rseg1.9 0.1.5

data/.gitignore

@@ -0,0 +1,4 @@
+test
+pkg
+.DS_Store
+*.gem

data/LICENSE

@@ -0,0 +1,30 @@
+Rseg includes two built-in dictionaries:
+
+* CC-CEDICT (http://cc-cedict.org/wiki/): Creative Commons Attribution-Share Alike 3.0 License (http://creativecommons.org/licenses/by-sa/3.0/)
+* Wikipedia Chinese article title list (http://download.wikimedia.org/zhwiki/): Creative Commons Attribution-Share Alike 3.0 License （http://creativecommons.org/licenses/by-sa/3.0/)
+
+The codes and others in Rseg are licensed under MIT license:
+
+===============================
+Copyright (c) 2009 Yuanyi Zhang
+
+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

@@ -0,0 +1,57 @@
+Introduction
+========
+Rseg is a Chinese Word Segmentation(中文分词) routine in pure Ruby.
+
+The algorithm is based on this article: http://xiecc.blog.163.com/blog/static/14032200671110224190/
+
+Usage
+========
+
+Rseg now support two modes: inline and C/S mode.
+
+1. Inline mode
+
+> require 'rubygems'
+> require 'rseg'
+> Rseg.segment("需要分词的文章")
+['需要', '分词', '的', '文章']
+
+The first call to Rseg#segment will need about 30 seconds to load the dictionary, the second call will be very fast, you can also call Rseg#load to load dictionaries manually.
+
+2. C/S mode
+
+$ rseg_server
+== Sinatra/0.9.4 has taken the stage on 4100
+
+This will start rseg server on http://localhost:4100
+
+You can visit it via your browser or the rseg command.
+
+$ rseg '需要分词的文章'
+需要 分词 的 文章
+
+You can also access server with the Rseg#remote_segment
+
+$ irb
+> require 'rubygems'
+> require 'rseg'
+> Rseg.remote_segment("需要分词的文章") # This will be very fast
+['需要', '分词', '的', '文章']
+
+Performance
+========
+About 5M character/s on my Macbook (Intel Core 2 Duo 2GHz/4G mem). 
+
+License
+========
+
+Rseg includes two built-in dictionaries:
+
+* CC-CEDICT (http://cc-cedict.org/wiki/) with Creative Commons Attribution-Share Alike 3.0 License (http://creativecommons.org/licenses/by-sa/3.0/)
+* Wikipedia Chinese article title list (http://download.wikimedia.org/zhwiki/) with Creative Commons Attribution-Share Alike 3.0 License（http://creativecommons.org/licenses/by-sa/3.0/)
+
+The codes and others in Rseg are licensed under MIT license.
+
+Feedback
+========
+All feedback are welcome, Yuanyi Zhang(zhangyuanyi#gmail.com)

data/Rakefile

@@ -0,0 +1,21 @@
+require 'rake'
+require 'rake/testtask'
+require 'rcov/rcovtask'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |s|
+    s.name = "rseg"
+    s.executables = ["rseg", 'rseg_server']
+    s.summary = "A Chinese Word Segmentation(中文分词) routine in pure Ruby"
+    s.email = "zhangyuanyi@gmail.com"
+    s.homepage = "http://github.com/yzhang/rseg"
+    s.description = "A Chinese Word Segmentation(中文分词) routine in pure Ruby"
+    s.authors = ["Yuanyi Zhang"]
+    s.files =  FileList["[A-Z]*", "{bin,lib,public,views}/**/*", '.gitignore', 'dict/dict.hash']
+    s.add_dependency 'haml'
+    s.add_dependency 'sinatra'
+  end
+rescue LoadError
+  puts "Jeweler, or one of its dependencies, is not available. Install it with: sudo gem install technicalpickles-jeweler -s http://gems.github.com"
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.7

data/bin/rseg

@@ -0,0 +1,11 @@
+#!/usr/bin/env ruby
+require File.join(File.dirname(__FILE__), '/../lib/rseg')
+
+input = ARGV[0]
+
+if input.nil? || input == ''
+  puts "Usage: rseg <text>"
+  exit
+end
+
+puts Rseg.remote_segment(input).join(' ')

