Class: BlueFeather::Parser

Inherits:
Object
  • Object
show all
Defined in:
lib/bluefeather.rb

Defined Under Namespace

Classes: RenderState

Constant Summary collapse

TabWidth =

Tab width for #detab! if none is specified

4
EmptyElementSuffix =

The tag-closing string – set to ‘>’ for HTML

" />"
EscapeTable =

Table of MD5 sums for escaped characters

{}
StrictBlockTags =

The list of tags which are considered block-level constructs and an alternation pattern suitable for use in regexps made from the list

%w[ p div h[1-6] blockquote pre table dl ol ul script noscript
form fieldset iframe math ins del ]
StrictTagPattern = 
StrictBlockTags.join('|')
LooseBlockTags = 
StrictBlockTags - %w[ins del]
LooseTagPattern = 
LooseBlockTags.join('|')
StrictBlockRegexp =

Nested blocks: <div> <div> tags for inner block must be indented. </div> </div>

%r{
      ^            # Start of line
      <(#{StrictTagPattern}) # Start tag: \2
      \b           # word break
      (.*\n)*?       # Any number of lines, minimal match
      </\1>          # Matching end tag
      [ ]*         # trailing spaces
      $            # End of line or document
}ix
LooseBlockRegexp =

More-liberal block-matching

%r{
      ^            # Start of line
      <(#{LooseTagPattern})  # start tag: \2
      \b           # word break
      (.*\n)*?       # Any number of lines, minimal match
      .*</\1>          # Anything + Matching end tag
      [ ]*         # trailing spaces
      $            # End of line or document
}ix
HruleBlockRegexp =

Special case for <hr />.

%r{
      (            # $1
\A\n?       # Start of doc + optional \n
|         # or
.*\n\n        # anything + blank line
      )
      (            # save in $2
            # BlueFeather fix: Not allow any space on line top
<hr         # Tag open
\b          # Word break
([^<>])*?   # Attributes
/?>         # Tag close
$           # followed by a blank line or end of document
      )
}ix
LinkRegexp =

Link defs are in the form: ^[id]: url “optional title”

%r{
      ^[ ]{0,#{TabWidth - 1}} # BlueFeather fix: indent < tab width
      \[(.+)\]:    # id = $1
 [ ]*
 \n?        # maybe *one* newline
 [ ]*
      <?(\S+?)>?       # url = $2
 [ ]*
 \n?        # maybe one newline
 [ ]*
      (?:
# Titles are delimited by "quotes" or (parens).
["(]
(.+?)     # title = $3
[")]      # Matching ) or "
[ ]*
      )? # title is optional
      (?:\n+|\Z)
}x
FootnoteDefinitionRegexp =

Footnotes defs are in the form: [^id]: footnote contents.

%r{
  ^[ ]{0,#{TabWidth - 1}}
  \[\^(.+?)\]\:    # id = $1
  [ ]*
  (.*)       # first line content = $2
  (?:\n|\Z)
  
  ( # second or more lines content = $3
    (?: 
      [ ]{#{TabWidth},} # indented
      .*
      (?:\n|\Z)
    |
      \n # blank line
    )*
  )?
  
}x
FootnoteIdRegexp = 
/^[a-zA-Z0-9\:\._-]+$/
TOCRegexp = 
%r{
  ^\{    # bracket on line-head 
  [ ]*    # optional inner space 
  toc
  
  (?:
    (?:
      [:]    # colon
      |      # or
      [ ]+   # 1 or more space
    )
    (.+?)    # $1 = parameter
  )?
  
  [ ]*    # optional inner space
  \}     # closer
  [ ]*$   # optional space on line-foot
}ix
TOCStartLevelRegexp = 
%r{
  ^
  (?:              # optional start
    h 
    ([1-6])        # $1 = start level
  )?
  
  (?:              # range symbol
    [.]{2,}|[-]    # .. or -
  )
  
  (?:              # optional end
    h?             # optional 'h'
    ([1-6])        # $2 = end level
  )?$
}ix
TableRegexp = 
%r{
  (?:
    ^([ ]{0,#{TabWidth - 1}}) # not indented
    (?:[|][ ]*)   # NOT optional border
    
    \S.*?  # 1st cell content
      
    (?:    # 2nd cell or later
      [|]    # cell splitter
      .+?    # content
    )+     # 1 or more..

    [|]?   # optional border
    (?:\n|\Z)  # line end
  )+
}x
TableSeparatorCellRegexp = 
%r{
  ^
  [ ]*
  ([:])?  # $1 = left-align symbol
  [ ]*
  [-]+    # border
  [ ]*
  ([:])?  # $2 = right-align symbol
  [ ]*
  $
}x
ListMarkerOl =

Patterns to match and transform lists

%r{\d+\.}
ListMarkerUl = 
%r{[*+-]}
ListMarkerAny = 
Regexp::union( ListMarkerOl, ListMarkerUl )
ListRegexp = 
%r{
 (?:
^[ ]{0,#{TabWidth - 1}}   # Indent < tab width
(#{ListMarkerAny})      # unordered or ordered ($1)
[ ]+            # At least one space
 )
 (?m:.+?)           # item content (include newlines)
 (?:
  \z            # Either EOF
|             #  or
  \n{2,}          # Blank line...
  (?=\S)          # ...followed by non-space
  (?![ ]*         # ...but not another item
  (#{ListMarkerAny})
   [ ]+)
 )
}x
ListItemRegexp =

Pattern for transforming list items

%r{
      (\n)?              # leading line = $1
      (^[ ]*)              # leading whitespace = $2
      (#{ListMarkerAny}) [ ]+      # list marker = $3
      ((?m:.+?)            # list item text   = $4
      \n)
      (?= (\n*) (\z | \2 (#{ListMarkerAny}) [ ]+))
}x
DefinitionListRegexp = 
%r{
  (?:
    (?:^.+\n)+ # dt
    \n*
    (?:
      ^[ ]{0,#{TabWidth - 1}} # Indent < tab width
      \: # dd marker (line head)
      [ ]* # space
      ((?m:.+?)) # dd content
      (?:
        \s*\z # end of string
        | # or
        \n{2,} # blank line
        (?=[ ]{0,#{TabWidth - 1}}\S) # ...followed by
      )
    )+
  )+
}x
DDLineRegexp = 
/^\:[ ]{0,#{TabWidth - 1}}(.*)/
CodeBlockRegexp =

Pattern for matching codeblocks

%r{
      (?:\n\n|\A|\A\n)
      (                  # $1 = the code block
 (?:
(?:[ ]{#{TabWidth}} | \t)   # a tab or tab-width of spaces
.*\n+
 )+
      )
      (^[ ]{0,#{TabWidth - 1}}\S|\Z)   # Lookahead for non-space at
                # line-start, or end of doc
}x
FencedCodeBlockRegexp = 
/^(\~{3,})\n((?m:.+?)\n)\1\n/
BlockQuoteRegexp =

Pattern for matching Markdown blockquote blocks

%r{
 (?:
^[ ]*>[ ]?    # '>' at the start of a line
  .+\n      # rest of the first line
(?:.+\n)*   # subsequent consecutive lines
\n*       # blanks
 )+
}x
PreChunk = 
%r{ ( ^ \s* <pre> .+? </pre> ) }xm
AutoAnchorURLRegexp =

$1 = url

/<(#{URI.regexp})>/
AutoAnchorEmailRegexp =

$2 = address

/<([^'">\s]+?\@[^'">\s]+[.][a-zA-Z]+)>/
Encoders =

Encoder functions to turn characters of an email address into encoded entities.

[
  lambda {|char| "&#%03d;" % char},
  lambda {|char| "&#x%X;" % char},
  lambda {|char| char.chr },
]
SetextHeaderRegexp =

Regexp for matching Setext-style headers

%r{
      (.+?)      # The title text ($1)
      
      (?: # Markdown Extra: Header Id Attribute (optional)
        [ ]* # space after closing #'s
        \{\#
(\S+?) # $2 = Id
        \}
        [ \t]* # allowed lazy spaces
      )?
      \n
      ([\-=])+   # Match a line of = or -. Save only one in $3.
      [ ]*\n+
}x
AtxHeaderRegexp =

Regexp for matching ATX-style headers

%r{
      ^(\#+) # $1 = string of #'s
      [ ]*
      (.+?)    # $2 = Header text
      [ ]*
      \#*      # optional closing #'s (not counted)
      
      (?: # Markdown Extra: Header Id Attribute (optional)
[ ]* # space after closing #'s
\{\#
  (\S+?) # $3 = Id
\}
[ \t]* # allowed lazy spaces
      )?
      
      \n+
}x
HeaderRegexp = 
Regexp.union(SetextHeaderRegexp, AtxHeaderRegexp)
IdRegexp = 
/^[a-zA-Z][a-zA-Z0-9\:\._-]*$/
RefLinkIdRegexp =

Pattern to match the linkid part of an anchor tag for reference-style links.

%r{
      [ ]?         # Optional leading space
      (?:\n[ ]*)?        # Optional newline + spaces
      \[
(.*?)       # Id = $1
      \]
}x
InlineLinkRegexp = 
%r{
      \(           # Literal paren
[ ]*        # Zero or more spaces
<?(.+?)>?     # URI = $1
[ ]*        # Zero or more spaces
(?:         # 
  ([\"\'])   # Opening quote char = $2
  (.*?)      # Title = $3
  \2       # Matching quote char
)?          # Title is optional
      \)
}x
BoldRegexp =

Pattern to match strong emphasis in Markdown text

%r{ (\*\*|__) (\S|\S.*?\S) \1 }x
ItalicRegexp =

Pattern to match normal emphasis in Markdown text

%r{ (\*|_) (\S|\S.*?\S) \1 }x
InlineImageRegexp =

Next, handle inline images: ![alt text](url “optional title”) Don’t forget: encode * and _

%r{
      (          # Whole match = $1
!\[ (.*?) \]  # alt text = $2
 \([ ]*
<?(\S+?)>?    # source url = $3
   [ ]*
(?:       # 
  (["'])    # quote char = $4
  (.*?)     # title = $5
  \4      # matching quote
  [ ]*
)?        # title is optional
 \)
      )
}x
ReferenceImageRegexp =

Reference-style images

%r{
      (          # Whole match = $1
!\[ (.*?) \]  # Alt text = $2
[ ]?      # Optional space
(?:\n[ ]*)?   # One optional newline + spaces
\[ (.*?) \]   # id = $3
      )
}x
CodeEscapeRegexp =

Regexp to match special characters in a code block

%r{( \* | _ | \{ | \} | \[ | \] | \\ )}x
HTMLCommentRegexp =

Matching constructs for tokenizing X/HTML

%r{ <! ( -- .*? -- \s* )+ > }mx
XMLProcInstRegexp = 
%r{ <\? .*? \?> }mx
MetaTag = 
Regexp::union( HTMLCommentRegexp, XMLProcInstRegexp )
HTMLTagOpenRegexp = 
%r{ < [a-z/!$] [^<>]* }imx
HTMLTagCloseRegexp = 
%r{ > }x
HTMLTagPart = 
Regexp::union( HTMLTagOpenRegexp, HTMLTagCloseRegexp )

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(*restrictions) ⇒ Parser

Create a new BlueFeather parser.



404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
 
# File 'lib/bluefeather.rb', line 404

def initialize(*restrictions)
  @log = Logger::new( $deferr )
  @log.level = $DEBUG ?
    Logger::DEBUG :
    ($VERBOSE ? Logger::INFO : Logger::WARN)
  @scanner = nil
  
  # Add any restrictions, and set the line-folding attribute to reflect

  # what happens by default.

  @filter_html = nil
  @filter_styles = nil
  restrictions.flatten.each {|r| __send__("#{r}=", true) }
  @fold_lines = true
  
  @use_header_id = true
  @display_warnings = true
  
  @log.debug "String is: %p" % self
end

Instance Attribute Details

#display_warnings ⇒ Object

BlueFeather Extension: display warnings on the top of output html (default: true)



439
440
441
 
# File 'lib/bluefeather.rb', line 439

def display_warnings
  @display_warnings
end

#filter_html ⇒ Object

Filters for controlling what gets output for untrusted input. (But really, you’re filtering bad stuff out of untrusted input at submission-time via untainting, aren’t you?)



432
433
434
 
# File 'lib/bluefeather.rb', line 432

def filter_html
  @filter_html
end

#filter_styles ⇒ Object

Filters for controlling what gets output for untrusted input. (But really, you’re filtering bad stuff out of untrusted input at submission-time via untainting, aren’t you?)



432
433
434
 
# File 'lib/bluefeather.rb', line 432

def filter_styles
  @filter_styles
end

#fold_lines ⇒ Object

RedCloth-compatibility accessor. Line-folding is part of Markdown syntax, so this isn’t used by anything.



436
437
438
 
# File 'lib/bluefeather.rb', line 436

def fold_lines
  @fold_lines
end

#use_header_id ⇒ Object

BlueFeather Extension: add id to each header, for toc and anchors. (default: true)



442
443
444
 
# File 'lib/bluefeather.rb', line 442

def use_header_id
  @use_header_id
end

Instance Method Details

#apply_block_transforms(str, rs) ⇒ Object

Do block-level transforms on a copy of str using the specified render state rs and return the results.



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
 
# File 'lib/bluefeather.rb', line 669

def apply_block_transforms( str, rs )
  rs.block_transform_depth += 1

  # Port: This was called '_runBlockGamut' in the original

  
  @log.debug "Applying block transforms to:\n  %p" % str
  text = str
  text = pretransform_fenced_code_blocks( text, rs )
  text = pretransform_block_separators(text, rs)
  
  text = transform_headers( text, rs )
  text = transform_toc(text, rs)
  
  text = transform_hrules( text, rs )
  text = transform_lists( text, rs )
  text = transform_definition_lists( text, rs ) # BlueFeather Extension

  text = transform_code_blocks( text, rs )
  text = transform_block_quotes( text, rs )
  text = hide_html_blocks( text, rs )
  
  text = transform_tables(text, rs)
  text = form_paragraphs( text, rs )
  
  rs.block_transform_depth -= 1
  @log.debug "Done with block transforms:\n  %p" % text
  return text
end

#apply_span_transforms(str, rs) ⇒ Object

Apply Markdown span transforms to a copy of the specified str with the given render state rs and return it.



700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
 
# File 'lib/bluefeather.rb', line 700

def apply_span_transforms( str, rs )
  @log.debug "Applying span transforms to:\n  %p" % str
  
  str = transform_code_spans( str, rs )
  str = transform_auto_links( str, rs )
  str = encode_html( str )
  str = transform_images( str, rs )
  str = transform_anchors( str, rs )
  str = transform_italic_and_bold( str, rs )
  
  # Hard breaks

  str.gsub!( / {2,}\n/, "<br#{EmptyElementSuffix}\n" )
  
  @log.debug "Done with span transforms:\n  %p" % str
  return str
end

#detab(str, tabwidth = TabWidth) ⇒ Object

Convert tabs in str to spaces. (this method is reformed to function-like method from original BlueCloth)



654
655
656
657
658
659
660
661
662
 
# File 'lib/bluefeather.rb', line 654

def detab( str, tabwidth=TabWidth )
  re = str.split( /\n/ ).collect {|line|
    line.gsub( /(.*?)\t/ ) do
      $1 + ' ' * (tabwidth - $1.length % tabwidth)
    end
  }.join("\n")
  
  re
end

#document_to_html(doc) ⇒ Object Also known as: doc2html 



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
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
 
# File 'lib/bluefeather.rb', line 559

def document_to_html(doc)
  rs = RenderState.new
  if doc.numbering? then
    rs.numbering = true
  end
  rs.numbering_start_level = doc.numbering_start_level
  
  body_html = nil
  
  if doc.encoding_type then
    Util.change_kcode(doc.kcode){
      body_html = parse_text(doc.body, rs)
    }
  else
    body_html = parse_text(doc.body, rs)
  end
  
  out = Util.generate_blank_string_io(doc.body)
  
  # XHTML decleration

  out.puts %Q|<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">|
  
  # html start

  out.puts %Q|<html>|
  
  # head

  out.puts %Q|<head>|
  
  if doc.encoding_type and (charset = EncodingType.type_to_charset(doc.encoding_type)) then
    out.puts %Q|<meta http-equiv="Content-Type" content="text/html; charset=#{charset}" />|
  end
  
  h1 = rs.headers.find{|x| x.level == 1}
  h1_content = (h1 ? h1.content : nil)
  title = Util.escape_html(doc.title || h1_content || 'no title (Generated by BlueFeather)')
  out.puts %Q|<title>#{title}</title>|

  %w(description keywords).each do |name|
    if doc[name] then
      content = Util.escape_html(doc[name])
      out.puts %Q|<meta name="#{name}" content="#{content}" />|
    end
  end


  if doc['css'] then
    href = Util.escape_html(doc.css)
    out.puts %Q|<link rel="stylesheet" type="text/css" href="#{href}" />|
    
  end
  
  if doc['rdf-feed'] then
    href = Util.escape_html(doc['rdf-feed'])
    out.puts %Q|<link rel="alternate" type="application/rdf+xml" href="#{href}" />|
  end

  
  
  if doc['rss-feed'] then
    href = Util.escape_html(doc['rss-feed'])
    out.puts %Q|<link rel="alternate" type="application/rss+xml" href="#{href}" />|
  end
  
  if doc['atom-feed'] then
    href = Util.escape_html(doc['atom-feed'])
    out.puts %Q|<link rel="alternate" type="application/atom+xml" href="#{href}" />|
  end
        
  out.puts %Q|</head>|
  
  # body

  out.puts %Q|<body>|
  out.puts
  out.puts body_html
  out.puts
  out.puts %Q|</body>|
  
  # html end

  out.puts %Q|</html>|

  
  return out.string
end

#encode_backslash_escapes(str) ⇒ Object

Return a copy of the given str with any backslashed special character in it replaced with MD5 placeholders.



928
929
930
931
932
933
934
935
936
937
938
939
 
# File 'lib/bluefeather.rb', line 928

def encode_backslash_escapes( str )
  # Make a copy with any double-escaped backslashes encoded

  text = str.gsub( /\\\\/, EscapeTable['\\\\'][:md5] )
  
  EscapeTable.each_pair {|char, esc|
    next if char == '\\\\'
    next unless char =~ /\\./
    text.gsub!( esc[:re], esc[:md5] )
  }
  
  return text
end

#encode_code(str, rs) ⇒ Object

Escape any characters special to HTML and encode any characters special to Markdown in a copy of the given str and return it.



1936
1937
1938
1939
1940
1941
 
# File 'lib/bluefeather.rb', line 1936

def encode_code( str, rs )
  str.gsub( %r{&}, '&amp;' ).
    gsub( %r{<}, '&lt;' ).
    gsub( %r{>}, '&gt;' ).
    gsub( CodeEscapeRegexp ) {|match| EscapeTable[match][:md5]}
end

#encode_email_address(addr) ⇒ Object

Transform a copy of the given email addr into an escaped version safer for posting publicly.



1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
 
# File 'lib/bluefeather.rb', line 1457

def encode_email_address( addr )
  
  rval = ''
  ("mailto:" + addr).each_byte {|b|
    case b
    when ?:
      rval += ":"
    when ?@
      rval += Encoders[ rand(2) ][ b ]
    else
      r = rand(100)
      rval += (
        r > 90 ? Encoders[2][ b ] :
        r < 45 ? Encoders[1][ b ] :
             Encoders[0][ b ]
      )
    end
  }
  
  return %{<a href="%s">%s</a>} % [ rval, rval.sub(/.+?:/, '') ]
end

#encode_html(str) ⇒ Object

Return a copy of str with angle brackets and ampersands HTML-encoded.



2038
2039
2040
2041
 
# File 'lib/bluefeather.rb', line 2038

def encode_html( str )
  str.gsub( /&(?!#?[x]?(?:[0-9a-f]+|\w+);)/i, "&amp;" ).
    gsub( %r{<(?![a-z/?\$!])}i, "&lt;" )
end

#escape_md(str) ⇒ Object

Escape any markdown characters in a copy of the given str and return it.



