redcloth3.rb 38.9 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131
#                                vim:ts=4:sw=4:
# = RedCloth - Textile and Markdown Hybrid for Ruby
#
# Homepage::  http://whytheluckystiff.net/ruby/redcloth/
# Author::    why the lucky stiff (http://whytheluckystiff.net/)
# Copyright:: (cc) 2004 why the lucky stiff (and his puppet organizations.)
# License::   BSD
#
# (see http://hobix.com/textile/ for a Textile Reference.)
#
# Based on (and also inspired by) both:
#
# PyTextile: http://diveintomark.org/projects/textile/textile.py.txt
# Textism for PHP: http://www.textism.com/tools/textile/
#
#

# = RedCloth
#
# RedCloth is a Ruby library for converting Textile and/or Markdown
# into HTML.  You can use either format, intermingled or separately.
# You can also extend RedCloth to honor your own custom text stylings.
#
# RedCloth users are encouraged to use Textile if they are generating
# HTML and to use Markdown if others will be viewing the plain text.
#
# == What is Textile?
#
# Textile is a simple formatting style for text
# documents, loosely based on some HTML conventions.
#
# == Sample Textile Text
#
#  h2. This is a title
#
#  h3. This is a subhead
#
#  This is a bit of paragraph.
#
#  bq. This is a blockquote.
#
# = Writing Textile
#
# A Textile document consists of paragraphs.  Paragraphs
# can be specially formatted by adding a small instruction
# to the beginning of the paragraph.
#
#  h[n].   Header of size [n].
#  bq.     Blockquote.
#  #       Numeric list.
#  *       Bulleted list.
#
# == Quick Phrase Modifiers
#
# Quick phrase modifiers are also included, to allow formatting
# of small portions of text within a paragraph.
#
#  \_emphasis\_
#  \_\_italicized\_\_
#  \*strong\*
#  \*\*bold\*\*
#  ??citation??
#  -deleted text-
#  +inserted text+
#  ^superscript^
#  ~subscript~
#  @code@
#  %(classname)span%
#
#  ==notextile== (leave text alone)
#
# == Links
#
# To make a hypertext link, put the link text in "quotation 
# marks" followed immediately by a colon and the URL of the link.
# 
# Optional: text in (parentheses) following the link text, 
# but before the closing quotation mark, will become a Title 
# attribute for the link, visible as a tool tip when a cursor is above it.
# 
# Example:
#
#  "This is a link (This is a title) ":http://www.textism.com
# 
# Will become:
# 
#  <a href="http://www.textism.com" title="This is a title">This is a link</a>
#
# == Images
#
# To insert an image, put the URL for the image inside exclamation marks.
#
# Optional: text that immediately follows the URL in (parentheses) will 
# be used as the Alt text for the image. Images on the web should always 
# have descriptive Alt text for the benefit of readers using non-graphical 
# browsers.
#
# Optional: place a colon followed by a URL immediately after the 
# closing ! to make the image into a link.
# 
# Example:
#
#  !http://www.textism.com/common/textist.gif(Textist)!
#
# Will become:
#
#  <img src="http://www.textism.com/common/textist.gif" alt="Textist" />
#
# With a link:
#
#  !/common/textist.gif(Textist)!:http://textism.com
#
# Will become:
#
#  <a href="http://textism.com"><img src="/common/textist.gif" alt="Textist" /></a>
#
# == Defining Acronyms
#
# HTML allows authors to define acronyms via the tag. The definition appears as a 
# tool tip when a cursor hovers over the acronym. A crucial aid to clear writing, 
# this should be used at least once for each acronym in documents where they appear.
#
# To quickly define an acronym in Textile, place the full text in (parentheses) 
# immediately following the acronym.
# 
# Example:
#
#  ACLU(American Civil Liberties Union)
#
# Will become:
#
132
#  <abbr title="American Civil Liberties Union">ACLU</abbr>
133 134 135
#
# == Adding Tables
#
marutosijp's avatar
marutosijp committed
136
# In Textile, simple tables can be added by separating each column by
137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166
# a pipe.
#
#     |a|simple|table|row|
#     |And|Another|table|row|
#
# Attributes are defined by style definitions in parentheses.
#
#     table(border:1px solid black).
#     (background:#ddd;color:red). |{}| | | |
#
# == Using RedCloth
# 
# RedCloth is simply an extension of the String class, which can handle
# Textile formatting.  Use it like a String and output HTML with its
# RedCloth#to_html method.
#
#  doc = RedCloth.new "
#
#  h2. Test document
#
#  Just a simple test."
#
#  puts doc.to_html
#
# By default, RedCloth uses both Textile and Markdown formatting, with
# Textile formatting taking precedence.  If you want to turn off Markdown
# formatting, to boost speed and limit the processor:
#
#  class RedCloth::Textile.new( str )

167
class RedCloth3 < String
168
    include Redmine::Helpers::URL
169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273

    VERSION = '3.0.4'
    DEFAULT_RULES = [:textile, :markdown]

    #
    # Two accessor for setting security restrictions.
    #
    # This is a nice thing if you're using RedCloth for
    # formatting in public places (e.g. Wikis) where you
    # don't want users to abuse HTML for bad things.
    #
    # If +:filter_html+ is set, HTML which wasn't
    # created by the Textile processor will be escaped.
    #
    # If +:filter_styles+ is set, it will also disable
    # the style markup specifier. ('{color: red}')
    #
    attr_accessor :filter_html, :filter_styles

    #
    # Accessor for toggling hard breaks.
    #
    # If +:hard_breaks+ is set, single newlines will
    # be converted to HTML break tags.  This is the
    # default behavior for traditional RedCloth.
    #
    attr_accessor :hard_breaks

    # Accessor for toggling lite mode.
    #
    # In lite mode, block-level rules are ignored.  This means
    # that tables, paragraphs, lists, and such aren't available.
    # Only the inline markup for bold, italics, entities and so on.
    #
    #   r = RedCloth.new( "And then? She *fell*!", [:lite_mode] )
    #   r.to_html
    #   #=> "And then? She <strong>fell</strong>!"
    #
    attr_accessor :lite_mode

    #
    # Accessor for toggling span caps.
    #
    # Textile places `span' tags around capitalized
    # words by default, but this wreaks havoc on Wikis.
    # If +:no_span_caps+ is set, this will be
    # suppressed.
    #
    attr_accessor :no_span_caps

    #
    # Establishes the markup predence.  Available rules include:
    #
    # == Textile Rules
    #
    # The following textile rules can be set individually.  Or add the complete
    # set of rules with the single :textile rule, which supplies the rule set in
    # the following precedence:
    #
    # refs_textile::          Textile references (i.e. [hobix]http://hobix.com/)
    # block_textile_table::   Textile table block structures
    # block_textile_lists::   Textile list structures
    # block_textile_prefix::  Textile blocks with prefixes (i.e. bq., h2., etc.)
    # inline_textile_image::  Textile inline images
    # inline_textile_link::   Textile inline links
    # inline_textile_span::   Textile inline spans
    # glyphs_textile:: Textile entities (such as em-dashes and smart quotes)
    #
    # == Markdown
    #
    # refs_markdown::         Markdown references (for example: [hobix]: http://hobix.com/)
    # block_markdown_setext:: Markdown setext headers
    # block_markdown_atx::    Markdown atx headers
    # block_markdown_rule::   Markdown horizontal rules
    # block_markdown_bq::     Markdown blockquotes
    # block_markdown_lists::  Markdown lists
    # inline_markdown_link::  Markdown links
    attr_accessor :rules

    # Returns a new RedCloth object, based on _string_ and
    # enforcing all the included _restrictions_.
    #
    #   r = RedCloth.new( "h1. A <b>bold</b> man", [:filter_html] )
    #   r.to_html
    #     #=>"<h1>A &lt;b&gt;bold&lt;/b&gt; man</h1>"
    #
    def initialize( string, restrictions = [] )
        restrictions.each { |r| method( "#{ r }=" ).call( true ) }
        super( string )
    end

    #
    # Generates HTML from the Textile contents.
    #
    #   r = RedCloth.new( "And then? She *fell*!" )
    #   r.to_html( true )
    #     #=>"And then? She <strong>fell</strong>!"
    #
    def to_html( *rules )
        rules = DEFAULT_RULES if rules.empty?
        # make our working copy
        text = self.dup
        
        @urlrefs = {}
        @shelf = []
274
        textile_rules = [:block_textile_table, :block_textile_lists,
275
                         :block_textile_prefix, :inline_textile_image, :inline_textile_link,
276
                         :inline_textile_code, :inline_textile_span, :glyphs_textile]
277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293
        markdown_rules = [:refs_markdown, :block_markdown_setext, :block_markdown_atx, :block_markdown_rule,
                          :block_markdown_bq, :block_markdown_lists, 
                          :inline_markdown_reflink, :inline_markdown_link]
        @rules = rules.collect do |rule|
            case rule
            when :markdown
                markdown_rules
            when :textile
                textile_rules
            else
                rule
            end
        end.flatten

        # start processor
        @pre_list = []
        rip_offtags text
294 295 296 297 298

        # standard clean up
        incoming_entities text
        clean_white_space text

299
        no_textile text
jplang's avatar
jplang committed
300
        escape_html_tags text
301 302
        # need to do this before #hard_break and #blocks
        block_textile_quotes text unless @lite_mode
303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344
        hard_break text 
        unless @lite_mode
            refs text
            blocks text
        end
        inline text
        smooth_offtags text

        retrieve text

        text.gsub!( /<\/?notextile>/, '' )
        text.gsub!( /x%x%/, '&#38;' )
        clean_html text if filter_html
        text.strip!
        text

    end

    #######
    private
    #######
    #
    # Mapping of 8-bit ASCII codes to HTML numerical entity equivalents.
    # (from PyTextile)
    #
    TEXTILE_TAGS =

        [[128, 8364], [129, 0], [130, 8218], [131, 402], [132, 8222], [133, 8230], 
         [134, 8224], [135, 8225], [136, 710], [137, 8240], [138, 352], [139, 8249], 
         [140, 338], [141, 0], [142, 0], [143, 0], [144, 0], [145, 8216], [146, 8217], 
         [147, 8220], [148, 8221], [149, 8226], [150, 8211], [151, 8212], [152, 732], 
         [153, 8482], [154, 353], [155, 8250], [156, 339], [157, 0], [158, 0], [159, 376]].

        collect! do |a, b|
            [a.chr, ( b.zero? and "" or "&#{ b };" )]
        end

    #
    # Regular expressions to convert to HTML.
    #
    A_HLGN = /(?:(?:<>|<|>|\=|[()]+)+)/
    A_VLGN = /[\-^~]/
345
    C_CLAS = '(?:\([^")]+\))'
346
    C_LNGE = '(?:\[[a-z\-_]+\])'
347
    C_STYL = '(?:\{[^{][^"}]+\})'
348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366
    S_CSPN = '(?:\\\\\d+)'
    S_RSPN = '(?:/\d+)'
    A = "(?:#{A_HLGN}?#{A_VLGN}?|#{A_VLGN}?#{A_HLGN}?)"
    S = "(?:#{S_CSPN}?#{S_RSPN}|#{S_RSPN}?#{S_CSPN}?)"
    C = "(?:#{C_CLAS}?#{C_STYL}?#{C_LNGE}?|#{C_STYL}?#{C_LNGE}?#{C_CLAS}?|#{C_LNGE}?#{C_STYL}?#{C_CLAS}?)"
    # PUNCT = Regexp::quote( '!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~' )
    PUNCT = Regexp::quote( '!"#$%&\'*+,-./:;=?@\\^_`|~' )
    PUNCT_NOQ = Regexp::quote( '!"#$&\',./:;=?@\\`|' )
    PUNCT_Q = Regexp::quote( '*-_+^~%' )
    HYPERLINK = '(\S+?)([^\w\s/;=\?]*?)(?=\s|<|$)'

