cbeta 2.2.6 → 2.2.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 388e5affee54e7c33d2afd0c1451330cc719898a
-  data.tar.gz: 11293a7c5ad31752a8ad2ee189bcf515c10072f5
+  metadata.gz: a3f8edd88730de817c9ecec347b516f552cd148a
+  data.tar.gz: 3f9b2eb3e8010094ce3ce47b84e261319d8ccac5
 SHA512:
-  metadata.gz: 0a24c14869c9d85cad5dc1ce61237f5e2cd97b7e382fceaf0df68a732604f3c06a13815019a9fcb75da68abd4c5a4b0ea1dbccc1c538d1f1b95d27cc62b5d871
-  data.tar.gz: f6b0d1a6f73a9cebeddf5e4809c0d382edaa88a3ba0dab11c9b6c9355abc2d38157acab7cc4caf23f7c2c90bc87523852ddbd525269feb5a41a10fb3602fe436
+  metadata.gz: 7e05cadab483733f7a5c531966fca41fcd453e1da9ae44f64433bf04e72d3ae9b129ea7b4dc0f94c3e7f304d9d5755ec192a572cd463a6528d3088ed4bcab5f0
+  data.tar.gz: 15f31074085847f332c3633f7de85706167c059709ae48a889081b9ebbe26f9e32cf626a07c8492cb29c6aadd2089b11e2dae16a66406d8c44038961047a55eb

data/lib/cbeta.rb

@@ -6,8 +6,41 @@
 require 'csv'
 
 class CBETA
+  CANON = 'DA|GA|GB|[A-Z]'
   DATA = File.join(File.dirname(__FILE__), 'data')
   PUNCS = '.[]。，、？「」『』《》＜＞〈〉〔〕［］【】〖〗'
+
+  # 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"
+  def self.get_canon_id_from_linehead(linehead)
+    linehead.sub(/^(#{CANON}).*$/, '\1')
+  end
+
+  # 由 冊號 取得 藏經 ID
+  # @param vol[String] 冊號, 例如 "T01" 或 "GA009"
+  # @return [String] 藏經 ID，例如 "T" 或 "GA"
+  def self.get_canon_from_vol(vol)
+    vol.sub(/^(#{CANON}).*$/, '\1')
+  end
+  
+  # 由 行首資訊 取得 XML檔相對路徑
+  # @param linehead[String] 行首資訊, 例如 "GA009n0008_p0003a01"
+  # @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\d+[a-zA-Z]?).*$/)
+      File.join(m[:canon], m[:vol], m[:work]+'.xml')
+    else
+      nil
+    end
+  end
+  
+  # 由 XML檔主檔名 取得 典籍編號
+  # @param fn[String] 檔名, 例如 "T01n0001" 或 "GA009n0008"
+  # @return [String] 典籍編號，例如 "T0001" 或 "GA0008"
+  def self.get_work_id_from_file_basename(fn)
+    fn.sub(/^(#{CANON})\d{2,3}n(.*)$/, '\1\2')
+  end
   
   # 將行首資訊轉為引用格式
   #
@@ -18,7 +51,7 @@ class CBETA
   #   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+)$/) {
+    linehead.match(/^((?:#{CANON})\d+)n(.*)_p(\d+)([a-z]\d+)$/) {
       return "#{$1}, no. #{$2}, p. #{$3}, #{$4}"
     }
     nil
@@ -68,12 +101,12 @@ class CBETA
     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]
+  def get_canon_nickname(id)
+    return nil unless @canon_nickname.key? id
+    @canon_nickname[id]
   end
   
   # 取得藏經略符

data/lib/cbeta/gaiji.rb

@@ -75,7 +75,6 @@ class CBETA::Gaiji
   
   def char_to_hash(char)
     r = {}
-    id = char['id']
     field_mapping = {
       'big5' => 'big5',
       'Character in the Siddham font' => 'char_in_siddham_font',

data/lib/cbeta/html_to_text.rb

@@ -103,7 +103,7 @@ class CBETA::HTMLToText
 
   def prepare_folder()
     folder = File.join(@out_root, @corpus, @vol)
-    FileUtils.remove_dir(folder, force=true)
+    FileUtils.remove_dir(folder, true)
     FileUtils.mkdir_p(folder)
     folder
   end

data/lib/cbeta/p5a_to_html.rb

@@ -540,10 +540,7 @@ class CBETA::P5aToHTML
     text.gsub!(/(<a class='noteAnchor'[^>]*><\/a>)(<div class="lg-cell"[^>]*>)/, '\2\1')
     
     juans = text.split(/(<juan \d+>)/)
-    open = false
-    fo = nil
     juan_no = nil
-    fn = ''
     buf = ''
     # 一卷一檔
     juans.each { |j|
@@ -618,9 +615,9 @@ class CBETA::P5aToHTML
     abort "未處理底本" if @orig.nil?
 
