org-parse 0.1.1

data/lib/org-parse/struct-scanner.rb

@@ -0,0 +1,272 @@
+# -*- coding: utf-8 -*-
+require ::File.join(OrgParse::LIBPATH , 'org-parse', 'inline-parser.rb')
+require ::File.join(OrgParse::LIBPATH , 'org-parse', 'utils.rb')
+require 'yaml'
+
+
+module OrgParse
+
+  # Org-modeの文字列を、構造レベルのトークンに分解する
+  # 
+  # 処理は、行単位で行う
+  #
+  class StructScanner
+    include Utils
+    include InlineUtils
+
+    GENERATOR = "OrgParse #{VERSION} Powered by Ruby #{RUBY_VERSION}"
+
+    ListSymbols = {
+      :UL_START => :UL_END, :OL_START => :OL_END,
+      :DL_START => :DL_END,
+    }
+
+    # コンストラクタ
+    # [_src_] ソース文字列（または、文字列の配列）
+    #         ソース文字列は、1行単位の配列として @srcに保存する
+    # [_title_] skip:t の場合にタイトルとして使われる
+    def initialize(src, title)
+      @src = (src.is_a? Array) ? src : src.to_a
+      @line_idx = 0
+      @outline_level = 0
+      @nest_stack = []
+      @token_que = []
+      @section_stack = []
+      @options = { :H => 3, :skip => false, :toc => true, :num => true,
+        :author => nil, 
+        :url => nil,
+        :email => nil,
+        :creator => GENERATOR, :timestamp => true,
+        :title => nil, :text => [], :language => 'ja', :charset => 'utf-8',
+        :default_title => title, :style => '', :uv => true,
+      }
+      read_options
+      opt = YAML.dump @options
+      File.open('dot.rc2', "w") {|f|
+        f.write opt
+      }
+      # p @options
+    end
+
+    # http://orgmode.org/manual/Export-options.html#Export-options
+    def read_options
+      @src.reject! do |line|
+        m = true
+        case line
+        when /^\s*#\+OPTIONS:\s/i
+          case $'
+          when /H:([0-9]+)/
+            @options[:H] = $1.to_i
+          when /skip:(\w)/
+            @options[:skip] = $1 != 'nil'
+          when /num:(\w+)/
+            @options[:num] = $1 != 'nil'
+          when /toc:(\w+)/
+            @options[:toc] = $1 != 'nil'
+          when /author:(\w+)/
+            @options[:author] = $1 != 'nil'
+          when /creator:(\w+)/
+            @options[:creator] = $1 != 'nil'
+          when /timestamp:(\w+)/
+            @options[:timestamp] = $1 != 'nil'
+          when /uv:(\w+)/
+            @options[:uv] = $1 != 'nil'
+          else
+            m = false
+          end
+        when /^\s*#\+TITLE:\s+(.*)$/i
+          @options[:title] = $1
+        when /^\s*#\+TEXT:\s+(.*)$/i
+          @options[:text] += line_parse($1 + "\n")
+        when /^\s*#\+LANGUAGE:\s+(.*)/i
+          @options[:language] = $1
+        when /^\s*#\+AUTHOR:\s*(.*)/i
+          @options[:author] = $1
+        when /^\s*#\+EMAIL:\s*(.*)/i
+          @options[:email] = $1
+        when /^\s*#\+STYLE:\s*(.*)$/i
+          @options[:style] += $1
+        else
+          m = false
+        end
+        m
+      end
+    end
+    
+    def next_token
+      return [[false, false],[]] if @token_que.empty?
+      # p @token_que[0]
+      token = @token_que.shift
+      vars = []
+
+      while token[0] == :VARIABLELINE and (token[1][0] == "ATTR_HTML" or token[1][0] == "CAPTION")
+        if token[1][0] == "CAPTION"
+          vars << "CAPTION:" + token[1][1]
+        else
+          vars << token[1][1]
+        end
+        return [[false, false], []] if @token_que.empty?
+        token = @token_que.shift
+      end
+      [token, vars]
+    end
+
+    # リスト開始ラインのネストをチェックする
+    # @nest_stack が、空なら新規リストの開始
+    # @nest_stack.last のインデントよりも、インデントが深ければ、
+    # ネストしたリストの開始
+    # @nest_stack.last のインデントとインデントが等しければ
+    # 新規のリストアイテムの開始
+    # @nest_stack.last のインデントよりインデントが浅ければ、
+    # @nest_stack.last のリストの終了後、新規リストを開始
+    def check_nest(kind, indent, string, dt = '')
+      last = @nest_stack.last
+      if @nest_stack.empty? 
+        # puts "0: line: #{line.chomp}  indent: #{indent} last: #{last.inspect}"
+        @nest_stack << [kind, indent]
+        @token_que << [kind, string]
+        @token_que << [:LI_START, [kind, string, dt]]
+      elsif last[1] < indent
+        # puts "1: line: #{line.chomp}  indent: #{indent} last: #{last.inspect}"
+        @nest_stack << [kind, indent]
+        # @token_que << [:LI_END, line]
+        @token_que << [kind, string]
+        @token_que << [:LI_START, [kind, string, dt]]
+      elsif last[1] > indent
+        # puts "2: line: #{line.chomp}  indent: #{indent} last: #{last.inspect}"
+        nest = @nest_stack.pop
+        @token_que << [:LI_END, string]
+        @token_que << [ListSymbols[nest[0]], ListSymbols[nest[0]]]
+        check_nest kind, indent, string
+      else
+        # puts "3: line: #{line.chomp}  indent: #{indent} last: #{last.inspect}"
+        @token_que << [:LI_END, string]
+        @token_que << [:LI_START, [kind, string, dt]]
+      end
+    end
+
+    # if in list then exit list.
+    def exit_nests(line)
+      indent = get_indent line
+      while @nest_stack.last and @nest_stack.last[1] >= indent
+        nest = @nest_stack.pop
+        @token_que << [:LI_END, line]
+        @token_que << [ListSymbols[nest[0]], line]
+      end
+    end
+
+    def exit_section(level)
+      cnt = 0
+      while @section_stack.last and @section_stack.last >= level
+        @token_que << [:SEC_END, level]
+        @section_stack.pop
+      end
+    end
+
+    def skip_to_1st_headline
+      @line_idx += 1 while @src[@line_idx] !~ /^\*\s+[^\s]/
+    end
+
+    # scan before 1st headline
+    def scan_before_1st_headline
+      title = nil
+      if @options[:title]
+        title =@options[:title]
+        skip_to_1st_headline if @options[:skip]
+      elsif @options[:skip]
+        skip_to_1st_headline
+        title = @options[:default_title]
+      else
+        @line_idx += 1 while @src[@line_idx] =~ /^\s*$/
+        title = @src[@line_idx].chomp.sub(/^\s*/, '')
+        if title =~ /^\*+\s*/
+          title = @options[:default_title]
+        else
+          @line_idx += 1
+        end
+      end
+      @options[:title] = line_parse title
+    end
+
+    # split to tokens from @src array and set to @token_que
+    def scan
+      @line_idx = 0
+      scan_before_1st_headline
+      example_flag = false
+      @token_que << [:DOCUMENT_START, @options]
+      while @line_idx < @src.size
+        line = @src[@line_idx]
+        if example_flag && line !~ /^\s*#\+end_(example|html|src)/i
+          @token_que << [:TEXTLINE, [line, get_indent(line)]]
+          @line_idx += 1
+          next
+        end
+
+        case line
+        when /^\s*$/ # WHITELINE
+          @token_que << [:WHITELINE, line]
+        when /^(\*+)(\s+)COMMENT(\s)/
+          @line_idx += 1
+          @line_idx += 1 while @src[@line_idx] and @src[@line_idx] !~ /^\*+\s/
+          @line_idx -= 1 if @src[@line_idx]
+        when /^(\*+)(\s+)/
+          rest = $'
+          level = $1
