cbeta 2.2.22 → 2.2.26

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c051fafb22469b41ce99482cb6c7e42c2b57a934
-  data.tar.gz: b844d9fd876dcda4236f3c0d74b21baa234fec5c
+  metadata.gz: d19eb4a198b323a6ee4601eee34ec46d56d41c50
+  data.tar.gz: 359ce18558763b5b65ac05682c4619d5fe106b7a
 SHA512:
-  metadata.gz: 74c281e563811da223290c5cd35fc5246bae9f25267d634c553010ed3e9e7a9d7451d745b54408dbda05bec0218e1ac553fcb447b34c7ab37dd6bdbe806782cc
-  data.tar.gz: 25a7190bde65648a11d5ea65f476b247a406c50736df9f66c1f9b90c12f7f14e3af7581023e4a397bd2fa4270134f9c9e66df257abed8bda7f752af8b8fdcaf7
+  metadata.gz: b25957a15c65e3e49cf6ef6f33a6e8bbec950cac63ebbb4a164286c55ce16080b4824d4b033773d5407d0b86fe9c0bc398eb5685ac7a09f9ee48c7d936b81cf4
+  data.tar.gz: 4af74f6871288f1bc15a8b858ccc03fd688cec5a6621578e9a38764c1f25f8dd3051f6088bd095e546d05f96ea336368b25aa2656384d06674a2e85036c08562

data/lib/cbeta.rb

@@ -32,6 +32,16 @@ class CBETA
     vol.sub(/^(#{CANON}).*$/, '\1')
   end
   
+  # @param file_basename[String] XML檔主檔名, 例如 "T01n0001" 或 "T25n1510a"
+  # @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)
+    r = file_basename
+    r += '_' if file_basename.match(/\d$/)
+    r += 'p' + lb
+    r
+  end
+  
   # 由 冊號 及 典籍編號 取得 XML 主檔名
   # @param vol[String] 冊號, 例如 "T01" 或 "GA009"
   # @param work[String] 典籍編號, 例如 "T0001" 或 "GA0008"

data/lib/cbeta/p5a_to_html.rb

@@ -307,7 +307,7 @@ class CBETA::P5aToHTML
 
     @char_count = 1
     @lb = e['n']
-    line_head = @sutra_no + '_p' + @lb
+    line_head = CBETA.get_linehad(@sutra_no, @lb)
     
     r = ''
     #if e.parent.name == 'lg' and $lg_row_open

data/lib/cbeta/p5a_to_html_for_every_edition.rb

@@ -72,7 +72,7 @@ class CBETA::P5aToHTMLForEveryEdition
 
   def convert_all
     Dir.entries(@xml_root).sort.each do |c|
-      next unless c.match(/^#{CBETA.CANON}$/)
+      next unless c.match(/^#{CBETA::CANON}$/)
       convert_canon(c)
     end
   end
@@ -139,29 +139,7 @@ class CBETA::P5aToHTMLForEveryEdition
     end
   end
   
-  
-  def filter_html(html, ed)
-    frag = Nokogiri::HTML.fragment(html)
-    frag.search("r").each do |node|
-      if node['w'].include? ed
-        html_only_this_edition = filter_html(node.inner_html, ed)
-        node.add_previous_sibling html_only_this_edition
-      end
-      node.remove
-    end
-    frag.to_html
-  end
-  
-  def get_editions(doc)
-    r = Set.new [@orig, "【CBETA】"] # 至少有底本及 CBETA 兩個版本
-    doc.xpath('//lem|//rdg').each do |e|
-      w = e['wit'].scan(/【.*?】/)
-      r.merge w
-    end
-    r
-  end
-
-  def handle_anchor(e)
+  def e_anchor(e)
     id = e['id']
     if e.has_attribute?('id')
       if id.start_with?('nkr_note_orig')
@@ -184,7 +162,7 @@ class CBETA::P5aToHTMLForEveryEdition
     ''
   end
 
-  def handle_app(e)
+  def e_app(e)
     r = ''
     if e['type'] == 'star'
       c = e['corresp'][1..-1]
@@ -193,14 +171,14 @@ class CBETA::P5aToHTMLForEveryEdition
     r + traverse(e)
   end
 
-  def handle_byline(e)
+  def e_byline(e)
     r = '<p class="byline">'
     r += line_info
     r += traverse(e)
     r + '</p>'
   end
 
-  def handle_cell(e)
+  def e_cell(e)
     doc = Nokogiri::XML::Document.new
     cell = doc.create_element('div')
     cell['class'] = 'bip-table-cell'
@@ -210,7 +188,7 @@ class CBETA::P5aToHTMLForEveryEdition
     to_html(cell)
   end
 
-  def handle_corr(e)
+  def e_corr(e)
     r = ''
     if e.parent.name == 'choice'
       sic = e.parent.at_xpath('sic')
@@ -231,7 +209,7 @@ class CBETA::P5aToHTMLForEveryEdition
     r + "<r w='【CBETA】' l='#{@lb}'><span class='cbeta'>%s</span></r>" % traverse(e)
   end
 
-  def handle_div(e)
+  def e_div(e)
     @div_count += 1
     n = @div_count
     if e.has_attribute? 'type'
@@ -244,11 +222,11 @@ class CBETA::P5aToHTMLForEveryEdition
     end
   end
 
-  def handle_figure(e)
+  def e_figure(e)
     "<p class='figure'>%s</p>" % traverse(e)
   end
 
-  def handle_g(e, mode)
+  def e_g(e, mode)
     # if 有 <mapping type="unicode">
     #   if 不在 Unicode Extension C, D, E 範圍裡
     #     直接採用
@@ -326,12 +304,12 @@ class CBETA::P5aToHTMLForEveryEdition
     "<a class='gaijiAnchor' href='##{gid}'>#{default}</a>"
   end
 
-  def handle_graphic(e)
+  def e_graphic(e)
     url = File.basename(e['url'])
     "<span imgsrc='#{url}' class='graphic'></span>"
   end
 
-  def handle_head(e)
+  def e_head(e)
     r = ''
     unless e['type'] == 'added'
       i = @open_divs.size
@@ -340,15 +318,15 @@ class CBETA::P5aToHTMLForEveryEdition
     r
   end
 
-  def handle_item(e)
+  def e_item(e)
     "<li>%s</li>\n" % traverse(e)
   end
 
-  def handle_juan(e)
+  def e_juan(e)
     "<p class='juan'>%s</p>" % traverse(e)
   end
 
-  def handle_l(e)
+  def e_l(e)
     if @lg_type == 'abnormal'
       return traverse(e)
     end
@@ -380,13 +358,13 @@ class CBETA::P5aToHTMLForEveryEdition
     r
   end
 
-  def handle_lb(e)
+  def e_lb(e)
     # 卍續藏有 X 跟 R 兩種 lb, 只處理 X
     return '' if e['ed'] != @series
 
     @char_count = 1
     @lb = e['n']
-    line_head = @sutra_no + '_p' + e['n']
+    line_head = CBETA.get_linehead(@sutra_no, e['n'])
     r = ''
     #if e.parent.name == 'lg' and $lg_row_open
     if @lg_row_open && !@in_l
@@ -408,7 +386,7 @@ class CBETA::P5aToHTMLForEveryEdition
     r
   end
 
-  def handle_lem(e)
+  def e_lem(e)
     r = ''
     content = traverse(e)
     wit = e['wit']
@@ -436,7 +414,7 @@ class CBETA::P5aToHTMLForEveryEdition
     r + ("<r w='#{w}' l='#{@lb}'>%s</r>" % content)
   end
 
-  def handle_lg(e)
+  def e_lg(e)
     r = ''
     @lg_type = e['type']
     if @lg_type == 'abnormal'
@@ -461,11 +439,11 @@ class CBETA::P5aToHTMLForEveryEdition
     r
   end
 
-  def handle_list(e)
+  def e_list(e)
     "<ul>%s</ul>" % traverse(e)
   end
 
-  def handle_milestone(e)
+  def e_milestone(e)
     r = ''
     if e['unit'] == 'juan'
 
@@ -484,7 +462,7 @@ class CBETA::P5aToHTMLForEveryEdition
     r
   end
 
-  def handle_mulu(e)
+  def e_mulu(e)
     r = ''
     if e['type'] == '品'
       @pass << false
@@ -493,49 +471,9 @@ class CBETA::P5aToHTMLForEveryEdition
     end
     r
   end
+  
 
-  def handle_node(e, mode)
-    return '' if e.comment?
-    return handle_text(e, mode) 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 'byline'    then handle_byline(e)
-    when 'cell'      then handle_cell(e)
-    when 'corr'      then handle_corr(e)
-    when 'div'       then handle_div(e)
-    when 'figure'    then handle_figure(e)
-    when 'foreign'   then ''
-    when 'g'         then handle_g(e, mode)
-    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 't'         then handle_t(e)
-    when 'tt'        then handle_tt(e)
-    when 'table'     then handle_table(e)
-    when 'unclear'   then handle_unclear(e)
-    else traverse(e)
-    end
-    r
-  end
-
-  def handle_note(e)
+  def e_note(e)
     n = e['n']
     if e.has_attribute?('type')
       t = e['type']
@@ -580,36 +518,8 @@ class CBETA::P5aToHTMLForEveryEdition
     end
   end
 
-  def handle_note_orig(e, anchor_type=nil)
-    n = e['n']
-    @pass << false
-    s = traverse(e)
-    @pass.pop
-    @notes_orig[@juan][n] = s
-    @notes_mod[@juan][n] = s
-    
-    c = @series
-    
-    # 如果 CBETA 沒有修訂，就跟底本的註一樣
-    # 但是 CBETA 修訂後的編號，有時會加上 a, b
-    # T01n0026, p. 506b07, 大正藏校勘 0506007, CBETA 拆為 0506007a, 0506007b
-    c += " cb" unless @mod_notes.include?(n) or @mod_notes.include?(n+'a')
 
-    label = case anchor_type
-    when 'biao' then " data-label='標#{n[-2..-1]}'"
-    when 'ke'   then " data-label='科#{n[-2..-1]}'"
-    else ''
-    end
-    s = "<a class='noteAnchor #{c}' href='#n#{n}'#{label}></a>"
-    r = "<r w='#{@orig}'>#{s}</r>"
-    
-    unless @mod_notes.include?(n)
-      r += "<r w='【CBETA】'>#{s}</r>"
-    end
-    r
-  end
-
-  def handle_p(e)
+  def e_p(e)
     if e.key? 'type'
       r = "<p class='%s'>" % e['type']
     else
@@ -620,24 +530,24 @@ class CBETA::P5aToHTMLForEveryEdition
     r + '</p>'
   end
   
-  def handle_rdg(e)
+  def e_rdg(e)
     r = traverse(e)
     "<r w='#{e['wit']}' l='#{@lb}' w='#{@char_count}'>#{r}</r>"
   end
 
-  def handle_row(e)
+  def e_row(e)
     "<div class='bip-table-row'>" + traverse(e) + "</div>"
   end
 
-  def handle_sg(e)
+  def e_sg(e)
     '(' + traverse(e) + ')'
   end
   
-  def handle_sic(e)
+  def e_sic(e)
     "<r w='#{@orig}' l='#{@lb}'>" + traverse(e) + "</r>"
   end
 
-  def handle_t(e)
+  def e_t(e)
     if e.has_attribute? 'place'
       return '' if e['place'].include? 'foot'
     end
@@ -659,15 +569,112 @@ class CBETA::P5aToHTMLForEveryEdition
     end
   end
 
-  def handle_tt(e)
+  def e_tt(e)
     @tt_type = e['type']
     traverse(e)
   end
 
-  def handle_table(e)
+  def e_table(e)
     "<div class='bip-table'>" + traverse(e) + "</div>"
   end
+  
+  def e_unclear(e)
+    '▆'
+  end
+  
+  def filter_html(html, ed)
+    progress "filter html ed: #{ed}"
+    frag = Nokogiri::HTML.fragment(html)
+    frag.search("r").each do |node|
+      if node['w'].include? ed
+        html_only_this_edition = filter_html(node.inner_html, ed)
+        node.add_previous_sibling html_only_this_edition
+      end
+      node.remove
+    end
+    frag.to_html
+  end
+  
+  def get_editions(doc)
+    r = Set.new [@orig, "【CBETA】"] # 至少有底本及 CBETA 兩個版本
+    doc.xpath('//lem|//rdg').each do |e|
+      w = e['wit'].scan(/【.*?】/)
+      r.merge w
+    end
+    r
+  end
 
+
+  def handle_node(e, mode)
+    return '' if e.comment?
+    return handle_text(e, mode) 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 'byline'    then e_byline(e)
+    when 'cell'      then e_cell(e)
+    when 'corr'      then e_corr(e)
+    when 'div'       then e_div(e)
+    when 'figure'    then e_figure(e)
+    when 'foreign'   then ''
+    when 'g'         then e_g(e, mode)
+    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 't'         then e_t(e)
+    when 'tt'        then e_tt(e)
+    when 'table'     then e_table(e)
+    when 'unclear'   then e_unclear(e)
+    else traverse(e)
+    end
+    r
+  end
+  
+  def handle_note_orig(e, anchor_type=nil)
+    n = e['n']
+    @pass << false
+    s = traverse(e)
+    @pass.pop
+    @notes_orig[@juan][n] = s
+    @notes_mod[@juan][n] = s
+    
+    c = @series
+    
+    # 如果 CBETA 沒有修訂，就跟底本的註一樣
+    # 但是 CBETA 修訂後的編號，有時會加上 a, b
+    # T01n0026, p. 506b07, 大正藏校勘 0506007, CBETA 拆為 0506007a, 0506007b
+    c += " cb" unless @mod_notes.include?(n) or @mod_notes.include?(n+'a')
+
+    label = case anchor_type
+    when 'biao' then " data-label='標#{n[-2..-1]}'"
+    when 'ke'   then " data-label='科#{n[-2..-1]}'"
+    else ''
+    end
+    s = "<a class='noteAnchor #{c}' href='#n#{n}'#{label}></a>"
+    r = "<r w='#{@orig}'>#{s}</r>"
+    
+    unless @mod_notes.include?(n)
+      r += "<r w='【CBETA】'>#{s}</r>"
+    end
+    r
+  end
+  
   def handle_text(e, mode)
     s = e.content().chomp
     return '' if s.empty?
@@ -689,11 +696,8 @@ class CBETA::P5aToHTMLForEveryEdition
     r
   end
   
-  def handle_unclear(e)
-    '▆'
-  end
-  
   def html_back(juan_no, ed)
+    progress "html back, juan: #{juan_no}, ed: #{ed}"
     r = ''
     case ed
     when '【CBETA】'
@@ -843,6 +847,11 @@ class CBETA::P5aToHTMLForEveryEdition
     text = traverse(body)
     text
   end
+  
+  def progress(msg)
+    puts Time.now.strftime("%Y-%m-%d %H:%M:%S")
+    puts msg
+  end
 
   def to_html(e)
     e.to_xml(encoding: 'UTF-8', :save_with => Nokogiri::XML::Node::SaveOptions::AS_XML)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cbeta
 version: !ruby/object:Gem::Version
-  version: 2.2.22
+  version: 2.2.26
 platform: ruby
 authors:
 - Ray Chou
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-12-03 00:00:00.000000000 Z
+date: 2016-12-12 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