cbeta 3.7.10 → 3.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fa8c0001a52f96df16ac52d46416bcf1630f841ea306940a3196e81ece5c1fac
-  data.tar.gz: 655f8c0438ff07cfd0b73f3ad1f749cde2b44c38c7567a11dc2dcd9d31b5219f
+  metadata.gz: fdc6811da84a63c0696ba421fe426e21de327089cfa018cc8ec3252b7981caed
+  data.tar.gz: 77ee88f62ae4ac35506ca756c7df764a5d35fcf1b2d8ce98a05c578873ef3164
 SHA512:
-  metadata.gz: a4d29529c018af7658c30da3350e75e295181df0ea86693be3ed8f63257fdbe7d1efcf6fbf311965de718fbf589ea8971c20eca3f8a296cad5a1c4b2d8205871
-  data.tar.gz: b2f23a65ebc368bd5b7d19c21b1da96ba84fa4e21cebd7f2a32651f9ba571cc6fd76463d2483af619550a2cfcfafc2342ff07438a39e64246900b907904d7a24
+  metadata.gz: 9d5e52c2087cc1d4c05fb8d0757dd1e1bb8d4e9a42a1d2aeb6c11f3455358d018380a777a7aeed914be3a4474dd12060222fbaa4118bf82fc69e9bf3cab7d26e
+  data.tar.gz: abb54c0eaa239d7545e02ec957ec0648bc776a3d4c9f27f18a130d7f09164ea9ed0a7fbf9a0cac4480bdf98eec2282f94ef6b737ab8af659e6cd564212ee1755

data/lib/cbeta/cbeta_share.rb

@@ -1,7 +1,7 @@
 module CbetaShare
   def each_canon(xml_root)
     Dir.entries(xml_root).sort.each do |c|
-      next unless c.match(/^#{CBETA::CANON}$/)
+      next unless c.match(CBETA::CANON_ID)
       yield(c)
     end
   end

data/lib/cbeta/p5a_checker.rb

@@ -192,9 +192,9 @@ class CBETA::P5aChecker
   
   def e_graphic(e)
     url = File.basename(e['url'])
-    fn = File.join(@figures, @canon, url)
-    unless File.exist? fn
-      error "[E05] 圖檔 不存在, url: #{url}"
+    path = File.join(@figures, @canon, url)
+    unless File.exist? path
+      error "[E05] 圖檔 不存在, url: #{e['url']}, path: #{path}"
     end
   end
 

data/lib/cbeta/p5a_to_html_for_every_edition.rb

@@ -75,7 +75,7 @@ class CBETA::P5aToHTMLForEveryEdition
 
   def convert_all
     Dir.entries(@xml_root).sort.each do |c|
-      next unless c.match(/^#{CBETA::CANON}$/)
+      next unless c.match(CBETA::CANON_ID)
       convert_canon(c)
     end
   end

data/lib/cbeta/p5a_to_text.rb

@@ -124,7 +124,7 @@ class CBETA::P5aToText
 
   def convert_all
     Dir.entries(@xml_root).sort.each do |c|
-      next unless c.match(/^#{CBETA::CANON}$/)
+      next unless c.match(CBETA::CANON_ID)
       handle_canon(c)
     end
   end

data/lib/cbeta.rb

@@ -6,22 +6,36 @@
 require 'csv'
 
 class CBETA
-  CANON = 'CC|DA|GA|GB|LC|TX|YP|ZS|ZW|[A-Z]'
+  # 藏經 ID, 例如 T, ZS
+  #
+  # 本身是 alternation, 已經包在 non-capturing group 裡,
+  # 所以插值到 regexp 時不需要 (也不應該) 再包一層 group:
+  #   正確: /\A#{CBETA::CANON}\z/
+  #   多餘: /\A(?:#{CBETA::CANON})\z/
+  # 若需要取出藏經 ID, 才用 capturing group 包起來: /^(#{CBETA::CANON})/
+  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 = ',.()[] 。‧．，、；？！：︰／（）「」『』《》＜＞〈〉〔〕［］【】〖〗〃…—─　～│┬▆△＊＋－＝'
-  
+
   # 經號 (不含 Canon ID):
   #   四碼數字 T0001
   #   四碼數字 + 英文字母 T0150A, T0128a
   #   英文字母 + 三碼數字 JA041, ZWa073
-  WORK_PART = '\d{4}[a-zA-Z]?|[ABa]\d{3}'
+  # 與 CANON 一樣已自帶 non-capturing group。
+  WORK_PART = '(?:\d{4}[a-zA-Z]?|[ABa]\d{3})'
 
   # XML file 主檔名
   # GA010n0009
-  BASENAME = "(?:#{CANON})\\d{2,3}n(?:#{WORK_PART})"
-  
+  BASENAME = "#{CANON}\\d{2,3}n#{WORK_PART}"
+
+  # 整個字串就是 藏經 ID, 例如 "T", "ZS"
+  CANON_ID = /\A#{CANON}\z/
+
+  # 整個字串就是 典籍編號, 例如 "T0001", "JB271", "ZWa073"
+  WORK_ID = /\A#{CANON}#{WORK_PART}\z/
+
   # 由 行首資訊 取得 藏經 ID
   # @param linehead[String] 行首資訊, 例如 "T01n0001_p0001a01" 或 "GA009n0008_p0003a01"
   # @return [String] 藏經 ID，例如 "T" 或 "GA"
@@ -142,7 +156,7 @@ class CBETA
   #   ex: J36nB348_p0284c01
   # @return [String] XML檔相對路徑，例如 "GA/GA009/GA009n0008.xml"
   def self.linehead_to_xml_file_path(linehead)
-    if m = linehead.match(/^(?<work>(?<vol>(?<canon>#{CANON})\d+)n(?:#{WORK_PART})).*$/)
+    if m = linehead.match(/^(?<work>(?<vol>(?<canon>#{CANON})\d+)n#{WORK_PART}).*$/)
       File.join(m[:canon], m[:vol], m[:work]+'.xml')
     else
       nil
@@ -172,7 +186,7 @@ class CBETA
   #   CBETA.linehead_to_s('T85n2838_p1291a03')
   #   # return "T85, no. 2838, p. 1291, a03"
   def self.linehead_to_s(linehead)
-    linehead.match(/^((?:#{CANON})\d+)n(.*)_p(\d+)([a-z]\d+)$/) {
+    linehead.match(/^(#{CANON}\d+)n(.*)_p(\d+)([a-z]\d+)$/) {
       return "#{$1}, no. #{$2}, p. #{$3}, #{$4}"
     }
     nil

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: cbeta
 version: !ruby/object:Gem::Version
-  version: 3.7.10
+  version: 3.8.0
 platform: ruby
 authors:
 - Ray Chou