From 2b8a9a835821f64fccfc7b571a7c4fb99328f684 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=A9my=20Lal?= Date: Sun, 11 Jul 2010 23:50:24 +0200 Subject: [PATCH] Use ronnjs 0.2 to generate docs. Small cosmetic change. --- LICENSE | 5 + Makefile | 6 +- doc/api_header.html | 2 - tools/ronnjs/CHANGES | 12 + tools/ronnjs/LICENSE | 62 ++ tools/ronnjs/README | 25 + tools/ronnjs/TODO | 7 + tools/ronnjs/bin/ronn.js | 102 +++ tools/ronnjs/lib/ext/markdown.js | 1454 ++++++++++++++++++++++++++++++ tools/ronnjs/lib/ext/opts.js | 268 ++++++ tools/ronnjs/lib/ronn.js | 321 +++++++ 11 files changed, 2259 insertions(+), 5 deletions(-) create mode 100644 tools/ronnjs/CHANGES create mode 100644 tools/ronnjs/LICENSE create mode 100644 tools/ronnjs/README create mode 100644 tools/ronnjs/TODO create mode 100755 tools/ronnjs/bin/ronn.js create mode 100644 tools/ronnjs/lib/ext/markdown.js create mode 100755 tools/ronnjs/lib/ext/opts.js create mode 100644 tools/ronnjs/lib/ronn.js diff --git a/LICENSE b/LICENSE index f83efa6c24..7b72de0719 100644 --- a/LICENSE +++ b/LICENSE @@ -28,6 +28,11 @@ are: - HTTP Parser, located at deps/http_parser, is a small C library copyrighted by Ryan Lienhart Dahl and has a MIT license. + - RonnJS, located at tools/ronnjs, is a library that generates man pages + and HTML from markdown. RonnJS is released under an MIT-style license + and has copyrights from Jérémy Lal, Ryan Tomayko, Dominic Baggott, Ash + Berlin, and Joey Mazzarelli. + Node's license follows: diff --git a/Makefile b/Makefile index ac65b39fad..f0f6e2d7a4 100644 --- a/Makefile +++ b/Makefile @@ -44,8 +44,8 @@ benchmark: all doc: doc/node.1 doc/api.html doc/index.html doc/changelog.html ## HACK to give the ronn-generated page a TOC -doc/api.html: doc/api.markdown doc/api_header.html doc/api_footer.html - ronn -f --html doc/api.markdown \ +doc/api.html: all doc/api.markdown doc/api_header.html doc/api_footer.html + build/default/node tools/ronnjs/bin/ronn.js --fragment doc/api.markdown \ | sed "s/

\(.*\)<\/h2>/

\1<\/h2>/g" \ | cat doc/api_header.html - doc/api_footer.html > doc/api.html @@ -53,7 +53,7 @@ doc/changelog.html: ChangeLog doc/changelog_header.html doc/changelog_footer.htm cat doc/changelog_header.html ChangeLog doc/changelog_footer.html > doc/changelog.html doc/node.1: doc/api.markdown - ronn --roff doc/api.markdown > doc/node.1 + build/default/node tools/ronnjs/bin/ronn.js --roff doc/api.markdown > doc/node.1 website-upload: doc scp doc/* ryan@nodejs.org:~/tinyclouds/node/ diff --git a/doc/api_header.html b/doc/api_header.html index 1b989fe571..7414bd91f0 100644 --- a/doc/api_header.html +++ b/doc/api_header.html @@ -300,8 +300,6 @@
-

node(1)

-
  1. node(1)
    2. diff --git a/tools/ronnjs/CHANGES b/tools/ronnjs/CHANGES new file mode 100644 index 0000000000..581617998d --- /dev/null +++ b/tools/ronnjs/CHANGES @@ -0,0 +1,12 @@ +Ronnjs Changes and Release Notes +============================== + +Version 0.2 +------------------------------ + +Supports output to html fragment. + +Version 0.1 +------------------------------ + +Initial release. diff --git a/tools/ronnjs/LICENSE b/tools/ronnjs/LICENSE new file mode 100644 index 0000000000..f9d7162531 --- /dev/null +++ b/tools/ronnjs/LICENSE @@ -0,0 +1,62 @@ +Ronnjs is a javascript port of Ronn, which is an original +work of Ryan Tomayko. + +Copyright: 2009 Ryan Tomayko +License: MIT + +Files: bin/ronn.js, lib/ronn.js +Copyright: 2010 Jérémy Lal +License : MIT + +Files: lib/ext/markdown.js +Copyright: 2009-2010 Dominic Baggott, 2009-2010 Ash Berlin +License: MIT + +Files: lib/ext/opts.js +Copyright: 2010 Joey Mazzarelli . All rights reserved. +License: Simplified BSD License + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions are met: + + 1. Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + 2. Redistributions in binary form must reproduce the above copyright notice, + this list of conditions and the following disclaimer in the documentation + and/or other materials provided with the distribution. + + THIS SOFTWARE IS PROVIDED BY JOEY MAZZARELLI 'AS IS' AND ANY EXPRESS OR IMPLIED + WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO + EVENT SHALL JOEY MAZZARELLI OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, + INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR + PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE + OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + + The views and conclusions contained in the software and documentation are those + of the authors and should not be interpreted as representing official policies, + either expressed or implied, of Joey Mazzarelli. + +License: MIT + Permission is hereby granted, free of charge, to any person + obtaining a copy of this software and associated documentation + files (the "Software"), to deal in the Software without restriction, + including without limitation the rights to use, copy, modify, + merge, publish, distribute, sublicense, and/or sell copies of + the Software, and to permit persons to whom the Software is furnished + to do so, subject to the following conditions: + + The above copyright notice and this permission notice shall be + included in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + SOFTWARE. diff --git a/tools/ronnjs/README b/tools/ronnjs/README new file mode 100644 index 0000000000..87474a4148 --- /dev/null +++ b/tools/ronnjs/README @@ -0,0 +1,25 @@ +ronnjs(1) -- markdown to roff converter +======================================= + +## Synopsis + +Javascript port of [ronn], using [markdown-js] to produce roff man pages. +Not fully compatible with [ronn], although it aims to be, wherever possible. + +## Usage + +This outputs doc.roff from a markdown file : + + ronn.js --build --roff doc.md + +Command-line options are listed with -h + + +## How it works ? + +[markdown-js] parses markdown text to a document model, which in turn is +used to ouput a man page. + + +[ronn]: http://github.com/rtomayko/ronn +[markdown-js]: http://github.com/evilstreak/markdown-js diff --git a/tools/ronnjs/TODO b/tools/ronnjs/TODO new file mode 100644 index 0000000000..fe65eed014 --- /dev/null +++ b/tools/ronnjs/TODO @@ -0,0 +1,7 @@ +# TODO + +* show
    tags using something like + \l'\n(.lu*8u/10u' + and take care of the current indentation. + +* tests ! diff --git a/tools/ronnjs/bin/ronn.js b/tools/ronnjs/bin/ronn.js new file mode 100755 index 0000000000..5087b8e2f1 --- /dev/null +++ b/tools/ronnjs/bin/ronn.js @@ -0,0 +1,102 @@ +#!/usr/bin/nodejs + +var opts = require(__dirname + '/../lib/ext/opts'); +var ronn = require(__dirname + '/../lib/ronn'); + +var options = [ + { short : 'V' + , description : 'Show version and exit' + , callback : function () { sys.puts('0.1'); process.exit(1); } + }, + { short : 'b' + , long : 'build' + , description : 'Output to files with appropriate extension' + }, + { short : 'm' + , long : 'man' + , description : 'Convert to roff and open with man' + }, + { short : 'r' + , long : 'roff' + , description : 'Convert to roff format' + }, + { short : '5' + , long : 'html' + , description : 'Convert to html format' + }, + { short : 'f' + , long : 'fragment' + , description : 'Convert to html fragment format' + }, + { long : 'manual' + , description : 'Set "manual" attribute' + , value : true + }, + { long : 'version' + , description : 'Set "version" attribute' + , value : true + }, + { long : 'date' + , description : 'Set "date" attribute' + , value : true + } +]; +var arguments = [ + { name : 'file' + , required : true + , description: 'A ronn file' + } +]; +opts.parse(options, arguments, true); + + +var sys = require('sys'); +var fs = require('fs'); +var path = require('path'); + +var fPath = opts.arg('file'); +var fBase = path.join(path.dirname(fPath), path.basename(fPath, path.extname(fPath))); + +var fTxt = fs.readFileSync(fPath, 'utf8'); +var ronn = new ronn.Ronn(fTxt, opts.get("version"), opts.get("manual"), opts.get("date")); + +if (opts.get("man") && !opts.get("build")) { + var spawn = require('child_process').spawn; + var man = spawn('man', ['--warnings', '-E UTF-8', '-l', '-'], {"LANG":"C"}); + man.stdout.addListener('data', function (data) { + sys.puts(data); + }); + man.stderr.addListener('data', function (data) { + sys.puts(data); + }); + man.addListener('exit', function() { + process.exit(0); + }); + man.stdin.write(ronn.roff(), 'utf8'); + man.stdin.end(); +} else { + var fRoff = null; + var fHtml = null; + var fFrag = null; + if (!opts.get("html") && !opts.get("fragment")) fRoff = ronn.roff(); + else { + if (opts.get("roff")) fRoff = ronn.roff(); + if (opts.get("html")) fHtml = ronn.html(); + if (opts.get("fragment")) { + if (opts.get("html")) { + sys.debug("Can't use both --fragment and --html"); + process.exit(-1); + } + fFrag = ronn.fragment(); + } + } + if (opts.get("build")) { + if (fRoff) fs.writeFileSync(fBase + ".roff", fRoff, 'utf8'); + if (fHtml) fs.writeFileSync(fBase + ".html", fHtml, 'utf8'); + if (fFrag) fs.writeFileSync(fBase + ".fragment", fFrag, 'utf8'); + } else { + if (fRoff) sys.puts(fRoff); + if (fHtml) sys.puts(fHtml); + if (fFrag) sys.puts(fFrag); + } +} diff --git a/tools/ronnjs/lib/ext/markdown.js b/tools/ronnjs/lib/ext/markdown.js new file mode 100644 index 0000000000..f46f59533d --- /dev/null +++ b/tools/ronnjs/lib/ext/markdown.js @@ -0,0 +1,1454 @@ +// Released under MIT license +// Copyright (c) 2009-2010 Dominic Baggott +// Copyright (c) 2009-2010 Ash Berlin + +(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 Markdown = expose.Markdown = function Markdown(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 = ""; +} + +/** + * 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 ) -> 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 ) { + var input = expose.toHTMLTree( source ); + + 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 ) { + // 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 ); + merge_text_nodes( html ); + return html; +} + +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.toSource = function() { + return "Markdown.mk_block( " + + uneval(block) + + ", " + + uneval(trail) + + ", " + + uneval(line) + + " )" + } + + 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 ) { + // [\s\S] matches _anything_ (newline or space) + var re = /([\s\S]+?)($|\n(?:\s*\n|$)+)/g, + blocks = [], + m; + + var line_no = 1; + + if ( ( m = (/^(\s*\n)/)(input) ) != null ) { + // skip (but count) leading blank lines + line_no += count_lines( m[0] ); + re.lastIndex = m[0].length; + } + + while ( ( m = re(input) ) != null ) { + 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 cvs.__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 ( !res instanceof Array || ( res.length > 0 && !( res[0] instanceof Array ) ) ) + 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: + 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; + + 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); + print.apply( print, 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(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|$)/ ); + + if ( !m ) return undefined; + + var header = [ "header", { level: m[ 1 ].length }, m[ 2 ] ]; + + if ( m[0].length < block.length ) + next.unshift( mk_block( block.substr( m[0].length ), block.trailing, block.lineNumber + 2 ) ); + + return [ header ]; + }, + + setextHeader: function setextHeader( block, next ) { + var m = block.match( /^(.*)\n([-=])\2\2+(?:\n|$)/ ); + + if ( !m ) return undefined; + + var level = ( m[ 2 ] === "=" ) ? 1 : 2; + var header = [ "header", { level : level }, 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 + var m = block.match( re ); + + if ( !m ) 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 + var m = next[0].match( re ); + + if ( !m ) 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
  2. ) and loose lists, + // which have an empty line between list items, resulting in (one or more) + // paragraphs inside the
  3. . + // + // 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( blocks[0] ) ) { + var b = blocks.shift(), + // Now remove that indent + x = b.replace( replace, ""); + + ret.push( mk_block( x, b.trailing, b.lineNumber ) ); + } + 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) ) ); + } + else { + var sublist = last_li.pop(); + last_li.push( ["para"].concat( last_li.splice(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( 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 ]; + + // 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 = stack.some(function(s, i) { + if ( s.indent != m[1] ) return false; + list = s.list; // Found the level we want + stack.splice(i+1); // Remove the others + //print("found"); + return true; // And stop looping + }); + + if (!found) { + //print("not found. l:", uneval(l)); + wanted_depth++; + if (wanted_depth <= stack.length) { + stack.splice(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 + stack.forEach( 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 + stack.forEach( 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 + if ( block[ 0 ] != ">" ) { + var lines = block.split( /\n/ ), + prev = []; + + // keep shifting lines until you find a crotchet + while ( lines.length && lines[ 0 ][ 0 ] != ">" ) { + prev.push( lines.shift() ); + } + + // reassemble! + block = lines.join( "\n" ); + jsonml.push.apply( jsonml, this.processBlock( prev.join( "\n" ), [] ) ); + } + + // if the next block is also a blockquote merge it in + while ( next.length && next[ 0 ][ 0 ] == ">" ) { + var b = next.shift(); + block += block.trailing + b; + block.trailing = b.trailing; + } + + // Strip off the leading "> " and re-process as a block. + var input = block.replace( /^> ?/gm, '' ), + old_tree = this.tree; + jsonml.push( this.toTree( input, [ "blockquote" ] ) ); + + 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, next ) { + // everything's a para! + return [ ["para"].concat( this.processInline( block ) ) ]; + } + } +} + +Markdown.dialects.Gruber.inline = { + __call__: function inline( text, patterns ) { + // Hmmm - should this function be directly in Md#processInline, or + // conversely, should Md#processBlock be moved into block.__call__ too + var out = [ ], + m, + // Look for the next occurange of a special character/pattern + re = new RegExp( "([\\s\\S]*?)(" + (patterns.source || patterns) + ")", "g" ), + lastIndex = 0; + + //D:var self = this; + //D:self.debug("processInline:", uneval(text) ); + 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 ( ( m = re.exec(text) ) != null) { + if ( m[1] ) add( m[1] ); // Some un-interesting text matched + else m[1] = { length: 0 }; // Or there was none, but make m[1].length == 0 + + var res; + if ( m[2] in this.dialect.inline ) { + res = this.dialect.inline[ m[2] ].call( + this, + text.substr( m.index + m[1].length ), m, out ); + } + // Default for now to make dev easier. just slurp special and output it. + res = res || [ m[2].length, m[2] ]; + + var len = res.shift(); + // Update how much input was consumed + re.lastIndex += ( len - m[2].length ); + + // Add children + res.forEach(add); + + lastIndex = re.lastIndex; + } + + // Add last 'boring' chunk + if ( text.length > lastIndex ) + add( text.substr( lastIndex ) ); + + return out; + }, + + "\\": function escaped( text ) { + // [ length of input processed, node/children to add... ] + // Only esacape: \ ` * _ { } [ ] ( ) # * + - . ! + if ( text.match( /^\\[\\`\*_{}\[\]()#\+.!\-]/ ) ) + return [ 2, text[1] ]; + else + // Not an esacpe + return [ 1, "\\" ]; + }, + + "![": function image( text ) { + // ![Alt text](/path/to/img.jpg "Optional title") + // 1 2 3 4 <--- captures + var m = text.match( /^!\[(.*?)\][ \t]*\([ \t]*(\S*)(?:[ \t]+(["'])(.*?)\3)?[ \t]*\)/ ); + + 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(), text: m[0] } ] ]; + } + + // Just consume the '![' + return [ 2, "![" ]; + }, + + "[": function link( text ) { + // [link text](/path/to/img.jpg "Optional title") + // 1 2 3 4 <--- captures + var m = text.match( /^\[([\s\S]*?)\][ \t]*\([ \t]*(\S+)(?:[ \t]+(["'])(.*?)\3)?[ \t]*\)/ ); + + if ( m ) { + if ( m[2] && m[2][0] == '<' && m[2][m[2].length-1] == '>' ) + m[2] = m[2].substring( 1, m[2].length - 1 ); + + // Process escapes only + m[2] = this.dialect.inline.__call__.call( this, m[2], /\\/ )[0]; + + var attrs = { href: m[2] || "" }; + if ( m[4] !== undefined) + attrs.title = m[4]; + + return [ m[0].length, [ "link", attrs, m[1] ] ]; + } + + // [Alt text][id] + // [Alt text] [id] + // [id] + m = text.match( /^\[([\s\S]*?)\](?: ?\[(.*?)\])?/ ); + + if ( m ) { + // [id] case, text == id + if ( m[2] === undefined || m[2] === "" ) m[2] = m[1]; + + // 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 [ + m[ 0 ].length, + [ + "link_ref", + { + ref: m[ 2 ].toLowerCase(), + original: m[ 0 ] + }, + m[ 1 ] + ] + ]; + } + + // 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( text ) { + 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, orig_match ) { + + 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 +} + +Markdown.dialects.Gruber.inline["**"] = strong_em("strong", "**"); +Markdown.dialects.Gruber.inline["__"] = strong_em("strong", "__"); +Markdown.dialects.Gruber.inline["*"] = strong_em("em", "*"); +Markdown.dialects.Gruber.inline["_"] = strong_em("em", "_"); + + +// 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 ) { + if (i == "__call__") continue; + var l = i.replace( /([\\.*+?|()\[\]{}])/g, "\\$1" ) + .replace( /\n/, "\\n" ); + patterns.push( i.length == 1 ? l : "(?:" + l + ")" ); + } + + patterns = patterns.join("|"); + //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); + } +} + +// 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 ); + +Markdown.dialects.Maruku = Markdown.subclassDialect( Markdown.dialects.Gruber ); + +Markdown.dialects.Maruku.block.document_meta = function document_meta( block, next ) { + // 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+:.*$/ ) ) return undefined; + + // make an attribute node if it doesn't exist + if ( !extract_attr( this.tree ) ) { + this.tree.splice( 1, 0, {} ); + } + + var pairs = block.split( /\n/ ); + for ( p in pairs ) { + var m = pairs[ p ].match( /(\w+):\s*(.*)$/ ), + key = m[ 1 ].toLowerCase(), + value = m[ 2 ]; + + this.tree[ 1 ][ key ] = value; + } + + // document_meta produces no content! + return []; +} + +Markdown.dialects.Maruku.block.block_meta = function block_meta( block, next ) { + // check if the last line of the block is an meta hash + var m = block.match( /(^|\n) {0,3}\{:\s*((?:\\\}|[^\}])*)\s*\}$/ ); + if ( !m ) return undefined; + + // process the meta hash + var attr = process_meta_hash( m[ 2 ] ); + + // if we matched ^ then we need to apply meta to the previous block + if ( m[ 1 ] === "" ) { + var node = this.tree[ this.tree.length - 1 ], + hash = extract_attr( node ); + + // if the node is a string (rather than JsonML), bail + if ( typeof node === "string" ) return undefined; + + // create the attribute hash if it doesn't exist + if ( !hash ) { + hash = {}; + node.splice( 1, 0, hash ); + } + + // add the attributes in + for ( a in attr ) { + hash[ a ] = attr[ a ]; + } + + // return nothing so the meta hash is removed + return []; + } + + // pull the meta hash off the block and process what's left + var b = block.replace( /\n.*$/, "" ), + result = this.processBlock( b, [] ); + + // get or make the attributes hash + var hash = extract_attr( result[ 0 ] ); + if ( !hash ) { + hash = {}; + result[ 0 ].splice( 1, 0, hash ); + } + + // attach the attributes to the block + for ( a in attr ) { + hash[ a ] = attr[ a ]; + } + + return result; +} + +Markdown.dialects.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+([^]+)$/, + list = [ "dl" ]; + + // see if we're dealing with a tight or loose block + if ( ( m = block.match( tight ) ) ) { + // pull subsequent tight DL blocks out of `next` + var blocks = [ block ]; + while ( next.length && tight.exec( next[ 0 ] ) ) { + blocks.push( next.shift() ); + } + + for ( var b = 0; b < blocks.length; ++b ) { + var m = blocks[ b ].match( tight ), + terms = m[ 1 ].replace( /\n$/, "" ).split( /\n/ ), + defns = m[ 2 ].split( /\n:\s+/ ); + + // print( uneval( m ) ); + + for ( var i = 0; i < terms.length; ++i ) { + list.push( [ "dt", terms[ i ] ] ); + } + + for ( var 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 ]; +} + +Markdown.dialects.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 = process_meta_hash( 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.buildBlockOrder ( Markdown.dialects.Maruku.block ); +Markdown.buildInlinePatterns( Markdown.dialects.Maruku.inline ); + +function extract_attr( jsonml ) { + return jsonml instanceof Array + && jsonml.length > 1 + && typeof jsonml[ 1 ] === "object" + && !