cbeta 1.3.3 → 1.3.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 251ea030c514e75aa21cee73df8e765357f52e44
-  data.tar.gz: 4acc339dd5a48ac0f89e219b5d64042bfc58c3da
+  metadata.gz: adee183353751f8a74f171836a257f0259389791
+  data.tar.gz: 781dbd2f88fdb9f5358c01333215489623ed2461
 SHA512:
-  metadata.gz: e5a9c75960a0fed07d3aa660acaa72258089b9c5e35693a1fba84b91a614ea4bf962482893fee3f3b5a4d8bfeb47eebc6cbec5105b90099d9d3864a5cd474fe0
-  data.tar.gz: 2f90d55112deb33061f989eef400bb08cc6f12e141b1747c84da21f61be4ea1c72fc577c193dea22f69ea7858c0eda2cb471bb1154a2027450f7f7b256c38df7
+  metadata.gz: 59ce383bb2e3a054d8279abcc0f3e6fafc4b8c3f7850ddffdbb8ab7e25c0456922d75325881757e95d2554236bc2812a29394028edd09be29b4b5612c4b711fe
+  data.tar.gz: a37ab4e373efff9d964dbf0c1fd83b5225b114419e7adee793fa0fc0ca9d4df7b129b4342ed07e2a86a962cd2d149d3b0dd95c29b9a3074870635e5f2cd7e805

data/lib/cbeta.rb

@@ -31,6 +31,11 @@ class CBETA
     doc
   end
   
+  # 傳入 缺字碼，傳回 Unicode PUA 字元
+  def self.pua(gid)
+    [0xf0000 + gid[2..-1].to_i].pack 'U'
+  end
+  
   # 傳入 蘭札體 缺字碼，傳回 Unicode PUA 字元
   def self.ranjana_pua(gid)
     i = 0x10000 + gid[-4..-1].hex

data/lib/cbeta/gaiji.rb

@@ -6,6 +6,14 @@ class CBETA::Gaiji
   def initialize()
     fn = File.join(File.dirname(__FILE__), '../data/gaiji.json')
     @gaijis = JSON.parse(File.read(fn))
+    
+    @zzs = {}
+    @gaijis.each do |k,v|
+      if v.key? 'zzs'
+        zzs = v['zzs']
+        @zzs[zzs] = k
+      end
+    end
   end
 
   # 取得缺字資訊
@@ -51,6 +59,13 @@ class CBETA::Gaiji
     File.write(output_json_filename, s)
   end
   
+  # 傳入 組字式，取得 PUA
+  def zzs2pua(zzs)
+    return nil unless @zzs.key? zzs
+    gid = @zzs[zzs]
+    CBETA.pua(gid)
+  end
+  
   private
   
   def char_to_hash(char)

data/lib/cbeta/p5a_to_text.rb

@@ -25,13 +25,17 @@ class CBETA::P5aToText
   # @param format [String] 輸出格式，例：'app'
   # @option opts [String] :format 輸出格式，例：'app'，預設是 normal
   # @option opts [String] :encoding 輸出編碼，預設 'UTF-8'
+  # @option opts [String] :gaiji 缺字處理方式，預設 'default'
+  #   * 'PUA': 缺字一律使用 Unicode PUA
+  #   * 'default': 優先使用通用字
   def initialize(xml_root, output_root, opts={})
     @xml_root = xml_root
     @output_root = output_root
     
     @settings = {
       format: nil,
-      encoding: 'UTF-8'
+      encoding: 'UTF-8',
+      gaiji: 'default'
     }
     @settings.merge!(opts)
     
@@ -192,6 +196,13 @@ class CBETA::P5aToText
     # else
     #   Unicode PUA
     gid = e['ref'][1..-1]
+    
+    if @settings[:gaiji] == 'PUA'
+      return CBETA.siddham_pua(gid) if gid.start_with?('SD') # 悉曇字
+      return CBETA.ranjana_pua(gid) if gid.start_with?('RJ') # 蘭札體
+      return CBETA.pua(gid)
+    end
+    
     g = @gaijis[gid]
     abort "Line:#{__LINE__} 無缺字資料:#{gid}" if g.nil?
     zzs = g['zzs']

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cbeta
 version: !ruby/object:Gem::Version
-  version: 1.3.3
+  version: 1.3.4
 platform: ruby
 authors:
 - Ray Chou
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-12-04 00:00:00.000000000 Z
+date: 2015-12-07 00:00:00.000000000 Z
 dependencies: []
 description: Ruby gem for use Chinese Buddhist Text resources made by CBETA (http://www.cbeta.org).
 email: zhoubx@gmail.com