hateda2md 0.0.1

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in hateda2md.gemspec
+gemspec

data/LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2012 kyoendo
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,93 @@
+# Hateda2md
+
+This is a converter that build separated markdown files using for Jekyll from a Hatena-Diary XML file, which written with Hatena notations. You can set several pre-defined filters and/or can define your original filters.
+
+`Hateda2md`は、はてな記法で書かれたXMLファイルから、Jekyll用のMarkdownファイルを生成するコンバータです。定義済みフィルタを使って、または自身でフィルタを定義して変換を行うことができます。
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'hateda2md'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install hateda2md
+
+## Usage
+
+    require "Hateda2md"
+
+    mdb = HateDa::MdBuilder.new('hatena-diary.xml')
+
+    # set several pre-defined filters
+    # 幾つかの定義済みフィルタをセットする
+    mdb.set :title
+    mdb.set :subtitle
+    mdb.set :link
+    mdb.set :amazon
+    
+    # run converter 
+    # 変換を実行する
+    mdb.run
+
+    # save converted data to separated markdown files correspond to each entry
+    # 変換後のデータを各エントリーに対応した複数のMarkdownファイルに保存する
+    mdb.save_to_files
+
+This process create several markdown files under `md` directory.
+
+本処理により`md`ディレクトリ以下に、複数のmarkdownファイルが生成されます。
+
+To set all pre-defined filters, you can call `MdBuilder#pre_defined_filters` or `HateDa::Converter.pre_defined_filters` method.
+
+すべての定義済みフィルタをセットするには、`MdBuilder#pre_defined_filters`または`HateDa::Converter.pre_defined_filters`メソッドを呼びます。
+
+    # read all pre-defined filters
+    # すべての定義済みフィルタを呼ぶ
+    filters = mdb.pre_defined_filters
+    # => [:title, :subtitle, :subsubtitle, :order_list, :unorder_list, :blockquote, :pre, :super_pre, :footnote, :br, :link, :hatebu, :amazon, :youtube, :image, :gist]
+
+    # set all the pre-defined filters
+    # すべての定義済みフィルタをセットする
+    filters.each { |f| mdb.set f }
+
+You can define filters.
+
+独自フィルタを定義できます。
+
+    # define a filter to convert wikipedia hatena tag to a correspond liquid tag
+    # はてな記法によるwikipediaタグをliquid tagに変換するフィルタを定義する
+    mdb.filter(/\[wikipedia:(.*?)\]/) do |md, st|
+      st[:wikipedias] << md[1]
+      "{% wikipedia #{md[1]} %}"
+    end
+
+`MdBuilder#run` can take parameters for selecting entries to be converted.
+
+`MdBuilder#run`に引数を渡すことで、特定のエントリだけを変換することができます。
+
+    # convert only #20 entry
+    # 20番目のエントリだけを変換
+    mdb.run(20)
+
+    # convert #100 to last entries
+    # 100番から最後のエントリを変換
+    mdb.run(100..-1)
+
+    # convert 20 entries from #10
+    # 10番から20件を変換
+    mdb.run(10,20)
+
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Added some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,2 @@
+#!/usr/bin/env rake
+require "bundler/gem_tasks"

data/example/example.rb

@@ -0,0 +1,9 @@
+# encoding: UTF-8
+require "../lib/hateda2md"
+
+mdb = HateDa::MdBuilder.new('example.xml')
+
+filters = mdb.pre_defined_filters
+filters.each { |f| mdb.set f }
+mdb.run(0..200)
+mdb.save_to_files

data/hateda2md.gemspec

@@ -0,0 +1,22 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/hateda2md/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["kyoendo"]
+  gem.email         = ["postagie@gmail.com"]
+  gem.description   = %q{Convert Hatena-Diary XML file to Markdown files for Jekyll}
+  gem.summary       = %q{
+    This is a converter that build separated markdown files using for Jekyll from a Hatena-Diary XML file, which written with Hatena notations. You can set several pre-defined filters or can define your original filters.
+    }.strip
+  gem.homepage      = "https://github.com/melborne/hateda2md"
+
+  gem.files         = `git ls-files`.split($\)
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.name          = "hateda2md"
+  gem.require_paths = ["lib"]
+  gem.version       = Hateda2md::VERSION
+  gem.required_ruby_version = '>=1.9.2'
+  gem.add_development_dependency 'rspec'
+  gem.add_dependency 'nokogiri'
+  gem.add_dependency 'gsub_filter'
+end