data/bin/rseg_server

@@ -0,0 +1,16 @@
+#!/usr/bin/env ruby
+$:.unshift File.expand_path(File.dirname(__FILE__))
+
+require 'rubygems'
+require 'haml'
+
+require File.join(File.dirname(__FILE__), '/../lib/rseg')
+require File.join(File.dirname(__FILE__), '/../lib/app')
+
+puts "Loading dictionaries, this will take about 30 seconds."
+puts "Please wait a moment..."
+Rseg.load
+puts "Dictionaries loaded."
+
+App.run! :host => '127.0.0.1', :port => 4100, :environment => 'production'
+exit

data/lib/app.rb

@@ -0,0 +1,22 @@
+require 'sinatra/base'
+
+class App < Sinatra::Base
+  set :root,   File.dirname(__FILE__) + "/.."
+  set :app_file, __FILE__
+
+  get '/' do
+    haml :index
+  end
+
+  post '/segment' do
+    @input = params[:input]
+    @result = Rseg.segment(@input).join(' ')
+    haml :index
+  end
+
+  post '/seg' do
+    @input = params[:input]
+    @result = Rseg.segment(@input)
+    @result.join(' ')
+  end
+end

data/lib/builder/dict.rb

@@ -0,0 +1,42 @@
+#coding: utf-8
+$KCODE = 'UTF8'
+
+def process(path, tree)
+  File.open(path, 'r') do |file|
+    file.each_line do |line|
+      node = nil
+      line.chars.each do |c|
+        next if c == "\n" || c == "\r"
+        if node
+          node[c] ||= {}
+          node = node[c]
+        else
+          tree[c] ||= Hash.new
+          node = tree[c]
+        end
+      end
+      node[:end] = true
+    end
+  end
+end
+
+def build
+  tree = {}
+  dictionaries = ['cedict.zh_CN.utf8', 'wikipedia.zh.utf8']
+  
+  dictionaries.each do |dictionary|
+    puts "Processing #{dictionary}..."
+    path = File.join(File.dirname(__FILE__), '../../dict', dictionary)
+    process(path, tree)
+  end
+  
+  File.open(hash_path, "wb") {|io| Marshal.dump(tree, io)}  
+  puts 'Done'
+end
+
+def hash_path
+  File.join(File.dirname(__FILE__), '../../dict/dict.hash')
+end
+
+build
+

data/lib/engines/dict.rb

@@ -0,0 +1,51 @@
+module RsegEngine
+  class Dict < Engine
+    @@root      = nil
+    @@dict_path = File.join(File.dirname(__FILE__), '../../dict/dict.hash')
+
+    class << self
+      def dict_path=(path)
+        @@dict_path = path
+      end
+    
+      def dict_path
+        @@dict_path
+      end
+    end
+  
+    def initialize
+      @@root ||= load_dict(@@dict_path)
+      @word = ''
+      @node = @@root
+      super
+    end
+  
+    def process(char)
+      match = false
+      word = nil
+    
+      if @node[char]
+        @word << char
+        @node = @node[char]
+        match = true
+      else
+        if @node[:end] || @word.chars.to_a.length == 1
+          word = @word
+        else
+          word = @word.chars.to_a
+        end
+      
+        @node = @@root
+        @word = ''
+        match = false
+      end
+    
+      [match, word]
+    end
+  
+    private
+    def load_dict(path)
+      File.open(path, "rb") {|io| Marshal.load(io)}
+    end
+  end
+end

data/lib/engines/engine.rb

@@ -0,0 +1,19 @@
+module RsegEngine
+  class Engine
+    def initialize
+      @running = true
+    end
+  
+    def stop
+      @running = false
+    end
+  
+    def run
+      @running = true
+    end
+  
+    def running?
+      @running
+    end
+  end
+end

data/lib/engines/english.rb

@@ -0,0 +1,26 @@
+module RsegEngine
+  LETTER_SYMBOLS = ('a'..'z').to_a + ('A'..'Z').to_a
+
+  class English < Engine
+    def initialize
+      @word = ''
+      super
+    end
+  
+    def process(char)
+      match = false
+      word = nil
+    
+      if LETTER_SYMBOLS.include?(char)
+        @word << char
+        match = true
+      else
+        word = @word
+        @word = ''
+        match = false
+      end
+    
+      [match, word]
+    end  
+  end
+end

