summaryrefslogtreecommitdiffstats
path: root/lib/readline/mbutil.c
blob: 17716357feb0c31b686636ccece7a1567426db35 (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
/* mbutil.c -- readline multibyte character utility functions */

/* Copyright (C) 2001-2017 Free Software Foundation, Inc.

   This file is part of the GNU Readline Library (Readline), a library
   for reading lines of text with interactive input and history editing.      

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

   Readline 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 General Public License for more details.

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

#define READLINE_LIBRARY

#if defined (HAVE_CONFIG_H)
#  include <config.h>
#endif

#include <sys/types.h>
#include <fcntl.h>
#include "posixjmp.h"

#if defined (HAVE_UNISTD_H)
#  include <unistd.h>	   /* for _POSIX_VERSION */
#endif /* HAVE_UNISTD_H */

#if defined (HAVE_STDLIB_H)
#  include <stdlib.h>
#else
#  include "ansi_stdlib.h"
#endif /* HAVE_STDLIB_H */

#include <stdio.h>
#include <ctype.h>

/* System-specific feature definitions and include files. */
#include "rldefs.h"
#include "rlmbutil.h"

#if defined (TIOCSTAT_IN_SYS_IOCTL)
#  include <sys/ioctl.h>
#endif /* TIOCSTAT_IN_SYS_IOCTL */

/* Some standard library routines. */
#include "readline.h"

#include "rlprivate.h"
#include "xmalloc.h"

/* Declared here so it can be shared between the readline and history
   libraries. */
#if defined (HANDLE_MULTIBYTE)
int rl_byte_oriented = 0;
#else
int rl_byte_oriented = 1;
#endif

/* Ditto */
int _rl_utf8locale = 0;

/* **************************************************************** */
/*								    */
/*		Multibyte Character Utility Functions		    */
/*								    */
/* **************************************************************** */

#if defined(HANDLE_MULTIBYTE)

/* **************************************************************** */
/*								    */
/*		UTF-8 specific Character Utility Functions	    */
/*								    */
/* **************************************************************** */

/* Return the length in bytes of the possibly-multibyte character beginning
   at S. Encoding is UTF-8. */
static int
_rl_utf8_mblen (const char *s, size_t n)
{
  unsigned char c, c1;

  if (s == 0)
    return (0);	/* no shift states */
  if (n <= 0)
    return (-1);

  c = (unsigned char)*s;
  if (c < 0x80)
    return (c != 0);
  if (c >= 0xc2)
    {
      c1 = (unsigned char)s[1];
      if (c < 0xe0)
	{
	  if (n >= 2 && (s[1] ^ 0x80) < 0x40)
	    return 2;
	}
      else if (c < 0xf0)
	{
	  if (n >= 3
		&& (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
		&& (c >= 0xe1 || c1 >= 0xa0)
		&& (c != 0xed || c1 < 0xa0))
	    return 3;
	}
      else if (c < 0xf8)
	{
	  if (n >= 4
		&& (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
	 	&& (s[3] ^ 0x80) < 0x40
		&& (c >= 0xf1 || c1 >= 0x90)
		&& (c < 0xf4 || (c == 0xf4 && c1 < 0x90)))
	    return 4;
	}
    }
  /* invalid or incomplete multibyte character */
  return -1;
}

static int
_rl_find_next_mbchar_internal (char *string, int seed, int count, int find_non_zero)
{
  size_t tmp, len;
  mbstate_t ps;
  int point;
  wchar_t wc;

  tmp = 0;

  memset(&ps, 0, sizeof (mbstate_t));
  if (seed < 0)
    seed = 0;
  if (count <= 0)
    return seed;

  point = seed + _rl_adjust_point (string, seed, &ps);
  /* if _rl_adjust_point returns -1, the character or string is invalid.
     treat as a byte. */
  if (point == seed - 1)	/* invalid */
    return seed + 1;
    