data/lib/hateda2md/converter.rb

@@ -0,0 +1,176 @@
+# encoding: UTF-8
+require "gsub_filter"
+require "uri"
+
+module HateDa::Converter
+  class NoFilterError < StandardError; end
+  
+  def set(item, *args)
+    unless HateDa::Converter.pre_defined_filters(true).include?(item)
+      raise NoFilterError, "#{item} does not pre-defined."
+    end
+    send item, *args
+  end
+  
+  def to_md(hdtext)
+    (@gf ||= GsubFilter.new).run(hdtext)
+  end
+
+  def clear_filter
+    @gf.filters.clear if @gf
+  end
+
+  def stocks
+    @gf.stocks if @gf
+  end
+  
+  def filter(pattern, opt={}, &replace)
+    @gf ||= GsubFilter.new
+    @gf.filter(pattern, opt, &replace)
+  end
+
+  def self.pre_defined_filters(aliases=false)
+    als = aliases ? [] : [:header, :subheader, :subsubheader, :ul, :ol]
+    private_instance_methods(false) - [:SYM] - als
+  end
+  
+  private
+  def SYM(key)
+    {h1:'#',h2:'##',h3:'###',h4:'####',h5:'#####'}[key]
+  end
+
+  def title(h=:h1)
+    filter(/\*p?\d+\*(.*)$/) do |md, st|
+      st[:titles] << md[1]
+      "#{SYM(h)}#{md[1]}"
+    end
+    filter(/^#{SYM(h)}.*$/, global:false) do |md, st|
+      st[:titles].size == 1 ? '' : md.to_s
+    end
+  end
+  alias :header :title
+
+  def subtitle(h=:h2)
+    filter(/^\*\*((?!\*).*)$/) do |md, st|
+      st[:subtitles] << md[1]
+      "#{SYM(h)}#{md[1]}"
+    end
+  end
+  alias :subheader :subtitle
+
+  def subsubtitle(h=:h3)
+    filter(/^\*\*\*((?!\*).*)$/) do |md, st|
+      st[:subsubtitles] << md[1]
+      "#{SYM(h)}#{md[1]}"
+    end
+  end
+  alias :subsubheader :subsubtitle
+
+  def order_list
+    filter(/^(\++)\s*(.*?)$/) do |md, st|
+      st[:order_lists] << md[2]
+      shift = (" " * 4) * (md[1].size-1)
+      "#{shift}1. #{md[2]}"
+    end
+  end
+  alias :ol :order_list
+  
+  def unorder_list
+    filter(/^(\-+)\s*(.*?)$/) do |md, st|
+      st[:unorder_lists] << md[2]
+      shift = (" " * 4) * (md[1].size-1)
+      "#{shift}- #{md[2]}"
+    end
+  end
+  alias :ul :unorder_list
+
+  def blockquote
+    filter(/^>>\n(.*?)^<<$/m) do |md|
+      "\n" + md[1].lines.map { |line| "> #{line}" }.join
+    end
+  end
+
+  def pre
+    filter(/^>\|\n(.*?)^\|<$/m) do |md|
+      "\n" + md[1].lines.map { |line| "    #{line}" }.join
+    end
+  end
+
+  def super_pre
+    filter(/^>\|(\w+)?\|/) do |md|
+      lang = md[1] || "bash"
+      "{% highlight #{lang} %}"
+    end
+
+    filter(/^\|\|</) { "{% endhighlight %}" }
+  end
+
+  def footnote
+    filter(/\(\((.*?)\)\)/) do |md, st|  
+      "{% fn_ref #{st[:footnotes].size+1} %}"
+      .tap { st[:footnotes] << "{% fn #{md[1]} %}" }
+    end
+  end
+
+  def br
+    filter("\n\n") { "\n" }
+  end
+
+  def link
+    url_r = URI.regexp(['http', 'https'])
+
+    filter(/(?:(?<=[ \(])|^)#{url_r}(?!\s%})(?:(?=[ \)])|$)/) do |md|
+      "[#{md}](#{md})"
+    end
+
+    filter(/\[(#{url_r})(?::title=?(.*?))\]/) do |md|
+      t = md.captures.last
+      title = t.empty? ? ((st = stocks[:titles]) ? st.first : 'link') : t
+      "[#{title}](#{md[1]})"
+    end
+  end
+
+  def hatebu
+    url_r = URI.regexp(['http', 'https'])
+    filter(/\[(#{url_r}):bookmark\]/) do |md|
+      "{% hatebu #{md[1]} %}"
+    end
+  end
+
+  def amazon
+    filter(/\[?(?:isbn|asin):(\w+)(?::(title|detail|image))?\]?/i) do |md|  
+      case md[2]
+      when 'title'
+        "{{ '#{md[1]}' | amazon_link }}"
+      when 'image'
+        "{{ '#{md[1]}' | amazon_medium_image }}"
+      when 'detail'
+        "{{ '#{md[1]}' | amazon_medium_image }}\n{{ '#{md[1]}' | amazon_link }} by {{ '#{md[1]}' | amazon_authors }}"
+      else
+        "{{ '#{md[1]}' | amazon_medium_image }}"
+      end
+    end
+  end
+
+  def youtube
+    filter(/[\(\[]?\s*https?:\/\/.*?youtube.*?\?v=([a-zA-Z0-9_-]+):movie\s*[\]\)]?/) do |md|
+      "{% youtube #{md[1]} %}"
+    end
+  end
+
+  def image
+    filter(/\[?f:id:(.*?):(\d+)(\w):image.*?\]?/) do |md|
+      m1, m2, m3 = md.captures
+      ft = %w(png jpg bmp gif).detect { |e| e[/^#{m3}/] }
+      host = "http://img.f.hatena.ne.jp/images/fotolife"
+      %{\n![image](#{host}/#{m1[0]}/#{m1}/#{m2[0,8]}/#{m2}.#{ft})\n}
+    end
+  end
+
+  def gist
+    host = %r{https?://gist.github.com/}
+    filter(/<script src=\"#{host}(\d+)\.js\?file=(.*?)\"><\/script>/) do |md|
+      "{% gist #{md[1]} #{md[2]} %}"
+    end
+  end
+end