+          exit_nests('')
+          exit_section(level.size)
+          @section_stack << level.size
+          @token_que << [:HEADLINE, [level, rest]]
+        when /^(\s*)-\s(.+)\s::\s+/
+          # Definition LIST
+          rest = $'
+          check_nest :DL_START, get_indent($1), rest, $2
+        when /^(\s*)[-+*]\s/
+          # Unordered LIST
+          rest = $'
+          check_nest :UL_START, get_indent($1), rest
+        when /^(\s*)[0-9]+(\.|\))\s+/
+          # Ordered LIST
+          rest = $'
+          check_nest :OL_START, get_indent($1), rest
+        when /^\s*#\+HTML:/
+          # #+HTML
+          rest = $'
+          @token_que << [:QUOTE, $']
+        when /^\s*#\+([^ :]+):\s*(.+)$/
+          @token_que << [:VARIABLELINE, [$1.upcase, $2.chomp]]
+        when /^(\s*):\s(.*)$/
+          @token_que << [:EXAMPLE, [$2+"\n", get_indent($1)]]
+        when /^\s*#\+BEGIN_([A-Z0-9_]+)/i # BLOCK
+          block_name = $1.upcase
+          exit_nests line
+          @token_que << [:BLOCK_START, [block_name, line, get_indent(line)]]
+          example_flag = true if ['EXAMPLE', 'HTML', 'SRC'].include? block_name.upcase
+        when /^\s*#\+END_([A-Z0-9_]+)/i # BLOCK
+          block_name = $1
+          exit_nests line
+          @token_que << [:BLOCK_END, [block_name, line]]
+          example_flag = false
+        when /^\s*\|[-\|\+]*\s*$/ # table separator
+          # an org-mode table separator has the first non-whitespace
+          # character as a | (pipe), then consists of nothing else other
+          # than pipes, hyphens, and pluses.
+          exit_nests line
+          @token_que << [:TABLE_SEP, line]
+        when /^\s*\|/             # table_row
+          # the first non-whitespace character is a | (pipe).
+          exit_nests line
+          @token_que << [:TABLE_ROW, line]
+        when /^\s*\[fn:([^\]]+)\]\s+(.+)$/
+          exit_nests line
+          @token_que << [:FOOTNOTE, [$1, $2]]
+        else
+          exit_nests line
+          @token_que << [:TEXTLINE, [line, get_indent(line)]]
+        end
+        @line_idx += 1
+      end
+      exit_nests ''
+      exit_section(0)
+    end
+  end
+end

data/lib/org-parse/templates/single.html.erb

@@ -0,0 +1,118 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
+               "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml"
+lang="<%= @language %>" xml:lang="<%= @language %>">
+<head>
+<title><%= @title %></title>
+<meta http-equiv="Content-Type" content="text/html;charset=<%= @charset %>"/>
+<meta name="generator" content="Org-parse"/>
+<meta name="generated" content="<%= Time.now.to_s %>"/>
+<% if @options[:author] %>
+  <meta name="author" content="<%= @options[:author] %>"/>
+<% end %>
+<meta name="description" content=""/>
+<meta name="keywords" content=""/>
+<style type="text/css">
+ <!--/*--><![CDATA[/*><!--*/
+  html { font-family: "ＭＳ Ｐゴシック",Osaka,sans-serif,serif,monospace,cursive,fantasy; font-size: 12pt; }
+  .title  { text-align: center; }
+  .todo   { color: red; }
+  .done   { color: green; }
+  .tag    { background-color: #add8e6; font-weight:normal }
+  .target { }
+  .timestamp { color: #bebebe; }
+  .timestamp-kwd { color: #5f9ea0; }
+  p.verse { margin-left: 3% }
+  pre {
+	border: 1pt solid #AEBDCC;
+	background-color: #F3F5F7;
+	padding: 5pt;
+	font-family: courier, monospace;
+        font-size: 90%;
+        overflow:auto;
+  }
+  blockquote {
+	border: 1pt solid #AEBDCC;
+	background-color: #F3F5F7;
+	padding: 5pt;
+	font-family: courier, monospace; 
+        font-size: 90%;
+        /* overflow:auto; */
+  }
+  table { border-collapse: collapse; }
+  td, th { vertical-align: top; }
+  dt { font-weight: bold; }
+  div.figure { padding: 0.5em; }
+  div.figure p { text-align: center; }
+  .linenr { font-size:smaller }
+  .code-highlighted {background-color:#ffff00;}
+  .org-info-js_info-navigation { border-style:none; }
+  #org-info-js_console-label { font-size:10px; font-weight:bold;
+                               white-space:nowrap; }
+  .org-info-js_search-highlight {background-color:#ffff00; color:#000000;
+                                 font-weight:bold; }
+  /*]]>*/-->
+</style>
+<%= @add_to_head %>
+<script type="text/javascript">
+<!--/*--><![CDATA[/*><!--*/
+ function CodeHighlightOn(elem, id)
+ {
+   var target = document.getElementById(id);
+   if(null != target) {
+     elem.cacheClassElem = elem.className;
+     elem.cacheClassTarget = target.className;
+     target.className = "code-highlighted";
+     elem.className   = "code-highlighted";
+   }
+ }
+ function CodeHighlightOff(elem, id)
+ {
+   var target = document.getElementById(id);
+   if(elem.cacheClassElem)
+     elem.className = elem.cacheClassElem;
+   if(elem.cacheClassTarget)
+     target.className = elem.cacheClassTarget;
+ }
+/*]]>*///-->
+</script>
+</head>
+<body>
+<div id="content">
+
+<h1 class="title"><%= @title %></h1>
+
+<%= @before_text %>
+
+<%= table_of_contents %>
+
+<%= @body %>
+
+<% unless @footnotes.empty? %>
+<div id="footnotes">
+  <h2 class="footnotes">Footnotes: </h2>
+  <div id="text-footnotes">
+    <%= footnotes %>
+  </div>
+</div>
+<% end %>
+
+<div id="postamble">
+<% if @options[:author] %>
+  <p class="author"> Author: <%= @options[:author] %>
+    <% if @options[:email] %>
+      <a href="mailto:<%= @options[:email] %>">&lt;<%= @options[:email] %>&gt;</a>
+    <% end %>
+  </p>
+<% end %>
+<% if @options[:timestamp] %>
+  <p class="date"> Date: <%= Time.now %> </p>
+<% end %>
+<% if @options[:creator] %>
+  <p class="creator">HTML generated by <%= @options[:creator] %></p>
+<% end %>
+</div>
+</div>
+</body>
+</html>

data/lib/org-parse/textile-visitor.rb

@@ -0,0 +1,296 @@
+# -*- coding: utf-8 -*-
+require 'rubygems'
+require ::File.join(OrgParse::LIBPATH , 'org-parse', 'visitor.rb')
+
+module OrgParse
+
+  # todo: 
+  # \\-    ­      \\-　
+  # --    –    --
+  # ---   —    ---
+  # ...   …   \ldots
+
+  # output HTML format
+  class TextileVisitor < OrgVisitor
+    include VisitorUtils
+
+    def initialize(root, cm_opts = {})
+      @body = @title = @add_to_head = ''
+      @root = root
+      @ul_stack = []
+      @list_level = 0
+      @body = ''
+      @options = cm_opts
+      super()
+    end
+
+    # build the textile
+    def build
+      @options = @root.options
+      @before_text = exec_list @options[:text]
+      title = exec_list @root.options[:title]
+      body = "h1. " + title + "\n\n" + @before_text
+      @footnotes = []
+      @footnote_idxs = []
+      start_flag = true
+      @root.children.each do |node|
+        if start_flag and node.kind != :SECTION
+          @before_text += execute(node)
+        else
+          start_flag = false
+          body += execute(node)
+        end
+      end
+      body += footnotes
+    end
+
+    def headline(node)
+      level = node.level+1
+      %Q|\nh#{level}. #{exec_children(node).chomp}\n\n|
+    end
+
+    # paragraph 
+    # if @p_tag_flag == false then we don't output <p></p> tags.
+    def textblock(node)
+      if node.verse? or node.example? or node.html? or node.src?
+        exec_children node
+      elsif @p_tag_flag
+        "p. #{exec_children(node).sub(/^\s*/,'').chomp}\n"
+      else
+        str = exec_children node
+        @p_tag_flag = true  # next paragraph has <p>
+        str
+      end
+    end
+
+    def textline(node)
+      str = exec_children(node)
+      str = h str unless node.verse? or node.example? or node.html? or node.src?
+      str
+    end
+
+    def example(node)
+      body = exec_children(node)
+      %Q|<pre>\n#{ body.chomp }\n</pre>\n|
+    end
+
+    def src(node)
+      if @options[:redmine]
+        text = exec_children(node)
+        syntax = node.syntax
+        %Q|<pre><code class="#{syntax}">\n#{ body.chomp }\n</code></pre>\n|
+      else
+        example node
+      end
+    end
+
+    def blockquote(node)
+      body = exec_children(node)
+      body.sub(/\n/, '<br/>')
+      %Q|\nbq.#{body.sub(/^\s*/,'').chomp}\n\n|
+    end
+
+    def blocks(node)
+      case node.block_name
+      when 'VERSE'
+        example node
+      when 'EXAMPLE'
+        example node
+      when 'QUOTE'
+        blockquote node
+      when 'HTML'
+        textblock node
+      when 'COMMENT'
+        ''
+      when 'SRC'
+        src node
+      else
+        puts "not implimented block=>[#{node.block_name}](#{node.inspect})"
+        exec_children(node)
+      end
+    end
+
+    def link(node)
+      desc = exec_children node
+      if desc.empty?
+        if node.uri =~ @image_file_reg
+          " !#{node.uri.sub(/^file:/, '')}! "
+        else
+          " #{node.uri.sub(/^file:/, '')} "
+        end
+      else
+        %Q| "#{desc}":#{node.uri.sub(/^file:/, '')} |
+      end
+    end
+
+    def table(node)
+      ret = ''
+      ret += exec_list node.hrows
+      ret += exec_children node
+    end
+      
+    def table_row(node)
+      ret = ''
+      s = node.is_head? ? '|_.' : '|'
+      node.children.each {|cols|
+        cols.each{|col|
+          ret += s + execute(col)
+        }
+      }
+      ret += "|\n"
+    end
+
+    def variable(node)
+      fvs = ['CAPTION', 'ATTR_HTML', 'TEXT']
+      if fvs.include? node.name
+        @flash_vars[node.name] = node.value
+      else
+        @options[node.name] = node.value
+      end
+      ''
+    end
+
+    def clear_vars
+      @flash_vars.clear
+    end
+
+    def lists(node)
+      tags = { :UNORDERED_LIST => ['<ul>', '</ul>'],
+        :ORDERED_LIST => ['<ol>', '</ol>'],
+        :DEFINITION_LIST => ['<dl>', '</dl>'],
+      }
+      @list_level += 1
+      body = exec_children node
+      @list_level -= 1
+      if node.kind == :DEFINITION_LIST
+        "#{tags[node.kind][0]}\n#{body.chomp}\n#{tags[node.kind][1]}\n"
+      else
+        body
+      end
+    end
+
+    # list_item 
+    def list_item(node)
+      marks = { :UL_START => '*', :OL_START => '#' }
+      if node.children.empty?
+        if node.type == :DL_START
+          "  <dt>#{exec_list(node.dt)}</dt>\n  <dd>#{exec_list(node.value).chomp}</dd>\n"
+        else
+          mark = marks[node.type] * @list_level
+          "#{mark} #{exec_list(node.value).chomp}\n"
+        end
+      else
+        @list_level += 1
+        @p_tag_flag = false
+        str = exec_list(node.value)
+        str += exec_children node
+        str.sub(/\n/, '<br/>')
+        if node.type == :DL_START
+          str = "  <dt>#{exec_list(node.dt)}</dt>\n  <dd>\n#{str.chomp}</dd>\n"
+        else
+          mark = marks[node.type] * @list_level
+          str = "#{mark} #{str.chomp}\n"
+        end
+        @p_tag_flag = true
+        @list_level -= 1
+        str
+      end
+    end
+
+    def footnote_link(node)
+      idx = @footnote_idxs.index node.value
+      unless idx
+        idx = @footnote_idxs.size
+        @footnote_idxs << node.value
+      end
+      idx += 1
+      "[#{idx}]"
+    end
+
+    def footnote_define(node)
+      idx = @footnote_idxs.index node.value
+      unless idx
+        idx = @footnote_idxs.size
+        @footnote_idxs << node.value
+      end
+      @footnotes[idx] = exec_children(node)
+      ''
+    end
+
+    def footnotes
+      ret = ''
+      @footnotes.each_index{|idx|
+        n = idx+1
+        val = @footnotes[idx]
+        ret += "fn#{n}. #{val}\n"
+      }
+      ret
+    end
+
+    def execute(node)
+      # puts "node:#{node.kind} [#{node.value}]\n"
+      # STDERR.puts node.inspect
+      return '' if node.done?
+      case node.kind
+      when :SECTION
+        str = execute node.headline
+        str += exec_children node # section node
+      when :HEADLINE
+        headline node
+      when :TEXTBLOCK
+        textblock node
+      when :WHITELINE, :WHITELINES
+        "\n" * node.value
+      when :STRING
+        node.value
+      when :QUOTE
+        if node.value == "\n"
+          '<br/>'
+        else
+          node.value
+        end
+      when :TEXTLINE
+        textline node
+      when :EMPHASIS
+        " *#{ exec_children node }* "
+      when :ITALIC
+        " _#{ exec_children node }_ "
+      when :UNDER_LINE
+        %Q| +#{exec_children node}+ |
+      when :STRIKE_THROUGH
+        " -#{ exec_children node}- "
+      when :CODE, :VERBATIM
+        " @#{ exec_children node }@ "
+      when :VARIABLE
+        variable node
+      when :UNORDERED_LIST, :ORDERED_LIST, :DEFINITION_LIST
+        lists node
+      when :LIST_ITEM
+        list_item node
+      when :LINK
+        link node
+      when :BLOCK
+        blocks node
+      when :TABLE
+        table node
+      when :TABLE_ROW
+        table_row node
+      when :FN_LINK
+        footnote_link node
+      when :FN_DEFINE
+        footnote_define node
+      else
+        puts "not implimented=>[#{node.kind}](#{node.inspect})"
+        ''
+      end
+    end
+
+    # HTML escape
+    def html_escape(s)
+      s.to_s.gsub(/&/, "&amp;").gsub(/>/, "&gt;").gsub(/</, "&lt;")
+    end
+    alias h html_escape
+
+  end
+
+end

data/lib/org-parse/utils.rb

@@ -0,0 +1,15 @@
+# -*- coding: utf-8 -*-
+
+module OrgParse
+
+  module Utils
+    # とりあえず
+    def get_indent(str)
+      return 0 if str.empty?
+      str =~ /^(\s*)/
+      $1.gsub(/([^\t]{8})|([^\t]*)\t/n){ [$+].pack("A8") }.size
+    end
+  end
+
+end
+