( jsonml[ 1 ] instanceof Array ) + ? jsonml[ 1 ] + : undefined; +} + +function process_meta_hash( 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(); + default : + parts[ parts.length - 1 ] += letter; + break; + } + } + + return parts; +} + +/** + * 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 + } + + while ( jsonml.length ) { + content.push( render_tree( jsonml.shift() ) ); + } + } + + return content.join( "\n" ).replace( /\n+$/, "" ); +} + +function render_tree( jsonml ) { + // basic case + if ( typeof jsonml === "string" ) { + return jsonml.replace( /&/g, "&" ) + .replace( //g, ">" ); + } + + 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( arguments.callee( jsonml.shift() ) ); + } + + var tag_attrs = ""; + for ( var a in attributes ) { + tag_attrs += " " + a + '="' + attributes[ a ] + '"'; + } + + var newlinetab = "\n ", + newline = "\n"; + + if ( ~["em", "strong", "img", "br", "a"].indexOf( tag ) ) { + newlinetab = ""; + newline = ""; + } + + // be careful about adding whitespace here for inline elements + return "<"+ tag + tag_attrs + ">" + newlinetab + content.join( "" ).replace( /\n$/, "" ).replace( /\n/g, "\n " ) + newline + "" + newline; +} + +function convert_tree_to_html( tree, references ) { + // shallow clone + var jsonml = tree.slice( 0 ); + + // Clone attributes if the exist + var attrs = extract_attr( jsonml ); + if ( attrs ) { + jsonml[ 1 ] = {}; + for ( var 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"; + var i = attrs ? 2 : 1; + var code = [ "code" ]; + code.push.apply( code, jsonml.splice( 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; + } + + // convert all the children + var 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; + } + // if there aren't, remove it + if ( i === 1 ) { + jsonml.splice( i, 1 ); + } + } + + for ( ; i < jsonml.length; ++i ) { + jsonml[ i ] = arguments.callee( jsonml[ i ], references ); + } + + 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 { + arguments.callee( jsonml[ i ] ); + ++i; + } + } +} + +} )( (function() { + if ( typeof exports === "undefined" ) { + window.markdown = {}; + return window.markdown; + } + else { + return exports; + } +} )() ); diff --git a/tools/ronnjs/lib/ext/opts.js b/tools/ronnjs/lib/ext/opts.js new file mode 100755 index 0000000000..92263b0bc9 --- /dev/null +++ b/tools/ronnjs/lib/ext/opts.js @@ -0,0 +1,268 @@ +/*************************************************************************** +Author : Joey Mazzarelli +Email : mazzarelli@gmail.com +Homepage : http://joey.mazzarelli.com/js-opts +Source : http://bitbucket.org/mazzarell/js-opts/ +License : Simplified BSD License +Version : 1.0 + +Copyright 2010 Joey Mazzarelli. All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + 1. Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + 2. Redistributions in binary form must reproduce the above copyright notice, + this list of conditions and the following disclaimer in the documentation + and/or other materials provided with the distribution. + +THIS SOFTWARE IS PROVIDED BY JOEY MAZZARELLI 'AS IS' AND ANY EXPRESS OR IMPLIED +WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO +EVENT SHALL JOEY MAZZARELLI OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, +INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE +OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF +ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +The views and conclusions contained in the software and documentation are those +of the authors and should not be interpreted as representing official policies, +either expressed or implied, of Joey Mazzarelli. +***************************************************************************/ + +var puts = require('sys').puts + , values = {} + , args = {} + , argv = [] + , errors = [] + , descriptors = {opts:[], args:[]}; + +/** + * Add a set of option descriptors, not yet ready to be parsed. + * See exports.parse for description of options object + * + * Additionally, it takes a namespace as an argument, useful for + * building options for a library in addition to the main app. + */ +exports.add = function (options, namespace) { + for (var i=0; i or by including the option; + * { + * long : 'help', + * description : 'Show this help message', + * callback : require('./opts').help, + * } + * + * ===== Arguments Docs ===== + * Arguments are different than options, and simpler. They typically come + * after the options, but the library really doesn't care. Each argument + * can have the form of: + * { + * name : 'script', + * required : true, // default false + * callback : function (value) { ... }, + * } + */ +exports.parse = function (options, params, help) { + + if (params === true) { + help = true; + } else if (!params) { + params = []; + } else { + for (var i=0; i + * License : MIT + */ + +var md = require(__dirname + '/ext/markdown'); +var sys = require('sys'); + +/* exports Ronn class + * usage : + * var ronn = new Ronn(rofftext, "1.0", "my manual name", "2010-12-25"); + * ronn.roff(); + * ronn.html(); + * ronn.fragment(); + */ + +exports.Ronn = function(text, version, manual, date) { + if (!manual) manual = ""; + if (!version) version = ""; + if (!date) date = new Date(); + else date = new Date(date + " GMT"); + + var gHtml = md.toHTMLTree(text); + + this.roff = function() { + return blockFilter("", gHtml, {parent:null, previous:null, position:null}); + }; + + this.html = function() { + return toHTML(gHtml); + }; + + this.fragment = function() { + return toHTMLfragment(gHtml); + }; + + function blockFilter(out, node, context) { + if (typeof node == "string") { + if (!node.match(/^\s*$/m)) sys.debug("unexpected text: " + node); + return out; + } + var tag = node.shift(); + var attributes = null; + if (node.length && typeof node[0] === "object" && !(node[0] instanceof Array)) { + attributes = node.shift(); + } + var fParent = context.parent; + var fPrevious = context.previous; + context.previous = null; + context.parent = tag; + switch (tag) { + case "html": + out = comment(out, "Generated with Ronnjs/v0.1"); + out = comment(out, "http://github.com/kapouer/ronnjs/"); + while (node.length) out = blockFilter(out, node.shift(), context); + break; + case "h1": + var fTagline = node.shift(); + var fMatch = /([\w_.\[\]~+=@:-]+)\s*\((\d\w*)\)\s*-+\s*(.*)/.exec(fTagline); + var fName, fSection; + if (fMatch != null) { + fName = fMatch[1]; + fSection = fMatch[2]; + fTagline = fMatch[3]; + } else { + fMatch = /([\w_.\[\]~+=@:-]+)\s+-+\s+(.*)/.exec(fTagline); + if (fMatch != null) { + fName = fMatch[1]; + fTagline = fMatch[2]; + } + } + if (fMatch == null) { + fName = ""; + fSection = ""; + fName = ""; + } + out = macro(out, "TH", [ + quote(esc(fName.toUpperCase())) + , quote(fSection) + , quote(manDate(date)) + , quote(version) + , quote(manual) + ]); + out = macro(out, "SH", quote("NAME")); + out += "\\fB" + fName + "\\fR"; + if (fTagline.length > 0) out += " \\-\\- " + esc(fTagline); + break; + case "h2": + out = macro(out, "SH", quote(esc(toHTML(node.shift())))); + break; + case "h3": + out = macro(out, "SS", quote(esc(toHTML(node.shift())))); + break; + case "hr": + out = macro(out, "HR"); + break; + case "p": + if (fPrevious && fParent && (fParent == "dd" || fParent == "li")) + out = macro(out, "IP"); + else if (fPrevious && !(fPrevious == "h1" || fPrevious == "h2" || fPrevious == "h3")) + out = macro(out, "P"); + out = callInlineChildren(out, node, context); + break; + case "pre": + var indent = (fPrevious == null || !(fPrevious == "h1" || fPrevious == "h2" || fPrevious == "h3")); + if (indent) out = macro(out, "IP", [quote(""), 4]); + out = macro(out, "nf"); + out = callInlineChildren(out, node, context); + out = macro(out, "fi"); + if (indent) out = macro(out, "IP", [quote(""), 0]); + break; + case "dl": + out = macro(out, "TP"); + while (node.length) out = blockFilter(out, node.shift(), context); + break; + case "dt": + if (fPrevious != null) out = macro(out, "TP"); + out = callInlineChildren(out, node, context); + out += "\n"; + break; + case "dd": + if (containsTag(node, {'p':true})) { + while (node.length) out = blockFilter(out, node.shift(), context); + } else { + out = callInlineChildren(out, node, context); + } + out += "\n"; + break; + case "ol": + case "ul": + context.position = 0; + while (node.length) { + out = blockFilter(out, node.shift(), context); + } + context.position = null; + out = macro(out, "IP", [quote(""), 0]); + break; + case "li": + if (fParent == "ol") { + context.position += 1; + out = macro(out, "IP", [quote(context.position), 4]); + } else if (fParent == "ul") { + out = macro(out, "IP", [quote("\\(bu"), 4]); + } + if (containsTag(node, {"p":true, "ol":true, "ul":true, "dl":true, "div":true})) { + while (node.length) out = blockFilter(out, node.shift(), context); + } else { + out = callInlineChildren(out, node, context); + } + out += "\n"; + break; + default: + sys.debug("unrecognized block tag: " + tag); + break; + } + context.parent = fParent; + context.previous = tag; + return out; + } + + function callInlineChildren(out, node, context) { + while (node.length) { + var lChild = node.shift(); + if (node.length > 0) context.hasNext = true; + else context.hasNext = false; + out = inlineFilter(out, lChild, context); + } + return out; + } + + function inlineFilter(out, node, context) { + if (typeof node == "string") { + if (context.previous && context.previous == "br") node = node.replace(/^\n+/gm, ''); + if (context.parent == "pre") { + // do nothing + } else if (context.previous == null && !context.hasNext) { + node = node.replace(/\n+$/gm, ''); + } else { + node = node.replace(/\n+$/gm, ' '); + } + out += esc(node); + return out; + } + var tag = node.shift(); + var attributes = null; + if (node.length && typeof node[0] === "object" && !(node[0] instanceof Array)) { + attributes = node.shift(); + } + var fParent = context.parent; + var fPrevious = context.previous; + context.parent = tag; + context.previous = null; + switch(tag) { + case "code": + if (fParent == "pre") { + out = callInlineChildren(out, node, context); + } else { + out += '\\fB'; + out = callInlineChildren(out, node, context); + out += '\\fR'; + } + break; + case "b": + case "strong": + case "kbd": + case "samp": + out += '\\fB'; + out = callInlineChildren(out, node, context); + out += '\\fR'; + break; + case "var": + case "em": + case "i": + case "u": + out += '\\fI'; + out = callInlineChildren(out, node, context); + out += '\\fR'; + break; + case "br": + out = macro(out, "br"); + break; + case "a": + var fStr = node[0]; + var fHref = attributes['href']; + if (fHref == fStr || decodeURI(fHref) == "mailto:" + decodeURI(fStr)) { + out += '\\fI'; + out = callInlineChildren(out, node, context); + out += '\\fR'; + } else { + out = callInlineChildren(out, node, context); + out += " "; + out += '\\fI'; + out += esc(fHref); + out += '\\fR'; + } + break; + default: + sys.debug("unrecognized inline tag: " + tag); + break; + } + context.parent = fParent; + context.previous = tag; + return out; + } + + function containsTag(node, tags) { + // browse ml tree searching for tags (hash {tag : true, ...}) + if (typeof node == "string") return false; + var jml = node.slice(0); + if (jml.length == 0) return false; + else while (jml.length && jml[0] instanceof Array) { + if (containsTag(jml.shift(), tags)) return true; + } + var tag = jml.shift(); + if (tags[tag] === true) return true; + if (jml.length && typeof jml[0] === "object" && !(jml[0] instanceof Array)) { + // skip attributes + jml.shift(); + } + // children + if (jml.length) { + if (containsTag(jml.shift(), tags)) return true; + } + // siblings + if (jml.length) return containsTag(jml, tags); + } + + function toHTML(node) { + // problème ici : les & sont remplacés par des & + return md.renderJsonML(node, {root:true}); + } + + function toHTMLfragment(node) { + return md.renderJsonML(node); + } + + function comment(out, str) { + return writeln(out, '.\\" ' + str); + } + + function quote(str) { + return '"' + str + '"'; + } + + function esc(str) { + return str + .replace(/\\/gm, "\\\\") + .replace(/-/gm, "\\-") + .replace(/^\./gm, "\\|.") + .replace(/\./gm, "\\.") + .replace(/'/gm, "\\'") + ; + } + + function writeln(out, str) { + if (out.length && out[out.length - 1] != "\n") out += "\n"; + out += str + "\n"; + return out; + } + + function macro(out, name, list) { + var fText = ".\n." + name; + if (list != null) { + if (typeof list == "string") { + fText += ' ' + list; + } else { + for (var i=0, len=list.length; i < len; i++) { + var item = list[i]; + if (item == null) continue; + fText += ' ' + item; + } + } + } + return writeln(out, fText); + } + + function manDate(pDate) { + var fMonth = ["January", "February", "March", "April", "May", "June", "July", "August", "September", "October", "November", "December"][pDate.getMonth()]; + return fMonth + " " + pDate.getFullYear(); + } +};