cbeta 1.1.15 → 1.1.16

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 84a0dbdb1f5f2be42922c7b7141d33549583599b
-  data.tar.gz: 55fbf7454a4da8b90e4f8776033e37101c938c64
+  metadata.gz: 96caf201945a8e525a455312cea612b569d13481
+  data.tar.gz: d5136a4f769b9ed10f23e78d65e96ba8ba781651
 SHA512:
-  metadata.gz: 59057ac310723e0217751c0c57a010c269ec09b7c1c1be02ea478ab2f2b890db6455e1a84c49bfbf9517d51a160618aae60b4b54f1570b6f76052ed9eb3a114f
-  data.tar.gz: a4aecb1d46a3068f689500b293b5ca7e0014c0ee281d98dc6d4f6552344dc5a11fc9684043d78e81921c601ab7075828ba31a102335a83b09afe3a40dad7356b
+  metadata.gz: b6bca7ac8a6f10024275360d7e15cc7b7bc16f81ff0c304cf3e24edff67e177c43990fea1b363f0976f9faa1aeb14c500c7582be9a596af7ef98a7792430d4d4
+  data.tar.gz: e2361d5614e1e6861aa27d9f38eb86543ef21accc59f777fefb0faad3a921aa6afe04e25c44cb5bf513e94b7960393f940334f7e3626d45e095bd818fe269511

data/lib/cbeta.rb

@@ -0,0 +1,111 @@
+# Ruby bools for access resources produced by CBETA 
+# (Chinese Buddhist Electronic Text Association, http://www.cbeta.org)
+#
+# 存取 CBETA 資源的 Ruby 工具
+
+require 'csv'
+
+class CBETA
+  # 將行首資訊轉為引用格式
+  #
+  # @param linehead [String] 行首資訊, 例如：T85n2838_p1291a03
+  # @return [String] 引用格式的出處資訊，例如：T85, no. 2838, p. 1291, a03
+  # 
+  # @example
+  #   CBETA.linehead_to_s('T85n2838_p1291a03')
+  #   # return "T85, no. 2838, p. 1291, a03"
+  def self.linehead_to_s(linehead)
+    linehead.match(/^([A-Z]\d+)n(.*)_p(\d+)([a-z]\d+)$/) {
+      return "#{$1}, no. #{$2}, p. #{$3}, #{$4}"
+    }
+    nil
+  end
+  
+  # 傳入 蘭札體 缺字碼，傳回 Unicode PUA 字元
+  def self.ranjana_pua(gid)
+    i = 0x10000 + gid[-4..-1].hex
+    [i].pack("U")
+  end
+  
+  # 傳入 悉曇字 缺字碼，傳回 Unicode PUA 字元
+  def self.siddham_pua(gid)
+    i = 0xFA000 + gid[-4..-1].hex
+    [i].pack("U")
+  end
+
+	# 載入藏經資料
+  def initialize()
+    fn = File.join(File.dirname(__FILE__), 'data/canons.csv')
+    text = File.read(fn)
+    @canon_abbr = {}
+    @canon_nickname = {}
+    CSV.parse(text, :headers => true) do |row|
+      id = row['id']
+      unless row['nickname'].nil?
+        @canon_nickname[id] = row['nickname']
+      end
+      next if row['abbreviation'].nil?
+    	next if row['abbreviation'].empty?
+      @canon_abbr[id] = row['abbreviation']
+    end
+    
+    fn = File.join(File.dirname(__FILE__), 'data/categories.json')
+    s = File.read(fn)
+    @categories = JSON.parse(s)
+  end
+
+  # @param id [String] 藏經 ID, 例如大正藏的 ID 是 "T"
+  # @return [String] 藏經短名，例如 "大正藏"
+	def get_canon_nickname(id)
+		return nil unless @canon_nickname.key? id
+		@canon_nickname[id]
+  end
+  
+  # 取得藏經略符
+  #
+  # @param id [String] 藏經 ID, 例如大正藏的 ID 是 "T"
+  # @return [String] 藏經略符，例如 "【大】"
+  #
+  # @example
+  #   cbeta = CBETA.new
+  #   cbeta.get_canon_symbol('T') # return "【大】"
+	def get_canon_symbol(id)
+		return nil unless @canon_abbr.key? id
+		@canon_abbr[id]
+	end
+  
+  # 取得藏經略名
+  #
+  # @param id [String] 藏經 ID, 例如大正藏的 ID 是 "T"
+  # @return [String] 藏經短名，例如 "大"
+  #
+  # @example
+  #   cbeta = CBETA.new
+  #   cbeta.get_canon_abbr('T') # return "大"
+	def get_canon_abbr(id)
+    r = get_canon_symbol(id)
+    return nil if r.nil?
+    r.sub(/^【(.*?)】$/, '\1')
+	end
+  
+  # 傳入經號，取得部類
+  # @param book_id [String] Book ID (經號), ex. "T0220"
+  # @return [String] 部類名稱，例如 "阿含部類"
+  #
+  # @example
+  #   cbeta = CBETA.new
+  #   cbeta.get_category('T0220') # return '般若部類'
+  def get_category(book_id)
+    @categories[book_id]
+  end
+end
+
+require 'cbeta/gaiji'
+require 'cbeta/bm_to_text'
+require 'cbeta/p5a_to_epub'
+require 'cbeta/p5a_to_html'
+require 'cbeta/p5a_to_html_for_every_edition'
+require 'cbeta/p5a_to_simple_html'
+require 'cbeta/p5a_to_text'
+require 'cbeta/p5a_validator'
+require 'cbeta/html_to_text'

