summaryrefslogtreecommitdiff
path: root/libguile/chars.c
blob: fe55f9e2e8c541d1871797e3551f569460b65a48 (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
/* Copyright 1995-1996,1998,2000-2001,2004,2006,2008-2011,2014,2018-2019
     Free Software Foundation, Inc.

   This file is part of Guile.

   Guile is free software: you can redistribute it and/or modify it
   under the terms of the GNU Lesser General Public License as published
   by the Free Software Foundation, either version 3 of the License, or
   (at your option) any later version.

   Guile is distributed in the hope that it will be useful, but WITHOUT
   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
   FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
   License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with Guile.  If not, see
   <https://www.gnu.org/licenses/>.  */




#ifdef HAVE_CONFIG_H
# include <config.h>
#endif

#include <ctype.h>
#include <limits.h>
#include <string.h>
#include <unicase.h>
#include <unictype.h>

#include "boolean.h"
#include "gsubr.h"
#include "numbers.h"
#include "pairs.h"
#include "srfi-14.h"
#include "symbols.h"

#include "chars.h"




SCM_DEFINE (scm_char_p, "char?", 1, 0, 0, 
            (SCM x),
	    "Return @code{#t} iff @var{x} is a character, else @code{#f}.")
#define FUNC_NAME s_scm_char_p
{
  return scm_from_bool (SCM_CHARP(x));
}
#undef FUNC_NAME

static SCM scm_i_char_eq_p (SCM x, SCM y, SCM rest);
SCM_DEFINE (scm_i_char_eq_p, "char=?", 0, 2, 1,
            (SCM x, SCM y, SCM rest),
            "Return @code{#t} if the Unicode code point of @var{x} is equal to the\n"
            "code point of @var{y}, else @code{#f}.\n")
#define FUNC_NAME s_scm_i_char_eq_p
{
  if (SCM_UNBNDP (x) || SCM_UNBNDP (y))
    return SCM_BOOL_T;
  while (!scm_is_null (rest))
    {
      if (scm_is_false (scm_char_eq_p (x, y)))
        return SCM_BOOL_F;
      x = y;
      y = scm_car (rest);
      rest = scm_cdr (rest);
    }
  return scm_char_eq_p (x, y);
}
#undef FUNC_NAME

SCM scm_char_eq_p (SCM x, SCM y)
#define FUNC_NAME s_scm_i_char_eq_p
{
  SCM_VALIDATE_CHAR (1, x);
  SCM_VALIDATE_CHAR (2, y);
  return scm_from_bool (scm_is_eq (x, y));
}
#undef FUNC_NAME


static SCM scm_i_char_less_p (SCM x, SCM y, SCM rest);
SCM_DEFINE (scm_i_char_less_p, "char<?", 0, 2, 1, 
            (SCM x, SCM y, SCM rest),
            "Return @code{#t} iff the code point of @var{x} is less than the code\n"
            "point of @var{y}, else @code{#f}.")
#define FUNC_NAME s_scm_i_char_less_p
{
  if (SCM_UNBNDP (x) || SCM_UNBNDP (y))
    return SCM_BOOL_T;
  while (!scm_is_null (rest))
    {
      if (scm_is_false (scm_char_less_p (x, y)))
        return SCM_BOOL_F;
      x = y;
      y = scm_car (rest);
      rest = scm_cdr (rest);
    }
  return scm_char_less_p (x, y);
}
#undef FUNC_NAME

SCM scm_char_less_p (SCM x, SCM y)
#define FUNC_NAME s_scm_i_char_less_p
{
  SCM_VALIDATE_CHAR (1, x);
  SCM_VALIDATE_CHAR (2, y);
  return scm_from_bool (SCM_CHAR(x) < SCM_CHAR(y));
}
#undef FUNC_NAME

static SCM scm_i_char_leq_p (SCM x, SCM y, SCM rest);
SCM_DEFINE (scm_i_char_leq_p, "char<=?", 0, 2, 1,
            (SCM x, SCM y, SCM rest),
            "Return @code{#t} if the Unicode code point of @var{x} is less than or\n"
            "equal to the code point of @var{y}, else @code{#f}.")
#define FUNC_NAME s_scm_i_char_leq_p
{
  if (SCM_UNBNDP (x) || SCM_UNBNDP (y))
    return SCM_BOOL_T;
  while (!scm_is_null (rest))
    {
      if (scm_is_false (scm_char_leq_p (x, y)))
        return SCM_BOOL_F;
      x = y;
      y = scm_car (rest);
      rest = scm_cdr (rest);
    }
  return scm_char_leq_p (x, y);
}
#undef FUNC_NAME

SCM scm_char_leq_p (SCM x, SCM y)
#define FUNC_NAME s_scm_i_char_leq_p
{
  SCM_VALIDATE_CHAR (1, x);
  SCM_VALIDATE_CHAR (2, y);
  return scm_from_bool (SCM_CHAR(x) <= SCM_CHAR(y));
}
#undef FUNC_NAME

static SCM scm_i_char_gr_p (SCM x, SCM y, SCM rest);
SCM_DEFINE (scm_i_char_gr_p, "char>?", 0, 2, 1,
            (SCM x, SCM y, SCM rest),
            "Return @code{#t} if the Unicode code point of @var{x} is greater than\n"
            "the code point of @var{y}, else @code{#f}.")
#define FUNC_NAME s_scm_i_char_gr_p
{
  if (SCM_UNBNDP (x) || SCM_UNBNDP (y))
    return SCM_BOOL_T;
  while (!scm_is_null (rest))
    {
      if (scm_is_false (scm_char_gr_p (x, y)))
        return SCM_BOOL_F;
      x = y;
      y = scm_car (rest);
      rest = scm_cdr (rest);
    }
  return scm_char_gr_p (x, y);
}
#undef FUNC_NAME

SCM scm_char_gr_p (SCM x, SCM y)
#define FUNC_NAME s_scm_i_char_gr_p
{
  SCM_VALIDATE_CHAR (1, x);
  SCM_VALIDATE_CHAR (2, y);
  return scm_from_bool (SCM_CHAR(x) > SCM_CHAR(y));
}
#undef FUNC_NAME

static SCM scm_i_char_geq_p (SCM x, SCM y, SCM rest);
SCM_DEFINE (scm_i_char_geq_p, "char>=?", 0, 2, 1,
            (SCM x, SCM y, SCM rest),
            "Return @code{#t} if the Unicode code point of @var{x} is greater than\n"
            "or equal to the code point of @var{y}, else @code{#f}.")
#define FUNC_NAME s_scm_i_char_geq_p
{
  if (SCM_UNBNDP (x) || SCM_UNBNDP (y))
    return SCM_BOOL_T;
  while (!scm_is_null (rest))
    {
      if (scm_is_false (scm_char_geq_p (x, y)))
        return SCM_BOOL_F;
      x = y;
      y = scm_car (rest);
      rest = scm_cdr (rest);
    }
  return scm_char_geq_p (x, y);
}
#undef FUNC_NAME

SCM scm_char_geq_p (SCM x, SCM y)
#define FUNC_NAME s_scm_i_char_geq_p
{
  SCM_VALIDATE_CHAR (1, x);
  SCM_VALIDATE_CHAR (2, y);
  return scm_from_bool (SCM_CHAR(x) >= SCM_CHAR(y));
}
#undef FUNC_NAME

/* FIXME?: R6RS specifies that these comparisons are case-folded.
   This is the same thing as comparing the uppercase characters in
   practice, but, not in theory.  Unicode has table containing their
   definition of case-folded character mappings.  A more correct
   implementation would be to use that table and make a char-foldcase
   function.  */

static SCM scm_i_char_ci_eq_p (SCM x, SCM y, SCM rest);
SCM_DEFINE (scm_i_char_ci_eq_p, "char-ci=?", 0, 2, 1,
            (SCM x, SCM y, SCM rest),
            "Return @code{#t} if the case-folded Unicode code point of @var{x} is\n"
            "the same as the case-folded code point of @var{y}, else @code{#f}.")
#define FUNC_NAME s_scm_i_char_ci_eq_p
{
  if (SCM_UNBNDP (x) || SCM_UNBNDP (y))
    return SCM_BOOL_T;
  while (!scm_is_null (rest))
    {
      if (scm_is_false (scm_char_ci_eq_p (x, y)))
        return SCM_BOOL_F;
      x = y;
      y = scm_car (rest);
      rest = scm_cdr (rest);
    }
  return scm_char_ci_eq_p (x, y);
}
#undef FUNC_NAME

SCM scm_char_ci_eq_p (SCM x, SCM y)
#define FUNC_NAME s_scm_i_char_ci_eq_p
{
  SCM_VALIDATE_CHAR (1, x);
  SCM_VALIDATE_CHAR (2, y);
  return scm_from_bool (scm_c_upcase(SCM_CHAR(x))==scm_c_upcase(SCM_CHAR(y)));
}
#undef FUNC_NAME

static SCM scm_i_char_ci_less_p (SCM x, SCM y, SCM rest);
SCM_DEFINE (scm_i_char_ci_less_p, "char-ci<?", 0, 2, 1,
            (SCM x, SCM y, SCM rest),
            "Return @code{#t} if the case-folded Unicode code point of @var{x} is\n"
            "less than the case-folded code point of @var{y}, else @code{#f}.")
#define FUNC_NAME s_scm_i_char_ci_less_p
{
  if (SCM_UNBNDP (x) || SCM_UNBNDP (y))
    return SCM_BOOL_T;
  while (!scm_is_null (rest))
    {
      if (scm_is_false (scm_char_ci_less_p (x, y)))
        return SCM_BOOL_F;
      x = y;
      y = scm_car (rest);
      rest = scm_cdr (rest);
    }
  return scm_char_ci_less_p (x, y);
}
#undef FUNC_NAME

SCM scm_char_ci_less_p (SCM x, SCM y)
#define FUNC_NAME s_scm_i_char_ci_less_p
{
  SCM_VALIDATE_CHAR (1, x);
  SCM_VALIDATE_CHAR (2, y);
  return scm_from_bool ((scm_c_upcase(SCM_CHAR(x))) < scm_c_upcase(SCM_CHAR(y)));
}
#undef FUNC_NAME

static SCM scm_i_char_ci_leq_p (SCM x, SCM y, SCM rest);
SCM_DEFINE (scm_i_char_ci_leq_p, "char-ci<=?", 0, 2, 1,
            (SCM x, SCM y, SCM rest),
            "Return @code{#t} iff the case-folded Unicode code point of @var{x} is\n"
            "less than or equal to the case-folded code point of @var{y}, else\n"
            "@code{#f}")
#define FUNC_NAME s_scm_i_char_ci_leq_p
{
  if (SCM_UNBNDP (x) || SCM_UNBNDP (y))
    return SCM_BOOL_T;
  while (!scm_is_null (rest))
    {
      if (scm_is_false (scm_char_ci_leq_p (x, y)))
        return SCM_BOOL_F;
      x = y;
      y = scm_car (rest);
      rest = scm_cdr (rest);
    }
  return scm_char_ci_leq_p (x, y);
}
#undef FUNC_NAME

SCM scm_char_ci_leq_p (SCM x, SCM y)
#define FUNC_NAME s_scm_i_char_ci_leq_p
{
  SCM_VALIDATE_CHAR (1, x);
  SCM_VALIDATE_CHAR (2, y);
  return scm_from_bool (scm_c_upcase(SCM_CHAR(x)) <= scm_c_upcase(SCM_CHAR(y)));
}
#undef FUNC_NAME

static SCM scm_i_char_ci_gr_p (SCM x, SCM y, SCM rest);
SCM_DEFINE (scm_i_char_ci_gr_p, "char-ci>?", 0, 2, 1,
            (SCM x, SCM y, SCM rest),
            "Return @code{#t} iff the case-folded code point of @var{x} is greater\n"
            "than the case-folded code point of @var{y}, else @code{#f}.")
#define FUNC_NAME s_scm_i_char_ci_gr_p
{
  if (SCM_UNBNDP (x) || SCM_UNBNDP (y))
    return SCM_BOOL_T;
  while (!scm_is_null (rest))
    {
      if (scm_is_false (scm_char_ci_gr_p (x, y)))
        return SCM_BOOL_F;
      x = y;
      y = scm_car (rest);
      rest = scm_cdr (rest);
    }
  return scm_char_ci_gr_p (x, y);
}
#undef FUNC_NAME