    # Text markup tags, don't conflict with block tags
    SIMPLE_HTML_TAGS = [
        'tt', 'b', 'i', 'big', 'small', 'em', 'strong', 'dfn', 'code', 
        'samp', 'kbd', 'var', 'cite', 'abbr', 'acronym', 'a', 'img', 'br',
        'br', 'map', 'q', 'sub', 'sup', 'span', 'bdo'
    ]

    QTAGS = [
367 368
        ['**', 'b', :limit],
        ['*', 'strong', :limit],
369 370
        ['??', 'cite', :limit],
        ['-', 'del', :limit],
371
        ['__', 'i', :limit],
372 373 374
        ['_', 'em', :limit],
        ['%', 'span', :limit],
        ['+', 'ins', :limit],
375 376
        ['^', 'sup', :limit],
        ['~', 'sub', :limit]
377
    ] 
378 379
    QTAGS_JOIN = QTAGS.map {|rc, ht, rtype| Regexp::quote rc}.join('|')
    
380 381 382 383 384
    QTAGS.collect! do |rc, ht, rtype|
        rcq = Regexp::quote rc
        re =
            case rtype
            when :limit
385
                /(^|[>\s\(])          # sta
386
                (?!\-\-)
387 388
                (#{QTAGS_JOIN}|)      # oqs
                (#{rcq})              # qtag
389
                ([[:word:]]|[^\s].*?[^\s])    # content
390
                (?!\-\-)
391
                #{rcq}
392
                (#{QTAGS_JOIN}|)      # oqa
393
                (?=[[:punct:]]|<|\s|\)|$)/x
394 395 396 397
            else
                /(#{rcq})
                (#{C})
                (?::(\S+))?
398
                ([[:word:]]|[^\s\-].*?[^\s\-])
399 400 401 402 403 404 405 406
                #{rcq}/xm 
            end
        [rc, ht, re, rtype]
    end

    # Elements to handle
    GLYPHS = [
    #   [ /([^\s\[{(>])?\'([dmst]\b|ll\b|ve\b|\s|:|$)/, '\1&#8217;\2' ], # single closing
407 408 409
    #   [ /([^\s\[{(>#{PUNCT_Q}][#{PUNCT_Q}]*)\'/, '\1&#8217;' ], # single closing
    #   [ /\'(?=[#{PUNCT_Q}]*(s\b|[\s#{PUNCT_NOQ}]))/, '&#8217;' ], # single closing
    #   [ /\'/, '&#8216;' ], # single opening
410 411
    #   [ /</, '&lt;' ], # less-than
    #   [ />/, '&gt;' ], # greater-than
412
    #   [ /([^\s\[{(])?"(\s|:|$)/, '\1&#8221;\2' ], # double closing
413 414 415
    #   [ /([^\s\[{(>#{PUNCT_Q}][#{PUNCT_Q}]*)"/, '\1&#8221;' ], # double closing
    #   [ /"(?=[#{PUNCT_Q}]*[\s#{PUNCT_NOQ}])/, '&#8221;' ], # double closing
    #   [ /"/, '&#8220;' ], # double opening
416
    #   [ /\b( )?\.{3}/, '\1&#8230;' ], # ellipsis
417
    #   [ /\b([A-Z][A-Z0-9]{2,})\b(?:[(]([^)]*)[)])/, '<acronym title="\2">\1</acronym>' ], # 3+ uppercase acronym
418 419 420 421 422 423 424 425
    #   [ /(^|[^"][>\s])([A-Z][A-Z0-9 ]+[A-Z0-9])([^<A-Za-z0-9]|$)/, '\1<span class="caps">\2</span>\3', :no_span_caps ], # 3+ uppercase caps
    #   [ /(\.\s)?\s?--\s?/, '\1&#8212;' ], # em dash
    #   [ /\s->\s/, ' &rarr; ' ], # right arrow
    #   [ /\s-\s/, ' &#8211; ' ], # en dash
    #   [ /(\d+) ?x ?(\d+)/, '\1&#215;\2' ], # dimension sign
    #   [ /\b ?[(\[]TM[\])]/i, '&#8482;' ], # trademark
    #   [ /\b ?[(\[]R[\])]/i, '&#174;' ], # registered
    #   [ /\b ?[(\[]C[\])]/i, '&#169;' ] # copyright
426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443
    ]

    H_ALGN_VALS = {
        '<' => 'left',
        '=' => 'center',
        '>' => 'right',
        '<>' => 'justify'
    }

    V_ALGN_VALS = {
        '^' => 'top',
        '-' => 'middle',
        '~' => 'bottom'
    }

    #
    # Flexible HTML escaping
    #
jplang's avatar
jplang committed
444 445
    def htmlesc( str, mode=:Quotes )
      if str
446 447 448 449 450
        str.gsub!( '&', '&amp;' )
        str.gsub!( '"', '&quot;' ) if mode != :NoQuotes
        str.gsub!( "'", '&#039;' ) if mode == :Quotes
        str.gsub!( '<', '&lt;')
        str.gsub!( '>', '&gt;')
jplang's avatar
jplang committed
451 452
      end
      str
453 454 455 456
    end

