cbeta 0.6.1 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 20467d7b166bf2c6daf7ec2a174472ba7cbd6a56
-  data.tar.gz: efcbf9c7d8c3cf5d71b371d0ef0745c6d3988466
+  metadata.gz: e7b3afd9fe14f3c71a3f519aa0a15dc5b2e198ab
+  data.tar.gz: 898fddd049d4f076edb446c6f2751a10e41e248e
 SHA512:
-  metadata.gz: 41b01556ca22270c458d806a0b45833d4eb64b0c38d64110a39232e09dc925d3c5081fd382f75da4857d3c05177250541a03c22d5236ea1c799ee73a33fcdec7
-  data.tar.gz: b4081c2d5e1f68a26072eba3409bd12372c28765487c8e12217a7e9c7389a1bf002e42af63c10a267e4dde7a87c4537654a5b146506d50263ec09b6a6842ddc0
+  metadata.gz: bd71006daf93b24dc46bd1afe004d1726cc6ef0b6de6159357ec01a3c255e732642f551037ffc8dc05be7e2997599bbb2ca015dcbc05bc497c029c903a0fca3c
+  data.tar.gz: f860ffec038a6924de638861a46e94c8bcb325a8114fb00aad19f898036c2722657229e4b25f83ac8b19143f65b100212041f4e51a95c3a208f632e163f7c276

data/lib/cbeta.rb

@@ -52,11 +52,25 @@ class CBETA
   #
   # @example
   #   cbeta = CBETA.new
-  #   cbeta.get_canon_abbr('T') # return "【大】"
-	def get_canon_abbr(id)
+  #   cbeta.get_canon_symbol('T') # return "【大】"
+	def get_canon_symbol(id)
 		return nil unless @canon_abbr.key? id
 		@canon_abbr[id]
 	end
+  
+  # 取得藏經略名
+  #
+  # @param id [String] 藏經 ID, 例如大正藏的 ID 是 "T"
+  # @return [String] 藏經短名，例如 "大"
+  #
+  # @example
+  #   cbeta = CBETA.new
+  #   cbeta.get_canon_abbr('T') # return "大"
+	def get_canon_abbr(id)
+    r = get_canon_symbol(id)
+    return nil if r.nil?
+    r.sub(/^【(.*?)】$/, '\1')
+	end
 end
 
 require 'cbeta/gaiji'

data/lib/cbeta/gaiji.rb

@@ -37,10 +37,65 @@ class CBETA::Gaiji
   # @return [Array<String>]
   #
   # @example
-  #   g = Cbeta::Gaiji.new
+  #   g = CBETA::Gaiji.new
   #   g.zhuyin("CB00023") # return [ "ㄍㄢˇ", "ㄍㄢ", "ㄧㄤˊ", "ㄇㄧˇ", "ㄇㄧㄝ", "ㄒㄧㄤˊ" ]
   def zhuyin(cb)
   	return nil unless @gaijis.key? cb
     @gaijis[cb]['zhuyin']
   end
+  
+  # 讀 XML P5 檔頭的缺字資料，更新現有缺字資料，輸出 JSON
+  def update_from_p5(p5_folder, output_json_filename)
+    update_from_p5_folder(p5_folder)
+    s = JSON.pretty_generate(@gaijis)
+    File.write(output_json_filename, s)
+  end
+  
+  private
+  def char_to_hash(char)
+    r = {}
+    id = char['id']
+    char.xpath('charProp').each do |e|
+      prop = e.at('localName').text
+      case prop
+      when 'composition'
+        r['zzs'] = e.at('value').text
+      when 'normalized form'
+        r['normal'] = e.at('value').text
+      else
+        puts "未處理 charProp/localName: #{prop}"
+      end
+    end
+    char.xpath('mapping').each do |e|
+      case e['type']
+      when 'unicode'
+        u = e.text[2..-1]
+        r['unicode'] = u
+        r['unicode-char'] = [u.hex].pack('U')
+      end
+    end
+    r
+  end
+  
+  def update_from_p5_file(fn)
+    f = File.open(fn)
+    doc = Nokogiri::XML(f)
+    f.close
+    doc.remove_namespaces!()
+    doc.xpath("//charDecl/char").each do |char|
+      @gaijis[char['id']] = char_to_hash(char)
+    end
+  end
+  
+  def update_from_p5_folder(folder)
+    Dir.entries(folder).each do |f|
+      path = File.join(folder, f)
+      next if f.start_with? '.'
+      if Dir.exist? path
+        update_from_p5_folder path
+      else
+        update_from_p5_file path
+      end
+    end
+  end
 end

data/lib/cbeta/p5a_to_epub.rb

@@ -323,14 +323,6 @@ eos
     abort "Line:#{__LINE__} 無缺字資料:#{gid}" if g.nil?
     zzs = g['zzs']
     
-    if mode == 'txt'
-      return g['roman'] if gid.start_with?('SD')
-      if zzs.nil?
-        abort "缺組字式：#{g}"
-      else
-        return zzs
-      end
-    end
 
     if gid.start_with?('SD')
       case gid
@@ -339,14 +331,43 @@ eos
       when 'SD-E35B'
         return '）'
       else
-        return g['roman']
+        return g['roman'] if g.key? 'roman'
+        
+        if mode == 'txt'
+          puts "警告：純文字模式出現悉曇字：#{gid}"
+          return gid
+        else
+          # 如果沒有羅馬轉寫就顯示圖檔
+          src = File.join(@settings[:graphic_base], 'sd-gif', gid[3..4], gid+'.gif')
+          basename = File.basename(src)
+          dest = File.join(@temp_folder, 'img', basename)
+          FileUtils.copy(src, dest)    
+          return "<img src='../img/#{basename}' />"
+        end
       end
     end
     
     if gid.start_with?('RJ')
-      return g['roman']
+      return g['roman'] if g.key? 'roman'
+      
+      if mode == 'txt'
+        puts "警告：純文字模式出現蘭札體：#{gid}"
+        return gid
+      else
+        # 如果沒有羅馬轉寫就顯示圖檔
+        src = File.join(@settings[:graphic_base], 'rj-gif', gid[3..4], gid+'.gif')
+        basename = File.basename(src)
+        dest = File.join(@temp_folder, 'img', basename)
+        FileUtils.copy(src, dest)    
+        return "<img src='../img/#{basename}' />"
+      end
     end
-   
+    
+    if mode == 'txt'
+      abort "缺組字式：#{g}" if zzs.nil?
+      return zzs
+    end
+    
     default = ''
     if g.has_key?('unicode')
       if @unicode1.include?(g['unicode'])
@@ -359,7 +380,7 @@ eos
 
   def handle_graphic(e)
     url = e['url']
-    url.sub!(/^.*figures\/(.*)$/, '\1')
+    url.sub!(/^.*(figures\/.*)$/, '\1')
     
     src = File.join(@settings[:graphic_base], url)
     basename = File.basename(src)
@@ -516,6 +537,7 @@ eos
     return '' if e.comment?
     return handle_text(e, mode) if e.text?
     return '' if PASS.include?(e.name)
+
     r = case e.name
     when 'anchor'    then handle_anchor(e)
     when 'app'       then handle_app(e)

data/lib/cbeta/p5a_to_text.rb

@@ -15,6 +15,10 @@ require 'set'
 #   c.convert('T01')
 #
 class CBETA::P5aToText
+  # 內容不輸出的元素
+  PASS=['back', 'teiHeader']
+  
+  private_constant :PASS
 
   # @param xml_root [String] 來源 CBETA XML P5a 路徑
   # @param output_root [String] 輸出 Text 路徑
@@ -444,7 +448,7 @@ class CBETA::P5aToText
   def handle_vol(vol)
     puts "convert volumn: #{vol}"
 
-    @orig = @cbeta.get_canon_abbr(vol[0])
+    @orig = @cbeta.get_canon_symbol(vol[0])
     abort "未處理底本" if @orig.nil?
 
     @vol = vol
@@ -508,7 +512,11 @@ class CBETA::P5aToText
       text = frag.content
       text = appify(text) if @format == 'app'
 
-      fn = "#{ed}.txt"
+      if ed == @orig
+        fn = "#{ed}-orig.txt"
+      else
+        fn = "#{ed}.txt"
+      end
       output_path = File.join(folder, fn)
       File.write(output_path, text)
     end

data/lib/data/gaiji.json

@@ -50,10 +50,7 @@
   "CB00178": {
     "zzs": "[木*奈]",
     "unicode": "3B88",
-    "unicode-char": "㮈",
-    "zhuyin": [
-      "ㄋㄞˋ"
-    ]
+    "unicode-char": "㮈"
   },
   "CB00238": {
     "zzs": "[打-丁+毛]",
@@ -107,10 +104,7 @@
     "zzs": "[馬*犬]",
     "normal": "馱",
     "unicode": "4B7E",
-    "unicode-char": "䭾",
-    "zhuyin": [
-      "ㄊㄨㄛˊ"
-    ]
+    "unicode-char": "䭾"
   },
   "CB00509": {
     "zzs": "[商/衣]",
@@ -2933,8 +2927,7 @@
   },
   "CB04775": {
     "zzs": "[柷-口+登]",
-    "normal": "凳",
-    "normal_unicode": "櫈"
+    "normal": "凳"
   },
   "CB00144": {
     "zzs": "[少/免]",
@@ -3403,10 +3396,7 @@
   "CB05105": {
     "zzs": "[契-大+石]",
     "unicode": "40AE",
-    "unicode-char": "䂮",
-    "zhuyin": [
-      "ㄌㄩㄝˋ"
-    ]
+    "unicode-char": "䂮"
   },
   "SD-CFC5": {
     "sd-char": "狣",
@@ -42271,10 +42261,7 @@
   "CB06535": {
     "zzs": "[自/本]",
     "unicode": "2690E",
-    "unicode-char": "𦤎",
-    "zhuyin": [
-      "ㄍㄠ"
-    ]
+    "unicode-char": "𦤎"
   },
   "CB06952": {
     "zzs": "[狂-王+羊]",
@@ -45192,11 +45179,7 @@
   "CB05711": {
     "zzs": "[颱-台+日]",
     "unicode": "4AFB",
-    "unicode-char": "䫻",
-    "zhuyin": [
-      "ㄒㄩㄝˊ",
-      "ㄩˋ"
-    ]
+    "unicode-char": "䫻"
   },
   "CB15400": {
     "zzs": "[身*國]",
@@ -49191,11 +49174,7 @@
     "zzs": "[仁-二+嶲]",
     "normal": "俊",
     "unicode": "349E",
-    "unicode-char": "㒞",
-    "zhuyin": [
-      "ㄐㄩㄣˋ",
-      "ㄎㄜˇ"
-    ]
+    "unicode-char": "㒞"
   },
   "CB13910": {
     "zzs": "[打-丁+閵]"
@@ -126184,5 +126163,72 @@
       "ㄅㄧㄣˇ",
       "ㄌㄧㄣˇ"
     ]
+  },
+  "CB32783": {
+    "zzs": "[(糸*子)/心]"
+  },
+  "CB32784": {
+    "zzs": "[受-又+(撤-育)]"
+  },
+  "CB32785": {
+    "zzs": "[烈-列+((白/匕)*旡)]"
+  },
+  "CB32781": {
+    "zzs": "[虫*雷]",
+    "unicode": "274BD",
+    "unicode-char": "𧒽"
+  },
+  "CB32792": {
+    "zzs": "[番*韭]",
+    "unicode": "2940F",
+    "unicode-char": "𩐏"
+  },
+  "CB32793": {
+    "zzs": "[米*(產-文+(立-一))]"
+  },
+  "CB32821": {
+    "zzs": "[入/耳]",
+    "normal": "聞",
+    "unicode": "26535",
+    "unicode-char": "𦔵"
+  },
+  "CB32825": {
+    "zzs": "[舟*定]",
+    "unicode": "26A58",
+    "unicode-char": "𦩘"
+  },
+  "CB32828": {
+    "zzs": "[打-丁+審]",
+    "unicode": "22E19",
+    "unicode-char": "𢸙"
+  },
+  "CB32832": {
+    "zzs": "[卄/(袖-由+任)]"
+  },
+  "CB32830": {
+    "zzs": "[烈-列+毛]",
+    "unicode": "241AC",
+    "unicode-char": "𤆬"
+  },
+  "CB32983": {
+    "zzs": "[雨/如]",
+    "unicode": "290B0",
+    "unicode-char": "𩂰"
+  },
+  "CB32984": {
+    "zzs": "[貝*昜]",
+    "normal": "賜",
+    "unicode": "27DBD",
+    "unicode-char": "𧶽"
+  },
+  "CB32985": {
+    "zzs": "[怡-台+志]",
+    "unicode": "2267A",
+    "unicode-char": "𢙺"
+  },
+  "CB32986": {
+    "zzs": "[棣-木+王]",
+    "unicode": "3ED6",
+    "unicode-char": "㻖"
   }
 }

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cbeta
 version: !ruby/object:Gem::Version
-  version: 0.6.1
+  version: 1.0.0
 platform: ruby
 authors:
 - Ray Chou
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-09-11 00:00:00.000000000 Z
+date: 2015-09-24 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