SCM scm_char_ci_gr_p (SCM x, SCM y)
#define FUNC_NAME s_scm_i_char_ci_gr_p
{
  SCM_VALIDATE_CHAR (1, x);
  SCM_VALIDATE_CHAR (2, y);
  return scm_from_bool (scm_c_upcase(SCM_CHAR(x)) > scm_c_upcase(SCM_CHAR(y)));
}
#undef FUNC_NAME

static SCM scm_i_char_ci_geq_p (SCM x, SCM y, SCM rest);
SCM_DEFINE (scm_i_char_ci_geq_p, "char-ci>=?", 0, 2, 1,
            (SCM x, SCM y, SCM rest),
            "Return @code{#t} iff the case-folded Unicode code point of @var{x} is\n"
            "greater than or equal to the case-folded code point of @var{y}, else\n"
            "@code{#f}.")
#define FUNC_NAME s_scm_i_char_ci_geq_p
{
  if (SCM_UNBNDP (x) || SCM_UNBNDP (y))
    return SCM_BOOL_T;
  while (!scm_is_null (rest))
    {
      if (scm_is_false (scm_char_ci_geq_p (x, y)))
        return SCM_BOOL_F;
      x = y;
      y = scm_car (rest);
      rest = scm_cdr (rest);
    }
  return scm_char_ci_geq_p (x, y);
}
#undef FUNC_NAME

SCM scm_char_ci_geq_p (SCM x, SCM y)
#define FUNC_NAME s_scm_i_char_ci_geq_p
{
  SCM_VALIDATE_CHAR (1, x);
  SCM_VALIDATE_CHAR (2, y);
  return scm_from_bool (scm_c_upcase(SCM_CHAR(x)) >= scm_c_upcase(SCM_CHAR(y)));
}
#undef FUNC_NAME


SCM_DEFINE (scm_char_alphabetic_p, "char-alphabetic?", 1, 0, 0,
           (SCM chr),
	    "Return @code{#t} iff @var{chr} is alphabetic, else @code{#f}.\n")
#define FUNC_NAME s_scm_char_alphabetic_p
{
  return scm_char_set_contains_p (scm_char_set_letter, chr);
}
#undef FUNC_NAME

SCM_DEFINE (scm_char_numeric_p, "char-numeric?", 1, 0, 0, 
           (SCM chr),
	    "Return @code{#t} iff @var{chr} is numeric, else @code{#f}.\n")
#define FUNC_NAME s_scm_char_numeric_p
{
  return scm_char_set_contains_p (scm_char_set_digit, chr);
}
#undef FUNC_NAME

SCM_DEFINE (scm_char_whitespace_p, "char-whitespace?", 1, 0, 0, 
           (SCM chr),
	    "Return @code{#t} iff @var{chr} is whitespace, else @code{#f}.\n")
#define FUNC_NAME s_scm_char_whitespace_p
{
  return scm_char_set_contains_p (scm_char_set_whitespace, chr);
}
#undef FUNC_NAME


SCM_DEFINE (scm_char_upper_case_p, "char-upper-case?", 1, 0, 0, 
           (SCM chr),
	    "Return @code{#t} iff @var{chr} is uppercase, else @code{#f}.\n")
#define FUNC_NAME s_scm_char_upper_case_p
{
  return scm_char_set_contains_p (scm_char_set_upper_case, chr);
}
#undef FUNC_NAME


SCM_DEFINE (scm_char_lower_case_p, "char-lower-case?", 1, 0, 0, 
           (SCM chr),
	    "Return @code{#t} iff @var{chr} is lowercase, else @code{#f}.\n")
#define FUNC_NAME s_scm_char_lower_case_p
{
  return scm_char_set_contains_p (scm_char_set_lower_case, chr);
}
#undef FUNC_NAME

SCM_DEFINE (scm_char_is_both_p, "char-is-both?", 1, 0, 0, 
            (SCM chr),
	    "Return @code{#t} iff @var{chr} is either uppercase or lowercase, else\n"
            "@code{#f}.\n")
#define FUNC_NAME s_scm_char_is_both_p
{
  if (scm_is_true (scm_char_set_contains_p (scm_char_set_lower_case, chr)))
    return SCM_BOOL_T;
  return scm_char_set_contains_p (scm_char_set_upper_case, chr);
}
#undef FUNC_NAME


SCM_DEFINE (scm_char_to_integer, "char->integer", 1, 0, 0, 
            (SCM chr),
            "Return the Unicode code point of @var{chr}.")
#define FUNC_NAME s_scm_char_to_integer
{
  SCM_VALIDATE_CHAR (1, chr);
  return scm_from_uint32 (SCM_CHAR(chr));
}
#undef FUNC_NAME


SCM_DEFINE (scm_integer_to_char, "integer->char", 1, 0, 0, 
           (SCM n),
            "Return the character that has Unicode code point @var{n}.  The integer\n"
            "@var{n} must be a valid code point.  Valid code points are in the\n"
            "ranges 0 to @code{#xD7FF} inclusive or @code{#xE000} to\n"
            "@code{#x10FFFF} inclusive.")
#define FUNC_NAME s_scm_integer_to_char
{
  scm_t_wchar cn;

  cn = scm_to_wchar (n);

  /* Avoid the surrogates.  */
  if (!SCM_IS_UNICODE_CHAR (cn))
    scm_out_of_range (FUNC_NAME, n);

  return SCM_MAKE_CHAR (cn);
}
#undef FUNC_NAME


SCM_DEFINE (scm_char_upcase, "char-upcase", 1, 0, 0, 
           (SCM chr),
	    "Return the uppercase character version of @var{chr}.")
#define FUNC_NAME s_scm_char_upcase
{
  SCM_VALIDATE_CHAR (1, chr);
  return scm_c_make_char (scm_c_upcase (SCM_CHAR (chr)));
}
#undef FUNC_NAME


SCM_DEFINE (scm_char_downcase, "char-downcase", 1, 0, 0, 
           (SCM chr),
	    "Return the lowercase character version of @var{chr}.")
#define FUNC_NAME s_scm_char_downcase
{
  SCM_VALIDATE_CHAR (1, chr);
  return scm_c_make_char (scm_c_downcase (SCM_CHAR(chr)));
}
#undef FUNC_NAME

SCM_DEFINE (scm_char_titlecase, "char-titlecase", 1, 0, 0,
	   (SCM chr),
	    "Return the titlecase character version of @var{chr}.")
#define FUNC_NAME s_scm_char_titlecase
{
  SCM_VALIDATE_CHAR (1, chr);
  return scm_c_make_char (scm_c_titlecase (SCM_CHAR(chr)));
}
#undef FUNC_NAME

SCM_DEFINE (scm_char_general_category, "char-general-category", 1, 0, 0,
           (SCM chr),
            "Return a symbol representing the Unicode general category of "
            "@var{chr} or @code{#f} if a named category cannot be found.")
#define FUNC_NAME s_scm_char_general_category
{
  const char *sym;
  uc_general_category_t cat;

  SCM_VALIDATE_CHAR (1, chr);
  cat = uc_general_category (SCM_CHAR (chr));
  sym = uc_general_category_name (cat);

  if (sym != NULL)
    return scm_from_utf8_symbol (sym);
  return SCM_BOOL_F;
}
#undef FUNC_NAME





/*
TODO: change name  to scm_i_.. ? --hwn
*/


scm_t_wchar
scm_c_upcase (scm_t_wchar c)
{
  return uc_toupper ((int) c);
}


scm_t_wchar
scm_c_downcase (scm_t_wchar c)
{
  return uc_tolower ((int) c);
}

scm_t_wchar
scm_c_titlecase (scm_t_wchar c)
{
  return uc_totitle ((int) c);
}



/* There are a few sets of character names: R5RS, Guile
   extensions for control characters, and leftover Guile extensions.
   They are listed in order of precedence.  */

static const char *const scm_r5rs_charnames[] = {
  "space", "newline"
};

static const uint32_t scm_r5rs_charnums[] = {
  0x20, 0x0a
};

#define SCM_N_R5RS_CHARNAMES (sizeof (scm_r5rs_charnames) / sizeof (char *))

static const char *const scm_r6rs_charnames[] = {
  "nul", "alarm", "backspace", "tab", "linefeed", "vtab", "page",
  "return", "esc", "delete"
  /* 'space' and 'newline' are already included from the R5RS list.  */
};

static const uint32_t scm_r6rs_charnums[] = {
  0x00, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c,
  0x0d, 0x1b, 0x7f
};

#define SCM_N_R6RS_CHARNAMES (sizeof (scm_r6rs_charnames) / sizeof (char *))

static const char *const scm_r7rs_charnames[] = {
  "escape"
};

static const uint32_t scm_r7rs_charnums[] = {
  0x1b
};

#define SCM_N_R7RS_CHARNAMES (sizeof (scm_r7rs_charnames) / sizeof (char *))

/* The abbreviated names for control characters.  */
static const char *const scm_C0_control_charnames[] = {
  /* C0 controls */
  "nul", "soh", "stx", "etx", "eot", "enq", "ack", "bel",
  "bs",  "ht",  "lf",  "vt",  "ff",  "cr",  "so",  "si",
  "dle", "dc1", "dc2", "dc3", "dc4", "nak", "syn", "etb", 
  "can", "em",  "sub", "esc", "fs",  "gs",  "rs",  "us",
  "sp", "del"
};

static const uint32_t scm_C0_control_charnums[] = {
  0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
  0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
  0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
  0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
  0x20, 0x7f
};

#define SCM_N_C0_CONTROL_CHARNAMES (sizeof (scm_C0_control_charnames) / sizeof (char *))

static const char *const scm_alt_charnames[] = {
  "null", "nl", "np"
};

static const uint32_t scm_alt_charnums[] = {
  0x00, 0x0a, 0x0c
};

#define SCM_N_ALT_CHARNAMES (sizeof (scm_alt_charnames) / sizeof (char *))

/* Returns the string charname for a character if it exists, or NULL
   otherwise.  */
const char *
scm_i_charname (SCM chr)
{
  size_t c;
  uint32_t i = SCM_CHAR (chr);

  for (c = 0; c < SCM_N_R5RS_CHARNAMES; c++)
    if (scm_r5rs_charnums[c] == i)
      return scm_r5rs_charnames[c];

  for (c = 0; c < SCM_N_R6RS_CHARNAMES; c++)
    if (scm_r6rs_charnums[c] == i)
      return scm_r6rs_charnames[c];

  for (c = 0; c < SCM_N_R7RS_CHARNAMES; c++)
    if (scm_r7rs_charnums[c] == i)
      return scm_r7rs_charnames[c];

  for (c = 0; c < SCM_N_C0_CONTROL_CHARNAMES; c++)
    if (scm_C0_control_charnums[c] == i)
      return scm_C0_control_charnames[c];

  /* Since the characters in scm_alt_charnums is a subset of
     scm_C0_control_charnums, this code is never reached.  */
  for (c = 0; c < SCM_N_ALT_CHARNAMES; c++)
    if (scm_alt_charnums[c] == i)
      return scm_alt_charnames[c];

  return NULL;
}

/* Return a character from a string charname.  */
SCM
scm_i_charname_to_char (const char *charname, size_t charname_len)
{
  size_t c;

  /* The R5RS charnames.  These are supposed to be case insensitive. */
  for (c = 0; c < SCM_N_R5RS_CHARNAMES; c++)
    if ((strlen (scm_r5rs_charnames[c]) == charname_len)
	&& (!strncasecmp (scm_r5rs_charnames[c], charname, charname_len)))
      return SCM_MAKE_CHAR (scm_r5rs_charnums[c]);

  /* The R6RS charnames.  R6RS says that these should be case-sensitive.
     They are left as case-insensitive to avoid confusion.  */
  for (c = 0; c < SCM_N_R6RS_CHARNAMES; c++)
    if ((strlen (scm_r6rs_charnames[c]) == charname_len)
	&& (!strncasecmp (scm_r6rs_charnames[c], charname, charname_len)))
      return SCM_MAKE_CHAR (scm_r6rs_charnums[c]);

  /* The R7RS charnames.  R7RS says that these should be case-sensitive.
     They are left as case-insensitive to avoid confusion.  */
  for (c = 0; c < SCM_N_R7RS_CHARNAMES; c++)
    if ((strlen (scm_r7rs_charnames[c]) == charname_len)
	&& (!strncasecmp (scm_r7rs_charnames[c], charname, charname_len)))
      return SCM_MAKE_CHAR (scm_r7rs_charnums[c]);

  /* Then come the controls.  By Guile convention, these are not case
     sensitive.  */
  for (c = 0; c < SCM_N_C0_CONTROL_CHARNAMES; c++)
    if ((strlen (scm_C0_control_charnames[c]) == charname_len)
	&& (!strncasecmp (scm_C0_control_charnames[c], charname, charname_len)))
      return SCM_MAKE_CHAR (scm_C0_control_charnums[c]);

  /* Lastly are some old names carried over for compatibility.  */
  for (c = 0; c < SCM_N_ALT_CHARNAMES; c++)
    if ((strlen (scm_alt_charnames[c]) == charname_len)
	&& (!strncasecmp (scm_alt_charnames[c], charname, charname_len)))
      return SCM_MAKE_CHAR (scm_alt_charnums[c]);

  return SCM_BOOL_F;
}




void
scm_init_chars ()
{
#include "chars.x"
}