bean-kramdown 0.13.5

data/lib/kramdown/parser/kramdown.rb

@@ -0,0 +1,339 @@
+# -*- coding: utf-8 -*-
+#
+#--
+# Copyright (C) 2009-2012 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 'strscan'
+require 'stringio'
+
+#TODO: use [[:alpha:]] in all regexp to allow parsing of international values in 1.9.1
+#NOTE: use @src.pre_match only before other check/match?/... operations, otherwise the content is changed
+
+module Kramdown
+
+  module Parser
+
+    # Used for parsing a document in kramdown format.
+    #
+    # If you want to extend the functionality of the parser, you need to do the following:
+    #
+    # * Create a new subclass
+    # * add the needed parser methods
+    # * modify the @block_parsers and @span_parsers variables and add the names of your parser
+    #   methods
+    #
+    # Here is a small example for an extended parser class that parses ERB style tags as raw text if
+    # they are used as span-level elements (an equivalent block-level parser should probably also be
+    # made to handle the block case):
+    #
+    #   require 'kramdown/parser/kramdown'
+    #
+    #   class Kramdown::Parser::ERBKramdown < Kramdown::Parser::Kramdown
+    #
+    #      def initialize(source, options)
+    #        super
+    #        @span_parsers.unshift(:erb_tags)
+    #      end
+    #
+    #      ERB_TAGS_START = /<%.*?%>/
+    #
+    #      def parse_erb_tags
+    #        @src.pos += @src.matched_size
+    #        @tree.children << Element.new(:raw, @src.matched)
+    #      end
+    #      define_parser(:erb_tags, ERB_TAGS_START, '<%')
+    #
+    #   end
+    #
+    # The new parser can be used like this:
+    #
+    #   require 'kramdown/document'
+    #   # require the file with the above parser class
+    #
+    #   Kramdown::Document.new(input_text, :input => 'ERBKramdown').to_html
+    #
+    class Kramdown < Base
+
+      include ::Kramdown
+
+      # Create a new Kramdown parser object with the given +options+.
+      def initialize(source, options)
+        super
+
+        reset_env
+
+        @root.options[:abbrev_defs] = {}
+        @alds = {}
+        @link_defs = {}
+        @footnotes = {}
+
+        @block_parsers = [:blank_line, :codeblock, :codeblock_fenced, :blockquote, :atx_header,
+                          :horizontal_rule, :list, :definition_list, :block_html, :setext_header,
+                          :table, :footnote_definition, :link_definition, :abbrev_definition,
+                          :block_extensions, :block_math, :eob_marker, :paragraph]
+        @span_parsers =  [:emphasis, :codespan, :autolink, :span_html, :footnote_marker, :link, :image, :smart_quotes, :inline_math,
+                         :span_extensions, :html_entity, :typographic_syms, :line_break, :escaped_chars]
+
+      end
+      private_class_method(:new, :allocate)
+
+
+      # The source string provided on initialization is parsed into the @root element.
+      def parse
+        configure_parser
+        parse_blocks(@root, adapt_source(source))
+        update_tree(@root)
+        replace_abbreviations(@root)
+        @footnotes.each {|name,data| update_tree(data[:marker].value) if data[:marker]}
+      end
+
+      #######
+      protected
+      #######
+
+      # Adapt the object to allow parsing like specified in the options.
+      def configure_parser
+        @parsers = {}
+        (@block_parsers + @span_parsers).each do |name|
+          if self.class.has_parser?(name)
+            @parsers[name] = self.class.parser(name)
+          else
+            raise Kramdown::Error, "Unknown parser: #{name}"
+          end
+        end
+        @span_start, @span_start_re = span_parser_regexps
+      end
+
+      # Create the needed span parser regexps.
+      def span_parser_regexps(parsers = @span_parsers)
+        span_start = /#{parsers.map {|name| @parsers[name].span_start}.join('|')}/
+        [span_start, /(?=#{span_start})/]
+      end
+
+      # Parse all block-level elements in +text+ into the element +el+.
+      def parse_blocks(el, text = nil)
+        @stack.push([@tree, @src, @block_ial])
+        @tree, @src, @block_ial = el, (text.nil? ? @src : StringScanner.new(text)), nil
+
+        status = catch(:stop_block_parsing) do
+          while !@src.eos?
+            block_ial_set = @block_ial
+            @block_parsers.any? do |name|
+              if @src.check(@parsers[name].start_re)
+                send(@parsers[name].method)
+              else
+                false
+              end
+            end || begin
+              warning('Warning: this should not occur - no block parser handled the line')
+              add_text(@src.scan(/.*\n/))
+            end
+            @block_ial = nil if block_ial_set
+          end
+        end
+
+        @tree, @src, @block_ial = *@stack.pop
+        status
+      end
+
+      # Update the tree by parsing all :+raw_text+ elements with the span-level parser (resets the
+      # environment) and by updating the attributes from the IALs.
+      def update_tree(element)
+        last_blank = nil
+        element.children.map! do |child|
+          if child.type == :raw_text
+            last_blank = nil
+            reset_env(:src => StringScanner.new(child.value), :text_type => :text)
+            parse_spans(child)
+            child.children
+          elsif child.type == :eob
+            []
+          elsif child.type == :blank
+            if last_blank
+              last_blank.value << child.value
+              []
+            else
+              last_blank = child
+              child
+            end
+          else
+            last_blank = nil
+            update_tree(child)
+            update_attr_with_ial(child.attr, child.options[:ial]) if child.options[:ial]
+            child
+          end
+        end.flatten!
+      end
+
+      # Parse all span-level elements in the source string of @src into +el+.
+      #
+      # If the parameter +stop_re+ (a regexp) is used, parsing is immediately stopped if the regexp
+      # matches and if no block is given or if a block is given and it returns +true+.
+      #
+      # The parameter +parsers+ can be used to specify the (span-level) parsing methods that should
+      # be used for parsing.
+      #
+      # The parameter +text_type+ specifies the type which should be used for created text nodes.
+      def parse_spans(el, stop_re = nil, parsers = nil, text_type = @text_type)
+        @stack.push([@tree, @text_type]) unless @tree.nil?
+        @tree, @text_type = el, text_type
+
+        span_start = @span_start
+        span_start_re = @span_start_re
+        span_start, span_start_re = span_parser_regexps(parsers) if parsers
+        parsers = parsers || @span_parsers
+
+        used_re = (stop_re.nil? ? span_start_re : /(?=#{Regexp.union(stop_re, span_start)})/)
+        stop_re_found = false
+        while !@src.eos? && !stop_re_found
+          if result = @src.scan_until(used_re)
+            add_text(result)
+            if stop_re && @src.check(stop_re)
+              stop_re_found = (block_given? ? yield : true)
+            end
+            processed = parsers.any? do |name|
+              if @src.check(@parsers[name].start_re)
+                send(@parsers[name].method)
+                true
+              else
+                false
+              end
+            end unless stop_re_found
+            add_text(@src.getch) if !processed && !stop_re_found
+          else
+            (add_text(@src.rest); @src.terminate) unless stop_re
+            break
+          end
+        end
+
+        @tree, @text_type = @stack.pop
+
+        stop_re_found
+      end
+
+      # Reset the current parsing environment. The parameter +env+ can be used to set initial
+      # values for one or more environment variables.
+      def reset_env(opts = {})
+        opts = {:text_type => :raw_text, :stack => []}.merge(opts)
+        @src = opts[:src]
+        @tree = opts[:tree]
+        @block_ial = opts[:block_ial]
+        @stack = opts[:stack]
+        @text_type = opts[:text_type]
+      end
+
+      # Return the current parsing environment.
+      def save_env
+        [@src, @tree, @block_ial, @stack,  @text_type]
+      end
+
+      # Restore the current parsing environment.
+      def restore_env(env)
+        @src, @tree, @block_ial, @stack,  @text_type = *env
+      end
+
+      # Update the given attributes hash +attr+ with the information from the inline attribute list
+      # +ial+ and all referenced ALDs.
+      def update_attr_with_ial(attr, ial)
+        ial[:refs].each do |ref|
+          update_attr_with_ial(attr, ref) if ref = @alds[ref]
+        end if ial[:refs]
+        ial.each do |k,v|
+          if k == IAL_CLASS_ATTR
+            attr[k] = (attr[k] || '') << " #{v}"
+            attr[k].lstrip!
+          elsif k.kind_of?(String)
+            attr[k] = v
+          end
+        end
+      end
+
+      # Create a new block-level element, taking care of applying a preceding block IAL if it
+      # exists. This method should always be used for creating a block-level element!
+      def new_block_el(*args)
+        el = Element.new(*args)
+        el.options[:ial] = @block_ial if @block_ial && el.type != :blank && el.type != :eob
+        el
+      end
+
+      @@parsers = {}
+
+      # Struct class holding all the needed data for one block/span-level parser method.
+      Data = Struct.new(:name, :start_re, :span_start, :method)
+
+      # Add a parser method
+      #
+      # * with the given +name+,
+      # * using +start_re+ as start regexp
+      # * and, for span parsers, +span_start+ as a String that can be used in a regexp and
+      #   which identifies the starting character(s)
+      #
+      # to the registry. The method name is automatically derived from the +name+ or can explicitly
+      # be set by using the +meth_name+ parameter.
+      def self.define_parser(name, start_re, span_start = nil, meth_name = "parse_#{name}")
+        raise "A parser with the name #{name} already exists!" if @@parsers.has_key?(name)
+        @@parsers[name] = Data.new(name, start_re, span_start, meth_name)
+      end
+
+      # Return the Data structure for the parser +name+.
+      def self.parser(name = nil)
+        @@parsers[name]
+      end
+
+      # Return +true+ if there is a parser called +name+.
+      def self.has_parser?(name)
+        @@parsers.has_key?(name)
+      end
+
+      # Regexp for matching indentation (one tab or four spaces)
+      INDENT = /^(?:\t| {4})/
+      # Regexp for matching the optional space (zero or up to three spaces)
+      OPT_SPACE = / {0,3}/
+
+      require 'kramdown/parser/kramdown/blank_line'
+      require 'kramdown/parser/kramdown/eob'
+      require 'kramdown/parser/kramdown/paragraph'
+      require 'kramdown/parser/kramdown/header'
+      require 'kramdown/parser/kramdown/blockquote'
+      require 'kramdown/parser/kramdown/table'
+      require 'kramdown/parser/kramdown/codeblock'
+      require 'kramdown/parser/kramdown/horizontal_rule'
+      require 'kramdown/parser/kramdown/list'
+      require 'kramdown/parser/kramdown/link'
+      require 'kramdown/parser/kramdown/image'
+      require 'kramdown/parser/kramdown/extensions'
+      require 'kramdown/parser/kramdown/footnote'
+      require 'kramdown/parser/kramdown/html'
+      require 'kramdown/parser/kramdown/escaped_chars'
+      require 'kramdown/parser/kramdown/html_entity'
+      require 'kramdown/parser/kramdown/line_break'
+      require 'kramdown/parser/kramdown/typographic_symbol'
+      require 'kramdown/parser/kramdown/autolink'
+      require 'kramdown/parser/kramdown/codespan'
+      require 'kramdown/parser/kramdown/emphasis'
+      require 'kramdown/parser/kramdown/smart_quotes'
+      require 'kramdown/parser/kramdown/math'
+      require 'kramdown/parser/kramdown/abbreviation'
+
+    end
+
+  end
+
+end

data/lib/kramdown/parser/kramdown/abbreviation.rb

@@ -0,0 +1,71 @@
+# -*- coding: utf-8 -*-
+#
+#--
+# Copyright (C) 2009-2012 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/>.
+#++
+#
+
+module Kramdown
+  module Parser
+    class Kramdown
+
+      ABBREV_DEFINITION_START = /^#{OPT_SPACE}\*\[(.+?)\]:(.*?)\n/
+
+      # Parse the link definition at the current location.
+      def parse_abbrev_definition
+        @src.pos += @src.matched_size
+        abbrev_id, abbrev_text = @src[1], @src[2]
+        abbrev_text.strip!
+        warning("Duplicate abbreviation ID '#{abbrev_id}' - overwriting") if @root.options[:abbrev_defs][abbrev_id]
+        @root.options[:abbrev_defs][abbrev_id] = abbrev_text
+        @tree.children << Element.new(:eob, :abbrev_def)
+        true
+      end
+      define_parser(:abbrev_definition, ABBREV_DEFINITION_START)
+
+      # Replace the abbreviation text with elements.
+      def replace_abbreviations(el, regexps = nil)
+        return if @root.options[:abbrev_defs].empty?
+        if !regexps
+          regexps = [Regexp.union(*@root.options[:abbrev_defs].keys.map {|k| /#{Regexp.escape(k)}/})]
+          regexps << /(?=(?:\W|^)#{regexps.first}(?!\w))/ # regexp should only match on word boundaries
+        end
+        el.children.map! do |child|
+          if child.type == :text
+            if child.value =~ regexps.first
+              result = []
+              strscan = StringScanner.new(child.value)
+              while temp = strscan.scan_until(regexps.last)
+                temp << strscan.scan(/\W|^/)
+                abbr = strscan.scan(regexps.first)
+                result << Element.new(:text, temp) << Element.new(:abbreviation, abbr)
+              end
+              result << Element.new(:text, strscan.rest)
+            else
+              child
+            end
+          else
+            replace_abbreviations(child, regexps)
+            child
+          end
+        end.flatten!
+      end
+
+    end
+  end
+end

data/lib/kramdown/parser/kramdown/autolink.rb

@@ -0,0 +1,53 @@
+# -*- coding: utf-8 -*-
+#
+#--
+# Copyright (C) 2009-2012 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/>.
+#++
+#
+
+module Kramdown
+  module Parser
+    class Kramdown
+
+      if RUBY_VERSION == '1.8.5'
+        ACHARS = '\w\x80-\xFF'
+      elsif RUBY_VERSION < '1.9.0'
+        ACHARS = '\w'
+      else
+        ACHARS = '[[:alnum:]]'
+      end
+      AUTOLINK_START_STR = "<((mailto|https?|ftps?):.+?|[-.#{ACHARS}]+@[-#{ACHARS}]+(?:\.[-#{ACHARS}]+)*\.[a-z]+)>"
+      if RUBY_VERSION < '1.9.0'
+        AUTOLINK_START = /#{AUTOLINK_START_STR}/u
+      else
+        AUTOLINK_START = /#{AUTOLINK_START_STR}/
+      end
+
+      # Parse the autolink at the current location.
+      def parse_autolink
+        @src.pos += @src.matched_size
+        href = (@src[2].nil? ? "mailto:#{@src[1]}" : @src[1])
+        el = Element.new(:a, nil, {'href' => href})
+        add_text(@src[1].sub(/^mailto:/, ''), el)
+        @tree.children << el
+      end
+      define_parser(:autolink, AUTOLINK_START, '<')
+
+    end
+  end
+end