summaryrefslogtreecommitdiff
path: root/src/Type1/token.c
blob: 6fb4109e2a0d1e442bda9758d4509b759c4d5a68 (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
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
/* $Xorg: token.c,v 1.4 2000/08/17 19:46:34 cpqbld Exp $ */
/* Copyright International Business Machines,Corp. 1991
 * All Rights Reserved
 *
 * License to use, copy, modify, and distribute this software
 * and its documentation for any purpose and without fee is
 * hereby granted, provided that the above copyright notice
 * appear in all copies and that both that copyright notice and
 * this permission notice appear in supporting documentation,
 * and that the name of IBM not be used in advertising or
 * publicity pertaining to distribution of the software without
 * specific, written prior permission.
 *
 * IBM PROVIDES THIS SOFTWARE "AS IS", WITHOUT ANY WARRANTIES
 * OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, BUT NOT
 * LIMITED TO ANY IMPLIED WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE, AND NONINFRINGEMENT OF
 * THIRD PARTY RIGHTS.  THE ENTIRE RISK AS TO THE QUALITY AND
 * PERFORMANCE OF THE SOFTWARE, INCLUDING ANY DUTY TO SUPPORT
 * OR MAINTAIN, BELONGS TO THE LICENSEE.  SHOULD ANY PORTION OF
 * THE SOFTWARE PROVE DEFECTIVE, THE LICENSEE (NOT IBM) ASSUMES
 * THE ENTIRE COST OF ALL SERVICING, REPAIR AND CORRECTION.  IN
 * NO EVENT SHALL IBM BE LIABLE FOR ANY SPECIAL, INDIRECT OR
 * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING
 * FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF
 * CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
 * OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS
 * SOFTWARE.
 */
/* $XFree86: xc/lib/font/Type1/token.c,v 1.6 2003/05/27 22:26:47 tsi Exp $ */
/* Authors: Sig Nin & Carol Thompson IBM Almaden Research Laboratory */
#include "t1stdio.h"
#include "util.h"
#include "digit.h"
#include "token.h"
#include "tokst.h"
#include "hdigit.h"
 
/*
 * -------------------------------------------------------------------
 * Globals
 * -------------------------------------------------------------------
 */
 
/* These variables are set by the caller */
char           *tokenStartP;   /* Pointer to token buffer in VM */
char           *tokenMaxP;     /* Pointer to last byte in buffer + 1 */
 
/* These variables are set by TOKEN */
int             tokenLength;   /* Characters in token */
boolean         tokenTooLong;  /* Token too long for buffer */
int             tokenType;     /* Type of token identified */
psvalue         tokenValue;    /* Token value */
 
/*
 * -------------------------------------------------------------------
 * Private variables
 * -------------------------------------------------------------------
 */
 
static FILE    *inputFileP;    /* Current input file */
 
 
/* Token */
static char    *tokenCharP;    /* Pointer to next character in token */
 
/*
 * -------------------------------------------------------------------
 * Private routines for manipulating numbers
 * -------------------------------------------------------------------
 */
 
#define Exp10(e) \
((e) == 0\
 ? (double)(1.0)\
 : (-64 <= (e) && (e) <= 63\
    ? Exp10T[(e)+64]\
    : P10(e)\
   )\
)
 
