gitdown 0.0.1

data/lib/kramdown/parser/kramdown/list.rb

@@ -0,0 +1,240 @@
+# -*- coding: utf-8 -*-
+#
+#--
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
+#
+# This file is part of kramdown.
+#
+# kramdown is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#++
+#
+
+require 'kramdown/parser/kramdown/blank_line'
+require 'kramdown/parser/kramdown/eob'
+require 'kramdown/parser/kramdown/horizontal_rule'
+require 'kramdown/parser/kramdown/extensions'
+
+module Kramdown
+  module Parser
+    class Kramdown
+
+      LIST_ITEM_IAL = /^\s*(?:\{:(?!(?:#{ALD_ID_NAME})?:|\/)(#{ALD_ANY_CHARS}+)\})\s*/
+      LIST_ITEM_IAL_CHECK = /^#{LIST_ITEM_IAL}?\s*\n/
+
+      # Used for parsing the first line of a list item or a definition, i.e. the line with list item
+      # marker or the definition marker.
+      def parse_first_list_line(indentation, content)
+        if content =~ self.class::LIST_ITEM_IAL_CHECK
+          indentation = 4
+        else
+          while content =~ /^ *\t/
+            temp = content.scan(/^ */).first.length + indentation
+            content.sub!(/^( *)(\t+)/) {$1 << " "*(4 - (temp % 4) + ($2.length - 1)*4)}
+          end
+          indentation += content.scan(/^ */).first.length
+        end
+        content.sub!(/^\s*/, '')
+
+        indent_re = /^ {#{indentation}}/
+        content_re = /^(?:(?:\t| {4}){#{indentation / 4}} {#{indentation % 4}}|(?:\t| {4}){#{indentation / 4 + 1}}).*\S.*\n/
+        lazy_re = /(?!^ {0,#{[indentation, 3].min}}(?:#{IAL_BLOCK}|#{LAZY_END_HTML_STOP}|#{LAZY_END_HTML_START})).*\S.*\n/
+        [content, indentation, content_re, lazy_re, indent_re]
+      end
+
+
+      LIST_START_UL = /^(#{OPT_SPACE}[+*-])([\t| ].*?\n)/
+      LIST_START_OL = /^(#{OPT_SPACE}\d+\.)([\t| ].*?\n)/
+      LIST_START = /#{LIST_START_UL}|#{LIST_START_OL}/
+
+      # Parse the ordered or unordered list at the current location.
+      def parse_list
+        type, list_start_re = (@src.check(LIST_START_UL) ? [:ul, LIST_START_UL] : [:ol, LIST_START_OL])
+        list = new_block_el(type)
+
+        item = nil
+        content_re, lazy_re, indent_re = nil
+        eob_found = false
+        nested_list_found = false
+        last_is_blank = false
+        while !@src.eos?
+          if last_is_blank && @src.check(HR_START)
+            break
+          elsif @src.scan(EOB_MARKER)
+            eob_found = true
+            break
+          elsif @src.scan(list_start_re)
+            item = Element.new(:li)
+            item.value, indentation, content_re, lazy_re, indent_re = parse_first_list_line(@src[1].length, @src[2])
+            list.children << item
+
+            item.value.sub!(self.class::LIST_ITEM_IAL) do |match|
+              parse_attribute_list($1, item.options[:ial] ||= {})
+              ''
+            end
+
+            list_start_re = (type == :ul ? /^( {0,#{[3, indentation - 1].min}}[+*-])([\t| ].*?\n)/ :
+                             /^( {0,#{[3, indentation - 1].min}}\d+\.)([\t| ].*?\n)/)
+            nested_list_found = (item.value =~ LIST_START)
+            last_is_blank = false
+          elsif (result = @src.scan(content_re)) || (!last_is_blank && (result = @src.scan(lazy_re)))
+            result.sub!(/^(\t+)/) { " "*($1 ? 4*$1.length : 0) }
+            result.sub!(indent_re, '')
+            if !nested_list_found && result =~ LIST_START
+              item.value << "^\n"
+              nested_list_found = true
+            end
+            item.value << result
+            last_is_blank = false
+          elsif result = @src.scan(BLANK_LINE)
+            nested_list_found = true
+            last_is_blank = true
+            item.value << result
+          else
+            break
+          end
+        end
+
+        @tree.children << list
+
+        last = nil
+        list.children.each do |it|
+          temp = Element.new(:temp)
+          parse_blocks(temp, it.value)
+          it.children = temp.children
+          it.value = nil
+          next if it.children.size == 0
+
+          # Handle the case where an EOB marker is inserted by a block IAL for the first paragraph
+          it.children.delete_at(1) if it.children.first.type == :p &&
+            it.children.length >= 2 && it.children[1].type == :eob && it.children.first.options[:ial]