data/lib/hateda2md/entry.rb

@@ -0,0 +1,5 @@
+# encoding: UTF-8
+
+class HateDa::Entry < Struct.new(:ent_date, :ent_body, :ent_mdbody, :ent_title)
+end
+  

data/lib/hateda2md/mdbuilder.rb

@@ -0,0 +1,105 @@
+# encoding: UTF-8
+require "nokogiri"
+class String
+  def ~
+    mergin = scan(/^ +/).map(&:size).min
+    gsub(/^ {#{mergin}}/, '')
+  end
+
+  def to_nil
+    self.empty? ? nil : self
+  end
+end
+
+class HateDa::MdBuilder
+  attr_reader :entries
+  def initialize(path)
+    @entries = build_entries(path)
+  end
+  
+  def build_entries(filepath)
+    xml = Nokogiri::XML(open filepath)
+    xml.search('day').map do |ent|
+      date = ent.attributes['date'].value
+      body = ent.css('body').text.strip
+      mdbody = nil
+      title = ent.attributes['title'].value
+      HateDa::Entry[date, body, mdbody, title]
+    end
+  end
+
+  def set(item, *args)
+    entries.each { |ent| ent.set item, *args }
+  end
+  
+  def filter(pattern, opt={}, &replace)
+    entries.each { |ent| ent.filter(pattern, opt, &replace) }
+  end
+
+  def pre_defined_filters(alias_flag=false)
+    HateDa::Converter.pre_defined_filters(alias_flag)
+  end
+  
+  def run(*range)
+    range = [0..-1] if range.empty?
+    entries[*range].map do |entry|
+      md = entry.to_md(entry.ent_body)
+      entry.ent_title = get_title(entry) if entry.ent_title.empty?
+      entry.ent_mdbody = md
+      entry
+    end
+  end
+
+  def save_to_files(dir='md', ext='md')
+    md_entries = entries.select { |ent| ent.ent_mdbody }
+    unless md_entries.empty?
+      Dir.mkdir(dir) unless Dir.exist?(dir)
+      md_entries.each do |ent|
+        path = "#{dir}/#{ent.ent_date}-#{title_for_file(ent.ent_title)}.#{ext}"
+        File.open(path, 'w') do |f|
+          f.puts header(ent.ent_title, ent.ent_date)
+          f.puts ent.ent_mdbody
+          f.puts footnotes(ent.stocks[:footnotes]) unless ent.stocks[:footnotes].empty?
+        end
+      end
+    end
+  rescue => e
+    print "class => #{e.class}\nmessage => #{e.message}\nbacktrace => #{e.backtrace}\n"
+  end
+
+  private
+  def get_title(entry)
+    entry.stocks[:titles].first || 'notitle'
+  end
+
+  def title_for_file(title)
+    title.scan(/\w+/).join('-').to_nil || 'notitle'
+  end
+
+  def header(title, date)
+    title = title.gsub(/['"`]/, '')
+    ~<<-EOS
+    ---
+    layout: post
+    title: "#{title}"
+    date: #{date}
+    comments: true
+    categories:
+    tags:
+    published: true
+    ---
+
+    EOS
+  end
+
+  def footnotes(fnotes)
+    notes = fnotes.map { |note| "#{note}" }.join("\n    ")
+    ~<<-EOS
+
+    {% footnotes %}
+    #{notes}
+    {% endfootnotes %}
+    EOS
+  end
+end
+

data/lib/hateda2md/version.rb

@@ -0,0 +1,3 @@
+module Hateda2md
+  VERSION = "0.0.1"
+end

data/lib/hateda2md.rb

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+# encoding: UTF-8
+module HateDa
+  require_relative 'hateda2md/entry'
+  require_relative 'hateda2md/mdbuilder'
+  require_relative 'hateda2md/converter'
+
+  Entry.send(:include, Converter)
+end
+

data/spec/hateda_converter_spec.rb

@@ -0,0 +1,369 @@
+# encoding: UTF-8
+
+require_relative "spec_helper"
+
+include HateDa::Converter
+
+describe HateDa::Converter do
+  context "pass a text to to_md method" do
+    before(:each) do
+      @hdtext = <<EOS
+*p1*title1
+content1
+content2
+**subtitle1
+content3
+content4
+**subtitle2
+contetn5
+*123*title2
+
+EOS
+    end
+    
+    after(:each) do
+      clear_filter
+    end
+    
+    it "should not change the text when filter is empty" do
+      hdtext = "*p1*title1\ncontent"
+      to_md(hdtext).should eql hdtext
+    end
+
+    it "should raise error when set non-defined tags" do
+      ->{ set(:hello) }.should raise_error(HateDa::Converter::NoFilterError)
+    end
+
+    context "header" do
+      it "change a header" do
+        hdtext = "*p1*title1\ncontent\n*p2*title2"
+        md     = "#title1\ncontent\n#title2"
+        set :header
+        to_md(hdtext).should eql md
+        stocks[:titles].should eql ['title1', 'title2']
+      end
+
+      it "change a header by h3" do
+        hdtext = "*p1*title1\ncontent\n*p2*title2\ncontent"
+        md     = "###title1\ncontent\n###title2\ncontent"
+        set :header, :h3
+        to_md(hdtext).should eql md
+      end
+
+      it "change several headers with :title(alias of :header)" do
+        hdtext = "*123*title1\ncontent1\n*p3*title2\ncontent2"
+        md     = "#title1\ncontent1\n#title2\ncontent2"
+        set :title
+        to_md(hdtext).should eql md
+        stocks[:titles].should eql ['title1', 'title2']
+      end
+
+      it "change a subheader" do
+        hdtext = "**subtitle1\ncontent**2"
+        md     = "##subtitle1\ncontent**2"
+        set :subheader
+        to_md(hdtext).should eql md
+      end
+
+      it "change subheaders with :subtitle(alias of :subheader)" do
+        hdtext = "**subtitle1\ncontent1\n**subtitle2\ncontent**2"
+        md     = "##subtitle1\ncontent1\n##subtitle2\ncontent**2"
+        set :subtitle
+        to_md(hdtext).should eql md
+      end
+
+      it "change a subsubheader" do
+        hdtext = "***subsubtitle1\ncontent***2"
+        md     = "###subsubtitle1\ncontent***2"
+        set :subsubheader
+        to_md(hdtext).should eql md
+      end
+
+      it "change mixed title cases1" do
+        hdtext = "*p1*title\n***sstitle\ncontent\n**stit***le\nconten**t\n***sstitle"
+        set :subheader
+        md = "*p1*title\n***sstitle\ncontent\n##stit***le\nconten**t\n***sstitle"
+        to_md(hdtext).should eql md
+      end
+
+      it "change mixed title cases2" do
+        hdtext = "*p1*title\n***sstitle\ncontent\n**stit***le\nconten**t\n***sstitle"
+        set :subsubtitle
+        md = "*p1*title\n###sstitle\ncontent\n**stit***le\nconten**t\n###sstitle"
+        to_md(hdtext).should eql md
+      end
+
+      it "change mixed title cases3" do
+        hdtext = "*p1*title\n***sstitle\ncontent\n**stit***le\n*p2*title2\nconten**t\n***sstitle"
+        set :title
+        set :subtitle
+        md = "#title\n***sstitle\ncontent\n##stit***le\n#title2\nconten**t\n***sstitle"
+        to_md(hdtext).should eql md
+      end
+
+      it "change mixed title cases4" do
+        hdtext = "*p1*title\n***sstitle1\ncontent\n**stit***le\nconten**t\n***sstitle2"
+        set :subtitle
+        set :subsubtitle
+        md = "*p1*title\n###sstitle1\ncontent\n##stit***le\nconten**t\n###sstitle2"
+        to_md(hdtext).should eql md
+      end
+    end
+    
+    context "list" do
+      it "change ordered list" do
+        hdtext = "+item1\n+item2\n+item3"
+        set :order_list
+        md     = "1. item1\n1. item2\n1. item3"
+        to_md(hdtext).should eql md
+      end
+
+      it "change nested ordered list" do
+        hdtext = <<EOS
++item1
+++item1-1
+++item1-2
++item2
++item3
+++item3-1
++++item3-1-1
++++item3-1-2
+++item3-2
+EOS
+        
+        md = <<EOS
+1. item1
+    1. item1-1
+    1. item1-2
+1. item2
+1. item3
+    1. item3-1
+        1. item3-1-1
+        1. item3-1-2
+    1. item3-2
+EOS
+        set :order_list
+        to_md(hdtext).should eql md
+      end
+
+      it "change unordered list" do
+        hdtext = "-item1\n-item2\n-item3"
+        set :unorder_list
+        md     = "- item1\n- item2\n- item3"
+        to_md(hdtext).should eql md
+      end
+
+      it "change nested unordered list" do
+        hdtext = <<EOS
+-item1
+--item1-1
+--item1-2
+-item2
+-item3
+--item3-1
+---item3-1-1
+---item3-1-2
+--item3-2
+EOS
+
+        md = <<EOS
+- item1
+    - item1-1
+    - item1-2
+- item2
+- item3
+    - item3-1
+        - item3-1-1
+        - item3-1-2
+    - item3-2
+EOS
+        set :unorder_list
+        to_md(hdtext).should eql md
+      end
+
+
+    end
+
+    context "pre" do
+      it "change blockquote '>> <<' to '>'" do
+        hdtext = <<EOS
+>>
+blockquoted
+blockquoted
+blockquoted
+<<
+EOS
+      md = <<EOS
+
+> blockquoted
+> blockquoted
+> blockquoted
+
+EOS
+        set :blockquote
+        to_md(hdtext).should eql md
+      end
+
+      it "change pre '>|' to 4 spaces" do
+        hdtext = <<EOS
+>|
+blockquoted
+blockquoted
+blockquoted
+|<
+EOS
+      md = <<EOS
+
+    blockquoted
+    blockquoted
+    blockquoted
+
+EOS
+        set :pre
+        to_md(hdtext).should eql md
+      end
+
+      it "change super_pre '>|type|' to highlight tag" do
+        hdtext = <<EOS
+>|ruby|
+def hello(name)
+  "hello, \#{name}!"
+end
+||<
+EOS
+      md = <<EOS
+{% highlight ruby %}
+def hello(name)
+  "hello, \#{name}!"
+end
+{% endhighlight %}
+EOS
+        set :super_pre
+        to_md(hdtext).should eql md
+      end
+    end
+
+    context "footnote" do
+      it "change '(())' to footnote tag" do
+        hdtext = "sentence((aaa)), sentence\nsentence((bbb))"
+        md     = "sentence{% fn_ref 1 %}, sentence\nsentence{% fn_ref 2 %}"
+        set :footnote
+        to_md(hdtext).should eql md
+        stocks[:footnotes].should eql ["{% fn aaa %}", "{% fn bbb %}"]
+      end
+    end
+
+    context "br" do
+      it "change '\n\n' to <br/>" do
+        hdtext = "content\n\ncontent\ncontent\n\ncontent"
+        md     = "content\ncontent\ncontent\ncontent"
+        set :br
+        to_md(hdtext).should eql md
+      end
+    end
+
+    context "link" do
+      it "change a url to a link" do
+        hdtext = <<EOS
+sentence
+http://www.abc.com
+sentence http://www.efg.com/123_456 sentence
+sentence(https://www.xyz.co.jp),sen..
+EOS
+        md     = <<EOS
+sentence
+[http://www.abc.com](http://www.abc.com)
+sentence [http://www.efg.com/123_456](http://www.efg.com/123_456) sentence
+sentence([https://www.xyz.co.jp](https://www.xyz.co.jp)),sen..
+EOS
+        set :link
+        to_md(hdtext).should eql md
+      end
+
+      it "change a url with title to a link" do
+        hdtext = <<EOS
+*p1*Title X
+sentence
+[http://www.abc.com/:title]
+sentence [http://www.efg.com/123_456:title=Title1] sentence
+*p3*Title Y
+sentence([https://www.xyz.co.jp/:title=Title no.2]),sen..
+http://mmm.ff.co.jp/
+EOS
+        md     = <<EOS
+#Title X
+sentence
+[Title X](http://www.abc.com/)
+sentence [Title1](http://www.efg.com/123_456) sentence
+#Title Y
+sentence([Title no.2](https://www.xyz.co.jp/)),sen..
+[http://mmm.ff.co.jp/](http://mmm.ff.co.jp/)
+EOS
+        set :title
+        set :link
+        to_md(hdtext).should eql md
+      end
+    end
+  
+    context "amazon" do
+      it "change amazon detail link to amazon tag" do
+        hdtext = "[asin:4797356014:detail]"
+        md     = "{{ '4797356014' | amazon_medium_image }}\n{{ '4797356014' | amazon_link }} by {{ '4797356014' | amazon_authors }}"
+        set :amazon
+        to_md(hdtext).should eql md
+      end
+
+      it "change amazon image link to amazon tag" do
+        hdtext = "[asin:4797356014:image]"
+        md     = "{{ '4797356014' | amazon_medium_image }}"
+        set :amazon
+        to_md(hdtext).should eql md
+      end
+    end
+  
+    context "youtube" do
+      it "change youtube link to youtube tag" do
+        hdtext = "[http://www.youtube.com/watch?v=oDSigzI6YKw:movie]"
+        md     = "{% youtube oDSigzI6YKw %}"
+        set :youtube
+        to_md(hdtext).should eql md
+      end
+    end
+
+    context "fotolife" do
+      it "change fotolife link to image tag" do
+        hdtext = "[f:id:keyesberry:20110209105103p:image]"
+        md     = "\n![image](http://img.f.hatena.ne.jp/images/fotolife/k/keyesberry/20110209/20110209105103.png)\n"
+        set :image
+        to_md(hdtext).should eql md
+      end
+    end
+
+    context "gist" do
+      it "change gist link to gist tag" do
+        hdtext = %{<script src="https://gist.github.com/2177656.js?file=gsub_filter.rb"></script>}
+        md     = "{% gist 2177656 gsub_filter.rb %}"
+        set :gist
+        to_md(hdtext).should eql md
+      end
+    end
+
+    context "hatebu" do
+      it "change hatena bookmark link to gist tag" do
+        hdtext = %{[http://d.hatena.ne.jp/keyesberry/20090318/p1:bookmark]}
+        md     = "{% hatebu http://d.hatena.ne.jp/keyesberry/20090318/p1 %}"
+        set :hatebu
+        to_md(hdtext).should eql md
+      end
+
+      it "change mixed case for hatebu link and regular link" do
+        hdtext = %{[http://d.hatena.ne.jp/keyesberry/20090318/p1:title='hello'][http://d.hatena.ne.jp/keyesberry/20090318/p1:bookmark]}
+        md     = "['hello'](http://d.hatena.ne.jp/keyesberry/20090318/p1){% hatebu http://d.hatena.ne.jp/keyesberry/20090318/p1 %}"
+        set :hatebu
+        set :link
+        to_md(hdtext).should eql md
+      end
+    end
+  end
+end
+

data/spec/hateda_entry_spec.rb

@@ -0,0 +1,34 @@
+# encoding: UTF-8
+require_relative 'spec_helper'
+
+describe HateDa::Entry do
+  context "when created" do
+    context "without argument" do
+      before(:each) do
+        @entry = HateDa::Entry.new
+      end
+
+      it "should have ent_date, ent_title, ent_body, ent_mdbody property" do
+        ->{ @entry.ent_date }.should_not raise_error
+        ->{ @entry.ent_title }.should_not raise_error
+        ->{ @entry.ent_body }.should_not raise_error
+        ->{ @entry.ent_mdbody }.should_not raise_error
+      end
+    end
+
+    context "with data" do
+      before(:each) do
+        @date, @body, @mdbody, @title = '2012-04-21', "hello\nfriend!", "", "hello"
+        @entry = HateDa::Entry.new(@date, @body, @mdbody, @title)
+      end
+
+      it "should return data" do
+        @entry.ent_date.should eql @date
+        @entry.ent_body.should eql @body
+        @entry.ent_mdbody.should eql @mdbody
+        @entry.ent_title.should eql @title
+      end
+    end
+  end
+end
+

data/spec/hateda_mdbuilder_spec.rb

@@ -0,0 +1,111 @@
+# encoding: UTF-8
+require_relative "spec_helper"
+require "fileutils"
+
+describe HateDa::MdBuilder do
+  before(:each) do
+    @mdb = HateDa::MdBuilder.new('spec/test1.xml')
+  end
+
+  context "when initialized with a sample xml" do
+    it "create entries property" do
+      ->{ @mdb.entries }.should_not raise_error
+    end
+
+    it "create entries which are Entry classes" do
+      @mdb.entries.each { |entry| entry.class.should eql HateDa::Entry }
+    end
+
+    it "set date, body, mdbody, titlefor each entry" do
+      body = "*p1*Title\nline1\nline2\nline3\n**SubTitle\nline4"
+      a_entry = @mdb.entries.first
+      a_entry.ent_date.should eql '2012-03-01'
+      a_entry.ent_body.should eql body
+      a_entry.ent_mdbody.should eql nil
+      a_entry.ent_title.should eql 'hello'
+    end
+  end
+
+  context "when run for building markdown data for each entry" do
+    it "set original body to mdbody of entry with no filter" do
+      @mdb.run
+      a_entry = @mdb.entries.first
+      a_entry.ent_mdbody.should eql a_entry.ent_body
+    end
+
+    it "set markdowned body to mdbody of entry" do
+      md = "\nline1\nline2\nline3\n##SubTitle\nline4"
+      a_entry = @mdb.entries.first
+      a_entry.set :title
+      a_entry.set :subtitle
+      @mdb.run
+      a_entry.ent_mdbody.should eql md
+    end
+
+    it "set title of entry when it is empty" do
+      body = "*p1*Title1\nline1\nline2\nline3\n\n*p2*Title2\nline4\nline5"
+      a_entry, b_entry = @mdb.entries.take(2)
+      a_entry.set :title
+      b_entry.set :title
+      @mdb.run
+      a_entry.ent_title.should eql 'hello'
+      b_entry.ent_title.should eql 'Title1'
+    end
+  end
+
+  context "set filter to all entries at once" do
+    before(:each) do
+      @mdb2 = HateDa::MdBuilder.new('spec/test2.xml')
+    end
+
+    it "set title with set method" do
+      md1 = "\nline1\nline2\nline3\n**SubTitle\nline4"
+      md2 = "#Title1\nline1\nline2\nline3\n\n#Title2\nline4\nline5"
+      @mdb2.set :title
+      @mdb2.run
+      entries = @mdb2.entries.zip([md1, md2])
+      entries.each do |ent, md|
+        ent.ent_mdbody.should eql md
+      end
+    end
+
+    it "set title & subtitle with filter method" do
+      md1 = "#Title\nline1\nline2\nline3\n##SubTitle\nline4"
+      md2 = "#Title1\nline1\nline2\nline3\n\n#Title2\nline4\nline5"
+      @mdb2.filter(/\*p?\d+\*(.*)$/) do |md, st|
+        st[:titles] << md[1]
+        "##{md[1]}"
+      end
+      @mdb2.filter(/^\*\*((?!\*).*)$/) do |md, st|
+        st[:subtitles] << md[1]
+        "###{md[1]}"
+      end
+      @mdb2.run
+      entries = @mdb2.entries.zip([md1, md2])
+      entries.each do |ent, md|
+        ent.ent_mdbody.should eql md
+      end
+    end
+  end
+
+  context "run option" do
+    it "run for top 2 entries" do
+      nilness = [false, false, true, true]
+      @mdb.run(0,2)
+      @mdb.entries.take(4).map { |ent| ent.ent_mdbody.nil? }.should eql nilness
+    end
+  end
+
+  context "save md data to files" do
+    it "save md to separate files" do
+      files = Dir['md/*']
+      FileUtils.rm(Dir['md/*']) unless files.empty?
+      num = 5
+      filters = @mdb.pre_defined_filters
+      filters.each { |f| @mdb.set f }
+      @mdb.run(0...num)
+      @mdb.save_to_files
+      Dir['md/*'].size.should eql num
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,4 @@
+$:.unshift File.join(File.dirname(__FILE__), '..', 'lib')
+
+require "rspec"
+require "hateda2md"

data/spec/test1.xml

@@ -0,0 +1,127 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<diary>
+<day date="2012-03-01" title="hello">
+<body>
+*p1*Title
+line1
+line2
+line3
+**SubTitle
+line4
+
+</body>
+</day>
+<day date="2012-04-01" title="">
+<body>
+*p1*Title1
+line1
+line2
+line3
+
+*p2*Title2
+line4
+line5
+
+*123*タイトル3
+ライン１
+ライン２
+ライン３
+</body>
+</day>
+<day date="2012-04-04" title="">
+<body>
+*1135046820*Title1
+
+content
+**SubTitle1
+line1
+line2
+**SubTitle2
+line3
++list1
++list2
+++list2-1
+++list2-2
+
+***SubSubTitle
+line4
+-list1
+-list2
+-list3
+
+http://arena.nikkeibp.co.jp/rev/20051124/114391/index.shtml
+
+asin:B000BGEAR2:image:small
+asin:B000BGEAR2:title
+
+[http://local.google.co.jp/maps?q=%E6%98%AD%E6%96%87%E7%A4%BE&amp;near=%E5%8D%83%E4%BB%A3%E7%94%B0%E5%8C%BA%E9%BA%B9%E7%94%BA%EF%BC%93&amp;btnG=%E6%A4%9C%E7%B4%A2&amp;sll=36.562600,136.362305&amp;sspn=23.257402,31.684570&amp;t=&amp;hl=ja&amp;cid=35684108,139738742,6343705222926448571&amp;li=lmd&amp;z=0:title]
+Google local
+
+
+[http://earth.google.com/:title]
+
+</body>
+</day>
+<day date="2012-05-16" title="">
+<body>
+*p1*RubyでText Dollarを解く-CodeEval
+なんか想像以上に手こずったよ^^;
+case式内が見苦しい..
+もっと簡単なやり方あるんだろうな
+Integer#dollarizeを定義してみた
+
+
+数字を英語のドル表記に変換
+&lt;script src=&quot;https://gist.github.com/1697463.js?file=print_check.rb&quot;&gt;&lt;/script&gt;
+
+</body>
+</day>
+<day date="2012-05-18" title="">
+<body>
+*p1*RubyでLevenshtein Distanceを解く-CodeEval
+できません..
+アルゴリズム的にはできてるんだけど(('causes'の解答が一致した))
+答えを得るのに1時間とかorz..
+5秒で答えなきゃいけないのに
+あとグローバル変数を使ってしまった
+
+
+どうも高速化は苦手です
+そこに注力する気がなかなか起きない..
+
+[http://d.hatena.ne.jp/keyesberry/20120211/p1:title=RubyのEnumerable#mapをもっと便利にしたいよ - hp12c]
+
+&gt;|ruby|
+module Enumerable
+  def mapp(op=nil, *args, &amp;blk)
+    op ? map { |e| op.intern.to_proc[e, *args]} : map(&amp;blk)
+  end
+end
+
+langs = [&quot;Ruby&quot;, &quot;Python&quot;, &quot;Lisp&quot;, &quot;Haskell&quot;]
+langs.mapp(:+, 'ist') # =&gt; [&quot;Rubyist&quot;, &quot;Pythonist&quot;, &quot;Lispist&quot;, &quot;Haskellist&quot;]
+
+[1, 2, 3].mapp(:+, 10) # =&gt; [11, 12, 13]
+
+(1..5).mapp(:**, 2) # =&gt; [1, 4, 9, 16, 25]
+
+[[1,2,3,4], [5,6,7,8], [9,10,11,12]].mapp(:last, 2) # =&gt; [[3, 4], [7, 8], [11, 12]]
+
+[&quot;ruby&quot;, &quot;python&quot;, &quot;lisp&quot;, &quot;haskell&quot;].mapp(:[], -2, 2) # =&gt; [&quot;by&quot;, &quot;on&quot;, &quot;sp&quot;, &quot;ll&quot;]
+||&lt;
+
+レーベンシュタイン距離が1の語同士をfriendとして
+与えられた辞書におけるhelloの語から始まる
+friendの輪に含まれるすべての語の数を答える
+&lt;script src=&quot;https://gist.github.com/1697463.js?file=levenshtein_distance.rb&quot;&gt;&lt;/script&gt;
+
+&gt;&gt;
+それはここまで来たらもうmappは
+要らないんじゃないかってことなんだ
+&lt;&lt;
+</body>
+</day>
+
+
+
+</diary>

data/spec/test2.xml

@@ -0,0 +1,25 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<diary>
+<day date="2012-03-01" title="hello">
+<body>
+*p1*Title
+line1
+line2
+line3
+**SubTitle
+line4
+
+</body>
+</day>
+<day date="2012-04-01" title="">
+<body>
+*p1*Title1
+line1
+line2
+line3
+
+*p2*Title2
+line4
+line5
+</body>
+</day>

metadata

@@ -0,0 +1,106 @@
+--- !ruby/object:Gem::Specification
+name: hateda2md
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- kyoendo
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-05-04 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: &2153771040 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *2153771040
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: &2153770580 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2153770580
+- !ruby/object:Gem::Dependency
+  name: gsub_filter
+  requirement: &2153770160 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2153770160
+description: Convert Hatena-Diary XML file to Markdown files for Jekyll
+email:
+- postagie@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .DS_Store
+- .gitignore
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- example/example.rb
+- hateda2md.gemspec
+- lib/hateda2md.rb
+- lib/hateda2md/converter.rb
+- lib/hateda2md/entry.rb
+- lib/hateda2md/mdbuilder.rb
+- lib/hateda2md/version.rb
+- spec/hateda_converter_spec.rb
+- spec/hateda_entry_spec.rb
+- spec/hateda_mdbuilder_spec.rb
+- spec/spec_helper.rb
+- spec/test1.xml
+- spec/test2.xml
+homepage: https://github.com/melborne/hateda2md
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: 1.9.2
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.11
+signing_key: 
+specification_version: 3
+summary: This is a converter that build separated markdown files using for Jekyll
+  from a Hatena-Diary XML file, which written with Hatena notations. You can set several
+  pre-defined filters or can define your original filters.
+test_files:
+- spec/hateda_converter_spec.rb
+- spec/hateda_entry_spec.rb
+- spec/hateda_mdbuilder_spec.rb
+- spec/spec_helper.rb
+- spec/test1.xml
+- spec/test2.xml
+has_rdoc: