schema_init.c 101 KB
Newer Older
1
2
3
/* schema_init.c - init builtin schema */
/* $OpenLDAP$ */
/*
Kurt Zeilenga's avatar
Kurt Zeilenga committed
4
 * Copyright 1998-2000 The OpenLDAP Foundation, All Rights Reserved.
5
6
7
8
9
10
11
12
13
14
15
16
17
 * COPYING RESTRICTIONS APPLY, see COPYRIGHT file
 */

#include "portable.h"

#include <stdio.h>

#include <ac/ctype.h>
#include <ac/string.h>
#include <ac/socket.h>

#include "slap.h"
#include "ldap_pvt.h"
18

19
20
#define UTF8MATCH 1

21
22
#ifdef USE_MD5
#include "lutil_md5.h"
23
24
25
26
27
28
/* We should replace MD5 with a faster hash */
#define HASH_BYTES				LUTIL_MD5_BYTES
#define HASH_CONTEXT			lutil_MD5_CTX
#define HASH_Init(c)			lutil_MD5Init(c)
#define HASH_Update(c,buf,len)	lutil_MD5Update(c,buf,len)
#define HASH_Final(d,c)			lutil_MD5Final(d,c)
29
30
31
32
33
34
35
36
37
#else
#include "lutil_hash.h"
/* We should replace MD5 with a faster hash */
#define HASH_BYTES				LUTIL_HASH_BYTES
#define HASH_CONTEXT			lutil_HASH_CTX
#define HASH_Init(c)			lutil_HASHInit(c)
#define HASH_Update(c,buf,len)	lutil_HASHUpdate(c,buf,len)
#define HASH_Final(d,c)			lutil_HASHFinal(d,c)
#endif
38

39
/* recycled validatation routines */
40
#define berValidate						blobValidate
41

42
/* recycled normalization routines */
43
44
45
#define faxNumberNormalize				numericStringNormalize
#define phoneNumberNormalize			numericStringNormalize
#define telexNumberNormalize			numericStringNormalize
46
47
48
49

/* unimplemented pretters */
#define dnPretty						NULL
#define integerPretty					NULL
50
51

/* recycled matching routines */
52
#define bitStringMatch					octetStringMatch
53
#define integerMatch					caseIgnoreIA5Match
54
55
56
#define numericStringMatch				caseIgnoreMatch
#define objectIdentifierMatch			numericStringMatch
#define telephoneNumberMatch			numericStringMatch
57
#define telephoneNumberSubstringsMatch	caseIgnoreIA5SubstringsMatch
58
59
#define generalizedTimeMatch			numericStringMatch
#define generalizedTimeOrderingMatch	numericStringMatch
60
#define uniqueMemberMatch				dnMatch
61

62
63
/* approx matching rules */
#define directoryStringApproxMatchOID	"1.3.6.1.4.1.4203.666.4.4"
64
65
66
#define directoryStringApproxMatch  	approxMatch
#define directoryStringApproxIndexer 	approxIndexer
#define directoryStringApproxFilter  	approxFilter
67
#define IA5StringApproxMatchOID			"1.3.6.1.4.1.4203.666.4.5"
68
69
70
#define IA5StringApproxMatch  			approxMatch
#define IA5StringApproxIndexer			approxIndexer
#define IA5StringApproxFilter  			approxFilter
71

72
73
74
75
/* orderring matching rules */
#define caseIgnoreOrderingMatch			caseIgnoreMatch
#define caseExactOrderingMatch			caseExactMatch

76
/* unimplemented matching routines */
77
78
79
80
81
82
83
84
#define caseIgnoreListMatch				NULL
#define caseIgnoreListSubstringsMatch	NULL
#define presentationAddressMatch		NULL
#define protocolInformationMatch		NULL
#define integerFirstComponentMatch		NULL

#define OpenLDAPaciMatch				NULL
#define authPasswordMatch				NULL
85
86

/* recycled indexing/filtering routines */
87
88
#define dnIndexer						caseIgnoreIndexer
#define dnFilter						caseIgnoreFilter
89
90
#define integerIndexer					caseIgnoreIA5Indexer
#define integerFilter					caseIgnoreIA5Filter
91

92
93
94
95
static char *strcasechr( const char *str, int c )
{
	char *lower = strchr( str, TOLOWER(c) );
	char *upper = strchr( str, TOUPPER(c) );
96

97
98
99
100
101
102
103
104
	if( lower && upper ) {
		return lower < upper ? lower : upper;
	} else if ( lower ) {
		return lower;
	} else {
		return upper;
	}
}
105

106
107
108
static int
octetStringMatch(
	int *matchp,
109
	slap_mask_t flags,
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *value,
	void *assertedValue )
{
	int match = value->bv_len - ((struct berval *) assertedValue)->bv_len;

	if( match == 0 ) {
		match = memcmp( value->bv_val,
			((struct berval *) assertedValue)->bv_val,
			value->bv_len );
	}

	*matchp = match;
	return LDAP_SUCCESS;
}

/* Index generation function */
int octetStringIndexer(
129
130
	slap_mask_t use,
	slap_mask_t flags,
131
132
133
134
135
136
137
138
139
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *prefix,
	struct berval **values,
	struct berval ***keysp )
{
	int i;
	size_t slen, mlen;
	struct berval **keys;
140
141
	HASH_CONTEXT   HASHcontext;
	unsigned char   HASHdigest[HASH_BYTES];
142
	struct berval digest;
143
144
	digest.bv_val = HASHdigest;
	digest.bv_len = sizeof(HASHdigest);
145

146
147
148
	/* we should have at least one value at this point */
	assert( values != NULL && values[0] != NULL );

149
150
151
152
153
154
155
156
157
158
	for( i=0; values[i] != NULL; i++ ) {
		/* just count them */
	}

	keys = ch_malloc( sizeof( struct berval * ) * (i+1) );

	slen = strlen( syntax->ssyn_oid );
	mlen = strlen( mr->smr_oid );

	for( i=0; values[i] != NULL; i++ ) {
159
		HASH_Init( &HASHcontext );
160
		if( prefix != NULL && prefix->bv_len > 0 ) {
161
			HASH_Update( &HASHcontext,
162
163
				prefix->bv_val, prefix->bv_len );
		}
164
		HASH_Update( &HASHcontext,
165
			syntax->ssyn_oid, slen );
166
		HASH_Update( &HASHcontext,
167
			mr->smr_oid, mlen );
168
		HASH_Update( &HASHcontext,
169
			values[i]->bv_val, values[i]->bv_len );
170
		HASH_Final( HASHdigest, &HASHcontext );
171
172
173
174
175
176
177
178
179
180
181
182
183

		keys[i] = ber_bvdup( &digest );
	}

	keys[i] = NULL;

	*keysp = keys;

	return LDAP_SUCCESS;
}

/* Index generation function */
int octetStringFilter(
184
185
	slap_mask_t use,
	slap_mask_t flags,
186
187
188
189
190
191
192
193
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *prefix,
	void * assertValue,
	struct berval ***keysp )
{
	size_t slen, mlen;
	struct berval **keys;
194
195
	HASH_CONTEXT   HASHcontext;
	unsigned char   HASHdigest[HASH_BYTES];
196
197
	struct berval *value = (struct berval *) assertValue;
	struct berval digest;
198
199
	digest.bv_val = HASHdigest;
	digest.bv_len = sizeof(HASHdigest);
200
201
202
203
204
205

	slen = strlen( syntax->ssyn_oid );
	mlen = strlen( mr->smr_oid );

	keys = ch_malloc( sizeof( struct berval * ) * 2 );

206
	HASH_Init( &HASHcontext );
207
	if( prefix != NULL && prefix->bv_len > 0 ) {
208
		HASH_Update( &HASHcontext,
209
210
			prefix->bv_val, prefix->bv_len );
	}
211
	HASH_Update( &HASHcontext,
212
		syntax->ssyn_oid, slen );
213
	HASH_Update( &HASHcontext,
214
		mr->smr_oid, mlen );
215
	HASH_Update( &HASHcontext,
216
		value->bv_val, value->bv_len );
217
	HASH_Final( HASHdigest, &HASHcontext );
218
219
220
221
222
223
224
225

	keys[0] = ber_bvdup( &digest );
	keys[1] = NULL;

	*keysp = keys;

	return LDAP_SUCCESS;
}
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
static int
dnValidate(
	Syntax *syntax,
	struct berval *in )
{
	int rc;
	char *dn;

	if( in->bv_len == 0 ) return LDAP_SUCCESS;

	dn = ch_strdup( in->bv_val );

	rc = dn_validate( dn ) == NULL
		? LDAP_INVALID_SYNTAX : LDAP_SUCCESS;

	ch_free( dn );
	return rc;
}

static int
dnNormalize(
	Syntax *syntax,
	struct berval *val,
	struct berval **normalized )
{
	struct berval *out = ber_bvdup( val );

	if( out->bv_len != 0 ) {
		char *dn;
#ifdef USE_DN_NORMALIZE
		dn = dn_normalize( out->bv_val );
#else
		dn = dn_validate( out->bv_val );
#endif

		if( dn == NULL ) {
			ber_bvfree( out );
			return LDAP_INVALID_SYNTAX;
		}

		out->bv_val = dn;
		out->bv_len = strlen( dn );
	}

	*normalized = out;
	return LDAP_SUCCESS;
}

static int
dnMatch(
277
	int *matchp,
278
	slap_mask_t flags,
279
280
281
282
283
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *value,
	void *assertedValue )
{
284
	int match;
285
286
	struct berval *asserted = (struct berval *) assertedValue;
	
287
288
289
	match = value->bv_len - asserted->bv_len;

	if( match == 0 ) {
290
#ifdef USE_DN_NORMALIZE
291
		match = strcmp( value->bv_val, asserted->bv_val );
292
#else
293
		match = strcasecmp( value->bv_val, asserted->bv_val );
294
#endif
295
296
297
298
299
300
301
	}

	Debug( LDAP_DEBUG_ARGS, "dnMatch %d\n\t\"%s\"\n\t\"%s\"\n",
	    match, value->bv_val, asserted->bv_val );

	*matchp = match;
	return LDAP_SUCCESS;
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
static int
nameUIDValidate(
	Syntax *syntax,
	struct berval *in )
{
	int rc;
	struct berval *dn;

	if( in->bv_len == 0 ) return LDAP_SUCCESS;

	dn = ber_bvdup( in );

	if( dn->bv_val[dn->bv_len-1] == '\'' ) {
		/* assume presence of optional UID */
		ber_len_t i;

		for(i=dn->bv_len-2; i>2; i--) {
			if( dn->bv_val[i] != '0' &&	dn->bv_val[i] != '1' ) {
				break;
			}
		}
		if( dn->bv_val[i] != '\'' ) {
			return LDAP_INVALID_SYNTAX;
		}
		if( dn->bv_val[i-1] != 'B' ) {
			return LDAP_INVALID_SYNTAX;
		}
		if( dn->bv_val[i-2] != '#' ) {
			return LDAP_INVALID_SYNTAX;
		}

