cbeta 0.4.3 → 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/cbeta.rb +2 -1
- data/lib/cbeta/gaiji.rb +1 -1
- data/lib/cbeta/p5a_to_epub.rb +780 -0
- data/lib/cbeta/p5a_to_html.rb +5 -11
- data/lib/cbeta/p5a_to_simple_html.rb +0 -5
- data/lib/cbeta/p5a_to_text.rb +0 -5
- data/lib/{canons.csv → data/canons.csv} +0 -0
- data/lib/data/epub-donate.xhtml +23 -0
- data/lib/data/epub-nav.xhtml +11 -0
- data/lib/data/epub-readme.xhtml +27 -0
- data/lib/{cbeta → data}/gaiji.json +0 -0
- data/lib/{cbeta → data}/unicode-1.1.json +0 -0
- metadata +9 -5
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 416026a7921c0c2bb6c602be134095f4079951fe
|
4
|
+
data.tar.gz: d72055681fb1c8ff22a4317ed0310fc368381e1a
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 0d71cdacc97c1d6111cc2dc1dc9b5190d2398f05b9a45280744b7475579dd8f612efa382c0cfd16f07429391f99e330a8fe1c3db1c48d770076f90abe20d15c4
|
7
|
+
data.tar.gz: bd62c4cdfe0def5b62d7440f0ec029c2535e1384d0ac9865e2ba91a643db46b6a1fed02ed8a4c4435d9e26b878d8acfc7e3c91994bac50899b7e8ec4413b8717
|
data/lib/cbeta.rb
CHANGED
@@ -35,7 +35,7 @@ class CBETA
|
|
35
35
|
|
36
36
|
# 載入藏經資料
|
37
37
|
def initialize()
|
38
|
-
fn = File.join(File.dirname(__FILE__), 'canons.csv')
|
38
|
+
fn = File.join(File.dirname(__FILE__), 'data/canons.csv')
|
39
39
|
text = File.read(fn)
|
40
40
|
@canon_abbr = {}
|
41
41
|
CSV.parse(text, :headers => true) do |row|
|
@@ -61,6 +61,7 @@ end
|
|
61
61
|
|
62
62
|
require 'cbeta/gaiji'
|
63
63
|
require 'cbeta/bm_to_text'
|
64
|
+
require 'cbeta/p5a_to_epub'
|
64
65
|
require 'cbeta/p5a_to_html'
|
65
66
|
require 'cbeta/p5a_to_simple_html'
|
66
67
|
require 'cbeta/p5a_to_text'
|
data/lib/cbeta/gaiji.rb
CHANGED
@@ -0,0 +1,780 @@
|
|
1
|
+
require 'cgi'
|
2
|
+
require 'date'
|
3
|
+
require 'fileutils'
|
4
|
+
require 'json'
|
5
|
+
require 'nokogiri'
|
6
|
+
require 'set'
|
7
|
+
require 'gepub'
|
8
|
+
require 'pp'
|
9
|
+
|
10
|
+
# Convert CBETA XML P5a to EPUB
|
11
|
+
#
|
12
|
+
# CBETA XML P5a 可由此取得: https://github.com/cbeta-git/xml-p5a
|
13
|
+
class CBETA::P5aToEPUB
|
14
|
+
# 內容不輸出的元素
|
15
|
+
PASS=['back', 'teiHeader']
|
16
|
+
|
17
|
+
# 某版用字缺的符號
|
18
|
+
MISSING = '-'
|
19
|
+
|
20
|
+
NAV_TEMPLATE = File.read(File.join(File.dirname(__FILE__), '../data/epub-nav.xhtml'))
|
21
|
+
MAIN = 'main.xhtml'
|
22
|
+
|
23
|
+
# @param temp_folder [String] 供 EPUB 暫存工作檔案的路徑
|
24
|
+
# @param graphic_base [String] 存放圖片的路徑
|
25
|
+
def initialize(temp_folder, graphic_base)
|
26
|
+
@temp_folder = temp_folder
|
27
|
+
@graphic_base = graphic_base
|
28
|
+
@cbeta = CBETA.new
|
29
|
+
@gaijis = CBETA::Gaiji.new
|
30
|
+
end
|
31
|
+
|
32
|
+
# 將某個 xml 轉為一個 EPUB
|
33
|
+
def convert_file(input_path, output_path)
|
34
|
+
return false unless input_path.end_with? '.xml'
|
35
|
+
|
36
|
+
FileUtils.remove_dir(@temp_folder, force=true)
|
37
|
+
FileUtils::mkdir_p @temp_folder
|
38
|
+
|
39
|
+
@book_id = File.basename(input_path, ".xml")
|
40
|
+
|
41
|
+
sutra_init
|
42
|
+
|
43
|
+
handle_file(input_path)
|
44
|
+
create_epub(output_path)
|
45
|
+
end
|
46
|
+
|
47
|
+
# 將某個資料夾下的每個 xml 檔都轉為一個對應的 EPUB。
|
48
|
+
# 資料夾可以是巢狀,全部都會遞迴處理。
|
49
|
+
#
|
50
|
+
# @example
|
51
|
+
# require 'cbeta'
|
52
|
+
#
|
53
|
+
# TEMP = '/temp/epub-work'
|
54
|
+
# IMG = '/Users/ray/Documents/Projects/D道安/figures'
|
55
|
+
#
|
56
|
+
# c = CBETA::P5aToEPUB.new(TEMP, IMG)
|
57
|
+
# c.convert_folder('/Users/ray/Documents/Projects/D道安/xml-p5a/DA', '/temp/cbeta-epub/DA')
|
58
|
+
def convert_folder(input_folder, output_folder)
|
59
|
+
FileUtils.remove_dir(output_folder, force=true)
|
60
|
+
FileUtils::mkdir_p output_folder
|
61
|
+
Dir.foreach(input_folder) do |f|
|
62
|
+
next if f.start_with? '.'
