cbeta 3.6.2 → 3.6.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f2007fa55a92c4a68dc438764c107ffbc212bb3b6010a142cd461f6dd4b94836
-  data.tar.gz: 57268cdd51b3390c5e0d636d26d31a1f9893d7cdae9b4e5e8b42f95db0f544af
+  metadata.gz: 49e62ac8c7805abccecdd47d26c301797f3b5262659f1aca46dd4d314dfd50ae
+  data.tar.gz: 72e3a47fd5fe23c0ecef82d9cbcbfd9d1c4079a41133c1325d1f5220b68f24a7
 SHA512:
-  metadata.gz: 46e9830b7171683c4e43642c8eef1851e059cde4cb1696df85bb7fea7d48e4d28a1728975a9a8c36cdd3b6591f8b0d0290f74123bb29c44dee2d4a41425453a9
-  data.tar.gz: 36db93a0d3bc3794b248aa249bea059f53c4c176de4263b19f8abcf30799dd9a17b1323c28e9697645f511452e6b118d09a67279f8f1349a1b5e59dae98a76fe
+  metadata.gz: ab60c18e220fad95a78aac7700726a2e629759933cac1b489f05890141ffdaa770a650479e56f8316b65592979ba9241a9a8f1015070af8883e0f19744b526bd
+  data.tar.gz: e5cd339be96a043c1186e2968cf12f6c91f779039130024423859729d58c180fa262a6c5d3447b85ebecb0eaf81b5513f48f24a0d2f8275d21a2ac779f189055

data/lib/cbeta/p5a_checker.rb

@@ -1,7 +1,15 @@
 require_relative 'cbeta_share'
 
 # 檢查 CBETA XML P5a
+#
+# * 錯誤類型
+#   * [E01] 行號重複
+#   * [E02] 文字直接出現在 div 下
+#   * [E03] 星號校勘 app 沒有對應的 note
+# * 警告類型
+#   * [W01] 夾注包夾注
 class CBETA::P5aChecker
+
   # @param xml_root [String] 來源 CBETA XML P5a 路徑
   # @param figures [String] 插圖 路徑 (可由 https://github.com/cbeta-git/CBR2X-figures 取得)
   # @param log [String] Log file path
@@ -14,6 +22,13 @@ class CBETA::P5aChecker
     @g_errors = {}
   end
   
+  # 檢查全部 CBETA XML P5a
+  # @example 
+  #   CBETA::P5aChecker.new(
+  #     xml_root: '~/git-repos/cbeta-xml-p5a', 
+  #     figures: '~/git-repos/CBR2X-figures', 
+  #     log: '~/log/check-cbeta-xml.log'
+  #   ).check
   def check
     puts "xml: #{@xml_root}"
     each_canon(@xml_root) do |c|
@@ -25,6 +40,31 @@ class CBETA::P5aChecker
     display_errors
   end
   
+  # 檢查某部藏經
+  # @param canon [String] 藏經 ID, example: "T"
+  def check_canon(canon)
+    @canon = canon
+    path = File.join(@xml_root, @canon)
+    handle_canon(path)
+    display_errors
+  end
+
+  # 檢查某一冊
+  # @param vol [String] 冊號, example: "T01"
+  def check_vol(vol)
+    @vol = vol
+    @canon = CBETA.get_canon_from_vol(vol)
+    path = File.join(@xml_root, @canon, vol)
+    handle_vol(path)
+    display_errors
+  end
+
+  # 檢查單一檔案
+  # @example 
+  #   CBETA::P5aChecker.new(
+  #     figures: '~/git-repos/CBR2X-figures',
+  #     log: '~/log/check-cbeta-xml.log'
+  #   ).check_file('~/git-repos/cbeta-xml-p5a/A/A110/A110n1490.xml')
   def check_file(fn)
     handle_file(fn)
     display_errors
@@ -50,11 +90,11 @@ class CBETA::P5aChecker
     if @errors.empty?
       puts "檢查完成，未發現錯誤。"
     elsif @log.nil?
-      puts "\n發現錯誤："
+      puts "發現錯誤："
       puts @errors
     else
       File.write(@log, @errors)
-      puts "\n發現錯誤，請查看 #{@log}"
+      puts "發現錯誤，請查看 #{@log}"
     end
   end
 
@@ -108,6 +148,16 @@ class CBETA::P5aChecker
     traverse(e)
   end
 
+  def e_note(e)
+    return unless e['place'] == 'inline'
+    if @element_stack.include?('inline_note')
+      @errors << "[W01] 夾注包夾注: #{@basename}, lb: #{@lb}\n"
+    end
+    @element_stack << 'inline_note'
+    traverse(e)
+    @element_stack.pop
+  end
+
   def e_rdg(e)
     return if e['type'] == 'cbetaRemark'
     unless e.key?('wit')
@@ -127,7 +177,6 @@ class CBETA::P5aChecker
     Dir.entries(folder).sort.each do |f|
       next if f.start_with? '.'
       @vol = f
-      $stderr.print "#{@vol} "
       path = File.join(folder, @vol)
       handle_vol(path)
     end
@@ -147,6 +196,7 @@ class CBETA::P5aChecker
       doc.remove_namespaces!
       @lbs = Set.new
       read_notes(doc)
+      @element_stack = []
       traverse(doc.root)
     else
       @errors << "錯誤: #{@basename} not well-formed\n"
@@ -160,12 +210,14 @@ class CBETA::P5aChecker
     when 'graphic' then e_graphic(e)
     when 'lb'      then e_lb(e)
     when 'lem'     then e_lem(e)
+    when 'note'    then e_note(e)
     when 'rdg'     then e_rdg(e)
     else traverse(e)
     end
   end
   
   def handle_vol(folder)
+    puts "check vol: #{File.basename(folder)}"
     Dir.entries(folder).sort.each do |f|
       next if f.start_with? '.'
       path = File.join(folder, f)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cbeta
 version: !ruby/object:Gem::Version
-  version: 3.6.2
+  version: 3.6.4
 platform: ruby
 authors:
 - Ray Chou
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-04-21 00:00:00.000000000 Z
+date: 2025-04-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: unihan2