data/lib/cbeta/p5a_to_epub.rb

@@ -90,6 +90,7 @@ class CBETA::P5aToEPUB
   #   c = CBETA::P5aToEPUB.new(TEMP, IMG)
   #   c.convert_folder('/Users/ray/Documents/Projects/D道安/xml-p5a/DA', '/temp/cbeta-epub/DA')
   def convert_folder(input_folder, output_folder)
+    puts "convert folder: #{input_folder} to #{output_folder}"
     @todo = {}
     
     # 先檢視整個資料夾，哪些是要多檔合一
@@ -168,12 +169,13 @@ class CBETA::P5aToEPUB
     
     title = @title
     book_id = @book_id
+    creator = @author
     builder = GEPUB::Builder.new {
       language 'zh-TW'
       unique_identifier "http://www.cbeta.org/#{book_id}", 'BookID', 'URL'
       title title
 
-      creator 'CBETA'
+      creator creator
 
       contributors 'DILA'
 
@@ -752,7 +754,7 @@ eos
     @current_nav = [@nav_root_ol]
     
     if @settings[:front_page_title]
-      @nav_root_ol.add_child("<li><a href='readme.xhtml'>編輯說明</a></li>")
+      @nav_root_ol.add_child("<li><a href='front.xhtml'>編輯說明</a></li>")
     end
     
     li = @nav_root_ol.add_child("<li><a href='#'>章節目次</a></li>").first
@@ -807,6 +809,8 @@ eos
     @title = traverse(e, 'txt')
     @title = @title.split()[-1]
     
+    @author = doc.at_xpath("//titleStmt/author").text
+    
     read_mod_notes(doc)
 
     root = doc.root()

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cbeta
 version: !ruby/object:Gem::Version
-  version: 1.1.15
+  version: 1.1.16
 platform: ruby
 authors:
 - Ray Chou
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-10-30 00:00:00.000000000 Z
+date: 2015-11-03 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
@@ -16,6 +16,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- lib/cbeta.rb
 - lib/cbeta/bm_to_text.rb
 - lib/cbeta/gaiji.rb
 - lib/cbeta/html_to_text.rb