    # Search and replace for Textile glyphs (quotes, dashes, other symbols)
    def pgl( text )
457 458 459 460
        #GLYPHS.each do |re, resub, tog|
        #    next if tog and method( tog ).call
        #    text.gsub! re, resub
        #end
461
        text.gsub!(/\b([A-Z][A-Z0-9]{1,})\b(?:[(]([^)]*)[)])/) do |m|
462
          "<abbr title=\"#{htmlesc $2}\">#{$1}</abbr>"
463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478
        end
    end

    # Parses Textile attribute lists and builds an HTML attribute string
    def pba( text_in, element = "" )
        
        return '' unless text_in

        style = []
        text = text_in.dup
        if element == 'td'
            colspan = $1 if text =~ /\\(\d+)/
            rowspan = $1 if text =~ /\/(\d+)/
            style << "vertical-align:#{ v_align( $& ) };" if text =~ A_VLGN
        end

479 480 481 482
        if text.sub!( /\{([^"}]*)\}/, '' ) && !filter_styles
          sanitized = sanitize_styles($1)
          style << "#{ sanitized };" unless sanitized.blank?
        end
483 484

        lang = $1 if
485
            text.sub!( /\[([a-z\-_]+?)\]/, '' )
486 487 488 489 490 491 492 493 494 495 496 497

        cls = $1 if
            text.sub!( /\(([^()]+?)\)/, '' )
                        
        style << "padding-left:#{ $1.length }em;" if
            text.sub!( /([(]+)/, '' )

        style << "padding-right:#{ $1.length }em;" if text.sub!( /([)]+)/, '' )

        style << "text-align:#{ h_align( $& ) };" if text =~ A_HLGN

        cls, id = $1, $2 if cls =~ /^(.*?)#(.*)$/
498 499 500 501 502 503 504 505 506

        # add wiki-class- and wiki-id- to classes and ids to prevent setting of
        # arbitrary classes and ids
        cls = cls.split(/\s+/).map do |c|
          c.starts_with?('wiki-class-') ? c : "wiki-class-#{c}"
        end.join(' ') if cls

        id = id.starts_with?('wiki-id-') ? id : "wiki-id-#{id}" if id

507 508 509 510 511 512 513 514 515 516 517
        atts = ''
        atts << " style=\"#{ style.join }\"" unless style.empty?
        atts << " class=\"#{ cls }\"" unless cls.to_s.empty?
        atts << " lang=\"#{ lang }\"" if lang
        atts << " id=\"#{ id }\"" if id
        atts << " colspan=\"#{ colspan }\"" if colspan
        atts << " rowspan=\"#{ rowspan }\"" if rowspan
        
        atts
    end

518
    STYLES_RE = /^(color|(min-|max-)?+(width|height)|border|background|padding|margin|font|text|float)(-[a-z]+)*:\s*((\d+%?|\d+px|\d+(\.\d+)?em|#[0-9a-f]+|[a-z]+)\s*)+$/i
519 520 521 522 523 524 525 526 527

    def sanitize_styles(str)
      styles = str.split(";").map(&:strip)
      styles.reject! do |style|
        !style.match(STYLES_RE)
      end
      styles.join(";")
    end

528 529 530 531 532 533 534 535 536 537
    TABLE_RE = /^(?:table(_?#{S}#{A}#{C})\. ?\n)?^(#{A}#{C}\.? ?\|.*?\|)(\n\n|\Z)/m
    
    # Parses a Textile table block, building HTML from the result.
    def block_textile_table( text ) 
        text.gsub!( TABLE_RE ) do |matches|

            tatts, fullrow = $~[1..2]
            tatts = pba( tatts, 'table' )
            tatts = shelve( tatts ) if tatts
            rows = []
538
            fullrow.gsub!(/([^|\s])\s*\n/, "\\1<br />")
jplang's avatar
jplang committed
539
            fullrow.each_line do |row|
540 541
                ratts, row = pba( $1, 'tr' ), $2 if row =~ /^(#{A}#{C}\. )(.*)/m
                cells = []
542 543
                # the regexp prevents wiki links with a | from being cut as cells 
                row.scan(/\|(_?#{S}#{A}#{C}\. ?)?((\[\[[^|\]]*\|[^|\]]*\]\]|[^|])*?)(?=\|)/) do |modifiers, cell|
544
                    ctyp = 'd'
545
                    ctyp = 'h' if modifiers && modifiers =~ /^_/
546

547
                    catts = nil
548
                    catts = pba( modifiers, 'td' ) if modifiers
549

jplang's avatar
jplang committed
550 551
                    catts = shelve( catts ) if catts
                    cells << "\t\t\t<t#{ ctyp }#{ catts }>#{ cell }</t#{ ctyp }>" 
552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597
                end
                ratts = shelve( ratts ) if ratts
                rows << "\t\t<tr#{ ratts }>\n#{ cells.join( "\n" ) }\n\t\t</tr>"
            end
            "\t<table#{ tatts }>\n#{ rows.join( "\n" ) }\n\t</table>\n\n"
        end
    end

    LISTS_RE = /^([#*]+?#{C} .*?)$(?![^#*])/m
    LISTS_CONTENT_RE = /^([#*]+)(#{A}#{C}) (.*)$/m

    # Parses Textile lists and generates HTML
    def block_textile_lists( text ) 
        text.gsub!( LISTS_RE ) do |match|
            lines = match.split( /\n/ )
            last_line = -1
            depth = []
            lines.each_with_index do |line, line_id|
                if line =~ LISTS_CONTENT_RE 
                    tl,atts,content = $~[1..3]
                    if depth.last
                        if depth.last.length > tl.length
                            (depth.length - 1).downto(0) do |i|
                                break if depth[i].length == tl.length
                                lines[line_id - 1] << "</li>\n\t</#{ lT( depth[i] ) }l>\n\t"
                                depth.pop
                            end
                        end
                        if depth.last and depth.last.length == tl.length
                            lines[line_id - 1] << '</li>'
                        end
                    end
                    unless depth.last == tl
                        depth << tl
                        atts = pba( atts )
                        atts = shelve( atts ) if atts
                        lines[line_id] = "\t<#{ lT(tl) }l#{ atts }>\n\t<li>#{ content }"
                    else
                        lines[line_id] = "\t\t<li>#{ content }"
                    end
                    last_line = line_id

