jisho_sort 0.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: cd6b034701246bd87b1010e88382dd95ba9e72b237a286b984e941d049680a0a
+  data.tar.gz: d9b54a9eec95dd837973032562fcffd0a491e150e93a51eff18069f5d87bcf46
+SHA512:
+  metadata.gz: 98ec88fb0b147653349f057150cabf0fcde117d7a9dd1852a0b930129fcff5c7ebc23885538de110eeb6022556966aa7dcf97b3f913b399ad33531ac88384771
+  data.tar.gz: 5556bba3f0456cacec3ada3fecb68eb79850a3163f160baf92524945f38ef63875bda3b6777a2fdb48ede47073f064d0cf6b560162bbad6d6ab1f4cd95742ec6

data/README.md

@@ -0,0 +1,53 @@
+# jisho_sort
+
+`jisho_sort` is a Ruby sorting library based on MeCab.
+It provides functionality to sort Japanese strings containing a mix of Chinese and Japanese Letters in dictionary order.
+
+## Installation
+
+This code depends on MeCab, so you need to install MeCab.
+For more MeCab Install instructions, please refer to the [MeCab installation guide](https://taku910.github.io/mecab/#install).
+
+After installing MeCab, Add this line to Gemfile:
+
+```ruby
+gem 'jisho_sort'
+```
+
+And then execute:
+
+```sh
+bundle install
+```
+
+Or install it as:
+
+```sh
+gem install jisho_sort
+```
+
+## Usage
+
+Here's a basic example of how to use JishoSort:
+
+```ruby
+require 'jisho_sort'
+
+array = [
+  'ゆく川の流れは絶えずして、しかももとの水にあらず',
+  'メロスは激怒した',
+  '国境の長いトンネルを抜けると雪国であった'
+]
+```
+
+When you run this code, you will get the following result:
+
+```sh
+$ ruby sample.rb
+=> ["ゆく川の流れは絶えずして、しかももとの水にあらず", "メロスは激怒した", "国境の長いトンネルを抜けると雪国であった"]
+```
+
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/lib/jisho_sort/comparable.rb

@@ -0,0 +1,13 @@
+module JishoSort
+  module Comparable
+    # Compares the current string include chines and japanese character with another string based on their japanese pronunciation(furigana).
+    #
+    # @param other [String] The object to compare with.
+    # @return [Integer] Returns -1 if the current object's furigana is less than the other's, 0 if they are equal, and 1 if it is greater.
+    def compare_by_furigana(other)
+      raise ArgumentError unless other.instance_of?(String)
+
+      furigana <=> other.furigana
+    end
+  end
+end

data/lib/jisho_sort/enumerable.rb

@@ -0,0 +1,34 @@
+require 'jisho_sort/sortable'
+
+module Enumerable
+  include JishoSort::Sortable
+
+  # Sorts an array of strings using the Japanese pronunciation (dictionary)order.
+  # If a block is given, it sorts using the provided block.
+  #
+  # @yield [a, b] Optional block to customize the sorting logic.
+  # @yieldparam a [String] The first string to compare.
+  # @yieldparam b [String] The second string to compare.
+  # @return [Array<String>] The sorted array.
+  # @raise [ArgumentError] If no block is given and any element is not a String.
+  def jisho_sort(&block)
+    raise ArgumentError if block.nil? && !all? { |item| item.instance_of?(String) }
+
+    return sort { |a, b| a.compare_by_furigana(b) } if block.nil?
+
+    sort(&block)
+  end
+
+  # Sorts the elements of the enumerable based on the japanese pronunciation of the strings
+  # returned by the given block.
+  #
+  # @yield [item] Gives each element of the enumerable to the block.
+  # @yieldreturn [String] The string whose japanese pronunciation will be used for sorting.
+  # @return [Array] A new array with the elements sorted by the japanese pronunciation of the strings.
+  # @raise [ArgumentError] If any element does not yield a String.
+  def jisho_sort_by
+    raise ArgumentError unless all? { |item| yield(item).instance_of?(String) }
+
+    sort_by{ |item| yield(item).furigana }
+  end
+end

data/lib/jisho_sort/sortable.rb

@@ -0,0 +1,7 @@
+module JishoSort
+  module Sortable
+    def compare_by_furigana(other)
+      furigana <=> other.furigana
+    end
+  end
+end

data/lib/jisho_sort/string.rb

@@ -0,0 +1,7 @@
+require 'jisho_sort/tokenizable'
+require 'jisho_sort/comparable'
+
+class String
+  include JishoSort::Tokenizable
+  include JishoSort::Comparable
+end

data/lib/jisho_sort/tokenizable.rb

@@ -0,0 +1,46 @@
+require 'natto'
+
+module JishoSort
+  module Tokenizable
+    NATTO_KATAKANA_TYPE = 7
+    NATTO_FURIGANA_INDEX = 7
+
+    def furigana
+      tokenize
+    end
+
+    private
+
+    def tokenize
+      call_natto_parser
+    end
+
+    def call_natto_parser
+      strings = separate_ascii_string_from_others
+
+      # Extract the elements of furigana within this gem.
+      # When specifying a format in the argument of Natto::MeCab.new, the error `MECAB_NBEST request type is not set (Natto::MeCabError)` occurs.
+      nm = Natto::MeCab.new
+      memo = []
+      strings.each do |s|
+        next memo << s if s.ascii_only?
+
+        nm.parse(s) do |n|
+          next if n.is_eos?
+          next memo << n.surface if n.char_type == NATTO_KATAKANA_TYPE
+
+          n_furigana = n.feature.split(',')[NATTO_FURIGANA_INDEX]
+
+          memo << n_furigana
+        end
+      end
+
+      memo.join
+    end
+
+    def separate_ascii_string_from_others
+      chars.chunk_while { |s1, s2| s1.ascii_only? == s2.ascii_only? }
+           .map(&:join)
+    end
+  end
+end

data/lib/jisho_sort.rb

@@ -0,0 +1,5 @@
+require 'jisho_sort/string'
+require 'jisho_sort/enumerable'
+
+module JishoSort
+end

metadata

@@ -0,0 +1,73 @@
+--- !ruby/object:Gem::Specification
+name: jisho_sort
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+platform: ruby
+authors:
+- fvknk
+bindir: bin
+cert_chain: []
+date: 2025-02-24 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: ffi
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.9.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.9.0
+- !ruby/object:Gem::Dependency
+  name: natto
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Sort Japanese letters, including Chinese letters, in dictionary order.
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- README.md
+- lib/jisho_sort.rb
+- lib/jisho_sort/comparable.rb
+- lib/jisho_sort/enumerable.rb
+- lib/jisho_sort/sortable.rb
+- lib/jisho_sort/string.rb
+- lib/jisho_sort/tokenizable.rb
+homepage: https://github.com/fvknk
+licenses: []
+metadata:
+  rubygems_mfa_required: 'true'
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.6.2
+specification_version: 4
+summary: Sort Japanese letters in dictionary order.
+test_files: []