cbeta 3.7.0 → 3.7.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 22ece655cfcd0c962034b74bd4bb530a21f034422b183540588965eda67b7fb7
-  data.tar.gz: c1ea4749573d1eaee1f6635dcd1c8c2b818f94a13f9075e8ddde39b96baa3946
+  metadata.gz: 39eb1f61afb89d24ea315ae9d8e2e97f65dc832d93c54379a3bc06e1aed0fa4c
+  data.tar.gz: e405963de32214ab99964b8450f8cdbe1f1c559c99e0315369e49a6a2ebad241
 SHA512:
-  metadata.gz: df5dca4c13c0e1be0d8142145685b350d0773073b3f8fe378d68e67ce49f7eae24f12f455d0d74bb2c5c91dcb4c7fa28576d31cc5da44d43ee854878d4903cac
-  data.tar.gz: 73dacb3d58b47812309f6f16c9b11c30407cd0b9ff390d6648bba89b91b5a2d10366ea4283888e3f4ffc1fa6536a5633e93c8b91c9765d9607669f49c05a7452
+  metadata.gz: a54a5e8928f796f059f704db993671603b63bc3ae84e089ad049df1766e4f8ae197697d9f5747e7a050634c00b3ba8a15be6390b9cdccafb2eb5226025c32eff
+  data.tar.gz: aeebdf68c165c9b2fb4c7b9864e8aa319fed4b2abd5b38ce387b3678d354c21ed20f92e444db2430d5b628c6e61363d2310b68db40771bbb18f77730554b68f3

data/lib/cbeta/p5a_checker.rb

@@ -17,6 +17,7 @@ require_relative 'cbeta_share'
 #   * [E12] note 直接出現在 lg 下
 #   * [E13] tt 直接出現在 lg 下
 #   * [E14] <anchor type="right"> 不應直接出現在 div 或 body 下
+#   * [E15] <note> corresp 無對應的 <note>
 #
 # * 警告類型
 #   * [W01] 夾注包夾注
@@ -33,7 +34,7 @@ class CBETA::P5aChecker
     @xml_root = xml_root
     @figures = figures
     @log = log
-    @errors = ''
+    @errors = []
     @g_errors = {}
   end
   
@@ -118,17 +119,17 @@ class CBETA::P5aChecker
   def display_errors
     @g_errors.keys.sort.each do |k|
       s = @g_errors[k].to_a.join(',')
-      @errors << "#{k} 無缺字資料，出現於：#{s}\n"
+      @errors << "#{k} 無缺字資料，出現於：#{s}"
     end
     
     if @errors.empty?
       puts "檢查完成，未發現錯誤。"
     elsif @log.nil?
-      puts "發現錯誤："
-      puts @errors
+      puts "發現 #{@errors.size} 錯誤："
+      puts @errors.join("\n")
     else
-      File.write(@log, @errors)
-      puts "發現錯誤，請查看 #{@log}"
+      File.write(@log, @errors.join("\n"))
+      puts "發現 #{@errors.size} 錯誤，請查看 #{@log}"
     end
   end
 
@@ -197,13 +198,9 @@ class CBETA::P5aChecker
   end
 
   def e_note(e)
-    if e.parent.name == 'div'
-      error "[E11] note 直接出現在 div 下"
-    end
-    
-    if e.parent.name == 'lg'
-      error "[E12] note 直接出現在 lg 下"
-    end
+    error "[E11] note 直接出現在 div 下" if e.parent.name == 'div'    
+    error "[E12] note 直接出現在 lg 下" if e.parent.name == 'lg'
+    e_note_corresp(e) if e.key?('corresp')
 
     unless e['place'] == 'inline'
       traverse(e)
@@ -213,11 +210,18 @@ class CBETA::P5aChecker
     if @element_stack.include?('inline_note')
       error "[W01] 夾注包夾注"
     end
+
     @element_stack << 'inline_note'
     traverse(e)
     @element_stack.pop
   end
 
+  def e_note_corresp(e)
+    n = e['corresp'].delete_prefix('#')
+    return if @notes.include?(n)
+    error "[E15] note corresp #{n} 無對應 note"
+  end
+
   def e_p(e)
     if e.parent.name == 'list'
       error "[E10] p 不應直接出現在 list 下"
@@ -261,8 +265,8 @@ class CBETA::P5aChecker
   end
 
   def error(msg)
-    s = "#{msg}, #{@basename}, lb: #{@lb}\n"
-    print s
+    s = "#{msg}, #{@basename}, lb: #{@lb}"
+    puts "\n#{s}"
     @errors << s
   end
   
@@ -281,7 +285,7 @@ class CBETA::P5aChecker
 
     s = File.read(fn)
     if s.include? "\u200B"
-      @errors << "#{@basename} 含有 U+200B Zero Width Space 字元\n"
+      @errors << "#{@basename} 含有 U+200B Zero Width Space 字元"
     end
     
     doc = Nokogiri::XML(s)
@@ -292,7 +296,7 @@ class CBETA::P5aChecker
       @element_stack = []
       traverse(doc.root)
     else
-      @errors << "錯誤: #{@basename} not well-formed\n"
+      @errors << "錯誤: #{@basename} not well-formed"
     end
   end
 
@@ -315,7 +319,7 @@ class CBETA::P5aChecker
   end
   
   def handle_vol(folder)
-    puts "check vol: #{File.basename(folder)}"
+    print "\rcheck vol: #{File.basename(folder)}  "
     Dir.entries(folder).sort.each do |f|
       next if f.start_with? '.'
       path = File.join(folder, f)

data/lib/cbeta.rb

@@ -6,8 +6,8 @@
 require 'csv'
 
 class CBETA
-  CANON = 'CC|DA|GA|GB|LC|TX|ZS|ZW|[A-Z]'
-  SORT_ORDER = %w(T X A K S F C D U P J L G M N ZS I ZW B GA GB Y LC TX CC)
+  CANON = 'CC|DA|GA|GB|LC|TX|YP|ZS|ZW|[A-Z]'
+  SORT_ORDER = %w(T X A K S F C D U P J L G M N ZS I ZW B GA GB Y LC TX YP CC)
   VOL3 = %w[A CC C G GA GB L M P U]
   DATA = File.join(File.dirname(__FILE__), 'data')
   PUNCS = ',.()[] 。‧．，、；？！：︰／（）「」『』《》＜＞〈〉〔〕［］【】〖〗〃…—─　～│┬▆△＊＋－＝'
@@ -47,6 +47,8 @@ class CBETA
   # @param lb[String] 例如 "0001a01" 或 "0757b29"
   # @return [String] CBETA 行首資訊，例如 "T01n0001_p0001a01" 或 "T25n1510ap0757b29"
   def self.get_linehead(file_basename, lb)
+    return nil if file_basename.nil?
+    
     if file_basename.match(/^(T\d\dn0220)/)
       r = $1
     else

data/lib/data/canons.csv

@@ -24,6 +24,7 @@ TX,太虛大師全書,Corpus of Venerable Tai Xu's Buddhist Studies,太虛全書
 U,洪武南藏,Southern Hongwu Edition of the Canon,初刻南藏,【洪武】,,成都: 四川省佛教協會,1999
 X,卍新纂大日本續藏經,Manji Shinsan Dainihon Zokuzōkyō,新纂卍續藏,【卍續】,河村照孝,東京: 株式會社國書刊行會,1975-1989
 Y,印順法師佛學著作集,Corpus of Venerable Yin Shun's Buddhist Studies,印順全集,【印順】,正聞出版社,台北,2003-2016
+YP,演培法師全集,The Complete Works of Venerable Yen Pei,演培法師全集,【演培】,演培法師全集出版委員會,高雄,2006
 Z,卍大日本續藏經,Manji Dainihon Zokuzōkyō,,,,京都: 藏經書院,1905-1912
 ZS,正史佛教資料類編,Passages concerning Buddhism from the Official Histories,正史,【正史】,杜斗城,蘭州: 甘肅文化出版社,2006
 ZW,藏外佛教文獻,Buddhist Texts not contained in the Tripiṭaka,藏外,【藏外】,方廣錩,北京: 宗教文化出版社,1995-2003

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: cbeta
 version: !ruby/object:Gem::Version
-  version: 3.7.0
+  version: 3.7.2
 platform: ruby
 authors:
 - Ray Chou
@@ -34,7 +34,7 @@ cert_chain:
   xyQse8slbARanDyyT6HCYtlaKD9WYw647tkJhyY2GniloCNcOJS0URvhlulLzJYg
   9CrAxVAO2NMeM6tbxg1VjYbqopjoLCwLdAJouA==
   -----END CERTIFICATE-----
-date: 2025-10-13 00:00:00.000000000 Z
+date: 2025-11-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: unihan2