                else
                    last_line = line_id
                end
                if line_id - last_line > 1 or line_id == lines.length - 1
598
                    while v = depth.pop
599 600 601 602 603 604 605
                        lines[last_line] << "</li>\n\t</#{ lT( v ) }l>"
                    end
                end
            end
            lines.join( "\n" )
        end
    end
606
    
jplang's avatar
jplang committed
607
    QUOTES_RE = /(^>+([^\n]*?)(\n|$))+/m
608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628
    QUOTES_CONTENT_RE = /^([> ]+)(.*)$/m
    
    def block_textile_quotes( text )
      text.gsub!( QUOTES_RE ) do |match|
        lines = match.split( /\n/ )
        quotes = ''
        indent = 0
        lines.each do |line|
          line =~ QUOTES_CONTENT_RE 
          bq,content = $1, $2
          l = bq.count('>')
          if l != indent
            quotes << ("\n\n" + (l>indent ? '<blockquote>' * (l-indent) : '</blockquote>' * (indent-l)) + "\n\n")
            indent = l
          end
          quotes << (content + "\n")
        end
        quotes << ("\n" + '</blockquote>' * indent + "\n\n")
        quotes
      end
    end
629 630 631 632 633 634 635 636 637 638 639 640

    CODE_RE = /(\W)
        @
        (?:\|(\w+?)\|)?
        (.+?)
        @
        (?=\W)/x

    def inline_textile_code( text ) 
        text.gsub!( CODE_RE ) do |m|
            before,lang,code,after = $~[1..4]
            lang = " lang=\"#{ lang }\"" if lang
641
            rip_offtags( "#{ before }<code#{ lang }>#{ code }</code>#{ after }", false )
642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718
        end
    end

    def lT( text ) 
        text =~ /\#$/ ? 'o' : 'u'
    end

    def hard_break( text )
        text.gsub!( /(.)\n(?!\Z| *([#*=]+(\s|$)|[{|]))/, "\\1<br />" ) if hard_breaks
    end

    BLOCKS_GROUP_RE = /\n{2,}(?! )/m

    def blocks( text, deep_code = false )
        text.replace( text.split( BLOCKS_GROUP_RE ).collect do |blk|
            plain = blk !~ /\A[#*> ]/

            # skip blocks that are complex HTML
            if blk =~ /^<\/?(\w+).*>/ and not SIMPLE_HTML_TAGS.include? $1
                blk
            else
                # search for indentation levels
                blk.strip!
                if blk.empty?
                    blk
                else
                    code_blk = nil
                    blk.gsub!( /((?:\n(?:\n^ +[^\n]*)+)+)/m ) do |iblk|
                        flush_left iblk
                        blocks iblk, plain
                        iblk.gsub( /^(\S)/, "\t\\1" )
                        if plain
                            code_blk = iblk; ""
                        else
                            iblk
                        end
                    end

                    block_applied = 0 
                    @rules.each do |rule_name|
                        block_applied += 1 if ( rule_name.to_s.match /^block_/ and method( rule_name ).call( blk ) )
                    end
                    if block_applied.zero?
                        if deep_code
                            blk = "\t<pre><code>#{ blk }</code></pre>"
                        else
                            blk = "\t<p>#{ blk }</p>"
                        end
                    end
                    # hard_break blk
                    blk + "\n#{ code_blk }"
                end
            end

        end.join( "\n\n" ) )
    end

    def textile_bq( tag, atts, cite, content )
        cite, cite_title = check_refs( cite )
        cite = " cite=\"#{ cite }\"" if cite
        atts = shelve( atts ) if atts
        "\t<blockquote#{ cite }>\n\t\t<p#{ atts }>#{ content }</p>\n\t</blockquote>"
    end

    def textile_p( tag, atts, cite, content )
        atts = shelve( atts ) if atts
        "\t<#{ tag }#{ atts }>#{ content }</#{ tag }>"
    end

    alias textile_h1 textile_p
    alias textile_h2 textile_p
    alias textile_h3 textile_p
    alias textile_h4 textile_p
    alias textile_h5 textile_p
    alias textile_h6 textile_p

    def textile_fn_( tag, num, atts, cite, content )
719
        atts << " id=\"fn#{ num }\" class=\"footnote\""
720 721 722 723 724 725 726 727 728 729 730 731 732
        content = "<sup>#{ num }</sup> #{ content }"
        atts = shelve( atts ) if atts
        "\t<p#{ atts }>#{ content }</p>"
    end

    BLOCK_RE = /^(([a-z]+)(\d*))(#{A}#{C})\.(?::(\S+))? (.*)$/m

    def block_textile_prefix( text ) 
        if text =~ BLOCK_RE
            tag,tagpre,num,atts,cite,content = $~[1..6]
            atts = pba( atts )

            # pass to prefix handler
733
            replacement = nil
734
            if respond_to? "textile_#{ tag }", true
735
              replacement = method( "textile_#{ tag }" ).call( tag, atts, cite, content )
736
            elsif respond_to? "textile_#{ tagpre }_", true
737
              replacement = method( "textile_#{ tagpre }_" ).call( tagpre, num, atts, cite, content )  
738
            end
739
            text.gsub!( $& ) { replacement } if replacement
740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780
        end
    end
    