static double Exp10T[128] = {
  1e-64, 1e-63, 1e-62, 1e-61, 1e-60, 1e-59, 1e-58, 1e-57,
  1e-56, 1e-55, 1e-54, 1e-53, 1e-52, 1e-51, 1e-50, 1e-49,
  1e-48, 1e-47, 1e-46, 1e-45, 1e-44, 1e-43, 1e-42, 1e-41,
  1e-40, 1e-39, 1e-38, 1e-37, 1e-36, 1e-35, 1e-34, 1e-33,
  1e-32, 1e-31, 1e-30, 1e-29, 1e-28, 1e-27, 1e-26, 1e-25,
  1e-24, 1e-23, 1e-22, 1e-21, 1e-20, 1e-19, 1e-18, 1e-17,
  1e-16, 1e-15, 1e-14, 1e-13, 1e-12, 1e-11, 1e-10, 1e-9,
  1e-8, 1e-7, 1e-6, 1e-5, 1e-4, 1e-3, 1e-2, 1e-1,
  1e0, 1e1, 1e2, 1e3, 1e4, 1e5, 1e6, 1e7,
  1e8, 1e9, 1e10, 1e11, 1e12, 1e13, 1e14, 1e15,
  1e16, 1e17, 1e18, 1e19, 1e20, 1e21, 1e22, 1e23,
  1e24, 1e25, 1e26, 1e27, 1e28, 1e29, 1e30, 1e31,
  1e32, 1e33, 1e34, 1e35, 1e36, 1e37, 1e38, 1e39,
  1e40, 1e41, 1e42, 1e43, 1e44, 1e45, 1e46, 1e47,
  1e48, 1e49, 1e50, 1e51, 1e52, 1e53, 1e54, 1e55,
  1e56, 1e57, 1e58, 1e59, 1e60, 1e61, 1e62, 1e63
};
 
static double 
P10(long exponent)
{
  double value, power;
 
  if (exponent < 0) {
    power = 0.1;
    value = (exponent & 1 ? power : 1.0);
    exponent++;
    exponent = -(exponent >> 1); /* portable C for -(exponent/2) */
  }
  else {
    power = 10.0;
    value = (exponent & 1 ? power : 1.0);
    exponent = exponent >> 1;
  }
 
  while(exponent > 0) {
    power *= power;
    if (exponent & 1)
      value *= power;
    exponent >>= 1;
  }
 
  return(value);
}
 
/*
 * -------------------------------------------------------------------
 * Private routines and macros for manipulating the input
 * -------------------------------------------------------------------
 */
 
/* Get next character from the input --
 *
 */
#define next_ch()    (_XT1getc(inputFileP))
 
/* Push a character back into the input --
 *
 * Ungetc of EOF will fail, but that's ok: the next getc will
 * return EOF.
 *
 * NOTE:  These macros are presently written to return the character
 * pushed, or EOF if none was pushed.  However, they are not
 * required to return anything in particular, and callers should
 * not rely on the returned value.
 */
#define back_ch(ch)   (T1Ungetc(ch, inputFileP))
 
/* Push a character back into the input if it was not white space.
 * If it is a carriage return (\r) then check next char for
 * linefeed and consume them both, otherwise put next char back.
 *
 */
#define back_ch_not_white(ch) \
(\
isWHITE_SPACE(ch)\
 ? ((ch == '\r')\
   ? (((ch = next_ch()) == '\n')\
     ? EOF\
     : back_ch(ch)\
     )\
   : EOF\
   )\
 : back_ch(ch)\
)
 
/*
 * -------------------------------------------------------------------
 * Private routines and macros for manipulating the token buffer
 * -------------------------------------------------------------------
 */
 
/* Add a character to the token
 * ---- use ONLY when you KNOW that this character will
 *      be stored within the token buffer.
 */
#define save_unsafe_ch(ch) (*tokenCharP++ = ch)
 
/* Add a character to the token, if not too long to fit */
#define save_ch(ch) \
((tokenCharP < tokenMaxP)\
 ? save_unsafe_ch(ch)\
 : (tokenTooLong = TRUE)\
)

#define save_ch_no_inc(ch) \
if (tokenCharP < tokenMaxP) *tokenCharP = ch
 
/*
 * -------------------------------------------------------------------
 * Action Routines
 *
 *  These routines all
 *    -- take int ch as a parameter
 *    -- return int ch if no token was recognized, DONE otherwise
 *    -- leave the next character in the input, if returning DONE
 * -------------------------------------------------------------------
 */
 
#define DONE  (256)
 
/* Get the next input character */
static int 
next_char(int ch)
{
  return(next_ch());
}
 
/* Add character to token */
static int 
add_char(int ch)
{
  save_ch(ch);
  return(next_ch());
}
 
 
/* -------------------------------------------------------------------
 * Skip white space and comments
 */
 
/* Skip white space */
static int 
skip_space(int ch)
{
  do {
    ch = next_ch();
  } while(isWHITE_SPACE(ch));
  return(ch);
}
 