  /* if this is true, means that seed was not pointing to a byte indicating
     the beginning of a multibyte character.  Correct the point and consume
     one char. */
  if (seed < point)
    count--;

  while (count > 0)  
    {
      len = strlen (string + point);
      if (len == 0)
	break;
      if (_rl_utf8locale && UTF8_SINGLEBYTE(string[point]))
	{
	  tmp = 1;
	  wc = (wchar_t) string[point];
	  memset(&ps, 0, sizeof(mbstate_t));
	}
      else
	tmp = mbrtowc (&wc, string+point, len, &ps);
      if (MB_INVALIDCH ((size_t)tmp))
	{
	  /* invalid bytes. assume a byte represents a character */
	  point++;
	  count--;
	  /* reset states. */
	  memset(&ps, 0, sizeof(mbstate_t));
	}
      else if (MB_NULLWCH (tmp))
	break;			/* found wide '\0' */
      else
	{
	  /* valid bytes */
	  point += tmp;
	  if (find_non_zero)
	    {
	      if (WCWIDTH (wc) == 0)
		continue;
	      else
		count--;
	    }
	  else
	    count--;
	}
    }

  if (find_non_zero)
    {
      tmp = mbrtowc (&wc, string + point, strlen (string + point), &ps);
      while (MB_NULLWCH (tmp) == 0 && MB_INVALIDCH (tmp) == 0 && WCWIDTH (wc) == 0)
	{
	  point += tmp;
	  tmp = mbrtowc (&wc, string + point, strlen (string + point), &ps);
	}
    }

  return point;
}

/*static*/ int
_rl_find_prev_mbchar_internal (char *string, int seed, int find_non_zero)
{
  mbstate_t ps;
  int prev, non_zero_prev, point, length;
  size_t tmp;
  wchar_t wc;

  memset(&ps, 0, sizeof(mbstate_t));
  length = strlen(string);
  
  if (seed < 0)
    return 0;
  else if (length < seed)
    return length;

  prev = non_zero_prev = point = 0;
  while (point < seed)
    {
      if (_rl_utf8locale && UTF8_SINGLEBYTE(string[point]))
	{
	  tmp = 1;
	  wc = (wchar_t) string[point];
	  memset(&ps, 0, sizeof(mbstate_t));
	}
      else
	tmp = mbrtowc (&wc, string + point, length - point, &ps);
      if (MB_INVALIDCH ((size_t)tmp))
	{
	  /* in this case, bytes are invalid or too short to compose
	     multibyte char, so assume that the first byte represents
	     a single character anyway. */
	  tmp = 1;
	  /* clear the state of the byte sequence, because
	     in this case effect of mbstate is undefined  */
	  memset(&ps, 0, sizeof (mbstate_t));

	  /* Since we're assuming that this byte represents a single
	     non-zero-width character, don't forget about it. */
	  prev = point;
	}
      else if (MB_NULLWCH (tmp))
	break;			/* Found '\0' char.  Can this happen? */
      else
	{
	  if (find_non_zero)
	    {
	      if (WCWIDTH (wc) != 0)
		prev = point;
	    }
	  else
	    prev = point;  
	}

      point += tmp;
    }

  return prev;
}

/* return the number of bytes parsed from the multibyte sequence starting
   at src, if a non-L'\0' wide character was recognized. It returns 0, 
   if a L'\0' wide character was recognized. It  returns (size_t)(-1), 
   if an invalid multibyte sequence was encountered. It returns (size_t)(-2) 
   if it couldn't parse a complete  multibyte character.  */
int
_rl_get_char_len (char *src, mbstate_t *ps)
{
  size_t tmp, l;
  int mb_cur_max;

  /* Look at no more than MB_CUR_MAX characters */
  l = (size_t)strlen (src);
  if (_rl_utf8locale && l > 0 && UTF8_SINGLEBYTE(*src))
    tmp = (*src != 0) ? 1 : 0;
  else
    {
      mb_cur_max = MB_CUR_MAX;
      tmp = mbrlen((const char *)src, (l < mb_cur_max) ? l : mb_cur_max, ps);
    }
  if (tmp == (size_t)(-2))
    {
      /* too short to compose multibyte char */
      if (ps)
	memset (ps, 0, sizeof(mbstate_t));
      return -2;
    }
  else if (tmp == (size_t)(-1))
    {
      /* invalid to compose multibyte char */
      /* initialize the conversion state */
      if (ps)
	memset (ps, 0, sizeof(mbstate_t));
      return -1;
    }
  else if (tmp == (size_t)0)
    return 0;
  else
    return (int)tmp;
}

/* compare the specified two characters. If the characters matched,
   return 1. Otherwise return 0. */
int
_rl_compare_chars (char *buf1, int pos1, mbstate_t *ps1, char *buf2, int pos2, mbstate_t *ps2)
{
  int i, w1, w2;

  if ((w1 = _rl_get_char_len (&buf1[pos1], ps1)) <= 0 || 
	(w2 = _rl_get_char_len (&buf2[pos2], ps2)) <= 0 ||
	(w1 != w2) ||
	(buf1[pos1] != buf2[pos2]))
    return 0;

  for (i = 1; i < w1; i++)
    if (buf1[pos1+i] != buf2[pos2+i])
      return 0;

  return 1;
}

/* adjust pointed byte and find mbstate of the point of string.
   adjusted point will be point <= adjusted_point, and returns
   differences of the byte(adjusted_point - point).
   if point is invalid (point < 0 || more than string length),
   it returns -1 */
int
_rl_adjust_point (char *string, int point, mbstate_t *ps)
{
  size_t tmp;
  int length, pos;

  tmp = 0;
  pos = 0;
  length = strlen(string);
  if (point < 0)
    return -1;
  if (length < point)
    return -1;
  
  while (pos < point)
    {
      if (_rl_utf8locale && UTF8_SINGLEBYTE(string[pos]))
	tmp = 1;
      else
	tmp = mbrlen (string + pos, length - pos, ps);
      if (MB_INVALIDCH ((size_t)tmp))
	{
	  /* in this case, bytes are invalid or too short to compose
	     multibyte char, so assume that the first byte represents
	     a single character anyway. */
	  pos++;
	  /* clear the state of the byte sequence, because
	     in this case effect of mbstate is undefined  */
	  if (ps)
	    memset (ps, 0, sizeof (mbstate_t));
	}
      else if (MB_NULLWCH (tmp))
	pos++;
      else
	pos += tmp;
    }

  return (pos - point);
}

int
_rl_is_mbchar_matched (char *string, int seed, int end, char *mbchar, int length)
{
  int i;

  if ((end - seed) < length)
    return 0;

  for (i = 0; i < length; i++)
    if (string[seed + i] != mbchar[i])
      return 0;
  return 1;
}

wchar_t
_rl_char_value (char *buf, int ind)
{
  size_t tmp;
  wchar_t wc;
  mbstate_t ps;
  int l;

  if (MB_LEN_MAX == 1 || rl_byte_oriented)
    return ((wchar_t) buf[ind]);
  if (_rl_utf8locale && UTF8_SINGLEBYTE(buf[ind]))
    return ((wchar_t) buf[ind]);
  l = strlen (buf);
  if (ind >= l - 1)
    return ((wchar_t) buf[ind]);
  if (l < ind)			/* Sanity check */
    l = strlen (buf+ind);
  memset (&ps, 0, sizeof (mbstate_t));
  tmp = mbrtowc (&wc, buf + ind, l - ind, &ps);
  if (MB_INVALIDCH (tmp) || MB_NULLWCH (tmp))  
    return ((wchar_t) buf[ind]);
  return wc;
}
#endif /* HANDLE_MULTIBYTE */

/* Find next `count' characters started byte point of the specified seed.
   If flags is MB_FIND_NONZERO, we look for non-zero-width multibyte
   characters. */
#undef _rl_find_next_mbchar
int
_rl_find_next_mbchar (char *string, int seed, int count, int flags)
{
#if defined (HANDLE_MULTIBYTE)
  return _rl_find_next_mbchar_internal (string, seed, count, flags);
#else
  return (seed + count);
#endif
}

/* Find previous character started byte point of the specified seed.
   Returned point will be point <= seed.  If flags is MB_FIND_NONZERO,
   we look for non-zero-width multibyte characters. */
#undef _rl_find_prev_mbchar
int
_rl_find_prev_mbchar (char *string, int seed, int flags)
{
#if defined (HANDLE_MULTIBYTE)
  return _rl_find_prev_mbchar_internal (string, seed, flags);
#else
  return ((seed == 0) ? seed : seed - 1);
#endif
}