summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/scripts/convbkmk/convbkmk.rb
blob: c5bceb5a574918052dd1c946651ac91c586365c5 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
#!/usr/bin/ruby
# -*- coding: utf-8 -*-

=begin

= convbkmk Ver.0.10a

  2014.12.29
  Takuji Tanaka
  ttk (at) t-lab.opal.ne.jp
((<URL:http://www.t-lab.opal.ne.jp/tex/uptex_en.html>))


== Abstract

((*convbkmk*)) is a tiny utility for making correct bookmarks in pdf files
typesetted by platex/uplatex with the hyperref package.
platex/uplatex + hyperref outputs data of bookmarks
in their internal encodings (EUC-JP, Shift_JIS or UTF-8).
On the other hand, the PostScript/PDF format requests that
the data is written in a certain syntax with UTF-16 or PDFDocEncoding.
Thus, data conversion is required to create correct bookmarks.
((*convbkmk*)) provides a function of
the encoding conversion and formatting the bookmark data.

== Requirement

ruby 1.8.3 or later
ruby 1.8.x will not be supported in the near future release.

== Examples

platex (internal kanji code: euc) + hyperref + dvips :
 $ platex doc00.tex
 $ platex doc00.tex
 $ dvips doc00.dvi
 $ convbkmk.rb -e doc00.ps
 $ ps2pdf doc00-convbkmk.ps

platex (internal kanji code: sjis) + hyperref + dvipdfmx :
 $ platex doc01.tex
 $ platex doc01.tex
 $ convbkmk.rb -s -o doc01.out
 $ platex doc01.tex
 $ dvipdfmx doc01.dvi

uplatex + hyperref + dvips :
 $ uplatex doc02.tex
 $ uplatex doc02.tex
 $ dvips doc02.dvi
 $ convbkmk.rb doc02.ps
 $ ps2pdf doc02-convbkmk.ps

uplatex + hyperref + dvipdfmx :
 $ uplatex doc03.tex
 $ uplatex doc03.tex
 $ convbkmk.rb -o doc03.out
 $ uplatex doc03.tex
 $ dvipdfmx doc03.dvi

More examples are included in the uptex source archive.

== License

convbkmk

Copyright (c) 2009-2014 Takuji Tanaka

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.

== History

: 2009.08.02  0.00
 * Initial version.
: 2011.05.02  0.01
 * Bug fix: BOM was not correct.
: 2012.05.08  0.02
 * Bug fix: for a case of dvips with -z option and Ruby1.8.
 * Add conversion of /Creator and /Producer .
: 2012.05.12  0.03
 * Suppress halfwidth -> fullwidth katakana conversion and MIME decoding in Ruby1.8.
: 2012.06.01  0.04
 * Support escape sequences: \n, \r, \t, \b, \f, \\, \ddd (octal, PDFDocEncoding) and \0xUUUU (Unicode UTF-16BE).
 * Support sequences of end of line: '\' or other followed by "\n", "\r\n" or "\r" .
 * Set file IO to binary mode.
: 2012.07.26  0.05
 * Add -o option to support conversion of OUT files generated by dvipdfmx.
: 2012.08.07  0.06
 * Bug fix: Ver.0.05 does not work with Ruby1.9.
: 2012.09.17  0.07
 * Bug fix: An infinite loop occurs in Ver.0.05, 0.06 with -g option in some cases.
 * Add reference for PDFDocEncoding.
: 2013.05.11  0.08
 * Add -O option: overwrite output files onto input files instead of creating foo-convbkmk.ps .
 * Make comments rd/rdtool friendly.
: 2014.03.02  0.09
 * Bug fix: Conversion was not complete in some cases.
: 2014.03.08  0.10
 * Bug fix: Output of binary data might be broken in filter mode on Windows.
: 2014.12.29  0.10a
 * Update the author's mail address and web site.

