2007-09-02 22:41:47 +02:00
|
|
|
# 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:
|
|
|
|
#
|
2013-10-26 09:15:08 +02:00
|
|
|
# <abbr title="American Civil Liberties Union">ACLU</abbr>
|
2007-09-02 22:41:47 +02:00
|
|
|
#
|
|
|
|
# == Adding Tables
|
|
|
|
#
|
2014-04-16 01:57:52 +02:00
|
|
|
# In Textile, simple tables can be added by separating each column by
|
2007-09-02 22:41:47 +02:00
|
|
|
# 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 )
|
|
|
|
|
2008-09-11 19:19:26 +02:00
|
|
|
class RedCloth3 < String
|
2016-06-01 19:32:35 +02:00
|
|
|
include Redmine::Helpers::URL
|
2007-09-02 22:41:47 +02:00
|
|
|
|
|
|
|
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 <b>bold</b> 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 = []
|
2009-12-09 11:30:23 +01:00
|
|
|
textile_rules = [:block_textile_table, :block_textile_lists,
|
2007-09-02 22:41:47 +02:00
|
|
|
:block_textile_prefix, :inline_textile_image, :inline_textile_link,
|
2008-10-18 13:25:27 +02:00
|
|
|
:inline_textile_code, :inline_textile_span, :glyphs_textile]
|
2007-09-02 22:41:47 +02:00
|
|
|
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
|
|
|
|
|
|
|
|
# standard clean up
|
|
|
|
incoming_entities text
|
|
|
|
clean_white_space text
|
|
|
|
|
|
|
|
# start processor
|
|
|
|
@pre_list = []
|
|
|
|
rip_offtags text
|
|
|
|
no_textile text
|
2008-03-09 12:47:36 +01:00
|
|
|
escape_html_tags text
|
2011-03-14 21:35:36 +01:00
|
|
|
# need to do this before #hard_break and #blocks
|
|
|
|
block_textile_quotes text unless @lite_mode
|
2007-09-02 22:41:47 +02:00
|
|
|
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%/, '&' )
|
|
|
|
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 = /[\-^~]/
|
2012-02-17 23:31:01 +01:00
|
|
|
C_CLAS = '(?:\([^")]+\))'
|
2014-11-30 15:55:03 +01:00
|
|
|
C_LNGE = '(?:\[[a-z\-_]+\])'
|
2012-02-17 23:31:01 +01:00
|
|
|
C_STYL = '(?:\{[^"}]+\})'
|
2007-09-02 22:41:47 +02:00
|
|
|
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 = [
|
2007-10-03 20:00:50 +02:00
|
|
|
['**', 'b', :limit],
|
|
|
|
['*', 'strong', :limit],
|
2007-09-02 22:41:47 +02:00
|
|
|
['??', 'cite', :limit],
|
|
|
|
['-', 'del', :limit],
|
2007-10-03 20:00:50 +02:00
|
|
|
['__', 'i', :limit],
|
2007-09-02 22:41:47 +02:00
|
|
|
['_', 'em', :limit],
|
|
|
|
['%', 'span', :limit],
|
|
|
|
['+', 'ins', :limit],
|
2007-10-03 20:00:50 +02:00
|
|
|
['^', 'sup', :limit],
|
|
|
|
['~', 'sub', :limit]
|
2007-09-02 22:41:47 +02:00
|
|
|
]
|
2010-03-11 20:55:31 +01:00
|
|
|
QTAGS_JOIN = QTAGS.map {|rc, ht, rtype| Regexp::quote rc}.join('|')
|
|
|
|
|
2007-09-02 22:41:47 +02:00
|
|
|
QTAGS.collect! do |rc, ht, rtype|
|
|
|
|
rcq = Regexp::quote rc
|
|
|
|
re =
|
|
|
|
case rtype
|
|
|
|
when :limit
|
2010-03-12 14:43:11 +01:00
|
|
|
/(^|[>\s\(]) # sta
|
2010-03-20 13:54:23 +01:00
|
|
|
(?!\-\-)
|
2010-03-12 14:43:11 +01:00
|
|
|
(#{QTAGS_JOIN}|) # oqs
|
|
|
|
(#{rcq}) # qtag
|
2015-06-06 09:15:55 +02:00
|
|
|
([[:word:]]|[^\s].*?[^\s]) # content
|
2010-03-20 13:54:23 +01:00
|
|
|
(?!\-\-)
|
2007-09-02 22:41:47 +02:00
|
|
|
#{rcq}
|
2010-03-12 14:43:11 +01:00
|
|
|
(#{QTAGS_JOIN}|) # oqa
|
2010-04-30 19:50:34 +02:00
|
|
|
(?=[[:punct:]]|<|\s|\)|$)/x
|
2007-09-02 22:41:47 +02:00
|
|
|
else
|
|
|
|
/(#{rcq})
|
|
|
|
(#{C})
|
|
|
|
(?::(\S+))?