1950
1951
1952
1953
 
# File 'lib/bluefeather.rb', line 1950

def escape_md( str )
  str.
    gsub( /\*|_/ ){|symbol| EscapeTable[symbol][:md5]}
end

#escape_special_chars(str) ⇒ Object

Escape special characters in the given str



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
 
# File 'lib/bluefeather.rb', line 884

def escape_special_chars( str )
  @log.debug "  Escaping special characters"
  text = ''
  
  # The original Markdown source has something called '$tags_to_skip'

  # declared here, but it's never used, so I don't define it.

  
  tokenize_html( str ) {|token, str|
    @log.debug "   Adding %p token %p" % [ token, str ]
    case token
  
    # Within tags, encode * and _

    when :tag
      text += str.
        gsub( /\*/, EscapeTable['*'][:md5] ).
        gsub( /_/, EscapeTable['_'][:md5] )
  
    # Encode backslashed stuff in regular text

    when :text
      text += encode_backslash_escapes( str )
    else
      raise TypeError, "Unknown token type %p" % token
    end
  }
  
  @log.debug "  Text with escapes is now: %p" % text
  return text
end

#form_paragraphs(str, rs) ⇒ Object

Wrap all remaining paragraph-looking text in a copy of str inside <p> tags and return it.



1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
 
# File 'lib/bluefeather.rb', line 1604

def form_paragraphs( str, rs )
  @log.debug " Forming paragraphs"
  grafs = str.
    sub( /\A\n+/, '' ).
    sub( /\n+\z/, '' ).
    split( /\n{2,}/ )
  
  rval = grafs.collect {|graf|
  
    # Unhashify HTML blocks if this is a placeholder

    if rs.html_blocks.key?( graf )
      rs.html_blocks[ graf ]
    
    # no output if this is block separater

    elsif graf == '~' then
      ''
  
    # Otherwise, wrap in <p> tags

    else
      apply_span_transforms(graf, rs).
        sub( /^[ ]*/, '<p>' ) + '</p>'
    end
  }.join( "\n\n" )
  
  @log.debug " Formed paragraphs: %p" % rval
  return rval
end

#hide_html_blocks(str, rs) ⇒ Object

Replace all blocks of HTML in str that start in the left margin with tokens.



773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
 
# File 'lib/bluefeather.rb', line 773

def hide_html_blocks( str, rs )
  @log.debug "Hiding HTML blocks in %p" % str
  
  # Tokenizer proc to pass to gsub

  tokenize = lambda {|match|
    key = Digest::MD5::hexdigest( match )
    rs.html_blocks[ key ] = match
    @log.debug "Replacing %p with %p" % [ match, key ]
    "\n\n#{key}\n\n"
  }
  
  rval = str.dup
  
  @log.debug "Finding blocks with the strict regex..."
  rval.gsub!( StrictBlockRegexp, &tokenize )
  
  @log.debug "Finding blocks with the loose regex..."
  rval.gsub!( LooseBlockRegexp, &tokenize )
  
  @log.debug "Finding hrules..."
  rval.gsub!( HruleBlockRegexp ) {|match| $1 + tokenize[$2] }
  
  return rval
end

#indent(str) ⇒ Object 



2050
2051
2052
 
# File 'lib/bluefeather.rb', line 2050

def indent(str)
  str.gsub( /^/, ' ' * TabWidth)
end

#outdent(str) ⇒ Object

Return one level of line-leading tabs or spaces from a copy of str and return it.



2046
2047
2048
 
# File 'lib/bluefeather.rb', line 2046

def outdent( str )
  str.gsub( /^(\t|[ ]{1,#{TabWidth}})/, '')
end

#parse_document(source, default_enc = EncodingType::UTF8) ⇒ Object 



543
544
545
546
547
 
# File 'lib/bluefeather.rb', line 543

def parse_document(source, default_enc = EncodingType::UTF8)
  doc = Document.parse(source, default_enc)
  
  return document_to_html(doc)
end

#parse_document_file(path, default_enc = EncodingType::UTF8) ⇒ Object 



549
550
551
552
553
554
555
556
 
# File 'lib/bluefeather.rb', line 549

def parse_document_file(path, default_enc = EncodingType::UTF8)
  doc = nil
  open(path){|f|
    doc = Document.parse_io(f, default_enc)
  }
  
  return document_to_html(doc)
end

#parse_text(source, rs = nil) ⇒ Object Also known as: parse

Render Markdown-formatted text in this string object as HTML and return it. The parameter is for compatibility with RedCloth, and is currently unused, though that may change in the future.



447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
 
# File 'lib/bluefeather.rb', line 447

def parse_text(source, rs = nil)
  rs ||= RenderState.new
  
  # Create a StringScanner we can reuse for various lexing tasks

  @scanner = StringScanner::new( '' )
  
  # Make a copy of the string with normalized line endings, tabs turned to

  # spaces, and a couple of guaranteed newlines at the end

  
  text = detab(source.gsub( /\r\n?/, "\n" ))
  text += "\n\n"
  @log.debug "Normalized line-endings: %p" % text
  
  # Filter HTML if we're asked to do so

  if self.filter_html
    text.gsub!( "<", "&lt;" )
    text.gsub!( ">", "&gt;" )
    @log.debug "Filtered HTML: %p" % text
  end
  
  # Simplify blank lines

  text.gsub!( /^ +$/, '' )
  @log.debug "Tabs -> spaces/blank lines stripped: %p" % text
  
  
  # Replace HTML blocks with placeholders

  text = hide_html_blocks( text, rs )
  @log.debug "Hid HTML blocks: %p" % text
  @log.debug "Render state: %p" % rs
  
  
  # Strip footnote definitions, store in render state

  text = strip_footnote_definitions( text, rs )
  @log.debug "Stripped footnote definitions: %p" % text
  @log.debug "Render state: %p" % rs

  
  # Strip link definitions, store in render state

  text = strip_link_definitions( text, rs )
  @log.debug "Stripped link definitions: %p" % text
  @log.debug "Render state: %p" % rs
  
  # Escape meta-characters

  text = escape_special_chars( text )
  @log.debug "Escaped special characters: %p" % text
  
  # Transform block-level constructs

  text = apply_block_transforms( text, rs )
  @log.debug "After block-level transforms: %p" % text
  
  # Now swap back in all the escaped characters

  text = unescape_special_chars( text )
  @log.debug "After unescaping special characters: %p" % text
  
  # Extend footnotes

  unless rs.footnotes.empty? then
    text << %Q|<div class="footnotes"><hr#{EmptyElementSuffix}\n<ol>\n|
    rs.found_footnote_ids.each do |id|
      content = rs.footnotes[id]
      html = apply_block_transforms(content.sub(/\n+\Z/, '') + %Q| <a href="#footnote-ref:#{id}" rev="footnote">&#8617;</a>|, rs)
      text << %Q|<li id="footnote:#{id}">\n#{html}\n</li>|
    end
    text << %Q|</ol>\n</div>\n|
  end
  
  # Display warnings

  if @display_warnings then
    unless rs.warnings.empty? then
      html = %Q|<pre><strong>[WARNINGS]\n|
      html << rs.warnings.map{|x| Util.escape_html(x)}.join("\n")
      html << %Q|</strong></pre>|
      
      text = html + text
    end
  end
  
  return text
end

#parse_text_file(path) ⇒ Object Also known as: parse_file 



536
537
538
 
# File 'lib/bluefeather.rb', line 536

def parse_text_file(path)
  parse_text(File.read(path))
end

#parse_text_with_render_state(str, rs = nil) ⇒ Object

return values are extended. (mainly for testing)



529
530
531
532
533
534
 
# File 'lib/bluefeather.rb', line 529

def parse_text_with_render_state(str, rs = nil)
  rs ||= RenderState.new
  html = parse_text(str, rs)
  
  return [html, rs]
end

#pretransform_block_separators(str, rs) ⇒ Object 



942
943
944
945
946
 
# File 'lib/bluefeather.rb', line 942

def pretransform_block_separators(str, rs)
  str.gsub(/^[ ]{0,#{TabWidth - 1}}[~][ ]*\n/){
    "\n~\n\n"
  }
end

#pretransform_fenced_code_blocks(str, rs) ⇒ Object 



1377
1378
1379
1380
1381
1382
1383
 
# File 'lib/bluefeather.rb', line 1377

def pretransform_fenced_code_blocks( str, rs )
  @log.debug " Transforming fenced code blocks => standard code blocks"
  
  str.gsub( FencedCodeBlockRegexp ) {|block|
    "\n~\n\n" + indent($2) + "\n~\n\n"
  }
end

#strip_footnote_definitions(str, rs) ⇒ Object 



857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
 
# File 'lib/bluefeather.rb', line 857

def strip_footnote_definitions(str, rs)
  str.gsub( FootnoteDefinitionRegexp ) {|match|
    id = $1; content1 = $2; content2 = $3
    
    unless id =~ FootnoteIdRegexp then
      rs.warnings << "illegal footnote id - #{id} (legal chars: a-zA-Z0-9_-.:)"
    end
    
    if content2 then
      @log.debug "   Stripping multi-line definition %p, %p" % [$2, $3]
      content = content1 + "\n" + outdent(content2.chomp)
      @log.debug "   Stripped multi-line definition %p, %p" % [id, content]
      rs.footnotes[id] = content
    else
      content = content1 || ''
      @log.debug "   Stripped single-line definition %p, %p" % [id, content]
      rs.footnotes[id] = content
    end
    
    

    ""
  }
end

#strip_link_definitions(str, rs) ⇒ Object

Strip link definitions from str, storing them in the given RenderState rs.



822
823
824
825
826
827
828
829
830
831
832
833
 
# File 'lib/bluefeather.rb', line 822

def strip_link_definitions( str, rs )
  str.gsub( LinkRegexp ) {|match|
    id, url, title = $1, $2, $3
    
    rs.urls[ id.downcase ] = encode_html( url )
    unless title.nil?
      rs.titles[ id.downcase ] = title.gsub( /"/, "&quot;" )
    end

    ""
  }
end

#tokenize_html(str) ⇒ Object

Break the HTML source in str into a series of tokens and return them. The tokens are just 2-element Array tuples with a type and the actual content. If this function is called with a block, the type and text parts of each token will be yielded to it one at a time as they are extracted.



1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
 
# File 'lib/bluefeather.rb', line 1970

def tokenize_html( str )
  depth = 0
  tokens = []
  @scanner.string = str.dup
  type, token = nil, nil
  
  until @scanner.empty?
    @log.debug "Scanning from %p" % @scanner.rest
  
    # Match comments and PIs without nesting

    if (( token = @scanner.scan(MetaTag) ))
      type = :tag
  
    # Do nested matching for HTML tags

    elsif (( token = @scanner.scan(HTMLTagOpenRegexp) ))
      tagstart = @scanner.pos
      @log.debug " Found the start of a plain tag at %d" % tagstart
  
      # Start the token with the opening angle

      depth = 1
      type = :tag
  
      # Scan the rest of the tag, allowing unlimited nested <>s. If

      # the scanner runs out of text before the tag is closed, raise

      # an error.

      while depth.nonzero?
  
        # Scan either an opener or a closer

        chunk = @scanner.scan( HTMLTagPart ) or
          raise "Malformed tag at character %d: %p" % 
            [ tagstart, token + @scanner.rest ]
          
        @log.debug "  Found another part of the tag at depth %d: %p" % [ depth, chunk ]
  
        token += chunk
  
        # If the last character of the token so far is a closing

        # angle bracket, decrement the depth. Otherwise increment

        # it for a nested tag.

        depth += ( token[-1, 1] == '>' ? -1 : 1 )
        @log.debug "  Depth is now #{depth}"
      end
  
    # Match text segments

    else
      @log.debug " Looking for a chunk of text"
      type = :text
  
      # Scan forward, always matching at least one character to move

      # the pointer beyond any non-tag '<'.

      token = @scanner.scan_until( /[^<]+/m )
    end
  
    @log.debug " type: %p, token: %p" % [ type, token ]
  
    # If a block is given, feed it one token at a time. Add the token to

    # the token list to be returned regardless.

    if block_given?
      yield( type, token )
    end
    tokens << [ type, token ]
  end
  
  return tokens
end

#transform_anchors(str, rs) ⇒ Object

Apply Markdown anchor transforms to a copy of the specified str with the given render state rs and return it.



