summaryrefslogtreecommitdiff
path: root/lib/util/charset/util_str.c
blob: 30961d068a3eed3fa03cf24f1e6252c54e6381bd (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
/*
   Unix SMB/CIFS implementation.
   Samba utility functions
   Copyright (C) Andrew Tridgell 1992-2001
   Copyright (C) Simo Sorce 2001
   Copyright (C) Andrew Bartlett 2011
   Copyright (C) Jeremy Allison  1992-2007

   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"

#ifdef strcasecmp
#undef strcasecmp
#endif

/**
 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_handle *iconv_handle = get_iconv_handle();

	/* 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_handle(iconv_handle, s1, &size1);
		c2 = next_codepoint_handle(iconv_handle, 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;
}

/**
 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_handle *iconv_handle = get_iconv_handle();

	/* 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_handle(iconv_handle, s1, &size1);
		c2 = next_codepoint_handle(iconv_handle, 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(const char *s1,const char *s2)
{
	if (s1 == s2)
		return true;
	if (!s1 || !s2)
		return false;

	return strcmp(s1,s2) == 0;
}

/**
 * Calculate the number of units (8 or 16-bit, depending on the
 * destination charset), that would be needed to convert the input
 * string which is expected to be in in src_charset encoding to the
 * destination charset (which should be a unicode charset).
 */
_PUBLIC_ size_t strlen_m_ext(const char *s, charset_t src_charset, charset_t dst_charset)
{
	size_t count = 0;
	struct smb_iconv_handle *ic = get_iconv_handle();

	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_handle_ext(ic, s, src_charset, &c_size);
		s += c_size;

		switch (dst_charset) {
		case CH_UTF16LE:
		case CH_UTF16BE:
		case CH_UTF16MUNGED:
			if (c < 0x10000) {
				/* Unicode char fits into 16 bits. */
				count += 1;
			} else {
				/* Double-width unicode char - 32 bits. */
				count += 2;
			}
			break;
		case CH_UTF8:
			/*
			 * this only checks ranges, and does not
			 * check for invalid codepoints
			 */
			if (c < 0x80) {
				count += 1;
			} else if (c < 0x800) {
				count += 2;
			} else if (c < 0x1000) {
				count += 3;
			} else {
				count += 4;
			}
			break;
		default:
			/*
			 * non-unicode encoding:
			 * assume that each codepoint fits into
			 * one unit in the destination encoding.
			 */
			count += 1;
		}
	}

	return count;
}

_PUBLIC_ size_t strlen_m_ext_term(const char *s, const charset_t src_charset,
				  const charset_t dst_charset)
{
	if (!s) {
		return 0;
	}
	return strlen_m_ext(s, src_charset, dst_charset) + 1;
}

/**
 * Calculate the number of 16-bit units that would be needed to convert
 * the input string which is expected to be in CH_UNIX encoding to UTF16.
 *
 * 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)
{
	return strlen_m_ext(s, CH_UNIX, CH_UTF16LE);
}

/**
   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 *src, char c)
{
	const char *s;
	struct smb_iconv_handle *ic = get_iconv_handle();
	if (src == 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(src, c);
	}

	/* 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) */

	for (s = src; *s && !(((unsigned char)s[0]) & 0x80); s++) {
		if (*s == c)
			return (char *)s;
	}

	if (!*s)
		return NULL;

#ifdef BROKEN_UNICODE_COMPOSE_CHARACTERS
	/* With compose characters we must restart from the beginning. JRA. */
	s = src;
#endif

	while (*s) {
		size_t size;
		codepoint_t c2 = next_codepoint_handle(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_handle *ic = get_iconv_handle();
	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);
	}

	/* 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). Also, in Samba
	   we only search for ascii characters in 'c' and that
	   in all mb character sets with a compound character
	   containing c, if 'c' is not a match at position
	   p, then p[-1] > 0x7f. JRA. */

	{
		size_t len = strlen(s);
		const char *cp = s;
		bool got_mb = false;

		if (len == 0)
			return NULL;
		cp += (len - 1);
		do {
			if (c == *cp) {
				/* Could be a match. Part of a multibyte ? */
				if ((cp > s) &&
					(((unsigned char)cp[-1]) & 0x80)) {
					/* Yep - go slow :-( */
					got_mb = true;
					break;
				}
				/* No - we have a match ! */
				return (char *)cp;
			}
		} while (cp-- != s);
		if (!got_mb)
			return NULL;
	}

	while (*s) {
		size_t size;
		codepoint_t c2 = next_codepoint_handle(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_handle *ic = get_iconv_handle();
	while (*string) {
		size_t c_size;
		codepoint_t s;
		codepoint_t t;

		s = next_codepoint_handle(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_handle *ic = get_iconv_handle();
	while (*string) {
		size_t c_size;
		codepoint_t s;
		codepoint_t t;

		s = next_codepoint_handle(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;
}