summaryrefslogtreecommitdiffstats
path: root/lib/util/charset/util_unistr.c
blob: 4658d91b0c83496f591f0744244e34a9df9cd713 (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
/* 
   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 "replace.h"
#include "system/locale.h"
#include "charset.h"
#include "lib/util/byteorder.h"
#include "lib/util/fault.h"

/**
 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_handle *ic = get_iconv_handle();
	while (s && *s) {
		size_t size;
		codepoint_t c = next_codepoint_handle(ic, s, &size);
		if (c == oldc) {
			*s = newc;
		}
		s += size;
	}
}

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

	if(src == NULL) {
		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*(strlen(src))+1);
	if (dest == NULL) {
		return NULL;
	}

	while (*src) {
		size_t c_size;
		codepoint_t c = next_codepoint_handle(iconv_handle, src, &c_size);
		src += c_size;

		c = tolower_m(c);

		c_size = push_codepoint_handle(iconv_handle, 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;
}

_PUBLIC_ char *strlower_talloc(TALLOC_CTX *ctx, const char *src)
{
	struct smb_iconv_handle *iconv_handle = get_iconv_handle();
	return strlower_talloc_handle(iconv_handle, ctx, src);
}

/**
 Convert a string to UPPER case, allocated with talloc
 source length limited to n bytes, iconv handle supplied
**/
_PUBLIC_ char *strupper_talloc_n_handle(struct smb_iconv_handle *iconv_handle,
					TALLOC_CTX *ctx, const char *src, size_t n)
{
	size_t size=0;
	char *dest;

	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 (n && *src) {
		size_t c_size;
		codepoint_t c = next_codepoint_handle_ext(iconv_handle, src, n,
							  CH_UNIX, &c_size);
		src += c_size;
		n -= c_size;

		c = toupper_m(c);

		c_size = push_codepoint_handle(iconv_handle, 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)
{
	struct smb_iconv_handle *iconv_handle = get_iconv_handle();
	return strupper_talloc_n_handle(iconv_handle, ctx, src, n);
}
/**
 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);
}

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

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

	return count;
}

size_t ucs2_align(const void *base_ptr, const void *p, int flags)
{
	if (flags & (STR_NOALIGN|STR_ASCII)) {
		return 0;
	}
	return PTR_DIFF(p, base_ptr) & 1;
}

/**
return the number of bytes occupied by a buffer in CH_UTF16 format
the result includes the null termination
**/
size_t utf16_len(const void *buf)
{
	size_t len;

	for (len = 0; SVAL(buf,len); len += 2) ;

	return len + 2;
}

/**
return the number of bytes occupied by a buffer in CH_UTF16 format
the result includes the null termination
limited by 'n' bytes
**/
size_t utf16_len_n(const void *src, size_t n)
{
	size_t len;

	for (len = 0; (len+2 < n) && SVAL(src, len); len += 2) ;

	if (len+2 <= n) {
		len += 2;
	}

	return len;
}

/**
 * Copy a string from a char* unix src to a dos codepage string destination.
 *
 * @converted_size the number of bytes occupied by the string in the destination.
 * @return bool true if success.
 *
 * @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 bool push_ascii_string(void *dest, const char *src, size_t dest_len, int flags, size_t *converted_size)
{
	size_t src_len;
	bool ret;

	if (flags & STR_UPPER) {
		char *tmpbuf = strupper_talloc(NULL, src);
		if (tmpbuf == NULL) {
			return false;
		}
		ret = push_ascii_string(dest, tmpbuf, dest_len, flags & ~STR_UPPER, converted_size);
		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, converted_size);
}

/**
 * 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_string(char *dest, const void *src, size_t dest_len, size_t src_len, int flags)
{
	size_t size = 0;

	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;
		}
	}

	/* We're ignoring the return here.. */
	(void)convert_string(CH_DOS, CH_UNIX, src, src_len, dest, dest_len, &size);

	if (dest_len)
		dest[MIN(size, 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 size = 0;
	bool ret;

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

	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, &size);
	if (ret == false) {
		return 0;
	}

	len += size;

	return (ssize_t)len;
}


/**
 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 size = 0;

	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;

	/* We're ignoring the return here.. */
	(void)convert_string(CH_UTF16, CH_UNIX, src, src_len, dest, dest_len, &size);
	if (dest_len)
		dest[MIN(size, dest_len-1)] = 0;

	return src_len;
}

/**
 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) {
		size_t size = 0;
		if (push_ascii_string(dest, src, dest_len, flags, &size)) {
			return (ssize_t)size;
		} else {
			return (ssize_t)-1;
		}
	} 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_string(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;
	}
}