/* Skip comments */
static int 
skip_comment(int ch)
{
  do {
    ch = next_ch();
  } while(isCOMMENT(ch));
  return(ch);
}
 
/* -------------------------------------------------------------------
 * Collect value elements for a number
 */
 
/* decimal integer or real number mantissa */
static int m_sign;
static long m_value;
static long m_scale;
 
/* real number exponent */
static int e_sign;
static long e_value;
 
/* radix number */
static long r_base;
static long r_value;
static long r_scale;
 
static int 
add_sign(int ch)
{
  m_sign = ch;
  save_unsafe_ch(ch);
  return(next_ch());
}
 
static int 
add_1st_digits(int ch)
{
  m_sign = '+';
  return(add_digits(ch));
}
 
static int 
add_digits(int ch)
{
  long value, p_value, scale;
  int digit;
 
  /* On entry, expect m_sign to be set to '+' or '-';
   *  ch is a decimal digit.
   * Expect at most one character saved at this point,
   *  a sign.  This routine will save up to 10 more
   *  characters without checking the buffer boundary.
   */
 
  value = ch - '0';
  save_unsafe_ch(ch);
  ch = next_ch();
 
  while(isDECIMAL_DIGIT(ch) && value < (MAX_INTEGER/10)) {
    value = (value << 3) + (value << 1) + (ch - '0');
    save_unsafe_ch(ch);
    ch = next_ch();
  }
 
  /* Quick exit for small integers --
   *    |x| <= 10*((MAX_INTEGER/10)-1)+9
   *    |x| <= 2,147,483,639 for 32 bit integers
   */
  if (isNUMBER_ENDER(ch)) {
    back_ch_not_white(ch);
    tokenValue.integer = (m_sign == '-' ? -value : value);
    tokenType = TOKEN_INTEGER;
    return(DONE);
  }
 
  /* Handle additional digits.  Beyond the boundary case,
   *   10*(MAX_INTEGER/10) <= |number| <= MAX_INTEGER
   * just count the digits: the number is too large to
   * represent as an integer and will be returned as a real.
   * The mantissa of a real holds fewer bits than an integer.
   */
  p_value = value;
  value = (m_sign == '-' ? -value : value);
  scale = 0;
 
  if (isDECIMAL_DIGIT(ch)) {
 
    /* Handle the boundary case */
    if (p_value == (MAX_INTEGER/10)) {
      digit = ch - '0';
 
      /* Must handle positive and negative values separately  */
      /* for 2's complement arithmetic */
      if (value > 0) {
        if (digit <= MAX_INTEGER%10)
          value = (value << 3) + (value << 1) + digit;
        else
          ++scale;  /* Too big, just count it */
      }
      else {
        /* Use positive % operands for portability */
        if (digit <= -(MIN_INTEGER+10)%10)
          value = (value << 3) + (value << 1) - digit;
        else
          ++scale;  /* Too big, just count it */
      }
    }
    else
      ++scale;  /* Not boundary case, just count digit */
 
    save_unsafe_ch(ch);
    ch = next_ch();
 
    /* Continue scanning digits, but can't store them */
    while(isDECIMAL_DIGIT(ch)) {
      ++scale;
      save_ch(ch);
      ch = next_ch();
    }
  }
 
  /* Continue from here scanning radix integer or real */
  m_value = value;
  m_scale = scale;
 
  /* Initialize for possible real */
  e_sign = '+';
  e_value = 0;
 
  return(ch);
}
 
static int 
add_1st_decpt(int ch)
{
  m_sign = '+';
  return(add_decpt(ch));
}
 
static int 
add_decpt(int ch)
{
  /* On entry, expect m_sign to be set to '+' or '-' */
  m_value = 0;
  m_scale = 0;
  save_unsafe_ch(ch);
  return(next_ch());
}
 
static int 
add_fraction(int ch)
{
  long value, scale;
  int digit;
 
  /* On entry, expect m_value and m_scale to be initialized,
   * and m_sign to be set to '+' or '-'.  Expect m_value and m_sign
   * to be consistent (this is not checked).
   */
  value = m_value;
  scale = m_scale;
 
