indent = ""; + }; + + /** + * Markdown.dialects + * + * Namespace of built-in dialects. + **/ + Markdown.dialects = {}; + + + + + // 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__; + + if ( "__call__" in cbs ) + return cbs.__call__.call(this, block, next); + + for ( var i = 0; i < ord.length; i++ ) { + //D:this.debug( "Testing", ord[i] ); + var res = cbs[ ord[i] ].call( this, block, next ); + if ( res ) { + //D:this.debug(" matched"); + if ( !isArray(res) || ( res.length > 0 && !( isArray(res[0]) ) ) ) + this.debug(ord[i], "didn't return a proper array"); + //D:this.debug( "" ); + return res; + } + } + + // 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#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" ]; + + 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_loop; + + this.tree.push.apply( this.tree, b ); + } + return this.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" ) + print.apply( print, args ); + 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(); + + while ( b.length && (m = re.exec(b) ) !== null ) { + b = b.substr( m[0].length ); + cb.call(this, m); + } + return b; + }; + + // 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); + }; + }; + + + + + var extract_attr = MarkdownHelpers.extract_attr; + + /** + * 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() ) ); + } + + return content.join( "\n\n" ); + }; + + + /** + * 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, "'" ); + } + + function render_tree( jsonml ) { + // basic case + if ( typeof jsonml === "string" ) + return escapeHTML( jsonml ); + + 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 = ""; + 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" ) + 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 ]; + } + attrs = jsonml[ 1 ]; + } + + // basic case + if ( typeof jsonml === "string" ) + return jsonml; + + // convert this node + switch ( jsonml[ 0 ] ) { + case "header": + jsonml[ 0 ] = "h" + jsonml[ 1 ].level; + delete jsonml[ 1 ].level; + break; + case "bulletlist": + jsonml[ 0 ] = "ul"; + break; + case "numberlist": + jsonml[ 0 ] = "ol"; + break; + case "listitem": + jsonml[ 0 ] = "li"; + break; + case "para": + jsonml[ 0 ] = "p"; + break; + case "markdown": + jsonml[ 0 ] = "html"; + if ( attrs ) + delete attrs.references; + break; + case "code_block": + jsonml[ 0 ] = "pre"; + i = attrs ? 2 : 1; + var code = [ "code" ]; + code.push.apply( code, jsonml.splice( i, jsonml.length - i ) ); + jsonml[ i ] = code; + break; + case "inlinecode": + jsonml[ 0 ] = "code"; + break; + case "img": + jsonml[ 1 ].src = jsonml[ 1 ].href; + delete jsonml[ 1 ].href; + break; + case "linebreak": + jsonml[ 0 ] = "br"; + break; + case "link": + jsonml[ 0 ] = "a"; + break; + case "link_ref": + jsonml[ 0 ] = "a"; + + // grab this ref and clean up the attribute node + var ref = references[ attrs.ref ]; + + // if the reference exists, make the link + if ( ref ) { + delete attrs.ref; + + // add in the href and title, if present + attrs.href = ref.href; + if ( ref.title ) + attrs.title = ref.title; + + // get rid of the unneeded original text + delete attrs.original; + } + // the reference doesn't exist, so revert to plain text + else { + return attrs.original; + } + break; + case "img_ref": + jsonml[ 0 ] = "img"; + + // grab this ref and clean up the attribute node + var ref = references[ attrs.ref ]; + + // if the reference exists, make the link + if ( ref ) { + delete attrs.ref; + + // add in the href and title, if present + attrs.src = ref.href; + if ( ref.title ) + attrs.title = ref.title; + + // get rid of the unneeded original text + delete attrs.original; + } + // the reference doesn't exist, so revert to plain text + else { + return attrs.original; + } + break; + } + + // 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 ] ) { + 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 ]; + } + else { + ++i; + } + } + // if it's not a string recurse + else { + merge_text_nodes( jsonml[ i ] ); + ++i; + } + } + }; + + + + 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 }, 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 ); + // 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( /^ / ) ) { + 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; + } + + // Make sure all listitems up the stack are paragraphs + forEach( stack, paragraphify, this); + + loose = true; + continue loose_search; + } + break; + } // loose_search + + return ret; + }; + })(), + + blockquote: function blockquote( block, next ) { + 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; + + // make an attribute node if it doesn't exist + 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 = {}; + + var b = this.loop_re_over_block(re, block, function( 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]; + + } ); + + 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 + var m = 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]; + 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 ]; + } + + // [id] + // Only if id is plain (no formatting.) + if ( children.length === 1 && typeof children[0] === "string" ) { + + attrs = { ref: children[0].toLowerCase(), 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 ) { + // 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" ] ]; + } + + } + }; + + // Meta Helper/generator method for em and strong handling + function strong_em( tag, md ) { + + var state_slot = tag + "_state", + other_slot = tag === "strong" ? "em_state" : "strong_state"; + + function CloseTag(len) { + this.len_after = len; + this.name = "close_" + md; + } + + return function ( text ) { + + if ( this[state_slot][0] === md ) { + // Most recent em is of this type + //D:this.debug("closing", md); + this[state_slot].shift(); + + // "Consume" everything to go back to the recrusion in the else-block below + return[ text.length, new CloseTag(text.length-md.length) ]; + } + else { + // Store a clone of the em/strong states + var other = this[other_slot].slice(), + state = this[state_slot].slice(); + + this[state_slot].unshift(md); + + //D:this.debug_indent += " "; + + // Recurse + var res = this.processInline( text.substr( md.length ) ); + //D:this.debug_indent = this.debug_indent.substr(2); + + var last = res[res.length - 1]; + + //D:this.debug("processInline from", tag + ": ", uneval( res ) ); + + var check = this[state_slot].shift(); + if ( last instanceof CloseTag ) { + res.pop(); + // We matched! Huzzah. + var consumed = text.length - last.len_after; + return [ consumed, [ tag ].concat(res) ]; + } + else { + // Restore the state of the other kind. We might have mistakenly closed it. + this[other_slot] = other; + this[state_slot] = state; + + // We can't reuse the processed result as it could have wrong parsing contexts in it. + return [ md.length, md ]; + } + } + }; // End returned function + } + + Gruber.inline["**"] = strong_em("strong", "**"); + Gruber.inline["__"] = strong_em("strong", "__"); + Gruber.inline["*"] = strong_em("em", "*"); + Gruber.inline["_"] = strong_em("em", "_"); + + Markdown.dialects.Gruber = Gruber; + Markdown.buildBlockOrder ( Markdown.dialects.Gruber.block ); + Markdown.buildInlinePatterns( Markdown.dialects.Gruber.inline ); + + + + var Maruku = DialectHelpers.subclassDialect( Gruber ), + extract_attr = MarkdownHelpers.extract_attr, + forEach = MarkdownHelpers.forEach; + + Maruku.processMetaHash = function processMetaHash( meta_string ) { + var meta = split_meta_hash( meta_string ), + attr = {}; + + for ( var i = 0; i < meta.length; ++i ) { + // id: #foo + if ( /^#/.test( meta[ i ] ) ) + attr.id = meta[ i ].substring( 1 ); + // class: .foo + else if ( /^\./.test( meta[ i ] ) ) { + // if class already exists, append the new one + if ( attr["class"] ) + attr["class"] = attr["class"] + meta[ i ].replace( /./, " " ); + else + attr["class"] = meta[ i ].substring( 1 ); + } + // attribute: foo=bar + else if ( /\=/.test( meta[ i ] ) ) { + var s = meta[ i ].split( /\=/ ); + attr[ s[ 0 ] ] = s[ 1 ]; + } + } + + return attr; + }; + + function split_meta_hash( meta_string ) { + var meta = meta_string.split( "" ), + parts = [ "" ], + in_quotes = false; + + while ( meta.length ) { + var letter = meta.shift(); + switch ( letter ) { + case " " : + // if we're in a quoted section, keep it + if ( in_quotes ) + parts[ parts.length - 1 ] += letter; + // otherwise make a new part + else + parts.push( "" ); + break; + case "'" : + case '"' : + // reverse the quotes and move straight on + in_quotes = !in_quotes; + break; + case "\\" : + // shift off the next letter to be used straight away. + // it was escaped so we'll keep it whatever it is + letter = meta.shift(); + /* falls through */ + default : + parts[ parts.length - 1 ] += letter; + break; + } + } + + return parts; + } + + Maruku.block.document_meta = function document_meta( block ) { + // we're only interested in the first block + if ( block.lineNumber > 1 ) + return undefined; + + // document_meta blocks consist of one or more lines of `Key: Value\n` + if ( ! block.match( /^(?:\w+:.*\n)*\w+:.*$/ ) ) + return undefined; + + // make an attribute node if it doesn't exist + if ( !extract_attr( this.tree ) ) + this.tree.splice( 1, 0, {} ); + + var pairs = block.split( /\n/ ); + for ( var p in pairs ) { + var m = pairs[ p ].match( /(\w+):\s*(.*)$/ ), + key = m[ 1 ].toLowerCase(), + value = m[ 2 ]; + + this.tree[ 1 ][ key ] = value; + } + + // document_meta produces no content! + return []; + }; + + Maruku.block.block_meta = function block_meta( block ) { + // check if the last line of the block is an meta hash + var m = block.match( /(^|\n) {0,3}\{:\s*((?:\\\}|[^\}])*)\s*\}$/ ); + if ( !m ) + return undefined; + + // process the meta hash + var attr = this.dialect.processMetaHash( m[ 2 ] ), + hash; + + // if we matched ^ then we need to