=end

Version = "0.10"

require "optparse"

if RUBY_VERSION >= "1.9"
  $RUBY_M17N = true

  class String
    def to_utf8(enc)
      self.force_encoding(enc.current).encode('UTF-8')
    end
    def utf16be_to_utf8
      self.force_encoding('UTF-16BE').encode('UTF-8')
    end
    def utf8_to_utf16be
      self.force_encoding('UTF-8').encode('UTF-16BE')
    end
  end
else
  $RUBY_M17N = false

  require "jcode" # for method each_char
  require "nkf"
  class String
    def to_utf8(enc)
      NKF.nkf('-w -x -m0 '+enc.kconv_enc, self)
    end
    def utf16be_to_utf8
      NKF.nkf('-w -x -m0 --utf16-input', self)
    end
    def utf8_to_utf16be
      NKF.nkf('-w16 -x -m0 --utf8-input', self)
    end
    def ascii_only?
      return self !~ /[\x80-\xFF]/n
    end
    REPLACE_TABLE = {"\n" => "\\n", "\r" => "\\r", "\t" => "\\t",
      "\b" => "\\b", "\f" => "\\f", "\e" => "\\e", "\"" => "\\\""}
    def valid_encoding?
      conv = ''
      tmp = self.dup
      while tmp.length>0 do
        case tmp
        when /\A\\\\/
          conv += "\\\\\\\\"
        when /\A\\[nrtbf()]/, /\A\\[0-3][0-7][0-7]/, /\A\\0x[0-9A-F]{4}/i
          conv += "\\"+$&
        when /\A\\/
          conv += "\\\\"
        when /\A[^\\]*/
          conv += $&
        else
          raise 'unexpected input!'
        end
        tmp = $'
      end
      conv.gsub!(/[\n\r\t\b\f\e"]/) { |s| REPLACE_TABLE[s] }
      conv.gsub!(/([\000-\037\177])/) { "\\%#03o" % $1.unpack("C*") }
      tmp = "\"" + conv + "\""
#      puts 's:' + self
#      puts 't:' + tmp
#      puts 'i:' + self.inspect
      return tmp == self.inspect
    end
    def force_encoding(enc)
      if (enc =~ /^(Shift_JIS|EUC-JP|UTF-8)/i)
        $KCODE=enc
      end
      return self
    end
  end
end

class TeXEncoding
  attr_accessor :current, :option, :status, :is_8bit, :kconv_enc
  attr_reader :list

  def initialize
    @current = false
    @option = false
    @status = false
    @is_8bit = false
    @list = ['Shift_JIS', 'EUC-JP', 'UTF-8']
    if !$RUBY_M17N
      @kconv_enc = nil
      @kconv_list = {'Shift_JIS' => '--sjis-input',
                     'EUC-JP' => '--euc-input',
                     'UTF-8' => '--utf8-input'}
    end
  end

  def set_process_encoding(enc)
    if @status == 'fixed'
      raise 'dupulicate definition'
    end
    if enc == 'guess'
      @option = 'guess'
      @status = 'guess'
    else
      @current = enc
      @option = enc
      @status = 'fixed'
      if !$RUBY_M17N
        @kconv_enc = @kconv_list[enc]
      end
    end
    return enc
  end
end
enc = TeXEncoding.new

Opts = {}

OptionParser.new do |opt|
  opt.on('-e', '--euc-jp',
         'set pTeX internal encoding to EUC-JP') {|v|
    enc.set_process_encoding('EUC-JP')
  }
  opt.on('-s', '--shift_jis',
         'set pTeX internal encoding to Shift_JIS') {|v|
    enc.set_process_encoding('Shift_JIS')
  }
  opt.on('-u', '--utf-8',
         'set upTeX internal encoding to UTF-8') {|v|
    enc.set_process_encoding('UTF-8')
  }
  opt.on('-g', '--guess',
         'guess pTeX/upTeX internal encoding') {|v|
    enc.set_process_encoding('guess')
  }
  enc_alias = Hash.new
  enc.list.each { |e|
    enc_alias[e] = e
    enc_alias[e[0]] = e
    enc_alias[e.downcase] = e
  }
  opt.on('--enc=ENC', enc_alias,
         'set pTeX/upTeX internal encoding to ENC') {|v|
    enc.set_process_encoding(v)
  }
  opt.on('-o', '--out',
         'treat OUT files') {|v|
    Opts[:mode] = 'out'
    require "fileutils"
  }
  opt.on('-O', '--overwrite',
         'overwrite output files') {|v|
    Opts[:mode] = 'overwrite'
    require "fileutils"
  }
  opt.banner += " file0.ps [file1.ps ...]\n" \
    + opt.banner.sub('Usage:','      ') + " < in_file.ps > out_file.ps\n" \
    + opt.banner.sub('Usage:','      ') + ' -o file0.out [file1.out ...]'