		/* trim the UID to allow use of dn_validate */
		dn->bv_val[i-2] = '\0';
	}

	rc = dn_validate( dn->bv_val ) == NULL
		? LDAP_INVALID_SYNTAX : LDAP_SUCCESS;

	ber_bvfree( dn );
	return rc;
}

static int
nameUIDNormalize(
	Syntax *syntax,
	struct berval *val,
	struct berval **normalized )
{
	struct berval *out = ber_bvdup( val );

	if( out->bv_len != 0 ) {
		char *dn;
		ber_len_t dnlen;
		char *uid = NULL;
		ber_len_t uidlen = 0;

		if( out->bv_val[out->bv_len-1] == '\'' ) {
			/* assume presence of optional UID */
			uid = strrchr( out->bv_val, '#' );

			if( uid == NULL ) {
				ber_bvfree( out );
				return LDAP_INVALID_SYNTAX;
			}

			uidlen = out->bv_len - (out->bv_val - uid);
			/* temporarily trim the UID */
			*uid = '\0';
		}

#ifdef USE_DN_NORMALIZE
		dn = dn_normalize( out->bv_val );
#else
		dn = dn_validate( out->bv_val );
#endif

		if( dn == NULL ) {
			ber_bvfree( out );
			return LDAP_INVALID_SYNTAX;
		}

		dnlen = strlen(dn);

		if( uidlen ) {
			/* restore the separator */
			*uid = '#';
			/* shift the UID */
			SAFEMEMCPY( &dn[dnlen], uid, uidlen );
		}

		out->bv_val = dn;
		out->bv_len = dnlen + uidlen;
	}

	*normalized = out;
	return LDAP_SUCCESS;
}

402
403
404
405
406
407
408
409
410
static int
inValidate(
	Syntax *syntax,
	struct berval *in )
{
	/* any value allowed */
	return LDAP_OTHER;
}

411
static int
412
blobValidate(
413
414
415
416
	Syntax *syntax,
	struct berval *in )
{
	/* any value allowed */
417
	return LDAP_SUCCESS;
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
static int
bitStringValidate(
	Syntax *syntax,
	struct berval *in )
{
	ber_len_t i;

	/* very unforgiving validation, requires no normalization
	 * before simplistic matching
	 */
	if( in->bv_len < 3 ) {
		return LDAP_INVALID_SYNTAX;
	}
	if( in->bv_val[0] != 'B' ||
		in->bv_val[1] != '\'' ||
		in->bv_val[in->bv_len-1] != '\'' )
	{
		return LDAP_INVALID_SYNTAX;
	}

	for( i=in->bv_len-2; i>1; i-- ) {
		if( in->bv_val[i] != '0' && in->bv_val[i] != '1' ) {
			return LDAP_INVALID_SYNTAX;
		}
	}

	return LDAP_SUCCESS;
}

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
/*
 * Handling boolean syntax and matching is quite rigid.
 * A more flexible approach would be to allow a variety
 * of strings to be normalized and prettied into TRUE
 * and FALSE.
 */
static int
booleanValidate(
	Syntax *syntax,
	struct berval *in )
{
	/* very unforgiving validation, requires no normalization
	 * before simplistic matching
	 */

	if( in->bv_len == 4 ) {
		if( !memcmp( in->bv_val, "TRUE", 4 ) ) {
			return LDAP_SUCCESS;
		}
	} else if( in->bv_len == 5 ) {
		if( !memcmp( in->bv_val, "FALSE", 5 ) ) {
			return LDAP_SUCCESS;
		}
	}

	return LDAP_INVALID_SYNTAX;
}

static int
booleanMatch(
	int *matchp,
480
	slap_mask_t flags,
481
482
483
484
485
486
487
488
489
490
491
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *value,
	void *assertedValue )
{
	/* simplistic matching allowed by rigid validation */
	struct berval *asserted = (struct berval *) assertedValue;
	*matchp = value->bv_len != asserted->bv_len;
	return LDAP_SUCCESS;
}

492
#if UTF8MATCH
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
static int
UTF8casecmp(
	struct berval *right,
	struct berval *left )
{
	ber_len_t r, l;
	int rlen, llen;
	ldap_unicode_t ru, lu;
	ldap_unicode_t ruu, luu;

	for( r=0, l=0;
		r < right->bv_len && l < left->bv_len;
		r+=rlen, l+=llen )
	{
		/*
		 * XXYYZ: we convert to ucs4 even though -llunicode
		 * expects ucs2 in an unsigned long
		 */
		ru = ldap_utf8_to_ucs4( &right->bv_val[r] );
		if( ru == LDAP_UCS4_INVALID ) {
			return 1;
		}

		lu = ldap_utf8_to_ucs4( &left->bv_val[l] );
		if( lu == LDAP_UCS4_INVALID ) {
			return -1;
		}

		ruu = uctoupper( ru );
		luu = uctoupper( lu );

		if( ruu > luu ) {
			return 1;
		} else if( luu > ruu ) {
			return -1;
		}

		rlen = LDAP_UTF8_CHARLEN( &right->bv_val[r] );
		llen = LDAP_UTF8_CHARLEN( &left->bv_val[l] );
	}

	if( r < right->bv_len ) {
		/* less left */
		return -1;
	}

	if( l < left->bv_len ) {
		/* less right */
		return 1;
	}

	return 0;
}
Kurt Zeilenga's avatar
Kurt Zeilenga committed
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

