chawan 0.0.1 → 0.0.2

data/README

@@ -26,6 +26,22 @@ Class
 Example
 =======
 
+  Chawan.parse('本日は晴天なり')
+  => [<名詞: '本日'>, <助詞: 'は'>, <名詞: '晴天'>, <助動詞: 'なり'>]
+
+  Chawan.parse('本日は晴天なり').select{|node| node.category == '名詞'}.join
+  => "本日晴天"
+
+  
+Analyzer
+========
+
+  Parser engine is defined as 'analyzer'.
+  Available analyzers are:
+
+    * mecab : (default)
+    * chasen
+    
   Chawan[:mecab].parse('test')
   => [<名詞: 'test'>]
 
@@ -35,14 +51,7 @@ Example
   #   Chawan.parse('test')  # default analyzer is :mecab
 
   Chawan[:chasen].parse('test')
-  # ChasenAnalyzer is not implemented yet
-
-
-  Chawan.parse('本日は晴天なり')
-  => [<名詞: '本日'>, <助詞: 'は'>, <名詞: '晴天'>, <助動詞: 'なり'>]
-
-  Chawan.parse('本日は晴天なり').select{|node| node.category == '名詞'}.join
-  => "本日晴天"
+  => [<記号: 't'>, <記号: 'e'>, <記号: 's'>, <記号: 't'>]
 
 
 Required
@@ -55,7 +64,6 @@ Required
 Todo
 ====
 
-  * implement ChasenAnalyzer
   * gateway interface to Chawan#parse such as grep, noun, ...
   * use open3 rather than backquote for executing unix commands
 

data/Rakefile

@@ -6,7 +6,7 @@ AUTHOR = "maiha"
 EMAIL = "maiha@wota.jp"
 HOMEPAGE = "http://github.com/maiha/chawan"
 SUMMARY = "A cup for chasen that provides an easy to use for extracting Japanese"
-GEM_VERSION = "0.0.1"
+GEM_VERSION = "0.0.2"
 
 spec = Gem::Specification.new do |s|
   s.rubyforge_project = 'asakusarb'

data/lib/chawan/analyzers/chasen_analyzer.rb

@@ -2,7 +2,9 @@
 module Chawan
   module Analyzers
     class ChasenAnalyzer < AbstractAnalyzer
-      Fields = []
+      # "%m\t%y\t%M\t%U(%P-)\t%\t%\n" # default format
+      Format = "%m\t%P:\t%y\t\n"
+      Fields = %w{ 見出し 品詞 読み }
 
       def parse(text)
         lines = execute(text).split(/\n/)
@@ -14,12 +16,14 @@ module Chawan
       private
         def execute(text)
           require 'chasen'
-#    format = %w[%m %y %M %Y %h %P- %t %T- %f %F- %?U/unknown/known/].join("\t") + "\t\n"
-          Chasen.getopt('-i', 'w')
+          Chasen.getopt('-i', 'w', '-F', self.class::Format)
           Chasen.sparse(text)
         end
 
-        def instantiate(line, fields)
+        def instantiate(line, keys)
+          vals = line.split(/,|\s/)
+          vals[1] = vals[1].split(/:/).first # '名詞-副詞可能' -> '名詞'
+          Node.new(vals, keys)
         end
     end
   end

data/spec/chasen_spec.rb

@@ -0,0 +1,27 @@
+
+require File.join(File.dirname(__FILE__), 'spec_helper.rb')
+
+describe Chawan::Analyzers::ChasenAnalyzer do
+  before do
+    @a = Chawan::Analyzers::ChasenAnalyzer.new
+  end
+
+  it "should provide #parse" do
+    @a.should respond_to(:parse)
+  end
+
+  describe "#parse" do
+    it "should return an Array of Node" do
+      text = data("example1.txt")
+      @a.parse(text).each do |node|
+        node.should be_kind_of(Chawan::Node)
+      end
+    end
+
+    it "should work as expected" do
+      text = data("example1.txt")
+      @a.parse(text).map(&:inspect).join.should ==
+        "<名詞: '本日'><助詞: 'は'><名詞: '晴天'><助動詞: 'なり'><記号: '。'>"
+    end
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: chawan
 version: !ruby/object:Gem::Version 
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors: 
 - maiha
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-01-03 00:00:00 +09:00
+date: 2010-01-05 00:00:00 +09:00
 default_executable: 
 dependencies: []
 
@@ -34,6 +34,7 @@ files:
 - lib/chawan/node.rb
 - lib/chawan/commands.rb
 - lib/chawan.rb
+- spec/chasen_spec.rb
 - spec/api_spec.rb
 - spec/mecab_spec.rb
 - spec/analyzer_spec.rb