Class: CBETA

Inherits:
Object
  • Object
show all
Defined in:
lib/cbeta.rb

Defined Under Namespace

Classes: BMToText, Canon, CharCount, CharFrequency, Gaiji, HTMLToPDF, HTMLToText, P5aToHTML, P5aToHTMLForEveryEdition, P5aToHTMLForPDF, P5aToSimpleHTML, P5aToText, P5aValidator

Constant Summary collapse

CANON = 
'CC|DA|GA|GB|LC|TX|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 CC)
VOL3 = 
%w[A CC C G GA GB L M P U]
DATA = 
File.join(File.dirname(__FILE__), 'data')
PUNCS = 
',.()[] 。‧．，、；？！：︰／（）「」『』《》＜＞〈〉〔〕［］【】〖〗〃…—─　～│┬▆＊＋－＝'

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ CBETA

載入藏經資料



155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
 
# File 'lib/cbeta.rb', line 155

def initialize()
  @canon_abbr = {}
  @canon_nickname = {}
  fn = File.join(File.dirname(__FILE__), 'data/canons.csv')
  CSV.foreach(fn, :headers => true, encoding: 'utf-8') do |row|
    id = row['id']
    unless row['nickname'].nil?
      @canon_nickname[id] = row['nickname']
    end
    next if row['abbreviation'].nil?
    next if row['abbreviation'].empty?
    @canon_abbr[id] = row['abbreviation']
  end
  
  fn = File.join(File.dirname(__FILE__), 'data/categories.json')
  s = File.read(fn)
  @categories = JSON.parse(s)
end

Class Method Details

.get_canon_from_vol(vol) ⇒ String

由 冊號 取得 藏經 ID



32
33
34
 
# File 'lib/cbeta.rb', line 32

def self.get_canon_from_vol(vol)
  vol.sub(/^(#{CANON}).*$/, '\1')
end

.get_canon_id_from_linehead(linehead) ⇒ String

由 行首資訊 取得 藏經 ID



18
19
20
 
# File 'lib/cbeta.rb', line 18

def self.get_canon_id_from_linehead(linehead)
  linehead.sub(/^(#{CANON}).*$/, '\1')
end

.get_canon_id_from_work_id(work) ⇒ String

由 典籍編號 取得 藏經 ID



25
26
27
 
# File 'lib/cbeta.rb', line 25

def self.get_canon_id_from_work_id(work)
  work.sub(/^(#{CANON}).*$/, '\1')
end

.get_linehead(file_basename, lb) ⇒ String 



39
40
41
42
43
44
45
46
47
48
 
# File 'lib/cbeta.rb', line 39

def self.get_linehead(file_basename, lb)
  if file_basename.match(/^(T\d\dn0220)/)
    r = $1
  else
    r = file_basename
  end
  r += '_' if r.match(/\d$/)
  r += 'p' + lb
  r
end

.get_sort_order_from_canon_id(canon) ⇒ String

由「藏經 ID」取得「排序用編號」，例如：傳入 “T” 回傳 “A”；傳入 “X” 回傳 “B”



81
82
83
84
85
86
87
88
89
90
 
# File 'lib/cbeta.rb', line 81

def self.get_sort_order_from_canon_id(canon)
  # CBETA 提供，惠敏法師最後決定的全文檢索順序表, 2016-06-03
  i = SORT_ORDER.index(canon)
  if i.nil?
    puts "unknown canon id: #{canon}" 
    return nil
  end
  
  (i + 'A'.ord).chr
end

.get_work_id_from_file_basename(fn) ⇒ String

由 XML檔主檔名 取得 典籍編號



72
73
74
75
76
 
# File 'lib/cbeta.rb', line 72

def self.get_work_id_from_file_basename(fn)
  r = fn.sub(/^(#{CANON})\d{2,3}n(.*)$/, '\1\2')
  r = 'T0220' if r.start_with? 'T0220'
  r
end

.get_xml_file_from_vol_and_work(vol, work) ⇒ String

由 冊號 及 典籍編號 取得 XML 主檔名



54
55
56
 
# File 'lib/cbeta.rb', line 54

def self.get_xml_file_from_vol_and_work(vol, work)
  vol + 'n' + work.sub(/^(#{CANON})(.*)$/, '\2')
end

.linehead_to_s(linehead) ⇒ String

將行首資訊轉為引用格式

Examples:

CBETA.linehead_to_s('T85n2838_p1291a03')
# return "T85, no. 2838, p. 1291, a03"



100
101
102
103
104
105
 
# File 'lib/cbeta.rb', line 100

def self.linehead_to_s(linehead)
  linehead.match(/^((?:#{CANON})\d+)n(.*)_p(\d+)([a-z]\d+)$/) {
    return "#{$1}, no. #{$2}, p. #{$3}, #{$4}"
  }
  nil
end

.linehead_to_xml_file_path(linehead) ⇒ String

由 行首資訊 取得 XML檔相對路徑



61
62
63
64
65
66
67
 
# File 'lib/cbeta.rb', line 61

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

.normalize_vol(vol) ⇒ Object 



107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
 
# File 'lib/cbeta.rb', line 107

def self.normalize_vol(vol)
  if vol.match(/^(#{CANON})(.*)$/)
    canon = $1
    vol = $2
  
    if VOL3.include? canon
      # 這些藏經的冊號是三碼
      vol_len = 3
    else
      vol_len = 2      
    end
    canon + vol.rjust(vol_len, '0')
  else
    abort "unknown vol format: #{vol}"
  end
end

.open_xml(fn) ⇒ Object 



124
125
126
127
128
129
 
# File 'lib/cbeta.rb', line 124

def self.open_xml(fn)
  s = File.read(fn)
  doc = Nokogiri::XML(s)
  doc.remove_namespaces!()
  doc
end

.pua(gid) ⇒ Object

傳入 缺字碼，傳回 Unicode PUA 字元



132
133
134
135
136
137
138
139
140
 
# File 'lib/cbeta.rb', line 132

def self.pua(gid)
  if gid.start_with? 'SD'
    siddham_pua(gid)
  elsif gid.start_with? 'RJ'
    ranjana_pua(gid)
  else
    [0xf0000 + gid[2..-1].to_i].pack 'U'
  end
end

.ranjana_pua(gid) ⇒ Object

傳入 蘭札體 缺字碼，傳回 Unicode PUA 字元



143
144
145
146
 
# File 'lib/cbeta.rb', line 143

def self.ranjana_pua(gid)
  i = 0x100000 + gid[-4..-1].hex
  [i].pack("U")
end

.siddham_pua(gid) ⇒ Object

傳入 悉曇字 缺字碼，傳回 Unicode PUA 字元



149
150
151
152
 
# File 'lib/cbeta.rb', line 149

def self.siddham_pua(gid)
  i = 0xFA000 + gid[-4..-1].hex
  [i].pack("U")
end

Instance Method Details

#get_canon_abbr(id) ⇒ String

取得藏經略名

Examples:

cbeta = CBETA.new
cbeta.get_canon_abbr('T') # return "大"



202
203
204
205
206
 
# File 'lib/cbeta.rb', line 202

def get_canon_abbr(id)
   r = get_canon_symbol(id)
   return nil if r.nil?
   r.sub(/^【(.*?)】$/, '\1')
end

#get_canon_nickname(id) ⇒ String 



176
177
178
179
 
# File 'lib/cbeta.rb', line 176

def get_canon_nickname(id)
  return nil unless @canon_nickname.key? id
  @canon_nickname[id]
end

#get_canon_symbol(id) ⇒ String

取得藏經略符

Examples:

cbeta = CBETA.new
cbeta.get_canon_symbol('T') # return "【大】"



189
190
191
192
 
# File 'lib/cbeta.rb', line 189

def get_canon_symbol(id)
  return nil unless @canon_abbr.key? id
  @canon_abbr[id]
end

#get_category(book_id) ⇒ String

傳入經號，取得部類

Examples:

cbeta = CBETA.new
cbeta.get_category('T0220') # return '般若部類'



215
216
217
 
# File 'lib/cbeta.rb', line 215

def get_category(book_id)
  @categories[book_id]
end