    SETEXT_RE = /\A(.+?)\n([=-])[=-]* *$/m
    def block_markdown_setext( text )
        if text =~ SETEXT_RE
            tag = if $2 == "="; "h1"; else; "h2"; end
            blk, cont = "<#{ tag }>#{ $1 }</#{ tag }>", $'
            blocks cont
            text.replace( blk + cont )
        end
    end

    ATX_RE = /\A(\#{1,6})  # $1 = string of #'s
              [ ]*
              (.+?)       # $2 = Header text
              [ ]*
              \#*         # optional closing #'s (not counted)
              $/x
    def block_markdown_atx( text )
        if text =~ ATX_RE
            tag = "h#{ $1.length }"
            blk, cont = "<#{ tag }>#{ $2 }</#{ tag }>\n\n", $'
            blocks cont
            text.replace( blk + cont )
        end
    end

    MARKDOWN_BQ_RE = /\A(^ *> ?.+$(.+\n)*\n*)+/m

    def block_markdown_bq( text )
        text.gsub!( MARKDOWN_BQ_RE ) do |blk|
            blk.gsub!( /^ *> ?/, '' )
            flush_left blk
            blocks blk
            blk.gsub!( /^(\S)/, "\t\\1" )
            "<blockquote>\n#{ blk }\n</blockquote>\n\n"
        end
    end

    MARKDOWN_RULE_RE = /^(#{
781
        ['*', '-', '_'].collect { |ch| ' ?(' + Regexp::quote( ch ) + ' ?){3,}' }.join( '|' )
782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799
    })$/

    def block_markdown_rule( text )
        text.gsub!( MARKDOWN_RULE_RE ) do |blk|
            "<hr />"
        end
    end

    # XXX TODO XXX
    def block_markdown_lists( text )
    end

    def inline_textile_span( text ) 
        QTAGS.each do |qtag_rc, ht, qtag_re, rtype|
            text.gsub!( qtag_re ) do |m|
             
                case rtype
                when :limit
800 801 802 803 804
                    sta,oqs,qtag,content,oqa = $~[1..6]
                    atts = nil
                    if content =~ /^(#{C})(.+)$/
                      atts, content = $~[1..2]
                    end
805 806 807 808 809 810 811
                else
                    qtag,atts,cite,content = $~[1..4]
                    sta = ''
                end
                atts = pba( atts )
                atts = shelve( atts ) if atts

812
                "#{ sta }#{ oqs }<#{ ht }#{ atts }>#{ content }</#{ ht }>#{ oqa }"
813 814 815 816 817 818

            end
        end
    end

    LINK_RE = /
819
            (
820 821 822
            ([\s\[{(]|[#{PUNCT}])?     # $pre
            "                          # start
            (#{C})                     # $atts
jplang's avatar
jplang committed
823
            ([^"\n]+?)                 # $text
824 825 826
            \s?
            (?:\(([^)]+?)\)(?="))?     # $title
            ":
827
            (                          # $url
jplang's avatar
jplang committed
828
            (\/|[a-zA-Z]+:\/\/|www\.|mailto:)  # $proto
829
            [[:alnum:]_\/]\S+?
830
            )               
831
            (\/)?                      # $slash
832
            ([^[:alnum:]_\=\/;\(\)]*?)         # $post
833
            )
834 835
            (?=<|\s|$)
        /x 
836
#"
837 838
    def inline_textile_link( text ) 
        text.gsub!( LINK_RE ) do |m|
839 840 841 842
          all,pre,atts,text,title,url,proto,slash,post = $~[1..9]
          if text.include?('<br />')
            all
          else
843 844 845
            url, url_title = check_refs( url )
            title ||= url_title
            
846 847 848 849 850 851
            # Idea below : an URL with unbalanced parethesis and
            # ending by ')' is put into external parenthesis
            if ( url[-1]==?) and ((url.count("(") - url.count(")")) < 0 ) )
              url=url[0..-2] # discard closing parenth from url
              post = ")"+post # add closing parenth to post
            end
852
            atts = pba( atts )
853
            atts = " href=\"#{ htmlesc url }#{ slash }\"#{ atts }"
854
            atts << " title=\"#{ htmlesc title }\"" if title
855 856
            atts = shelve( atts ) if atts
            
857
            external = (url =~ /^https?:\/\//) ? ' class="external"' : ''
858 859
            
            "#{ pre }<a#{ atts }#{ external }>#{ text }</a>#{ post }"
860
          end
861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914
        end
    end

    MARKDOWN_REFLINK_RE = /
            \[([^\[\]]+)\]      # $text
            [ ]?                # opt. space
            (?:\n[ ]*)?         # one optional newline followed by spaces
            \[(.*?)\]           # $id
        /x 

    def inline_markdown_reflink( text ) 
        text.gsub!( MARKDOWN_REFLINK_RE ) do |m|
            text, id = $~[1..2]

            if id.empty?
                url, title = check_refs( text )
            else
                url, title = check_refs( id )
            end
            
            atts = " href=\"#{ url }\""
            atts << " title=\"#{ title }\"" if title
            atts = shelve( atts )
            
            "<a#{ atts }>#{ text }</a>"
        end
    end

    MARKDOWN_LINK_RE = /
            \[([^\[\]]+)\]      # $text
            \(                  # open paren
            [ \t]*              # opt space
            <?(.+?)>?           # $href
            [ \t]*              # opt space
            (?:                 # whole title
            (['"])              # $quote
            (.*?)               # $title
            \3                  # matching quote
            )?                  # title is optional
            \)
        /x 

    def inline_markdown_link( text ) 
        text.gsub!( MARKDOWN_LINK_RE ) do |m|
            text, url, quote, title = $~[1..4]

            atts = " href=\"#{ url }\""
            atts << " title=\"#{ title }\"" if title
            atts = shelve( atts )
            