/* case insensitive UTF8 strncmp with offset for second string */
static int
UTF8oncasecmp(
	struct berval *right,
	struct berval *left,
	ber_len_t len,
	ber_len_t offset )
{
	ber_len_t r, l;
	int rlen, llen;
	int rslen, lslen;
	ldap_unicode_t ru, lu;
	ldap_unicode_t ruu, luu;

	rslen = len < right->bv_len ? len : right->bv_len;
	lslen = len + offset < left->bv_len ? len : left->bv_len;

	for( r = 0, l = offset;
		r < rslen && l < lslen;
		r+=rlen, l+=llen )
	{
		/*
		 * XXYYZ: we convert to ucs4 even though -llunicode
		 * expects ucs2 in an unsigned long
		 */
		ru = ldap_utf8_to_ucs4( &right->bv_val[r] );
		if( ru == LDAP_UCS4_INVALID ) {
			return 1;
		}

		lu = ldap_utf8_to_ucs4( &left->bv_val[l] );
		if( lu == LDAP_UCS4_INVALID ) {
			return -1;
		}

		ruu = uctoupper( ru );
		luu = uctoupper( lu );

		if( ruu > luu ) {
			return 1;
		} else if( luu > ruu ) {
			return -1;
		}

		rlen = LDAP_UTF8_CHARLEN( &right->bv_val[r] );
		llen = LDAP_UTF8_CHARLEN( &left->bv_val[l] );
	}

	if( r < rslen ) {
		/* less left */
		return -1;
	}

	if( l < lslen ) {
		/* less right */
		return 1;
	}

	return 0;
}

static char *UTF8casechr( const char *str, const char *c )
{
	char *p, *lower, *upper;
	ldap_ucs4_t tch, ch = ldap_utf8_to_ucs4(c);

	tch = uctolower ( ch );
	for( p = (char *) str; *p != '\0'; LDAP_UTF8_INCR(p) ) {
		if( ldap_utf8_to_ucs4( p ) == tch ) {
			break;
		} 
	}
	lower = *p != '\0' ? p : NULL;

	tch = uctoupper ( ch );
	for( p = (char *) str; *p != '\0'; LDAP_UTF8_INCR(p) ) {
		if( ldap_utf8_to_ucs4( p ) == tch ) {
			break;
		} 
	}
	upper = *p != '\0' ? p : NULL;
	
	if( lower && upper ) {
		return lower < upper ? lower : upper;
	} else if ( lower ) {
		return lower;
	} else {
		return upper;
	}
}
637
638
#endif

639
640
641
642
643
644
645
646
647
static int
UTF8StringValidate(
	Syntax *syntax,
	struct berval *in )
{
	ber_len_t count;
	int len;
	unsigned char *u = in->bv_val;

648
649
	if( !in->bv_len ) return LDAP_INVALID_SYNTAX;

650
	for( count = in->bv_len; count > 0; count-=len, u+=len ) {
651
652
653
654
		/* get the length indicated by the first byte */
		len = LDAP_UTF8_CHARLEN( u );

		/* should not be zero */
655
		if( len == 0 ) return LDAP_INVALID_SYNTAX;
656
657
658

		/* make sure len corresponds with the offset
			to the next character */
659
		if( LDAP_UTF8_OFFSET( u ) != len ) return LDAP_INVALID_SYNTAX;
660
661
	}

662
	if( count != 0 ) return LDAP_INVALID_SYNTAX;
663

664
	return LDAP_SUCCESS;
665
666
667
668
669
670
671
672
673
}

static int
UTF8StringNormalize(
	Syntax *syntax,
	struct berval *val,
	struct berval **normalized )
{
	struct berval *newval;
674
	char *p, *q, *s;
675

676
	newval = ch_malloc( sizeof( struct berval ) );
677

678
	p = val->bv_val;
679

680
681
682
	/* Ignore initial whitespace */
	while ( ldap_utf8_isspace( p ) ) {
		LDAP_UTF8_INCR( p );
Kurt Zeilenga's avatar
Kurt Zeilenga committed
683
	}
684

685
686
	if( *p == '\0' ) {
		ch_free( newval );
Kurt Zeilenga's avatar
Kurt Zeilenga committed
687
688
		return LDAP_INVALID_SYNTAX;
	}
689

690
691
692
	newval->bv_val = ch_strdup( p );
	p = q = newval->bv_val;
	s = NULL;
693

694
695
	while ( *p ) {
		int len;
696

697
698
699
700
701
		if ( ldap_utf8_isspace( p ) ) {
			len = LDAP_UTF8_COPY(q,p);
			s=q;
			p+=len;
			q+=len;
702

703
704
705
706
			/* Ignore the extra whitespace */
			while ( ldap_utf8_isspace( p ) ) {
				LDAP_UTF8_INCR( p );
			}
Kurt Zeilenga's avatar
Kurt Zeilenga committed
707
		} else {
708
709
710
711
			len = LDAP_UTF8_COPY(q,p);
			s=NULL;
			p+=len;
			q+=len;
Kurt Zeilenga's avatar
Kurt Zeilenga committed
712
		}
713
714
715
716
	}

	assert( *newval->bv_val );
	assert( newval->bv_val < p );
Kurt Zeilenga's avatar
Kurt Zeilenga committed
717
	assert( q <= p );
718

719
720
721
722
723
724
725
726
727
728
729
	/* cannot start with a space */
	assert( !ldap_utf8_isspace(newval->bv_val) );

	/*
	 * If the string ended in space, backup the pointer one
	 * position.  One is enough because the above loop collapsed
	 * all whitespace to a single space.
	 */

	if ( s != NULL ) {
		q = s;
Kurt Zeilenga's avatar
Kurt Zeilenga committed
730
	}
731

732
733
734
735
736
737
738
739
	/* cannot end with a space */
	assert( !ldap_utf8_isspace( LDAP_UTF8_PREV(q) ) );

	/* null terminate */
	*q = '\0';

	newval->bv_len = q - newval->bv_val;
	*normalized = newval;
740

741
	return LDAP_SUCCESS;
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
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
#if defined(SLAPD_APPROX_MULTISTRING)

#if defined(SLAPD_APPROX_INITIALS)
#define SLAPD_APPROX_DELIMITER "._ "
#define SLAPD_APPROX_WORDLEN 2
#else
#define SLAPD_APPROX_DELIMITER " "
#define SLAPD_APPROX_WORDLEN 1
#endif

static int
approxMatch(
	int *matchp,
	slap_mask_t flags,
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *value,
	void *assertedValue )
{
	char *val, *assertv, **values, **words, *c;
	int i, count, len, nextchunk=0, nextavail=0;


	/* Isolate how many words there are */
	val = ch_strdup( value->bv_val );
	for( c=val,count=1; *c; c++ ) {
		c = strpbrk( c, SLAPD_APPROX_DELIMITER );
		if ( c == NULL ) break;
		*c = '\0';
		count++;
	}

	/* Get a phonetic copy of each word */
	words = (char **)ch_malloc( count * sizeof(char *) );
	values = (char **)ch_malloc( count * sizeof(char *) );
	for( c=val,i=0;  i<count;  i++,c+=strlen(c)+1 ) {
		words[i] = c;
		values[i] = phonetic(c);
	}


	/* Work through the asserted value's words, to see if  at least some
	   of the words are there, in the same order. */
	assertv = ch_strdup( ((struct berval *)assertedValue)->bv_val );
	len = 0;
	while ( nextchunk < ((struct berval *)assertedValue)->bv_len ) {
		len = strcspn( assertv + nextchunk, SLAPD_APPROX_DELIMITER);
#if defined(SLAPD_APPROX_INITIALS)
		if( len <= 1 ) {
			/* Single letter words need to at least match one word's initial */
			for( i=nextavail; i<count; i++ )
				if( !strncasecmp( assertv+nextchunk, words[i], 1 ))
					break;
		}

		else
#endif
		{
			/* Isolate the next word in the asserted value and phonetic it */
			assertv[nextchunk+len] = '\0';
			val = phonetic( assertv + nextchunk );

			/* See if this phonetic chunk is in the remaining words of *value */
			for( i=nextavail; i<count; i++ ){
				if( !strcmp( val, values[i] ) ){
					nextavail = i+1;
					break;
				}
			}
		}

		/* This chunk in the asserted value was NOT within the *value. */
		if( i >= count ) {
			nextavail=-1;
			break;
		}

		/* Go on to the next word in the asserted value */
		nextchunk += len+1;
	}

	/* If some of the words were seen, call it a match */
	if( nextavail > 0 ) {
		*matchp = 0;
	}
	else {
		*matchp = 1;
	}

	/* Cleanup allocs */
	ch_free( assertv );
	for( i=0; i<count; i++ ) {
		ch_free( values[i] );
	}
	ch_free( values );
	ch_free( words );
	ch_free( val );

	return LDAP_SUCCESS;
}


int 
approxIndexer(
	slap_mask_t use,
	slap_mask_t flags,
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *prefix,
	struct berval **values,
	struct berval ***keysp )
{
	char *val, *c;
	int i,j, len, wordcount, keycount=0;
	struct berval **newkeys, **keys=NULL;


	for( j=0; values[j] != NULL; j++ ) {

		/* Isolate how many words there are. There will be a key for each */
		val = ch_strdup( values[j]->bv_val );
		for( wordcount=0,c=val;  *c;  c++) {
			len = strcspn(c, SLAPD_APPROX_DELIMITER);
			if( len >= SLAPD_APPROX_WORDLEN ) wordcount++;
			c+= len;
			if (*c == '\0') break;
			*c = '\0';
		}

		/* Allocate/increase storage to account for new keys */
		newkeys = (struct berval **)ch_malloc( (keycount + wordcount + 1) 
		   * sizeof(struct berval *) );
		memcpy( newkeys, keys, keycount * sizeof(struct berval *) );
		if( keys ) ch_free( keys );
		keys = newkeys;

		/* Get a phonetic copy of each word */
		for( c=val,i=0;  i<wordcount;  c+=len+1  ) {
			len = strlen( c );
			if( len < SLAPD_APPROX_WORDLEN ) continue;
			keys[keycount] = (struct berval *)ch_malloc( sizeof(struct berval) );
			keys[keycount]->bv_val = phonetic( c );
			keys[keycount]->bv_len = strlen( keys[keycount]->bv_val );
			keycount++;
			i++;
		}

		ch_free( val );
	}
	keys[keycount] = NULL;
	*keysp = keys;

	return LDAP_SUCCESS;
}


int 
approxFilter(
	slap_mask_t use,
	slap_mask_t flags,
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *prefix,
	void * assertValue,
	struct berval ***keysp )
{
	char *val, *c;
	int i, count, len;
	struct berval **keys;


	/* Isolate how many words there are. There will be a key for each */
	val = ch_strdup( ((struct berval *)assertValue)->bv_val );
	for( count=0,c=val;  *c;  c++) {
		len = strcspn(c, SLAPD_APPROX_DELIMITER);
		if( len >= SLAPD_APPROX_WORDLEN ) count++;
		c+= len;
		if (*c == '\0') break;
		*c = '\0';
	}

	/* Allocate storage for new keys */
	keys = (struct berval **)ch_malloc( (count + 1) * sizeof(struct berval *) );

	/* Get a phonetic copy of each word */
	for( c=val,i=0;  i<count; c+=len+1 ) {
		len = strlen(c);
		if( len < SLAPD_APPROX_WORDLEN ) continue;
		keys[i] = (struct berval *)ch_malloc( sizeof(struct berval) );
		keys[i]->bv_val = phonetic( c );
		keys[i]->bv_len = strlen( keys[i]->bv_val );
		i++;
	}

	ch_free( val );

	keys[count] = NULL;
	*keysp = keys;

	return LDAP_SUCCESS;
}


#else
/* No other form of Approximate Matching is defined */

static int
approxMatch(
	int *matchp,
	slap_mask_t flags,
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *value,
	void *assertedValue )
{
	char *vapprox, *avapprox;

	vapprox = phonetic( value->bv_val );
	avapprox = phonetic( ((struct berval *)assertedValue)->bv_val);

	*matchp = strcmp( vapprox, avapprox );

	ch_free( vapprox );
	ch_free( avapprox );

	return LDAP_SUCCESS;
}

int 
approxIndexer(
	slap_mask_t use,
	slap_mask_t flags,
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *prefix,
	struct berval **values,
	struct berval ***keysp )
{
	int i;
	struct berval **keys;


	for( i=0; values[i] != NULL; i++ ) {
		/* just count them */
	}
	assert( i > 0 );

	keys = (struct berval **)ch_malloc( sizeof( struct berval * ) * (i+1) );

	/* Copy each value and run it through phonetic() */
	for( i=0; values[i] != NULL; i++ ) {
		keys[i] = ch_malloc( sizeof( struct berval * ) );
		keys[i]->bv_val = phonetic( values[i]->bv_val );
		keys[i]->bv_len = strlen( keys[i]->bv_val );
	}
	keys[i] = NULL;

	*keysp = keys;
	return LDAP_SUCCESS;
}


int 
approxFilter(
	slap_mask_t use,
	slap_mask_t flags,
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *prefix,
	void * assertValue,
	struct berval ***keysp )
{
	struct berval **keys;


	keys = (struct berval **)ch_malloc( sizeof( struct berval * ) * 2 );

	/* Copy the value and run it through phonetic() */
	keys[0] = ch_malloc( sizeof( struct berval * ) );
	keys[0]->bv_val = phonetic( ((struct berval *)assertValue)->bv_val );
	keys[0]->bv_len = strlen( keys[0]->bv_val );
	keys[1] = NULL;

	*keysp = keys;
	return LDAP_SUCCESS;
}
#endif


1033
static int
1034
caseExactMatch(
1035
	int *matchp,
1036
	slap_mask_t flags,
1037
1038
1039
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *value,
1040
	void *assertedValue )
1041
{
1042
1043
1044
	int match = value->bv_len - ((struct berval *) assertedValue)->bv_len;

	if( match == 0 ) {
1045
1046
1047
		match = strncmp( value->bv_val,
			((struct berval *) assertedValue)->bv_val,
			value->bv_len );
1048
1049
1050
	}

	*matchp = match;
1051
	return LDAP_SUCCESS;
1052
1053
}

1054
static int
1055
caseExactSubstringsMatch(
1056
	int *matchp,
1057
	slap_mask_t flags,
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *value,
	void *assertedValue )
{
	int match = 0;
	SubstringsAssertion *sub = assertedValue;
	struct berval left = *value;
	int i;
	ber_len_t inlen=0;

1069
	/* Add up asserted input length */
1070
1071
1072
1073
	if( sub->sa_initial ) {
		inlen += sub->sa_initial->bv_len;
	}
	if( sub->sa_any ) {
1074
1075
		for(i=0; sub->sa_any[i] != NULL; i++) {
			inlen += sub->sa_any[i]->bv_len;
1076
1077
1078
1079
1080
1081
1082
		}
	}
	if( sub->sa_final ) {
		inlen += sub->sa_final->bv_len;
	}

	if( sub->sa_initial ) {
Kurt Zeilenga's avatar
Kurt Zeilenga committed
1083
1084
1085
1086
1087
		if( inlen > left.bv_len ) {
			match = 1;
			goto done;
		}

1088
1089
		match = strncmp( sub->sa_initial->bv_val, left.bv_val,
			sub->sa_initial->bv_len );
1090
1091
1092
1093
1094
1095
1096

		if( match != 0 ) {
			goto done;
		}

		left.bv_val += sub->sa_initial->bv_len;
		left.bv_len -= sub->sa_initial->bv_len;
1097
		inlen -= sub->sa_initial->bv_len;
Kurt Zeilenga's avatar
Kurt Zeilenga committed
1098
	}
1099

Kurt Zeilenga's avatar
Kurt Zeilenga committed
1100
	if( sub->sa_final ) {
1101
1102
1103
1104
		if( inlen > left.bv_len ) {
			match = 1;
			goto done;
		}
1105

1106
1107
1108
		match = strncmp( sub->sa_final->bv_val,
			&left.bv_val[left.bv_len - sub->sa_final->bv_len],
			sub->sa_final->bv_len );
1109
1110
1111
1112
1113
1114

		if( match != 0 ) {
			goto done;
		}

		left.bv_len -= sub->sa_final->bv_len;
1115
		inlen -= sub->sa_final->bv_len;
1116
1117
1118
	}

	if( sub->sa_any ) {
1119
1120
1121
1122
1123
		for(i=0; sub->sa_any[i]; i++) {
			ber_len_t idx;
			char *p;

retry:
Kurt Zeilenga's avatar
Kurt Zeilenga committed
1124
1125
1126
1127
1128
1129
			if( inlen > left.bv_len ) {
				/* not enough length */
				match = 1;
				goto done;
			}

1130
1131
1132
1133
			if( sub->sa_any[i]->bv_len == 0 ) {
				continue;
			}

1134
			p = strchr( left.bv_val, *sub->sa_any[i]->bv_val );
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157

			if( p == NULL ) {
				match = 1;
				goto done;
			}

			idx = p - left.bv_val;
			assert( idx < left.bv_len );

			if( idx >= left.bv_len ) {
				/* this shouldn't happen */
				return LDAP_OTHER;
			}

			left.bv_val = p;
			left.bv_len -= idx;

			if( sub->sa_any[i]->bv_len > left.bv_len ) {
				/* not enough left */
				match = 1;
				goto done;
			}

1158
1159
1160
			match = strncmp( left.bv_val,
				sub->sa_any[i]->bv_val,
				sub->sa_any[i]->bv_len );
1161
1162

			if( match != 0 ) {
1163
1164
				left.bv_val++;
				left.bv_len--;
1165
1166
1167
1168
1169
				goto retry;
			}

			left.bv_val += sub->sa_any[i]->bv_len;
			left.bv_len -= sub->sa_any[i]->bv_len;
1170
			inlen -= sub->sa_any[i]->bv_len;
1171
		}
1172
1173
1174
1175
1176
1177
1178
	}

done:
	*matchp = match;
	return LDAP_SUCCESS;
}

1179
/* Index generation function */
1180
int caseExactIndexer(
1181
1182
	slap_mask_t use,
	slap_mask_t flags,
1183
1184
1185
1186
1187
1188
1189
1190
1191
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *prefix,
	struct berval **values,
	struct berval ***keysp )
{
	int i;
	size_t slen, mlen;
	struct berval **keys;
1192
1193
	HASH_CONTEXT   HASHcontext;
	unsigned char   HASHdigest[HASH_BYTES];
1194
	struct berval digest;
1195
1196
	digest.bv_val = HASHdigest;
	digest.bv_len = sizeof(HASHdigest);
1197

1198
1199
1200
	/* we should have at least one value at this point */
	assert( values != NULL && values[0] != NULL );

1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
	for( i=0; values[i] != NULL; i++ ) {
		/* just count them */
	}

	keys = ch_malloc( sizeof( struct berval * ) * (i+1) );

	slen = strlen( syntax->ssyn_oid );
	mlen = strlen( mr->smr_oid );

	for( i=0; values[i] != NULL; i++ ) {
		struct berval *value = values[i];

1213
		HASH_Init( &HASHcontext );
1214
		if( prefix != NULL && prefix->bv_len > 0 ) {
1215
			HASH_Update( &HASHcontext,
1216
1217
				prefix->bv_val, prefix->bv_len );
		}
1218
		HASH_Update( &HASHcontext,
1219
			syntax->ssyn_oid, slen );
1220
		HASH_Update( &HASHcontext,
1221
			mr->smr_oid, mlen );
1222
		HASH_Update( &HASHcontext,
1223
			value->bv_val, value->bv_len );
1224
		HASH_Final( HASHdigest, &HASHcontext );
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234

		keys[i] = ber_bvdup( &digest );
	}

	keys[i] = NULL;
	*keysp = keys;
	return LDAP_SUCCESS;
}

/* Index generation function */
1235
int caseExactFilter(
1236
1237
	slap_mask_t use,
	slap_mask_t flags,
1238
1239
1240
1241
1242
1243
1244
1245
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *prefix,
	void * assertValue,
	struct berval ***keysp )
{
	size_t slen, mlen;
	struct berval **keys;
1246
1247
	HASH_CONTEXT   HASHcontext;
	unsigned char   HASHdigest[HASH_BYTES];
1248
1249
	struct berval *value;
	struct berval digest;
1250
1251
	digest.bv_val = HASHdigest;
	digest.bv_len = sizeof(HASHdigest);
1252
1253
1254
1255
1256
1257
1258
1259

	slen = strlen( syntax->ssyn_oid );
	mlen = strlen( mr->smr_oid );

	value = (struct berval *) assertValue;

	keys = ch_malloc( sizeof( struct berval * ) * 2 );

1260
	HASH_Init( &HASHcontext );
1261
	if( prefix != NULL && prefix->bv_len > 0 ) {
1262
		HASH_Update( &HASHcontext,
1263
1264
			prefix->bv_val, prefix->bv_len );
	}
1265
	HASH_Update( &HASHcontext,
1266
		syntax->ssyn_oid, slen );
1267
	HASH_Update( &HASHcontext,
1268
		mr->smr_oid, mlen );
1269
	HASH_Update( &HASHcontext,
1270
		value->bv_val, value->bv_len );
1271
	HASH_Final( HASHdigest, &HASHcontext );
1272
1273
1274
1275
1276
1277
1278

	keys[0] = ber_bvdup( &digest );
	keys[1] = NULL;

	*keysp = keys;
	return LDAP_SUCCESS;
}
1279

1280
/* Substrings Index generation function */
1281
int caseExactSubstringsIndexer(
1282
1283
	slap_mask_t use,
	slap_mask_t flags,
1284
1285
1286
1287
1288
1289
	Syntax *syntax,
	MatchingRule *mr,
	struct berval *prefix,
	struct berval **values,
	struct berval ***keysp )
{
1290
	ber_len_t i, nkeys;
1291
1292
	size_t slen, mlen;
	struct berval **keys;
1293
1294
	HASH_CONTEXT   HASHcontext;
	unsigned char   HASHdigest[HASH_BYTES];
1295
	struct berval digest;
1296
1297
	digest.bv_val = HASHdigest;
	digest.bv_len = sizeof(HASHdigest);
1298

1299
1300
1301
	/* we should have at least one value at this point */
	assert( values != NULL && values[0] != NULL );

1302
1303
1304
	nkeys=0;
	for( i=0; values[i] != NULL; i++ ) {
		/* count number of indices to generate */
1305
		if( values[i]->bv_len < SLAP_INDEX_SUBSTR_MINLEN ) {
1306
1307
1308
			continue;
		}

1309
		if( flags & SLAP_INDEX_SUBSTR_INITIAL ) {
1310
			if( values[i]->bv_len >= SLAP_INDEX_SUBSTR_MAXLEN ) {
1311
				nkeys += SLAP_INDEX_SUBSTR_MAXLEN -
1312
					( SLAP_INDEX_SUBSTR_MINLEN - 1);
1313
			} else {
1314
				nkeys += values[i]->bv_len - ( SLAP_INDEX_SUBSTR_MINLEN - 1 );
1315
1316
1317
			}
		}

1318
		if( flags & SLAP_INDEX_SUBSTR_ANY ) {
1319
1320
			if( values[i]->bv_len >= SLAP_INDEX_SUBSTR_MAXLEN ) {
				nkeys += values[i]->bv_len - ( SLAP_INDEX_SUBSTR_MAXLEN - 1 );
1321
1322
1323
			}
		}

1324
		if( flags & SLAP_INDEX_SUBSTR_FINAL ) {
1325
			if( values[i]->bv_len >= SLAP_INDEX_SUBSTR_MAXLEN ) {
1326
				nkeys += SLAP_INDEX_SUBSTR_MAXLEN -
1327
					( SLAP_INDEX_SUBSTR_MINLEN - 1);
1328
			} else {
1329
				nkeys += values[i]->bv_len - ( SLAP_INDEX_SUBSTR_MINLEN - 1 );
1330
			}
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
		}
	}

	if( nkeys == 0 ) {
		/* no keys to generate */
		*keysp = NULL;
		return LDAP_SUCCESS;
	}

	keys = ch_malloc( sizeof( struct berval * ) * (nkeys+1) );

	slen = strlen( syntax->ssyn_oid );
	mlen = strlen( mr->smr_oid );

	nkeys=0;
	for( i=0; values[i] != NULL; i++ ) {
1347
		ber_len_t j,max;
1348
1349
		struct berval *value;

1350
		value = values[i];
1351
		if( value->bv_len < SLAP_INDEX_SUBSTR_MINLEN ) continue;
1352

1353
		if( ( flags & SLAP_INDEX_SUBSTR_ANY ) &&
1354
			( value->bv_len >= SLAP_INDEX_SUBSTR_MAXLEN ) )
1355
1356
		{
			char pre = SLAP_INDEX_SUBSTR_PREFIX;
1357
			max = value->bv_len - ( SLAP_INDEX_SUBSTR_MAXLEN - 1);
1358

1359
			for( j=0; j<max; j++ ) {
1360
				HASH_Init( &HASHcontext );
1361
				if( prefix != NULL && prefix->bv_len > 0 ) {
1362
					HASH_Update( &HASHcontext,
1363
1364
						prefix->bv_val, prefix->bv_len );
				}
1365

1366
				HASH_Update( &HASHcontext,
1367
					&pre, sizeof( pre ) );
1368
				HASH_Update( &HASHcontext,
1369
					syntax->ssyn_oid, slen );
1370
				HASH_Update( &HASHcontext,
1371
					mr->smr_oid, mlen );
1372
				HASH_Update( &HASHcontext,
1373
1374
					&value->bv_val[j],
					SLAP_INDEX_SUBSTR_MAXLEN );
1375
				HASH_Final( HASHdigest, &HASHcontext );
1376
1377
1378
1379
1380

				keys[nkeys++] = ber_bvdup( &digest );
			}
		}

1381
1382
		max = SLAP_INDEX_SUBSTR_MAXLEN < value->bv_len
			? SLAP_INDEX_SUBSTR_MAXLEN : value->bv_len;
1383

1384
		for( j=SLAP_INDEX_SUBSTR_MINLEN; j<=max; j++ ) {
1385
1386
			char pre;

1387
			if( flags & SLAP_INDEX_SUBSTR_INITIAL ) {
1388
				pre = SLAP_INDEX_SUBSTR_INITIAL_PREFIX;
1389
				HASH_Init( &HASHcontext );
1390
				if( prefix != NULL && prefix->bv_len > 0 ) {
1391
					HASH_Update( &HASHcontext,
1392
1393
						prefix->bv_val, prefix->bv_len );
				}
1394
				HASH_Update( &HASHcontext,
1395
					&pre, sizeof( pre ) );
1396
				HASH_Update( &HASHcontext,
1397
					syntax->ssyn_oid, slen );
1398
				HASH_Update( &HASHcontext,
1399
					mr->smr_oid, mlen );
1400
				HASH_Update( &HASHcontext,
1401
					value->bv_val, j );
1402
				HASH_Final( HASHdigest, &HASHcontext );
1403
1404
1405
1406

				keys[nkeys++] = ber_bvdup( &digest );
			}

1407
			if( flags & SLAP_INDEX_SUBSTR_FINAL ) {
1408
				pre = SLAP_INDEX_SUBSTR_FINAL_PREFIX;
1409
				HASH_Init( &HASHcontext );
1410
				if( prefix != NULL && prefix->bv_len > 0 ) {
1411
					HASH_Update( &HASHcontext,
1412
1413
						prefix->bv_val, prefix->bv_len );
				}
1414
				HASH_Update( &HASHcontext,
1415
					&pre, sizeof( pre ) );
1416
				HASH_Update( &HASHcontext,
1417
					syntax->ssyn_oid, slen );
1418
				HASH_Update( &HASHcontext,
1419
					mr->smr_oid, mlen );
1420
				HASH_Update( &HASHcontext,
1421
					&value->bv_val[value->bv_len-j], j );
1422
				HASH_Final( HASHdigest, &HASHcontext );
1423
1424
1425
1426
1427
1428
1429

				keys[nkeys++] = ber_bvdup( &digest );
			}

		}
	}

1430
1431
1432
1433
1434
1435
1436
1437
	if( nkeys > 0 ) {
		keys[nkeys] = NULL;
		*keysp = keys;
	} else {
		ch_free( keys );
		*keysp = NULL;
	}

1438
1439
	return LDAP_SUCCESS;
}
1440

Kurt Zeilenga's avatar