apply meta to the previous block + if ( m[ 1 ] === "" ) { + var node = this.tree[ this.tree.length - 1 ]; + hash = extract_attr( node ); + + // if the node is a string (rather than JsonML), bail + if ( typeof node === "string" ) + return undefined; + + // create the attribute hash if it doesn't exist + if ( !hash ) { + hash = {}; + node.splice( 1, 0, hash ); + } + + // add the attributes in + for ( var a in attr ) + hash[ a ] = attr[ a ]; + + // return nothing so the meta hash is removed + return []; + } + + // pull the meta hash off the block and process what's left + var b = block.replace( /\n.*$/, "" ), + result = this.processBlock( b, [] ); + + // get or make the attributes hash + hash = extract_attr( result[ 0 ] ); + if ( !hash ) { + hash = {}; + result[ 0 ].splice( 1, 0, hash ); + } + + // attach the attributes to the block + for ( var a in attr ) + hash[ a ] = attr[ a ]; + + return result; + }; + + Maruku.block.definition_list = function definition_list( block, next ) { + // one or more terms followed by one or more definitions, in a single block + var tight = /^((?:[^\s:].*\n)+):\s+([\s\S]+)$/, + list = [ "dl" ], + i, m; + + // see if we're dealing with a tight or loose block + if ( ( m = block.match( tight ) ) ) { + // pull subsequent tight DL blocks out of `next` + var blocks = [ block ]; + while ( next.length && tight.exec( next[ 0 ] ) ) + blocks.push( next.shift() ); + + for ( var b = 0; b < blocks.length; ++b ) { + var m = blocks[ b ].match( tight ), + terms = m[ 1 ].replace( /\n$/, "" ).split( /\n/ ), + defns = m[ 2 ].split( /\n:\s+/ ); + + // print( uneval( m ) ); + + for ( i = 0; i < terms.length; ++i ) + list.push( [ "dt", terms[ i ] ] ); + + for ( i = 0; i < defns.length; ++i ) { + // run inline processing over the definition + list.push( [ "dd" ].concat( this.processInline( defns[ i ].replace( /(\n)\s+/, "$1" ) ) ) ); + } + } + } + else { + return undefined; + } + + return [ list ]; + }; + + // splits on unescaped instances of @ch. If @ch is not a character the result + // can be unpredictable + + Maruku.block.table = function table ( block ) { + + var _split_on_unescaped = function( s, ch ) { + ch = ch || '\\s'; + if ( ch.match(/^[\\|\[\]{}?*.+^$]$/) ) + ch = '\\' + ch; + var res = [ ], + r = new RegExp('^((?:\\\\.|[^\\\\' + ch + '])*)' + ch + '(.*)'), + m; + while ( ( m = s.match( r ) ) ) { + res.push( m[1] ); + s = m[2]; + } + res.push(s); + return res; + }; + + var leading_pipe = /^ {0,3}\|(.+)\n {0,3}\|\s*([\-:]+[\-| :]*)\n((?:\s*\|.*(?:\n|$))*)(?=\n|$)/, + // find at least an unescaped pipe in each line + no_leading_pipe = /^ {0,3}(\S(?:\\.|[^\\|])*\|.*)\n {0,3}([\-:]+\s*\|[\-| :]*)\n((?:(?:\\.|[^\\|])*\|.*(?:\n|$))*)(?=\n|$)/, + i, + m; + if ( ( m = block.match( leading_pipe ) ) ) { + // remove leading pipes in contents + // (header and horizontal rule already have the leading pipe left out) + m[3] = m[3].replace(/^\s*\|/gm, ''); + } else if ( ! ( m = block.match( no_leading_pipe ) ) ) { + return undefined; + } + + var table = [ "table", [ "thead", [ "tr" ] ], [ "tbody" ] ]; + + // remove trailing pipes, then split on pipes + // (no escaped pipes are allowed in horizontal rule) + m[2] = m[2].replace(/\|\s*$/, '').split('|'); + + // process alignment + var html_attrs = [ ]; + forEach (m[2], function (s) { + if (s.match(/^\s*-+:\s*$/)) + html_attrs.push({align: "right"}); + else if (s.match(/^\s*:-+\s*$/)) + html_attrs.push({align: "left"}); + else if (s.match(/^\s*:-+:\s*$/)) + html_attrs.push({align: "center"}); + else + html_attrs.push({}); + }); + + // now for the header, avoid escaped pipes + m[1] = _split_on_unescaped(m[1].replace(/\|\s*$/, ''), '|'); + for (i = 0; i < m[1].length; i++) { + table[1][1].push(['th', html_attrs[i] || {}].concat( + this.processInline(m[1][i].trim()))); + } + + // now for body contents + forEach (m[3].replace(/\|\s*$/mg, '').split('\n'), function (row) { + var html_row = ['tr']; + row = _split_on_unescaped(row, '|'); + for (i = 0; i < row.length; i++) + html_row.push(['td', html_attrs[i] || {}].concat(this.processInline(row[i].trim()))); + table[2].push(html_row); + }, this); + + return [table]; + }; + + Maruku.inline[ "{:" ] = function inline_meta( text, matches, out ) { + if ( !out.length ) + return [ 2, "{:" ]; + + // get the preceeding element + var before = out[ out.length - 1 ]; + + if ( typeof before === "string" ) + return [ 2, "{:" ]; + + // match a meta hash + var m = text.match( /^\{:\s*((?:\\\}|[^\}])*)\s*\}/ ); + + // no match, false alarm + if ( !m ) + return [ 2, "{:" ]; + + // attach the attributes to the preceeding element + var meta = this.dialect.processMetaHash( m[ 1 ] ), + attr = extract_attr( before ); + + if ( !attr ) { + attr = {}; + before.splice( 1, 0, attr ); + } + + for ( var k in meta ) + attr[ k ] = meta[ k ]; + + // cut out the string and replace it with nothing + return [ m[ 0 ].length, "" ]; + }; + + + Markdown.dialects.Maruku = Maruku; + Markdown.dialects.Maruku.inline.__escape__ = /^\\[\\`\*_{}\[\]()#\+.!\-|:]/; + Markdown.buildBlockOrder ( Markdown.dialects.Maruku.block ); + Markdown.buildInlinePatterns( Markdown.dialects.Maruku.inline ); + + +// Include all our depndencies and; + expose.Markdown = Markdown; + expose.parse = Markdown.parse; + expose.toHTML = Markdown.toHTML; + expose.toHTMLTree = Markdown.toHTMLTree; + expose.renderJsonML = Markdown.renderJsonML; + +})(function() { + window.markdown = {}; + return window.markdown; +}()); diff --git a/javascripts/markdown-browser-0.6.0-beta1/markdown.min.js b/javascripts/markdown-browser-0.6.0-beta1/markdown.min.js new file mode 100644 index 00000000..68a1b457 --- /dev/null +++ b/javascripts/markdown-browser-0.6.0-beta1/markdown.min.js @@ -0,0 +1 @@ +!function(a){function b(){return"Markdown.mk_block( "+uneval(this.toString())+", "+uneval(this.trailing)+", "+uneval(this.lineNumber)+" )"}function c(){var a=require("util");return"Markdown.mk_block( "+a.inspect(this.toString())+", "+a.inspect(this.trailing)+", "+a.inspect(this.lineNumber)+" )"}function d(a){for(var b=0,c=-1;-1!==(c=a.indexOf("\n",c+1));)b++;return b}function e(a){return a.replace(/&/g,"&").replace(//g,">").replace(/"/g,""").replace(/'/g,"'")}function f(a){if("string"==typeof a)return e(a);var b=a.shift(),c={},d=[];for(!a.length||"object"!=typeof a[0]||a[0]instanceof Array||(c=a.shift());a.length;)d.push(f(a.shift()));var g="";for(var h in c)g+=" "+h+'="'+e(c[h])+'"';return"img"===b||"br"===b||"hr"===b?"