summaryrefslogtreecommitdiff
path: root/tool/transcode-tblgen.rb
blob: cdeb27f0fdcd28f3af6d531b498d8e9b136d07a0 (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
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
require 'optparse'
require 'erb'
require 'fileutils'

C_ESC = {
  "\\" => "\\\\",
  '"' => '\"',
  "\n" => '\n',
}

0x00.upto(0x1f) {|ch| C_ESC[[ch].pack("C")] ||= "\\%03o" % ch }
0x7f.upto(0xff) {|ch| C_ESC[[ch].pack("C")] = "\\%03o" % ch }
C_ESC_PAT = Regexp.union(*C_ESC.keys)

def c_esc(str)
  '"' + str.gsub(C_ESC_PAT) { C_ESC[$&] } + '"'
end

class StrSet
  def self.parse(pattern)
    if /\A\s*(([0-9a-f][0-9a-f]|\{([0-9a-f][0-9a-f]|[0-9a-f][0-9a-f]-[0-9a-f][0-9a-f])(,([0-9a-f][0-9a-f]|[0-9a-f][0-9a-f]-[0-9a-f][0-9a-f]))*\})+(\s+|\z))*\z/i !~ pattern
      raise ArgumentError, "invalid pattern: #{pattern.inspect}"
    end
    result = []
    pattern.scan(/\S+/) {|seq|
      seq_result = []
      while !seq.empty?
        if /\A([0-9a-f][0-9a-f])/i =~ seq
          byte = $1.to_i(16)
          seq_result << [byte..byte]
          seq = $'
        elsif /\A\{([^\}]+)\}/ =~ seq
          set = $1
          seq = $'
          set_result = []
          set.scan(/[^,]+/) {|range|
            if /\A([0-9a-f][0-9a-f])-([0-9a-f][0-9a-f])\z/ =~ range
              b = $1.to_i(16)
              e = $2.to_i(16)
              set_result << (b..e)
            elsif /\A([0-9a-f][0-9a-f])\z/ =~ range
              byte = $1.to_i(16)
              set_result << (byte..byte)
            else
              raise "invalid range: #{range.inspect}"
            end
          }
          seq_result << set_result
        else
          raise "invalid sequence: #{seq.inspect}"
        end
      end
      result << seq_result
    }
    self.new(result)
  end

  def initialize(pat)
    @pat = pat
  end

  def hash
    @pat.hash
  end

  def eql?(other)
    self.class == other.class &&
    @pat == other.instance_eval { @pat }
  end

  alias == eql?

  def to_s
    if @pat.empty?
      "(empset)"
    else
      @pat.map {|seq|
        if seq.empty?
          "(empstr)"
        else
          seq.map {|byteset|
            if byteset.length == 1 && byteset[0].begin == byteset[0].end
              "%02x" % byteset[0].begin
            else
              "{" + 
              byteset.map {|range|
                if range.begin == range.end
                  "%02x" % range.begin
                else
                  "%02x-%02x" % [range.begin, range.end]
                end
              }.join(',') +
              "}"
            end
          }.join('')
        end
      }.join(' ')
    end
  end

  def inspect
    "\#<#{self.class}: #{self.to_s}>"
  end

  def min_length
    if @pat.empty?
      nil
    else
      @pat.map {|seq| seq.length }.min
    end
  end

  def max_length
    if @pat.empty?
      nil
    else
      @pat.map {|seq| seq.length }.max
    end
  end

  def emptyable?
    @pat.any? {|seq|
      seq.empty?
    }
  end

  def first_bytes
    result = {}
    @pat.each {|seq|
      next if seq.empty?
      seq.first.each {|range|
        range.each {|byte|
          result[byte] = true
        }
      }
    }
    result.keys.sort
  end

  def each_firstbyte
    h = {}
    @pat.each {|seq|
      next if seq.empty?
      seq.first.each {|range|
        range.each {|byte|
          (h[byte] ||= []) << seq[1..-1]
        }
      }
    }
    h.keys.sort.each {|byte|
      yield byte, StrSet.new(h[byte])
    }
  end
end

class ActionMap
  def self.parse(hash)
    h = {}
    hash.each {|pat, action|
      h[StrSet.parse(pat)] = action
    }
    self.new(h)
  end

  def initialize(h)
    @map = h
  end

  def hash
    hash = 0
    @map.each {|k,v|
      hash ^= k.hash ^ v.hash
    }
    hash
  end

  def eql?(other)
    self.class == other.class &&
    @map == other.instance_eval { @map }
  end

  alias == eql?

  def inspect
    "\#<#{self.class}:" + 
    @map.map {|k, v| " [" + k.to_s + "]=>" + v.inspect }.join('') +
    ">"
  end

  def max_input_length
    @map.keys.map {|k| k.max_length }.max
  end

  def empty_action
    @map.each {|ss, action|
      return action if ss.emptyable?
    }
    nil
  end

  def each_firstbyte(valid_encoding=nil)
    h = {}
    @map.each {|ss, action|
      if ss.emptyable?
        raise "emptyable pattern"
      else
        ss.each_firstbyte {|byte, rest|
          h[byte] ||= {}
          if h[byte][rest]
            raise "ambiguous %s or %s (%02X/%s)" % [h[byte][rest], action, byte, rest]
          end
          h[byte][rest] = action
        }
      end
    }
    if valid_encoding
      valid_encoding.each_firstbyte {|byte, rest|
        if h[byte]
          am = ActionMap.new(h[byte])
          yield byte, am, rest
        else
          am = ActionMap.new(rest => :undef)
          yield byte, am, nil
        end
      }
    else
      h.keys.sort.each {|byte|
        am = ActionMap.new(h[byte])
        yield byte, am, nil
      }
    end
  end

  OffsetsMemo = {}
  InfosMemo = {}

  def format_offsets(min, max, offsets)
    offsets = offsets[min..max]
    code = "%d, %d,\n" % [min, max]
    0.step(offsets.length-1,16) {|i|
      code << "    "
      code << offsets[i,8].map {|off| "%3d," % off.to_s }.join('')
      if i+8 < offsets.length
        code << "  "
        code << offsets[i+8,8].map {|off| "%3d," % off.to_s }.join('')
      end
      code << "\n"
    }
    code
  end

  def generate_info(info)
    case info
    when :nomap
      "NOMAP"
    when :undef
      "UNDEF"
    when :invalid
      "INVALID"
    when :func_ii
      "FUNii"
    when :func_si
      "FUNsi"
    when :func_io
      "FUNio"
    when :func_so
      "FUNso"
    when /\A([0-9a-f][0-9a-f])\z/i
      "o1(0x#$1)"
    when /\A([0-9a-f][0-9a-f])([0-9a-f][0-9a-f])\z/i
      "o2(0x#$1,0x#$2)"
    when /\A([0-9a-f][0-9a-f])([0-9a-f][0-9a-f])([0-9a-f][0-9a-f])\z/i
      "o3(0x#$1,0x#$2,0x#$3)"
    when /\A([0-9a-f][0-9a-f])([0-9a-f][0-9a-f])([0-9a-f][0-9a-f])([0-9a-f][0-9a-f])\z/i
      "o4(0x#$1,0x#$2,0x#$3,0x#$4)"
    when /\A\/\*BYTE_LOOKUP\*\// # pointer to BYTE_LOOKUP structure
      info.to_s
    else
      raise "unexpected action: #{info.inspect}"
    end
  end

  def format_infos(infos)
    infos = infos.map {|info| generate_info(info) }
    maxlen = infos.map {|info| info.length }.max
    columns = maxlen <= 16 ? 4 : 2
    code = "{\n"
    0.step(infos.length-1, columns) {|i|
      code << "    "
      is = infos[i,columns]
      is.each {|info|
        code << sprintf(" %#{maxlen}s,", info)
      }
      code << "\n"
    }
    code << "}"
    code
  end

  def generate_lookup_node(bytes_code, words_code, name, table)
    offsets = []
    infos = []
    infomap = {}
    min = max = nil
    table.each_with_index {|action, byte|
      action ||= :invalid
      if action != :invalid
        min = byte if !min
        max = byte
      end
      unless o = infomap[action]
        infomap[action] = o = infos.length
        infos[o] = action
      end
      offsets[byte] = o
    }
    if !min
      min = max = 0
    end

    offsets_key = [min, max, offsets[min..max]]
    if n = OffsetsMemo[offsets_key]
      offsets_name = n
    else
      offsets_name = "#{name}_offsets"
      OffsetsMemo[offsets_key] = offsets_name
      if bytes_code.empty?
        bytes_code << <<"End"
static const unsigned char
byte_array[0] = {
};
End
      end
      size = bytes_code[/\[\d+\]/][1...-1].to_i
      bytes_code.sub!(/^(\};\n\z)/) {
        "\#define #{offsets_name} (byte_array+#{size})\n" +
        format_offsets(min,max,offsets) + "\n" +
        $1
      }
      size += 2+max-min+1
      bytes_code.sub!(/\[\d+\]/) { "[#{size}]" }
    end

    if n = InfosMemo[infos]
      infos_name = n
      infos_code = ''
    else
      infos_name = "#{name}_infos"
      infos_code = <<"End"
static const uintptr_t
#{infos_name}[#{infos.length}] = #{format_infos(infos)};
\#define #{infos_name} ((uintptr_t)#{infos_name})
End
      InfosMemo[infos] = infos_name
    end

    r = infos_code + <<"End"
static const BYTE_LOOKUP
#{name} = {
    (uintptr_t)#{offsets_name},
    #{infos_name}
};
\#define #{name} ((uintptr_t)#{name})

End
    words_code << r
  end

  PreMemo = {}
  PostMemo = {}
  NextName = "a"

  def generate_node(bytes_code, words_code, name_hint=nil, valid_encoding=nil)
    if n = PreMemo[[self,valid_encoding]]
      return n
    end

    table = Array.new(0x100, :invalid)
    each_firstbyte(valid_encoding) {|byte, rest, rest_valid_encoding|
      if a = rest.empty_action
        table[byte] = a
      else
        name_hint2 = nil
        name_hint2 = "#{name_hint}_#{'%02X' % byte}" if name_hint
        table[byte] = "/*BYTE_LOOKUP*/" + rest.generate_node(bytes_code, words_code, name_hint2, rest_valid_encoding)
      end
    }

    if n = PostMemo[table]
      return n
    end

    if !name_hint
      name_hint = "fun_" + NextName.dup
      NextName.succ!
    end

    PreMemo[[self,valid_encoding]] = PostMemo[table] = name_hint

    generate_lookup_node(bytes_code, words_code, name_hint, table)
    name_hint
  end

  def gennode(bytes_code, words_code, name_hint=nil, valid_encoding=nil)
    name = generate_node(bytes_code, words_code, name_hint, valid_encoding)
    return name
  end
end

def citrus_mskanji_cstomb(csid, index)
  case csid
  when 0
    index
  when 1
    index + 0x80
  when 2, 3
    row = index >> 8
    raise "invalid byte sequence" if row < 0x21
    if csid == 3
      if row <= 0x2F
        offset = (row == 0x22 || row >= 0x26) ? 0xED : 0xF0
      elsif row >= 0x4D && row <= 0x7E
        offset = 0xCE
      else
        raise "invalid byte sequence"
      end
    else
      raise "invalid byte sequence" if row > 0x97
      offset = (row < 0x5F) ? 0x81 : 0xC1
    end
    col = index & 0xFF
    raise "invalid byte sequence" if (col < 0x21 || col > 0x7E)

    row -= 0x21
    col -= 0x21
    if (row & 1) == 0
      col += 0x40
      col += 1 if (col >= 0x7F)
    else
      col += 0x9F;
    end
    row = row / 2 + offset
    (row << 8) | col
  end.to_s(16)
end

def citrus_euc_cstomb(csid, index)
  case csid
  when 0x0000
    index
  when 0x8080
    index | 0x8080
  when 0x0080
    index | 0x8E80
  when 0x8000
    index | 0x8F8080
  end.to_s(16)
end

def citrus_cstomb(ces, csid, index)
  case ces
  when 'mskanji'
    citrus_mskanji_cstomb(csid, index)
  when 'euc'
    citrus_euc_cstomb(csid, index)
  end
end

