jlpt 1.0.0 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 351c7b81b049e4ef39a34cacf7d20e1d7ce04f1d302b7ed0033f62d48dd6eef3
-  data.tar.gz: 903b1e3d8e7b5054a20ae4cb532325cd823dfe0e9de98800ec9705acd80b8651
+  metadata.gz: 589a9e7366fdbd813dda518ecf956168a94fe5290784dee57f2e675e97ca536f
+  data.tar.gz: 6cce29bc0a1388f9304f6423670d7513a061b053c1a144e59d85cf565c6ab4ef
 SHA512:
-  metadata.gz: 6b5c45194f1469bc1c9e2345b8ea82766a36aa0d21e276f696baa560c7f02a1e4b57f252b9998d1d8e8cf15a2ee1ace6cda520c242ba5e39462fd413b5cb8567
-  data.tar.gz: b41d13beb80bcc12238ed986a5c516f5c3d7ea38a5fd2be6e994c39bdf10ffa62c1c0ab023bf0307bdc74ffdc44ff30b7054aba84fce6a7197db7eb585f8ea96
+  metadata.gz: b7931f4110fe6090c93843a0c594d764d01c7f854bdd661aa3ab23daac4e38e5da9525d15960256e454fd6fa1f22269700bd6ff92ded603f2c4535acda223f37
+  data.tar.gz: 6d450ed73830940157be8354f95a38060e1a502ad441c5d04f4f4d884d1f9549fd192f4bd1ef0f4f89d1f7815afe50788f65b722dec71d3a83b10aaa6f8abcaf

data/README.ja.md

@@ -44,7 +44,7 @@ JLPT Gemは、日本語テキストの形態素解析、語彙および漢字の
 `Gemfile` に以下を追加してください:
 
 ```ruby
-gem 'jlpt', '~> 1.0.0'
+gem 'jlpt', '~> 1.1.0'
 ```
 
 その後、以下のコマンドを実行します:

data/lib/jlpt/analyzers/onomatopeia.rb

@@ -9,9 +9,15 @@ module JLPT
     ONOMATOPOEIA_PATTERNS = %w[
       どきどき わくわく ぺらぺら にこにこ ふわふわ ぎっしり
       ギリギリ イライラ キラキラ ドキドキ ニコニコ ペラペラ
-      もちもち すらすら どんどん だんだん いろいろ
+      もちもち すらすら どんどん だんだん いろいろ ぴったり
+      すっきり さっぱり のんびり うっとり がっかり しっかり
+      はっきり こっそり ゆっくり びっくり ばっちり めっきり
+      うろうろ ぶらぶら ごちゃごちゃ そわそわ すやすや ぐっすり
     ].freeze
 
+    # Regex for 2-mora repeated reduplicated patterns (ABAB)
+    REDUPLICATED_REGEX = /^(\p{Hiragana}{2}|\p{Katakana}{2})\1$/.freeze
+
     class << self
       # Extract onomatopoeia words from Japanese text
       #
@@ -22,6 +28,12 @@ module JLPT
         return [] if cleaned.empty?
 
         matches = ONOMATOPOEIA_PATTERNS.select { |word| cleaned.include?(word) }
+        morphemes = Tokenizer.lemmata(cleaned)
+
+        morphemes.each do |m|
+          matches << m if m.match?(REDUPLICATED_REGEX) && m.length == 4
+        end
+
         matches.uniq
       end
     end

data/lib/jlpt/analyzers/pitch_accent.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require 'json'
+
 module JLPT
   # Pitch Accent Profiler and Pattern Lookup.
   #
@@ -7,16 +9,9 @@ module JLPT
   # for Japanese vocabulary words.
   #
   module PitchAccent
-    # Built-in pitch accent database for common words
-    ACCENT_MAP = {
-      '学校' => { type: :odaka, pattern: 0 },
-      '私' => { type: :heiban, pattern: 0 },
-      '日本' => { type: :atamadaka, pattern: 1 },
-      '猫' => { type: :atamadaka, pattern: 1 },
-      '犬' => { type: :atamadaka, pattern: 2 },
-      '本' => { type: :atamadaka, pattern: 1 },
-      '先生' => { type: :nakadaka, pattern: 3 }
-    }.freeze
+    DATA_PATH = File.expand_path('../data/pitch_accent.json', __dir__)
+    MUTEX = Mutex.new
+    @dataset = nil
 
     class << self
       # Lookup pitch accent for a vocabulary word
@@ -26,7 +21,14 @@ module JLPT
       def accent_for(word)
         return nil if word.nil? || word.to_s.strip.empty?
 
-        ACCENT_MAP[word.to_s.strip] || { type: :heiban, pattern: 0 }
+        w = word.to_s.strip
+        dataset = load_dataset!
+
+        if dataset.key?(w)
+          { type: dataset[w]['type'].to_sym, pattern: dataset[w]['pattern'] }
+        else
+          { type: :heiban, pattern: 0 }
+        end
       end
 
       # Profile pitch accent patterns in Japanese text
@@ -46,6 +48,18 @@ module JLPT
         end
         result
       end
+
+      private
+
+      def load_dataset!
+        return @dataset if @dataset
+
+        MUTEX.synchronize do
+          return @dataset if @dataset
+
+          @dataset = File.exist?(DATA_PATH) ? JSON.parse(File.read(DATA_PATH)) : {}
+        end
+      end
     end
   end
 end

data/lib/jlpt/analyzers/simplifier.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require 'json'
+
 module JLPT
   # Text Simplifier and Beginner Synonym Recommender.
   #
@@ -7,16 +9,9 @@ module JLPT
   # N5/N4/N3 synonym alternatives for Japanese language learners.
   #
   module Simplifier
-    SIMPLIFICATIONS = {
-      '著しい' => { reading: 'いちじるしい', suggestions: %w[大きい 目立つ] },
-      '著しく' => { reading: 'いちじるしく', suggestions: %w[大きく 目立って] },
-      '未曽有' => { reading: 'みぞう', suggestions: %w[今までにない 初めての] },
-      '浸透' => { reading: 'しんとう', suggestions: %w[広がる 伝わる] },
-      '阻害' => { reading: 'そがい', suggestions: %w[邪魔する 妨げる] },
-      '急速' => { reading: 'きゅうそく', suggestions: %w[とても速い 急に] },
-      '懸念' => { reading: 'けねん', suggestions: %w[心配 不安] },
-      '普及' => { reading: 'ふきゅう', suggestions: %w[広まる みんなが使う] }
-    }.freeze
+    DATA_PATH = File.expand_path('../data/simplifications.json', __dir__)
+    MUTEX = Mutex.new
+    @dataset = nil
 
     class << self
       # Analyze text and return simplification suggestions for high-level words
@@ -27,7 +22,8 @@ module JLPT
         cleaned = Preprocessor.clean(text)
         return [] if cleaned.empty?
 
-        SIMPLIFICATIONS.filter_map do |word, data|
+        dataset = load_dataset!
+        dataset.filter_map do |word, data|
           build_suggestion(word, data) if cleaned.include?(word)
         end
       end
@@ -39,10 +35,20 @@ module JLPT
         {
           word: word,
           level: level,
-          reading: data[:reading],
-          suggestions: data[:suggestions]
+          reading: data['reading'],
+          suggestions: data['suggestions']
         }
       end
+
+      def load_dataset!
+        return @dataset if @dataset
+
+        MUTEX.synchronize do
+          return @dataset if @dataset
+
+          @dataset = File.exist?(DATA_PATH) ? JSON.parse(File.read(DATA_PATH)) : {}
+        end
+      end
     end
   end
 end

data/lib/jlpt/core/kanji_details.rb

@@ -1,23 +1,16 @@
 # frozen_string_literal: true
 
+require 'json'
+
 module JLPT
   # Kanji Details Inspector.
   #
-  # Provides stroke count, radical, On'yomi, Kun'yomi, English meanings, and JLPT levels for Kanji.
+  # Provides stroke count, radical, On'yomi, Kun'yomi, and JLPT levels for Kanji.
   #
   module KanjiDetails
-    KANJI_DATA = {
-      '私' => { character: '私', strokes: 7, radical: '禾', onyomi: %w[シ], kunyomi: %w[わたし], level: :n5 },
-      '学' => { character: '学', strokes: 8, radical: '子', onyomi: %w[ガク], kunyomi: %w[まな.ぶ], level: :n5 },
-      '校' => { character: '校', strokes: 10, radical: '木', onyomi: %w[コウ], kunyomi: [], level: :n5 },
-      '日' => { character: '日', strokes: 4, radical: '日', onyomi: %w[ニチ], kunyomi: %w[ひ], level: :n5 },
-      '本' => { character: '本', strokes: 5, radical: '木', onyomi: %w[ホン], kunyomi: %w[もと], level: :n5 },
-      '語' => { character: '語', strokes: 14, radical: '言', onyomi: %w[ゴ], kunyomi: %w[かた.る], level: :n5 },
-      '食' => { character: '食', strokes: 9, radical: '食', onyomi: %w[ショク], kunyomi: %w[た.べる], level: :n5 },
-      '飲' => { character: '飲', strokes: 12, radical: '食', onyomi: %w[イン], kunyomi: %w[の.む], level: :n5 },
-      '行' => { character: '行', strokes: 6, radical: '行', onyomi: %w[コウ], kunyomi: %w[い.く], level: :n5 },
-      '来' => { character: '来', strokes: 7, radical: '木', onyomi: %w[ライ], kunyomi: %w[く.る], level: :n5 }
-    }.freeze
+    DATA_PATH = File.expand_path('../data/kanji_details.json', __dir__)
+    MUTEX = Mutex.new
+    @dataset = nil
 
     class << self
       # Lookup Kanji details for a single character
@@ -30,8 +23,7 @@ module JLPT
         kanji_char = char.to_s.strip[0]
         return nil unless kanji_char.match?(/[\u4E00-\u9FFF]/)
 
-        level = Dictionary.kanji_level(kanji_char) || :out_of_jlpt
-        KANJI_DATA[kanji_char] || default_kanji_details(kanji_char, level)
+        fetch_details(kanji_char)
       end
 
       # Get details for all unique kanji in text
@@ -45,11 +37,43 @@ module JLPT
 
       private
 
+      def fetch_details(char)
+        dataset = load_dataset!
+        level = Dictionary.kanji_level(char) || :out_of_jlpt
+
+        if dataset.key?(char)
+          format_entry(dataset[char])
+        else
+          default_kanji_details(char, level)
+        end
+      end
+
+      def format_entry(entry)
+        {
+          character: entry['character'],
+          strokes: entry['strokes'],
+          radical: entry['radical'],
+          onyomi: entry['onyomi'],
+          kunyomi: entry['kunyomi'],
+          level: entry['level'].to_sym
+        }
+      end
+
+      def load_dataset!
+        return @dataset if @dataset
+
+        MUTEX.synchronize do
+          return @dataset if @dataset
+
+          @dataset = File.exist?(DATA_PATH) ? JSON.parse(File.read(DATA_PATH)) : {}
+        end
+      end
+
       def default_kanji_details(char, level)
         {
           character: char,
           strokes: 8,
-          radical: 'undefined',
+          radical: char,
           onyomi: [],
           kunyomi: [],
           level: level