+
+          if it.children.first.type == :p &&
+              (it.children.length < 2 || it.children[1].type != :blank ||
+               (it == list.children.last && it.children.length == 2 && !eob_found)) &&
+              (list.children.last != it || list.children.size == 1 ||
+               list.children[0..-2].any? {|cit| cit.children.first.type != :p || cit.children.first.options[:transparent]})
+            it.children.first.children.first.value << "\n" if it.children.size > 1 && it.children[1].type != :blank
+            it.children.first.options[:transparent] = true
+          end
+
+          if it.children.last.type == :blank
+            last = it.children.pop
+          else
+            last = nil
+          end
+        end
+
+        @tree.children << last if !last.nil? && !eob_found
+
+        true
+      end
+      define_parser(:list, LIST_START)
+
+
+      DEFINITION_LIST_START = /^(#{OPT_SPACE}:)([\t| ].*?\n)/
+
+      # Parse the ordered or unordered list at the current location.
+      def parse_definition_list
+        children = @tree.children
+        if !children.last || (children.length == 1 && children.last.type != :p ) ||
+            (children.length >= 2 && children[-1].type != :p && (children[-1].type != :blank || children[-1].value != "\n" || children[-2].type != :p))
+          return false
+        end
+
+        first_as_para = false
+        deflist = new_block_el(:dl)
+        para = @tree.children.pop
+        if para.type == :blank
+          para = @tree.children.pop
+          first_as_para = true
+        end
+        para.children.first.value.split(/\n/).each do |term|
+          el = Element.new(:dt)
+          el.children << Element.new(:raw_text, term)
+          deflist.children << el
+        end
+
+        item = nil
+        content_re, lazy_re, indent_re = nil
+        def_start_re = DEFINITION_LIST_START
+        last_is_blank = false
+        while !@src.eos?
+          if @src.scan(def_start_re)
+            item = Element.new(:dd)
+            item.options[:first_as_para] = first_as_para
+            item.value, indentation, content_re, lazy_re, indent_re = parse_first_list_line(@src[1].length, @src[2])
+            deflist.children << item
+
+            item.value.sub!(self.class::LIST_ITEM_IAL) do |match|
+              parse_attribute_list($1, item.options[:ial] ||= {})
+              ''
+            end
+
+            def_start_re = /^( {0,#{[3, indentation - 1].min}}:)([\t| ].*?\n)/
+            first_as_para = false
+            last_is_blank = false
+          elsif @src.check(EOB_MARKER)
+            break
+          elsif (result = @src.scan(content_re)) || (!last_is_blank && (result = @src.scan(lazy_re)))
+            result.sub!(/^(\t+)/) { " "*($1 ? 4*$1.length : 0) }
+            result.sub!(indent_re, '')
+            item.value << result
+            first_as_para = false
+            last_is_blank = false
+          elsif result = @src.scan(BLANK_LINE)
+            first_as_para = true
+            item.value << result
+            last_is_blank = true
+          else
+            break
+          end
+        end
+
+        last = nil
+        deflist.children.each do |it|
+          next if it.type == :dt
+
+          parse_blocks(it, it.value)
+          it.value = nil
+          next if it.children.size == 0
+
+          if it.children.last.type == :blank
+            last = it.children.pop
+          else
+            last = nil
+          end
+          if it.children.first.type == :p && !it.options.delete(:first_as_para)
+            it.children.first.children.first.value << "\n" if it.children.size > 1
+            it.children.first.options[:transparent] = true
+          end
+        end
+
+        if @tree.children.length >= 1 && @tree.children.last.type == :dl
+          @tree.children[-1].children.concat(deflist.children)
+        elsif @tree.children.length >= 2 && @tree.children[-1].type == :blank && @tree.children[-2].type == :dl
+          @tree.children.pop
+          @tree.children[-1].children.concat(deflist.children)
+        else
+          @tree.children << deflist
+        end
+
+        @tree.children << last if !last.nil?