  /* Scan leading zeroes */
  if (value == 0) {
    while(ch == '0') {
      --scale;
      save_ch(ch);
      ch = next_ch();
    }
 
    /* Scan first significant digit */
    if (isDECIMAL_DIGIT(ch)) {
      --scale;
      value = ch - '0';
      value = (m_sign == '-' ? -value : value);
      save_ch(ch);
      ch = next_ch();
    }
    else
      /* no significant digits -- number is zero */
      scale = 0;
  }
  /* value != 0 || value == 0 && !isDECIMAL_DIGIT(ch) */
 
  /* Scan additional significant digits */
  if (isDECIMAL_DIGIT(ch)) {
    if (value > 0) {
      while(isDECIMAL_DIGIT(ch) && value < (MAX_INTEGER/10)) {
        --scale;
        value = (value << 3) + (value << 1) + (ch - '0');
        save_ch(ch);
        ch = next_ch();
      }
      /* Check boundary case */
      if (isDECIMAL_DIGIT(ch) && value == (MAX_INTEGER/10)) {
        digit = ch - '0';
        if (digit <= MAX_INTEGER%10) {
          --scale;
          value = (value << 3) + (value << 1) + digit;
          save_ch(ch);
          ch = next_ch();
        }
      }
    }
    else {
      /* value < 0 */
      while(isDECIMAL_DIGIT(ch) && value > -(-(MIN_INTEGER+10)/10+1)) {
        /* Use positive / operands for portability */
        --scale;
        value = (value << 3) + (value << 1) - (ch - '0');
        save_ch(ch);
        ch = next_ch();
      }
      /* Check boundary case */
      if (isDECIMAL_DIGIT(ch)
          && value == -(-(MIN_INTEGER+10)/10+1)) {
        digit = ch - '0';
        if (digit <= -(MIN_INTEGER+10)%10) {
        /* Use positive % operands for portability */
          --scale;
          value = (value << 3) + (value << 1) - digit;
          save_ch(ch);
          ch = next_ch();
        }
      }
    }
 
    /* Additional digits can be discarded */
    while(isDECIMAL_DIGIT(ch)) {
      save_ch(ch);
      ch = next_ch();
    }
  }
 
  /* Store results */
  m_value = value;
  m_scale = scale;
 
  /* Initialize for possible real */
  e_sign = '+';
  e_value = 0;
 
  return(ch);
}
 
static int 
add_e_sign(int ch)
{
  e_sign = ch;
  save_ch(ch);
  return(next_ch());
}
 
static int 
add_exponent(int ch)
{
  long value, p_value;
  long scale = 0;
  int digit;
 
  /* On entry, expect e_sign to be set to '+' or '-' */
 
  value = ch - '0';
  save_ch(ch);
  ch = next_ch();
 
  while(isDECIMAL_DIGIT(ch) && value < (MAX_INTEGER/10)) {
    value = (value << 3) + (value << 1) + (ch - '0');
    save_ch(ch);
    ch = next_ch();
  }
 
  p_value = value;
  value = (e_sign == '-' ? -value : value);
 
  /* Handle additional digits.  Beyond the boundary case,
   *   10*(MAX_INTEGER/10) <= |number| <= MAX_INTEGER
   * just count the digits: the number is too large to
   * represent as an integer.
   */
  if (isDECIMAL_DIGIT(ch)) {
 
    /* Examine boundary case */
    if (p_value == (MAX_INTEGER/10)) {
      digit = ch - '0';
 
      /* Must handle positive and negative values separately */
      /*  for 2's complement arithmetic */
      if (value > 0) {
        if (digit <= MAX_INTEGER%10)
          value = (value << 3) + (value << 1) + digit;
        else
          ++scale; /* Too big, just count it */
      }
      else {
        /* Use positive % operands for portability */
        if (digit <= -(MIN_INTEGER+10)%10)
          value = (value << 3) + (value << 1) - digit;
        else
          ++scale; /* Too big, just count it */
      }
    }
    else
      ++scale;  /* Not boundary case, just count digit */
 
    save_ch(ch);
    ch = next_ch();
 