            "<a#{ atts }>#{ text }</a>"
        end
    end

915
    TEXTILE_REFS_RE =  /(^ *)\[([^\[\n]+?)\](#{HYPERLINK})(?=\s|$)/
916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946
    MARKDOWN_REFS_RE = /(^ *)\[([^\n]+?)\]:\s+<?(#{HYPERLINK})>?(?:\s+"((?:[^"]|\\")+)")?(?=\s|$)/m

    def refs( text )
        @rules.each do |rule_name|
            method( rule_name ).call( text ) if rule_name.to_s.match /^refs_/
        end
    end

    def refs_textile( text ) 
        text.gsub!( TEXTILE_REFS_RE ) do |m|
            flag, url = $~[2..3]
            @urlrefs[flag.downcase] = [url, nil]
            nil
        end
    end
    
    def refs_markdown( text )
        text.gsub!( MARKDOWN_REFS_RE ) do |m|
            flag, url = $~[2..3]
            title = $~[6]
            @urlrefs[flag.downcase] = [url, title]
            nil
        end
    end

    def check_refs( text ) 
        ret = @urlrefs[text.downcase] if text
        ret || [text, nil]
    end

    IMAGE_RE = /
947
            (>|\s|^)           # start of line?
948 949 950 951 952 953 954 955 956 957 958 959 960 961
            \!                   # opening
            (\<|\=|\>)?          # optional alignment atts
            (#{C})               # optional style,class atts
            (?:\. )?             # optional dot-space
            ([^\s(!]+?)          # presume this is the src
            \s?                  # optional space
            (?:\(((?:[^\(\)]|\([^\)]+\))+?)\))?   # optional title
            \!                   # closing
            (?::#{ HYPERLINK })? # optional href
        /x 

    def inline_textile_image( text ) 
        text.gsub!( IMAGE_RE )  do |m|
            stln,algn,atts,url,title,href,href_a1,href_a2 = $~[1..8]
jplang's avatar
jplang committed
962
            htmlesc title
963
            atts = pba( atts )
964
            atts = " src=\"#{ htmlesc url.dup }\"#{ atts }"
965 966 967 968 969 970 971 972
            atts << " title=\"#{ title }\"" if title
            atts << " alt=\"#{ title }\"" 
            # size = @getimagesize($url);
            # if($size) $atts.= " $size[3]";

            href, alt_title = check_refs( href ) if href
            url, url_title = check_refs( url )

973
            next m unless uri_with_safe_scheme?(url)
974

975 976 977 978 979 980 981 982 983 984
            out = ''
            out << "<a#{ shelve( " href=\"#{ href }\"" ) }>" if href
            out << "<img#{ shelve( atts ) } />"
            out << "</a>#{ href_a1 }#{ href_a2 }" if href
            
            if algn 
                algn = h_align( algn )
                if stln == "<p>"
                    out = "<p style=\"float:#{ algn }\">#{ out }"
                else
985
                    out = "#{ stln }<span style=\"float:#{ algn }\">#{ out }</span>"
986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000
                end
            else
                out = stln + out
            end

            out
        end
    end

    def shelve( val ) 
        @shelf << val
        " :redsh##{ @shelf.length }:"
    end
    
    def retrieve( text ) 
1001 1002
        text.gsub!(/ :redsh#(\d+):/) do
          @shelf[$1.to_i - 1] || $&
1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037
        end
    end

    def incoming_entities( text ) 
        ## turn any incoming ampersands into a dummy character for now.
        ## This uses a negative lookahead for alphanumerics followed by a semicolon,
        ## implying an incoming html entity, to be skipped

        text.gsub!( /&(?![#a-z0-9]+;)/i, "x%x%" )
    end

    def no_textile( text ) 
        text.gsub!( /(^|\s)==([^=]+.*?)==(\s|$)?/,
            '\1<notextile>\2</notextile>\3' )
        text.gsub!( /^ *==([^=]+.*?)==/m,
            '\1<notextile>\2</notextile>\3' )
    end

    def clean_white_space( text ) 
        # normalize line breaks
        text.gsub!( /\r\n/, "\n" )
        text.gsub!( /\r/, "\n" )
        text.gsub!( /\t/, '    ' )
        text.gsub!( /^ +$/, '' )
        text.gsub!( /\n{3,}/, "\n\n" )
        text.gsub!( /"$/, "\" " )

        # if entire document is indented, flush
        # to the left side
        flush_left text
    end

    def flush_left( text )
        indt = 0
        if text =~ /^ /
1038
            while text !~ /^ {#{indt}}[^ ]/
1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052
                indt += 1
            end unless text.empty?
            if indt.nonzero?
                text.gsub!( /^ {#{indt}}/, '' )
            end
        end
    end

    def footnote_ref( text ) 
        text.gsub!( /\b\[([0-9]+?)\](\s)?/,
            '<sup><a href="#fn\1">\1</a></sup>\2' )
    end
    
    OFFTAGS = /(code|pre|kbd|notextile)/
1053
    OFFTAG_MATCH = /(?:(<\/#{ OFFTAGS }\b>)|(<#{ OFFTAGS }\b[^>]*>))(.*?)(?=<\/?#{ OFFTAGS }\b\W|\Z)/mi
1054 1055 1056 1057 1058 1059 1060
    OFFTAG_OPEN = /<#{ OFFTAGS }/
    OFFTAG_CLOSE = /<\/?#{ OFFTAGS }/
    HASTAG_MATCH = /(<\/?\w[^\n]*?>)/m
    ALLTAG_MATCH = /(<\/?\w[^\n]*?>)|.*?(?=<\/?\w[^\n]*?>|$)/m

