parser.js

if (typeof define !== 'function') { var define = require('amdefine')(module) }

define(['./markdown_helpers', './core'], function(MarkdownHelpers, Markdown) {

  // 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 );
  };

  /**
   *  count_lines( str ) -> count
   *  - str (String): String whose lines we want to count
   *
   *  Counts the number of linebreaks in `str`
   **/
  function count_lines( str ) {
    return str.split("\n").length - 1;
  }

  // Internal - split source into rough blocks
  Markdown.prototype.split_blocks = function splitBlocks( input ) {
    // Normalize linebreaks to \n.
    input = input.replace(/\r\n?/g, "\n");
    // Match until the end of the string, a newline followed by #, or two or more newlines.
    // [\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 ) {

        if ( !isArray(res) || ( res.length > 0 && !( isArray(res[0]) ) && ( typeof res[0] !== "string")) ) {
          this.debug(ord[i], "didn't return proper JsonML");
        }

        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);
    };
  };

  return Markdown;
});