cbeta 3.1.3 → 3.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4bb29e86cf68e6503bb935c35f6499132f8106fc43e11de6a2e733df44901009
-  data.tar.gz: 454dcfbffbc118c6071c4f7932fc8c18118bcd7bbc60e3797f7386920e4f7b77
+  metadata.gz: 5d32b2ace3526aa8492fcfb42bbbebf08edfa1a1df1d3ef5aecc8e409e7423a9
+  data.tar.gz: 67bb568adb4710f114216161e16a6c7c5e0a0c34af6b770a42fc1e26143a3b03
 SHA512:
-  metadata.gz: d2ddd9c064712fe4bc74912d936479046080b97fe68b9884af164be26802efdc0a6455d7171e7f2854df5ce3106a8112441589dbcd4563388f44dbb3567a018d
-  data.tar.gz: c5d210953964044077cac5b264fdf07fe0a3e0fe04a3b74c2dadf36ec28e0117e5b5292b7d6333075d621ca67894b078c63e0bf0667bf0ade266e2a27bba764b
+  metadata.gz: 71ade7189b3f3bf90f9436e1d756c88f72164285972d7cab8cb81bb2ed27d2c13a048e2909cfb58f8250288e5d31bee888acedf6cf4ea225db5e7ea5605db575
+  data.tar.gz: f84625e849635021b7ba2c10b7b54725830bce6786eb40fe8b3696b8b732274ec89cbbb4fbedb9e494be88f221e7252c23d90fe83fe8e8b81edc8189bf9969f0

data/lib/cbeta/gaiji.rb

@@ -69,6 +69,8 @@ class CBETA::Gaiji
     end
     
     g = @gaijis[gid]
+    return nil if g.nil?
+    
     if gid.start_with? 'CB'
       cb_priority.each do |k|
         if k == 'PUA'

data/lib/cbeta/xml_document.rb

@@ -0,0 +1,340 @@
+require 'nokogiri'
+
+class CBETA::XMLDocument
+  PASS = %w(back graphic mulu rdg sic teiHeader)
+
+  attr_reader :doc
+
+  def initialize(string_or_io)
+    @doc = Nokogiri::XML(string_or_io)
+    @doc.remove_namespaces!
+    @gaiji = CBETA::Gaiji.new
+  end
+
+  def to_text
+    @format = 'text'
+    @gaiji_norm = [true]
+    @next_line_buf = ''
+    traverse(@doc.root)
+  end
+
+  private
+
+  def e_anchor(e)
+    if e.has_attribute?('type')
+      if e['type'] == 'circle'
+        return '◎'
+      end
+    end
+
+    ''
+  end
+
+  def e_app(e)
+    traverse(e)
+  end
+
+  def e_body(e)
+    traverse(e)
+  end
+
+  def e_byline(e)
+    traverse(e) + "\n"
+  end
+
+  def e_caesura(e)
+    '　'
+  end
+
+  def e_caption(e)
+    traverse(e) + "\n"
+  end
+
+  def e_cell(e)
+    traverse(e) + "\n"
+  end
+
+  def e_cit(e)
+    traverse(e)
+  end
+
+  def e_closer(e)
+    traverse(e) + "\n"
+  end
+  
+  def e_corr(e)
+    traverse(e)
+  end
+  
+  def e_date(e)
+    traverse(e)
+  end
+
+  def e_dialog(e)
+    traverse(e)
+  end
+
+  def e_div(e)
+    traverse(e)
+  end
+
+  def e_docAuthor(e)
+    traverse(e)
+  end
+  
+  def e_docNumber(e)
+    traverse(e) + "\n"
+  end
+
+  def e_event(e)
+    traverse(e) + "\n"
+  end
+
+  def e_figure(e)
+    r = traverse(e)
+    r << "\n" unless r.empty?
+    r
+  end
+
+  def e_figDesc(e)
+    traverse(e) + "\n"
+  end
+
+  def e_foreign(e)
+    return '' if e.key?('place') and e['place'].include?('foot')
+    traverse(e)
+  end
+
+  def e_g(e)
+    if @gaiji_norm.last
+      cb_priority = %w(uni_char norm_uni_char norm_big5_char composition)
+    else
+      cb_priority = %w(uni_char composition)
+    end
+
+    gid = e['ref'].delete_prefix('#')
+
+    unless @gaiji.key?(gid)
+      raise "在 CBETA 缺字庫中找不到此缺字碼: #{gid}"
+    end
+
+    @gaiji.to_s(gid, cb_priority:)
+  end
+
+  def e_head(e)
+    r = traverse(e)
+    r << "\n" unless r.empty?
+    r
+  end
+
+  def e_hi(e)
+    traverse(e)
+  end
+
+  def e_item(e)
+    r = "\n"
+
+    list_level = e.xpath('ancestor::list').size
+    r << '　' * (list_level - 1)
+    r << traverse(e)
+    if e.key? 'n'
+      r = e['n'] + r
+    end
+    r
+  end
+
+  def e_jhead(e)
+    traverse(e)
+  end
+
+  def e_juan(e)
+    traverse(e) + "\n"
+  end
+
+  def e_l(e)
+    r = traverse(e)
+    r << "\n" unless @lg_type == 'abnormal'
+    r
+  end
+
+  def e_lb(e)
+    return '' if e['type']=='old'
+    r = ''
+    r << "\n" if @p_type == 'pre'
+    unless @next_line_buf.empty?
+      r << @next_line_buf + "\n"
+      @next_line_buf = ''
+    end
+    r
+  end
+
+  def e_lem(e)
+    traverse(e)
+  end
+
+  def e_lg(e)
+    traverse(e)
+  end
+
+  def e_list(e)
+    r = traverse(e)
+    r << "\n\n" unless e.parent.name == 'item'
+    r
+  end
+
+  def e_milestone(e)
+    ''
+  end
+
+  def e_note(e)
+    if e.has_attribute?('place')
+      if "inline inline2 interlinear".include?(e['place'])
+        r = traverse(e)
+        return "(#{r})"
+      end
+    end
+    ''
+  end
+
+  def e_p(e)
+    @p_type = e['type']
+    r = traverse(e) + "\n"
+    @p_type = nil
+    r
+  end
+
+  def e_pb(e)
+    ''
+  end
+
+  def e_quote(e)
+    traverse(e)
+  end
+
+  def e_ref(e)
+    traverse(e)
+  end
+
+  def e_reg(e)
+    r = ''
+    choice = e.at_xpath('ancestor::choice')
+    r = traverse(e) if choice.nil?
+    r
+  end
+
+  def e_row(e)
+    traverse(e) + "\n"
+  end
+
+  def e_seg(e)
+    traverse(e)
+  end
+
+  def e_sg(e)
+    '(' + traverse(e) + ')'
+  end
+
+  # speech
+  def e_sp(e)
+    traverse(e)
+  end
+
+  def e_space(e)
+    return '' if e['quantity']=='0'
+    '　' * e['quantity'].to_i
+  end
+
+  def e_t(e)
+    if e.has_attribute? 'place'
+      return '' if e['place'].include? 'foot'
+    end
+    r = traverse(e)
+
+    # 如果不是雙行對照
+    tt = e.at_xpath('ancestor::tt')
+    unless tt.nil? 
+      return r if %w(app single-line).include? tt['type']
+      return r if tt['place'] == 'inline'
+      return r if tt['rend'] == 'normal'
+    end
+
+    # 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) + "\n"
+  end
+
+  def e_term(e)
+    norm = true
+    if e['behaviour'] == "no-norm"
+      norm = false
+    end
+    @gaiji_norm.push norm
+    r = traverse(e)
+    @gaiji_norm.pop
+    r
+  end
+
+  def e_text(e)
+    norm = true
+    if e['behaviour'] == "no-norm"
+      norm = false
+    end
+    @gaiji_norm.push norm
+    r = traverse(e)
+    @gaiji_norm.pop
+    r
+  end
+
+  def e_tt(e)
+    traverse(e)
+  end
+
+  def e_unclear(e)
+    r = traverse(e)
+    r = '▆' if r.empty?
+    r
+  end
+
+  def handle_node(e)
+    return '' if e.comment?
+    return handle_text(e) if e.text?
+    return '' if PASS.include?(e.name)
+    send("e_#{e.name}", e)
+  end
+
+  def handle_text(e)
+    s = e.content().chomp
+    return '' if s.empty?
+    return '' if e.parent.name == 'app'
+
+    # cbeta xml 文字之間會有多餘的換行
+    r = s.gsub(/[\n\r]/, '')
+
+    if @format == 'html'
+      r = CGI.escapeHTML(r) # 把 & 轉為 &amp;
+    end
+
+    r
+  end
+
+  def traverse(e)
+    r = ''
+    e.children.each do |c| 
+      r << handle_node(c)
+    end
+    r
+  end
+
+end

data/lib/cbeta.rb

@@ -234,3 +234,4 @@ require 'cbeta/p5a_to_simple_html'
 require 'cbeta/p5a_to_text'
 require 'cbeta/p5a_validator'
 require 'cbeta/html_to_text'
+require 'cbeta/xml_document'

data/lib/data/cbeta_gaiji.json

@@ -174568,5 +174568,17 @@
     "composition": "[弓*并]",
     "moe_variant_id": "C03427",
     "pua": "U+F87C6"
+  },
+  "CB34759": {
+    "composition": "[△@▲]",
+    "pua": "U+F87C7"
+  },
+  "CB34760": {
+    "unicode": "20B4F",
+    "uni_char": "𠭏",
+    "composition": "[山/〦/中/又]",
+    "norm_big5_char": "事",
+    "moe_variant_id": "A00048-003",
+    "pua": "U+F87C8"
   }
 }

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cbeta
 version: !ruby/object:Gem::Version
-  version: 3.1.3
+  version: 3.2.1
 platform: ruby
 authors:
 - Ray Chou
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-02-06 00:00:00.000000000 Z
+date: 2024-03-11 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
@@ -31,6 +31,7 @@ files:
 - lib/cbeta/p5a_to_simple_html.rb
 - lib/cbeta/p5a_to_text.rb
 - lib/cbeta/p5a_validator.rb
+- lib/cbeta/xml_document.rb
 - lib/data/canons.csv
 - lib/data/categories.json
 - lib/data/cbeta_gaiji.json
@@ -57,7 +58,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.22
+rubygems_version: 3.5.6
 signing_key:
 specification_version: 4
 summary: CBETA Tools