    /* Continue scanning digits, but can't store any more */
    while(isDECIMAL_DIGIT(ch)) {
      ++scale;
      save_ch(ch);
      ch = next_ch();
    }
  }
 
  /* Store results */
  e_value = value;
 
  return(ch);
}
 
static int 
add_radix(int ch)
{
  if (2 <= m_value && m_value <= 36 && m_scale == 0) {
    r_base = m_value;
    save_ch(ch);
    return(next_ch());
  }
  else {
    /* Radix invalid, complete a name token */
    return(AAH_NAME(ch));
  }
}
 
static int 
add_r_digits(int ch)
{
  unsigned long value;
  long radix, scale;
  int digit;
 
  /* NOTE:  The syntax of a radix number allows only for
   * values of zero or more.  The value will be stored as
   * a 32 bit integer, which PostScript then interprets
   * as signed.  This means, for example, that the numbers:
   *
   *     8#37777777777
   *    10#4294967295
   *    16#FFFFFFFF
   *    36#1Z141Z3
   *
   * are all interpreted as -1.  This routine implements this
   * idea explicitly:  it accumulates the number's value
   * as unsigned, then casts it to signed when done.
   */
 
  /* Expect r_base to be initialized */
  radix = r_base;
  value = 0;
  scale = 0;
 
  /* Scan leading zeroes */
  while(ch == '0') {
    save_ch(ch);
    ch = next_ch();
  }
 
  /* Handle first non-zero digit */
  if ((digit=digit_value[ch]) < radix) {
    value = digit;
    save_ch(ch);
    ch = next_ch();
 
    /* Add digits until boundary case reached */
    while((digit=digit_value[ch]) < radix
            && value < (MAX_ULONG / radix)) {
      value = value * radix + digit;
      save_ch(ch);
      ch = next_ch();
    };
 
    /* Scan remaining digits */
    if ((digit=digit_value[ch]) < radix) {
 
      /* Examine boundary case ---
       *   radix*(MAX_ULONG/radix) <= number <= MAX_ULONG
       */
      if (value == (MAX_ULONG/radix) && digit <= MAX_ULONG%radix)
        value = value * radix + digit;
      else
        ++scale;
 
      /* Continue scanning digits, but can't store them */
      save_ch(ch);
      ch = next_ch();
      while(digit_value[ch] < radix) {
        ++scale;
        save_ch(ch);
        ch = next_ch();
      }
    }
  }
 
  /* Store result */
  r_value = (long) value; /* result is signed */
  r_scale = scale;
 
  return(ch);
}
 
/* -------------------------------------------------------------------
 * Complete a number; set token type and done flag.
 * Put current input character back, if it is not white space.
 */
 
/* Done: Radix Number */
static int 
RADIX_NUMBER(int ch)
{
  back_ch_not_white(ch);
  if (r_scale == 0) {
    tokenValue.integer = r_value;
    tokenType = TOKEN_INTEGER;
  }
  else {
    tokenType = TOKEN_NAME;
  }
  return(DONE);
}
 
/* Done: Integer */
static int 
INTEGER(int ch)
{
  back_ch_not_white(ch);
  if (m_scale == 0) {
    tokenValue.integer = m_value;
    tokenType = TOKEN_INTEGER;
  }
  else {
    tokenValue.real = (double)(m_value) * Exp10(m_scale);
    tokenType = TOKEN_REAL;
  }
  return(DONE);
}
 
/* Done: Real */
static int 
REAL(int ch)
{
  double temp;
 
  back_ch_not_white(ch);
 
  /* HAZARD: exponent overflow of intermediate result
   * (e.g., in 370 floating point); this should not be a problem
   * with IEEE floating point.  Reduce exponent overflow hazard by
   * combining m_scale and e_value first, if they have different signs,
   * or multiplying m_value and one of the other factors, if both
   * m_scale and e_value are negative.
   */
  if ((m_scale >= 0 && e_value <= 0)
      || (m_scale <= 0 && e_value >= 0)) {
    tokenValue.real = (double)(m_value) * Exp10(m_scale + e_value);
  }
  else {
    temp = (double)(m_value) * Exp10(m_scale);
    tokenValue.real = temp * Exp10(e_value);
  }
 
  tokenType = TOKEN_REAL;
  return(DONE);
}
 
 
/* -------------------------------------------------------------------
 * Assemble a hex string; set token type and done flag.
 */
 
/* Done: Hex String */
static int 
HEX_STRING(int ch)
{
  int value;
 
  while(TRUE) {
 
    /* Process odd digit */
    ch = next_ch();
    if (!isHEX_DIGIT(ch)) {
 
      /* Skip white space */
      while(isWHITE_SPACE(ch))
        ch = next_ch();
 
      /* Check for terminator */
      if (!isHEX_DIGIT(ch)) {
        break;
      }
    }
    value = digit_value[ch] << 4;
 
    /* Process even digit */
    ch = next_ch();
    if (!isHEX_DIGIT(ch)) {
 
      /* Skip white space */
      while(isWHITE_SPACE(ch))
        ch = next_ch();
 
      /* Check for terminator */
      if (!isHEX_DIGIT(ch)) {
        save_ch(value);
        break;
      }
    }
    save_ch(value + digit_value[ch]);
  }
 
  /* Classify result, based on why loop ended */
  if (ch == '>')
    tokenType = TOKEN_HEX_STRING;
  else {
    /* save the invalid character for error reporting */
    save_ch(ch);
    tokenType = TOKEN_INVALID;
  }
 
  return(DONE);
}
 
/* -------------------------------------------------------------------
 * Assemble a string; set token type and done flag
 */
 
/* Save a backslash-coded character in a string --
 *
 *   Store the proper character for special cases
 *   "\b", "\f", "\n", "\r", and "\t".
 *
 *   Decode and store octal-coded character, up to
 *   three octal digits, "\o", "\oo", and "\ooo".
 *
 *   The sequence "\<newline>" is a line continuation,
 *   so consume both without storing anything.
 *
 *   The sequence "\<EOF>" is an error; exit without
 *   storing anything and let the caller handle it.
 *
 *   For other characters, including the sequences
 *   "\\", "\(", and "\)", simply store the second
 *   character.
 */
static void 
save_digraph(int ch)
{
  int value;
 
  switch (ch) {
 
    case 'b':   /* backspace */
      ch = '\b';
      break;
 
    case 'f':   /* formfeed */
      ch = '\f';
      break;
 
    case 'n':   /* newline */
      ch = '\n';
      break;
 
    case 'r':   /* carriage return */
      ch = '\r';
      break;
 
    case 't':   /* horizontal tab */
      ch = '\t';
      break;
 
    case '\n':  /* line continuation -- consume it */
      return;
 
    case '\r':  /* carriage return   -- consume it */
      ch = next_ch();   /* look at next character, is it \n?  */
      if (ch == '\n')  return;
      back_ch(ch);      /* if not a line feed, then return it */
      return;
 
    case EOF:   /* end of file -- forget it */
      return;
 
  default:
    /* scan up to three octal digits to get value */
    if (isOCTAL_DIGIT(ch)) {
      value = digit_value[ch];
      ch = next_ch();
      if (isOCTAL_DIGIT(ch)) {
        value = (value << 3) + digit_value[ch];
        ch = next_ch();
        if (isOCTAL_DIGIT(ch))
          value = (value << 3) + digit_value[ch];
        else
          back_ch(ch);
      }
      else
        back_ch(ch);
      ch = value;
    }
  }
 
  /* Found a character to save */
  save_ch(ch);
}
 
/* Done: String */
static int 
STRING(int ch)
{
  int nest_level = 1;
 
  tokenType = TOKEN_STRING;
 
  do {
 
    ch = next_ch();
    while(!isSTRING_SPECIAL(ch)) {
      save_ch(ch);
      ch = next_ch();
    };
 
    switch (ch) {
 
     case '(':
       ++nest_level;
       save_ch(ch);
       break;
 
     case ')':
       if (--nest_level > 0)
         save_ch(ch);
       break;
 
     case '\\':
          save_digraph(next_ch());
        break;
 
     case '\r':
        /* All carriage returns (\r) are turned into linefeeds (\n)*/
          ch = next_ch();       /* get the next one, is it \n? */
          if (ch != '\n') {     /* if not, then put it back.   */
            back_ch(ch);
          }
          save_ch('\n');        /* in either case, save a linefeed */
        break;
 
 
     case EOF:
       tokenType = TOKEN_INVALID;  /* Unterminated string */
       nest_level = 0;
       break;
    }
 
  } while(nest_level > 0);
 
  /* If there's room, add a 0-byte termination without increasing string
     length.  This fixes certain dependencies on 0-terminated strings */
  save_ch_no_inc(0);

  return(DONE);
}
 
 
/* -------------------------------------------------------------------
 * Assemble a name; set token type and done flag.
 * Put current input character back, if it is not white space.
 */
 
/* Done: Name
 *  (Safe version used to complete name tokens that
 *   start out looking like something else).
 */
 
static int 
AAH_NAME(int ch)
{
  do {
    save_ch(ch);
    ch = next_ch();
  } while(isNAME(ch));
 
  back_ch_not_white(ch);
  tokenType = TOKEN_NAME;
  return(DONE);
}
 
/* Done: Name */
static int 
NAME(int ch)
{
  save_unsafe_ch(ch);
  ch = next_ch();
  if (isNAME(ch)) {
    save_unsafe_ch(ch);
    ch = next_ch();
    if (isNAME(ch)) {
      save_unsafe_ch(ch);
      ch = next_ch();
      if (isNAME(ch)) {
        save_unsafe_ch(ch);
        ch = next_ch();
        if (isNAME(ch)) {
          save_unsafe_ch(ch);
          ch = next_ch();
          if (isNAME(ch)) {
            save_unsafe_ch(ch);
            ch = next_ch();
            if (isNAME(ch)) {
              save_unsafe_ch(ch);
              ch = next_ch();
              while(isNAME(ch)) {
                save_ch(ch);
                ch = next_ch();
              }
            }
          }
        }
      }
    }
  }
 
  back_ch_not_white(ch);
  tokenType = TOKEN_NAME;
  return(DONE);
}
 
/* Done: Literal Name */
static int 
LITERAL_NAME(int ch)
{
  if (isNAME(ch)) {
    save_unsafe_ch(ch);
    ch = next_ch();
    if (isNAME(ch)) {
      save_unsafe_ch(ch);
      ch = next_ch();
      if (isNAME(ch)) {
        save_unsafe_ch(ch);
        ch = next_ch();
        if (isNAME(ch)) {
          save_unsafe_ch(ch);
          ch = next_ch();
          if (isNAME(ch)) {
            save_unsafe_ch(ch);
            ch = next_ch();
            if (isNAME(ch)) {
              save_unsafe_ch(ch);
              ch = next_ch();
              while(isNAME(ch)) {
                save_ch(ch);
                ch = next_ch();
              }
            }
          }
        }
      }
    }
  }
 
  back_ch_not_white(ch);
  tokenType = TOKEN_LITERAL_NAME;
  return(DONE);
}
 
/* Done: immediate Name */
static int 
IMMED_NAME(int ch)
{
  ch = next_ch();
  if (isNAME(ch)) {
    save_unsafe_ch(ch);
    ch = next_ch();
    if (isNAME(ch)) {
      save_unsafe_ch(ch);
      ch = next_ch();
      if (isNAME(ch)) {
        save_unsafe_ch(ch);
        ch = next_ch();
        if (isNAME(ch)) {
          save_unsafe_ch(ch);
          ch = next_ch();
          if (isNAME(ch)) {
            save_unsafe_ch(ch);
            ch = next_ch();
            if (isNAME(ch)) {
              save_unsafe_ch(ch);
              ch = next_ch();
              while(isNAME(ch)) {
                save_ch(ch);
                ch = next_ch();
              }
            }
          }
        }
      }
    }
  }
 
  back_ch_not_white(ch);
  tokenType = TOKEN_IMMED_NAME;
  return(DONE);
}
 
/* Done: Name found while looking for something else */
static int 
OOPS_NAME(int ch)
{
  back_ch_not_white(ch);
  tokenType = TOKEN_NAME;
  return(DONE);
}
 