SUBDIR = %w/APPLE AST BIG5 CNS CP EBCDIC GB GEORGIAN ISO646 ISO-8859 JIS KAZAKH KOI KS MISC TCVN/


def citrus_decode_mapsrc(ces, csid, mapsrcs)
  table = []
  mapsrcs.split(',').each do |mapsrc|
    path = [$srcdir]
    mode = nil
    if mapsrc.start_with?('UCS')
      mode = :from_ucs
      from = mapsrc[4..-1]
      path << SUBDIR.find{|x| from.start_with?(x) }
    else
      mode = :to_ucs
      path << SUBDIR.find{|x| mapsrc.start_with?(x) }
    end
    path << mapsrc.gsub(':', '@')
    path = File.join(*path)
    path << ".src"
    path[path.rindex('/')] = '%'
    STDERR.puts 'load mapsrc %s' % path if VERBOSE_MODE
    open(path) do |f|
      f.each_line do |l|
        break if /^BEGIN_MAP/ =~ l
      end
      f.each_line do |l|
        next if /^\s*(?:#|$)/ =~ l
          break if /^END_MAP/ =~ l
        case mode
        when :from_ucs
          case l
          when /0x(\w+)\s*-\s*0x(\w+)\s*=\s*INVALID/
            # Citrus OOB_MODE
          when /(0x\w+)\s*=\s*(0x\w+)/
            table.push << [$1.hex, citrus_cstomb(ces, csid, $2.hex)]
          else
            raise "unknown notation '%s'"% l
          end
        when :to_ucs
          case l
          when /(0x\w+)\s*=\s*(0x\w+)/
            table.push << [citrus_cstomb(ces, csid, $1.hex), $2.hex]
          else
            raise "unknown notation '%s'"% l
          end
        end
      end
    end
  end
  return table
end

def encode_utf8(map)
  r = []
  map.each {|k, v|
    # integer means UTF-8 encoded sequence.
    k = [k].pack("U").unpack("H*")[0].upcase if Integer === k
    v = [v].pack("U").unpack("H*")[0].upcase if Integer === v
    r << [k,v]
  }
  r
end

def transcode_compile_tree(name, from, map)
  map = encode_utf8(map)
  h = {}
  map.each {|k, v|
    h[k] = v unless h[k] # use first mapping
  }
  am = ActionMap.parse(h)

  max_input = am.max_input_length

  if ValidEncoding[from]
    valid_encoding = StrSet.parse(ValidEncoding[from])
  else
    valid_encoding = nil
  end

  defined_name = am.gennode(TRANSCODE_GENERATED_BYTES_CODE, TRANSCODE_GENERATED_WORDS_CODE, name, valid_encoding)
  return defined_name, max_input
end

TRANSCODERS = []
TRANSCODE_GENERATED_BYTES_CODE = ''
TRANSCODE_GENERATED_WORDS_CODE = ''
TRANSCODE_GENERATED_TRANSCODER_CODE = ''

def transcode_tblgen(from, to, map)
  STDERR.puts "converter from #{from} to #{to}" if VERBOSE_MODE
  id_from = from.tr('^0-9A-Za-z', '_')
  id_to = to.tr('^0-9A-Za-z', '_')
  if from == "UTF-8"
    tree_name = "to_#{id_to}"
  elsif to == "UTF-8"
    tree_name = "from_#{id_from}"
  else
    tree_name = "from_#{id_from}_to_#{id_to}"
  end
  map = encode_utf8(map)
  real_tree_name, max_input = transcode_compile_tree(tree_name, from, map)
  transcoder_name = "rb_#{tree_name}"
  TRANSCODERS << transcoder_name
  input_unit_length = UnitLength[from]
  max_output = map.map {|k,v| String === v ? v.length/2 : 1 }.max
  transcoder_code = <<"End"
static const rb_transcoder
#{transcoder_name} = {
    #{c_esc from}, #{c_esc to}, #{real_tree_name},
    #{input_unit_length}, /* input_unit_length */
    #{max_input}, /* max_input */
    #{max_output}, /* max_output */
    stateless_converter, /* stateful_type */
    NULL, NULL, NULL, NULL,
    NULL, NULL, NULL
};
End
  TRANSCODE_GENERATED_TRANSCODER_CODE << transcoder_code
  ''
end

def transcode_generate_node(am, name_hint=nil)
  STDERR.puts "converter for #{name_hint}" if VERBOSE_MODE
  name = am.gennode(TRANSCODE_GENERATED_BYTES_CODE, TRANSCODE_GENERATED_WORDS_CODE, name_hint)
  ''
end

def transcode_generated_code
  TRANSCODE_GENERATED_BYTES_CODE + TRANSCODE_GENERATED_WORDS_CODE + TRANSCODE_GENERATED_TRANSCODER_CODE
end

def transcode_register_code
  code = ''
  TRANSCODERS.each {|transcoder_name|
    code << "    rb_register_transcoder(&#{transcoder_name});\n"
  }
  code
end

UnitLength = {
  'UTF-16BE'    => 2,
  'UTF-16LE'    => 2,
  'UTF-32BE'    => 4,
  'UTF-32LE'    => 4,
}
UnitLength.default = 1

ValidEncoding = {
  '1byte'       => '{00-ff}',
  '2byte'       => '{00-ff}{00-ff}',
  '4byte'       => '{00-ff}{00-ff}{00-ff}{00-ff}',
  'US-ASCII'    => '{00-7f}',
  'UTF-8'       => '{00-7f}
                    {c2-df}{80-bf}
                         e0{a0-bf}{80-bf}
                    {e1-ec}{80-bf}{80-bf}
                         ed{80-9f}{80-bf}
                    {ee-ef}{80-bf}{80-bf}
                         f0{90-bf}{80-bf}{80-bf}
                    {f1-f3}{80-bf}{80-bf}{80-bf}
                         f4{80-8f}{80-bf}{80-bf}',
  'UTF-16BE'    => '{00-d7,e0-ff}{00-ff}
                    {d8-db}{00-ff}{dc-df}{00-ff}',
  'UTF-16LE'    => '{00-ff}{00-d7,e0-ff}
                    {00-ff}{d8-db}{00-ff}{dc-df}',
  'UTF-32BE'    => '0000{00-d7,e0-ff}{00-ff}
                    00{01-10}{00-ff}{00-ff}',
  'UTF-32LE'    => '{00-ff}{00-d7,e0-ff}0000
                    {00-ff}{00-ff}{01-10}00',
  'EUC-JP'      => '{00-7f}
                    {a1-fe}{a1-fe}
                    8e{a1-fe}
                    8f{a1-fe}{a1-fe}',
  'CP51932'     => '{00-7f}
                    {a1-fe}{a1-fe}
                    8e{a1-fe}',
  'Shift_JIS'   => '{00-7f}
                    {81-9f,e0-fc}{40-7e,80-fc}
                    {a1-df}',
  'EUC-KR'      => '{00-7f}
                    {a1-fe}{a1-fe}',
  'CP949'       => '{00-7f}
                    {81-fe}{41-5a,61-7a,81-fe}',
  'Big5'        => '{00-7f}
                    {81-fe}{40-7e,a1-fe}',
  'EUC-TW'      => '{00-7f}
                    {a1-fe}{a1-fe}
                    8e{a1-b0}{a1-fe}{a1-fe}',
  'GBK'         => '{00-80}
                    {81-fe}{40-7e,80-fe}',
  'GB18030'     => '{00-7f}
                    {81-fe}{40-7e,80-fe}
                    {81-fe}{30-39}{81-fe}{30-39}',
}

{
  'ASCII-8BIT'  => '1byte',
  'ISO-8859-1'  => '1byte',
  'ISO-8859-2'  => '1byte',
  'ISO-8859-3'  => '1byte',
  'ISO-8859-4'  => '1byte',
  'ISO-8859-5'  => '1byte',
  'ISO-8859-6'  => '1byte',
  'ISO-8859-7'  => '1byte',
  'ISO-8859-8'  => '1byte',
  'ISO-8859-9'  => '1byte',
  'ISO-8859-10' => '1byte',
  'ISO-8859-11' => '1byte',
  'ISO-8859-13' => '1byte',
  'ISO-8859-14' => '1byte',
  'ISO-8859-15' => '1byte',
  'Windows-31J' => 'Shift_JIS',
  'eucJP-ms'    => 'EUC-JP'
}.each {|k, v|
  ValidEncoding[k] = ValidEncoding.fetch(v)
}

def make_signature(filename, src)
  "src=#{filename.dump}, len=#{src.length}, checksum=#{src.sum}"
end

output_filename = nil
verbose_mode = false
force_mode = false

op = OptionParser.new
op.def_option("--help", "show help message") { puts op; exit 0 }
op.def_option("--verbose", "verbose mode") { verbose_mode = true }
op.def_option("--force", "force table generation") { force_mode = true }
op.def_option("--output=FILE", "specify output file") {|arg| output_filename = arg }
op.parse!

VERBOSE_MODE = verbose_mode

arg = ARGV.shift
$srcdir = File.dirname(arg)
$:.unshift $srcdir unless $:.include? $srcdir
src = File.read(arg)
src.force_encoding("ascii-8bit") if src.respond_to? :force_encoding
this_script = File.read(__FILE__)
this_script.force_encoding("ascii-8bit") if this_script.respond_to? :force_encoding

base_signature = "/* autogenerated. */\n"
base_signature << "/* #{make_signature(File.basename(__FILE__), this_script)} */\n"
base_signature << "/* #{make_signature(File.basename(arg), src)} */\n"

if !force_mode && output_filename && File.readable?(output_filename)
  old_signature = File.open(output_filename) {|f| f.gets("").chomp }
  chk_signature = base_signature.dup
  old_signature.each_line {|line|
    if %r{/\* src="([0-9a-z_.-]+)",} =~ line
      name = $1
      next if name == File.basename(arg) || name == File.basename(__FILE__)
      path = File.join($srcdir, name)
      if File.readable? path
        chk_signature << "/* #{make_signature(name, File.read(path))} */\n"
      end
    end
  }
  if old_signature == chk_signature
    now = Time.now
    File.utime(now, now, output_filename)
    STDERR.puts "already up-to-date: #{output_filename}" if VERBOSE_MODE
    exit
  end
end

if VERBOSE_MODE
  if output_filename
    STDERR.puts "generating #{output_filename} ..."
  end
end

libs1 = $".dup
erb = ERB.new(src, nil, '%')
erb.filename = arg
erb_result = erb.result(binding)
libs2 = $".dup

libs = libs2 - libs1
lib_sigs = ''
libs.each {|lib|
  lib = File.basename(lib)
  path = File.join($srcdir, lib)
  if File.readable? path
    lib_sigs << "/* #{make_signature(lib, File.read(path))} */\n"
  end
}

result = ''
result << base_signature
result << lib_sigs
result << "\n"
result << erb_result
result << "\n"

if output_filename
  new_filename = output_filename + ".new"
  FileUtils.mkdir_p(File.dirname(output_filename))
  File.open(new_filename, "wb") {|f| f << result }
  File.rename(new_filename, output_filename)
  STDERR.puts "done." if VERBOSE_MODE
else
  print result
end