|
63
|
+
p1 = File.join(input_folder, f)
|
64
|
+
if File.file?(p1)
|
65
|
+
f.sub!(/.xml$/, '.epub')
|
66
|
+
p2 = File.join(output_folder, f)
|
67
|
+
convert_file(p1, p2)
|
68
|
+
else
|
69
|
+
p2 = File.join(output_folder, f)
|
70
|
+
convert_folder(p1, p2)
|
71
|
+
end
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
# 將多個 xml 檔案合成一個 EPUB
|
76
|
+
#
|
77
|
+
# @example 大般若經 跨三冊 合成一個 EPUB
|
78
|
+
# require 'cbeta'
|
79
|
+
#
|
80
|
+
# TEMP = '/temp/epub-work'
|
81
|
+
#
|
82
|
+
# xml_files = [
|
83
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/05/T05n0220a.xml',
|
84
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/06/T06n0220b.xml',
|
85
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220c.xml',
|
86
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220d.xml',
|
87
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220e.xml',
|
88
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220f.xml',
|
89
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220g.xml',
|
90
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220h.xml',
|
91
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220i.xml',
|
92
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220j.xml',
|
93
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220k.xml',
|
94
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220l.xml',
|
95
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220m.xml',
|
96
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220n.xml',
|
97
|
+
# '/Users/ray/git-repos/cbeta-xml-p5a/T/07/T07n0220o.xml',
|
98
|
+
# ]
|
99
|
+
#
|
100
|
+
# c = CBETA::P5aToEPUB.new(TEMP)
|
101
|
+
# c.convert_sutra('T0220', '大般若經', xml_files, '/temp/cbeta-epub/T0220.epub')
|
102
|
+
def convert_sutra(book_id, title, xml_files, out)
|
103
|
+
@book_id = book_id
|
104
|
+
sutra_init
|
105
|
+
xml_files.each { |f| handle_file(f) }
|
106
|
+
|
107
|
+
@title = title
|
108
|
+
create_epub(out)
|
109
|
+
end
|
110
|
+
|
111
|
+
private
|
112
|
+
|
113
|
+
def copy_static_files(src, dest)
|
114
|
+
p1 = File.join(File.dirname(__FILE__), '../data', src)
|
115
|
+
p2 = File.join(@temp_folder, dest)
|
116
|
+
FileUtils.copy(p1, p2)
|
117
|
+
end
|
118
|
+
|
119
|
+
def create_epub(output_path)
|
120
|
+
copy_static_files('epub-readme.xhtml', 'readme.xhtml')
|
121
|
+
copy_static_files('epub-donate.xhtml', 'donate.xhtml')
|
122
|
+
create_main_html
|
123
|
+
create_nav_html
|
124
|
+
|
125
|
+
title = @title
|
126
|
+
book_id = @book_id
|
127
|
+
builder = GEPUB::Builder.new {
|
128
|
+
language 'zh-TW'
|
129
|
+
unique_identifier "http://www.cbeta.org/#{book_id}", 'BookID', 'URL'
|
130
|
+
title title
|
131
|
+
|
132
|
+
creator 'CBETA'
|
133
|
+
|
134
|
+
contributors 'DILA'
|
135
|
+
|
136
|
+
date Date.today.to_s
|
137
|
+
}
|
138
|
+
|
139
|
+
# in resources block, you can define resources by its relative path and datasource.
|
140
|
+
# item creator methods are: files, file.
|
141
|
+
builder.resources(:workdir => @temp_folder) {
|
142
|
+
glob 'img/*'
|
143
|
+
|
144
|
+
# this is navigation document.
|
145
|
+
nav 'nav.xhtml'
|
146
|
+
|
147
|
+
# ordered item. will be added to spine.
|
148
|
+
ordered {
|
149
|
+
file 'readme.xhtml'
|
150
|
+
file 'main.xhtml'
|
151
|
+
file 'donate.xhtml'
|
152
|
+
}
|
153
|
+
}
|
154
|
+
builder.generate_epub(output_path)
|
155
|
+
puts "output: #{output_path}"
|
156
|
+
end
|
157
|
+
|
158
|
+
def create_main_html
|
159
|
+
fn = File.join(@temp_folder, MAIN)
|
160
|
+
s = <<eos
|
161
|
+
<html xmlns="http://www.w3.org/1999/xhtml">
|
162
|
+
<head>
|
163
|
+
<meta charset="utf-8" />
|
164
|
+
<title>#{@title}</title>
|
165
|
+
</head>
|
166
|
+
<body>
|
167
|
+
<div id='body'>
|
168
|
+
eos
|
169
|
+
s += @main_text + "\n</div><!-- end of div[@id='body'] -->\n"
|
170
|
+
s += "<div id='back'>\n" + @back + "</div></body></html>\n"
|
171
|
+
File.write(fn, s)
|
172
|
+
end
|
173
|
+
|
174
|
+
def create_nav_html
|
175
|
+
@nav_root_ol.add_child("<li><a href='donate.xhtml'>贊助資訊</a></li>")
|
176
|
+
|
177
|
+
fn = File.join(@temp_folder, 'nav.xhtml')
|
178
|
+
s = NAV_TEMPLATE % to_html(@nav_root_ol)
|
179
|
+
File.write(fn, s)
|
180
|
+
end
|
181
|
+
|
182
|
+
def handle_anchor(e)
|
183
|
+
id = e['id']
|
184
|
+
if e.has_attribute?('id')
|
185
|
+
if id.start_with?('nkr_note_orig')
|
186
|
+
note = @notes[id]
|
187
|
+
note_text = traverse(note)
|
188
|
+
n = id[/^nkr_note_orig_(.*)$/, 1]
|
189
|
+
@back += "<span class='footnote' id='n#{n}'>#{note_text}</span>\n"
|
190
|
+
return "<a class='noteAnchor' href='#n#{n}'></a>"
|
191
|
+
elsif id.start_with? 'fx'
|
192
|
+
return "<span class='star'>[*]</span>"
|
193
|
+
end
|
194
|
+
end
|
195
|
+
|
196
|
+
if e.has_attribute?('type')
|
197
|
+
if e['type'] == 'circle'
|
198
|
+
return '◎'
|
199
|
+
end
|
200
|
+
end
|
201
|
+
|
202
|
+
''
|
203
|
+
end
|
204
|
+
|
205
|
+
def handle_app(e)
|
206
|
+
r = ''
|
207
|
+
if e['type'] == 'star'
|
208
|
+
c = e['corresp'][1..-1]
|
209
|
+
r = "<a class='noteAnchor star' href='#n#{c}'></a>"
|
210
|
+
end
|
211
|
+
r + traverse(e)
|
212
|
+
end
|
213
|
+
|
214
|
+
def handle_byline(e)
|
215
|
+
r = '<p class="byline">'
|
216
|
+
r += "<span class='lineInfo'>#{@lb}</span>"
|
217
|
+
r += traverse(e)
|
218
|
+
r + '</p>'
|
219
|
+
end
|
220
|
+
|
221
|
+
def handle_cell(e)
|
222
|
+
doc = Nokogiri::XML::Document.new
|
223
|
+
cell = doc.create_element('td')
|
224
|
+
cell['rowspan'] = e['rows'] if e.key? 'rows'
|
225
|
+
cell['colspan'] = e['cols'] if e.key? 'cols'
|
226
|
+
cell.inner_html = traverse(e)
|
227
|
+
to_html(cell) + "\n"
|
228
|
+
end
|
229
|
+
|
230
|
+
def handle_corr(e)
|
231
|
+
r = ''
|
232
|
+
if e.parent.name == 'choice'
|
233
|
+
sic = e.parent.at_xpath('sic')
|
234
|
+
unless sic.nil?
|
235
|
+
@dila_note += 1
|
236
|
+
r = "<a class='noteAnchor dila' href='#dila_note#{@dila_note}'></a>"
|
237
|
+
|
238
|
+
note = @orig
|
239
|
+
sic_text = traverse(sic, 'back')
|
240
|
+
if sic_text.empty?
|
241
|
+
note += MISSING
|
242
|
+
else
|
243
|
+
note += sic_text
|
244
|
+
end
|
245
|
+
@back += "<span class='footnote_dila' id='dila_note#{@dila_note}'>#{note}</span>\n"
|
246
|
+
end
|
247
|
+
end
|
248
|
+
r + "<span class='cbeta'>%s</span>" % traverse(e)
|
249
|
+
end
|
250
|
+
|
251
|
+
def handle_div(e)
|
252
|
+
if e.has_attribute? 'type'
|
253
|
+
@open_divs << e
|
254
|
+
r = traverse(e)
|
255
|
+
@open_divs.pop
|
256
|
+
return "<div class='div-#{e['type']}'>#{r}</div>"
|
257
|
+
else
|
258
|
+
return traverse(e)
|
259
|
+
end
|
260
|
+
end
|
261
|
+
|
262
|
+
def handle_figure(e)
|
263
|
+
"<div class='figure'>%s</div>" % traverse(e)
|
264
|
+
end
|
265
|
+
|
266
|
+
def handle_g(e, mode)
|
267
|
+
# if 有 <mapping type="unicode">
|
268
|
+
# if 不在 Unicode Extension C, D, E 範圍裡
|
269
|
+
# 直接採用
|
270
|
+
# else
|
271
|
+
# 預設呈現 unicode, 但仍包缺字資訊,供點選開 popup
|
272
|
+
# else if 有 <mapping type="normal_unicode">
|
273
|
+
# 預設呈現 normal_unicode, 但仍包缺字資訊,供點選開 popup
|
274
|
+
# else if 有 normalized form
|
275
|
+
# 預設呈現 normalized form, 但仍包缺字資訊,供點選開 popup
|
276
|
+
# else
|
277
|
+
# 預設呈現組字式, 但仍包缺字資訊,供點選開 popup
|
278
|
+
gid = e['ref'][1..-1]
|
279
|
+
g = @gaijis[gid]
|
280
|
+
abort "Line:#{__LINE__} 無缺字資料:#{gid}" if g.nil?
|
281
|
+
zzs = g['zzs']
|
282
|
+
|
283
|
+
if mode == 'txt'
|
284
|
+
return g['roman'] if gid.start_with?('SD')
|
285
|
+
if zzs.nil?
|
286
|
+
abort "缺組字式:#{g}"
|
287
|
+
else
|
288
|
+
return zzs
|
289
|
+
end
|
290
|
+
end
|
291
|
+
|
292
|
+
if gid.start_with?('SD')
|
293
|
+
case gid
|
294
|
+
when 'SD-E35A'
|
295
|
+
return '('
|
296
|
+
when 'SD-E35B'
|
297
|
+
return ')'
|
298
|
+
else
|
299
|
+
return "<span class='siddam' roman='#{g['roman']}' code='#{gid}' char='#{g['sd-char']}'/>"
|
300
|
+
end
|
301
|
+
end
|
302
|
+
|
303
|
+
if gid.start_with?('RJ')
|
304
|
+
return "<span class='ranja' roman='#{g['roman']}' code='#{gid}' char='#{g['rj-char']}'/>"
|
305
|
+
end
|
306
|
+
|
307
|
+
default = ''
|
308
|
+
if g.has_key?('unicode')
|
309
|
+
#if @unicode1.include?(g['unicode'])
|
310
|
+
# 如果在 unicode ext-C, ext-D, ext-E 範圍內
|
311
|
+
if (0x2A700..0x2CEAF).include? g['unicode'].hex
|
312
|
+
default = g['unicode-char']
|
313
|
+
else
|
314
|
+
return g['unicode-char'] # 直接採用 unicode
|
315
|
+
end
|
316
|
+
end
|
317
|
+
|
318
|
+
nor = ''
|
319
|
+
if g.has_key?('normal_unicode')
|
320
|
+
nor = g['normal_unicode']
|
321
|
+
default = nor if default.empty?
|
322
|
+
end
|
323
|
+
|
324
|
+
if g.has_key?('normal')
|
325
|
+
nor += ', ' unless nor==''
|
326
|
+
nor += g['normal']
|
327
|
+
default = g['normal'] if default.empty?
|
328
|
+
end
|
329
|
+
|
330
|
+
default = zzs if default.empty?
|
331
|
+
|
332
|
+
href = 'http://dict.cbeta.org/dict_word/gaiji-cb/%s/%s.gif' % [gid[2, 2], gid]
|
333
|
+
unless @back.include?(href)
|
334
|
+
@back += "<span id='#{gid}' class='gaijiInfo' figure_url='#{href}' zzs='#{zzs}' nor='#{nor}'>#{default}</span>\n"
|
335
|
+
end
|
336
|
+
"<a class='gaijiAnchor' href='##{gid}'>#{default}</a>"
|
337
|
+
end
|
338
|
+
|
339
|
+
def handle_graphic(e)
|
340
|
+
url = e['url']
|
341
|
+
url.sub!(/^.*figures\/(.*)$/, '\1')
|
342
|
+
|
343
|
+
src = File.join(@graphic_base, url)
|
344
|
+
basename = File.basename(src)
|
345
|
+
dest = File.join(@temp_folder, 'img', basename)
|
346
|
+
FileUtils.copy(src, dest)
|
347
|
+
|
348
|
+
"<img src='img/#{basename}' />"
|
349
|
+
end
|
350
|
+
|
351
|
+
def handle_head(e)
|
352
|
+
r = ''
|
353
|
+
unless e['type'] == 'added'
|
354
|
+
i = @open_divs.size
|
355
|
+
r = "<p class='head' data-head-level='#{i}'>%s</p>" % traverse(e)
|
356
|
+
end
|
357
|
+
r
|
358
|
+
end
|
359
|
+
|
360
|
+
def handle_item(e)
|
361
|
+
"<li>%s</li>\n" % traverse(e)
|
362
|
+
end
|
363
|
+
|
364
|
+
def handle_juan(e)
|
365
|
+
"<p class='juan'>%s</p>" % traverse(e)
|
366
|
+
end
|
367
|
+
|
368
|
+
def handle_l(e)
|
369
|
+
if @lg_type == 'abnormal'
|
370
|
+
return traverse(e)
|
371
|
+
end
|
372
|
+
|
373
|
+
@in_l = true
|
374
|
+
|
375
|
+
doc = Nokogiri::XML::Document.new
|
376
|
+
cell = doc.create_element('div')
|
377
|
+
cell['class'] = 'lg-cell'
|
378
|
+
cell.inner_html = traverse(e)
|
379
|
+
|
380
|
+
if @first_l
|
381
|
+
parent = e.parent()
|
382
|
+
if parent.has_attribute?('rend')
|
383
|
+
indent = parent['rend'].scan(/text-indent:[^:]*/)
|
384
|
+
unless indent.empty?
|
385
|
+
cell['style'] = indent[0]
|
386
|
+
end
|
387
|
+
end
|
388
|
+
@first_l = false
|
389
|
+
end
|
390
|
+
r = to_html(cell)
|
391
|
+
|
392
|
+
unless @lg_row_open
|
393
|
+
r = "\n<div class='lg-row'>" + r
|
394
|
+
@lg_row_open = true
|
395
|
+
end
|
396
|
+
@in_l = false
|
397
|
+
r
|
398
|
+
end
|
399
|
+
|
400
|
+
def handle_lb(e)
|
401
|
+
# 卍續藏有 X 跟 R 兩種 lb, 只處理 X
|
402
|
+
return '' if e['ed'] != @series
|
403
|
+
|
404
|
+
@lb = e['n']
|
405
|
+
r = ''
|
406
|
+
#if e.parent.name == 'lg' and $lg_row_open
|
407
|
+
if @lg_row_open && !@in_l
|
408
|
+
# 每行偈頌放在一個 lg-row 裡面
|
409
|
+
# T46n1937, p. 914a01, l 包雙行夾註跨行
|
410
|
+
# T20n1092, 337c16, lb 在 l 中間,不結束 lg-row
|
411
|
+
r += "</div><!-- end of lg-row -->"
|
412
|
+
@lg_row_open = false
|
413
|
+
end
|
414
|
+
unless @next_line_buf.empty?
|
415
|
+
r += @next_line_buf
|
416
|
+
@next_line_buf = ''
|
417
|
+
end
|
418
|
+
r
|
419
|
+
end
|
420
|
+
|
421
|
+
def handle_lem(e)
|
422
|
+
r = ''
|
423
|
+
w = e['wit']
|
424
|
+
if w.include? 'CBETA' and not w.include? @orig
|
425
|
+
@dila_note += 1
|
426
|
+
r = "<a class='noteAnchor dila' href='#dila_note#{@dila_note}'></a>"
|
427
|
+
r += "<span class='cbeta'>%s</span>" % traverse(e)
|
428
|
+
|
429
|
+
note = lem_note_cf(e)
|
430
|
+
note += lem_note_rdg(e)
|
431
|
+
@back += "<span class='footnote_dila' id='dila_note#{@dila_note}'>#{note}</span>\n"
|
432
|
+
else
|
433
|
+
r = traverse(e)
|
434
|
+
end
|
435
|
+
r
|
436
|
+
end
|
437
|
+
|
438
|
+
def handle_lg(e)
|
439
|
+
r = ''
|
440
|
+
@lg_type = e['type']
|
441
|
+
if @lg_type == 'abnormal'
|
442
|
+
r = "<p class='lg-abnormal'>" + traverse(e) + "</p>"
|
443
|
+
else
|
444
|
+
@first_l = true
|
445
|
+
doc = Nokogiri::XML::Document.new
|
446
|
+
node = doc.create_element('div')
|
447
|
+
node['class'] = 'lg'
|
448
|
+
if e.has_attribute?('rend')
|
449
|
+
rend = e['rend'].gsub(/text-indent:[^:]*/, '')
|
450
|
+
node['style'] = rend
|
451
|
+
end
|
452
|
+
@lg_row_open = false
|
453
|
+
node.inner_html = traverse(e)
|
454
|
+
if @lg_row_open
|
455
|
+
node.inner_html += '</div><!-- end of lg -->'
|
456
|
+
@lg_row_open = false
|
457
|
+
end
|
458
|
+
r = "\n" + to_html(node)
|
459
|
+
end
|
460
|
+
r
|
461
|
+
end
|
462
|
+
|
463
|
+
def handle_list(e)
|
464
|
+
"<ul>%s</ul>" % traverse(e)
|
465
|
+
end
|
466
|
+
|
467
|
+
def handle_milestone(e)
|
468
|
+
''
|
469
|
+
end
|
470
|
+
|
471
|
+
def handle_mulu(e)
|
472
|
+
return '' if e['type'] == '卷'
|
473
|
+
|
474
|
+
level = e['level'].to_i
|
475
|
+
while @current_nav.size > level
|
476
|
+
@current_nav.pop
|
477
|
+
end
|
478
|
+
|
479
|
+
label = traverse(e, 'txt')
|
480
|
+
@mulu_count += 1
|
481
|
+
li = @current_nav.last.add_child("<li><a href='#{@main_html}#mulu#{@mulu_count}'>#{label}</a></li>").first
|
482
|
+
ol = li.add_child('<ol></ol>').first
|
483
|
+
@current_nav << ol
|
484
|
+
"<a id='mulu#{@mulu_count}' />"
|
485
|
+
end
|
486
|
+
|
487
|
+
def handle_node(e, mode)
|
488
|
+
return '' if e.comment?
|
489
|
+
return handle_text(e, mode) if e.text?
|
490
|
+
return '' if PASS.include?(e.name)
|
491
|
+
r = case e.name
|
492
|
+
when 'anchor' then handle_anchor(e)
|
493
|
+
when 'app' then handle_app(e)
|
494
|
+
when 'byline' then handle_byline(e)
|
495
|
+
when 'cell' then handle_cell(e)
|
496
|
+
when 'corr' then handle_corr(e)
|
497
|
+
when 'div' then handle_div(e)
|
498
|
+
when 'figure' then handle_figure(e)
|
499
|
+
when 'foreign' then ''
|
500
|
+
when 'g' then handle_g(e, mode)
|
501
|
+
when 'graphic' then handle_graphic(e)
|
502
|
+
when 'head' then handle_head(e)
|
503
|
+
when 'item' then handle_item(e)
|
504
|
+
when 'juan' then handle_juan(e)
|
505
|
+
when 'l' then handle_l(e)
|
506
|
+
when 'lb' then handle_lb(e)
|
507
|
+
when 'lem' then handle_lem(e)
|
508
|
+
when 'lg' then handle_lg(e)
|
509
|
+
when 'list' then handle_list(e)
|
510
|
+
when 'mulu' then handle_mulu(e)
|
511
|
+
when 'note' then handle_note(e)
|
512
|
+
when 'milestone' then handle_milestone(e)
|
513
|
+
when 'p' then handle_p(e)
|
514
|
+
when 'rdg' then ''
|
515
|
+
when 'reg' then ''
|
516
|
+
when 'row' then handle_row(e)
|
517
|
+
when 'sic' then ''
|
518
|
+
when 'sg' then handle_sg(e)
|
519
|
+
when 't' then handle_t(e)
|
520
|
+
when 'tt' then handle_tt(e)
|
521
|
+
when 'table' then handle_table(e)
|
522
|
+
else traverse(e)
|
523
|
+
end
|
524
|
+
r
|
525
|
+
end
|
526
|
+
|
527
|
+
def handle_note(e)
|
528
|
+
n = e['n']
|
529
|
+
if e.has_attribute?('type')
|
530
|
+
t = e['type']
|
531
|
+
case t
|
532
|
+
when 'equivalent'
|
533
|
+
return ''
|
534
|
+
when 'orig'
|
535
|
+
return handle_note_orig(e)
|
536
|
+
when 'orig_biao'
|
537
|
+
return handle_note_orig(e, 'biao')
|
538
|
+
when 'orig_ke'
|
539
|
+
return handle_note_orig(e, 'ke')
|
540
|
+
when 'mod'
|
541
|
+
@pass << false
|
542
|
+
s = traverse(e)
|
543
|
+
@pass.pop
|
544
|
+
@back += "<span class='footnote_cb' id='n#{n}'>#{s}</span>\n"
|
545
|
+
return "<a class='noteAnchor' href='#n#{n}'></a>"
|
546
|
+
when 'rest'
|
547
|
+
return ''
|
548
|
+
else
|
549
|
+
return '' if t.start_with?('cf')
|
550
|
+
end
|
551
|
+
end
|
552
|
+
|
553
|
+
if e.has_attribute?('resp')
|
554
|
+
return '' if e['resp'].start_with? 'CBETA'
|
555
|
+
end
|
556
|
+
|
557
|
+
if e.has_attribute?('place') && e['place']=='inline'
|
558
|
+
r = traverse(e)
|
559
|
+
return "<span class='doube-line-note'>#{r}</span>"
|
560
|
+
else
|
561
|
+
return traverse(e)
|
562
|
+
end
|
563
|
+
end
|
564
|
+
|
565
|
+
def handle_note_orig(e, anchor_type=nil)
|
566
|
+
n = e['n']
|
567
|
+
@pass << false
|
568
|
+
s = traverse(e)
|
569
|
+
@pass.pop
|
570
|
+
@back += "<span class='footnote_orig' id='n#{n}'>#{s}</span>\n"
|
571
|
+
|
572
|
+
if @mod_notes.include? n
|
573
|
+
return ''
|
574
|
+
else
|
575
|
+
label = case anchor_type
|
576
|
+
when 'biao' then " data-label='標#{n[-2..-1]}'"
|
577
|
+
when 'ke' then " data-label='科#{n[-2..-1]}'"
|
578
|
+
else ''
|
579
|
+
end
|
580
|
+
return "<a class='noteAnchor' href='#n#{n}'#{label}></a>"
|
581
|
+
end
|
582
|
+
end
|
583
|
+
|
584
|
+
def handle_p(e)
|
585
|
+
r = "<div class='p'>\n"
|
586
|
+
r += traverse(e)
|
587
|
+
r + "</div>\n"
|
588
|
+
end
|
589
|
+
|
590
|
+
def handle_row(e)
|
591
|
+
"<tr>" + traverse(e) + "</tr>\n"
|
592
|
+
end
|
593
|
+
|
594
|
+
def handle_sg(e)
|
595
|
+
'(' + traverse(e) + ')'
|
596
|
+
end
|
597
|
+
|
598
|
+
def handle_file(xml_fn)
|
599
|
+
puts "read #{xml_fn}"
|
600
|
+
@in_l = false
|
601
|
+
@lg_row_open = false
|
602
|
+
@mod_notes = Set.new
|
603
|
+
@next_line_buf = ''
|
604
|
+
@open_divs = []
|
605
|
+
|
606
|
+
if @book_id.start_with? 'DA'
|
607
|
+
@orig = nil?
|
608
|
+
else
|
609
|
+
@orig = @cbeta.get_canon_abbr(@book_id[0])
|
610
|
+
abort "未處理底本: #{@book_id[0]}" if @orig.nil?
|
611
|
+
end
|
612
|
+
|
613
|
+
text = parse_xml(xml_fn)
|
614
|
+
|
615
|
+
# 註標移到 lg-cell 裡面,不然以 table 呈現 lg 會有問題
|
616
|
+
text.gsub!(/(<a class='noteAnchor'[^>]*><\/a>)(<div class="lg-cell"[^>]*>)/, '\2\1')
|
617
|
+
|
618
|
+
@main_text += text
|
619
|
+
end
|
620
|
+
|
621
|
+
def handle_t(e)
|
622
|
+
if e.has_attribute? 'place'
|
623
|
+
return '' if e['place'].include? 'foot'
|
624
|
+
end
|
625
|
+
r = traverse(e)
|
626
|
+
|
627
|
+
# <tt type="app"> 不是 悉漢雙行對照
|
628
|
+
return r if @tt_type == 'app'
|
629
|
+
|
630
|
+
# 處理雙行對照
|
631
|
+
i = e.xpath('../t').index(e)
|
632
|
+
case i
|
633
|
+
when 0
|
634
|
+
return r + ' '
|
635
|
+
when 1
|
636
|
+
@next_line_buf += r + ' '
|
637
|
+
return ''
|
638
|
+
else
|
639
|
+
return r
|
640
|
+
end
|
641
|
+
end
|
642
|
+
|
643
|
+
def handle_tt(e)
|
644
|
+
@tt_type = e['type']
|
645
|
+
traverse(e)
|
646
|
+
end
|
647
|
+
|
648
|
+
def handle_table(e)
|
649
|
+
"<table>" + traverse(e) + "</table>"
|
650
|
+
end
|
651
|
+
|
652
|
+
def handle_text(e, mode)
|
653
|
+
s = e.content().chomp
|
654
|
+
return '' if s.empty?
|
655
|
+
return '' if e.parent.name == 'app'
|
656
|
+
|
657
|
+
# cbeta xml 文字之間會有多餘的換行
|
658
|
+
r = s.gsub(/[\n\r]/, '')
|
659
|
+
|
660
|
+
# 把 & 轉為 &
|
661
|
+
CGI.escapeHTML(r)
|
662
|
+
end
|
663
|
+
|
664
|
+
def lem_note_cf(e)
|
665
|
+
# ex: T32n1670A.xml, p. 703a16
|
666
|
+
# <note type="cf1">K30n1002_p0257a01-a23</note>
|
667
|
+
refs = []
|
668
|
+
e.xpath('./note').each { |n|
|
669
|
+
if n.key?('type') and n['type'].start_with? 'cf'
|
670
|
+
refs << n.content
|
671
|
+
end
|
672
|
+
}
|
673
|
+
if refs.empty?
|
674
|
+
''
|
675
|
+
else
|
676
|
+
'修訂依據:' + refs.join(';') + '。'
|
677
|
+
end
|
678
|
+
end
|
679
|
+
|
680
|
+
def lem_note_rdg(lem)
|
681
|
+
r = ''
|
682
|
+
app = lem.parent
|
683
|
+
@pass << false
|
684
|
+
app.xpath('rdg').each { |rdg|
|
685
|
+
if rdg['wit'].include? @orig
|
686
|
+
s = traverse(rdg, 'back')
|
687
|
+
s = MISSING if s.empty?
|
688
|
+
r += @orig + s
|
689
|
+
end
|
690
|
+
}
|
691
|
+
@pass.pop
|
692
|
+
r += '。' unless r.empty?
|
693
|
+
r
|
694
|
+
end
|
695
|
+
|
696
|
+
def sutra_init
|
697
|
+
s = NAV_TEMPLATE % '<ol></ol>'
|
698
|
+
@nav_doc = Nokogiri::XML(s)
|
699
|
+
|
700
|
+
@nav_doc.remove_namespaces!()
|
701
|
+
@nav_root_ol = @nav_doc.at_xpath('//ol')
|
702
|
+
@current_nav = [@nav_root_ol]
|
703
|
+
|
704
|
+
@nav_root_ol.add_child("<li><a href='readme.xhtml'>編輯說明</a></li>")
|
705
|
+
|
706
|
+
@mulu_count = 0
|
707
|
+
@main_text = ''
|
708
|
+
@back = ''
|
709
|
+
@dila_note = 0
|
710
|
+
|
711
|
+
FileUtils::mkdir_p File.join(@temp_folder, 'img')
|
712
|
+
end
|
713
|
+
|
714
|
+
def open_xml(fn)
|
715
|
+
s = File.read(fn)
|
716
|
+
|
717
|
+
if fn.include? 'T16n0657'
|
718
|
+
# 這個地方 雙行夾註 跨兩行偈頌
|
719
|
+
# 把 lb 移到 note 結束之前
|
720
|
+
# 讓 lg-row 先結束,再結束雙行夾註
|
721
|
+
s.sub!(/(<\/note>)(\n<lb n="0206b29" ed="T"\/>)/, '\2\1')
|
722
|
+
end
|
723
|
+
|
724
|
+
# <milestone unit="juan"> 前面的 lb 屬於新的這一卷
|
725
|
+
s.gsub!(%r{((?:<pb [^>]+>\n?)?(?:<lb [^>]+>\n?)+)(<milestone [^>]*unit="juan"[^/>]*/>)}, '\2\1')
|
726
|
+
|
727
|
+
doc = Nokogiri::XML(s)
|
728
|
+
doc.remove_namespaces!()
|
729
|
+
doc
|
730
|
+
end
|
731
|
+
|
732
|
+
def read_mod_notes(doc)
|
733
|
+
doc.xpath("//note[@type='mod']").each { |e|
|
734
|
+
@mod_notes << e['n']
|
735
|
+
}
|
736
|
+
end
|
737
|
+
|
738
|
+
def parse_xml(xml_fn)
|
739
|
+
@pass = [false]
|
740
|
+
|
741
|
+
doc = open_xml(xml_fn)
|
742
|
+
|
743
|
+
e = doc.xpath("//titleStmt/title")[0]
|
744
|
+
@title = traverse(e, 'txt')
|
745
|
+
@title = @title.split()[-1]
|
746
|
+
|
747
|
+
read_mod_notes(doc)
|
748
|
+
|
749
|
+
root = doc.root()
|
750
|
+
body = root.xpath("text/body")[0]
|
751
|
+
@pass = [true]
|
752
|
+
|
753
|
+
text = traverse(body)
|
754
|
+
text
|
755
|
+
end
|
756
|
+
|
757
|
+
def remove_empty_nav(node_list)
|
758
|
+
node_list.each do |n|
|
759
|
+
if n[:nav].empty?
|
760
|
+
n.delete(:nav)
|
761
|
+
else
|
762
|
+
remove_empty_nav(n[:nav])
|
763
|
+
end
|
764
|
+
end
|
765
|
+
end
|
766
|
+
|
767
|
+
def to_html(e)
|
768
|
+
e.to_xml(encoding: 'UTF-8', pertty: true, :save_with => Nokogiri::XML::Node::SaveOptions::AS_XML)
|
769
|
+
end
|
770
|
+
|
771
|
+
def traverse(e, mode='html')
|
772
|
+
r = ''
|
773
|
+
e.children.each { |c|
|
774
|
+
s = handle_node(c, mode)
|
775
|
+
r += s
|
776
|
+
}
|
777
|
+
r
|
778
|
+
end
|
779
|
+
|
780
|
+
end
|
data/lib/cbeta/p5a_to_html.rb
CHANGED
@@ -5,18 +5,17 @@ require 'json'
|
|
5
5
|
require 'nokogiri'
|
6
6
|
require 'set'
|
7
7
|
|
8
|
-
# 內容不輸出的元素
|
9
|
-
PASS=['back', 'teiHeader']
|
10
|
-
|
11
|
-
# 某版用字缺的符號
|
12
|
-
MISSING = '-'
|
13
|
-
|
14
8
|
# Convert CBETA XML P5a to HTML
|
15
9
|
#
|
16
10
|
# CBETA XML P5a 可由此取得: https://github.com/cbeta-git/xml-p5a
|
17
11
|
#
|
18
12
|
# 轉檔規則請參考: http://wiki.ddbc.edu.tw/pages/CBETA_XML_P5a_轉_HTML
|
19
13
|
class CBETA::P5aToHTML
|
14
|
+
# 內容不輸出的元素
|
15
|
+
PASS=['back', 'teiHeader']
|
16
|
+
|
17
|
+
# 某版用字缺的符號
|
18
|
+
MISSING = '-'
|
20
19
|
|
21
20
|
# @param xml_root [String] 來源 CBETA XML P5a 路徑
|
22
21
|
# @param out_root [String] 輸出 HTML 路徑
|
@@ -25,11 +24,6 @@ class CBETA::P5aToHTML
|
|
25
24
|
@out_root = out_root
|
26
25
|
@cbeta = CBETA.new
|
27
26
|
@gaijis = CBETA::Gaiji.new
|
28
|
-
|
29
|
-
# 載入 unicode 1.1 字集列表
|
30
|
-
#fn = File.join(File.dirname(__FILE__), 'unicode-1.1.json')
|
31
|
-
#json = File.read(fn)
|
32
|
-
#@unicode1 = JSON.parse(json)
|
33
27
|
end
|
34
28
|
|
35
29
|
# 將 CBETA XML P5a 轉為 HTML
|
@@ -22,11 +22,6 @@ class CBETA::P5aToSimpleHTML
|
|
22
22
|
@output_root = output_root
|
23
23
|
@cbeta = CBETA.new
|
24
24
|
@gaijis = CBETA::Gaiji.new
|
25
|
-
|
26
|
-
# 載入 unicode 1.1 字集列表
|
27
|
-
fn = File.join(File.dirname(__FILE__), 'unicode-1.1.json')
|
28
|
-
json = File.read(fn)
|
29
|
-
@unicode1 = JSON.parse(json)
|
30
25
|
end
|
31
26
|
|
32
27
|
# 將 CBETA XML P5a 轉為 Text
|
data/lib/cbeta/p5a_to_text.rb
CHANGED
@@ -25,11 +25,6 @@ class CBETA::P5aToText
|
|
25
25
|
@format = format
|
26
26
|
@cbeta = CBETA.new
|
27
27
|
@gaijis = CBETA::Gaiji.new
|
28
|
-
|
29
|
-
# 載入 unicode 1.1 字集列表
|
30
|
-
fn = File.join(File.dirname(__FILE__), 'unicode-1.1.json')
|
31
|
-
json = File.read(fn)
|
32
|
-
@unicode1 = JSON.parse(json)
|
33
28
|
end
|
34
29
|
|
35
30
|
# 將 CBETA XML P5a 轉為 Text
|
File without changes
|
@@ -0,0 +1,23 @@
|
|
1
|
+
<?xml version="1.0" encoding="utf-8" standalone="no"?>
|
2
|
+
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
|
3
|
+
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
|
4
|
+
|
5
|
+
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="zh-TW" xmlns:xml="http://www.w3.org/XML/1998/namespace">
|
6
|
+
<head>
|
7
|
+
<link href="../Styles/stylesheet.css" rel="stylesheet" type="text/css" />
|
8
|
+
|
9
|
+
<title>贊助</title>
|
10
|
+
</head>
|
11
|
+
|
12
|
+
<body>
|
13
|
+
<p><b>歡迎隨喜贊助</b></p>
|
14
|
+
|
15
|
+
<p><b>劃撥捐款</b></p>
|
16
|
+
|
17
|
+
<p>郵政劃撥帳號:19624224</p>
|
18
|
+
|
19
|
+
<p>戶名:財團法人智諭老和尚教育紀念基金會</p>
|
20
|
+
|
21
|
+
<p>若欲指定特殊用途者,請特別註明,我們會專款專用。</p>
|
22
|
+
</body>
|
23
|
+
</html>
|
@@ -0,0 +1,27 @@
|
|
1
|
+
<?xml version="1.0" encoding="utf-8" standalone="no"?>
|
2
|
+
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
|
3
|
+
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
|
4
|
+
|
5
|
+
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="zh-TW" xmlns:xml="http://www.w3.org/XML/1998/namespace">
|
6
|
+
<head>
|
7
|
+
<link href="../Styles/stylesheet.css" rel="stylesheet" type="text/css" />
|
8
|
+
|
9
|
+
<title>說明</title>
|
10
|
+
</head>
|
11
|
+
|
12
|
+
<body>
|
13
|
+
<div>
|
14
|
+
<h2>編輯說明</h2>
|
15
|
+
|
16
|
+
<ul>
|
17
|
+
<li>本電子書以<a href="http://www.seeland.org.tw/www/zhiyu/index.html">「西蓮淨苑智諭老和尚著作全集」</a>為資料來源。</li>
|
18
|
+
|
19
|
+
<li>漢字呈現以 Unicode 1.1 為基礎,不在此範圍的字則採用 <a href="http://www.cbeta.org/format/rare-rule.php">組字式</a> 表達。</li>
|
20
|
+
|
21
|
+
<li><span style="line-height: 1.6em;">若有發現任何問題,歡迎來函</span> <a href="mailto:seeland77@gmail.com" style="line-height: 1.6em;">seeland77@gmail.com</a> <span style="line-height: 1.6em;">回報。</span><br /></li>
|
22
|
+
|
23
|
+
<li>版權所有,歡迎自由流通,但禁止營利使用。</li>
|
24
|
+
</ul><br />
|
25
|
+
</div>
|
26
|
+
</body>
|
27
|
+
</html>
|
File without changes
|
File without changes
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: cbeta
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.5.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Ray Chou
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-08-
|
11
|
+
date: 2015-08-22 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: Ruby gem for use Chinese Buddhist Text resources made by CBETA (http://www.cbeta.org).
|
14
14
|
email: zhoubx@gmail.com
|
@@ -16,16 +16,20 @@ executables: []
|
|
16
16
|
extensions: []
|
17
17
|
extra_rdoc_files: []
|
18
18
|
files:
|
19
|
-
- lib/canons.csv
|
20
19
|
- lib/cbeta.rb
|
21
20
|
- lib/cbeta/bm_to_text.rb
|
22
|
-
- lib/cbeta/gaiji.json
|
23
21
|
- lib/cbeta/gaiji.rb
|
24
22
|
- lib/cbeta/html_to_text.rb
|
23
|
+
- lib/cbeta/p5a_to_epub.rb
|
25
24
|
- lib/cbeta/p5a_to_html.rb
|
26
25
|
- lib/cbeta/p5a_to_simple_html.rb
|
27
26
|
- lib/cbeta/p5a_to_text.rb
|
28
|
-
- lib/
|
27
|
+
- lib/data/canons.csv
|
28
|
+
- lib/data/epub-donate.xhtml
|
29
|
+
- lib/data/epub-nav.xhtml
|
30
|
+
- lib/data/epub-readme.xhtml
|
31
|
+
- lib/data/gaiji.json
|
32
|
+
- lib/data/unicode-1.1.json
|
29
33
|
homepage: https://github.com/RayCHOU/ruby-cbeta
|
30
34
|
licenses:
|
31
35
|
- MIT
|