 
/* -------------------------------------------------------------------
 * Complete a miscellaneous token; set token type and done flag.
 */
 
/* Done: Unmatched Right Angle-Bracket */
static int 
RIGHT_ANGLE(int ch)
{
  tokenType = TOKEN_RIGHT_ANGLE;
  return(DONE);
}
 
/* Done: Unmatched Right Parenthesis */
static int 
RIGHT_PAREN(int ch)
{
  tokenType = TOKEN_RIGHT_PAREN;
  return(DONE);
}
 
/* Done: Left Brace */
static int 
LEFT_BRACE(int ch)
{
  tokenType = TOKEN_LEFT_BRACE;
  return(DONE);
}
 
/* Done: Right Brace */
static int 
RIGHT_BRACE(int ch)
{
  tokenType = TOKEN_RIGHT_BRACE;
  return(DONE);
}
 
/* Done: Left Bracket */
static int 
LEFT_BRACKET(int ch)
{
  save_unsafe_ch(ch);
  tokenType = TOKEN_LEFT_BRACKET;
  return(DONE);
}
 
/* Done: Right Bracket */
static int 
RIGHT_BRACKET(int ch)
{
  save_unsafe_ch(ch);
  tokenType = TOKEN_RIGHT_BRACKET;
  return(DONE);
}
 
/* Done: Break */
static int 
BREAK_SIGNAL(int ch)
{
  tokenType = TOKEN_BREAK;
  return(DONE);
}
 
/* Done: No Token Found */
static int 
NO_TOKEN(int ch)
{
  tokenType = TOKEN_EOF;
  return(DONE);
}
 
 
/*
 * -------------------------------------------------------------------
 *  scan_token -- scan one token from the input.  It uses a simple
 *    finite state machine to recognize token classes.
 *
 *  The input is from a file.
 *
 *  On entry --
 *
 *    inputP -> input PostScript object, a file.
 *    tokenStartP -> buffer in VM for accumulating the token.
 *    tokenMaxP -> last character in the token buffer
 *
 *  On exit --
 *
 *    tokenLength = number of characters in the token
 *    tokenTooLong = TRUE if the token did not fit in the buffer
 *    tokenType = code for the type of token parsed.
 *    tokenValue = converted value of a numeric token.
 *
 *
 * -------------------------------------------------------------------
 */
void 
scan_token(psobj *inputP)
{
  int ch;
  unsigned char *stateP = s0;
  unsigned char entry;
  int (*actionP)(int);
 
  /* Define input source */
  inputFileP = inputP->data.fileP;
  if (inputFileP == NULL)  {
    tokenType = TOKEN_EOF;
    return;
  }
 
  /* Ensure enough space for most cases
   * (so we don't have to keep checking)
   * The length needs to cover the maximum number
   * of save_unsafe_ch() calls that might be executed.
   * That number is 11 (a sign and 10 decimal digits, e.g.,
   * when scanning -2147483648), but use MAX_NAME_LEN
   * in case someone changes that without checking.
   */
  tokenStartP = vm_next_byte();
  tokenMaxP = tokenStartP + MIN(vm_free_bytes(), MAX_STRING_LEN);
 
  if ((tokenMaxP-tokenStartP) < (MAX_NAME_LEN)) {
    tokenLength = 0;
    tokenTooLong = TRUE;
    tokenType = TOKEN_NONE;
    tokenValue.integer = 0;
    return;
  }
 
  /* Reset token */
  tokenCharP = tokenStartP;
  tokenTooLong = FALSE;
 
  /* Scan one token */
  ch = next_ch();
  do {
    entry = stateP[ch];
    stateP = classActionTable[entry].nextStateP;
    actionP = classActionTable[entry].actionRoutineP;
    ch = (*actionP)(ch);
  } while(ch != DONE);
 
 
  /* Return results */
  tokenLength = tokenCharP - tokenStartP;
}