     @vol = vol
-    @series = vol[0]
+    @series = CBETA.get_canon_from_vol(vol)
     @out_folder = File.join(@out_root, @series, vol)
-    FileUtils.remove_dir(@out_folder, force=true)
+    FileUtils.remove_dir(@out_folder, true)
     FileUtils::mkdir_p @out_folder
     
     source = File.join(@xml_root, @series, vol)
@@ -631,7 +628,7 @@ class CBETA::P5aToHTML
 
   def handle_vols(v1, v2)
     puts "convert volumns: #{v1}..#{v2}"
-    @series = v1[0]
+    @series = CBETA.get_canon_from_vol(v1)
     folder = File.join(@xml_root, @series)
     Dir.foreach(folder) { |vol|
       next if vol < v1
@@ -677,16 +674,11 @@ class CBETA::P5aToHTML
   end
   
   def linehead_exist_in_cbeta(s)
-    @xml_root
-    corpus = s[0]
-    if s.match(/^(([A-Z]\d+)n\d+[a-zA-Z]?).*$/)
-      sutra = $1
-      vol = $2
-      path = File.join(@xml_root, corpus, vol, sutra+'.xml')
-      return File.exist? path
-    else
-      return false
-    end
+    fn = CBETA.linehead_to_xml_file_path(s)
+    return false if fn.nil?
+    
+    path = File.join(@xml_root, fn)
+    File.exist? path
   end
 
   def open_xml(fn)

data/lib/cbeta/p5a_to_html_for_every_edition.rb

@@ -106,10 +106,7 @@ class CBETA::P5aToHTMLForEveryEdition
     text.gsub!(/(<a class='noteAnchor'[^>]*><\/a>)(<div class="lg-cell"[^>]*>)/, '\2\1')
     
     juans = text.split(/(<juan \d+>)/)
-    open = false
-    fo = nil
     juan_no = nil
-    fn = ''
     buf = ''
     # 一卷一檔
     juans.each { |j|
@@ -122,8 +119,7 @@ class CBETA::P5aToHTMLForEveryEdition
         buf = ''
       end
     }
-  end
-  
+  end  
   
   def convert_vol(vol)
     puts "convert volumn: #{vol}"
@@ -414,12 +410,12 @@ class CBETA::P5aToHTMLForEveryEdition
   def handle_lem(e)
     r = ''
     content = traverse(e)
-    w = e['wit']
-    if w.include? 'CBETA' and not w.include? @orig
+    wit = e['wit']
+    if wit.include? 'CBETA' and not wit.include? @orig
       n = @notes_dila[@juan].size + 1
       r = "<a class='noteAnchor dila' href='#dila_note#{n}'></a>"
       r += "<span class='cbeta'>%s</span>" % content
-      r = "<r w='#{w}' l='#{@lb}'>#{r}</r>"
+      r = "<r w='#{wit}' l='#{@lb}'>#{r}</r>"
 
       note = lem_note_cf(e)
       note += lem_note_rdg(e)
@@ -625,7 +621,6 @@ class CBETA::P5aToHTMLForEveryEdition
   
   def handle_rdg(e)
     r = traverse(e)
-    w = e['wit'].scan(/【.*?】/)
     "<r w='#{e['wit']}' l='#{@lb}' w='#{@char_count}'>#{r}</r>"
   end
 
@@ -788,16 +783,11 @@ class CBETA::P5aToHTMLForEveryEdition
   end
   
   def linehead_exist_in_cbeta(s)
-    @xml_root
-    corpus = s[0]
-    if s.match(/^(([A-Z]\d+)n\d+[a-zA-Z]?).*$/)
-      sutra = $1
-      vol = $2
-      path = File.join(@xml_root, corpus, vol, sutra+'.xml')
-      return File.exist? path
-    else
-      return false
-    end
+    fn = CBETA.linehead_to_xml_file_path(s)
+    return false if fn.nil?
+    
+    path = File.join(@xml_root, fn)
+    File.exist? path
   end
 
   def open_xml(fn)
@@ -872,10 +862,9 @@ class CBETA::P5aToHTMLForEveryEdition
     else
       work = @sutra_no.sub(/^([A-Z]{1,2})\d{2,3}n(.*)$/, '\1\2')
     end
-    canon = work[0]
     juan = "%03d" % juan_no
     folder = File.join(@out_folder, work, juan)
-    FileUtils.remove_dir(folder, force=true)
+    FileUtils.remove_dir(folder, true)
     FileUtils.makedirs folder
     
     @editions.each do |ed|

data/lib/cbeta/p5a_to_html_for_pdf.rb

@@ -198,8 +198,6 @@ class CBETA::P5aToHTMLForPDF
   end
 
   def handle_anchor(e)
-    id = e['id']
-
     if e.has_attribute?('type')
       if e['type'] == 'circle'
         return '◎'
@@ -496,7 +494,6 @@ class CBETA::P5aToHTMLForPDF
   end
 
   def handle_note(e)
-    n = e['n']
     if e.has_attribute?('type')
       t = e['type']
       if %w(equivalent orig orig_biao orig_ke mod rest).include? t
@@ -638,13 +635,9 @@ class CBETA::P5aToHTMLForPDF
     abort "未處理底本" if @orig.nil?
 
     @vol = vol
-    if vol.start_with? 'DA'
-      @series = 'DA'
-    else
-      @series = vol[0]
-    end
+    @series = CBETA.get_canon_from_vol(vol)
     @out_folder = File.join(@out_root, @series, vol)
-    FileUtils.remove_dir(@out_folder, force=true)
+    FileUtils.remove_dir(@out_folder, true)
     FileUtils::mkdir_p @out_folder
     
     source = File.join(@xml_root, @series, vol)
@@ -657,7 +650,7 @@ class CBETA::P5aToHTMLForPDF
 
   def handle_vols(v1, v2)
     puts "convert volumns: #{v1}..#{v2}"
-    @series = v1[0]
+    @series = CBETA.get_canon_from_vol(v1)
     folder = File.join(@xml_root, @series)
     Dir.foreach(folder) { |vol|
       next if vol < v1

data/lib/cbeta/p5a_to_simple_html.rb

@@ -119,7 +119,6 @@ class CBETA::P5aToSimpleHTML
     gid = e['ref'][1..-1]
     g = @gaijis[gid]
     abort "Line:#{__LINE__} 無缺字資料:#{gid}" if g.nil?
-    zzs = g['zzs']
     
     if gid.start_with?('SD') # 悉曇字
       case gid
@@ -257,10 +256,7 @@ class CBETA::P5aToSimpleHTML
     FileUtils.makedirs @out_sutra
 
     juans = text.split(/(<juan \d+>)/)
-    open = false
-    fo = nil
     juan_no = nil
-    fn = ''
     buf = ''
     # 一卷一檔
     juans.each { |j|
@@ -324,9 +320,9 @@ class CBETA::P5aToSimpleHTML
     @orig_short = @orig.sub(/^【(.*)】$/, '\1')
 
     @vol = vol
-    @series = vol[0]
+    @series = CBETA.get_canon_from_vol(vol)
     @out_vol = File.join(@output_root, @series, vol)
-    FileUtils.remove_dir(@out_vol, force=true)
+    FileUtils.remove_dir(@out_vol, true)
     FileUtils.makedirs @out_vol
     
     source = File.join(@xml_root, @series, vol)
@@ -337,7 +333,7 @@ class CBETA::P5aToSimpleHTML
 
   def handle_vols(v1, v2)
     puts "convert volumns: #{v1}..#{v2}"
-    @series = v1[0]
+    @series = CBETA.get_canon_from_vol(v1)
     folder = File.join(@xml_root, @series)
     Dir.foreach(folder) { |vol|
       next if vol < v1

data/lib/cbeta/p5a_to_text.rb

@@ -70,8 +70,8 @@ class CBETA::P5aToText
     return convert_all if target.nil?
 
     arg = target.upcase
-    if arg.size == 1
-      handle_collection(arg)
+    if arg.size <= 2
+      handle_canon(arg)
     else
       if arg.include? '..'
         arg.match(/^([^\.]+?)\.\.([^\.]+)$/) {
@@ -124,7 +124,7 @@ class CBETA::P5aToText
   def convert_all
     Dir.entries(@xml_root).sort.each do |c|
       next unless c.match(/^[A-Z]$/)
-      handle_collection(c)
+      handle_canon(c)
     end
   end
 
@@ -138,7 +138,7 @@ class CBETA::P5aToText
     r
   end
   
-  def handle_anchor(e)
+  def e_anchor(e)
     if e.has_attribute?('type')
       if e['type'] == 'circle'
         return '◎'
@@ -148,53 +148,43 @@ class CBETA::P5aToText
     ''
   end
 
-  def handle_app(e)
+  def e_app(e)
     traverse(e)
   end
 
-  def handle_byline(e)
+  def e_byline(e)
     r = traverse(e)
     r += @settings[:format]=='app' ? "\t" : "\n"
     r
   end
 
-  def handle_cell(e)
+  def e_cell(e)
     r = traverse(e)
     r += @settings[:format]=='app' ? "\t" : "\n"
     r
   end
 
-  def handle_collection(c)
-    @series = c
-    puts 'handle_collection ' + c
-    folder = File.join(@xml_root, @series)
-    Dir.entries(folder).sort.each do |vol|
-      next if vol.start_with? '.'
-      handle_vol(vol)
-    end
-  end
-
-  def handle_corr(e)
+  def e_corr(e)
     "<r w='【CBETA】'>%s</r>" % traverse(e)
   end
 
-  def handle_div(e)
+  def e_div(e)
     traverse(e)
   end
 
-  def handle_docNumber(e)
+  def e_docNumber(e)
     r = traverse(e)
     r += @settings[:format] == 'app' ? "\t" : "\n"
     r
   end
 
-  def handle_figure(e)
+  def e_figure(e)
     r = traverse(e)
     r += @settings[:format] == 'app' ? "\t" : "\n"
     r
   end
 
-  def handle_g(e)
+  def e_g(e)
     # if 悉曇字、蘭札體
     #   使用 Unicode PUA
     # else if 有 <mapping type="unicode">
@@ -215,7 +205,6 @@ class CBETA::P5aToText
     
     g = @gaijis[gid]
     abort "Line:#{__LINE__} 無缺字資料:#{gid}" if g.nil?
-    zzs = g['zzs']
     
     if gid.start_with?('SD') # 悉曇字
       case gid
@@ -240,28 +229,28 @@ class CBETA::P5aToText
     [0xf0000 + gid[2..-1].to_i].pack 'U'
   end
 
-  def handle_graphic(e)
+  def e_graphic(e)
     ''
   end
 
-  def handle_head(e)
+  def e_head(e)
     r = traverse(e)
     r += @settings[:format] == 'app' ? "\t" : "\n"
     r
   end
 
-  def handle_item(e)
+  def e_item(e)
     r = traverse(e)
     r += @settings[:format] == 'app' ? "\t" : "\n"
   end
 
-  def handle_juan(e)
+  def e_juan(e)
     r = traverse(e)
     r += @settings[:format] == 'app' ? "\t" : "\n"
     r
   end
 
-  def handle_l(e)
+  def e_l(e)
     r = traverse(e)
     if @settings[:format] == 'app'
       r += "\t"
@@ -271,7 +260,7 @@ class CBETA::P5aToText
     r
   end
 
-  def handle_lb(e)
+  def e_lb(e)
     r = ''
     if @settings[:format] == 'app'
       r += "\n#{e['n']}║"
@@ -283,7 +272,7 @@ class CBETA::P5aToText
     r
   end
 
-  def handle_lem(e)
+  def e_lem(e)
     # 沒有 rdg 的版本，用字同 lem
     editions = Set.new @editions
     e.xpath('./following-sibling::rdg').each do |rdg|
@@ -296,17 +285,17 @@ class CBETA::P5aToText
     "<r w='#{w}'>%s</r>" % traverse(e)
   end
 
-  def handle_lg(e)
+  def e_lg(e)
     traverse(e)
   end
 
-  def handle_list(e)
+  def e_list(e)
     r = ''
     r += "\n" unless @settings[:format] == 'app'
     r + traverse(e)
   end
 
-  def handle_milestone(e)
+  def e_milestone(e)
     r = ''
     if e['unit'] == 'juan'
       @juan = e['n'].to_i
@@ -315,55 +304,11 @@ class CBETA::P5aToText
     r
   end
 
-  def handle_mulu(e)
+  def e_mulu(e)
     ''
   end
 
-  def handle_node(e)
-    return '' if e.comment?
-    return handle_text(e) 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)
-    when 'back'      then ''
-    when 'byline'    then handle_byline(e)
-    when 'cell'      then handle_cell(e)
-    when 'corr'      then handle_corr(e)
-    when 'div'       then handle_div(e)
-    when 'docNumber' then handle_docNumber(e)
-    when 'figure'    then handle_figure(e)
-    when 'foreign'   then ''
-    when 'g'         then handle_g(e)
-    when 'graphic'   then handle_graphic(e)
-    when 'head'      then handle_head(e)
-    when 'item'      then handle_item(e)
-    when 'juan'      then handle_juan(e)
-    when 'l'         then handle_l(e)
-    when 'lb'        then handle_lb(e)
-    when 'lem'       then handle_lem(e)
-    when 'lg'        then handle_lg(e)
-    when 'list'      then handle_list(e)
-    when 'mulu'      then handle_mulu(e)
-    when 'note'      then handle_note(e)
-    when 'milestone' then handle_milestone(e)
-    when 'p'         then handle_p(e)
-    when 'rdg'       then handle_rdg(e)
-    when 'reg'       then ''
-    when 'row'       then handle_row(e)
-    when 'sic'       then handle_sic(e)
-    when 'sg'        then handle_sg(e)
-    when 'tt'        then handle_tt(e)
-    when 't'         then handle_t(e)
-    when 'table'     then handle_table(e)
-    when 'teiHeader' then ''
-    when 'unclear'   then '▆'
-    else traverse(e)
-    end
-    r
-  end
-
-  def handle_note(e)
+  def e_note(e)
     if e.has_attribute?('place') && e['place']=='inline'
       r = traverse(e)
       return "（#{r}）"
@@ -371,28 +316,108 @@ class CBETA::P5aToText
     ''
   end
 
-  def handle_p(e)
+  def e_p(e)
     r = traverse(e)
     r += @settings[:format] == 'app' ? "\t" : "\n"
     r
   end
 
-  def handle_rdg(e)
+  def e_rdg(e)
     "<r w='#{e['wit']}'>%s</r>" % traverse(e)
   end
 
-  def handle_row(e)
+  def e_row(e)
     traverse(e)
   end
 
-  def handle_sg(e)
+  def e_sg(e)
     '(' + traverse(e) + ')'
   end
 
-  def handle_sic(e)
+  def e_sic(e)
     "<r w='#{@orig}'>" + traverse(e) + "</r>"
   end
 
+  def e_t(e)
+    if e.has_attribute? 'place'
+      return '' if e['place'].include? 'foot'
+    end
+    r = traverse(e)
+
+    # 不是雙行對照
+    return r if @tt_type == 'app'
+
+    # 處理雙行對照
+    i = e.xpath('../t').index(e)
+    case i
+    when 0
+      return r + '　'
+    when 1
+      @next_line_buf += r + '　'
+      return ''
+    else
+      return r
+    end
+  end
+
+  def e_table(e)
+    traverse(e)
+  end
+
+  def handle_canon(c)
+    @canon = c
+    puts 'handle_canon ' + c
+    folder = File.join(@xml_root, @canon)
+    Dir.entries(folder).sort.each do |vol|
+      next if vol.start_with? '.'
+      handle_vol(vol)
+    end
+  end
+
+  def handle_node(e)
+    return '' if e.comment?
+    return handle_text(e) if e.text?
+    return '' if PASS.include?(e.name)
+    r = case e.name
+    when 'anchor'    then e_anchor(e)
+    when 'app'       then e_app(e)
+    when 'back'      then ''
+    when 'byline'    then e_byline(e)
+    when 'cell'      then e_cell(e)
+    when 'corr'      then e_corr(e)
+    when 'div'       then e_div(e)
+    when 'docNumber' then e_docNumber(e)
+    when 'figure'    then e_figure(e)
+    when 'foreign'   then ''
+    when 'g'         then e_g(e)
+    when 'graphic'   then e_graphic(e)
+    when 'head'      then e_head(e)
+    when 'item'      then e_item(e)
+    when 'juan'      then e_juan(e)
+    when 'l'         then e_l(e)
+    when 'lb'        then e_lb(e)
+    when 'lem'       then e_lem(e)
+    when 'lg'        then e_lg(e)
+    when 'list'      then e_list(e)
+    when 'mulu'      then e_mulu(e)
+    when 'note'      then e_note(e)
+    when 'milestone' then e_milestone(e)
+    when 'p'         then e_p(e)
+    when 'rdg'       then e_rdg(e)
+    when 'reg'       then ''
+    when 'row'       then e_row(e)
+    when 'sic'       then e_sic(e)
+    when 'sg'        then e_sg(e)
+    when 'tt'        then e_tt(e)
+    when 't'         then e_t(e)
+    when 'table'     then e_table(e)
+    when 'teiHeader' then ''
+    when 'unclear'   then '▆'
+    else traverse(e)
+    end
+    r
+  end
+
   def handle_sutra(xml_fn)
     puts "convert sutra #{xml_fn}"
     @dila_note = 0
@@ -418,10 +443,7 @@ class CBETA::P5aToText
     FileUtils.makedirs @out_sutra
 
     juans = text.split(/(<juan \d+>)/)
-    open = false
-    fo = nil
     juan_no = nil
-    fn = ''
     buf = ''
     # 一卷一檔
     juans.each { |j|
@@ -438,32 +460,6 @@ class CBETA::P5aToText
     }
   end
 
-  def handle_t(e)
-    if e.has_attribute? 'place'
-      return '' if e['place'].include? 'foot'
-    end
-    r = traverse(e)
-
-    # 不是雙行對照
-    return r if @tt_type == 'app'
-
-    # 處理雙行對照
-    i = e.xpath('../t').index(e)
-    case i
-    when 0
-      return r + '　'
-    when 1
-      @next_line_buf += r + '　'
-      return ''
-    else
-      return r
-    end
-  end
-
-  def handle_table(e)
-    traverse(e)
-  end
-
   def handle_text(e)
     s = e.content().chomp
     return '' if s.empty?
@@ -476,7 +472,7 @@ class CBETA::P5aToText
     CGI.escapeHTML(r)
   end
 
-  def handle_tt(e)
+  def e_tt(e)
     @tt_type = e['type']
     traverse(e)
   end
@@ -488,12 +484,12 @@ class CBETA::P5aToText
     abort "未處理底本" if @orig.nil?
 
     @vol = vol
-    @series = vol[0]
-    @out_vol = File.join(@output_root, @series, vol)
-    FileUtils.remove_dir(@out_vol, force=true)
+    @canon = CBETA.get_canon_from_vol(vol)
+    @out_vol = File.join(@output_root, @canon, vol)
+    FileUtils.remove_dir(@out_vol, true)
     FileUtils.makedirs @out_vol
     
-    source = File.join(@xml_root, @series, vol)
+    source = File.join(@xml_root, @canon, vol)
     Dir.entries(source).sort.each { |f|
       next if f.start_with? '.'
       fn = File.join(source, f)
@@ -503,8 +499,8 @@ class CBETA::P5aToText
 
   def handle_vols(v1, v2)
     puts "convert volumns: #{v1}..#{v2}"
-    @series = v1[0]
-    folder = File.join(@xml_root, @series)
+    @canon = get_canon_from_vol(v1)
+    folder = File.join(@xml_root, @canon)
     Dir.entries(folder).sort.each do |vol|
       next if vol < v1
       next if vol > v2

data/lib/cbeta/p5a_validator.rb

@@ -85,7 +85,7 @@ class CBETA::P5aValidator
     def check_well_form(xml)
       r = ''
       begin
-        doc = Nokogiri::XML(xml) { |config| config.strict }
+        Nokogiri::XML(xml) { |config| config.strict }
       rescue Nokogiri::XML::SyntaxError => e
         r = "caught exception: #{e}"
       end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cbeta
 version: !ruby/object:Gem::Version
-  version: 2.2.6
+  version: 2.2.9
 platform: ruby
 authors:
 - Ray Chou
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-07-29 00:00:00.000000000 Z
+date: 2016-08-31 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