<"+b+g+"/>":"<"+b+g+">"+d.join("")+""}function g(a,b,c){var d;c=c||{};var e=a.slice(0);"function"==typeof c.preprocessTreeNode&&(e=c.preprocessTreeNode(e,b));var f=o(e);if(f){e[1]={};for(d in f)e[1][d]=f[d];f=e[1]}if("string"==typeof e)return e;switch(e[0]){case"header":e[0]="h"+e[1].level,delete e[1].level;break;case"bulletlist":e[0]="ul";break;case"numberlist":e[0]="ol";break;case"listitem":e[0]="li";break;case"para":e[0]="p";break;case"markdown":e[0]="html",f&&delete f.references;break;case"code_block":e[0]="pre",d=f?2:1;var h=["code"];h.push.apply(h,e.splice(d,e.length-d)),e[d]=h;break;case"inlinecode":e[0]="code";break;case"img":e[1].src=e[1].href,delete e[1].href;break;case"linebreak":e[0]="br";break;case"link":e[0]="a";break;case"link_ref":e[0]="a";var i=b[f.ref];if(!i)return f.original;delete f.ref,f.href=i.href,i.title&&(f.title=i.title),delete f.original;break;case"img_ref":e[0]="img";var i=b[f.ref];if(!i)return f.original;delete f.ref,f.src=i.href,i.title&&(f.title=i.title),delete f.original}if(d=1,f){for(var j in e[1]){d=2;break}1===d&&e.splice(d,1)}for(;d1&&"object"==typeof a[1]&&!l(a[1])?a[1]:void 0};var m=function(a){switch(typeof a){case"undefined":this.dialect=m.dialects.Gruber;break;case"object":this.dialect=a;break;default:if(!(a in m.dialects))throw new Error("Unknown Markdown dialect '"+String(a)+"'");this.dialect=m.dialects[a]}this.em_state=[],this.strong_state=[],this.debug_indent=""};m.dialects={};var n=m.mk_block=k.mk_block,l=k.isArray;m.parse=function(a,b){var c=new m(b);return c.toTree(a)},m.prototype.split_blocks=function(a){a=a.replace(/(\r\n|\n|\r)/g,"\n");var b,c=/([\s\S]+?)($|\n#|\n(?:\s*\n|$)+)/g,e=[],f=1;for(null!==(b=/^(\s*\n)/.exec(a))&&(f+=d(b[0]),c.lastIndex=b[0].length);null!==(b=c.exec(a));)"\n#"===b[2]&&(b[2]="\n",c.lastIndex--),e.push(n(b[1],b[2],f)),f+=d(b[0]);return e},m.prototype.processBlock=function(a,b){var c=this.dialect.block,d=c.__order__;if("__call__"in c)return c.__call__.call(this,a,b);for(var e=0;e0&&!l(f[0]))&&this.debug(d[e],"didn't return a proper array"),f}return[]},m.prototype.processInline=function(a){return this.dialect.inline.__call__.call(this,String(a))},m.prototype.toTree=function(a,b){var c=a instanceof Array?a:this.split_blocks(a),d=this.tree;try{for(this.tree=b||this.tree||["markdown"];c.length;){var e=this.processBlock(c.shift(),c);e.length&&this.tree.push.apply(this.tree,e)}return this.tree}finally{b&&(this.tree=d)}},m.prototype.debug=function(){var a=Array.prototype.slice.call(arguments);a.unshift(this.debug_indent),"undefined"!=typeof print&&print.apply(print,a),"undefined"!=typeof console&&"undefined"!=typeof console.log&&console.log.apply(null,a)},m.prototype.loop_re_over_block=function(a,b,c){for(var d,e=b.valueOf();e.length&&null!==(d=a.exec(e));)e=e.substr(d[0].length),c.call(this,d);return e},m.buildBlockOrder=function(a){var b=[];for(var c in a)"__order__"!==c&&"__call__"!==c&&b.push(c);a.__order__=b},m.buildInlinePatterns=function(a){var b=[];for(var c in a)if(!c.match(/^__.*__$/)){var d=c.replace(/([\\.*+?|()\[\]{}])/g,"\\$1").replace(/\n/,"\\n");b.push(1===c.length?d:"(?:"+d+")")}b=b.join("|"),a.__patterns__=b;var e=a.__call__;a.__call__=function(a,c){return void 0!==c?e.call(this,a,c):e.call(this,a,b)}};var o=k.extract_attr;m.renderJsonML=function(a,b){b=b||{},b.root=b.root||!1;var c=[];if(b.root)c.push(f(a));else for(a.shift(),!a.length||"object"!