summaryrefslogtreecommitdiff
path: root/source3/lib/util_unistr.c
blob: 7beb65c863afc7476ab2b665293a2a38c8f1f89a (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
/* 
   Unix SMB/CIFS implementation.
   Samba utility functions
   Copyright (C) Andrew Tridgell 1992-2001
   Copyright (C) Simo Sorce 2001
   Copyright (C) Jeremy Allison 2005
   
   This program 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.
   
   This program 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 this program.  If not, see <http://www.gnu.org/licenses/>.
*/

#include "includes.h"

#ifndef MAXUNI
#define MAXUNI 1024
#endif

/* these 3 tables define the unicode case handling.  They are loaded
   at startup either via mmap() or read() from the lib directory */
static uint8 *valid_table;
static bool initialized;

/* Copy into a smb_ucs2_t from a possibly unaligned buffer. Return the copied smb_ucs2_t */
#define COPY_UCS2_CHAR(dest,src) (((unsigned char *)(dest))[0] = ((unsigned char *)(src))[0],\
				((unsigned char *)(dest))[1] = ((unsigned char *)(src))[1], (dest))


/* return an ascii version of a ucs2 character */
#define UCS2_TO_CHAR(c) (((c) >> UCS2_SHIFT) & 0xff)


/**
 * Destroy global objects allocated by load_case_tables()
 **/
void gfree_case_tables(void)
{
	if ( valid_table ) {
		unmap_file(valid_table, 0x10000);
		valid_table = NULL;
	}
	initialized = false;
}

/**
 * Load the valid character map table from <tt>valid.dat</tt> or
 * create from the configured codepage.
 *
 * This function is called whenever the configuration is reloaded.
 * However, the valid character table is not changed if it's loaded
 * from a file, because we can't unmap files.
 **/

static void init_valid_table(void)
{
	if (valid_table) {
		return;
	}

	valid_table = (uint8 *)map_file(data_path("valid.dat"), 0x10000);
	if (!valid_table) {
		smb_panic("Could not load valid.dat file required for mangle method=hash");
		return;
	}
}

/*******************************************************************
 Write a string in (little-endian) unicode format. src is in
 the current DOS codepage. len is the length in bytes of the
 string pointed to by dst.

 if null_terminate is True then null terminate the packet (adds 2 bytes)

 the return value is the length in bytes consumed by the string, including the
 null termination if applied
********************************************************************/

size_t dos_PutUniCode(char *dst,const char *src, size_t len, bool null_terminate)
{
	int flags = null_terminate ? STR_UNICODE|STR_NOALIGN|STR_TERMINATE
				   : STR_UNICODE|STR_NOALIGN;
	return push_ucs2(NULL, dst, src, len, flags);
}


/*******************************************************************
 Skip past a unicode string, but not more than len. Always move
 past a terminating zero if found.
********************************************************************/

char *skip_unibuf(char *src, size_t len)
{
	char *srcend = src + len;

	while (src < srcend && SVAL(src,0)) {
		src += 2;
	}

	if(!SVAL(src,0)) {
		src += 2;
	}

	return src;
}

/* Converts a string from internal samba format to unicode
 */

int rpcstr_push(void *dest, const char *src, size_t dest_len, int flags)
{
	return push_ucs2(NULL, dest, src, dest_len, flags|STR_UNICODE|STR_NOALIGN);
}

/* Converts a string from internal samba format to unicode. Always terminates.
 * Actually just a wrapper round push_ucs2_talloc().
 */

int rpcstr_push_talloc(TALLOC_CTX *ctx, smb_ucs2_t **dest, const char *src)
{
	size_t size;
	if (push_ucs2_talloc(ctx, dest, src, &size))
		return size;
	else
		return -1;
}

/*******************************************************************
 Determine if a character is valid in a 8.3 name.
********************************************************************/

bool isvalid83_w(smb_ucs2_t c)
{
	init_valid_table();
	return valid_table[SVAL(&c,0)] != 0;
}

/*******************************************************************
 Count the number of characters in a smb_ucs2_t string.
********************************************************************/

size_t strlen_w(const smb_ucs2_t *src)
{
	size_t len;
	smb_ucs2_t c;

	for(len = 0; *(COPY_UCS2_CHAR(&c,src)); src++, len++) {
		;
	}

	return len;
}

/*******************************************************************
 Count up to max number of characters in a smb_ucs2_t string.
********************************************************************/

size_t strnlen_w(const smb_ucs2_t *src, size_t max)
{
	size_t len;
	smb_ucs2_t c;

	for(len = 0; (len < max) && *(COPY_UCS2_CHAR(&c,src)); src++, len++) {
		;
	}

	return len;
}

/*******************************************************************
 Wide strchr().
********************************************************************/

smb_ucs2_t *strchr_w(const smb_ucs2_t *s, smb_ucs2_t c)
{
	smb_ucs2_t cp;
	while (*(COPY_UCS2_CHAR(&cp,s))) {
		if (c == cp) {
			return (smb_ucs2_t *)s;
		}
		s++;
	}
	if (c == cp) {
		return (smb_ucs2_t *)s;
	}

	return NULL;
}

smb_ucs2_t *strchr_wa(const smb_ucs2_t *s, char c)
{
	return strchr_w(s, UCS2_CHAR(c));
}

/*******************************************************************
 Wide strrchr().
********************************************************************/

smb_ucs2_t *strrchr_w(const smb_ucs2_t *s, smb_ucs2_t c)
{
	smb_ucs2_t cp;
	const smb_ucs2_t *p = s;
	int len = strlen_w(s);

	if (len == 0) {
		return NULL;
	}
	p += (len - 1);
	do {
		if (c == *(COPY_UCS2_CHAR(&cp,p))) {
			return (smb_ucs2_t *)p;
		}
	} while (p-- != s);
	return NULL;
}

/*******************************************************************
 Wide version of strrchr that returns after doing strrchr 'n' times.
********************************************************************/

smb_ucs2_t *strnrchr_w(const smb_ucs2_t *s, smb_ucs2_t c, unsigned int n)
{
	smb_ucs2_t cp;
	const smb_ucs2_t *p = s;
	int len = strlen_w(s);

	if (len == 0 || !n) {
		return NULL;
	}
	p += (len - 1);
	do {
		if (c == *(COPY_UCS2_CHAR(&cp,p))) {
			n--;
		}

		if (!n) {
			return (smb_ucs2_t *)p;
		}
	} while (p-- != s);
	return NULL;
}

/*******************************************************************
 Wide strstr().
********************************************************************/

smb_ucs2_t *strstr_w(const smb_ucs2_t *s, const smb_ucs2_t *ins)
{
	smb_ucs2_t *r;
	size_t inslen;

	if (!s || !*s || !ins || !*ins) {
		return NULL;
	}

	inslen = strlen_w(ins);
	r = (smb_ucs2_t *)s;

	while ((r = strchr_w(r, *ins))) {
		if (strncmp_w(r, ins, inslen) == 0) {
			return r;
		}
		r++;
	}

	return NULL;
}

/*******************************************************************
 Convert a string to lower case.
 return True if any char is converted

 This is unsafe for any string involving a UTF16 character
********************************************************************/

bool strlower_w(smb_ucs2_t *s)
{
	smb_ucs2_t cp;
	bool ret = False;

	while (*(COPY_UCS2_CHAR(&cp,s))) {
		smb_ucs2_t v = tolower_m(cp);
		if (v != cp) {
			COPY_UCS2_CHAR(s,&v);
			ret = True;
		}
		s++;
	}
	return ret;
}

/*******************************************************************
 Convert a string to upper case.
 return True if any char is converted

 This is unsafe for any string involving a UTF16 character
********************************************************************/

bool strupper_w(smb_ucs2_t *s)
{
	smb_ucs2_t cp;
	bool ret = False;
	while (*(COPY_UCS2_CHAR(&cp,s))) {
		smb_ucs2_t v = toupper_m(cp);
		if (v != cp) {
			COPY_UCS2_CHAR(s,&v);
			ret = True;
		}
		s++;
	}
	return ret;
}

/*******************************************************************
 Convert a string to "normal" form.
********************************************************************/

void strnorm_w(smb_ucs2_t *s, int case_default)
{
	if (case_default == CASE_UPPER) {
		strupper_w(s);
	} else {
		strlower_w(s);
	}
}

int strcmp_w(const smb_ucs2_t *a, const smb_ucs2_t *b)
{
	smb_ucs2_t cpa, cpb;

	while ((*(COPY_UCS2_CHAR(&cpb,b))) && (*(COPY_UCS2_CHAR(&cpa,a)) == cpb)) {
		a++;
		b++;
	}
	return (*(COPY_UCS2_CHAR(&cpa,a)) - *(COPY_UCS2_CHAR(&cpb,b)));
	/* warning: if *a != *b and both are not 0 we return a random
		greater or lesser than 0 number not realted to which
		string is longer */
}

int strncmp_w(const smb_ucs2_t *a, const smb_ucs2_t *b, size_t len)
{
	smb_ucs2_t cpa, cpb;
	size_t n = 0;

	while ((n < len) && (*(COPY_UCS2_CHAR(&cpb,b))) && (*(COPY_UCS2_CHAR(&cpa,a)) == cpb)) {
		a++;
		b++;
		n++;
	}
	return (len - n)?(*(COPY_UCS2_CHAR(&cpa,a)) - *(COPY_UCS2_CHAR(&cpb,b))):0;
}

/*******************************************************************
 Case insensitive string comparison.
********************************************************************/

int strcasecmp_w(const smb_ucs2_t *a, const smb_ucs2_t *b)
{
	smb_ucs2_t cpa, cpb;

	while ((*COPY_UCS2_CHAR(&cpb,b)) && toupper_m(*(COPY_UCS2_CHAR(&cpa,a))) == toupper_m(cpb)) {
		a++;
		b++;
	}
	return (tolower_m(*(COPY_UCS2_CHAR(&cpa,a))) - tolower_m(*(COPY_UCS2_CHAR(&cpb,b))));
}

/*******************************************************************
 Case insensitive string comparison, length limited.
********************************************************************/

int strncasecmp_w(const smb_ucs2_t *a, const smb_ucs2_t *b, size_t len)
{
	smb_ucs2_t cpa, cpb;
	size_t n = 0;

	while ((n < len) && *COPY_UCS2_CHAR(&cpb,b) && (toupper_m(*(COPY_UCS2_CHAR(&cpa,a))) == toupper_m(cpb))) {
		a++;
		b++;
		n++;
	}
	return (len - n)?(tolower_m(*(COPY_UCS2_CHAR(&cpa,a))) - tolower_m(*(COPY_UCS2_CHAR(&cpb,b)))):0;
}

/*******************************************************************
 Compare 2 strings.
********************************************************************/

bool strequal_w(const smb_ucs2_t *s1, const smb_ucs2_t *s2)
{
	if (s1 == s2) {
		return(True);
	}
	if (!s1 || !s2) {
		return(False);
	}
  
	return(strcasecmp_w(s1,s2)==0);
}

/*******************************************************************
 Compare 2 strings up to and including the nth char.
******************************************************************/

bool strnequal_w(const smb_ucs2_t *s1,const smb_ucs2_t *s2,size_t n)
{
	if (s1 == s2) {
		return(True);
	}
	if (!s1 || !s2 || !n) {
		return(False);
	}
  
	return(strncasecmp_w(s1,s2,n)==0);
}

/*******************************************************************
 Duplicate string.
********************************************************************/

smb_ucs2_t *strdup_w(const smb_ucs2_t *src)
{
	return strndup_w(src, 0);
}

/* if len == 0 then duplicate the whole string */

smb_ucs2_t *strndup_w(const smb_ucs2_t *src, size_t len)
{
	smb_ucs2_t *dest;
	
	if (!len) {
		len = strlen_w(src);
	}
	dest = SMB_MALLOC_ARRAY(smb_ucs2_t, len + 1);
	if (!dest) {
		DEBUG(0,("strdup_w: out of memory!\n"));
		return NULL;
	}

	memcpy(dest, src, len * sizeof(smb_ucs2_t));
	dest[len] = 0;
	return dest;
}

/*******************************************************************
 Copy a string with max len.
********************************************************************/

smb_ucs2_t *strncpy_w(smb_ucs2_t *dest, const smb_ucs2_t *src, const size_t max)
{
	smb_ucs2_t cp;
	size_t len;
	
	if (!dest || !src) {
		return NULL;
	}
	
	for (len = 0; (*COPY_UCS2_CHAR(&cp,(src+len))) && (len < max); len++) {
		cp = *COPY_UCS2_CHAR(dest+len,src+len);
	}
	cp = 0;
	for ( /*nothing*/ ; len < max; len++ ) {
		cp = *COPY_UCS2_CHAR(dest+len,&cp);
	}
	
	return dest;
}

/*******************************************************************
 Append a string of len bytes and add a terminator.
********************************************************************/

smb_ucs2_t *strncat_w(smb_ucs2_t *dest, const smb_ucs2_t *src, const size_t max)
{	
	size_t start;
	size_t len;	
	smb_ucs2_t z = 0;

	if (!dest || !src) {
		return NULL;
	}
	
	start = strlen_w(dest);
	len = strnlen_w(src, max);

	memcpy(&dest[start], src, len*sizeof(smb_ucs2_t));			
	z = *COPY_UCS2_CHAR(dest+start+len,&z);

	return dest;
}

smb_ucs2_t *strcat_w(smb_ucs2_t *dest, const smb_ucs2_t *src)
{	
	size_t start;
	size_t len;	
	smb_ucs2_t z = 0;
	
	if (!dest || !src) {
		return NULL;
	}
	
	start = strlen_w(dest);
	len = strlen_w(src);

	memcpy(&dest[start], src, len*sizeof(smb_ucs2_t));			
	z = *COPY_UCS2_CHAR(dest+start+len,&z);
	
	return dest;
}


/*******************************************************************
 Replace any occurence of oldc with newc in unicode string.
********************************************************************/

void string_replace_w(smb_ucs2_t *s, smb_ucs2_t oldc, smb_ucs2_t newc)
{
	smb_ucs2_t cp;

	for(;*(COPY_UCS2_CHAR(&cp,s));s++) {
		if(cp==oldc) {
			COPY_UCS2_CHAR(s,&newc);
		}
	}
}

/*******************************************************************
 Trim unicode string.
********************************************************************/

bool trim_string_w(smb_ucs2_t *s, const smb_ucs2_t *front,
				  const smb_ucs2_t *back)
{
	bool ret = False;
	size_t len, front_len, back_len;

	if (!s) {
		return False;
	}

	len = strlen_w(s);

	if (front && *front) {
		front_len = strlen_w(front);
		while (len && strncmp_w(s, front, front_len) == 0) {
			memmove(s, (s + front_len), (len - front_len + 1) * sizeof(smb_ucs2_t));
			len -= front_len;
			ret = True;
		}
	}
	
	if (back && *back) {
		back_len = strlen_w(back);
		while (len && strncmp_w((s + (len - back_len)), back, back_len) == 0) {
			s[len - back_len] = 0;
			len -= back_len;
			ret = True;
		}
	}

	return ret;
}

/*
  The *_wa() functions take a combination of 7 bit ascii
  and wide characters They are used so that you can use string
  functions combining C string constants with ucs2 strings

  The char* arguments must NOT be multibyte - to be completely sure
  of this only pass string constants */

int strcmp_wa(const smb_ucs2_t *a, const char *b)
{
	smb_ucs2_t cp = 0;

	while (*b && *(COPY_UCS2_CHAR(&cp,a)) == UCS2_CHAR(*b)) {
		a++;
		b++;
	}
	return (*(COPY_UCS2_CHAR(&cp,a)) - UCS2_CHAR(*b));
}

int strncmp_wa(const smb_ucs2_t *a, const char *b, size_t len)
{
	smb_ucs2_t cp = 0;
	size_t n = 0;

	while ((n < len) && *b && *(COPY_UCS2_CHAR(&cp,a)) == UCS2_CHAR(*b)) {
		a++;
		b++;
		n++;
	}
	return (len - n)?(*(COPY_UCS2_CHAR(&cp,a)) - UCS2_CHAR(*b)):0;
}

smb_ucs2_t *strpbrk_wa(const smb_ucs2_t *s, const char *p)
{
	smb_ucs2_t cp;

	while (*(COPY_UCS2_CHAR(&cp,s))) {
		int i;
		for (i=0; p[i] && cp != UCS2_CHAR(p[i]); i++) 
			;
		if (p[i]) {
			return (smb_ucs2_t *)s;
		}
		s++;
	}
	return NULL;
}

smb_ucs2_t *strstr_wa(const smb_ucs2_t *s, const char *ins)
{
	smb_ucs2_t *r;
	size_t inslen;

	if (!s || !ins) { 
		return NULL;
	}

	inslen = strlen(ins);
	r = (smb_ucs2_t *)s;

	while ((r = strchr_w(r, UCS2_CHAR(*ins)))) {
		if (strncmp_wa(r, ins, inslen) == 0) 
			return r;
		r++;
	}

	return NULL;
}

/*************************************************************
 ascii only toupper - saves the need for smbd to be in C locale.
*************************************************************/

int toupper_ascii(int c)
{
	smb_ucs2_t uc = toupper_m(UCS2_CHAR(c));
	return UCS2_TO_CHAR(uc);
}

/*************************************************************
 ascii only tolower - saves the need for smbd to be in C locale.
*************************************************************/

int tolower_ascii(int c)
{
	smb_ucs2_t uc = tolower_m(UCS2_CHAR(c));
	return UCS2_TO_CHAR(uc);
}

/*************************************************************
 ascii only isupper - saves the need for smbd to be in C locale.
*************************************************************/

int isupper_ascii(int c)
{
	return isupper_m(UCS2_CHAR(c));
}

/*************************************************************
 ascii only islower - saves the need for smbd to be in C locale.
*************************************************************/

int islower_ascii(int c)
{
	return islower_m(UCS2_CHAR(c));
}