natsukantou 0.1.3 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1b299497adbec2c0446350fc1085c4f17c6a9ebe165246dbba07fef1914348e5
-  data.tar.gz: 8164f3a25f80bc7fde73fd8062563ecbdf34f5abc2f5b1b594e78a219bafe2b8
+  metadata.gz: d29dec07a03407ea767c53dce9760627262abf2fb35d3f9888659be3c2442efa
+  data.tar.gz: 36b30c5b5fff59a62293acdf660fd7f508c0b8bfc20c1882c3f7139b7ba4a06c
 SHA512:
-  metadata.gz: 34b63359b8441b651ffc071c841eae8cb74a29b2c7ea0fb2a717794a16de5dcc2fa8b94c5abf9e59f600cc49c7c9716a668e456790e01bf709d70a39737ef435
-  data.tar.gz: 951610545756fbe6b1b8384ba358b64b32f471ec6e5574f270b88f166ec70ef575270ac90b4ec2624f904d3d8bfb6ffe7b977a3aa4930ac82fc6ed04f1d90d70
+  metadata.gz: 07cb8f6e26187a971f0ff080767b7662a62ce7f0eb7730c647586ea351925ba94190156400ac37d3012d8bdaa7f848bd7456dc58b0216cb5e5ccb386ba9d4be5
+  data.tar.gz: da43175d1d13f63a0c2255cdc110257e35e54d8164ec65fbbdab1c81c1eff01b146db8e5239cef8312bfea87802e6be9258dcf42401991a72e379f35d5ba4288

data/CHANGELOG.md

@@ -17,3 +17,11 @@
 ## [0.1.3] - 2023-02-27
 
 - Skip interlacing if nodes' text() are identical
+
+## [0.2.0] - 2023-03-05
+
+- Add ChatGPT
+ 
+## [0.2.1] - 2023-04-30
+
+- Remove newline characters in HandleRubyMarkup, which helps improving translation

data/README.md

@@ -36,6 +36,7 @@ If you choose to save the config (`translator_config.rb`), next time you can reu
 
 * [DeepL API](https://www.deepl.com/pro-api)
 * [みんなの自動翻訳＠TexTra](https://mt-auto-minhon-mlt.ucri.jgn-x.jp/)
+* [ChatGPT](https://openai.com/)
 
 ### Middlewares
 

data/lib/natsukantou/chat_gpt.rb

@@ -0,0 +1,78 @@
+# frozen_string_literal: true
+
+require 'openai'
+
+# Machine translator
+#
+# ChatGPT
+module Natsukantou
+  class ChatGpt
+    include UtilityBase
+
+    # @param app [Hash]
+    # @param access_token [String] API access token
+    #
+    # @param translate_by_section [String] CSS selector to translate matched elements one by one.
+    #   Specify a css path (e.g. "body>p") to translate in smaller chunks.
+    def initialize(
+      app, access_token:,
+      translate_by_section:
+    )
+      @app = app
+      @access_token = access_token
+
+      ### Non request related setting
+      @translate_by_section = translate_by_section
+    end
+
+    attr_reader :env
+    attr_reader :access_token
+    attr_reader :translate_by_section
+
+    def call(env)
+      @env = env
+
+      if translate_by_section
+        env[:dom].css(translate_by_section).each do |node|
+          next if node.text.empty?
+
+          translated_xml = translate(node.to_xml)
+          node.replace(dom_node(translated_xml))
+        end
+      else
+        # TODO
+      end
+
+      env[:dom].lang = env[:lang_to].code
+
+      @app.call(env)
+    end
+
+    private
+
+    def translate(text)
+      message = "Please help me to translate the XML `#{text}` from #{env.lang_from.code} to #{env.lang_to.code}, maintaining XML structure." # rubocop:disable Layout/LineLength
+
+      response = client.chat(
+        parameters: {
+          model: "gpt-3.5-turbo",
+          messages: [{ role: "user", content: message }],
+          temperature: 0.7,
+        }
+      )
+
+      translated_xml = response.dig("choices", 0, "message", "content")
+
+      translated_xml.strip!
+
+      translated_xml
+    rescue Net::OpenTimeout
+      sleep 10
+      retry
+    end
+
+    def client
+      @client ||= ::OpenAI::Client.new(access_token: access_token)
+    end
+  end
+end

data/lib/natsukantou/handle_ruby_markup.rb

@@ -26,7 +26,7 @@ module Natsukantou
 
     def process_node(node)
       node.css('rt').each(&:remove)
-      node.inner_text = node.text.gsub(' ', '')
+      node.inner_text = node.text.gsub(/[[:space:]]/, '')
     end
   end
 end

data/lib/natsukantou/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Natsukantou
-  VERSION = "0.1.3"
+  VERSION = "0.2.1"
 end

data/lib/natsukantou.rb

@@ -33,6 +33,7 @@ module Natsukantou
   # Translators
   autoload_and_register :translator, :DeepL, "natsukantou/deep_l"
   autoload_and_register :translator, :Minhon, "natsukantou/minhon"
+  autoload_and_register :translator, :ChatGpt, "natsukantou/chat_gpt"
 
   # Middlewares
   autoload_and_register :middleware, :SubstitudeGlossary, "natsukantou/substitude_glossary"

data/natsukantou.gemspec

@@ -9,7 +9,7 @@ Gem::Specification.new do |spec|
   spec.email = ["mark@goodlife.tw"]
 
   spec.summary = "human language translation library for XML documents"
-  spec.description = "human language translation library for XML documents, supporting DeepL"
+  spec.description = "human language translation library for XML documents, supporting DeepL and ChatGPT"
   spec.homepage = "https://gitlab.com/lulalala/natsukantou"
   spec.license = "MIT"
   spec.required_ruby_version = ">= 2.7.0"
@@ -42,6 +42,9 @@ Gem::Specification.new do |spec|
   # Minhon
   spec.add_dependency 'oauth', '~> 0.5.1'
 
+  # ChatGPT
+  spec.add_dependency 'ruby-openai', '~> 3.5.0'
+
   # For more information and examples about making a new gem, check out our
   # guide at: https://bundler.io/guides/creating_gem.html
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: natsukantou
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.2.1
 platform: ruby
 authors:
 - lulalala
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-02-27 00:00:00.000000000 Z
+date: 2023-04-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: middleware
@@ -108,7 +108,22 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 0.5.1
+- !ruby/object:Gem::Dependency
+  name: ruby-openai
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.5.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.5.0
 description: human language translation library for XML documents, supporting DeepL
+  and ChatGPT
 email:
 - mark@goodlife.tw
 executables:
@@ -128,6 +143,7 @@ files:
 - lib/monkey_patch/oga_document.rb
 - lib/monkey_patch/runner.rb
 - lib/natsukantou.rb
+- lib/natsukantou/chat_gpt.rb
 - lib/natsukantou/deep_l.rb
 - lib/natsukantou/handle_ruby_markup.rb
 - lib/natsukantou/minhon.rb
@@ -167,7 +183,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.6
+rubygems_version: 3.4.12
 signing_key:
 specification_version: 4
 summary: human language translation library for XML documents