=typeof a[0]||a[0]instanceof Array||a.shift();a.length;)c.push(f(a.shift()));return c.join("\n\n")},m.toHTMLTree=function(a,b,c){"string"==typeof a&&(a=this.parse(a,b));var d=o(a),e={};d&&d.references&&(e=d.references);var f=g(a,e,c);return h(f),f},m.toHTML=function(a,b,c){var d=this.toHTMLTree(a,b,c);return this.renderJsonML(d)};var p={};p.inline_until_char=function(a,b){for(var c=0,d=[];;){if(a.charAt(c)===b)return c++,[c,d];if(c>=a.length)return null;var e=this.dialect.inline.__oneElement__.call(this,a.substr(c));c+=e[0],d.push.apply(d,e.slice(1))}},p.subclassDialect=function(a){function b(){}function c(){}return b.prototype=a.block,c.prototype=a.inline,{block:new b,inline:new c}};var q=k.forEach,o=k.extract_attr,n=k.mk_block,r=k.isEmpty,s=p.inline_until_char,t={block:{atxHeader:function(a,b){var c=a.match(/^(#{1,6})\s*(.*?)\s*#*\s*(?:\n|$)/);if(!c)return void 0;var d=["header",{level:c[1].length}];return Array.prototype.push.apply(d,this.processInline(c[2])),c[0].length1&&c.unshift(d);for(var f=0;f1&&"string"==typeof e[e.length-1]?e[e.length-1]+=g:e.push(g)}}function d(a,b){for(var c=new RegExp("^("+i+"{"+a+"}.*?\\n?)*$"),d=new RegExp("^"+i+"{"+a+"}","gm"),e=[];b.length>0&&c.exec(b[0]);){var f=b.shift(),g=f.replace(d,"");e.push(n(g,f.trailing,f.lineNumber))}return e}function e(a,b,c){var d=a.list,e=d[d.length-1];if(!(e[1]instanceof Array&&"para"===e[1][0]))if(b+1===c.length)e.push(["para"].concat(e.splice(1,e.length-1)));else{var f=e.pop();e.push(["para"].concat(e.splice(1,e.length-1)),f)}}var f="[*+-]|\\d+\\.",g=/[*+-]/,h=new RegExp("^( {0,3})("+f+")[ ]+"),i="(?: {0,3}\\t| {4})";return function(f,i){function j(a){var b=g.exec(a[2])?["bulletlist"]:["numberlist"];return n.push({list:b,indent:a[1]}),b}var k=f.match(h);if(!k)return void 0;for(var l,m,n=[],o=j(k),p=!1,r=[n[0].list];;){for(var s=f.split(/(?=\n)/),t="",u="",v=0;vn.length)o=j(k),l.push(o),l=o[1]=["listitem"];else{var z=!1;for(m=0;mk[0].length&&(t+=u+w.substr(k[0].length))}t.length&&(c(l,p,this.processInline(t),u),p=!1,t="");var A=d(n.length,i);A.length>0&&(q(n,e,this),l.push.apply(l,this.toTree(A,[])));var B=i[0]&&i[0].valueOf()||"";if(!B.match(h)&&!B.match(/^ /))break;f=i.shift();var C=this.dialect.block.horizRule(f,i);if(C){r.push.apply(r,C);break}q(n,e,this),p=!0}return r}}(),blockquote:function(a,b){if(!a.match(/^>/m))return void 0;var c=[];if(">"!==a[0]){for(var d=a.split(/\n/),e=[],f=a.lineNumber;d.length&&">"!==d[0][0];)e.push(d.shift()),f++;var g=n(e.join("\n"),"\n",a.lineNumber);c.push.apply(c,this.processBlock(g,[])),a=n(d.join("\n"),a.trailing,f)}for(;b.length&&">"===b[0][0];){var h=b.shift();a=n(a+a.trailing+h,h.trailing,a.lineNumber)}var i=a.replace(/^> ?/gm,""),j=(this.tree,this.toTree(i,["blockquote"])),k=o(j);return k&&k.references&&(delete k.references,r(k)&&j.splice(1,1)),c.push(j),c},referenceDefn:function(a,b){var c=/^\s*\[(.*?)\]:\s*(\S+)(?:\s+(?:(['"])(.*?)\3|\((.*?)\)))?\n?/;if(!a.match(c))return void 0;o(this.tree)||this.tree.splice(1,0,{});var d=o(this.tree);void 0===d.references&&(d.references={});var e=this.loop_re_over_block(c,a,function(a){a[2]&&"<"===a[2][0]&&">"===a[2][a[2].length-1]&&(a[2]=a[2].substring(1,a[2].length-1));var b=d.references[a[1].toLowerCase()]={href:a[2]};void 0!==a[4]?b.title=a[4]:void 0!==a[5]&&(b.title=a[5])});return e.length&&b.unshift(n(e,a.trailing)),[]},para:function(a){return[["para"].concat(this.processInline(a))]}},inline:{__oneElement__:function(a,b,c){var d,e;b=b||this.dialect.inline.__patterns__;var f=new RegExp("([\\s\\S]*?)("+(b.source||b)+")");if(d=f.exec(a),!d)return[a.length,a];if(d[1])return[d[1].length,d[1]];var e;return d[2]in this.dialect.inline&&(e=this.dialect.inline[d[2]].call(this,a.substr(d.index),d,c||[])),e=e||[d[2].length,d[2]]},__call__:function(a,b){function c(a){"string"==typeof a&&"string"==typeof e[e.length-1]?e[e.length-1]+=a:e.push(a)}for(var d,e=[];a.length>0;)d=this.dialect.inline.__oneElement__.call(this,a,b,e),a=a.substr(d.shift()),q(d,c);return e},"]":function(){},"}":function(){},__escape__:/^\\[\\`\*_{}\[\]()#\+.!\-]/,"\\":function(a){return this.dialect.inline.__escape__.exec(a)?[2,a.charAt(1)]:[1,"\\"]},"![":function(a){var b=a.match(/^!\[(.*?)\][ \t]*\([ \t]*([^")]*?)(?:[ \t]+(["'])(.*?)\3)?[ \t]*\)/);if(b){b[2]&&"<"===b[2][0]&&">"===b[2][b[2].length-1]&&(b[2]=b[2].substring(1,b[2].length-1)),b[2]=this.dialect.inline.__call__.call(this,b[2],/\\/)[0];var c={alt:b[1],href:b[2]||""};return void 0!==b[4]&&(c.title=b[4]),[b[0].length,["img",c]]}return b=a.match(/^!\[(.*?)\][ \t]*\[(.*?)\]/),b?[b[0].length,["img_ref",{alt:b[1],ref:b[2].toLowerCase(),original:b[0]}]]:[2,"!["]},"[":function v(a){var b=String(a),c=s.call(this,a.substr(1),"]");if(!c)return[1,"["];var v,d,e=1+c[0],f=c[1];a=a.substr(e);var g=a.match(/^\s*\([ \t]*([^"']*)(?:[ \t]+(["'])(.*?)\2)?[ \t]*\)/);if(g){var h=g[1];if(e+=g[0].length,h&&"<"===h[0]&&">"===h[h.length-1]&&(h=h.substring(1,h.length-1)),!g[3])for(var i=1,j=0;j]+)|(.*?@.*?\.[a-zA-Z]+))>/))?b[3]?[b[0].length,["link",{href:"mailto:"+b[3]},b[3]]]:"mailto"===b[2]?[b[0].length,["link",{href:b[1]},b[1].substr("mailto:".length)]]:[b[0].length,["link",{href:b[1]},b[1]]]:[1,"<"]},"`":function(a){var b=a.match(/(`+)(([\s\S]*?)\1)/);return b&&b[2]?[b[1].length+b[2].length,["inlinecode",b[3]]]:[1,"`"]}," \n":function(){return[3,["linebreak"]]}}};t.inline["**"]=i("strong","**"),t.inline.__=i("strong","__"),t.inline["*"]=i("em","*"),t.inline._=i("em","_"),m.dialects.Gruber=t,m.buildBlockOrder(m.dialects.Gruber.block),m.buildInlinePatterns(m.dialects.Gruber.inline);var u=p.subclassDialect(t),o=k.extract_attr,q=k.forEach;u.processMetaHash=function(a){for(var b=j(a),c={},d=0;d1)return void 0;if(!a.match(/^(?:\w+:.*\n)*\w+:.*$/))return void 0;o(this.tree)||this.tree.splice(1,0,{});var b=a.split(/\n/);for(var c in b){var d=b[c].match(/(\w+):\s*(.*)$/),e=d[1].toLowerCase(),f=d[2];this.tree[1][e]=f}return[]},u.block.block_meta=function(a){var b=a.match(/(^|\n) {0,3}\{:\s*((?:\\\}|[^\}])*)\s*\}$/);if(!b)return void 0;var c,d=this.dialect.processMetaHash(b[2]);if(""===b[1]){var e=this.tree[this.tree.length-1];if(c=o(e),"string"==typeof e)return void 0;c||(c={},e.splice(1,0,c));for(var f in d)c[f]=d[f];return[]}var g=a.replace(/\n.*$/,""),h=this.processBlock(g,[]);c=o(h[0]),c||(c={},h[0].splice(1,0,c));for(var f in d)c[f]=d[f];return h},u.block.definition_list=function(a,b){var c,d,e=/^((?:[^\s:].*\n)+):\s+([\s\S]+)$/,f=["dl"];if(!(d=a.match(e)))return void 0;for(var g=[a];b.length&&e.exec(b[0]);)g.push(b.shift());for(var h=0;h