summaryrefslogtreecommitdiff
path: root/src/core/string.c
blob: 1e3817c879867c60b7372efe8fe357603c03c8ad (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
/*
 * This file is part of libdom.
 * Licensed under the MIT License,
 *                http://www.opensource.org/licenses/mit-license.php
 * Copyright 2007 John-Mark Bell <jmb@netsurf-browser.org>
 */

#include <ctype.h>
#include <inttypes.h>
#include <string.h>

#include <dom/core/string.h>

#include "core/document.h"
#include "utils/utils.h"
#include "utils/utf8.h"
#include "utils/utf16.h"

/**
 * A DOM string
 *
 * DOM strings store either a pointer to allocated data, a pointer
 * to constant data or an offset into a document buffer.
 *
 * They are reference counted so freeing is performed correctly.
 */
struct dom_string {
	enum { DOM_STRING_PTR,
	       DOM_STRING_CONST_PTR,
	       DOM_STRING_OFFSET,
	       DOM_STRING_PTR_NODOC
	} type;				/**< String type */

	dom_string_charset charset;	/**< Charset of string */

	union {
		uint8_t *ptr;
		const uint8_t *cptr;
		uint32_t offset;
	} data;				/**< Type-specific data */

	size_t len;			/**< Byte length of string */

	union {
		struct dom_document *doc;	/**< Owning document */
		struct {
			dom_alloc alloc;	/**< Memory (de)allocation
						 * function */
			void *pw;	/**< Client-specific data */
		} nodoc;
	} ctx;				/**< Allocation context */

	uint32_t refcnt;		/**< Reference count */
};

static struct dom_string empty_string = { 
	.type = DOM_STRING_CONST_PTR,
	.charset = DOM_STRING_UTF8,
	.data.ptr = NULL,
	.len = 0,
	.ctx.doc = NULL,
	.refcnt = 1
};

static dom_exception __dom_string_get_data(struct dom_string *str,
		const uint8_t **data, size_t *len);

/**
 * Claim a reference on a DOM string
 *
 * \param str  The string to claim a reference on
 */
void dom_string_ref(struct dom_string *str)
{
	str->refcnt++;
}

/**
 * Release a reference on a DOM string
 *
 * \param str  The string to release the reference from
 *
 * If the reference count reaches zero, any memory claimed by the
 * string will be released
 */
void dom_string_unref(struct dom_string *str)
{
	if (--str->refcnt == 0) {
		if (str->type == DOM_STRING_PTR_NODOC) {
			str->ctx.nodoc.alloc(str->data.ptr, 0,
					str->ctx.nodoc.pw);

			str->ctx.nodoc.alloc(str, 0, str->ctx.nodoc.pw);
		} else {
			if (str->type == DOM_STRING_PTR) {
				dom_document_alloc(str->ctx.doc,
						str->data.ptr, 0);
			}

			dom_document_alloc(str->ctx.doc, str, 0);
		}
	}
}

/**
 * Create a DOM string from an offset into the document buffer
 *
 * \param doc  The document in which the string resides
 * \param off  Offset from start of document buffer
 * \param len  Length, in bytes, of string
 * \param str  Pointer to location to receive pointer to new string
 * \return DOM_NO_ERR on success, DOM_NO_MEM_ERR on memory exhaustion
 *
 * The returned string will already be referenced, so there is no need
 * to explicitly reference it.
 */
dom_exception dom_string_create_from_off(struct dom_document *doc,
		uint32_t off, size_t len, struct dom_string **str)
{
	struct dom_string *ret;

	ret = dom_document_alloc(doc, NULL, sizeof(struct dom_string));
	if (ret == NULL)
		return DOM_NO_MEM_ERR;

	ret->type = DOM_STRING_OFFSET;

	ret->charset = dom_document_get_charset(doc);

	ret->data.offset = off;

	ret->len = len;

	ret->ctx.doc = doc;

	ret->refcnt = 1;

	*str = ret;

	return DOM_NO_ERR;
}

/**
 * Create a DOM string from a string of characters
 *
 * \param doc  The document in which the string resides
 * \param ptr  Pointer to string of characters
 * \param len  Length, in bytes, of string of characters
 * \param str  Pointer to location to receive pointer to new string
 * \return DOM_NO_ERR on success, DOM_NO_MEM_ERR on memory exhaustion
 *
 * The returned string will already be referenced, so there is no need
 * to explicitly reference it.
 *
 * The string of characters passed in will be copied for use by the
 * returned DOM string.
 */
dom_exception dom_string_create_from_ptr(struct dom_document *doc,
		const uint8_t *ptr, size_t len, struct dom_string **str)
{
	struct dom_string *ret;

	ret = dom_document_alloc(doc, NULL, sizeof(struct dom_string));
	if (ret == NULL)
		return DOM_NO_MEM_ERR;

	ret->data.ptr = dom_document_alloc(doc, NULL, len);
	if (ret->data.ptr == NULL) {
		dom_document_alloc(doc, ret, 0);
		return DOM_NO_MEM_ERR;
	}

	ret->type = DOM_STRING_PTR;

	ret->charset = dom_document_get_charset(doc);

	memcpy(ret->data.ptr, ptr, len);

	ret->len = len;

	ret->ctx.doc = doc;

	ret->refcnt = 1;

	*str = ret;

	return DOM_NO_ERR;
}

/**
 * Create a DOM string from a constant string of characters
 *
 * \param doc  The document in which the string resides
 * \param ptr  Pointer to string of characters
 * \param len  Length, in bytes, of string of characters
 * \param str  Pointer to location to receive pointer to new string
 * \return DOM_NO_ERR on success, DOM_NO_MEM_ERR on memory exhaustion
 *
 * The returned string will already be referenced, so there is no need
 * to explicitly reference it.
 *
 * The string of characters passed in will _not_ be copied for use by the
 * returned DOM string.
 */
dom_exception dom_string_create_from_const_ptr(struct dom_document *doc,
		const uint8_t *ptr, size_t len, struct dom_string **str)
{
	struct dom_string *ret;

	ret = dom_document_alloc(doc, NULL, sizeof(struct dom_string));
	if (ret == NULL)
		return DOM_NO_MEM_ERR;

	ret->type = DOM_STRING_CONST_PTR;

	ret->charset = dom_document_get_charset(doc);

	ret->data.cptr = ptr;

	ret->len = len;

	ret->ctx.doc = doc;

	ret->refcnt = 1;

	*str = ret;

	return DOM_NO_ERR;
}

/**
 * Create a DOM string from a string of characters that does not belong
 * to a document
 *
 * \param alloc    Memory (de)allocation function
 * \param pw       Pointer to client-specific private data
 * \param charset  The charset of the string
 * \param ptr      Pointer to string of characters
 * \param len      Length, in bytes, of string of characters
 * \param str      Pointer to location to receive result
 * \return DOM_NO_ERR on success, DOM_NO_MEM_ERR on memory exhaustion
 *
 * The returned string will already be referenced, so there is no need
 * to explicitly reference it.
 *
 * The string of characters passed in will be copied for use by the
 * returned DOM string.
 */
dom_exception dom_string_create_from_ptr_no_doc(dom_alloc alloc, void *pw,
		dom_string_charset charset, const uint8_t *ptr, size_t len, 
		struct dom_string **str)
{
	struct dom_string *ret;

	ret = alloc(NULL, sizeof(struct dom_string), pw);
	if (ret == NULL)
		return DOM_NO_MEM_ERR;

	ret->data.ptr = alloc(NULL, len, pw);
	if (ret->data.ptr == NULL) {
		alloc(ret, 0, pw);
		return DOM_NO_MEM_ERR;
	}

	ret->type = DOM_STRING_PTR_NODOC;

	ret->charset = charset;

	memcpy(ret->data.ptr, ptr, len);

	ret->len = len;

	ret->ctx.nodoc.alloc = alloc;
	ret->ctx.nodoc.pw = pw;

	ret->refcnt = 1;

	*str = ret;

	return DOM_NO_ERR;
}

/**
 * Case sensitively compare two DOM strings
 *
 * \param s1  The first string to compare
 * \param s2  The second string to compare
 * \return 0 if strings match, non-0 otherwise
 *
 * NULL and "" will match.
 */
int dom_string_cmp(struct dom_string *s1, struct dom_string *s2)
{
	const uint8_t *d1 = NULL;
	const uint8_t *d2 = NULL;
	size_t l1, l2;
	dom_exception err;

	err = __dom_string_get_data(s1, &d1, &l1);
	if (err != DOM_NO_ERR)
		return 1; /* arbitrary */

	err = __dom_string_get_data(s2, &d2, &l2);
	if (err != DOM_NO_ERR)
		return 1; /* arbitrary */

	while (l1 > 0 && l2 > 0) {
		uint32_t c1, c2;
		size_t cl1, cl2;
		charset_error err;

		err = (s1->charset == DOM_STRING_UTF8) 
				? _dom_utf8_to_ucs4(d1, l1, &c1, &cl1) 
				: _dom_utf16_to_ucs4(d1, l1, &c1, &cl1);
		if (err != CHARSET_OK) {
		}

		err = (s2->charset == DOM_STRING_UTF8)
				? _dom_utf8_to_ucs4(d2, l2, &c2, &cl2)
				: _dom_utf16_to_ucs4(d2, l2, &c2, &cl2);
		if (err != CHARSET_OK) {
		}

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

		d1 += cl1;
		d2 += cl2;

		l1 -= cl1;
		l2 -= cl2;
	}

	return (int)(l1 - l2);
}

/**
 * Case insensitively compare two DOM strings
 *
 * \param s1  The first string to compare
 * \param s2  The second string to compare
 * \return 0 if strings match, non-0 otherwise
 *
 * NULL and "" will match.
 */
int dom_string_icmp(struct dom_string *s1, struct dom_string *s2)
{
	const uint8_t *d1 = NULL;
	const uint8_t *d2 = NULL;
	size_t l1, l2;
	dom_exception err;

	err = __dom_string_get_data(s1, &d1, &l1);
	if (err != DOM_NO_ERR)
		return 1; /* arbitrary */

	err = __dom_string_get_data(s2, &d2, &l2);
	if (err != DOM_NO_ERR)
		return 1; /* arbitrary */

	while (l1 > 0 && l2 > 0) {
		uint32_t c1, c2;
		size_t cl1, cl2;
		charset_error err;

		err = (s1->charset == DOM_STRING_UTF8) 
				? _dom_utf8_to_ucs4(d1, l1, &c1, &cl1) 
				: _dom_utf16_to_ucs4(d1, l1, &c1, &cl1);
		if (err != CHARSET_OK) {
		}

		err = (s2->charset == DOM_STRING_UTF8)
				? _dom_utf8_to_ucs4(d2, l2, &c2, &cl2)
				: _dom_utf16_to_ucs4(d2, l2, &c2, &cl2);
		if (err != CHARSET_OK) {
		}

		/** \todo improved lower-casing algorithm */
		if (tolower(c1) != tolower(c2)) {
			return (int)(tolower(c1) - tolower(c2));
		}

		d1 += cl1;
		d2 += cl2;

		l1 -= cl1;
		l2 -= cl2;
	}

	return (int)(l1 - l2);
}

/**
 * Get the index of the first occurrence of a character in a dom string 
 * 
 * \param str  The string to search in
 * \param chr  UCS4 value to look for
 * \return Character index of found character, or -1 if none found 
 */
uint32_t dom_string_index(struct dom_string *str, uint32_t chr)
{
	const uint8_t *s;
	size_t clen, slen;
	uint32_t c, index;
	charset_error err;

	__dom_string_get_data(str, &s, &slen);

	index = 0;

	while (slen > 0) {
		if (str->charset == DOM_STRING_UTF8) {
			err = _dom_utf8_to_ucs4(s, slen, &c, &clen);
		} else {
			err = _dom_utf16_to_ucs4(s, slen, &c, &clen);
		}

		if (err != CHARSET_OK) {
			return (uint32_t) -1;
		}

		if (c == chr) {
			return index;
		}

		s += clen;
		slen -= clen;
		index++;
	}

	return (uint32_t) -1;
}

/**
 * Get the index of the last occurrence of a character in a dom string 
 * 
 * \param str  The string to search in
 * \param chr  UCS4 value to look for
 * \return Character index of found character, or -1 if none found
 */
uint32_t dom_string_rindex(struct dom_string *str, uint32_t chr)
{
	const uint8_t *s;
	size_t clen, slen;
	uint32_t c, index;
	charset_error err;

	__dom_string_get_data(str, &s, &slen);

	index = dom_string_length(str);

	while (slen > 0) {
		if (str->charset == DOM_STRING_UTF8) {
			err = _dom_utf8_prev(s, slen, &clen);
			if (err == CHARSET_OK) {
				err = _dom_utf8_to_ucs4(s + clen, slen - clen, 
						&c, &clen);
			}
		} else {
			err = _dom_utf16_prev(s, slen, &clen);
			if (err == CHARSET_OK) {
				err = _dom_utf16_to_ucs4(s + clen, slen - clen,
						&c, &clen);
			}
		}

		if (err != CHARSET_OK) {
			return (uint32_t) -1;
		}

		if (c == chr) {
			return index;
		}

		slen -= clen;
		index--;
	}

	return (uint32_t) -1;

}

/**
 * Get the length, in characters, of a dom string
 *
 * \param str  The string to measure the length of
 * \return The length of the string, in characters
 */
uint32_t dom_string_length(struct dom_string *str)
{
	const uint8_t *s;
	size_t slen;
	uint32_t clen;
	charset_error err;

	__dom_string_get_data(str, &s, &slen);

	if (str->charset == DOM_STRING_UTF8) {
		err = _dom_utf8_length(s, slen, &clen);
	} else {
		err = _dom_utf16_length(s, slen, &clen);
	}

	if (err != CHARSET_OK) {
		return 0;
	}

	return clen;
}

/** 
 * Concatenate two dom strings 
 * 
 * \param s1      The first string
 * \param s2      The second string
 * \param result  Pointer to location to receive result
 * \return DOM_NO_ERR on success, DOM_NO_MEM_ERR on memory exhaustion
 *
 * The returned string will be allocated using the allocation details
 * stored in ::s1.
 * 
 * The returned string will have its reference count increased. The client
 * should dereference it once it has finished with it.
 */
dom_exception dom_string_concat(struct dom_string *s1, struct dom_string *s2,
		struct dom_string **result)
{
	struct dom_string *concat;
	const uint8_t *s;
	size_t slen;

	if (s1->type == DOM_STRING_PTR_NODOC) {
		concat = s1->ctx.nodoc.alloc(NULL, 
				sizeof(struct dom_string), s1->ctx.nodoc.pw);
	} else {
		concat = dom_document_alloc(s1->ctx.doc, 
				NULL, sizeof(struct dom_string));
	}

	if (concat == NULL) {
		return DOM_NO_MEM_ERR;
	}

	/** \todo support attempted concatenation of mismatched charsets */

	if (s1->type == DOM_STRING_PTR_NODOC) {
		concat->data.ptr = s1->ctx.nodoc.alloc(NULL, 
				s1->len + s2->len, s1->ctx.nodoc.pw);
	} else {
		concat->data.ptr = dom_document_alloc(s1->ctx.doc, 
				NULL, s1->len + s2->len);
	}
	if (concat->data.ptr == NULL) {
		if (s1->type == DOM_STRING_PTR_NODOC) {
			s1->ctx.nodoc.alloc(concat, 0, s1->ctx.nodoc.pw);
		} else {
			dom_document_alloc(s1->ctx.doc, concat, 0);
		}
		return DOM_NO_MEM_ERR;
	}

	concat->type = (s1->type == DOM_STRING_PTR_NODOC) 
			? DOM_STRING_PTR_NODOC : DOM_STRING_PTR;

	concat->charset = s1->charset;

	__dom_string_get_data(s1, &s, &slen);

	memcpy(concat->data.ptr, s, slen);

	__dom_string_get_data(s2, &s, &slen);

	memcpy(concat->data.ptr + s1->len, s, slen);

	concat->len = s1->len + s2->len;

	if (concat->type == DOM_STRING_PTR_NODOC) {
		concat->ctx.nodoc.alloc = s1->ctx.nodoc.alloc;
		concat->ctx.nodoc.pw = s1->ctx.nodoc.pw;
	} else {
		concat->ctx.doc = s1->ctx.doc;
	}

	concat->refcnt = 1;

	*result = concat;

	return DOM_NO_ERR;
}

/**
 * Extract a substring from a dom string 
 *
 * \param str     The string to extract from
 * \param i1      The character index of the start of the substring
 * \param i2      The character index of the end of the substring
 * \param result  Pointer to location to receive result
 * \return DOM_NO_ERR on success, DOM_NO_MEM_ERR on memory exhaustion
 *
 * The returned string will be allocated using the allocation details
 * stored in ::str.
 *
 * The returned string will have its reference count increased. The client
 * should dereference it once it has finished with it.
 */
dom_exception dom_string_substr(struct dom_string *str, 
		uint32_t i1, uint32_t i2, struct dom_string **result)
{
	const uint8_t *s;
	size_t slen;
	size_t b1, b2;
	charset_error err;

	__dom_string_get_data(str, &s, &slen);

	/* Initialise the byte index of the start to 0 */
	b1 = 0;
	/* Make the end a character offset from the start */
	i2 -= i1;

	/* Calculate the byte index of the start */
	while (i1 > 0) {
		if (str->charset == DOM_STRING_UTF8) {
			err = _dom_utf8_next(s, slen, b1, &b1);
		} else {
			err = _dom_utf16_next(s, slen, b1, &b1);
		}

		if (err != CHARSET_OK) {
			return DOM_NO_MEM_ERR;
		}

		i1--;
	}

	/* Initialise the byte index of the end to that of the start */
	b2 = b1;

	/* Calculate the byte index of the end */
	while (i2 > 0) {
		if (str->charset == DOM_STRING_UTF8) {
			err = _dom_utf8_next(s, slen, b2, &b2);
		} else {
			err = _dom_utf16_next(s, slen, b2, &b2);
		}

		if (err != CHARSET_OK) {
			return DOM_NO_MEM_ERR;
		}

		i2--;
	}

	/* Create a string from the specified byte range */
	return (str->type == DOM_STRING_PTR_NODOC)
			? dom_string_create_from_ptr_no_doc(
					str->ctx.nodoc.alloc,
					str->ctx.nodoc.pw,
					str->charset, 
					s + b1, b2 - b1, result)
			: dom_string_create_from_ptr(str->ctx.doc,
					s + b1, b2 - b2, result);
}

/**
 * Duplicate a dom string 
 *
 * \param str     The string to duplicate
 * \param result  Pointer to location to receive result
 * \return DOM_NO_ERR on success, DOM_NO_MEM_ERR on memory exhaustion
 *
 * The returned string will be allocated using the allocation details
 * stored in ::str.
 *
 * The returned string will have its reference count increased. The client
 * should dereference it once it has finished with it.
 */
dom_exception dom_string_dup(struct dom_string *str, 
		struct dom_string **result)
{
	const uint8_t *s;
	size_t slen;

	__dom_string_get_data(str, &s, &slen);

	return str->type == DOM_STRING_PTR_NODOC 
			? dom_string_create_from_ptr_no_doc(
				str->ctx.nodoc.alloc,
				str->ctx.nodoc.pw,
				str->charset,
				s, slen, result) 
			: dom_string_create_from_ptr(str->ctx.doc,
					s, slen, result);
}

/**
 * Calculate a hash value from a dom string 
 *
 * \param str  The string to calculate a hash of
 * \return The hash value associated with the string
 */
uint32_t dom_string_hash(struct dom_string *str)
{
	const uint8_t *s;
	size_t slen;
	uint32_t hash = 0x01000193;

	__dom_string_get_data(str, &s, &slen);

	while (slen > 0) {
		hash *= 0x01000193;
		hash ^= *s;

		s++;
		slen--;
	}

	return hash;
}

/*                                                                           */
/*---------------------------------------------------------------------------*/
/*                                                                           */

/**
 * Get a pointer to the string of characters within a DOM string
 *
 * \param str   Pointer to DOM string to retrieve pointer from
 * \param data  Pointer to location to receive data
 * \param len   Pointer to location to receive byte length of data
 * \return DOM_NO_ERR on success
 *
 * The caller must have previously claimed a reference on the DOM string.
 * The returned pointer must not be freed.
 */
dom_exception __dom_string_get_data(struct dom_string *str,
		const uint8_t **data, size_t *len)
{
	/* Assume that a NULL str pointer indicates the empty string */
	if (str == NULL)
		str = &empty_string;

	switch (str->type) {
	case DOM_STRING_PTR:
		*data = str->data.ptr;
		break;
	case DOM_STRING_CONST_PTR:
		*data = str->data.cptr;
		break;
	case DOM_STRING_OFFSET:
		*data = dom_document_get_base(str->ctx.doc) +
				str->data.offset;
		break;
	case DOM_STRING_PTR_NODOC:
		*data = str->data.ptr;
		break;
	}

	*len = str->len;

	return DOM_NO_ERR;
}