1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
 
# File 'lib/bluefeather.rb', line 1658

def transform_anchors( str, rs )
  @log.debug " Transforming anchors"
  @scanner.string = str.dup
  text = ''
  
  # Scan the whole string

  until @scanner.empty?
  
    if @scanner.scan( /\[/ )
      link = ''; linkid = ''
      depth = 1
      startpos = @scanner.pos
      @log.debug " Found a bracket-open at %d" % startpos
  
      # Scan the rest of the tag, allowing unlimited nested []s. If

      # the scanner runs out of text before the opening bracket is

      # closed, append the text and return (wasn't a valid anchor).

      while depth.nonzero?
        linktext = @scanner.scan_until( /\]|\[/ )
  
        if linktext
          @log.debug "  Found a bracket at depth %d: %p" % [ depth, linktext ]
          link += linktext
  
          # Decrement depth for each closing bracket

          depth += ( linktext[-1, 1] == ']' ? -1 : 1 )
          @log.debug "  Depth is now #{depth}"
  
        # If there's no more brackets, it must not be an anchor, so

        # just abort.

        else
          @log.debug "  Missing closing brace, assuming non-link."
          link += @scanner.rest
          @scanner.terminate
          return text + '[' + link
        end
      end
      link.slice!( -1 ) # Trim final ']'

      @log.debug " Found leading link %p" % link
      
      
  
      # Markdown Extra: Footnote

      if link =~ /^\^(.+)/ then
        id = $1
        if rs.footnotes[id] then
          rs.found_footnote_ids << id
          label = "[#{rs.found_footnote_ids.size}]"
        else
          rs.warnings << "undefined footnote id - #{id}"
          label = '[?]'
        end
        
        text += %Q|<sup id="footnote-ref:#{id}"><a href="#footnote:#{id}" rel="footnote">#{label}</a></sup>|
        
      # Look for a reference-style second part

      elsif @scanner.scan( RefLinkIdRegexp )
        linkid = @scanner[1]
        linkid = link.dup if linkid.empty?
        linkid.downcase!
        @log.debug "  Found a linkid: %p" % linkid
  
        # If there's a matching link in the link table, build an

        # anchor tag for it.

        if rs.urls.key?( linkid )
          @log.debug "   Found link key in the link table: %p" % rs.urls[linkid]
          url = escape_md( rs.urls[linkid] )
  
          text += %{<a href="#{url}"}
          if rs.titles.key?(linkid)
            text += %{ title="%s"} % escape_md( rs.titles[linkid] )
          end
          text += %{>#{link}</a>}
  
        # If the link referred to doesn't exist, just append the raw

        # source to the result

        else
          @log.debug "  Linkid %p not found in link table" % linkid
          @log.debug "  Appending original string instead: "
          @log.debug "%p" % @scanner.string[ startpos-1 .. @scanner.pos-1 ]
          
          rs.warnings << "link-id not found - #{linkid}"
          text += @scanner.string[ startpos-1 .. @scanner.pos-1 ]
        end
  
      # ...or for an inline style second part

      elsif @scanner.scan( InlineLinkRegexp )
        url = @scanner[1]
        title = @scanner[3]
        @log.debug "  Found an inline link to %p" % url
  
        text += %{<a href="%s"} % escape_md( url )
        if title
          title.gsub!( /"/, "&quot;" )
          text += %{ title="%s"} % escape_md( title )
        end
        text += %{>#{link}</a>}
  
      # No linkid part: just append the first part as-is.

      else
        @log.debug "No linkid, so no anchor. Appending literal text."
        text += @scanner.string[ startpos-1 .. @scanner.pos-1 ]
      end # if linkid

  
    # Plain text

    else
      @log.debug " Scanning to the next link from %p" % @scanner.rest
      text += @scanner.scan( /[^\[]+/ )
    end
  
  end # until @scanner.empty?

  
  return text
end

#transform_auto_links(str, rs) ⇒ Object

Transform URLs in a copy of the specified str into links and return it.



1437
1438
1439
1440
1441
1442
1443
1444
 
# File 'lib/bluefeather.rb', line 1437

def transform_auto_links( str, rs )
  @log.debug " Transforming auto-links"
  str.gsub(AutoAnchorURLRegexp){
    %|<a href="#{Util.escape_html($1)}">#{Util.escape_html($1)}</a>|
  }.gsub( AutoAnchorEmailRegexp ) {|addr|
    encode_email_address( unescape_special_chars($1) )
  }
end

#transform_block_quotes(str, rs) ⇒ Object

Transform Markdown-style blockquotes in a copy of the specified str and return it.



1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
 
# File 'lib/bluefeather.rb', line 1400

def transform_block_quotes( str, rs )
  @log.debug " Transforming block quotes"
  
  str.gsub( BlockQuoteRegexp ) {|quote|
    @log.debug "Making blockquote from %p" % quote
  
    quote.gsub!( /^ *> ?/, '' ) # Trim one level of quoting 

    quote.gsub!( /^ +$/, '' ) # Trim whitespace-only lines

  
    indent = " " * TabWidth
    quoted = %{<blockquote>\n%s\n</blockquote>\n\n} %
      apply_block_transforms( quote, rs ).
      gsub( /^/, indent ).
      gsub( PreChunk ) {|m| m.gsub(/^#{indent}/o, '') }
    @log.debug "Blockquoted chunk is: %p" % quoted
    quoted
  }
end

#transform_code_blocks(str, rs) ⇒ Object

Transform Markdown-style codeblocks in a copy of the specified str and return it.



1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
 
# File 'lib/bluefeather.rb', line 1348

def transform_code_blocks( str, rs )
  @log.debug " Transforming code blocks"
  
  str.gsub( CodeBlockRegexp ) {|block|
    codeblock = $1
    remainder = $2
    
    
    tmpl = %{\n\n<pre><code>%s\n</code></pre>\n\n%s}
    
    # patch for ruby 1.9.1 bug

    if tmpl.respond_to?(:force_encoding) then
      tmpl.force_encoding(str.encoding)
    end
    args = [ encode_code( outdent(codeblock), rs ).rstrip, remainder ]
    
    # recover all backslash escaped to original form

    EscapeTable.each {|char, hash|
      args[0].gsub!( hash[:md5re]){char}
    }
    
    # Generate the codeblock

    tmpl % args
  }
end

#transform_code_spans(str, rs) ⇒ Object

Transform backticked spans into <code> spans.



1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
 
# File 'lib/bluefeather.rb', line 1792

def transform_code_spans( str, rs )
  @log.debug " Transforming code spans"
  
  # Set up the string scanner and just return the string unless there's at

  # least one backtick.

  @scanner.string = str.dup
  unless @scanner.exist?( /`/ )
    @scanner.terminate
    @log.debug "No backticks found for code span in %p" % str
    return str
  end
  
  @log.debug "Transforming code spans in %p" % str
  
  # Build the transformed text anew

  text = ''
  
  # Scan to the end of the string

  until @scanner.empty?
  
    # Scan up to an opening backtick

    if pre = @scanner.scan_until( /.??(?=`)/m )
      text += pre
      @log.debug "Found backtick at %d after '...%s'" % [ @scanner.pos, text[-10, 10] ]
  
      # Make a pattern to find the end of the span

      opener = @scanner.scan( /`+/ )
      len = opener.length
      closer = Regexp::new( opener )
      @log.debug "Scanning for end of code span with %p" % closer
  
      # Scan until the end of the closing backtick sequence. Chop the

      # backticks off the resultant string, strip leading and trailing

      # whitespace, and encode any enitites contained in it.

      codespan = @scanner.scan_until( closer ) or
        raise FormatError::new( @scanner.rest[0,20],
          "No %p found before end" % opener )
  
      @log.debug "Found close of code span at %d: %p" % [ @scanner.pos - len, codespan ]
      codespan.slice!( -len, len )
      text += "<code>%s</code>" %
        encode_code( codespan.strip, rs )
  
    # If there's no more backticks, just append the rest of the string

    # and move the scan pointer to the end

    else
      text += @scanner.rest
      @scanner.terminate
    end
  end
  
  return text
end

#transform_definition_list_items(str, rs) ⇒ Object 



1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
 
# File 'lib/bluefeather.rb', line 1242

def transform_definition_list_items(str, rs)
  buf = Util.generate_blank_string_io(str)
  buf.puts %Q|<dl>|

  lines = str.split("\n")
  until lines.empty? do
  
    dts = []
    
    # get dt items

    while lines.first =~ /^(?!\:).+$/ do
      dts << lines.shift
    end
    
    
    dd_as_block = false
    
    # skip blank lines

    while not lines.empty? and lines.first.empty? do
      lines.shift
      dd_as_block = true
    end
    
    
    dds = []
    while lines.first =~ DDLineRegexp do
      dd_buf = []
      
      # dd first line

      unless (line = lines.shift).empty? then
        dd_buf << $1 << "\n"
      end
      
      # dd second and more lines (sequential with 1st-line)

      until lines.empty? or                      # stop if read all

      lines.first =~ /^[ ]{0,#{TabWidth - 1}}$/ or # stop if blank line

      lines.first =~ DDLineRegexp do             # stop if new dd found

        dd_buf << outdent(lines.shift) << "\n"
      end
      
      # dd second and more lines (separated with 1st-line)

      until lines.empty? do  # stop if all was read

        if lines.first.empty? then
          # blank line (skip)

          lines.shift
          dd_buf << "\n" 
        elsif lines.first =~ /^[ ]{#{TabWidth},}/ then
          # indented body

          dd_buf << outdent(lines.shift) << "\n"
        else
          # not indented body

          break
        end
        
      end
      
      
      dds << dd_buf.join
      
      # skip blank lines

      unless lines.empty? then
        while lines.first.empty? do
          lines.shift
        end
      end
    end
    
    # html output

    dts.each do |dt|
      buf.puts %Q|  <dt>#{apply_span_transforms(dt, rs)}</dt>|
    end
    
    dds.each do |dd|
      if dd_as_block then
        buf.puts %Q|  <dd>#{apply_block_transforms(dd, rs)}</dd>|
      else
        dd.gsub!(/\n+\z/, '') # chomp linefeeds

        buf.puts %Q|  <dd>#{apply_span_transforms(dd.chomp, rs)}</dd>|
      end
    end
  end
  
  buf.puts %Q|</dl>|

  return(buf.string)
end

#transform_definition_lists(str, rs) ⇒ Object 



1231
1232
1233
1234
1235
1236
1237
 
# File 'lib/bluefeather.rb', line 1231

def transform_definition_lists(str, rs)
  @log.debug " Transforming definition lists at %p" % (str[0,100] + '...')
  str.gsub( DefinitionListRegexp ) {|list|
    @log.debug "  Found definition list %p (captures=%p)" % [list, $~.captures]
    transform_definition_list_items(list, rs)
  }
end

#transform_headers(str, rs) ⇒ Object

Apply Markdown header transforms to a copy of the given str amd render state rs and return the result.



1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
 
# File 'lib/bluefeather.rb', line 1521

def transform_headers( str, rs )
  @log.debug " Transforming headers"
  
  # Setext-style headers:

  #    Header 1

  #    ========

  #  

  #    Header 2

  #    --------

  #

  
  section_numbers = [nil, nil, nil, nil, nil]
  
  str.
    gsub( HeaderRegexp ) {|m|
      if $1 then
        @log.debug "Found setext-style header"
        title, id, hdrchar = $1, $2, $3
        
        case hdrchar
        when '='
          level = 1
        when '-'
          level = 2
        end
      else
        @log.debug "Found ATX-style header"
        hdrchars, title, id = $4, $5, $6
        level = hdrchars.length
        
        if level >= 7 then
          rs.warnings << "illegal header level - h#{level} ('#' symbols are too many)"
        end
      end
      
      if rs.numbering? then
        if level >= rs.numbering_start_level and level <= 6 then
          depth = level - rs.numbering_start_level
          
          section_numbers.each_index do |i|
            if i == depth and section_numbers[depth] then
              # increment a deepest number if current header's level equals last header's

              section_numbers[i] += 1
            elsif i <= depth then
              # set default number if nil

              section_numbers[i] ||= 1
            else
              # clear discardeds

              section_numbers[i] = nil
            end
          end
          
          no = ''
          (0..depth).each do |i|
            no << "#{section_numbers[i]}."
          end
  
          title = "#{no} #{title}"
        end
      end
      
      title_html = apply_span_transforms( title, rs )
      id ||= "bfheader-#{Digest::MD5.hexdigest(title)}"
      
      unless id =~ IdRegexp then
        rs.warnings << "illegal header id - #{id} (legal chars: a-zA-Z0-9_-. | 1st: a-zA-Z)"
      end
      
      if rs.block_transform_depth == 1 then
        rs.headers << RenderState::Header.new(id, level, title, title_html)
      end
    
      if @use_header_id then
        %{<h%d id="%s">%s</h%d>\n\n} % [ level, id, title_html, level ]
      else
        %{<h%d>%s</h%d>\n\n} % [ level, title_html, level ]
      end
    }
end

#transform_hrules(str, rs) ⇒ Object

Transform any Markdown-style horizontal rules in a copy of the specified str and return it.



1129
1130
1131
1132
 
# File 'lib/bluefeather.rb', line 1129

def transform_hrules( str, rs )
  @log.debug " Transforming horizontal rules"
  str.gsub( /^( ?[\-\*_] ?){3,}$/, "\n<hr#{EmptyElementSuffix}\n" )
end

#transform_images(str, rs) ⇒ Object

Turn image markup into image tags.



1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
 
# File 'lib/bluefeather.rb', line 1877

def transform_images( str, rs )
  @log.debug " Transforming images %p" % str
  
  # Handle reference-style labeled images: ![alt text][id]

  str.
    gsub( ReferenceImageRegexp ) {|match|
      whole, alt, linkid = $1, $2, $3.downcase
      @log.debug "Matched %p" % match
      res = nil
      alt.gsub!( /"/, '&quot;' )
  
      # for shortcut links like ![this][].

      linkid = alt.downcase if linkid.empty?
  
      if rs.urls.key?( linkid )
        url = escape_md( rs.urls[linkid] )
        @log.debug "Found url '%s' for linkid '%s' " % [ url, linkid ]
  
        # Build the tag

        result = %{<img src="%s" alt="%s"} % [ url, alt ]
        if rs.titles.key?( linkid )
          result += %{ title="%s"} % escape_md( rs.titles[linkid] )
        end
        result += EmptyElementSuffix
  
      else
        result = whole
      end
  
      @log.debug "Replacing %p with %p" % [ match, result ]
      result
    }.
  
    # Inline image style

    gsub( InlineImageRegexp ) {|match|
      @log.debug "Found inline image %p" % match
      whole, alt, title = $1, $2, $5
      url = escape_md( $3 )
      alt.gsub!( /"/, '&quot;' )
  
      # Build the tag

      result = %{<img src="%s" alt="%s"} % [ url, alt ]
      unless title.nil?
        title.gsub!( /"/, '&quot;' )
        result += %{ title="%s"} % escape_md( title )
      end
      result += EmptyElementSuffix

      @log.debug "Replacing %p with %p" % [ match, result ]
      result
    }
end

#transform_italic_and_bold(str, rs) ⇒ Object

Transform italic- and bold-encoded text in a copy of the specified str and return it.



1782
1783
1784
1785
1786
1787
1788
 
# File 'lib/bluefeather.rb', line 1782

def transform_italic_and_bold( str, rs )
  @log.debug " Transforming italic and bold"
  
  str.
    gsub( BoldRegexp, %{<strong>\\2</strong>} ).
    gsub( ItalicRegexp, %{<em>\\2</em>} )
end

#transform_list_items(str, rs) ⇒ Object

Transform list items in a copy of the given str and return it.



1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
 
# File 'lib/bluefeather.rb', line 1188

def transform_list_items( str, rs )
  @log.debug " Transforming list items"
  
  # Trim trailing blank lines

  str = str.sub( /\n{2,}\z/, "\n" )
  str.gsub( ListItemRegexp ) {|line|
    @log.debug "  Found item line %p" % line
    leading_line, item = $1, $4
    separating_lines = $5 
  
    if leading_line or /\n{2,}/.match(item) or not separating_lines.empty? then
      @log.debug "   Found leading line or item has a blank"
      item = apply_block_transforms( outdent(item), rs )
    else
      # Recursion for sub-lists

      @log.debug "   Recursing for sublist"
      item = transform_lists( outdent(item), rs ).chomp
      item = apply_span_transforms( item, rs )
    end
  
    %{<li>%s</li>\n} % item
  }
end

#transform_lists(str, rs) ⇒ Object

Transform Markdown-style lists in a copy of the specified str and return it.



1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
 
# File 'lib/bluefeather.rb', line 1161

def transform_lists( str, rs )
  @log.debug " Transforming lists at %p" % (str[0,100] + '...')
  
  str.gsub( ListRegexp ) {|list|
    @log.debug "  Found list %p" % list
    bullet = $1
    list_type = (ListMarkerUl.match(bullet) ? "ul" : "ol")
  
    %{<%s>\n%s</%s>\n} % [
      list_type,
      transform_list_items( list, rs ),
      list_type,
    ]
  }
end

#transform_table_rows(str, rs) ⇒ Object 



1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
 
# File 'lib/bluefeather.rb', line 1064

def transform_table_rows(str, rs)

  # split cells to 2-d array

  data = str.split("\n").map{|x| x.split('|')}
  
  
  data.each do |row|
    # cut left space

    row.first.lstrip!
    
    # cut when optional side-borders is included

    row.shift if row.first.empty?
  end
  
  column_attrs = []
  
  re = ''
  re << "<table>\n"
  
  # head is exist?

  if data.size >= 3 and data[1].all?{|x| x =~ TableSeparatorCellRegexp} then
    head_row = data.shift
    separator_row = data.shift
    
    separator_row.each do |cell|
      cell.match TableSeparatorCellRegexp
      left = $1; right = $2

      if left and right then
        column_attrs << ' style="text-align: center"'
      elsif right then
        column_attrs << ' style="text-align: right"'
      elsif left then
        column_attrs << ' style="text-align: left"'
      else
        column_attrs << ''
      end
    end

    re << "\t<thead><tr>\n"
    head_row.each_with_index do |cell, i|
      re << "\t\t<th#{column_attrs[i]}>#{apply_span_transforms(cell.strip, rs)}</th>\n"
    end
    re << "\t</tr></thead>\n"
  end
  
  # data row

  re << "\t<tbody>\n"
  data.each do |row|
    re << "\t\t<tr>\n"
    row.each_with_index do |cell, i|
      re << "\t\t\t<td#{column_attrs[i]}>#{apply_span_transforms(cell.strip, rs)}</td>\n"
    end
    re << "\t\t</tr>\n"
  end
  re << "\t</tbody>\n"
  
  re << "</table>\n"

  re
end

#transform_tables(str, rs) ⇒ Object

Transform tables.



1046
1047
1048
1049
1050
 
# File 'lib/bluefeather.rb', line 1046

def transform_tables(str, rs)
  str.gsub(TableRegexp){
    transform_table_rows($~[0], rs)
  }
end

#transform_toc(str, rs) ⇒ Object

Transform any Markdown-style horizontal rules in a copy of the specified str and return it.



987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
 
# File 'lib/bluefeather.rb', line 987

def transform_toc( str, rs )
  @log.debug " Transforming tables of contents"
  str.gsub(TOCRegexp){
    start_level = 2 # default

    end_level = 6
  
    param = $1
    if param then
      if param =~ TOCStartLevelRegexp then
        if !($1) and !($2) then
          rs.warnings << "illegal TOC parameter - #{param} (valid example: 'h2..h4')"
        else
          start_level = ($1 ? $1.to_i : 2)
          end_level = ($2 ? $2.to_i : 6)
        end
      else
        rs.warnings << "illegal TOC parameter - #{param} (valid example: 'h2..h4')"
      end
    end
    
    if rs.headers.first and rs.headers.first.level >= (start_level + 1) then
      rs.warnings << "illegal structure of headers - h#{start_level} should be set before h#{rs.headers.first.level}"
    end
    
    
    ul_text = "\n\n"
    rs.headers.each do |header|
      if header.level >= start_level and header.level <= end_level then
        ul_text << ' ' * TabWidth * (header.level - start_level)
        ul_text << '* '
        ul_text << %Q|<a href="##{header.id}" rel="toc">#{header.content_html}</a>|
        ul_text << "\n"
      end
    end
    ul_text << "\n"
    
    ul_text # output

  
  }
end

#unescape_special_chars(str) ⇒ Object

Swap escaped special characters in a copy of the given str and return it.



916
917
918
919
920
921
922
923
 
# File 'lib/bluefeather.rb', line 916

def unescape_special_chars( str )
  EscapeTable.each {|char, hash|
    @log.debug "Unescaping escaped %p with %p" % [ char, hash[:md5re] ]
    str.gsub!( hash[:md5re], hash[:unescape] )
  }
  
  return str
end