igo 0.1.1 → 0.1.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f2595639cb911ec5464d15186707a89ccb04d67699b62e819bba4ffcc06b70f0
-  data.tar.gz: 49b7ed5a29ea28aa77db905d8997f7d0b671587717382cd8f4396bdab9a011b2
+  metadata.gz: e864f1dc86ce2b7164e50d13f42bc10d28b33fa4ae4f271ec912e410d461f697
+  data.tar.gz: 6e8ee3d9ac2e39306d2d02b79e9d86291bea4af1559cd7c4faf64bd009d947e3
 SHA512:
-  metadata.gz: 2f397f7ff33c578ff04d787605c694bd8a01a831bd34d7007333b560db8b45aae7ae9ddb1bc9c53bff05f4b167709b0e7b7be998d34a9762922a4a0199391b40
-  data.tar.gz: 231fd1296f291fda60291c72a26e4422b3ada2c29e024a67d572234d85fe352dc96abc28bda3b14f7a81f0a7667e620d290c21a507a8c6f0741bdf9c5feb9453
+  metadata.gz: ae7bee63027e8de27766e941f99e38b4775be1fc8bf8aaf5ca454d41bf7d0346ea9eb7e9f502f93ce5e0f1f347ab6e0eb9a2f01f8c6f1ce0e7362108a2813997
+  data.tar.gz: 97aa666160536500f5910a8d7c072e5652b435d1d9cecf6a5d5b98211ba45e1e4a76f6831d7cd90ed31fb394074f48962507a9475859a23fde355533a0a76330

data/README.en.md

@@ -0,0 +1,106 @@
+# 言語 :: Igo
+
+[🌏](README.md) | [中文](README.zh.md) | [English](README.en.md) | [日本語](README.ja.md)
+
+Support `zh-CN`, `ja-JP`
+
+```ruby
+ja.cut "あー、合成は結合法則を満たすんでしたね"
+#=> ["では", "、", "圏論", "の", "話", "を", "しましょ", "う", "か", "N", "この", "前", "は", "、圏", "について", "紹介 しました"]
+
+zh.tag "全世界的无产者，联合起来！", s: true
+#=> "全世界_n 的_uj 无产者_n ，_x 联合_v 起来_v ！_x"
+
+```
+
+## Install :: インストール
+
+```cmd
+gem install igo
+```
+
+for use `jisho-api`, `Thulac` in __Python__, you need to install:
+
+```cmd
+pip install jisho-api
+
+pip install thulac
+
+```
+
+## 使い方 :: Usage / Ja
+
+```ruby
+require 'igo'
+require 'igo/ja'
+
+j = Igo::Ja
+
+cutted = j.cut "あー、合成は結合法則を満たすんでしたね"
+#=> ["では", "、", "圏論", "の", "話", "を", "しましょ", "う", "か", "N", "この", "前", "は", "、圏", "について", "紹介 しました"]
+
+cutted = j.cut "あー、合成は結合法則を満たすんでしたね", s: true
+#=> "では 、 圏論 の 話 を しましょ う か N この 前 は 、圏 について 紹介しました"
+
+```
+
+下ノ関数は、暫く未完成です、ごめんね：
+
+`j.romaji`, `j.kana`, `j.tag`。
+
+## 用法 :: Usage / Zh
+
+Lack __Trad-Zh__ :: 暂不支持「正體中文」
+
+```ruby
+require 'igo'
+require 'igo/zh'
+z = Igo::Zh
+```
+
+### Pinyin :: 拼音
+
+```ruby
+z.pinyin "全世界的无产者，联合起来！"
+#=> ["quan2", "shi4", "jie4", "de", "wu2", "chan3", "zhe3", "lian2", "he2", "qi3", "lai2"]
+z.pinyin "全世界的无产者，联合起来！", s: 1
+#=> "quan2 shi4 jie4 de wu2 chan3 zhe3 lian2 he2 qi3 lai2"
+```
+
+### seperate word :: 分词
+
+```ruby
+z.cut "全世界的无产者，联合起来！"
+#=> ["全世界", "的", "無產階級", "，", "聯合", "起來", "！"]
+z.cut "全世界的无产者，联合起来！", s: true
+#=> "全世界 的 无产者 ！ 联合 起来 ！"
+```
+### Taging word :: 标注词类
+
+后续可能添加 `by` 关键词指定函数。
+
+```ruby
+z.tag "全世界的无产者，联合起来！"
+#=>  [["全世界", "n"], ["的", "uj"], ["无产者", "n"], ["！", "x"], ["联合", "v"], ["起来", "v"], ["！", "x"]]
+z.tag "全世界的无产者，联合起来！", s: true
+#=> "全世界_n 的_uj 无产者_n ，_x 联合_v 起来_v ！_x"
+```
+### 词频统计
+
+```ruby
+z.freq "全世界的无产者，联合起来！", 5
+#=>  [["无产者", 9.96885201925], ["全世界", 6.80147590842], ["联合", 5.64979650728], ["起来", 3.96134044655]]
+
+# alias 拼音, 分词, 标记, 词频
+
+```
+
+## LINCENCE :: 协议
+
+__MPL 2.0__
+
+## Requires
+
+- `jieba-rb`
+- `nokogiri`
+- `open-uri`

data/README.ja.md

@@ -0,0 +1,105 @@
+# 言語 :: Igo
+
+[🌏](README.md) | [中文](README.zh.md) | [English](README.en.md) | [日本語](README.ja.md)
+
+Support `zh-CN`, `ja-JP`
+
+```ruby
+ja.cut "あー、合成は結合法則を満たすんでしたね"
+#=> ["では", "、", "圏論", "の", "話", "を", "しましょ", "う", "か", "N", "この", "前", "は", "、圏", "について", "紹介 しました"]
+
+zh.tag "全世界的无产者，联合起来！", s: true
+#=> "全世界_n 的_uj 无产者_n ，_x 联合_v 起来_v ！_x"
+
+```
+
+## Install :: インストール
+
+```cmd
+gem install igo
+```
+
+__Python__ ノ `Jisho-api`・`Thulac` 使いたいなら、以下の pip がインストール必要です:
+
+```cmd
+pip install jisho-api
+
+pip install thulac
+```
+
+## 使い方 :: Usage / Ja
+
+```ruby
+require 'igo'
+require 'igo/ja'
+
+j = Igo::Ja
+
+cutted = j.cut "あー、合成は結合法則を満たすんでしたね"
+#=> ["では", "、", "圏論", "の", "話", "を", "しましょ", "う", "か", "N", "この", "前", "は", "、圏", "について", "紹介 しました"]
+
+cutted = j.cut "あー、合成は結合法則を満たすんでしたね", s: true
+#=> "では 、 圏論 の 話 を しましょ う か N この 前 は 、圏 について 紹介しました"
+
+```
+
+下ノ関数は、暫く未完成です、ごめんね：
+
+`j.romaji`, `j.kana`, `j.tag`。
+
+## 用法 :: Usage / Zh
+
+Lack __Trad-Zh__ :: 暂不支持「正體中文」
+
+```ruby
+require 'igo'
+require 'igo/zh'
+z = Igo::Zh
+```
+
+### Pinyin :: 拼音
+
+```ruby
+z.pinyin "全世界的无产者，联合起来！"
+#=> ["quan2", "shi4", "jie4", "de", "wu2", "chan3", "zhe3", "lian2", "he2", "qi3", "lai2"]
+z.pinyin "全世界的无产者，联合起来！", s: 1
+#=> "quan2 shi4 jie4 de wu2 chan3 zhe3 lian2 he2 qi3 lai2"
+```
+
+### seperate word :: 分词
+
+```ruby
+z.cut "全世界的无产者，联合起来！"
+#=> ["全世界", "的", "無產階級", "，", "聯合", "起來", "！"]
+z.cut "全世界的无产者，联合起来！", s: true
+#=> "全世界 的 无产者 ！ 联合 起来 ！"
+```
+### Taging word :: 标注词类
+
+后续可能添加 `by` 关键词指定函数。
+
+```ruby
+z.tag "全世界的无产者，联合起来！"
+#=>  [["全世界", "n"], ["的", "uj"], ["无产者", "n"], ["！", "x"], ["联合", "v"], ["起来", "v"], ["！", "x"]]
+z.tag "全世界的无产者，联合起来！", s: true
+#=> "全世界_n 的_uj 无产者_n ，_x 联合_v 起来_v ！_x"
+```
+### 词频统计
+
+```ruby
+z.freq "全世界的无产者，联合起来！", 5
+#=>  [["无产者", 9.96885201925], ["全世界", 6.80147590842], ["联合", 5.64979650728], ["起来", 3.96134044655]]
+
+# alias 拼音, 分词, 标记, 词频
+
+```
+
+## LINCENCE :: 协议
+
+__MPL 2.0__
+
+## Requires
+
+- `jieba-rb`
+- `nokogiri`
+- `open-uri`

data/README.md

@@ -1,39 +1,106 @@
-# Igo
+# 言語 :: Igo
 
-TODO: Delete this and the text below, and describe your gem
+[🌏](README.md) | [中文](README.zh.md) | [English](README.en.md) | [日本語](README.ja.md)
 
-Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/igo`. To experiment with that code, run `bin/console` for an interactive prompt.
+Support `zh-CN`, `ja-JP`
 
-## Installation
+```ruby
+ja.cut "あー、合成は結合法則を満たすんでしたね"
+#=> ["では", "、", "圏論", "の", "話", "を", "しましょ", "う", "か", "N", "この", "前", "は", "、圏", "について", "紹介 しました"]
 
-TODO: Replace `UPDATE_WITH_YOUR_GEM_NAME_PRIOR_TO_RELEASE_TO_RUBYGEMS_ORG` with your gem name right after releasing it to RubyGems.org. Please do not do it earlier due to security reasons. Alternatively, replace this section with instructions to install your gem from git if you don't plan to release to RubyGems.org.
+zh.tag "全世界的无产者，联合起来！", s: true
+#=> "全世界_n 的_uj 无产者_n ，_x 联合_v 起来_v ！_x"
 
-Install the gem and add to the application's Gemfile by executing:
+```
 
-    $ bundle add UPDATE_WITH_YOUR_GEM_NAME_PRIOR_TO_RELEASE_TO_RUBYGEMS_ORG
+## Install :: インストール
 
-If bundler is not being used to manage dependencies, install the gem by executing:
+```cmd
+gem install igo
+```
 
-    $ gem install UPDATE_WITH_YOUR_GEM_NAME_PRIOR_TO_RELEASE_TO_RUBYGEMS_ORG
+for use `jisho-api`, `Thulac` in __Python__, you need to install:
 
-## Usage
+```cmd
+pip install jisho-api
 
-TODO: Write usage instructions here
+pip install thulac
 
-## Development
+```
 
-After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+## 使い方 :: Usage / Ja
 
-To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+```ruby
+require 'igo'
+require 'igo/ja'
 
-## Contributing
+j = Igo::Ja
 
-Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/igo. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/[USERNAME]/igo/blob/master/CODE_OF_CONDUCT.md).
+cutted = j.cut "あー、合成は結合法則を満たすんでしたね"
+#=> ["では", "、", "圏論", "の", "話", "を", "しましょ", "う", "か", "N", "この", "前", "は", "、圏", "について", "紹介 しました"]
 
-## License
+cutted = j.cut "あー、合成は結合法則を満たすんでしたね", s: true
+#=> "では 、 圏論 の 話 を しましょ う か N この 前 は 、圏 について 紹介しました"
 
-The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+```
 
-## Code of Conduct
+下ノ関数は、暫く未完成です、ごめんね：
 
-Everyone interacting in the Igo project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/igo/blob/master/CODE_OF_CONDUCT.md).
+`j.romaji`, `j.kana`, `j.tag`。
+
+## 用法 :: Usage / Zh
+
+Lack __Trad-Zh__ :: 暂不支持「正體中文」
+
+```ruby
+require 'igo'
+require 'igo/zh'
+z = Igo::Zh
+```
+
+### Pinyin :: 拼音
+
+```ruby
+z.pinyin "全世界的无产者，联合起来！"
+#=> ["quan2", "shi4", "jie4", "de", "wu2", "chan3", "zhe3", "lian2", "he2", "qi3", "lai2"]
+z.pinyin "全世界的无产者，联合起来！", s: 1
+#=> "quan2 shi4 jie4 de wu2 chan3 zhe3 lian2 he2 qi3 lai2"
+```
+
+### seperate word :: 分词
+
+```ruby
+z.cut "全世界的无产者，联合起来！"
+#=> ["全世界", "的", "無產階級", "，", "聯合", "起來", "！"]
+z.cut "全世界的无产者，联合起来！", s: true
+#=> "全世界 的 无产者 ！ 联合 起来 ！"
+```
+### Taging word :: 标注词类
+
+后续可能添加 `by` 关键词指定函数。
+
+```ruby
+z.tag "全世界的无产者，联合起来！"
+#=>  [["全世界", "n"], ["的", "uj"], ["无产者", "n"], ["！", "x"], ["联合", "v"], ["起来", "v"], ["！", "x"]]
+z.tag "全世界的无产者，联合起来！", s: true
+#=> "全世界_n 的_uj 无产者_n ，_x 联合_v 起来_v ！_x"
+```
+### 词频统计
+
+```ruby
+z.freq "全世界的无产者，联合起来！", 5
+#=>  [["无产者", 9.96885201925], ["全世界", 6.80147590842], ["联合", 5.64979650728], ["起来", 3.96134044655]]
+
+# alias 拼音, 分词, 标记, 词频
+
+```
+
+## LINCENCE :: 协议
+
+__MPL 2.0__
+
+## Requires
+
+- `jieba-rb`
+- `nokogiri`
+- `open-uri`

data/README.zh.md

@@ -0,0 +1,106 @@
+# 言語 :: Igo
+
+[🌏](README.md) | [中文](README.zh.md) | [English](README.en.md) | [日本語](README.ja.md)
+
+Support `zh-CN`, `ja-JP`
+
+```ruby
+ja.cut "あー、合成は結合法則を満たすんでしたね"
+#=> ["では", "、", "圏論", "の", "話", "を", "しましょ", "う", "か", "N", "この", "前", "は", "、圏", "について", "紹介 しました"]
+
+zh.tag "全世界的无产者，联合起来！", s: true
+#=> "全世界_n 的_uj 无产者_n ，_x 联合_v 起来_v ！_x"
+
+```
+
+## Install :: 安装
+
+```cmd
+gem install igo
+```
+
+要使用 __Python__ 库的 `jisho_api`, `Thulac`，你得先安装...：
+
+```cmd
+pip install jisho-api
+
+pip install thulac
+
+```
+
+## 使い方 :: Usage / Ja
+
+```ruby
+require 'igo'
+require 'igo/ja'
+
+j = Igo::Ja
+
+cutted = j.cut "あー、合成は結合法則を満たすんでしたね"
+#=> ["では", "、", "圏論", "の", "話", "を", "しましょ", "う", "か", "N", "この", "前", "は", "、圏", "について", "紹介 しました"]
+
+cutted = j.cut "あー、合成は結合法則を満たすんでしたね", s: true
+#=> "では 、 圏論 の 話 を しましょ う か N この 前 は 、圏 について 紹介しました"
+
+```
+
+下ノ関数は、暫く未完成です、ごめんね：
+
+`j.romaji`, `j.kana`, `j.tag`。
+
+## 用法 :: Usage / Zh
+
+Lack __Trad-Zh__ :: 暂不支持「正體中文」
+
+```ruby
+require 'igo'
+require 'igo/zh'
+z = Igo::Zh
+```
+
+### Pinyin :: 拼音
+
+```ruby
+z.pinyin "全世界的无产者，联合起来！"
+#=> ["quan2", "shi4", "jie4", "de", "wu2", "chan3", "zhe3", "lian2", "he2", "qi3", "lai2"]
+z.pinyin "全世界的无产者，联合起来！", s: 1
+#=> "quan2 shi4 jie4 de wu2 chan3 zhe3 lian2 he2 qi3 lai2"
+```
+
+### seperate word :: 分词
+
+```ruby
+z.cut "全世界的无产者，联合起来！"
+#=> ["全世界", "的", "無產階級", "，", "聯合", "起來", "！"]
+z.cut "全世界的无产者，联合起来！", s: true
+#=> "全世界 的 无产者 ！ 联合 起来 ！"
+```
+### Taging word :: 标注词类
+
+后续可能添加 `by` 关键词指定函数。
+
+```ruby
+z.tag "全世界的无产者，联合起来！"
+#=>  [["全世界", "n"], ["的", "uj"], ["无产者", "n"], ["！", "x"], ["联合", "v"], ["起来", "v"], ["！", "x"]]
+z.tag "全世界的无产者，联合起来！", s: true
+#=> "全世界_n 的_uj 无产者_n ，_x 联合_v 起来_v ！_x"
+```
+### 词频统计
+
+```ruby
+z.freq "全世界的无产者，联合起来！", 5
+#=>  [["无产者", 9.96885201925], ["全世界", 6.80147590842], ["联合", 5.64979650728], ["起来", 3.96134044655]]
+
+# alias 拼音, 分词, 标记, 词频
+
+```
+
+## LINCENCE :: 协议
+
+__MPL 2.0__
+
+## Requires
+
+- `jieba-rb`
+- `nokogiri`
+- `open-uri`

data/lib/igo/ja.rb

@@ -1,15 +1,17 @@
 require 'jisho_api'
 require 'nokogiri'
 require 'open-uri'
-
+require 'uri'
+require 'nagisa'
 
 module Igo
-  module Jisho
+  module Ja
 
     SEARCH_URL = "https://jisho.org/search/"
 
     class << self
       def cut str, s: false
+        str = URI.encode_www_form_component(str)
         doc = Nokogiri::HTML(URI.open(SEARCH_URL + str).read)
         cutted = doc.css(".japanese_word__text_wrapper").map{_1.text.strip}
         s ? cutted.join(" ") : cutted
@@ -20,9 +22,13 @@ module Igo
       # def kana str
       # end
     end
+
+    def tag str, s: false, ns: 0
+
+    end
+
   end
 
-  Ja = Jisho
 
   class << self
     def 日本語

data/lib/igo/thulac.rb

@@ -0,0 +1,15 @@
+require 'pycall/import'
+
+module Thulac
+  PyCall.exec("import thulac")
+  PyCall.exec("thulac1 = thulac.thulac()")
+end
+class << Thulac
+  def cut str, text: false
+    text = text ? "True" : "False"
+    PyCall.eval(<<-EOF
+      thulac1.cut(#{str.inspect}, text=#{text})
+    EOF
+    )
+  end
+end

data/lib/igo/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Igo
-  VERSION = "0.1.1"
+  VERSION = "0.1.4.1"
 end

data/lib/igo/zh.rb

@@ -3,15 +3,17 @@ require 'ruby_pinyin'
 module Igo
   module Zh
 
-    Tagging = JiebaRb::Tagging
+    Tagging = JiebaRb::Tagging.new
     Segment = JiebaRb::Segment.new mode: :mix, user_dict: "ext/cppjieba/dict/user.dict.utf8"
     Keyword = JiebaRb::Keyword.new
 
     # @params chinese: String
     # @returns pinyin_numeraltone: String
     class << self
-      def pinyin str
-        str.each_char.map{PinYin.of_string(_1, :ascii)}
+      def pinyin str, s: false
+        res = str.each_char.map{PinYin.of_string(_1, :ascii)}.flatten
+        s ? res.join(" ") : res
+
       end
       def pinyin_tonal_s str
         PinYin.sentence(token, :ascii)
@@ -20,16 +22,28 @@ module Igo
         PinYin.of_string(token, :ascii)
       end
 
-      def cut str, s: false, tag: false
-        if tag
-          s ? Tagging.tag(str).map{_1.to_a.flatten.join("_")}.join(" ") : Tagging.tag(str).map{_1.to_a.flatten}
-        else
-          Segment.cut(str)
+      def cut str, s: false, tag: false, by: "jieba"
+        case by
+        when /jieba/
+          if tag
+            s ? Tagging.tag(str).map{_1.to_a.flatten.join("_")}.join(" ") : Tagging.tag(str).map{_1.to_a.flatten}
+          else
+            res = Segment.cut(str)
+            s ? res.join(" ") : res
+          end
+        when /thulac/
+          Thulac.cut(str, text: s)
         end
       end
 
-      def tag str, s: false
-        s ? Tagging.tag(str).map{_1.to_a.flatten.join("_")}.join(" ") : Tagging.tag(str).map{_1.to_a.flatten}
+      def tag str, s: false, by: 0
+        case by
+        when /thu/
+          require './thulac'
+          Thulac.cut str, text: s
+        else
+          s ? Tagging.tag(str).map{_1.to_a.flatten.join("_")}.join(" ") : Tagging.tag(str).map{_1.to_a.flatten}
+        end
       end
 
       def termfreq string, num

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: igo
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.4.1
 platform: ruby
 authors:
 - saisui
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-12-23 00:00:00.000000000 Z
+date: 2023-12-24 00:00:00.000000000 Z
 dependencies: []
 description: It is easy.
 email:
@@ -22,11 +22,15 @@ files:
 - CHANGELOG.md
 - CODE_OF_CONDUCT.md
 - LICENSE.txt
+- README.en.md
+- README.ja.md
 - README.md
+- README.zh.md
 - Rakefile
 - igo.rb
 - lib/igo.rb
 - lib/igo/ja.rb
+- lib/igo/thulac.rb
 - lib/igo/version.rb
 - lib/igo/zh.rb
 - sig/igo.rbs