  opt.parse!
end

# default encoding
if enc.status == false
  enc.set_process_encoding('UTF-8')
end
if Opts[:mode] == 'out'
  OpenP, CloseP, OpenPEsc, ClosePEsc = '{', '}', '\{', '\}'
  FileSfx = 'out'
else
  OpenP, CloseP, OpenPEsc, ClosePEsc = '(', ')', '\(', '\)'
  FileSfx = 'ps'
end

def try_guess_encoding(line, enc)
  return 'US-ASCII' if line.ascii_only?

  enc.is_8bit = true
  valid_enc = false
  count = 0
  enc.list.each { |e|
    if line.dup.force_encoding(e).valid_encoding?
      count += 1
      valid_enc = e
    end
  }
  if count == 1
    enc.set_process_encoding(valid_enc)
    return valid_enc
  elsif count > 1
    return false # ambiguous
  else
    raise 'Cannot guess encoding!'
  end
end


def check_parentheses_balance(line, enc)
  depth = 0
  count = 0
  tmp_prev = ''
  tmp_rest = line

  if enc.status == 'guess'
    if tmp_enc = try_guess_encoding(line, enc)
      # succeeded in guess or ascii only
      tmp_rest = line.force_encoding(tmp_enc)
    else
      # ambiguous
      raise 'unexpected internal condition!'
    end
  else
    tmp_enc = enc.current
    tmp_rest = tmp_rest.force_encoding(tmp_enc)
    unless tmp_rest.valid_encoding?
      # illegal input
      $stdout = STDERR
      p 'parameters: '
      p '  status: ' + enc.status
      p '  option: ' + enc.option
      p '  current: ' + enc.current
      p enc.is_8bit
      if !$RUBY_M17N
        p '  inspect: '   + tmp_rest.inspect
        p '  rest   :   [' + tmp_rest + ']'
      end
      p '             [' + line + ']'
      raise 'encoding is not consistent'
    end
  end

  while tmp_rest.length>0 do
    if    (tmp_rest =~ /\A(\\#{OpenPEsc}|\\#{ClosePEsc}|[^#{OpenP}#{CloseP}])*(#{OpenPEsc}|#{ClosePEsc})/o) # parenthis
      if $2 == OpenP
        depth += 1
        count += 1
      else
        depth -= 1
      end
      tmp_prev += $&
      tmp_rest = $'
    else
      tmp_prev += tmp_rest
      tmp_rest = ''
    end
    if depth<1
      break
    end
  end
  return depth, count, tmp_prev, tmp_rest
end

# PDFDocEncoding -> UTF-16BE
# Ref. "PDF Reference, Sixth Edition, version 1.7", 2006, Adobe Systems Incorporated
#   http://www.adobe.com/devnet/pdf/pdf_reference_archive.html
#   http://www.adobe.com/content/dam/Adobe/en/devnet/acrobat/pdfs/pdf_reference_1-7.pdf
PDF2UNI = Array(0..255)
PDF2UNI[0o030..0o037] = 0x02d8, 0x02c7, 0x02c6, 0x02d9, 0x02dd, 0x02db, 0x02da, 0x02dc
PDF2UNI[0o200..0o207] = 0x2022, 0x2020, 0x2021, 0x2026, 0x2014, 0x2013, 0x0192, 0x2044
PDF2UNI[0o210..0o217] = 0x2039, 0x203a, 0x2212, 0x2030, 0x201e, 0x201c, 0x201d, 0x2018
PDF2UNI[0o220..0o227] = 0x2019, 0x201a, 0x2122, 0xfb01, 0xfb02, 0x0141, 0x0152, 0x0160
PDF2UNI[0o230..0o237] = 0x0178, 0x017d, 0x0131, 0x0142, 0x0153, 0x0161, 0x017e, 0xfffd
PDF2UNI[0o240       ] = 0x20ac
PDF2UNI[0o255       ] = 0xfffd

def conv_string_to_utf16be(line, enc)
  if line !~ /(#{OpenPEsc})(.*)(#{ClosePEsc})/mo
    raise 'illegal input!'
  end
  pre, tmp, post = $`, $2, $'