|
2015-06-06 09:15:55 +02:00
|
|
|
([[:word:]]|[^\s\-].*?[^\s\-])
|
2007-09-02 22:41:47 +02:00
|
|
|
#{rcq}/xm
|
|
|
|
end
|
|
|
|
[rc, ht, re, rtype]
|
|
|
|
end
|
|
|
|
|
|
|
|
# Elements to handle
|
|
|
|
GLYPHS = [
|
|
|
|
# [ /([^\s\[{(>])?\'([dmst]\b|ll\b|ve\b|\s|:|$)/, '\1’\2' ], # single closing
|
2008-01-15 19:12:12 +01:00
|
|
|
# [ /([^\s\[{(>#{PUNCT_Q}][#{PUNCT_Q}]*)\'/, '\1’' ], # single closing
|
|
|
|
# [ /\'(?=[#{PUNCT_Q}]*(s\b|[\s#{PUNCT_NOQ}]))/, '’' ], # single closing
|
|
|
|
# [ /\'/, '‘' ], # single opening
|
2008-10-27 12:50:23 +01:00
|
|
|
# [ /</, '<' ], # less-than
|
|
|
|
# [ />/, '>' ], # greater-than
|
2007-09-02 22:41:47 +02:00
|
|
|
# [ /([^\s\[{(])?"(\s|:|$)/, '\1”\2' ], # double closing
|
2008-01-15 19:12:12 +01:00
|
|
|
# [ /([^\s\[{(>#{PUNCT_Q}][#{PUNCT_Q}]*)"/, '\1”' ], # double closing
|
|
|
|
# [ /"(?=[#{PUNCT_Q}]*[\s#{PUNCT_NOQ}])/, '”' ], # double closing
|
|
|
|
# [ /"/, '“' ], # double opening
|
2008-10-27 12:50:23 +01:00
|
|
|
# [ /\b( )?\.{3}/, '\1…' ], # ellipsis
|
2008-12-23 18:05:38 +01:00
|
|
|
# [ /\b([A-Z][A-Z0-9]{2,})\b(?:[(]([^)]*)[)])/, '<acronym title="\2">\1</acronym>' ], # 3+ uppercase acronym
|
2008-10-27 12:50:23 +01:00
|
|
|
# [ /(^|[^"][>\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—' ], # em dash
|
|
|
|
# [ /\s->\s/, ' → ' ], # right arrow
|
|
|
|
# [ /\s-\s/, ' – ' ], # en dash
|
|
|
|
# [ /(\d+) ?x ?(\d+)/, '\1×\2' ], # dimension sign
|
|
|
|
# [ /\b ?[(\[]TM[\])]/i, '™' ], # trademark
|
|
|
|
# [ /\b ?[(\[]R[\])]/i, '®' ], # registered
|
|
|
|
# [ /\b ?[(\[]C[\])]/i, '©' ] # copyright
|
2007-09-02 22:41:47 +02:00
|
|
|
]
|
|
|
|
|
|
|
|
H_ALGN_VALS = {
|
|
|
|
'<' => 'left',
|
|
|
|
'=' => 'center',
|
|
|
|
'>' => 'right',
|
|
|
|
'<>' => 'justify'
|
|
|
|
}
|
|
|
|
|
|
|
|
V_ALGN_VALS = {
|
|
|
|
'^' => 'top',
|
|
|
|
'-' => 'middle',
|
|
|
|
'~' => 'bottom'
|
|
|
|
}
|
|
|
|
|
|
|
|
#
|
|
|
|
# Flexible HTML escaping
|
|
|
|
#
|
2008-12-19 11:16:15 +01:00
|
|
|
def htmlesc( str, mode=:Quotes )
|
|
|
|
if str
|
2007-09-02 22:41:47 +02:00
|
|
|
str.gsub!( '&', '&' )
|
|
|
|
str.gsub!( '"', '"' ) if mode != :NoQuotes
|
|
|
|
str.gsub!( "'", ''' ) if mode == :Quotes
|
|
|
|
str.gsub!( '<', '<')
|
|
|
|
str.gsub!( '>', '>')
|
2008-12-19 11:16:15 +01:00
|
|
|
end
|
|
|
|
str
|
2007-09-02 22:41:47 +02:00
|
|
|
end
|
|
|
|
|
|
|
|
# Search and replace for Textile glyphs (quotes, dashes, other symbols)
|
|
|
|
def pgl( text )
|
2008-12-23 18:05:38 +01:00
|
|
|
#GLYPHS.each do |re, resub, tog|
|
|
|
|
# next if tog and method( tog ).call
|
|
|
|
# text.gsub! re, resub
|
|
|
|
#end
|
2010-11-06 14:29:23 +01:00
|
|
|
text.gsub!(/\b([A-Z][A-Z0-9]{1,})\b(?:[(]([^)]*)[)])/) do |m|
|
2013-10-26 09:15:08 +02:00
|
|
|
"<abbr title=\"#{htmlesc $2}\">#{$1}</abbr>"
|
2007-09-02 22:41:47 +02:00
|
|
|
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
|
|
|
|
|
2012-02-12 15:00:43 +01:00
|
|
|
if text.sub!( /\{([^"}]*)\}/, '' ) && !filter_styles
|
|
|
|
sanitized = sanitize_styles($1)
|
|
|
|
style << "#{ sanitized };" unless sanitized.blank?
|
|
|
|
end
|
2007-09-02 22:41:47 +02:00
|
|
|
|
|
|
|
lang = $1 if
|
2014-11-30 15:55:03 +01:00
|
|
|
text.sub!( /\[([a-z\-_]+?)\]/, '' )
|
2007-09-02 22:41:47 +02:00
|
|
|
|
|
|
|
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, $2 if cls =~ /^(.*?)#(.*)$/
|
|
|
|
|
|
|
|
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
|
|
|
|
|
2012-09-16 15:54:04 +02:00
|
|
|
STYLES_RE = /^(color|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
|
2012-02-12 15:00:43 +01:00
|
|
|
|
|
|
|
def sanitize_styles(str)
|
|
|
|
styles = str.split(";").map(&:strip)
|
|
|
|
styles.reject! do |style|
|
|
|
|
!style.match(STYLES_RE)
|
|
|
|
end
|
|
|
|
styles.join(";")
|
|
|
|
end
|
|
|
|
|
2007-09-02 22:41:47 +02:00
|
|
|
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 = []
|
2015-09-20 13:02:01 +02:00
|
|
|
fullrow.gsub!(/([^|\s])\s*\n/, "\\1<br />")
|
2008-06-04 19:12:59 +02:00
|
|
|
fullrow.each_line do |row|
|
2007-09-02 22:41:47 +02:00
|
|
|
ratts, row = pba( $1, 'tr' ), $2 if row =~ /^(#{A}#{C}\. )(.*)/m
|
|
|
|
cells = []
|
2015-01-19 21:38:48 +01:00
|
|
|
# the regexp prevents wiki links with a | from being cut as cells
|
|
|
|
row.scan(/\|(_?#{S}#{A}#{C}\. ?)?((\[\[[^|\]]*\|[^|\]]*\]\]|[^|])*?)(?=\|)/) do |modifiers, cell|
|
2007-09-02 22:41:47 +02:00
|
|
|
ctyp = 'd'
|
2015-01-19 21:38:48 +01:00
|
|
|
ctyp = 'h' if modifiers && modifiers =~ /^_/
|
2007-09-02 22:41:47 +02:00
|
|
|
|
2015-01-18 23:57:55 +01:00
|
|
|
catts = nil
|
2015-01-19 21:38:48 +01:00
|
|
|
catts = pba( modifiers, 'td' ) if modifiers
|
2007-09-02 22:41:47 +02:00
|
|
|
|
2008-06-04 19:12:59 +02:00
|
|
|
catts = shelve( catts ) if catts
|
|
|
|
cells << "\t\t\t<t#{ ctyp }#{ catts }>#{ cell }</t#{ ctyp }>"
|
2007-09-02 22:41:47 +02:00
|
|
|
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 = $~[1..3]
|
|
|
|
if depth.last
|
|
|
|
if depth.last.length > tl.length
|
|
|
|
(depth.length - 1).downto(0) do |i|
|
|
|
|
break if depth[i].length == tl.length
|
|
|
|
lines[line_id - 1] << "</li>\n\t</#{ lT( depth[i] ) }l>\n\t"
|
|
|
|
depth.pop
|
|
|
|
end
|
|
|
|
end
|
|
|
|
if depth.last and depth.last.length == tl.length
|
|
|
|
lines[line_id - 1] << '</li>'
|
|
|
|
end
|
|
|
|
end
|
|
|
|
unless depth.last == tl
|
|
|
|
depth << tl
|
|
|
|
atts = pba( atts )
|
|
|
|
atts = shelve( atts ) if atts
|
|
|
|
lines[line_id] = "\t<#{ lT(tl) }l#{ atts }>\n\t<li>#{ content }"
|
|
|
|
else
|
|
|
|
lines[line_id] = "\t\t<li>#{ content }"
|
|
|
|
end
|
|
|
|
last_line = line_id
|
|
|
|
|
|
|
|
else
|
|
|
|
last_line = line_id
|
|
|
|
end
|
|
|
|
if line_id - last_line > 1 or line_id == lines.length - 1
|
2012-04-18 14:00:54 +02:00
|
|
|
while v = depth.pop
|
2007-09-02 22:41:47 +02:00
|
|
|
lines[last_line] << "</li>\n\t</#{ lT( v ) }l>"
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
lines.join( "\n" )
|
|
|
|
end
|
|
|
|
end
|
2008-05-30 18:35:36 +02:00
|
|
|
|
2009-11-07 10:43:02 +01:00
|
|
|
QUOTES_RE = /(^>+([^\n]*?)(\n|$))+/m
|
2008-05-30 18:35:36 +02:00
|
|
|
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
|
2007-09-02 22:41:47 +02:00
|
|
|
|
|
|
|
CODE_RE = /(\W)
|
|
|
|
@
|
|
|
|
(?:\|(\w+?)\|)?
|
|
|
|
(.+?)
|
|
|
|
@
|
|
|
|
(?=\W)/x
|
|
|
|
|
|
|
|
def inline_textile_code( text )
|
|
|
|
text.gsub!( CODE_RE ) do |m|
|
|
|
|
before,lang,code,after = $~[1..4]
|
|
|
|
lang = " lang=\"#{ lang }\"" if lang
|
2010-03-12 16:12:23 +01:00
|
|
|
rip_offtags( "#{ before }<code#{ lang }>#{ code }</code>#{ after }", false )
|
2007-09-02 22:41:47 +02:00
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
def lT( text )
|
|
|
|
text =~ /\#$/ ? '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? $1
|
|
|
|
blk
|
|
|
|
else
|
|
|
|
# search for indentation levels
|
|
|
|
blk.strip!
|
|
|
|
if blk.empty?
|
|
|
|
blk
|
|
|
|
else
|
|
|
|
code_blk = nil
|
|
|
|
blk.gsub!( /((?:\n(?:\n^ +[^\n]*)+)+)/m ) do |iblk|
|
|
|
|
flush_left iblk
|
|
|
|
blocks iblk, plain
|
|
|
|
iblk.gsub( /^(\S)/, "\t\\1" )
|
|
|
|
if plain
|
|
|
|
code_blk = iblk; ""
|
|
|
|
else
|
|
|
|
iblk
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
block_applied = 0
|
|
|
|
@rules.each do |rule_name|
|
|
|
|
block_applied += 1 if ( rule_name.to_s.match /^block_/ and method( rule_name ).call( blk ) )
|
|
|
|
end
|
|
|
|
if block_applied.zero?
|
|
|
|
if deep_code
|
|
|
|
blk = "\t<pre><code>#{ blk }</code></pre>"
|
|
|
|
else
|
|
|
|
blk = "\t<p>#{ blk }</p>"
|
|
|
|
end
|
|
|
|
end
|
|
|
|
# hard_break blk
|
|
|
|
blk + "\n#{ code_blk }"
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
end.join( "\n\n" ) )
|
|
|
|
end
|
|
|
|
|
|
|
|
def textile_bq( tag, atts, cite, content )
|
|
|
|
cite, cite_title = check_refs( cite )
|
|
|
|
cite = " cite=\"#{ cite }\"" if cite
|
|
|
|
atts = shelve( atts ) if atts
|
|
|
|
"\t<blockquote#{ cite }>\n\t\t<p#{ atts }>#{ content }</p>\n\t</blockquote>"
|
|
|
|
end
|
|
|
|
|
|
|
|
def textile_p( tag, atts, cite, content )
|
|
|
|
atts = shelve( atts ) if atts
|
|
|
|
"\t<#{ tag }#{ atts }>#{ content }</#{ tag }>"
|
|
|
|
end
|
|
|
|
|
|
|
|
alias textile_h1 textile_p
|
|
|
|
alias textile_h2 textile_p
|
|
|
|
alias textile_h3 textile_p
|
|
|
|
alias textile_h4 textile_p
|
|
|
|
alias textile_h5 textile_p
|
|
|
|
alias textile_h6 textile_p
|
|
|
|
|
|
|
|
def textile_fn_( tag, num, atts, cite, content )
|
2008-10-18 13:25:27 +02:00
|
|
|
atts << " id=\"fn#{ num }\" class=\"footnote\""
|
2007-09-02 22:41:47 +02:00
|
|
|
content = "<sup>#{ num }</sup> #{ content }"
|
|
|
|
atts = shelve( atts ) if atts
|
|
|
|
"\t<p#{ atts }>#{ content }</p>"
|
|
|
|
end
|
|
|
|
|
|
|
|
BLOCK_RE = /^(([a-z]+)(\d*))(#{A}#{C})\.(?::(\S+))? (.*)$/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
|
2011-03-12 19:28:30 +01:00
|
|
|
replacement = nil
|
2007-09-02 22:41:47 +02:00
|
|
|
if respond_to? "textile_#{ tag }", true
|
2011-03-12 19:28:30 +01:00
|
|
|
replacement = method( "textile_#{ tag }" ).call( tag, atts, cite, content )
|
2007-09-02 22:41:47 +02:00
|
|
|
elsif respond_to? "textile_#{ tagpre }_", true
|
2011-03-12 19:28:30 +01:00
|
|
|
replacement = method( "textile_#{ tagpre }_" ).call( tagpre, num, atts, cite, content )
|
2007-09-02 22:41:47 +02:00
|
|
|
end
|
2011-03-12 19:28:30 +01:00
|
|
|
text.gsub!( $& ) { replacement } if replacement
|
2007-09-02 22:41:47 +02:00
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
SETEXT_RE = /\A(.+?)\n([=-])[=-]* *$/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 = /^(#{
|
2008-07-30 20:28:01 +02:00
|
|
|
['*', '-', '_'].collect { |ch| ' ?(' + Regexp::quote( ch ) + ' ?){3,}' }.join( '|' )
|
2007-09-02 22:41:47 +02:00
|
|
|
})$/
|
|
|
|
|
|
|
|
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
|
2010-03-12 14:43:11 +01:00
|
|
|
sta,oqs,qtag,content,oqa = $~[1..6]
|
|
|
|
atts = nil
|
|
|
|
if content =~ /^(#{C})(.+)$/
|
|
|
|
atts, content = $~[1..2]
|
|
|
|
end
|
2007-09-02 22:41:47 +02:00
|
|
|
else
|
|
|
|
qtag,atts,cite,content = $~[1..4]
|
|
|
|
sta = ''
|
|
|
|
end
|
|
|
|
atts = pba( atts )
|
|
|
|
atts = shelve( atts ) if atts
|
|
|
|
|
2010-03-11 20:55:31 +01:00
|
|
|
"#{ sta }#{ oqs }<#{ ht }#{ atts }>#{ content }</#{ ht }>#{ oqa }"
|
2007-09-02 22:41:47 +02:00
|
|
|
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
LINK_RE = /
|
2009-07-19 16:23:15 +02:00
|
|
|
(
|
2007-09-02 22:41:47 +02:00
|
|
|
([\s\[{(]|[#{PUNCT}])? # $pre
|
|
|
|
" # start
|
|
|
|
(#{C}) # $atts
|
2008-05-26 21:39:51 +02:00
|
|
|
([^"\n]+?) # $text
|
2007-09-02 22:41:47 +02:00
|
|
|
\s?
|
|
|
|
(?:\(([^)]+?)\)(?="))? # $title
|
|
|
|
":
|
2008-12-30 17:23:05 +01:00
|
|
|
( # $url
|
2009-04-07 19:35:52 +02:00
|
|
|
(\/|[a-zA-Z]+:\/\/|www\.|mailto:) # $proto
|
2012-11-24 15:20:01 +01:00
|
|
|
[[:alnum:]_\/]\S+?
|
2008-12-30 17:23:05 +01:00
|
|
|
)
|
2007-09-02 22:41:47 +02:00
|
|
|
(\/)? # $slash
|
2012-11-24 15:20:01 +01:00
|
|
|
([^[:alnum:]_\=\/;\(\)]*?) # $post
|
2009-07-19 16:23:15 +02:00
|
|
|
)
|
2007-09-02 22:41:47 +02:00
|
|
|
(?=<|\s|$)
|
|
|
|
/x
|
2008-09-17 18:48:04 +02:00
|
|
|
#"
|
2007-09-02 22:41:47 +02:00
|
|
|
def inline_textile_link( text )
|
|
|
|
text.gsub!( LINK_RE ) do |m|
|
2009-07-19 16:23:15 +02:00
|
|
|
all,pre,atts,text,title,url,proto,slash,post = $~[1..9]
|
|
|
|
if text.include?('<br />')
|
|
|
|
all
|
|
|
|
else
|
2007-09-02 22:41:47 +02:00
|
|
|
url, url_title = check_refs( url )
|
|
|
|
title ||= url_title
|
|
|
|
|
2008-09-17 18:48:04 +02:00
|
|
|
# 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
|
2007-09-02 22:41:47 +02:00
|
|
|
atts = pba( atts )
|
2010-03-24 21:26:22 +01:00
|
|
|
atts = " href=\"#{ htmlesc url }#{ slash }\"#{ atts }"
|
2008-12-23 18:05:38 +01:00
|
|
|
atts << " title=\"#{ htmlesc title }\"" if title
|
2007-09-02 22:41:47 +02:00
|
|
|
atts = shelve( atts ) if atts
|
|
|
|
|
2008-03-29 10:24:09 +01:00
|
|
|
external = (url =~ /^https?:\/\//) ? ' class="external"' : ''
|
2007-10-01 19:45:40 +02:00
|
|
|
|
|
|
|
"#{ pre }<a#{ atts }#{ external }>#{ text }</a>#{ post }"
|
2009-07-19 16:23:15 +02:00
|
|
|
end
|
2007-09-02 22:41:47 +02:00
|
|
|
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
|
|
|
|
|
2007-09-15 19:17:09 +02:00
|
|
|
TEXTILE_REFS_RE = /(^ *)\[([^\[\n]+?)\](#{HYPERLINK})(?=\s|$)/
|
2007-09-02 22:41:47 +02:00
|
|
|
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 = /
|
2009-11-04 11:22:57 +01:00
|
|
|
(>|\s|^) # start of line?
|
2007-09-02 22:41:47 +02:00
|
|
|
\! # 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 = $~[1..8]
|
2008-12-19 11:16:15 +01:00
|
|
|
htmlesc title
|
2007-09-02 22:41:47 +02:00
|
|
|
atts = pba( atts )
|
2011-10-03 23:45:17 +02:00
|
|
|
atts = " src=\"#{ htmlesc url.dup }\"#{ atts }"
|
2007-09-02 22:41:47 +02:00
|
|
|
atts << " title=\"#{ title }\"" if title
|
|
|
|
atts << " alt=\"#{ title }\""
|
|
|
|
# size = @getimagesize($url);
|
|
|
|
# if($size) $atts.= " $size[3]";
|
|
|
|
|
|
|
|
href, alt_title = check_refs( href ) if href
|
|
|
|
url, url_title = check_refs( url )
|
|
|
|
|
2016-06-01 19:32:35 +02:00
|
|
|
return m unless uri_with_safe_scheme?(url)
|
|
|
|
|
2007-09-02 22:41:47 +02:00
|
|
|
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
|
2016-06-04 09:31:29 +02:00
|
|
|
out = "#{ stln }<span style=\"float:#{ algn }\">#{ out }</span>"
|
2007-09-02 22:41:47 +02:00
|
|
|
end
|
|
|
|
else
|
|
|
|
out = stln + out
|
|
|
|
end
|
|
|
|
|
|
|
|
out
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
def shelve( val )
|
|
|
|
@shelf << val
|
|
|
|
" :redsh##{ @shelf.length }:"
|
|
|
|
end
|
|
|
|
|
|
|
|
def retrieve( text )
|
2015-01-19 21:46:08 +01:00
|
|
|
text.gsub!(/ :redsh#(\d+):/) do
|
|
|
|
@shelf[$1.to_i - 1] || $&
|
2007-09-02 22:41:47 +02:00
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
def incoming_entities( text )
|
|
|
|
## turn any incoming ampersands into a dummy character for now.
|
|
|
|
## This uses a negative lookahead for alphanumerics followed by a semicolon,
|
|
|
|
## implying an incoming html entity, to be skipped
|
|
|
|
|
|
|
|
text.gsub!( /&(?![#a-z0-9]+;)/i, "x%x%" )
|
|
|
|
end
|
|
|
|
|
|
|
|
def no_textile( text )
|
|
|
|
text.gsub!( /(^|\s)==([^=]+.*?)==(\s|$)?/,
|
|
|
|
'\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 =~ /^ /
|
|
|
|
while text !~ /^ {#{indt}}\S/
|
|
|
|
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)/
|
2009-11-11 17:23:11 +01:00
|
|
|
OFFTAG_MATCH = /(?:(<\/#{ OFFTAGS }>)|(<#{ OFFTAGS }[^>]*>))(.*?)(?=<\/?#{ OFFTAGS }\W|\Z)/mi
|
2007-09-02 22:41:47 +02:00
|
|
|
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
|
2008-10-27 12:50:23 +01:00
|
|
|
pgl text
|
2007-09-02 22:41:47 +02:00
|
|
|
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
|
|
|
|
|
2011-11-28 23:08:15 +01:00
|
|
|
def rip_offtags( text, escape_aftertag=true, escape_line=true )
|
2007-09-02 22:41:47 +02:00
|
|
|
if text =~ /<.*>/
|
|
|
|
## strip and encode <pre> content
|
|
|
|
codepre, used_offtags = 0, {}
|
|
|
|
text.gsub!( OFFTAG_MATCH ) do |line|
|
|
|
|
if $3
|
2010-03-14 10:05:58 +01:00
|
|
|
first, offtag, aftertag = $3, $4, $5
|
2007-09-02 22:41:47 +02:00
|
|
|
codepre += 1
|
|
|
|
used_offtags[offtag] = true
|
|
|
|
if codepre - used_offtags.length > 0
|
2011-11-28 23:08:15 +01:00
|
|
|
htmlesc( line, :NoQuotes ) if escape_line
|
2007-09-02 22:41:47 +02:00
|
|
|
@pre_list.last << line
|
|
|
|
line = ""
|
|
|
|
else
|
2010-03-14 10:05:58 +01:00
|
|
|
### 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+)">/)
|
2007-09-02 22:41:47 +02:00
|
|
|
line = "<redpre##{ @pre_list.length }>"
|
2010-03-14 10:05:58 +01:00
|
|
|
first.match(/<#{ OFFTAGS }([^>]*)>/)
|
2008-11-08 16:18:02 +01:00
|
|
|
tag = $1
|
2010-12-05 11:09:18 +01:00
|
|
|
$2.to_s.match(/(class\=("[^"]+"|'[^']+'))/i)
|
2008-11-08 16:18:02 +01:00
|
|
|
tag << " #{$1}" if $1
|
|
|
|
@pre_list << "<#{ tag }>#{ aftertag }"
|
2007-09-02 22:41:47 +02:00
|
|
|
end
|
|
|
|
elsif $1 and codepre > 0
|
|
|
|
if codepre - used_offtags.length > 0
|
2011-11-28 23:08:15 +01:00
|
|
|
htmlesc( line, :NoQuotes ) if escape_line
|
2007-09-02 22:41:47 +02:00
|
|
|
@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
|
2008-03-09 12:47:36 +01:00
|
|
|
|
2008-06-08 22:31:36 +02:00
|
|
|
ALLOWED_TAGS = %w(redpre pre code notextile)
|
2008-03-09 12:47:36 +01:00
|
|
|
|
|
|
|
def escape_html_tags(text)
|
2015-11-11 08:34:15 +01:00
|
|
|
text.gsub!(%r{<(\/?([!\w]+)[^<>\n]*)(>?)}) {|m| ALLOWED_TAGS.include?($2) ? "<#{$1}#{$3}" : "<#{$1}#{'>' unless $3.blank?}" }
|
2008-03-09 12:47:36 +01:00
|
|
|
end
|
2007-09-02 22:41:47 +02:00
|
|
|
end
|
|
|
|
|