summaryrefslogtreecommitdiff
path: root/ldb/common/attrib_handlers.c
blob: 5ec86b5b8fbe7f09fd078e7efb62e07149f39cef (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
/* 
   ldb database library

   Copyright (C) Andrew Tridgell  2005

     ** NOTE! The following LGPL license applies to the ldb
     ** library. This does NOT imply that all of Samba is released
     ** under the LGPL
   
   This library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 3 of the License, or (at your option) any later version.

   This library 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
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
/*
  attribute handlers for well known attribute types, selected by syntax OID
  see rfc2252
*/

#include "ldb_includes.h"
#include "system/locale.h"
#include "ldb_handlers.h"

/*
  default handler that just copies a ldb_val.
*/
int ldb_handler_copy(struct ldb_context *ldb, void *mem_ctx,
		     const struct ldb_val *in, struct ldb_val *out)
{
	*out = ldb_val_dup(mem_ctx, in);
	if (in->length > 0 && out->data == NULL) {
		ldb_oom(ldb);
		return -1;
	}
	return 0;
}

/*
  a case folding copy handler, removing leading and trailing spaces and
  multiple internal spaces

  We exploit the fact that utf8 never uses the space octet except for
  the space itself
*/
int ldb_handler_fold(struct ldb_context *ldb, void *mem_ctx,
			    const struct ldb_val *in, struct ldb_val *out)
{
	char *s, *t;
	int l;

	if (!in || !out || !(in->data)) {
		return -1;
	}

	out->data = (uint8_t *)ldb_casefold(ldb, mem_ctx, (const char *)(in->data), in->length);
	if (out->data == NULL) {
		ldb_debug(ldb, LDB_DEBUG_ERROR, "ldb_handler_fold: unable to casefold string [%s]", in->data);
		return -1;
	}

	s = (char *)(out->data);
	
	/* remove trailing spaces if any */
	l = strlen(s);
	while (l > 0 && s[l - 1] == ' ') l--;
	s[l] = '\0';
	
	/* remove leading spaces if any */
	if (*s == ' ') {
		for (t = s; *s == ' '; s++) ;

		/* remove leading spaces by moving down the string */
		memmove(t, s, l);

		s = t;
	}

	/* check middle spaces */
	while ((t = strchr(s, ' ')) != NULL) {
		for (s = t; *s == ' '; s++) ;

		if ((s - t) > 1) {
			l = strlen(s);

			/* remove all spaces but one by moving down the string */
			memmove(t + 1, s, l);
		}
	}

	out->length = strlen((char *)out->data);
	return 0;
}



/*
  canonicalise a ldap Integer
  rfc2252 specifies it should be in decimal form
*/
int ldb_canonicalise_Integer(struct ldb_context *ldb, void *mem_ctx,
				    const struct ldb_val *in, struct ldb_val *out)
{
	char *end;
	long long i = strtoll((char *)in->data, &end, 0);
	if (*end != 0) {
		return -1;
	}
	out->data = (uint8_t *)talloc_asprintf(mem_ctx, "%lld", i);
	if (out->data == NULL) {
		return -1;
	}
	out->length = strlen((char *)out->data);
	return 0;
}

/*
  compare two Integers
*/
int ldb_comparison_Integer(struct ldb_context *ldb, void *mem_ctx,
				  const struct ldb_val *v1, const struct ldb_val *v2)
{
	return strtoll((char *)v1->data, NULL, 0) - strtoll((char *)v2->data, NULL, 0);
}

/*
  compare two binary blobs
*/
int ldb_comparison_binary(struct ldb_context *ldb, void *mem_ctx,
			  const struct ldb_val *v1, const struct ldb_val *v2)
{
	if (v1->length != v2->length) {
		return v1->length - v2->length;
	}
	return memcmp(v1->data, v2->data, v1->length);
}

/*
  compare two case insensitive strings, ignoring multiple whitespaces
  and leading and trailing whitespaces
  see rfc2252 section 8.1
	
  try to optimize for the ascii case,
  but if we find out an utf8 codepoint revert to slower but correct function
*/
int ldb_comparison_fold(struct ldb_context *ldb, void *mem_ctx,
			       const struct ldb_val *v1, const struct ldb_val *v2)
{
	const char *s1=(const char *)v1->data, *s2=(const char *)v2->data;
	size_t n1 = v1->length, n2 = v2->length;
	const char *u1, *u2;
	char *b1, *b2;
	int ret;
	while (*s1 == ' ' && n1) { s1++; n1--; };
	while (*s2 == ' ' && n2) { s2++; n2--; };
	/* TODO: make utf8 safe, possibly with helper function from application */
	while (*s1 && *s2 && n1 && n2) {
		/* the first 127 (0x7F) chars are ascii and utf8 guarantes they
		 * never appear in multibyte sequences */
		if (((unsigned char)s1[0]) & 0x80) goto utf8str;
		if (((unsigned char)s2[0]) & 0x80) goto utf8str;
		if (toupper((unsigned char)*s1) != toupper((unsigned char)*s2))
			break;
		if (*s1 == ' ') {
			while (s1[0] == s1[1] && n1) { s1++; n1--; }
			while (s2[0] == s2[1] && n2) { s2++; n2--; }
		}
		s1++; s2++;
		n1--; n2--;
	}
	if (! (*s1 && *s2)) {
		/* check for trailing spaces only if one of the pointers
		 * has reached the end of the strings otherwise we
		 * can mistakenly match.
		 * ex. "domain users" <-> "domainUpdates"
		 */
		while (*s1 == ' ') { s1++; n1--; }
		while (*s2 == ' ') { s2++; n2--; }
	}
	if (n1 != n2) {
		return n1 - n2;
	}
	return (int)(toupper(*s1)) - (int)(toupper(*s2));

utf8str:
	/* no need to recheck from the start, just from the first utf8 char found */
	b1 = ldb_casefold(ldb, mem_ctx, s1, n1);
	b2 = ldb_casefold(ldb, mem_ctx, s2, n2);

	if (b1 && b2) {
		/* Both strings converted correctly */

		u1 = b1;
		u2 = b2;
	} else {
		/* One of the strings was not UTF8, so we have no options but to do a binary compare */

		u1 = s1;
		u2 = s2;
	}

	while (*u1 & *u2) {
		if (*u1 != *u2)
			break;
		if (*u1 == ' ') {
			while (u1[0] == u1[1]) u1++;
			while (u2[0] == u2[1]) u2++;
		}
		u1++; u2++;
	}
	if (! (*u1 && *u2)) {
		while (*u1 == ' ') u1++;
		while (*u2 == ' ') u2++;
	}
	ret = (int)(*u1 - *u2);

	talloc_free(b1);
	talloc_free(b2);
	
	return ret;
}


/*
  canonicalise a attribute in DN format
*/
int ldb_canonicalise_dn(struct ldb_context *ldb, void *mem_ctx,
			       const struct ldb_val *in, struct ldb_val *out)
{
	struct ldb_dn *dn;
	int ret = -1;

	out->length = 0;
	out->data = NULL;

	dn = ldb_dn_from_ldb_val(ldb, mem_ctx, in);
	if ( ! ldb_dn_validate(dn)) {
		return LDB_ERR_INVALID_DN_SYNTAX;
	}

	out->data = (uint8_t *)ldb_dn_alloc_casefold(mem_ctx, dn);
	if (out->data == NULL) {
		goto done;
	}
	out->length = strlen((char *)out->data);

	ret = 0;

done:
	talloc_free(dn);

	return ret;
}

/*
  compare two dns
*/
int ldb_comparison_dn(struct ldb_context *ldb, void *mem_ctx,
			     const struct ldb_val *v1, const struct ldb_val *v2)
{
	struct ldb_dn *dn1 = NULL, *dn2 = NULL;
	int ret;

	dn1 = ldb_dn_from_ldb_val(ldb, mem_ctx, v1);
	if ( ! ldb_dn_validate(dn1)) return -1;

	dn2 = ldb_dn_from_ldb_val(ldb, mem_ctx, v2);
	if ( ! ldb_dn_validate(dn2)) {
		talloc_free(dn1);
		return -1;
	} 

	ret = ldb_dn_compare(dn1, dn2);

	talloc_free(dn1);
	talloc_free(dn2);
	return ret;
}

/*
  compare two utc time values. 1 second resolution
*/
int ldb_comparison_utctime(struct ldb_context *ldb, void *mem_ctx,
				  const struct ldb_val *v1, const struct ldb_val *v2)
{
	time_t t1, t2;
	t1 = ldb_string_to_time((char *)v1->data);
	t2 = ldb_string_to_time((char *)v2->data);
	return (int)t2 - (int)t1;
}

/*
  canonicalise a utc time
*/
int ldb_canonicalise_utctime(struct ldb_context *ldb, void *mem_ctx,
				    const struct ldb_val *in, struct ldb_val *out)
{
	time_t t = ldb_string_to_time((char *)in->data);
	out->data = (uint8_t *)ldb_timestring(mem_ctx, t);
	if (out->data == NULL) {
		return -1;
	}
	out->length = strlen((char *)out->data);
	return 0;
}

/*
  table of standard attribute handlers
*/
static const struct ldb_schema_syntax ldb_standard_syntaxes[] = {
	{ 
		.name            = LDB_SYNTAX_INTEGER,
		.ldif_read_fn    = ldb_handler_copy,
		.ldif_write_fn   = ldb_handler_copy,
		.canonicalise_fn = ldb_canonicalise_Integer,
		.comparison_fn   = ldb_comparison_Integer
	},
	{ 
		.name            = LDB_SYNTAX_OCTET_STRING,
		.ldif_read_fn    = ldb_handler_copy,
		.ldif_write_fn   = ldb_handler_copy,
		.canonicalise_fn = ldb_handler_copy,
		.comparison_fn   = ldb_comparison_binary
	},
	{ 
		.name            = LDB_SYNTAX_DIRECTORY_STRING,
		.ldif_read_fn    = ldb_handler_copy,
		.ldif_write_fn   = ldb_handler_copy,
		.canonicalise_fn = ldb_handler_fold,
		.comparison_fn   = ldb_comparison_fold
	},
	{ 
		.name            = LDB_SYNTAX_DN,
		.ldif_read_fn    = ldb_handler_copy,
		.ldif_write_fn   = ldb_handler_copy,
		.canonicalise_fn = ldb_canonicalise_dn,
		.comparison_fn   = ldb_comparison_dn
	},
	{ 
		.name            = LDB_SYNTAX_OBJECTCLASS,
		.ldif_read_fn    = ldb_handler_copy,
		.ldif_write_fn   = ldb_handler_copy,
		.canonicalise_fn = ldb_handler_fold,
		.comparison_fn   = ldb_comparison_fold
	},
	{ 
		.name            = LDB_SYNTAX_UTC_TIME,
		.ldif_read_fn    = ldb_handler_copy,
		.ldif_write_fn   = ldb_handler_copy,
		.canonicalise_fn = ldb_canonicalise_utctime,
		.comparison_fn   = ldb_comparison_utctime
	}
};


/*
  return the attribute handlers for a given syntax name
*/
const struct ldb_schema_syntax *ldb_standard_syntax_by_name(struct ldb_context *ldb,
							    const char *syntax)
{
	int i;
	unsigned num_handlers = sizeof(ldb_standard_syntaxes)/sizeof(ldb_standard_syntaxes[0]);
	/* TODO: should be replaced with a binary search */
	for (i=0;i<num_handlers;i++) {
		if (strcmp(ldb_standard_syntaxes[i].name, syntax) == 0) {
			return &ldb_standard_syntaxes[i];
		}
	}
	return NULL;
}