  if tmp.ascii_only? && tmp !~ /\\0x[0-9A-F]{4}/i
    return line
  end

  conv = ''
  conv.force_encoding('UTF-8')
  tmp.force_encoding(enc.current)

  while tmp.length>0 do
    case tmp
    when /\A[^\\\n\r]+/
      conv += $&.to_utf8(enc)
    when /\A\\([0-3][0-7][0-7])/  # PDFDocEncoding -> UTF-8
      conv += [PDF2UNI[$1.oct]].pack("U*")
    when /\A\\0x(D[8-B][0-9A-F]{2})\\0x(D[C-F][0-9A-F]{2})/i  # surrogate pair
      conv += [$1.hex, $2.hex].pack("n*").utf16be_to_utf8
    when /\A\\0x([0-9A-F]{4})/i
      conv += [$1.hex].pack("U*")
    when /\A\\[nrtbf\\]/
      conv += eval(%!"#{$&}"!)
    when /\A(\r\n|\r|\n)/
      conv += "\n"
    when /\A\\([\r\n]{1,2})|\\/
      # ignore
    else
      raise 'unexpected input!'
    end
    tmp = $'
  end

  buf = ''
  conv16be = "\xFE\xFF"            # BOM U+FEFF
  conv16be.force_encoding('UTF-16BE') if $RUBY_M17N
  conv16be += conv.utf8_to_utf16be # UTF-16BE with BOM
  conv16be.each_byte {|byte|
    buf += (Opts[:mode] == 'out' ? '\%03o' : '%02X') % byte
  }
  buf = Opts[:mode] == 'out' ? '{' + buf + '}' : '<' + buf + '>'
  return pre + buf + post
end


def file_treatment(ifile, ofile, enc)
  if $RUBY_M17N
    ifile.set_encoding('ASCII-8BIT')
    ofile.set_encoding('ASCII-8BIT')
  end

  line = ''
  while l = ifile.gets do
    line.force_encoding('ASCII-8BIT') if $RUBY_M17N
    line += l
    reg = Opts[:mode] == 'out' ? %r!(\{)! : %r!(/Title|/Author|/Keywords|/Subject|/Creator|/Producer)(\s+\(|$)!
    if (line !~ reg )
      ofile.print line
      line = ''
      next
    end

    ofile.print $`
    line = $& + $'

    if Opts[:mode] != 'out'
      while line =~ %r!(/Title|/Author|/Keywords|/Subject|/Creator|/Producer)\Z! do
        line += ifile.gets
      end
    end

    if enc.status == 'guess'
      if tmp_enc = try_guess_encoding(line, enc)
        # succeeded in guess or ascii only
        line.force_encoding(tmp_enc)
      else
        # ambiguous
        next
      end
    end

    while line.length>0 do
      depth, count, tmp_prev, tmp_rest \
        = check_parentheses_balance(line, enc)
      if depth<0
        p depth, count, tmp_prev, tmp_rest
        raise 'illegal input! (depth<0)'
      elsif depth>0
        break
      elsif count==0
        ofile.print line
        line = ''
        break
      elsif count>0
        ofile.print conv_string_to_utf16be(tmp_prev, enc)
        line = tmp_rest
      else
        p depth, count, tmp_prev, tmp_rest
        raise 'illegal input! (count<0)'
      end
    end

  end

  if enc.status == 'guess' && enc.is_8bit
    raise 'did not succeed in guess encoding!'
  end
end


### main
if ARGV.size == 0
  ifile = STDIN.binmode
  ofile = STDOUT.binmode
  file_treatment(ifile, ofile, enc)
else
  ARGV.each {|fin|
    if (fin !~ /\.#{FileSfx}$/io)
      raise 'input file does not seem ' + FileSfx.upcase + ' file'
    end
    fout = fin.gsub(/\.#{FileSfx}$/io, "-convbkmk#{$&}")
    open(fin, 'rb') {|ifile|
      open(fout, 'wb') {|ofile|
        file_treatment(ifile, ofile, enc)
      }
    }
    if (Opts[:mode] == 'out' || Opts[:mode] == 'overwrite')
      FileUtils.mv(fout, fin) 
    end
  }
end