ruby-jdict 0.0.7 → 0.0.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b2236ff7f804ac1ade31ba8eb410d6a61c67a781
-  data.tar.gz: 2cd8e3132230029b547895cb0149f54861a91e3c
+  metadata.gz: f6e49f13e68f5f1a1f1421f9c814ce484a796da6
+  data.tar.gz: 726e6cae80ffd4da3041f5e1521f9f04a92c92f8
 SHA512:
-  metadata.gz: a016954bb6652c3822dfd5f4f720a4920e905ce4100027e89ca4c12a4571b60338b43dd65cdcd6eb40ed33c3c0bff3b1867d950d495cf932bd2f5cb45cdec7a5
-  data.tar.gz: aa5ba67f9b7ca1edaff47a702c765307e59044c4fba4ee30d010c4f78e199c895e5fcdd18eabe5f0dd46891345a07078bb470b3cc6690ec2ec3e2d337c2979eb
+  metadata.gz: cb7155746f0037ebe7a5f539766db87a9571d83b71a21a367872e150a149d3091c66bc4ace0c30e5e2f836fbd34799e702e2e49b287b0f38c2695eeb83f134dd
+  data.tar.gz: 9dc01e646e59e945691bdfb1098cb7afddd422120a5707f96160690e3f7401586c20ff5ba62d19079f7e3fff36254909751dc761a4b9fe1ceef53597368d471e

data/LICENSING

@@ -1,28 +1,28 @@
-Copyright (C) 2015 Ian Pickering
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions
-are met:
-
-1. Redistributions of source code must retain the above copyright
-   notice, this list of conditions and the following disclaimer.
-2. Redistributions in binary form must reproduce the above copyright
-   notice, this list of conditions and the following disclaimer in
-   the documentation and/or other materials provided with the
-   distribution.
-3. The name of the author may not be used to endorse or promote
-   products derived from this software without specific prior
-   written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE AUTHOR `AS IS'' AND ANY EXPRESS
-OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
-DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
-GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
-WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
-NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+Copyright (C) 2015 Ian Pickering
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions
+are met:
+
+1. Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+2. Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in
+   the documentation and/or other materials provided with the
+   distribution.
+3. The name of the author may not be used to endorse or promote
+   products derived from this software without specific prior
+   written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE AUTHOR `AS IS'' AND ANY EXPRESS
+OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
+DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
+GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

data/README.md

@@ -1,20 +1,18 @@
-# Ruby-JDict
-Ruby gem for accessing Jim Breen's Japanese dictionaries. Can currently access the following:
-  * JMdict (Japanese-English dictionary)
-
-*Note*: For the moment, uses SQLite (via [amalgalite](https://github.com/copiousfreetime/amalgalite)) for data storage. Not intended to be scalable.
-
-## Install
-```
-gem install ruby-jdict
-```
-
-## Usage
-See [this](https://github.com/Ruin0x11/ruby-jdict/blob/master/examples/query.rb) example for basic usage.
-
-If the dictionary file is not found, you will be prompted to download it.
-
-## Issues
-* The code for inserting Entry objects into the database is horrible. Should create multiple tables for each datatype instead of a single table for all datatypes.
-* Some routines need to be generalized to allow for the usage of dictionaries besides JMDict (like Tatoeba or KANJIDIC).
-* Many functions are getting too large/unreadable.
+# Ruby-JDict
+Ruby gem for accessing Jim Breen's Japanese dictionaries. Can currently access the following:
+  * JMdict (Japanese-English dictionary)
+
+*Note*: For the moment, uses SQLite (via [amalgalite](https://github.com/copiousfreetime/amalgalite)) for data storage. Not intended to be scalable.
+
+## Install
+```
+gem install ruby-jdict
+```
+
+## Usage
+See [this](https://github.com/Ruin0x11/ruby-jdict/blob/master/examples/query.rb) example for basic usage.
+
+## Issues
+* The code for inserting Entry objects into the database is horrible. Should create multiple tables for each datatype instead of a single table for all datatypes.
+* Some routines need to be generalized to allow for the usage of dictionaries besides JMDict (like Tatoeba or KANJIDIC).
+* Many functions are getting too large/unreadable.

data/Rakefile

@@ -1,30 +1,41 @@
-require 'rubygems'
-require 'rake'   #task runner
-
-INDEX_PATH  = 'index'
-JMDICT_PATH = 'dictionaries/JMdict'
-
-namespace :index do
-  
-  desc "Build the dictionary's search index"
-  task :build do
-    raise "Index already exists at path #{File.expand_path(INDEX_PATH)}" if File.exists? INDEX_PATH
-    @index = DictIndex.new(INDEX_PATH,
-                           JMDICT_PATH,
-                           false) # lazy_loadind? no. don't lazy load
-    puts "Index created at path #{File.expand_path(INDEX_PATH)}" if File.exists? INDEX_PATH
-    puts "Index with #{@index.size} entries."
-  end
-  
-  desc "Destroy the dictionary's search index"
-  task :destroy do
-    puts 'TODO: destory the index'
-    `sudo rm -R index`
-    # This will not work, because we don't have sudooooo.
-    # How do you delete folders in Ruby without sudo? Probably
-    # can't... that'd be more consistent actually.
-    # if File.exists? INDEX_PATH
-    #   File.delete INDEX_PATH
-    # end
-  end
-end
+require 'rubygems'
+require 'rake'   #task runner
+
+INDEX_PATH  = 'index'
+JMDICT_PATH = 'dictionaries/JMdict'
+
+namespace :index do
+  
+  desc "Build the dictionary's search index"
+  task :build do
+    raise "Index already exists at path #{File.expand_path(INDEX_PATH)}" if File.exists? INDEX_PATH
+    @index = DictIndex.new(INDEX_PATH,
+                           JMDICT_PATH,
+                           false) # lazy_loadind? no. don't lazy load
+    puts "Index created at path #{File.expand_path(INDEX_PATH)}" if File.exists? INDEX_PATH
+    puts "Index with #{@index.size} entries."
+  end
+  
+  desc "Destroy the dictionary's search index"
+  task :destroy do
+    puts 'TODO: destory the index'
+    `sudo rm -R index`
+    # This will not work, because we don't have sudooooo.
+    # How do you delete folders in Ruby without sudo? Probably
+    # can't... that'd be more consistent actually.
+    # if File.exists? INDEX_PATH
+    #   File.delete INDEX_PATH
+    # end
+  end
+end
+
+task :examples do
+  require_relative "lib/ruby-jdict.rb"
+  Dir['examples/*'].each do |example_file|
+    next if File.directory?(example_file)
+    puts "Running #{example_file}..."
+    puts
+
+    require_relative example_file
+  end
+end

data/examples/query.rb

@@ -1,22 +1,19 @@
-# -*- coding: utf-8 -*-
-require 'jdict'
-
-BASE_PATH   = ENV["HOME"]
-DICT_PATH   = File.join(BASE_PATH, '.dicts')
-
-JDict.configure do |config|
-  config.dictionary_path    = DICT_PATH                                  # directory containing dictionary files
-  config.language           = JDict::JMDictConstants::Languages::ENGLISH # language for search results
-  config.num_results        = 50                                         # maximum results to return from searching
-end
-
-dict = JDict::JMDict.new
-
-query = ARGV.pop.dup unless ARGV.empty?
-query ||= "日本語"
-
-results = dict.search(query)
-results.each do |entry|
-  puts entry.to_s
-  puts
-end
+# -*- coding: utf-8 -*-
+require 'ruby-jdict'
+
+DICT_PATH = File.join(ENV["HOME"], '.dicts')
+
+dict = JDict::Dictionary.new(DICT_PATH)
+dict.build_index!
+
+query = ARGV.pop.dup unless ARGV.empty?
+query ||= "日本語"
+
+puts "Searching for \"#{query}\"."
+puts
+
+results = dict.search(query)
+results.each do |entry|
+  puts entry.to_s
+  puts
+end

data/lib/ruby-jdict.rb

@@ -0,0 +1,14 @@
+require "ruby-jdict/dictionary"
+require "ruby-jdict/constants"
+require "ruby-jdict/convert"
+require "ruby-jdict/dictionary"
+require "ruby-jdict/index"
+require "ruby-jdict/jdict"
+require "ruby-jdict/version"
+
+require "ruby-jdict/indexer/dictionary_indexer"
+#require "ruby-jdict/indexer/libxml_dictionary_indexer"
+require "ruby-jdict/indexer/nokogiri_dictionary_indexer"
+
+require "ruby-jdict/models/entry"
+require "ruby-jdict/models/sense"

data/lib/{constants.rb → ruby-jdict/constants.rb}

@@ -1,64 +1,73 @@
-# Constants and descriptions for important elements/attributes
-# of the JMdict XML dictionary.                               
-# Descriptions come from JMdict.dtd (document type definition)
-module JDict
-  module JMDictConstants
-    
-    # TODO: change these strings to symbols ?
-    # XML elements of the JMDict file
-    module Elements
-      # Entries consist of kanji elements, kana elements, 
-      # general information and sense elements. Each entry must have at 
-      # least one kana element and one sense element. Others are optional.
-      ENTRY          = 'entry'
-      SEQUENCE       = 'ent_seq'
-
-      # This element will contain a word or short phrase in Japanese 
-      # which is written using at least one kanji. The valid characters are
-      # kanji, kana, related characters such as chouon and kurikaeshi, and
-      # in exceptional cases, letters from other alphabets.
-      KANJI          = 'keb'
-
-      # This element content is restricted to kana and related
-      # characters such as chouon and kurikaeshi. Kana usage will be
-      # consistent between the keb and reb elements; e.g. if the keb
-      # contains katakana, so too will the reb.
-      KANA           = 'reb'
-
-      # The sense element will record the translational equivalent
-      # of the Japanese word, plus other related information. Where there
-      # are several distinctly different meanings of the word, multiple
-      # sense elements will be employed.
-      SENSE          = 'sense'
-
-      # Part-of-speech information about the entry/sense. Should use 
-      # appropriate entity codes.
-      PART_OF_SPEECH = 'pos'
-
-      # Within each sense will be one or more "glosses", i.e. 
-      # target-language words or phrases which are equivalents to the 
-      # Japanese word. This element would normally be present, however it 
-      # may be omitted in entries which are purely for a cross-reference.
-      GLOSS          = 'gloss'
-
-      CROSSREFERENCE = 'xref'
-    end
-    
-    # Constants for selecting the search language.   
-    # Used in the "gloss" element's xml:lang attribute.
-    #   :eng never appears as a xml:lang constant because gloss is assumed to be English when not specified
-    #   :jpn never appears as a xml:lang because the dictionary itself pivots around Japanese
-    module Languages
-      JAPANESE  = :jpn
-      ENGLISH   = :eng
-      DUTCH     = :dut
-      FRENCH    = :fre
-      GERMAN    = :ger
-      RUSSIAN   = :rus
-      SPANISH   = :spa
-      SLOVENIAN = :slv
-      SWEDISH   = :swe
-      HUNGARIAN = :hun
-    end
-  end
-end
+# Constants and descriptions for important elements/attributes
+# of the JMdict XML dictionary.
+# Descriptions come from JMdict.dtd (document type definition)
+module JDict
+  module JMDictConstants
+    # TODO: change these strings to symbols ?
+    # XML elements of the JMDict file
+    module Elements
+      # Entries consist of kanji elements, kana elements,
+      # general information and sense elements. Each entry must have at
+      # least one kana element and one sense element. Others are optional.
+      ENTRY          = 'entry'
+      SEQUENCE       = 'ent_seq'
+
+      # This element will contain a word or short phrase in Japanese
+      # which is written using at least one kanji. The valid characters are
+      # kanji, kana, related characters such as chouon and kurikaeshi, and
+      # in exceptional cases, letters from other alphabets.
+      KANJI          = 'keb'
+
+      # This element content is restricted to kana and related
+      # characters such as chouon and kurikaeshi. Kana usage will be
+      # consistent between the keb and reb elements; e.g. if the keb
+      # contains katakana, so too will the reb.
+      KANA           = 'reb'
+
+      # The sense element will record the translational equivalent
+      # of the Japanese word, plus other related information. Where there
+      # are several distinctly different meanings of the word, multiple
+      # sense elements will be employed.
+      SENSE          = 'sense'
+
+      # Part-of-speech information about the entry/sense. Should use
+      # appropriate entity codes.
+      PART_OF_SPEECH = 'pos'
+
+      # Within each sense will be one or more "glosses", i.e.
+      # target-language words or phrases which are equivalents to the
+      # Japanese word. This element would normally be present, however it
+      # may be omitted in entries which are purely for a cross-reference.
+      GLOSS          = 'gloss'
+
+      CROSSREFERENCE = 'xref'
+    end
+
+    # Constants for selecting the search language.
+    # Used in the "gloss" element's xml:lang attribute.
+    #   :eng never appears as a xml:lang constant because gloss is assumed to be English when not specified
+    #   :jpn never appears as a xml:lang because the dictionary itself pivots around Japanese
+    module Languages
+      JAPANESE  = :jpn
+      ENGLISH   = :eng
+      DUTCH     = :dut
+      FRENCH    = :fre
+      GERMAN    = :ger
+      RUSSIAN   = :rus
+      SPANISH   = :spa
+      SLOVENIAN = :slv
+      SWEDISH   = :swe
+      HUNGARIAN = :hun
+    end
+
+    LANGUAGE_DEFAULT = Languages::ENGLISH
+  end
+
+  # Used when serializing entries to SQL.
+  module SerialConstants
+    LANGUAGE_SENTINEL = '&&'
+    MEANING_SENTINEL = '**'
+    PART_OF_SPEECH_SENTINEL = '$$'
+    SENSE_SENTINEL = '%%'
+  end
+end

data/lib/ruby-jdict/convert.rb

@@ -0,0 +1,33 @@
+# coding: utf-8
+module JDict
+  module Convert
+    HANKAKU_KATAKANA = "ﾊﾋﾌﾍﾎｳｶｷｸｹｺｻｼｽｾｿﾀﾁﾂﾃﾄｱｲｴｵﾅﾆﾇﾈﾉﾏﾐﾑﾒﾓﾔﾕﾖﾗﾘﾙﾚﾛﾜｦﾝｧｨｩｪｫｬｭｮｯ"
+    HANKAKU_VSYMBOLS= { '' => 0, 'ﾞ' => 1, 'ﾟ' => 2 }
+    ZENKAKU_KATAKANA = [
+      'ハヒフヘホウカキクケコサシスセソタチツテトアイエオ'+
+      'ナニヌネノマミムメモヤユヨラリルレロワヲンァィゥェォャュョッ',
+      'バビブベボヴガギグゲゴザジズゼゾダヂヅデド',
+      'パピプペポ']
+
+
+    def self.han_to_zen(term)
+      term.gsub!(/([ｦ-ｯｱ-ﾝ])([ﾞﾟ]?)/) do
+        katakana = $1
+        sym = $2
+        index = HANKAKU_VSYMBOLS[sym]
+        pos = HANKAKU_KATAKANA.index(katakana)
+        ZENKAKU_KATAKANA[index][pos] || ZENKAKU_KATAKANA[0][pos]
+      end
+    end
+
+    def self.fullwidth_kata_to_hira(term)
+      term.tr!('ァ-ン','ぁ-ん')
+    end
+
+    def self.kata_to_hira(term)
+      term = han_to_zen(term)
+      term = fullwidth_kata_to_hira(term)
+      term
+    end
+  end
+end

data/lib/ruby-jdict/dictionary.rb

@@ -0,0 +1,59 @@
+module JDict
+  class Dictionary
+    def initialize(path)
+      @dictionary_path = File.join(path, self.dict_file)
+      @entries = []
+
+      @index = DictIndex.new(@dictionary_path)
+    end
+
+    def size
+      @entries.size
+    end
+
+    def build_index!
+      @index.build_index!
+    end
+
+    def loaded?
+      @index.built?
+    end
+
+    def dict_file
+      "JMDict"
+    end
+
+    # Search this dictionary's index for the given string.
+    # @param query [String] the search query
+    # @return [Array(Entry)] the results of the search
+    def search(query, opts = {})
+      opts = opts.merge(default_search_options)
+
+      results = []
+      return results if query.empty?
+
+      results = @index.search(query, opts)
+    end
+
+    # Retrieves the definition of a part-of-speech from its abbreviation
+    # @param pos [String] the abbreviation for the part-of-speech
+    # @return [String] the full description of the part-of-speech
+    def get_pos(pos)
+      @index.get_pos(pos)
+    end
+
+    def delete!
+      @index.delete!
+    end
+
+    private
+
+    def default_search_options
+      {
+       max_results: 50,
+       language: JMDictConstants::LANGUAGE_DEFAULT,
+       exact: false,
+      }
+    end
+  end
+end