summaryrefslogtreecommitdiff
path: root/lib/util/charset/util_unistr.c
blob: 024dc70acc2748a22b5825b9616f8e46a0d4af5e (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
/* 
   Unix SMB/CIFS implementation.
   Samba utility functions
   Copyright (C) Andrew Tridgell 1992-2001
   Copyright (C) Simo Sorce 2001
   
   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"
#include "system/locale.h"

struct smb_iconv_convenience *global_iconv_convenience = NULL;

static inline struct smb_iconv_convenience *get_iconv_convenience(void)
{
	if (global_iconv_convenience == NULL)
		global_iconv_convenience = smb_iconv_convenience_init(talloc_autofree_context(), "ASCII", "UTF-8", true);
	return global_iconv_convenience;
}

/**
 Case insensitive string compararison
**/
_PUBLIC_ int strcasecmp_m(const char *s1, const char *s2)
{
	codepoint_t c1=0, c2=0;
	size_t size1, size2;
	struct smb_iconv_convenience *iconv_convenience = get_iconv_convenience();

	/* handle null ptr comparisons to simplify the use in qsort */
	if (s1 == s2) return 0;
	if (s1 == NULL) return -1;
	if (s2 == NULL) return 1;

	while (*s1 && *s2) {
		c1 = next_codepoint_convenience(iconv_convenience, s1, &size1);
		c2 = next_codepoint_convenience(iconv_convenience, s2, &size2);

		s1 += size1;
		s2 += size2;

		if (c1 == c2) {
			continue;
		}

		if (c1 == INVALID_CODEPOINT ||
		    c2 == INVALID_CODEPOINT) {
			/* what else can we do?? */
			return strcasecmp(s1, s2);
		}

		if (toupper_m(c1) != toupper_m(c2)) {
			return c1 - c2;
		}
	}

	return *s1 - *s2;
}

/**
 * Get the next token from a string, return False if none found.
 * Handles double-quotes.
 * 
 * Based on a routine by GJC@VILLAGE.COM. 
 * Extensively modified by Andrew.Tridgell@anu.edu.au
 **/
_PUBLIC_ bool next_token(const char **ptr,char *buff, const char *sep, size_t bufsize)
{
	const char *s;
	bool quoted;
	size_t len=1;

	if (!ptr)
		return false;

	s = *ptr;

	/* default to simple separators */
	if (!sep)
		sep = " \t\n\r";

	/* find the first non sep char */
	while (*s && strchr_m(sep,*s))
		s++;
	
	/* nothing left? */
	if (!*s)
		return false;
	
	/* copy over the token */
	for (quoted = false; len < bufsize && *s && (quoted || !strchr_m(sep,*s)); s++) {
		if (*s == '\"') {
			quoted = !quoted;
		} else {
			len++;
			*buff++ = *s;
		}
	}
	
	*ptr = (*s) ? s+1 : s;  
	*buff = 0;
	
	return true;
}

/**
 Case insensitive string compararison, length limited
**/
_PUBLIC_ int strncasecmp_m(const char *s1, const char *s2, size_t n)
{
	codepoint_t c1=0, c2=0;
	size_t size1, size2;
	struct smb_iconv_convenience *iconv_convenience = get_iconv_convenience();

	/* handle null ptr comparisons to simplify the use in qsort */
	if (s1 == s2) return 0;
	if (s1 == NULL) return -1;
	if (s2 == NULL) return 1;

	while (*s1 && *s2 && n) {
		n--;

		c1 = next_codepoint_convenience(iconv_convenience, s1, &size1);
		c2 = next_codepoint_convenience(iconv_convenience, s2, &size2);

		s1 += size1;
		s2 += size2;

		if (c1 == c2) {
			continue;
		}

		if (c1 == INVALID_CODEPOINT ||
		    c2 == INVALID_CODEPOINT) {
			/* what else can we do?? */
			return strcasecmp(s1, s2);
		}

		if (toupper_m(c1) != toupper_m(c2)) {
			return c1 - c2;
		}
	}

	if (n == 0) {
		return 0;
	}

	return *s1 - *s2;
}

/**
 * Compare 2 strings.
 *
 * @note The comparison is case-insensitive.
 **/
_PUBLIC_ bool strequal_m(const char *s1, const char *s2)
{
	return strcasecmp_m(s1,s2) == 0;
}

/**
 Compare 2 strings (case sensitive).
**/
_PUBLIC_ bool strcsequal_m(const char *s1,const char *s2)
{
	if (s1 == s2)
		return true;
	if (!s1 || !s2)
		return false;
	
	return strcmp(s1,s2) == 0;
}


/**
 String replace.
 NOTE: oldc and newc must be 7 bit characters
**/
_PUBLIC_ void string_replace_m(char *s, char oldc, char newc)
{
	struct smb_iconv_convenience *ic = get_iconv_convenience();
	while (s && *s) {
		size_t size;
		codepoint_t c = next_codepoint_convenience(ic, s, &size);
		if (c == oldc) {
			*s = newc;
		}
		s += size;
	}
}

/**
 Paranoid strcpy into a buffer of given length (includes terminating
 zero. Strips out all but 'a-Z0-9' and the character in other_safe_chars
 and replaces with '_'. Deliberately does *NOT* check for multibyte
 characters. Don't change it !
**/

_PUBLIC_ char *alpha_strcpy(char *dest, const char *src, const char *other_safe_chars, size_t maxlength)
{
	size_t len, i;

	if (maxlength == 0) {
		/* can't fit any bytes at all! */
		return NULL;
	}

	if (!dest) {
		DEBUG(0,("ERROR: NULL dest in alpha_strcpy\n"));
		return NULL;
	}

	if (!src) {
		*dest = 0;
		return dest;
	}  

	len = strlen(src);
	if (len >= maxlength)
		len = maxlength - 1;

	if (!other_safe_chars)
		other_safe_chars = "";

	for(i = 0; i < len; i++) {
		int val = (src[i] & 0xff);
		if (isupper(val) || islower(val) || isdigit(val) || strchr_m(other_safe_chars, val))
			dest[i] = src[i];
		else
			dest[i] = '_';
	}

	dest[i] = '\0';

	return dest;
}

/**
 Count the number of UCS2 characters in a string. Normally this will
 be the same as the number of bytes in a string for single byte strings,
 but will be different for multibyte.
**/
_PUBLIC_ size_t strlen_m(const char *s)
{
	size_t count = 0;
	struct smb_iconv_convenience *ic = get_iconv_convenience();

	if (!s) {
		return 0;
	}

	while (*s && !(((uint8_t)*s) & 0x80)) {
		s++;
		count++;
	}

	if (!*s) {
		return count;
	}

	while (*s) {
		size_t c_size;
		codepoint_t c = next_codepoint_convenience(ic, s, &c_size);
		if (c < 0x10000) {
			count += 1;
		} else {
			count += 2;
		}
		s += c_size;
	}

	return count;
}

/**
   Work out the number of multibyte chars in a string, including the NULL
   terminator.
**/
_PUBLIC_ size_t strlen_m_term(const char *s)
{
	if (!s) {
		return 0;
	}

	return strlen_m(s) + 1;
}

/*
 * Weird helper routine for the winreg pipe: If nothing is around, return 0,
 * if a string is there, include the terminator.
 */

_PUBLIC_ size_t strlen_m_term_null(const char *s)
{
	size_t len;
	if (!s) {
		return 0;
	}
	len = strlen_m(s);
	if (len == 0) {
		return 0;
	}

	return len+1;
}

/**
 Strchr and strrchr_m are a bit complex on general multi-byte strings. 
**/
_PUBLIC_ char *strchr_m(const char *s, char c)
{
	struct smb_iconv_convenience *ic = get_iconv_convenience();
	if (s == NULL) {
		return NULL;
	}
	/* characters below 0x3F are guaranteed to not appear in
	   non-initial position in multi-byte charsets */
	if ((c & 0xC0) == 0) {
		return strchr(s, c);
	}

	while (*s) {
		size_t size;
		codepoint_t c2 = next_codepoint_convenience(ic, s, &size);
		if (c2 == c) {
			return discard_const_p(char, s);
		}
		s += size;
	}

	return NULL;
}

/**
 * Multibyte-character version of strrchr
 */
_PUBLIC_ char *strrchr_m(const char *s, char c)
{
	struct smb_iconv_convenience *ic = get_iconv_convenience();
	char *ret = NULL;

	if (s == NULL) {
		return NULL;
	}

	/* characters below 0x3F are guaranteed to not appear in
	   non-initial position in multi-byte charsets */
	if ((c & 0xC0) == 0) {
		return strrchr(s, c);
	}

	while (*s) {
		size_t size;
		codepoint_t c2 = next_codepoint_convenience(ic, s, &size);
		if (c2 == c) {
			ret = discard_const_p(char, s);
		}
		s += size;
	}

	return ret;
}

/**
  return True if any (multi-byte) character is lower case
*/
_PUBLIC_ bool strhaslower(const char *string)
{
	struct smb_iconv_convenience *ic = get_iconv_convenience();
	while (*string) {
		size_t c_size;
		codepoint_t s;
		codepoint_t t;

		s = next_codepoint_convenience(ic, string, &c_size);
		string += c_size;

		t = toupper_m(s);

		if (s != t) {
			return true; /* that means it has lower case chars */
		}
	}

	return false;
} 

/**
  return True if any (multi-byte) character is upper case
*/
_PUBLIC_ bool strhasupper(const char *string)
{
	struct smb_iconv_convenience *ic = get_iconv_convenience();
	while (*string) {
		size_t c_size;
		codepoint_t s;
		codepoint_t t;

		s = next_codepoint_convenience(ic, string, &c_size);
		string += c_size;

		t = tolower_m(s);

		if (s != t) {
			return true; /* that means it has upper case chars */
		}
	}

	return false;
} 

/**
 Convert a string to lower case, allocated with talloc
**/
_PUBLIC_ char *strlower_talloc(TALLOC_CTX *ctx, const char *src)
{
	size_t size=0;
	char *dest;
	struct smb_iconv_convenience *iconv_convenience = get_iconv_convenience();

	/* this takes advantage of the fact that upper/lower can't
	   change the length of a character by more than 1 byte */
	dest = talloc_array(ctx, char, 2*(strlen(src))+1);
	if (dest == NULL) {
		return NULL;
	}

	while (*src) {
		size_t c_size;
		codepoint_t c = next_codepoint_convenience(iconv_convenience, src, &c_size);
		src += c_size;

		c = tolower_m(c);

		c_size = push_codepoint_convenience(iconv_convenience, dest+size, c);
		if (c_size == -1) {
			talloc_free(dest);
			return NULL;
		}
		size += c_size;
	}

	dest[size] = 0;

	/* trim it so talloc_append_string() works */
	dest = talloc_realloc(ctx, dest, char, size+1);

	talloc_set_name_const(dest, dest);

	return dest;
}

/**
 Convert a string to UPPER case, allocated with talloc
 source length limited to n bytes
**/
_PUBLIC_ char *strupper_talloc_n(TALLOC_CTX *ctx, const char *src, size_t n)
{
	size_t size=0;
	char *dest;
	struct smb_iconv_convenience *iconv_convenience = get_iconv_convenience();
	
	if (!src) {
		return NULL;
	}

	/* this takes advantage of the fact that upper/lower can't
	   change the length of a character by more than 1 byte */
	dest = talloc_array(ctx, char, 2*(n+1));
	if (dest == NULL) {
		return NULL;
	}

	while (*src && n--) {
		size_t c_size;
		codepoint_t c = next_codepoint_convenience(iconv_convenience, src, &c_size);
		src += c_size;

		c = toupper_m(c);

		c_size = push_codepoint_convenience(iconv_convenience, dest+size, c);
		if (c_size == -1) {
			talloc_free(dest);
			return NULL;
		}
		size += c_size;
	}

	dest[size] = 0;

	/* trim it so talloc_append_string() works */
	dest = talloc_realloc(ctx, dest, char, size+1);

	talloc_set_name_const(dest, dest);

	return dest;
}

/**
 Convert a string to UPPER case, allocated with talloc
**/
_PUBLIC_ char *strupper_talloc(TALLOC_CTX *ctx, const char *src)
{
	return strupper_talloc_n(ctx, src, src?strlen(src):0);
}

/**
 talloc_strdup() a unix string to upper case.
**/
_PUBLIC_ char *talloc_strdup_upper(TALLOC_CTX *ctx, const char *src)
{
	return strupper_talloc(ctx, src);
}

/**
 Convert a string to lower case.
**/
_PUBLIC_ void strlower_m(char *s)
{
	char *d;
	struct smb_iconv_convenience *iconv_convenience;

	/* this is quite a common operation, so we want it to be
	   fast. We optimise for the ascii case, knowing that all our
	   supported multi-byte character sets are ascii-compatible
	   (ie. they match for the first 128 chars) */
	while (*s && !(((uint8_t)*s) & 0x80)) {
		*s = tolower((uint8_t)*s);
		s++;
	}

	if (!*s)
		return;

	iconv_convenience = get_iconv_convenience();

	d = s;

	while (*s) {
		size_t c_size, c_size2;
		codepoint_t c = next_codepoint_convenience(iconv_convenience, s, &c_size);
		c_size2 = push_codepoint_convenience(iconv_convenience, d, tolower_m(c));
		if (c_size2 > c_size) {
			DEBUG(0,("FATAL: codepoint 0x%x (0x%x) expanded from %d to %d bytes in strlower_m\n",
				 c, tolower_m(c), (int)c_size, (int)c_size2));
			smb_panic("codepoint expansion in strlower_m\n");
		}
		s += c_size;
		d += c_size2;
	}
	*d = 0;
}

/**
 Convert a string to UPPER case.
**/
_PUBLIC_ void strupper_m(char *s)
{
	char *d;
	struct smb_iconv_convenience *iconv_convenience;

	/* this is quite a common operation, so we want it to be
	   fast. We optimise for the ascii case, knowing that all our
	   supported multi-byte character sets are ascii-compatible
	   (ie. they match for the first 128 chars) */
	while (*s && !(((uint8_t)*s) & 0x80)) {
		*s = toupper((uint8_t)*s);
		s++;
	}

	if (!*s)
		return;

	iconv_convenience = get_iconv_convenience();

	d = s;

	while (*s) {
		size_t c_size, c_size2;
		codepoint_t c = next_codepoint_convenience(iconv_convenience, s, &c_size);
		c_size2 = push_codepoint_convenience(iconv_convenience, d, toupper_m(c));
		if (c_size2 > c_size) {
			DEBUG(0,("FATAL: codepoint 0x%x (0x%x) expanded from %d to %d bytes in strupper_m\n",
				 c, toupper_m(c), (int)c_size, (int)c_size2));
			smb_panic("codepoint expansion in strupper_m\n");
		}
		s += c_size;
		d += c_size2;
	}
	*d = 0;
}


/**
 Find the number of 'c' chars in a string
**/
_PUBLIC_ size_t count_chars_m(const char *s, char c)
{
	struct smb_iconv_convenience *ic = get_iconv_convenience();
	size_t count = 0;

	while (*s) {
		size_t size;
		codepoint_t c2 = next_codepoint_convenience(ic, s, &size);
		if (c2 == c) count++;
		s += size;
	}

	return count;
}


/**
 * Copy a string from a char* unix src to a dos codepage string destination.
 *
 * @return the number of bytes occupied by the string in the destination.
 *
 * @param flags can include
 * <dl>
 * <dt>STR_TERMINATE</dt> <dd>means include the null termination</dd>
 * <dt>STR_UPPER</dt> <dd>means uppercase in the destination</dd>
 * </dl>
 *
 * @param dest_len the maximum length in bytes allowed in the
 * destination.  If @p dest_len is -1 then no maximum is used.
 **/
static ssize_t push_ascii(void *dest, const char *src, size_t dest_len, int flags)
{
	size_t src_len;
	ssize_t ret;

	if (flags & STR_UPPER) {
		char *tmpbuf = strupper_talloc(NULL, src);
		if (tmpbuf == NULL) {
			return -1;
		}
		ret = push_ascii(dest, tmpbuf, dest_len, flags & ~STR_UPPER);
		talloc_free(tmpbuf);
		return ret;
	}

	src_len = strlen(src);

	if (flags & (STR_TERMINATE | STR_TERMINATE_ASCII))
		src_len++;

	return convert_string(CH_UNIX, CH_DOS, src, src_len, dest, dest_len, false);
}

/**
 * Copy a string from a unix char* src to an ASCII destination,
 * allocating a buffer using talloc().
 *
 * @param dest always set at least to NULL 
 *
 * @returns The number of bytes occupied by the string in the destination
 *         or -1 in case of error.
 **/
_PUBLIC_ bool push_ascii_talloc(TALLOC_CTX *ctx, char **dest, const char *src, size_t *converted_size)
{
	size_t src_len = strlen(src)+1;
	*dest = NULL;
	return convert_string_talloc(ctx, CH_UNIX, CH_DOS, src, src_len, (void **)dest, converted_size, false);
}


/**
 * Copy a string from a dos codepage source to a unix char* destination.
 *
 * The resulting string in "dest" is always null terminated.
 *
 * @param flags can have:
 * <dl>
 * <dt>STR_TERMINATE</dt>
 * <dd>STR_TERMINATE means the string in @p src
 * is null terminated, and src_len is ignored.</dd>
 * </dl>
 *
 * @param src_len is the length of the source area in bytes.
 * @returns the number of bytes occupied by the string in @p src.
 **/
static ssize_t pull_ascii(char *dest, const void *src, size_t dest_len, size_t src_len, int flags)
{
	size_t ret;

	if (flags & (STR_TERMINATE | STR_TERMINATE_ASCII)) {
		if (src_len == (size_t)-1) {
			src_len = strlen((const char *)src) + 1;
		} else {
			size_t len = strnlen((const char *)src, src_len);
			if (len < src_len)
				len++;
			src_len = len;
		}
	}

	ret = convert_string(CH_DOS, CH_UNIX, src, src_len, dest, dest_len, false);

	if (dest_len)
		dest[MIN(ret, dest_len-1)] = 0;

	return src_len;
}

/**
 * Copy a string from a char* src to a unicode destination.
 *
 * @returns the number of bytes occupied by the string in the destination.
 *
 * @param flags can have:
 *
 * <dl>
 * <dt>STR_TERMINATE <dd>means include the null termination.
 * <dt>STR_UPPER     <dd>means uppercase in the destination.
 * <dt>STR_NOALIGN   <dd>means don't do alignment.
 * </dl>
 *
 * @param dest_len is the maximum length allowed in the
 * destination. If dest_len is -1 then no maxiumum is used.
 **/
static ssize_t push_ucs2(void *dest, const char *src, size_t dest_len, int flags)
{
	size_t len=0;
	size_t src_len = strlen(src);
	size_t ret;

	if (flags & STR_UPPER) {
		char *tmpbuf = strupper_talloc(NULL, src);
		if (tmpbuf == NULL) {
			return -1;
		}
		ret = push_ucs2(dest, tmpbuf, dest_len, flags & ~STR_UPPER);
		talloc_free(tmpbuf);
		return ret;
	}

	if (flags & STR_TERMINATE)
		src_len++;

	if (ucs2_align(NULL, dest, flags)) {
		*(char *)dest = 0;
		dest = (void *)((char *)dest + 1);
		if (dest_len) dest_len--;
		len++;
	}

	/* ucs2 is always a multiple of 2 bytes */
	dest_len &= ~1;

	ret = convert_string(CH_UNIX, CH_UTF16, src, src_len, dest, dest_len, false);
	if (ret == (size_t)-1) {
		return 0;
	}

	len += ret;

	return len;
}


/**
 * Copy a string from a unix char* src to a UCS2 destination,
 * allocating a buffer using talloc().
 *
 * @param dest always set at least to NULL 
 *
 * @returns The number of bytes occupied by the string in the destination
 *         or -1 in case of error.
 **/
_PUBLIC_ bool push_ucs2_talloc(TALLOC_CTX *ctx, smb_ucs2_t **dest, const char *src, size_t *converted_size)
{
	size_t src_len = strlen(src)+1;
	*dest = NULL;
	return convert_string_talloc(ctx, CH_UNIX, CH_UTF16, src, src_len, (void **)dest, converted_size, false);
}


/**
 * Copy a string from a unix char* src to a UTF-8 destination, allocating a buffer using talloc
 *
 * @param dest always set at least to NULL 
 *
 * @returns The number of bytes occupied by the string in the destination
 **/

_PUBLIC_ bool push_utf8_talloc(TALLOC_CTX *ctx, char **dest, const char *src, size_t *converted_size)
{
	size_t src_len = strlen(src)+1;
	*dest = NULL;
	return convert_string_talloc(ctx, CH_UNIX, CH_UTF8, src, src_len, (void **)dest, converted_size, false);
}

/**
 Copy a string from a ucs2 source to a unix char* destination.
 Flags can have:
  STR_TERMINATE means the string in src is null terminated.
  STR_NOALIGN   means don't try to align.
 if STR_TERMINATE is set then src_len is ignored if it is -1.
 src_len is the length of the source area in bytes
 Return the number of bytes occupied by the string in src.
 The resulting string in "dest" is always null terminated.
**/

static size_t pull_ucs2(char *dest, const void *src, size_t dest_len, size_t src_len, int flags)
{
	size_t ret;

	if (ucs2_align(NULL, src, flags)) {
		src = (const void *)((const char *)src + 1);
		if (src_len > 0)
			src_len--;
	}

	if (flags & STR_TERMINATE) {
		if (src_len == (size_t)-1) {
			src_len = utf16_len(src);
		} else {
			src_len = utf16_len_n(src, src_len);
		}
	}

	/* ucs2 is always a multiple of 2 bytes */
	if (src_len != (size_t)-1)
		src_len &= ~1;
	
	ret = convert_string(CH_UTF16, CH_UNIX, src, src_len, dest, dest_len, false);
	if (dest_len)
		dest[MIN(ret, dest_len-1)] = 0;

	return src_len;
}

/**
 * Copy a string from a ASCII src to a unix char * destination, allocating a buffer using talloc
 *
 * @param dest always set at least to NULL 
 *
 * @returns The number of bytes occupied by the string in the destination
 **/

_PUBLIC_ bool pull_ascii_talloc(TALLOC_CTX *ctx, char **dest, const char *src, size_t *converted_size)
{
	size_t src_len = strlen(src)+1;
	*dest = NULL;
	return convert_string_talloc(ctx, CH_DOS, CH_UNIX, src, src_len, (void **)dest, converted_size, false);
}

/**
 * Copy a string from a UCS2 src to a unix char * destination, allocating a buffer using talloc
 *
 * @param dest always set at least to NULL 
 *
 * @returns The number of bytes occupied by the string in the destination
 **/

_PUBLIC_ bool pull_ucs2_talloc(TALLOC_CTX *ctx, char **dest, const smb_ucs2_t *src, size_t *converted_size)
{
	size_t src_len = utf16_len(src);
	*dest = NULL;
	return convert_string_talloc(ctx, CH_UTF16, CH_UNIX, src, src_len, (void **)dest, converted_size, false);
}

/**
 * Copy a string from a UTF-8 src to a unix char * destination, allocating a buffer using talloc
 *
 * @param dest always set at least to NULL 
 *
 * @returns The number of bytes occupied by the string in the destination
 **/

_PUBLIC_ bool pull_utf8_talloc(TALLOC_CTX *ctx, char **dest, const char *src, size_t *converted_size)
{
	size_t src_len = strlen(src)+1;
	*dest = NULL;
	return convert_string_talloc(ctx, CH_UTF8, CH_UNIX, src, src_len, (void **)dest, converted_size, false);
}

/**
 Copy a string from a char* src to a unicode or ascii
 dos codepage destination choosing unicode or ascii based on the 
 flags in the SMB buffer starting at base_ptr.
 Return the number of bytes occupied by the string in the destination.
 flags can have:
  STR_TERMINATE means include the null termination.
  STR_UPPER     means uppercase in the destination.
  STR_ASCII     use ascii even with unicode packet.
  STR_NOALIGN   means don't do alignment.
 dest_len is the maximum length allowed in the destination. If dest_len
 is -1 then no maxiumum is used.
**/

_PUBLIC_ ssize_t push_string(void *dest, const char *src, size_t dest_len, int flags)
{
	if (flags & STR_ASCII) {
		return push_ascii(dest, src, dest_len, flags);
	} else if (flags & STR_UNICODE) {
		return push_ucs2(dest, src, dest_len, flags);
	} else {
		smb_panic("push_string requires either STR_ASCII or STR_UNICODE flag to be set");
		return -1;
	}
}


/**
 Copy a string from a unicode or ascii source (depending on
 the packet flags) to a char* destination.
 Flags can have:
  STR_TERMINATE means the string in src is null terminated.
  STR_UNICODE   means to force as unicode.
  STR_ASCII     use ascii even with unicode packet.
  STR_NOALIGN   means don't do alignment.
 if STR_TERMINATE is set then src_len is ignored is it is -1
 src_len is the length of the source area in bytes.
 Return the number of bytes occupied by the string in src.
 The resulting string in "dest" is always null terminated.
**/

_PUBLIC_ ssize_t pull_string(char *dest, const void *src, size_t dest_len, size_t src_len, int flags)
{
	if (flags & STR_ASCII) {
		return pull_ascii(dest, src, dest_len, src_len, flags);
	} else if (flags & STR_UNICODE) {
		return pull_ucs2(dest, src, dest_len, src_len, flags);
	} else {
		smb_panic("pull_string requires either STR_ASCII or STR_UNICODE flag to be set");
		return -1;
	}
}


/**
 * Convert string from one encoding to another, making error checking etc
 *
 * @param src pointer to source string (multibyte or singlebyte)
 * @param srclen length of the source string in bytes
 * @param dest pointer to destination string (multibyte or singlebyte)
 * @param destlen maximal length allowed for string
 * @returns the number of bytes occupied in the destination
 **/
_PUBLIC_ size_t convert_string(charset_t from, charset_t to,
				void const *src, size_t srclen, 
				void *dest, size_t destlen, 
				bool allow_badcharcnv)
{
	size_t ret;
	if (!convert_string_convenience(get_iconv_convenience(), from, to, 
									  src, srclen,
									  dest, destlen, &ret,
									  allow_badcharcnv))
		return -1;
	return ret;
}

/**
 * Convert between character sets, allocating a new buffer using talloc for the result.
 *
 * @param srclen length of source buffer.
 * @param dest always set at least to NULL
 * @param converted_size Size in bytes of the converted string
 * @note -1 is not accepted for srclen.
 *
 * @returns boolean indication whether the conversion succeeded
 **/

_PUBLIC_ bool convert_string_talloc(TALLOC_CTX *ctx, 
				       charset_t from, charset_t to, 
				       void const *src, size_t srclen, 
				       void *dest, size_t *converted_size, 
					   bool allow_badcharcnv)
{
	return convert_string_talloc_convenience(ctx, get_iconv_convenience(),
											 from, to, src, srclen, dest,
											 converted_size, 
											 allow_badcharcnv);
}


_PUBLIC_ codepoint_t next_codepoint(const char *str, size_t *size)
{
	return next_codepoint_convenience(get_iconv_convenience(), str, size);
}

_PUBLIC_ ssize_t push_codepoint(char *str, codepoint_t c)
{
	return push_codepoint_convenience(get_iconv_convenience(), str, c);
}