data/lib/engines/name.rb

@@ -0,0 +1,52 @@
+#coding: utf-8
+module RsegEngine
+  class Name < Engine
+    @@last_names = %W(丁 卜 刁 七 弓 干 于 王 尤 孔 方 申 白 甘 田 包 石 左 平 司 皮 史 池 艾 年 匡 充 江 印
+                    促 伊 伍 安 任 米 促 牟 向 吉 成 伏 吕 李 吴 沈 何 贝 狄 祁 杜 汪 阮 邢 汲 别 辛 冷 利 沃 谷
+                    扶 步 那 沙 周 金 吕 花 孟 和 邵 房 抗 灰 明 屈 松 牧 宓 武 幸 卓 易 尚 邰 空 竺 岳 东 林 
+                    施 姜 俞 查 封 秋 帅 祖 羿 柯 茅 柳 姚 纪 宣 咸 库 侯 洪 胡 哈 宣 郁 祝 苗 禹 娄 
+                    秦 奚 倪 度 凌 宰 宦 师 徐 翁 班 马 时 晃 乌 夏 贡 柴 能 家 宫 敖 索 晏 桑 高 凌 桂 容 姬 劳 桑 桂 袁 时 祝 席 徐 高 夏 凌 洪 翁 家 芮 乌 祖 索 贡 
+                    许 张 曹 戚 梅 屠 盛 崖 章 鱼 国 商 扈 寇 终 冯 苗 康 常 茅 闵 麻 胡 崔 邢 条 符 宿 堵 浦 习 鱼 
+                    梁 富 曾 程 项 钮 舒 彭 费 童 云 喻 嵇 范 费 贺 毕 付 黄 邵 祁 阮 强 童 邱 解 贲 单 富 钮 荀 惠 邴 焦 班 甯 钭 景 邰 劳 茹 寇 荆 
+                    莫 际 景 须 杨 詹 郎 雷 贾 路 骆 虞 经 裘 郁 滑 甄 靳 詹 闻 逄 雍 訾 郎 农 路 骆 虞 经 裘 郁 滑 靳 闻 逄 雍 
+                    赵 黄 褚 凤 郝 齐 臧 熊 管 裴 荣 郗 韶 郜 黎 翟 寿 通 
+                    卫 葛 鲁 乐 谈 董 樊 万 诸 刘 叶 都 满 广 殴 巩 养 
+                    郭 钱 陈 陶 鲍 穆 郭 堆 卢 陆 龙 噪 鄂 阴 苍 燕 冀 衡 融 蒯 逯 
+                    蒋 魏 谢 邹 潘 滕 邬 戴 钟 蔡 缪 应 储 糜 隗 历 蒲 慕 蔚 隆 鞠 关
+                    韩 萧 颜 庞 麦 双 璩 濮 聂 丰 看 
+                    郑 严 蓟 薄 谭 罗 买 蓝 蓬 怀 党 饶 顾 苏 龚 边 栾 权) #:nodoc:
+                  
+    @@first_names = %W(文 铭 菁 郁 怡 智 德 祥 志 华 孟 庆 雅 佩 晓 蓉 明 仁 宇 青 慧 豪 琪 安
+                     惠 宗 信 盈 君 秀 敏 伶 佳 国 荣 忠 宏 育 丽 圣 淑 彦 龙 冠 后 静 娟 子
+                     嘉 瑞 柏 弘 芳 正 玮 贞 如 凯 元 士 伟 杰 颍 霖 玲 仪 珮 英 建 政 真 珍
+                     美 世 立 秋 婷 贤 瑜 中 玉 维 莹 翔 家 芬 昌 裕 雯 萍 永 成 宜 鸿 珊 民
+                     欣 哲 良 伦 燕 梦 磊 丹 元 一 昌 红 健) #:nodoc:
+    def initialize
+      @word = ''
+      @last = false
+      super
+    end
+  
+    def process(char)
+      match = false
+      word = nil
+    
+      if !@last && @@last_names.include?(char)
+          @word << char
+          match = true
+          @last = true
+      elsif @last && @word.chars.to_a.length < 3 && @@first_names.include?(char)
+          @word << char
+          match = true
+          @unit = true
+      else
+        word = @word
+        @word = ''
+        @last = false
+        match = false
+      end
+
+      [match, word]
+    end
+  end
+end

data/lib/engines/number.rb

@@ -0,0 +1,62 @@
+#coding: utf-8
+module RsegEngine
+  class Number < Engine
+    @@number_symbols  = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 
+                      '一', '二', '三', '四', '五', '六', '七', '八', '九', '十', 
+                      '零', '〇', '百', '千', '壹', '贰', '叁', '肆', '柒', '捌',
+                      '玖', '拾', '之', '%', '¥', '分', '$', '.', '点', '第', '每']
+    @@subunit_symbols = ['多', '公', '英', '厘', '毫', '微', '纳', '海', '平', '立', 
+                       '方', '摄', '华', '氏', '美', '日', '澳', '港', '台', '新',
+                       '个', '百', '佰', '千', '仟', '万', '萬', '亿', '兆', '吉']
+    @@unit_symbols    = ['刻', '章', '回', '节', '名', '个', '届', '次', '集', '元', 
+                       '角', '例', '人', '斤', '克', '吨', '米', '里', '升', '码',
+                       '尺', '寸', '杆', '顷', '亩', '磅', '镑', '桶', '度', '秒',
+                       '分', '卡', '焦', '瓦', '匹', '圆', '币', '年', '月', '日', 
+                       '时', '秒', '点', '百', '佰', '仟', '千', '万', '萬', '亿', 
+                       '兆', '吉', '块', '半', '岁', '家', '所', '期', '场', '投',
+                       '中', '辆', '只', '头']
+
+    def initialize
+      @word = ''
+      @number = ''
+      @unit = false
+      @subunit = false
+      super
+    end
+  
+    def process(char)
+      match = false
+      word = nil
+    
+      if (!@subunit || @unit) && @@number_symbols.include?(char)
+        @number << char
+        match = true
+        @unit = false
+        @subunit = false
+      elsif (@number != '' || @unit) && @@subunit_symbols.include?(char)
+        @number << char
+        match = true
+        @subunit = true
+      end
+    
+      if (@number != '' || @subunit) && @@unit_symbols.include?(char)
+        @word << @number
+        @word << char if !match
+        @number = ''
+        @unit = true
+        match = true
+      end
+    
+      if !match
+        word = (@word != '') ? @word : @number
+        @word = ''
+        @number = ''
+        match = false
+        @unit = false
+        @subunit = false
+      end
+    
+      [match, word]
+    end
+  end
+end

data/lib/filters/conjunction.rb

@@ -0,0 +1,10 @@
+#coding: utf-8
+module RsegFilter
+  class Conjunction
+    @@conjunctions = %W(给 的 说 对 在 和 是 被 最 所 那 由 这 有 将 你 会 与 他 为 不 没 很 了 啊 哦 呵 把 去 从)
+
+    def self.filter(char)
+      @@conjunctions.include?(char) ? :conjunction : char
+    end
+  end
+end

data/lib/filters/fullwidth.rb

@@ -0,0 +1,20 @@
+#coding: utf-8
+module RsegFilter
+  class Fullwidth
+    @@fullwidth_chars = {'１' => '1', '２' => '2', '３' => '3', '４' => '4', '５' => '5', '６' => '6', '７' => '7', '８' => '8',
+                       '９' => '9', '０' => '0', 'ａ' => 'a', 'ｂ' => 'b', 'ｃ' => 'c', 'ｄ' => 'd', 'ｅ' => 'e', 'ｆ' => 'f',
+                       'ｇ' => 'g', 'ｈ' => 'h', 'ｉ' => 'i', 'ｊ' => 'j', 'ｋ' => 'k', 'ｌ' => 'l', 'ｍ' => 'm', 'ｎ' => 'n',
+                       'ｏ' => 'o', 'ｐ' => 'p', 'ｑ' => 'q', 'ｒ' => 'r', 'ｓ' => 's', 'ｔ' => 't', 'ｕ' => 'u', 'ｖ' => 'v',
+                       'ｗ' => 'w', 'ｘ' => 'x', 'ｙ' => 'y', 'ｚ' => 'z', 'Ａ' => 'A', 'Ｂ' => 'B', 'Ｃ' => 'C', 'Ｄ' => 'D',
+                       'Ｅ' => 'E', 'Ｆ' => 'F', 'Ｇ' => 'G', 'Ｈ' => 'H', 'Ｉ' => 'I', 'Ｊ' => 'J', 'Ｋ' => 'K', 'Ｌ' => 'L',
+                       'Ｍ' => 'M', 'Ｎ' => 'N', 'Ｏ' => 'O', 'Ｐ' => 'P', 'Ｑ' => 'Q', 'Ｒ' => 'R', 'Ｓ' => 'S', 'Ｔ' => 'T', 
+                       'Ｕ' => 'U', 'Ｖ' => 'V', 'Ｗ' => 'W', 'Ｘ' => 'X', 'Ｙ' => 'Y', 'Ｚ' => 'Z', '－' => '-', '＋' => '+',
+                       '—' => '-', '，' => ',', '／' => '/', '·' => '.'}
+                     
+    class << self
+      def filter(char)
+        @@fullwidth_chars[char].nil? ? char : @@fullwidth_chars[char]
+      end
+    end
+  end
+end

data/lib/filters/symbol.rb

@@ -0,0 +1,15 @@
+#coding: utf-8
+module RsegFilter
+  class Symbol
+    @@separators = ['｀', '［', '］', '、', '＝', '‘', '；', '。', '｜', '？', '》', 
+                  '《', '：', '“', '｛', '｝', '）', '（', '＊', '…', '＃', '！',
+                  '～', '’', '”', '〕', '〈', '〉', '「', '」', '『', '』', '〖', '〗', 
+                  '【', '】', '＜', '＞', '`', '~', '!', '@', '#', '^', 
+                  '&', '*', '\\', '(', ')', '=', '{', '}', '[', ']', 
+                  '|', ';', ':', "'", '<', '>', '?', "\n", "\t", "\r", 
+                  ' ', '-', '/', '+', ',', '　']
+    def self.filter(char)
+      @@separators.include?(char) ? :symbol : char
+    end
+  end
+end

data/lib/rseg.rb

@@ -0,0 +1,139 @@
+#coding: utf-8
+$KCODE = 'UTF8'
+
+require 'singleton'
+require 'net/http'
+
+require File.join(File.dirname(__FILE__), 'engines/engine')
+require File.join(File.dirname(__FILE__), 'engines/dict')
+require File.join(File.dirname(__FILE__), 'engines/english')
+require File.join(File.dirname(__FILE__), 'engines/number')
+require File.join(File.dirname(__FILE__), 'engines/name')
+
+require File.join(File.dirname(__FILE__), 'filters/fullwidth')
+require File.join(File.dirname(__FILE__), 'filters/symbol')
+require File.join(File.dirname(__FILE__), 'filters/conjunction')
+
+class Rseg
+  include Singleton
+  include RsegEngine
+  include RsegFilter
+  
+  class << self
+    def dict_path=(path)
+      RsegEngine::Dict.dict_path = path
+    end
+    
+    def segment(input)
+      Rseg.instance.input = input
+      Rseg.instance.segment
+    end
+    
+    def load
+      Rseg.instance
+      nil
+    end
+    
+    def remote_segment(input)
+      begin
+        response = Net::HTTP.post_form(URI.parse('http://127.0.0.1:4100/seg'), :input => input)
+        response.code == '200' ? response.body.split(' ') : 
+            ["Can't connect to http://localhost:4100\nUse rseg_server to start it"]
+      rescue
+        ["Can't connect to http://localhost:4100\nUse rseg_server to start it"]
+      end
+    end
+  end
+
+  def initialize
+    @input = ''
+    @words = []
+    init_engines
+    init_filters
+  end
+  
+  def input=(input)
+    @input = input
+  end
+  
+  def segment
+    @words = []
+    
+    @input.chars.each do |origin|
+      char = filter(origin)
+      process(char, origin)
+    end
+    
+    process(:symbol, '')
+    @words
+  end
+
+  private
+  def filter(char)
+    result = char
+    @filters.each do |klass|
+      result = klass.filter(result)
+    end
+    result
+  end
+  
+  def process(char, origin)
+    nomatch = true
+    word = ''
+    
+    engines.each do |engine|
+      next unless engine.running?
+      match, word = engine.process(char)
+      match ? nomatch = false : engine.stop
+    end
+    
+    if nomatch
+      if word == ''
+        @words << origin unless char == :symbol
+        reset_engines
+      else
+        reset_engines
+        @words << word if word.is_a?(String)
+        reprocess(word) if word.is_a?(Array)
+
+        # re-process current char
+        process(char, origin)
+      end
+    end
+  end
+  
+  def reprocess(word)
+    last = word.pop
+
+    word.each do |char|
+      process(char, char)
+    end
+    
+    process(:symbol, :symbol)
+    process(last, last)
+  end
+
+  def reset_engines
+    engines.each do |engine|
+      engine.run
+    end
+  end
+  
+  def engines=(engines)
+    @engines ||= engines
+  end
+
+  def engines
+    @engines
+  end
+
+  def init_filters
+    @filters = [Fullwidth, Symbol]
+  end
+  
+  def init_engines
+    @engines ||= [Dict, English, Number, Name].map do |engine_klass|
+      engine_klass.new
+    end
+  end
+end

data/public/screen.css

@@ -0,0 +1,123 @@
+div.clear           {clear: both;}
+body                {background: #EEEEEE; margin: 0; padding: 0;
+                     font-family: 'Lucida Grande', 'Lucida Sans Unicode',
+                     'Garuda';}
+code                {font-family: 'Lucida Console', monospace;
+                     font-size: 12px;}
+li                  {height: 18px;}
+ul                  {list-style: none; margin: 0; padding: 0;}
+ol:hover            {cursor: pointer;}
+ol li               {white-space: pre;}
+#explanation        {font-size: 12px; color: #666666;
+                     margin: 20px 0 0 100px;}
+/* WRAP */
+#wrap               {width: 860px; background: #FFFFFF; margin: 0 auto;
+                     padding: 30px 50px 20px 50px;
+                     border-left: 1px solid #DDDDDD;
+                     border-right: 1px solid #DDDDDD;}
+/* HEADER */
+#header             {margin: 0 auto 25px auto;}
+h1                  {margin: 0; font-size: 36px; color: #981919;}
+h2                  {margin: 0; font-size: 22px; color: #333333;}
+#header ul          {margin: 0; font-size: 12px; color: #666666;}
+#header ul li strong{color: #444444;}
+#header ul li       {display: inline; padding: 0 10px;}
+#header ul li.first {padding-left: 0;}
+#header ul li.last  {border: 0; padding-right: 0;}
+
+#content            {width: 860px; margin: 0 auto 10px auto;}
+
+h3                  {float: left; width: 100px; margin-bottom: 10px;
+                     color: #981919; font-size: 14px; font-weight: bold;}
+
+#footer             {width: 860px; margin: 0 auto 10px auto; clear:both;
+                     font-size: 18px; border-top:1px solid #000; padding-top: 10px;
+                     text-align: right;}
+
+textarea            {font-size: 18px; padding:10px;}
+#segform            { width: 430px; float: left; font-size: 18px;}
+#segresult          { width: 408px; float: left; font-size: 18px;
+                      padding: 10px; color: #D12F19;}
+/* --------------------------------------------------------------
+
+  buttons.css
+  * Gives you some great CSS-only buttons.
+
+  Created by Kevin Hale [particletree.com]
+  * particletree.com/features/rediscovering-the-button-element
+
+  See Readme.txt in this folder for instructions.
+
+-------------------------------------------------------------- */
+
+button {
+ display:block;
+ float:left;
+ margin:0 0.583em 0.667em 0;
+ padding:5px 10px 5px 7px;   /* Links */
+
+ border:1px solid #dedede;
+ border-top:1px solid #eee;
+ border-left:1px solid #eee;
+
+ background-color:#f5f5f5;
+ font-family:"Lucida Grande", Tahoma, Arial, Verdana, sans-serif;
+ font-size:100%;
+ line-height:130%;
+ text-decoration:none;
+ font-weight:bold;
+ color:#565656;
+ cursor:pointer;
+}
+button {
+ width:auto;
+ overflow:visible;
+ padding:4px 10px 3px 7px;   /* IE6 */
+}
+button[type] {
+ padding:4px 10px 4px 7px;   /* Firefox */
+ line-height:17px;           /* Safari */
+}
+*:first-child+html button[type] {
+ padding:4px 10px 3px 7px;   /* IE7 */
+}
+button img {
+ margin:0 3px -3px 0 !important;
+ padding:0;
+ border:none;
+ width:16px;
+ height:16px;
+ float:none;
+}
+
+
+/* Button colors
+-------------------------------------------------------------- */
+
+/* Standard */
+button:hover {
+ background-color:#dff4ff;
+ border:1px solid #c2e1ef;
+ color:#336699;
+}
+
+/* Positive */
+body .positive {
+ color:#529214;
+}
+button.positive:hover {
+ background-color:#E6EFC2;
+ border:1px solid #C6D880;
+ color:#529214;
+}
+
+/* Negative */
+body .negative {
+ color:#d12f19;
+}
+button.negative:hover {
+ background:#fbe3e4;
+ border:1px solid #fbc2c4;
+ color:#d12f19;
+}
+