    def glyphs_textile( text, level = 0 )
        if text !~ HASTAG_MATCH
1061
            pgl text
1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085
            footnote_ref text
        else
            codepre = 0
            text.gsub!( ALLTAG_MATCH ) do |line|
                ## matches are off if we're between <code>, <pre> etc.
                if $1
                    if line =~ OFFTAG_OPEN
                        codepre += 1
                    elsif line =~ OFFTAG_CLOSE
                        codepre -= 1
                        codepre = 0 if codepre < 0
                    end 
                elsif codepre.zero?
                    glyphs_textile( line, level + 1 )
                else
                    htmlesc( line, :NoQuotes )
                end
                # p [level, codepre, line]

                line
            end
        end
    end

1086
    def rip_offtags( text, escape_aftertag=true, escape_line=true )
1087 1088 1089 1090 1091
        if text =~ /<.*>/
            ## strip and encode <pre> content
            codepre, used_offtags = 0, {}
            text.gsub!( OFFTAG_MATCH ) do |line|
                if $3
1092
                    first, offtag, aftertag = $3, $4, $5
1093 1094 1095
                    codepre += 1
                    used_offtags[offtag] = true
                    if codepre - used_offtags.length > 0
1096
                        htmlesc( line, :NoQuotes ) if escape_line
1097 1098 1099
                        @pre_list.last << line
                        line = ""
                    else
1100 1101 1102 1103 1104
                        ### htmlesc is disabled between CODE tags which will be parsed with highlighter
                        ### Regexp in formatter.rb is : /<code\s+class="(\w+)">\s?(.+)/m
                        ### NB: some changes were made not to use $N variables, because we use "match"
                        ###   and it breaks following lines
                        htmlesc( aftertag, :NoQuotes ) if aftertag && escape_aftertag && !first.match(/<code\s+class="(\w+)">/)
1105
                        line = "<redpre##{ @pre_list.length }>"
1106
                        first.match(/<#{ OFFTAGS }([^>]*)>/)
1107
                        tag = $1
1108
                        $2.to_s.match(/(class\=("[^"]+"|'[^']+'))/i)
1109
                        tag << " #{$1}" if $1 && tag == 'code'
1110
                        @pre_list << "<#{ tag }>#{ aftertag }"
1111 1112 1113
                    end
                elsif $1 and codepre > 0
                    if codepre - used_offtags.length > 0
1114
                        htmlesc( line, :NoQuotes ) if escape_line
1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212
                        @pre_list.last << line
                        line = ""
                    end
                    codepre -= 1 unless codepre.zero?
                    used_offtags = {} if codepre.zero?
                end 
                line
            end
        end
        text
    end

    def smooth_offtags( text )
        unless @pre_list.empty?
            ## replace <pre> content
            text.gsub!( /<redpre#(\d+)>/ ) { @pre_list[$1.to_i] }
        end
    end

    def inline( text ) 
        [/^inline_/, /^glyphs_/].each do |meth_re|
            @rules.each do |rule_name|
                method( rule_name ).call( text ) if rule_name.to_s.match( meth_re )
            end
        end
    end

    def h_align( text ) 
        H_ALGN_VALS[text]
    end

    def v_align( text ) 
        V_ALGN_VALS[text]
    end

    def textile_popup_help( name, windowW, windowH )
        ' <a target="_blank" href="http://hobix.com/textile/#' + helpvar + '" onclick="window.open(this.href, \'popupwindow\', \'width=' + windowW + ',height=' + windowH + ',scrollbars,resizable\'); return false;">' + name + '</a><br />'
    end

    # HTML cleansing stuff
    BASIC_TAGS = {
        'a' => ['href', 'title'],
        'img' => ['src', 'alt', 'title'],
        'br' => [],
        'i' => nil,
        'u' => nil, 
        'b' => nil,
        'pre' => nil,
        'kbd' => nil,
        'code' => ['lang'],
        'cite' => nil,
        'strong' => nil,
        'em' => nil,
        'ins' => nil,
        'sup' => nil,
        'sub' => nil,
        'del' => nil,
        'table' => nil,
        'tr' => nil,
        'td' => ['colspan', 'rowspan'],
        'th' => nil,
        'ol' => nil,
        'ul' => nil,
        'li' => nil,
        'p' => nil,
        'h1' => nil,
        'h2' => nil,
        'h3' => nil,
        'h4' => nil,
        'h5' => nil,
        'h6' => nil, 
        'blockquote' => ['cite']
    }

    def clean_html( text, tags = BASIC_TAGS )
        text.gsub!( /<!\[CDATA\[/, '' )
        text.gsub!( /<(\/*)(\w+)([^>]*)>/ ) do
            raw = $~
            tag = raw[2].downcase
            if tags.has_key? tag
                pcs = [tag]
                tags[tag].each do |prop|
                    ['"', "'", ''].each do |q|
                        q2 = ( q != '' ? q : '\s' )
                        if raw[3] =~ /#{prop}\s*=\s*#{q}([^#{q2}]+)#{q}/i
                            attrv = $1
                            next if prop == 'src' and attrv =~ %r{^(?!http)\w+:}
                            pcs << "#{prop}=\"#{$1.gsub('"', '\\"')}\""
                            break
                        end
                    end
                end if tags[tag]
                "<#{raw[1]}#{pcs.join " "}>"
            else
                " "
            end
        end
    end
jplang's avatar
jplang committed
1213 1214
    
    
jplang's avatar
jplang committed
1215
    ALLOWED_TAGS = %w(redpre pre code kbd notextile)
jplang's avatar
jplang committed
1216
    def escape_html_tags(text)
jplang's avatar
jplang committed
1217
      text.gsub!(%r{<(\/?([!\w]+)[^<>\n]*)(>?)}) {|m| ALLOWED_TAGS.include?($2) ? "<#{$1}#{$3}" : "&lt;#{$1}#{'&gt;' unless $3.blank?}" }
jplang's avatar
jplang committed
1218
    end
1219 1220
end