+
+        true
+      end
+      define_parser(:definition_list, DEFINITION_LIST_START)
+
+    end
+  end
+end

data/lib/kramdown/parser/kramdown/math.rb

@@ -0,0 +1,64 @@
+# -*- coding: utf-8 -*-
+#
+#--
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
+#
+# This file is part of kramdown.
+#
+# kramdown is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#++
+#
+
+require 'kramdown/parser/kramdown/block_boundary'
+
+module Kramdown
+  module Parser
+    class Kramdown
+
+      BLOCK_MATH_START = /^#{OPT_SPACE}(\\)?\$\$(.*?)\$\$\s*?\n/m
+
+      # Parse the math block at the current location.
+      def parse_block_math
+        if !after_block_boundary?
+          return false
+        elsif @src[1]
+          @src.scan(/^#{OPT_SPACE}\\/)
+          return false
+        end
+        orig_pos = @src.pos
+        @src.pos += @src.matched_size
+        data = @src[2]
+        if before_block_boundary?
+          @tree.children << new_block_el(:math, data, nil, :category => :block)
+          true
+        else
+          @src.pos = orig_pos
+          false
+        end
+      end
+      define_parser(:block_math, BLOCK_MATH_START)
+
+
+      INLINE_MATH_START = /\$\$(.*?)\$\$/
+
+      # Parse the inline math at the current location.
+      def parse_inline_math
+        @src.pos += @src.matched_size
+        @tree.children << Element.new(:math, @src[1], nil, :category => :span)
+      end
+      define_parser(:inline_math, INLINE_MATH_START, '\$')
+
+    end
+  end
+end

data/lib/kramdown/parser/kramdown/paragraph.rb

@@ -0,0 +1,63 @@
+# -*- coding: utf-8 -*-
+#
+#--
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
+#
+# This file is part of kramdown.
+#
+# kramdown is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#++
+#
+
+require 'kramdown/parser/kramdown/blank_line'
+require 'kramdown/parser/kramdown/extensions'
+require 'kramdown/parser/kramdown/eob'
+require 'kramdown/parser/kramdown/list'
+require 'kramdown/parser/kramdown/html'
+
+module Kramdown
+  module Parser
+    class Kramdown
+
+      LAZY_END_HTML_SPAN_ELEMENTS = HTML_SPAN_ELEMENTS + %w{script}
+      LAZY_END_HTML_START = /<(?>(?!(?:#{LAZY_END_HTML_SPAN_ELEMENTS.join('|')})\b)#{REXML::Parsers::BaseParser::UNAME_STR})\s*(?>\s+#{REXML::Parsers::BaseParser::UNAME_STR}\s*=\s*(["']).*?\1)*\s*\/?>/m
+      LAZY_END_HTML_STOP = /<\/(?!(?:#{LAZY_END_HTML_SPAN_ELEMENTS.join('|')})\b)#{REXML::Parsers::BaseParser::UNAME_STR}\s*>/m
+
+      LAZY_END = /#{BLANK_LINE}|#{IAL_BLOCK_START}|#{EOB_MARKER}|^#{OPT_SPACE}#{LAZY_END_HTML_STOP}|^#{OPT_SPACE}#{LAZY_END_HTML_START}|\Z/
+
+      PARAGRAPH_START = /^#{OPT_SPACE}[^ \t].*?\n/
+      PARAGRAPH_MATCH = /^.*?\n/
+      PARAGRAPH_END = /#{LAZY_END}|#{DEFINITION_LIST_START}/
+
+      # Parse the paragraph at the current location.
+      def parse_paragraph
+        result = @src.scan(PARAGRAPH_MATCH)
+        while !@src.match?(self.class::PARAGRAPH_END)
+          result << @src.scan(PARAGRAPH_MATCH)
+        end
+        result.chomp!
+        if @tree.children.last && @tree.children.last.type == :p
+          @tree.children.last.children.first.value << "\n" << result
+        else
+          @tree.children << new_block_el(:p)
+          result.lstrip!
+          @tree.children.last.children << Element.new(@text_type, result)
+        end
+        true
+      end
+      define_parser(:paragraph, PARAGRAPH_START)
+
+    end
+  end
+end

data/lib/kramdown/parser/kramdown/smart_quotes.rb

@@ -0,0 +1,214 @@
+# -*- coding: utf-8 -*-
+#
+#--
+# Copyright (C) 2009-2010 Thomas Leitner <t_leitner@gmx.at>
+#
+# This file is part of kramdown.
+#
+# kramdown is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#++
+#
+#--
+# Parts of this file are based on code from Maruku by Andrea Censi.
+# The needed license statements follow:
+#
+#   Copyright (C) 2006  Andrea Censi  <andrea (at) rubyforge.org>
+#
+#   Maruku is free software; you can redistribute it and/or modify
+#   it under the terms of the GNU General Public License as published by
+#   the Free Software Foundation; either version 2 of the License, or
+#   (at your option) any later version.
+#
+#   Maruku is distributed in the hope that it will be useful,
+#   but WITHOUT ANY WARRANTY; without even the implied warranty of
+#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#   GNU General Public License for more details.
+#
+#   You should have received a copy of the GNU General Public License
+#   along with Maruku; if not, write to the Free Software
+#   Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+#
+# NOTA BENE:
+#
+# The following algorithm is a rip-off of RubyPants written by
+# Christian Neukirchen.
+#
+# RubyPants is a Ruby port of SmartyPants written by John Gruber.
+#
+# This file is distributed under the GPL, which I guess is compatible
+# with the terms of the RubyPants license.
+#
+# -- Andrea Censi
+#
+# = RubyPants -- SmartyPants ported to Ruby
+#
+# Ported by Christian Neukirchen <mailto:chneukirchen@gmail.com>
+#   Copyright (C) 2004 Christian Neukirchen
+#
+# Incooporates ideas, comments and documentation by Chad Miller
+#   Copyright (C) 2004 Chad Miller
+#
+# Original SmartyPants by John Gruber
+#   Copyright (C) 2003 John Gruber
+#
+#
+# = RubyPants -- SmartyPants ported to Ruby
+#
+#
+# [snip]
+#
+# == Authors
+#
+# John Gruber did all of the hard work of writing this software in
+# Perl for Movable Type and almost all of this useful documentation.
+# Chad Miller ported it to Python to use with Pyblosxom.
+#
+# Christian Neukirchen provided the Ruby port, as a general-purpose
+# library that follows the *Cloth API.
+#
+#
+# == Copyright and License
+#
+# === SmartyPants license:
+#
+# Copyright (c) 2003 John Gruber
+# (http://daringfireball.net)
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#
+# * Redistributions of source code must retain the above copyright
+#   notice, this list of conditions and the following disclaimer.
+#
+# * Redistributions in binary form must reproduce the above copyright
+#   notice, this list of conditions and the following disclaimer in
+#   the documentation and/or other materials provided with the
+#   distribution.
+#
+# * Neither the name "SmartyPants" nor the names of its contributors
+#   may be used to endorse or promote products derived from this
+#   software without specific prior written permission.
+#
+# This software is provided by the copyright holders and contributors
+# "as is" and any express or implied warranties, including, but not
+# limited to, the implied warranties of merchantability and fitness
+# for a particular purpose are disclaimed. In no event shall the
+# copyright owner or contributors be liable for any direct, indirect,
+# incidental, special, exemplary, or consequential damages (including,
+# but not limited to, procurement of substitute goods or services;
+# loss of use, data, or profits; or business interruption) however
+# caused and on any theory of liability, whether in contract, strict
+# liability, or tort (including negligence or otherwise) arising in
+# any way out of the use of this software, even if advised of the
+# possibility of such damage.
+#
+# === RubyPants license
+#
+# RubyPants is a derivative work of SmartyPants and smartypants.py.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#
+# * Redistributions of source code must retain the above copyright
+#   notice, this list of conditions and the following disclaimer.
+#
+# * Redistributions in binary form must reproduce the above copyright
+#   notice, this list of conditions and the following disclaimer in
+#   the documentation and/or other materials provided with the
+#   distribution.
+#
+# This software is provided by the copyright holders and contributors
+# "as is" and any express or implied warranties, including, but not
+# limited to, the implied warranties of merchantability and fitness
+# for a particular purpose are disclaimed. In no event shall the
+# copyright owner or contributors be liable for any direct, indirect,
+# incidental, special, exemplary, or consequential damages (including,
+# but not limited to, procurement of substitute goods or services;
+# loss of use, data, or profits; or business interruption) however
+# caused and on any theory of liability, whether in contract, strict
+# liability, or tort (including negligence or otherwise) arising in
+# any way out of the use of this software, even if advised of the
+# possibility of such damage.
+#
+# == Links
+#
+# John Gruber:: http://daringfireball.net
+# SmartyPants:: http://daringfireball.net/projects/smartypants
+#
+# Chad Miller:: http://web.chad.org
+#
+# Christian Neukirchen:: http://kronavita.de/chris
+#
+#++
+#
+
+module Kramdown
+  module Parser
+    class Kramdown
+
+      SQ_PUNCT = '[!"#\$\%\'()*+,\-.\/:;<=>?\@\[\\\\\]\^_`{|}~]'
+      SQ_CLOSE = %![^\ \\\\\t\r\n\\[{(-]!
+
+      SQ_RULES = [
+                  [/("|')(?=#{SQ_PUNCT}\B)/, [:rquote1]],
+                  # Special case for double sets of quotes, e.g.:
+                  #   <p>He said, "'Quoted' words in a larger quote."</p>
+                  [/(\s?)"'(?=\w)/, [1, :ldquo, :lsquo]],
+                  [/(\s?)'"(?=\w)/, [1, :lsquo, :ldquo]],
+                  # Special case for decade abbreviations (the '80s):
+                  [/(\s?)'(?=\d\ds)/, [1, :rsquo]],
+
+                  # Get most opening single/double quotes:
+                  [/(\s)('|")(?=\w)/, [1, :lquote2]],
+                  # Single/double closing quotes:
+                  [/(#{SQ_CLOSE})('|")/, [1, :rquote2]],
+                  # Special case for e.g. "<i>Custer</i>'s Last Stand."
+                  [/("|')(\s|s\b|$)/, [:rquote1, 2]],
+                  # Any remaining single quotes should be opening ones:
+                  [/(.?)'/m, [1, :lsquo]],
+                  [/(.?)"/m, [1, :ldquo]],
+                 ] #'"
+
+      SQ_SUBSTS = {
+        [:rquote1, '"'] => :rdquo,
+        [:rquote1, "'"] => :rsquo,
+        [:rquote2, '"'] => :rdquo,
+        [:rquote2, "'"] => :rsquo,
+        [:lquote1, '"'] => :ldquo,
+        [:lquote1, "'"] => :lsquo,
+        [:lquote2, '"'] => :ldquo,
+        [:lquote2, "'"] => :lsquo,
+      }
+      SMART_QUOTES_RE = /[^\\]?["']/
+
+      # Parse the smart quotes at current location.
+      def parse_smart_quotes
+        substs = SQ_RULES.find {|reg, subst| @src.scan(reg)}[1]
+        substs.each do |subst|
+          if subst.kind_of?(Integer)
+            add_text(@src[subst])
+          else
+            val = SQ_SUBSTS[[subst, @src[subst.to_s[-1,1].to_i]]] || subst
+            @tree.children << Element.new(:smart_quote, val)
+          end
+        end
+      end
+      define_parser(:smart_quotes, SMART_QUOTES_RE, '[^\\\\]?["\']')
+
+    end
+  end
+end