rubyrubi 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7cb77ba08c3b3dc229e661780995c5ab14642ded
-  data.tar.gz: 91061794091f1a8f75be1cb86474fae3434364df
+  metadata.gz: b005848f15f70889efb8ea6ab3fa98105e880721
+  data.tar.gz: 86f9fc910744efc2d59b0a9849b472add0277ee2
 SHA512:
-  metadata.gz: a81489f35977a484b9a99904bf1fa07394cd3c1e39d5798f1bffe308ac2c27ebe57c5aedb34307d0d53e723f5f4f1e0cf507ab1a95cbc7d7afbad1f0e17f4fc1
-  data.tar.gz: 6b29c681a67f9b066f0a8871c12a6ac2b68b9f88200ac2caa4720717e71c884cbf6003ad4b8266dfb5535527bfa3ef7e0ef22331f62da9232c01f334b9b8950d
+  metadata.gz: 033a61ebedf61ae3f2f2fe5dd762d9a8929f7bca7e25395a9ff045bb253ac20e9abdd3c9c99b1fad04a761454306ba352149970948b6a3708fc20a95f427cc45
+  data.tar.gz: ee1ce99f822b8de75a6d008a58ef5d6991e02139ab3c1615331957c18d6809c0c06432946b0127c53aede60826906cb02a07f765ff08d34fb8107143377d74ef

data/lib/rubyrubi/client.rb

@@ -9,6 +9,10 @@ module Rubyrubi
       parser = Parser::Base.new(result)
       parser.parse().join('')
     end
+
+    def tag(text, ruby)
+      Parser.ruby_tag(text, ruby)
+    end
   end
 end
 

data/lib/rubyrubi/parser/base.rb

@@ -1,15 +1,18 @@
 module Rubyrubi
   module Parser
-    KANJI = /^[一-龠]+/
-    OKURI = /[\p{hiragana}\p{katakana}ー〜]+$/
+    KANJI = /[一-龠]+/
+    OKURI = /[\p{hiragana}\p{katakana}ー＝〜・]+/
     KOMEI = /固名商品/
 
+    def self.ruby_tag(text, ruby)
+      "<ruby>#{text}<rp>（</rp><rt>#{ruby}</rt><rp>）</rp></ruby>"
+    end
+
     class Base
       def initialize(result)
         result = result.with_indifferent_access
         @result = result
         @original = result[:ResultSet][:ma_result][:word_list][:word]
-        #p @original
       end
 
       def parse()
@@ -20,34 +23,38 @@ module Rubyrubi
       end
 
       def add_rubi_and_okuri(word)
-        #p word
         if word['feature'] && word['feature'].scan(KOMEI).size > 0
           return word.clone
         end
 
-        kanji = word['surface'].scan(KANJI)[0]
-
-        if kanji == nil
-          return word.clone
-        end
+        kanji = word['surface'].scan(KANJI)
+        okuri = word['surface'].scan(OKURI)
+        yomi = '' + word['reading']
 
-        okuri = word['surface'].scan(OKURI)[0]
-        rubi = kanji == nil && okuri == nil ? nil
-          : word['reading'].gsub(Regexp.new("#{okuri}$"), '')
+        return word.clone if !kanji || kanji.size == 0
 
-        new_word = word.clone.merge({
-          'kanji' => kanji,
-          'okuri' => okuri,
-          'rubi' => rubi
-        })
-        new_word.keep_if { |k, v| v }
+        kanji.map.with_index do |k, i|
+          ret = { 'kanji' => k }
+          oku = okuri[i]
+          rubi = ''
+          if oku
+            ret.merge!({ 'okuri' => oku })
+            rubi = yomi.slice(0, yomi.index(oku))
+            yomi = yomi.slice(yomi.index(oku) + oku.length, yomi.length)
+          else
+            rubi = yomi
+          end
+          ret.merge!({ 'rubi' => rubi })
+        end
       end
 
       def create_markup(data)
-        data.map do |e, i|
-          if e['rubi']
-            "<ruby>#{e['kanji']}<rp>（</rp><rt>#{e['rubi']}</rt><rp>）</rp></ruby>#{e['okuri'] || ''}"
-          else
+        data.map.with_index do |e, i|
+          if e.class == Array
+            e.map do |r|
+              Parser.ruby_tag(r['kanji'], r['rubi']) << "#{r['okuri'] ? r['okuri'] : ''}"
+            end.join('')
+          elsif e['surface']
             "#{e['surface']}"
           end
         end

data/lib/rubyrubi/version.rb

@@ -1,3 +1,3 @@
 module Rubyrubi
-  VERSION = "0.2.0"
+  VERSION = "0.3.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rubyrubi
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - 110chang
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-02-08 00:00:00.000000000 Z
+date: 2016-02-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler