twkorean 0.0.2 → 0.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7c036bc9d6da0eb2bfa259b0eafa83b54a182eee
-  data.tar.gz: 0a8824c1b459e991791523d8b390aff58bcfb09b
+  metadata.gz: 9fa5c2b3f783010b5b67c23db599ffd3ec75ef61
+  data.tar.gz: 2117abd053395906001c822082aef413c91441c2
 SHA512:
-  metadata.gz: 76796b2e4b794b76270c3e46d39fe11d847aebf8e7bf890665e34c7748f2f5a8e68b2a7179b701bad4c2e5184935fd85a16ab49142e4e4f54f301f114ed77491
-  data.tar.gz: c83bdfdfc02020422a1f2a6afdbce104cd03640b7722ad700a81f2a3cd9bc4c70b0e17e26366a47a8c4adbadae525ebf1d44fb6e1fe4f6d515dd8f2b823fc091
+  metadata.gz: 7ed15b2886e42e367c0652e1a86aad07b98c09279b37e0cd02b1e733499076e69c9481573e91c51d01ae70ed4e3feec4d0610e8dd0bed059d5a536c9193ce776
+  data.tar.gz: 854b177257cf8252e1a81916a02ea721e01ef94ea3e3d4a4d02b02e65a9872bb30934d46c0b7c24a3cb8a8ae5fbca06dceb688496807a4d0f24a6c65ece08198

data/README.md

@@ -1,6 +1,8 @@
 # Twkorean
 
-TODO: Write a gem description
+## Compatibility
+
+Currently wraps [twitter-korean-text 3.0](https://github.com/twitter/twitter-korean-text/tree/korean-text-3.0) / 현재 이 프로젝트는 [twitter-korean-text 3.0](https://github.com/twitter/twitter-korean-text/tree/korean-text-3.0)을 사용중입니다.
 
 ## Installation
 
@@ -18,7 +20,8 @@ Or install it yourself as:
 
 ## Required
 
-    $ export JAVA_HOME=/etc/alternatives/java_sdk_{Your version}
+    $ export JAVA_HOME={Your Path}
+    $ gem install 'rjb'
 
 ## Test
     
@@ -26,8 +29,40 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+     describe "Twkorean" do
+        TEXT = "한국어를 처리하는 예시입니닼ㅋㅋㅋㅋㅋ #한국어"
+        before do
+          
+        end
+
+        it "Normalize" do
+          twkorean = Twkorean::TwitterKoreanText.new
+          p "Normlize"
+          p twkorean.normalize(TEXT)
+          # 한국어를 처리하는 예시입니다ㅋㅋ #한국어
+        end
+
+        it "Tokenize" do
+          twkorean = Twkorean::TwitterKoreanText.new(true, false)
+          p "#Tokenize"
+          p twkorean.tokenize(TEXT)
+          # ["한국어(Noun: 0, 3)", "를(Josa: 3, 1)", "처리(Noun: 5, 2)", "하는(Verb: 7, 2)", "예시(Noun: 10, 2)", "입니(Adjective: 12, 2)", "다(Eomi: 14, 1)", "ㅋㅋ(KoreanParticle: 15, 2)", "#한국어(Hashtag: 18, 4)"]
+        end
+
+        it "Stemming" do
+          twkorean = Twkorean::TwitterKoreanText.new
+          p "#Stemming"
+          p twkorean.tokenize(TEXT)
+          # ["한국어(Noun: 0, 3)", "를(Josa: 3, 1)", "처리(Noun: 5, 2)", "하다(Verb: 7, 2)", "예시(Noun: 10, 2)", "이다(Adjective: 12, 3)", "ㅋㅋ(KoreanParticle: 15, 2)", "#한국어(Hashtag: 18, 4)"]
+        end
 
+        it "Phrase extraction" do
+          twkorean = Twkorean::TwitterKoreanText.new
+          p "Phrase extraction"
+          p twkorean.extract_phrases(TEXT)
+          # ["한국어(Noun: 0, 3)", "처리(Noun: 5, 2)", "처리하는 예시(Noun: 5, 7)", "예시(Noun: 10, 2)", "#한국어(Hashtag: 18, 4)"]
+        end
+     end
 ## Contributing
 
 1. Fork it ( https://github.com/[my-github-username]/twkorean/fork )

data/lib/twkorean/twitter_korean_text.rb

@@ -1,6 +1,6 @@
 # @name                twkorean-ruby
 # @author              JunSangPil
-# @version             0.0.2
+# @version             0.0.3
 # @url                 https://github.com/jun85664396/twkorean-ruby
 # @license             Apache License 2.0
 module Twkorean
@@ -43,5 +43,9 @@ module Twkorean
       phrases.toArray.map{|x| x.toString}
     end
 
+    def parser(text)
+      text.match(/(.*)\(([a-zA-Z]*): ([0-9]+), ([0-9]+)\)/).to_a
+    end
+
   end
 end

data/lib/twkorean/version.rb

@@ -1,8 +1,8 @@
 # @name                twkorean-ruby
 # @author              JunSangPil
-# @version             0.0.2
+# @version             0.0.3
 # @url                 https://github.com/jun85664396/twkorean-ruby
 # @license             Apache License 2.0
 module Twkorean
-  VERSION = "0.0.2"
+  VERSION = "0.0.3"
 end

data/lib/twkorean.rb

@@ -1,6 +1,6 @@
 # @name                twkorean-ruby
 # @author              JunSangPil
-# @version             0.0.2
+# @version             0.0.3
 # @url                 https://github.com/jun85664396/twkorean-ruby
 # @license             Apache License 2.0
 require "twkorean/version"

data/test/test_helper.rb

@@ -1,6 +1,6 @@
 # @name                twkorean-ruby
 # @author              JunSangPil
-# @version             0.0.2
+# @version             0.0.3
 # @url                 https://github.com/jun85664396/twkorean-ruby
 # @license             Apache License 2.0
 require 'minitest/autorun'

data/test/twkorean.rb

@@ -1,6 +1,6 @@
 # @name                twkorean-ruby
 # @author              JunSangPil
-# @version             0.0.2
+# @version             0.0.3
 # @url                 https://github.com/jun85664396/twkorean-ruby
 # @license             Apache License 2.0
 require_relative 'test_helper'
@@ -9,31 +9,42 @@ require 'twkorean'
 describe "Twkorean" do
   TEXT = "한국어를 처리하는 예시입니닼ㅋㅋㅋㅋㅋ #한국어"
   before do
-    
+
   end
 
   it "Normalize" do
     twkorean = Twkorean::TwitterKoreanText.new
     p "Normlize"
     p twkorean.normalize(TEXT)
+    # 한국어를 처리하는 예시입니다ㅋㅋ #한국어
   end
 
   it "Tokenize" do
     twkorean = Twkorean::TwitterKoreanText.new(true, false)
     p "#Tokenize"
     p twkorean.tokenize(TEXT)
+    # ["한국어(Noun: 0, 3)", "를(Josa: 3, 1)", "처리(Noun: 5, 2)", "하는(Verb: 7, 2)", "예시(Noun: 10, 2)", "입니(Adjective: 12, 2)", "다(Eomi: 14, 1)", "ㅋㅋ(KoreanParticle: 15, 2)", "#한국어(Hashtag: 18, 4)"]
   end
 
   it "Stemming" do
     twkorean = Twkorean::TwitterKoreanText.new
     p "#Stemming"
     p twkorean.tokenize(TEXT)
+    # ["한국어(Noun: 0, 3)", "를(Josa: 3, 1)", "처리(Noun: 5, 2)", "하다(Verb: 7, 2)", "예시(Noun: 10, 2)", "이다(Adjective: 12, 3)", "ㅋㅋ(KoreanParticle: 15, 2)", "#한국어(Hashtag: 18, 4)"]
   end
 
   it "Phrase extraction" do
     twkorean = Twkorean::TwitterKoreanText.new
     p "Phrase extraction"
     p twkorean.extract_phrases(TEXT)
+    # ["한국어(Noun: 0, 3)", "처리(Noun: 5, 2)", "처리하는 예시(Noun: 5, 7)", "예시(Noun: 10, 2)", "#한국어(Hashtag: 18, 4)"]
+  end
+
+  it "Parser" do
+    twkorean = Twkorean::TwitterKoreanText.new(true, false)
+    p "#Tokenize Parser"
+    p twkorean.tokenize(TEXT).map{|x| twkorean.parser(x) }
+    # ["한국어(Noun: 0, 3)", "를(Josa: 3, 1)", "처리(Noun: 5, 2)", "하는(Verb: 7, 2)", "예시(Noun: 10, 2)", "입니(Adjective: 12, 2)", "다(Eomi: 14, 1)", "ㅋㅋ(KoreanParticle: 15, 2)", "#한국어(Hashtag: 18, 4)"]
   end
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: twkorean
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors:
 - JunSangPil
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-09-21 00:00:00.000000000 Z
+date: 2015-10-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler