kanji-translator 0.1.0 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c4f92f7987bc8ed9600c1b5849f56c0538f6af423afd53249ae70bc83e53a383
-  data.tar.gz: 226e287702852d0d05563b4a38aba069caef02e52c56c76d4011ef22e928c43c
+  metadata.gz: 6d693a0727ff440e9630d4ac66f28ff42da8c707a3d222deedfaa2a394304e55
+  data.tar.gz: 5c26cc604c58942286badd65577a7b8094f9f304d34ae5e8474489ce18757676
 SHA512:
-  metadata.gz: 7e09f7183a129996b4fbfeff7e56b86f51e7b6b53ef7db428bb3c45b4e1bea4acb644251e996dbb68fe05c39785b202d76d7d3aca1d50b9c6299ce15ec1c74a7
-  data.tar.gz: a99f5a503d9b9a1a715d3d9405a86306c110ebc13b0c6bb5c17c494453460f04c05130176a4662138c8d2e24dfa119fd0080f61943c0364e5dd2cab963d24d54
+  metadata.gz: b3e115cb0d6057dde1642b4fdf8c61acc59b4a8275e471df8a04e4ba01311dfe119677ef4a5fd7d39348687532d5e5d7711c9da2b598529960461eddff3fc140
+  data.tar.gz: 279143b96cef0e5ecccb6cd8e35b80409e6ca734ba9ec72ef61b0080aea94c76fb4d93f958155e43d4562a1a4143121f0cee4140d6f36b59fb6918f68823ab5e

data/CHANGELOG.md

@@ -1,5 +1,12 @@
 ## [Unreleased]
 
+## [1.0.0] - 2025-09-08
+
+- Breaking: `to_slug` のデフォルト挙動を `segmenter: :tiny` に変更（語境界ごとにハイフン区切り）。
+- Added: `segmenter: :space` オプションを追加。
+- Added: 依存に `tiny_segmenter (~> 0.0.6)` を追加。
+- Docs/Tests: READMEとRSpecを更新し新仕様を反映。
+
 ## [0.1.0] - 2025-09-08
 
 - Initial release

data/README.md

@@ -8,13 +8,11 @@
 
 Ruby 3.2以上が必要です。
 
-Rubygems公開後:
-
 ```bash
 bundle add kanji-translator
 ```
 
-未公開期間にGitHubから使う場合:
+GitHubから使う場合（任意）:
 
 ```ruby
 # Gemfile
@@ -51,15 +49,20 @@ require "kanji/translator/core_ext/string"
   - ひらがな読みをカタカナに変換して返します。
 - `Kanji::Translator.to_roma(text, **opts)`
   - 簡易ヘボン式のローマ字（ASCII、小文字）で返します。拗音/促音（ゃゅょ/っ）に対応。長音記号「ー」は無視します（例: おう→ou）。
-- `Kanji::Translator.to_slug(text, separator: "-", downcase: true, collapse: true, **opts)`
+- `Kanji::Translator.to_slug(text, separator: "-", downcase: true, collapse: true, segmenter: :tiny, **opts)`
   - `to_roma` の結果をスラッグ化します。
     - 非英数字を `separator` に置換、連続区切りを圧縮、前後の区切りをトリムします。
+   - `segmenter: :tiny`（デフォルト）: TinySegmenter で分かち、語ごとにハイフン区切り（例: "学校案内" → "gakkou-annai"）。
+   - `segmenter: :space`: 空白でのみ分割（例: "学校 案内" → "gakkou-annai"）。
+   - `segmenter: nil`: 分かちなし（語の自動区切りなし）。
 
 例（オプション）:
 
 ```ruby
 Kanji::Translator.to_hira("漢字", timeout: 3, retries: 1)
 Kanji::Translator.to_slug("東京タワー 2010") #=> "toukyou-tawa-2010"
+Kanji::Translator.to_slug("学校 案内", segmenter: :space) #=> "gakkou-annai"
+Kanji::Translator.to_slug("学校案内", segmenter: nil) #=> "gakkouannai"
 Kanji::Translator.to_slug("Foo Bar", separator: "_") #=> "foo_bar"
 ```
 

data/lib/kanji/translator/version.rb

@@ -2,6 +2,6 @@
 
 module Kanji
   module Translator
-    VERSION = "0.1.0"
+    VERSION = "1.0.0"
   end
 end

data/lib/kanji/translator.rb

@@ -31,10 +31,28 @@ module Kanji
       hiragana_to_romaji(hira)
     end
 
-    def self.to_slug(text, separator: "-", downcase: true, collapse: true, **)
-      roma = to_roma(text, **)
-      s = downcase ? roma.downcase : roma.dup
-      sep = separator
+    def self.to_slug(text, **opts)
+      sep       = opts.fetch(:separator, "-")
+      downcase  = opts.fetch(:downcase, true)
+      collapse  = opts.fetch(:collapse, true)
+      segmenter = opts.fetch(:segmenter, :tiny)
+      net_opts  = slice_opts(opts, :timeout, :retries, :backoff, :user_agent)
+
+      s = case segmenter
+          when :tiny
+            tokens = segment_with_tiny(text)
+            parts = tokens.filter_map { |tok| normalize_slug_part(tok, net_opts) }
+            parts.join(sep)
+          when :space
+            tokens = segment_with_space(text)
+            parts = tokens.filter_map { |tok| normalize_slug_part(tok, net_opts) }
+            parts.join(sep)
+          else
+            roma = to_roma(text, **net_opts)
+            roma.dup
+          end
+
+      s = s.downcase if downcase
       # Replace non-alphanumeric with separator
       s = s.gsub(/[^a-z0-9]+/, sep)
       # Collapse duplicate separators
@@ -193,5 +211,33 @@ module Kanji
       jitter = rand * 0.05
       sleep_s + jitter
     end
+
+    def self.segment_with_tiny(text)
+      require "tiny_segmenter"
+      TinySegmenter.new.segment(text)
+    rescue LoadError
+      raise Error, "tiny_segmenter gem is not installed. Add `tiny_segmenter` or omit segmenter option."
+    end
+
+    def self.japanese_token?(tok)
+      # Kanji, Kana, prolonged sound mark, iteration marks, small kana
+      !!(tok =~ /[一-龯々〆ヵヶぁ-ゖゝゞァ-ヴー]/)
+    end
+
+    def self.segment_with_space(text)
+      text.split(/\s+/)
+    end
+
+    def self.normalize_slug_part(tok, net_opts)
+      if japanese_token?(tok)
+        to_roma(tok, **net_opts)
+      elsif tok =~ /[A-Za-z0-9]+/
+        tok
+      end
+    end
+
+    def self.slice_opts(hash, *keys)
+      hash.slice(*keys)
+    end
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: kanji-translator
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 1.0.0
 platform: ruby
 authors:
 - Hiromu Kodani
@@ -23,6 +23,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.16'
+- !ruby/object:Gem::Dependency
+  name: tiny_segmenter
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.0.6
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.0.6
 description: |-
   Fetches readings for Japanese Kanji from yomikatawa.com and converts them
   to hiragana, katakana, or Hepburn-style romaji. Includes timeout/retry