data/views/index.haml

@@ -0,0 +1,8 @@
+#segform
+  %form{:action => '/segment', :method => 'post'}
+    %p
+      %textarea{:id => 'input', :rows => '15', :cols => '35', :name => 'input'}= @input || '输入要分词的文章'
+    %p
+      %button.negative{ :type => "submit" } 开始分词
+#segresult
+  %p= @result

data/views/layout.haml

@@ -0,0 +1,16 @@
+!!! Strict
+%html{ :lang => "en", :"xml:lang" => "en", :xmlns => "http://www.w3.org/1999/xhtml" }
+  %head
+    %meta{ :content => "text/html; charset=utf-8", :"http-equiv" => "Content-Type" }
+    %meta{ :content => "zh_CN", :"http-equiv" => "Content-Language" }
+    %title= "Rseg中文分词"
+    %link{ :rel => 'stylesheet',  :href => '/screen.css',  :type => 'text/css', :media => "screen"} 
+    
+  %body
+    #wrap
+      #header
+        %h1= "Rseg 中文分词"
+        %address.watermark
+      #content.condensed= yield
+      #footer= "作者： 张元一 <br />EMail：zhangyuanyi#gmail.com"
+

metadata

@@ -0,0 +1,104 @@
+--- !ruby/object:Gem::Specification
+name: rseg1.9
+version: !ruby/object:Gem::Version
+  version: 0.1.5
+  prerelease: 
+platform: ruby
+authors:
+- Yuanyi Zhang
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2010-11-28 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: haml
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: sinatra
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: A Chinese Word Segmentation(中文分词) routine in pure Ruby
+email: zhangyuanyi@gmail.com
+executables:
+- rseg
+- rseg_server
+extensions: []
+extra_rdoc_files:
+- LICENSE
+- README
+files:
+- .gitignore
+- LICENSE
+- README
+- Rakefile
+- VERSION
+- bin/rseg
+- bin/rseg_server
+- dict/dict.hash
+- lib/app.rb
+- lib/builder/dict.rb
+- lib/engines/dict.rb
+- lib/engines/engine.rb
+- lib/engines/english.rb
+- lib/engines/name.rb
+- lib/engines/number.rb
+- lib/filters/conjunction.rb
+- lib/filters/fullwidth.rb
+- lib/filters/symbol.rb
+- lib/rseg.rb
+- public/screen.css
+- views/index.haml
+- views/layout.haml
+homepage: http://github.com/yzhang/rseg
+licenses: []
+post_install_message: 
+rdoc_options:
+- --charset=UTF-8
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: A Chinese Word Segmentation(中文分词) routine in pure Ruby
+test_files: []
+has_rdoc: