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
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
|
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html401/loose.dtd">
<html>
<!-- Created on February, 24 2024 by texi2html 1.78a -->
<!--
Written by: Lionel Cons <Lionel.Cons@cern.ch> (original author)
Karl Berry <karl@freefriends.org>
Olaf Bachmann <obachman@mathematik.uni-kl.de>
and many others.
Maintained by: Many creative people.
Send bugs and suggestions to <texi2html-bug@nongnu.org>
-->
<head>
<title>GNU libunistring: 4. Elementary Unicode string functions <unistr.h></title>
<meta name="description" content="GNU libunistring: 4. Elementary Unicode string functions <unistr.h>">
<meta name="keywords" content="GNU libunistring: 4. Elementary Unicode string functions <unistr.h>">
<meta name="resource-type" content="document">
<meta name="distribution" content="global">
<meta name="Generator" content="texi2html 1.78a">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<style type="text/css">
<!--
a.summary-letter {text-decoration: none}
pre.display {font-family: serif}
pre.format {font-family: serif}
pre.menu-comment {font-family: serif}
pre.menu-preformatted {font-family: serif}
pre.smalldisplay {font-family: serif; font-size: smaller}
pre.smallexample {font-size: smaller}
pre.smallformat {font-family: serif; font-size: smaller}
pre.smalllisp {font-size: smaller}
span.roman {font-family:serif; font-weight:normal;}
span.sansserif {font-family:sans-serif; font-weight:normal;}
ul.toc {list-style: none}
-->
</style>
</head>
<body lang="en" bgcolor="#FFFFFF" text="#000000" link="#0000FF" vlink="#800080" alink="#FF0000">
<table cellpadding="1" cellspacing="1" border="0">
<tr><td valign="middle" align="left">[<a href="libunistring_3.html#SEC9" title="Beginning of this chapter or previous chapter"> << </a>]</td>
<td valign="middle" align="left">[<a href="libunistring_5.html#SEC30" title="Next chapter"> >> </a>]</td>
<td valign="middle" align="left"> </td>
<td valign="middle" align="left"> </td>
<td valign="middle" align="left"> </td>
<td valign="middle" align="left"> </td>
<td valign="middle" align="left"> </td>
<td valign="middle" align="left">[<a href="libunistring_toc.html#SEC_Top" title="Cover (top) of document">Top</a>]</td>
<td valign="middle" align="left">[<a href="libunistring_toc.html#SEC_Contents" title="Table of contents">Contents</a>]</td>
<td valign="middle" align="left">[<a href="libunistring_21.html#SEC94" title="Index">Index</a>]</td>
<td valign="middle" align="left">[<a href="libunistring_abt.html#SEC_About" title="About (help)"> ? </a>]</td>
</tr></table>
<hr size="2">
<a name="unistr_002eh"></a>
<a name="SEC10"></a>
<h1 class="chapter"> <a href="libunistring_toc.html#TOC10">4. Elementary Unicode string functions <code><unistr.h></code></a> </h1>
<p>This include file declares elementary functions for Unicode strings. It is
essentially the equivalent of what <code><string.h></code> is for C strings.
</p>
<hr size="6">
<a name="Elementary-string-checks"></a>
<a name="SEC11"></a>
<h2 class="section"> <a href="libunistring_toc.html#TOC11">4.1 Elementary string checks</a> </h2>
<p>The following function is available to verify the integrity of a Unicode string.
</p>
<dl>
<dt><u>Function:</u> const uint8_t * <b>u8_check</b><i> (const uint8_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX20"></a>
</dt>
<dt><u>Function:</u> const uint16_t * <b>u16_check</b><i> (const uint16_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX21"></a>
</dt>
<dt><u>Function:</u> const uint32_t * <b>u32_check</b><i> (const uint32_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX22"></a>
</dt>
<dd><p>This function checks whether a Unicode string is well-formed.
It returns NULL if valid, or a pointer to the first invalid unit otherwise.
</p></dd></dl>
<hr size="6">
<a name="Elementary-string-conversions"></a>
<a name="SEC12"></a>
<h2 class="section"> <a href="libunistring_toc.html#TOC12">4.2 Elementary string conversions</a> </h2>
<p>The following functions perform conversions between the different forms of Unicode strings.
</p>
<dl>
<dt><u>Function:</u> uint16_t * <b>u8_to_u16</b><i> (const uint8_t *<var>s</var>, size_t <var>n</var>, uint16_t *<var>resultbuf</var>, size_t *<var>lengthp</var>)</i>
<a name="IDX23"></a>
</dt>
<dd><p>Converts an UTF-8 string to an UTF-16 string.
</p>
<p>The <var>resultbuf</var> and <var>lengthp</var> arguments are as described in
chapter <a href="libunistring_2.html#SEC8">Conventions</a>.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint32_t * <b>u8_to_u32</b><i> (const uint8_t *<var>s</var>, size_t <var>n</var>, uint32_t *<var>resultbuf</var>, size_t *<var>lengthp</var>)</i>
<a name="IDX24"></a>
</dt>
<dd><p>Converts an UTF-8 string to an UTF-32 string.
</p>
<p>The <var>resultbuf</var> and <var>lengthp</var> arguments are as described in
chapter <a href="libunistring_2.html#SEC8">Conventions</a>.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint8_t * <b>u16_to_u8</b><i> (const uint16_t *<var>s</var>, size_t <var>n</var>, uint8_t *<var>resultbuf</var>, size_t *<var>lengthp</var>)</i>
<a name="IDX25"></a>
</dt>
<dd><p>Converts an UTF-16 string to an UTF-8 string.
</p>
<p>The <var>resultbuf</var> and <var>lengthp</var> arguments are as described in
chapter <a href="libunistring_2.html#SEC8">Conventions</a>.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint32_t * <b>u16_to_u32</b><i> (const uint16_t *<var>s</var>, size_t <var>n</var>, uint32_t *<var>resultbuf</var>, size_t *<var>lengthp</var>)</i>
<a name="IDX26"></a>
</dt>
<dd><p>Converts an UTF-16 string to an UTF-32 string.
</p>
<p>The <var>resultbuf</var> and <var>lengthp</var> arguments are as described in
chapter <a href="libunistring_2.html#SEC8">Conventions</a>.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint8_t * <b>u32_to_u8</b><i> (const uint32_t *<var>s</var>, size_t <var>n</var>, uint8_t *<var>resultbuf</var>, size_t *<var>lengthp</var>)</i>
<a name="IDX27"></a>
</dt>
<dd><p>Converts an UTF-32 string to an UTF-8 string.
</p>
<p>The <var>resultbuf</var> and <var>lengthp</var> arguments are as described in
chapter <a href="libunistring_2.html#SEC8">Conventions</a>.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint16_t * <b>u32_to_u16</b><i> (const uint32_t *<var>s</var>, size_t <var>n</var>, uint16_t *<var>resultbuf</var>, size_t *<var>lengthp</var>)</i>
<a name="IDX28"></a>
</dt>
<dd><p>Converts an UTF-32 string to an UTF-16 string.
</p>
<p>The <var>resultbuf</var> and <var>lengthp</var> arguments are as described in
chapter <a href="libunistring_2.html#SEC8">Conventions</a>.
</p></dd></dl>
<hr size="6">
<a name="Elementary-string-functions"></a>
<a name="SEC13"></a>
<h2 class="section"> <a href="libunistring_toc.html#TOC13">4.3 Elementary string functions</a> </h2>
<hr size="6">
<a name="Iterating"></a>
<a name="SEC14"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC14">4.3.1 Iterating over a Unicode string</a> </h3>
<p>The following functions inspect and return details about the first character
in a Unicode string.
</p>
<dl>
<dt><u>Function:</u> int <b>u8_mblen</b><i> (const uint8_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX29"></a>
</dt>
<dt><u>Function:</u> int <b>u16_mblen</b><i> (const uint16_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX30"></a>
</dt>
<dt><u>Function:</u> int <b>u32_mblen</b><i> (const uint32_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX31"></a>
</dt>
<dd><p>Returns the length (number of units) of the first character in <var>s</var>, which
is no longer than <var>n</var>. Returns 0 if it is the NUL character. Returns -1
upon failure.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/mblen.html"><code>mblen</code></a>, except that it operates on a
Unicode string and that <var>s</var> must not be NULL.
</p></dd></dl>
<dl>
<dt><u>Function:</u> int <b>u8_mbtouc</b><i> (ucs4_t *<var>puc</var>, const uint8_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX32"></a>
</dt>
<dt><u>Function:</u> int <b>u16_mbtouc</b><i> (ucs4_t *<var>puc</var>, const uint16_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX33"></a>
</dt>
<dt><u>Function:</u> int <b>u32_mbtouc</b><i> (ucs4_t *<var>puc</var>, const uint32_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX34"></a>
</dt>
<dd><p>Returns the length (number of units) of the first character in <var>s</var>,
putting its <code>ucs4_t</code> representation in <code>*<var>puc</var></code>. Upon failure,
<code>*<var>puc</var></code> is set to <code>0xfffd</code>, and an appropriate number of units
is returned.
</p>
<p>The number of available units, <var>n</var>, must be > 0.
</p>
<p>This function fails if an invalid sequence of units is encountered at the
beginning of <var>s</var>, or if additional units (after the <var>n</var> provided units)
would be needed to form a character.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/mbtowc.html"><code>mbtowc</code></a>, except that it operates on a
Unicode string, <var>puc</var> and <var>s</var> must not be NULL, <var>n</var> must be > 0,
and the NUL character is not treated specially.
</p></dd></dl>
<dl>
<dt><u>Function:</u> int <b>u8_mbtouc_unsafe</b><i> (ucs4_t *<var>puc</var>, const uint8_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX35"></a>
</dt>
<dt><u>Function:</u> int <b>u16_mbtouc_unsafe</b><i> (ucs4_t *<var>puc</var>, const uint16_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX36"></a>
</dt>
<dt><u>Function:</u> int <b>u32_mbtouc_unsafe</b><i> (ucs4_t *<var>puc</var>, const uint32_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX37"></a>
</dt>
<dd><p>This function is identical to <code>u8_mbtouc</code>/<code>u16_mbtouc</code>/<code>u32_mbtouc</code>.
Earlier versions of this function performed fewer range-checks on the sequence
of units.
</p></dd></dl>
<dl>
<dt><u>Function:</u> int <b>u8_mbtoucr</b><i> (ucs4_t *<var>puc</var>, const uint8_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX38"></a>
</dt>
<dt><u>Function:</u> int <b>u16_mbtoucr</b><i> (ucs4_t *<var>puc</var>, const uint16_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX39"></a>
</dt>
<dt><u>Function:</u> int <b>u32_mbtoucr</b><i> (ucs4_t *<var>puc</var>, const uint32_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX40"></a>
</dt>
<dd><p>Returns the length (number of units) of the first character in <var>s</var>,
putting its <code>ucs4_t</code> representation in <code>*<var>puc</var></code>. Upon failure,
<code>*<var>puc</var></code> is set to <code>0xfffd</code>, and -1 is returned for an invalid
sequence of units, -2 is returned for an incomplete sequence of units.
</p>
<p>The number of available units, <var>n</var>, must be > 0.
</p>
<p>This function is similar to <code>u8_mbtouc</code>, except that the return value
gives more details about the failure, similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/mbrtowc.html"><code>mbrtowc</code></a>.
</p></dd></dl>
<hr size="6">
<a name="Creating-Unicode-strings"></a>
<a name="SEC15"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC15">4.3.2 Creating Unicode strings one character at a time</a> </h3>
<p>The following function stores a Unicode character as a Unicode string in
memory.
</p>
<dl>
<dt><u>Function:</u> int <b>u8_uctomb</b><i> (uint8_t *<var>s</var>, ucs4_t <var>uc</var>, ptrdiff_t <var>n</var>)</i>
<a name="IDX41"></a>
</dt>
<dt><u>Function:</u> int <b>u16_uctomb</b><i> (uint16_t *<var>s</var>, ucs4_t <var>uc</var>, ptrdiff_t <var>n</var>)</i>
<a name="IDX42"></a>
</dt>
<dt><u>Function:</u> int <b>u32_uctomb</b><i> (uint32_t *<var>s</var>, ucs4_t <var>uc</var>, ptrdiff_t <var>n</var>)</i>
<a name="IDX43"></a>
</dt>
<dd><p>Puts the multibyte character represented by <var>uc</var> in <var>s</var>, returning its
length. Returns -1 upon failure, -2 if the number of available units, <var>n</var>,
is too small. The latter case cannot occur if <var>n</var> >= 6/2/1, respectively.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wctomb.html"><code>wctomb</code></a>, except that it operates on a
Unicode strings, <var>s</var> must not be NULL, and the argument <var>n</var> must be
specified.
</p></dd></dl>
<hr size="6">
<a name="Copying-Unicode-strings"></a>
<a name="SEC16"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC16">4.3.3 Copying Unicode strings</a> </h3>
<p>The following functions copy Unicode strings in memory.
</p>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_cpy</b><i> (uint8_t *<var>dest</var>, const uint8_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX44"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_cpy</b><i> (uint16_t *<var>dest</var>, const uint16_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX45"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_cpy</b><i> (uint32_t *<var>dest</var>, const uint32_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX46"></a>
</dt>
<dd><p>Copies <var>n</var> units from <var>src</var> to <var>dest</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/memcpy.html"><code>memcpy</code></a>, except that it operates on
Unicode strings.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_pcpy</b><i> (uint8_t *<var>dest</var>, const uint8_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX47"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_pcpy</b><i> (uint16_t *<var>dest</var>, const uint16_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX48"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_pcpy</b><i> (uint32_t *<var>dest</var>, const uint32_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX49"></a>
</dt>
<dd><p>Copies <var>n</var> units from <var>src</var> to <var>dest</var>, returning a pointer
after the last written unit.
</p>
<p>This function is similar to <code>mempcpy</code>, except that it operates on
Unicode strings.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_move</b><i> (uint8_t *<var>dest</var>, const uint8_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX50"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_move</b><i> (uint16_t *<var>dest</var>, const uint16_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX51"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_move</b><i> (uint32_t *<var>dest</var>, const uint32_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX52"></a>
</dt>
<dd><p>Copies <var>n</var> units from <var>src</var> to <var>dest</var>, guaranteeing correct
behavior for overlapping memory areas.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/memmove.html"><code>memmove</code></a>, except that it operates on
Unicode strings.
</p></dd></dl>
<p>The following function fills a Unicode string.
</p>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_set</b><i> (uint8_t *<var>s</var>, ucs4_t <var>uc</var>, size_t <var>n</var>)</i>
<a name="IDX53"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_set</b><i> (uint16_t *<var>s</var>, ucs4_t <var>uc</var>, size_t <var>n</var>)</i>
<a name="IDX54"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_set</b><i> (uint32_t *<var>s</var>, ucs4_t <var>uc</var>, size_t <var>n</var>)</i>
<a name="IDX55"></a>
</dt>
<dd><p>Sets the first <var>n</var> characters of <var>s</var> to <var>uc</var>. <var>uc</var> should be
a character that occupies only 1 unit.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/memset.html"><code>memset</code></a>, except that it operates on
Unicode strings.
</p></dd></dl>
<hr size="6">
<a name="Comparing-Unicode-strings"></a>
<a name="SEC17"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC17">4.3.4 Comparing Unicode strings</a> </h3>
<p>The following function compares two Unicode strings of the same length.
</p>
<dl>
<dt><u>Function:</u> int <b>u8_cmp</b><i> (const uint8_t *<var>s1</var>, const uint8_t *<var>s2</var>, size_t <var>n</var>)</i>
<a name="IDX56"></a>
</dt>
<dt><u>Function:</u> int <b>u16_cmp</b><i> (const uint16_t *<var>s1</var>, const uint16_t *<var>s2</var>, size_t <var>n</var>)</i>
<a name="IDX57"></a>
</dt>
<dt><u>Function:</u> int <b>u32_cmp</b><i> (const uint32_t *<var>s1</var>, const uint32_t *<var>s2</var>, size_t <var>n</var>)</i>
<a name="IDX58"></a>
</dt>
<dd><p>Compares <var>s1</var> and <var>s2</var>, each of length <var>n</var>, lexicographically.
Returns a negative value if <var>s1</var> compares smaller than <var>s2</var>,
a positive value if <var>s1</var> compares larger than <var>s2</var>, or 0 if
they compare equal.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/memcmp.html"><code>memcmp</code></a>, except that it operates on
Unicode strings.
</p></dd></dl>
<p>The following function compares two Unicode strings of possibly different
lengths.
</p>
<dl>
<dt><u>Function:</u> int <b>u8_cmp2</b><i> (const uint8_t *<var>s1</var>, size_t <var>n1</var>, const uint8_t *<var>s2</var>, size_t <var>n2</var>)</i>
<a name="IDX59"></a>
</dt>
<dt><u>Function:</u> int <b>u16_cmp2</b><i> (const uint16_t *<var>s1</var>, size_t <var>n1</var>, const uint16_t *<var>s2</var>, size_t <var>n2</var>)</i>
<a name="IDX60"></a>
</dt>
<dt><u>Function:</u> int <b>u32_cmp2</b><i> (const uint32_t *<var>s1</var>, size_t <var>n1</var>, const uint32_t *<var>s2</var>, size_t <var>n2</var>)</i>
<a name="IDX61"></a>
</dt>
<dd><p>Compares <var>s1</var> and <var>s2</var>, lexicographically.
Returns a negative value if <var>s1</var> compares smaller than <var>s2</var>,
a positive value if <var>s1</var> compares larger than <var>s2</var>, or 0 if
they compare equal.
</p>
<p>This function is similar to the gnulib function <code>memcmp2</code>, except that it
operates on Unicode strings.
</p></dd></dl>
<hr size="6">
<a name="Searching-for-a-character"></a>
<a name="SEC18"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC18">4.3.5 Searching for a character in a Unicode string</a> </h3>
<p>The following function searches for a given Unicode character.
</p>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_chr</b><i> (const uint8_t *<var>s</var>, size_t <var>n</var>, ucs4_t <var>uc</var>)</i>
<a name="IDX62"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_chr</b><i> (const uint16_t *<var>s</var>, size_t <var>n</var>, ucs4_t <var>uc</var>)</i>
<a name="IDX63"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_chr</b><i> (const uint32_t *<var>s</var>, size_t <var>n</var>, ucs4_t <var>uc</var>)</i>
<a name="IDX64"></a>
</dt>
<dd><p>Searches the string at <var>s</var> for <var>uc</var>. Returns a pointer to the first
occurrence of <var>uc</var> in <var>s</var>, or NULL if <var>uc</var> does not occur in
<var>s</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/memchr.html"><code>memchr</code></a>, except that it operates on
Unicode strings.
</p></dd></dl>
<hr size="6">
<a name="Counting-characters"></a>
<a name="SEC19"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC19">4.3.6 Counting the characters in a Unicode string</a> </h3>
<p>The following function counts the number of Unicode characters.
</p>
<dl>
<dt><u>Function:</u> size_t <b>u8_mbsnlen</b><i> (const uint8_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX65"></a>
</dt>
<dt><u>Function:</u> size_t <b>u16_mbsnlen</b><i> (const uint16_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX66"></a>
</dt>
<dt><u>Function:</u> size_t <b>u32_mbsnlen</b><i> (const uint32_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX67"></a>
</dt>
<dd><p>Counts and returns the number of Unicode characters in the <var>n</var> units
from <var>s</var>.
</p>
<p>This function is similar to the gnulib function <code>mbsnlen</code>, except that
it operates on Unicode strings.
</p></dd></dl>
<hr size="6">
<a name="Elementary-string-functions-with-memory-allocation"></a>
<a name="SEC20"></a>
<h2 class="section"> <a href="libunistring_toc.html#TOC20">4.4 Elementary string functions with memory allocation</a> </h2>
<p>The following function copies a Unicode string.
</p>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_cpy_alloc</b><i> (const uint8_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX68"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_cpy_alloc</b><i> (const uint16_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX69"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_cpy_alloc</b><i> (const uint32_t *<var>s</var>, size_t <var>n</var>)</i>
<a name="IDX70"></a>
</dt>
<dd><p>Makes a freshly allocated copy of <var>s</var>, of length <var>n</var>.
</p></dd></dl>
<hr size="6">
<a name="Elementary-string-functions-on-NUL-terminated-strings"></a>
<a name="SEC21"></a>
<h2 class="section"> <a href="libunistring_toc.html#TOC21">4.5 Elementary string functions on NUL terminated strings</a> </h2>
<hr size="6">
<a name="Iterating-over-a-NUL-terminated-Unicode-string"></a>
<a name="SEC22"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC22">4.5.1 Iterating over a NUL terminated Unicode string</a> </h3>
<p>The following functions inspect and return details about the first character
in a Unicode string.
</p>
<dl>
<dt><u>Function:</u> int <b>u8_strmblen</b><i> (const uint8_t *<var>s</var>)</i>
<a name="IDX71"></a>
</dt>
<dt><u>Function:</u> int <b>u16_strmblen</b><i> (const uint16_t *<var>s</var>)</i>
<a name="IDX72"></a>
</dt>
<dt><u>Function:</u> int <b>u32_strmblen</b><i> (const uint32_t *<var>s</var>)</i>
<a name="IDX73"></a>
</dt>
<dd><p>Returns the length (number of units) of the first character in <var>s</var>.
Returns 0 if it is the NUL character. Returns -1 upon failure.
</p></dd></dl>
<a name="IDX74"></a>
<dl>
<dt><u>Function:</u> int <b>u8_strmbtouc</b><i> (ucs4_t *<var>puc</var>, const uint8_t *<var>s</var>)</i>
<a name="IDX75"></a>
</dt>
<dt><u>Function:</u> int <b>u16_strmbtouc</b><i> (ucs4_t *<var>puc</var>, const uint16_t *<var>s</var>)</i>
<a name="IDX76"></a>
</dt>
<dt><u>Function:</u> int <b>u32_strmbtouc</b><i> (ucs4_t *<var>puc</var>, const uint32_t *<var>s</var>)</i>
<a name="IDX77"></a>
</dt>
<dd><p>Returns the length (number of units) of the first character in <var>s</var>,
putting its <code>ucs4_t</code> representation in <code>*<var>puc</var></code>. Returns 0
if it is the NUL character. Returns -1 upon failure.
</p></dd></dl>
<dl>
<dt><u>Function:</u> const uint8_t * <b>u8_next</b><i> (ucs4_t *<var>puc</var>, const uint8_t *<var>s</var>)</i>
<a name="IDX78"></a>
</dt>
<dt><u>Function:</u> const uint16_t * <b>u16_next</b><i> (ucs4_t *<var>puc</var>, const uint16_t *<var>s</var>)</i>
<a name="IDX79"></a>
</dt>
<dt><u>Function:</u> const uint32_t * <b>u32_next</b><i> (ucs4_t *<var>puc</var>, const uint32_t *<var>s</var>)</i>
<a name="IDX80"></a>
</dt>
<dd><p>Forward iteration step. Advances the pointer past the next character,
or returns NULL if the end of the string has been reached. Puts the
character's <code>ucs4_t</code> representation in <code>*<var>puc</var></code>.
</p></dd></dl>
<p>The following function inspects and returns details about the previous
character in a Unicode string.
</p>
<dl>
<dt><u>Function:</u> const uint8_t * <b>u8_prev</b><i> (ucs4_t *<var>puc</var>, const uint8_t *<var>s</var>, const uint8_t *<var>start</var>)</i>
<a name="IDX81"></a>
</dt>
<dt><u>Function:</u> const uint16_t * <b>u16_prev</b><i> (ucs4_t *<var>puc</var>, const uint16_t *<var>s</var>, const uint16_t *<var>start</var>)</i>
<a name="IDX82"></a>
</dt>
<dt><u>Function:</u> const uint32_t * <b>u32_prev</b><i> (ucs4_t *<var>puc</var>, const uint32_t *<var>s</var>, const uint32_t *<var>start</var>)</i>
<a name="IDX83"></a>
</dt>
<dd><p>Backward iteration step. Advances the pointer to point to the previous
character (the one that ends at <code><var>s</var></code>), or returns NULL if the
beginning of the string (specified by <code><var>start</var></code>) had been reached.
Puts the character's <code>ucs4_t</code> representation in <code>*<var>puc</var></code>.
Note that this function works only on well-formed Unicode strings.
</p></dd></dl>
<hr size="6">
<a name="Length"></a>
<a name="SEC23"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC23">4.5.2 Length of a NUL terminated Unicode string</a> </h3>
<p>The following functions determine the length of a Unicode string.
</p>
<dl>
<dt><u>Function:</u> size_t <b>u8_strlen</b><i> (const uint8_t *<var>s</var>)</i>
<a name="IDX84"></a>
</dt>
<dt><u>Function:</u> size_t <b>u16_strlen</b><i> (const uint16_t *<var>s</var>)</i>
<a name="IDX85"></a>
</dt>
<dt><u>Function:</u> size_t <b>u32_strlen</b><i> (const uint32_t *<var>s</var>)</i>
<a name="IDX86"></a>
</dt>
<dd><p>Returns the number of units in <var>s</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strlen.html"><code>strlen</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcslen.html"><code>wcslen</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<dl>
<dt><u>Function:</u> size_t <b>u8_strnlen</b><i> (const uint8_t *<var>s</var>, size_t <var>maxlen</var>)</i>
<a name="IDX87"></a>
</dt>
<dt><u>Function:</u> size_t <b>u16_strnlen</b><i> (const uint16_t *<var>s</var>, size_t <var>maxlen</var>)</i>
<a name="IDX88"></a>
</dt>
<dt><u>Function:</u> size_t <b>u32_strnlen</b><i> (const uint32_t *<var>s</var>, size_t <var>maxlen</var>)</i>
<a name="IDX89"></a>
</dt>
<dd><p>Returns the number of units in <var>s</var>, but at most <var>maxlen</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strnlen.html"><code>strnlen</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcsnlen.html"><code>wcsnlen</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<hr size="6">
<a name="Copying-a-NUL-terminated-Unicode-string"></a>
<a name="SEC24"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC24">4.5.3 Copying a NUL terminated Unicode string</a> </h3>
<p>The following functions copy portions of Unicode strings in memory.
</p>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_strcpy</b><i> (uint8_t *<var>dest</var>, const uint8_t *<var>src</var>)</i>
<a name="IDX90"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_strcpy</b><i> (uint16_t *<var>dest</var>, const uint16_t *<var>src</var>)</i>
<a name="IDX91"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_strcpy</b><i> (uint32_t *<var>dest</var>, const uint32_t *<var>src</var>)</i>
<a name="IDX92"></a>
</dt>
<dd><p>Copies <var>src</var> to <var>dest</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strcpy.html"><code>strcpy</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcscpy.html"><code>wcscpy</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_stpcpy</b><i> (uint8_t *<var>dest</var>, const uint8_t *<var>src</var>)</i>
<a name="IDX93"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_stpcpy</b><i> (uint16_t *<var>dest</var>, const uint16_t *<var>src</var>)</i>
<a name="IDX94"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_stpcpy</b><i> (uint32_t *<var>dest</var>, const uint32_t *<var>src</var>)</i>
<a name="IDX95"></a>
</dt>
<dd><p>Copies <var>src</var> to <var>dest</var>, returning the address of the terminating NUL
in <var>dest</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/stpcpy.html"><code>stpcpy</code></a>, except that it operates on
Unicode strings.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_strncpy</b><i> (uint8_t *<var>dest</var>, const uint8_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX96"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_strncpy</b><i> (uint16_t *<var>dest</var>, const uint16_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX97"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_strncpy</b><i> (uint32_t *<var>dest</var>, const uint32_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX98"></a>
</dt>
<dd><p>Copies no more than <var>n</var> units of <var>src</var> to <var>dest</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strncpy.html"><code>strncpy</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcsncpy.html"><code>wcsncpy</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_stpncpy</b><i> (uint8_t *<var>dest</var>, const uint8_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX99"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_stpncpy</b><i> (uint16_t *<var>dest</var>, const uint16_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX100"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_stpncpy</b><i> (uint32_t *<var>dest</var>, const uint32_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX101"></a>
</dt>
<dd><p>Copies no more than <var>n</var> units of <var>src</var> to <var>dest</var>. Returns a
pointer past the last non-NUL unit written into <var>dest</var>. In other words,
if the units written into <var>dest</var> include a NUL, the return value is the
address of the first such NUL unit, otherwise it is
<code><var>dest</var> + <var>n</var></code>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/stpncpy.html"><code>stpncpy</code></a>, except that it operates on
Unicode strings.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_strcat</b><i> (uint8_t *<var>dest</var>, const uint8_t *<var>src</var>)</i>
<a name="IDX102"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_strcat</b><i> (uint16_t *<var>dest</var>, const uint16_t *<var>src</var>)</i>
<a name="IDX103"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_strcat</b><i> (uint32_t *<var>dest</var>, const uint32_t *<var>src</var>)</i>
<a name="IDX104"></a>
</dt>
<dd><p>Appends <var>src</var> onto <var>dest</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strcat.html"><code>strcat</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcscat.html"><code>wcscat</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_strncat</b><i> (uint8_t *<var>dest</var>, const uint8_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX105"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_strncat</b><i> (uint16_t *<var>dest</var>, const uint16_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX106"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_strncat</b><i> (uint32_t *<var>dest</var>, const uint32_t *<var>src</var>, size_t <var>n</var>)</i>
<a name="IDX107"></a>
</dt>
<dd><p>Appends no more than <var>n</var> units of <var>src</var> onto <var>dest</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strncat.html"><code>strncat</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcsncat.html"><code>wcsncat</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<hr size="6">
<a name="Comparing-NUL-terminated-Unicode-strings"></a>
<a name="SEC25"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC25">4.5.4 Comparing NUL terminated Unicode strings</a> </h3>
<p>The following functions compare two Unicode strings.
They ignore locale-dependent collation rules.
</p>
<dl>
<dt><u>Function:</u> int <b>u8_strcmp</b><i> (const uint8_t *<var>s1</var>, const uint8_t *<var>s2</var>)</i>
<a name="IDX108"></a>
</dt>
<dt><u>Function:</u> int <b>u16_strcmp</b><i> (const uint16_t *<var>s1</var>, const uint16_t *<var>s2</var>)</i>
<a name="IDX109"></a>
</dt>
<dt><u>Function:</u> int <b>u32_strcmp</b><i> (const uint32_t *<var>s1</var>, const uint32_t *<var>s2</var>)</i>
<a name="IDX110"></a>
</dt>
<dd><p>Compares <var>s1</var> and <var>s2</var>, lexicographically.
Returns a negative value if <var>s1</var> compares smaller than <var>s2</var>,
a positive value if <var>s1</var> compares larger than <var>s2</var>, or 0 if
they compare equal.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strcmp.html"><code>strcmp</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcscmp.html"><code>wcscmp</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<a name="IDX111"></a>
<dl>
<dt><u>Function:</u> int <b>u8_strcoll</b><i> (const uint8_t *<var>s1</var>, const uint8_t *<var>s2</var>)</i>
<a name="IDX112"></a>
</dt>
<dt><u>Function:</u> int <b>u16_strcoll</b><i> (const uint16_t *<var>s1</var>, const uint16_t *<var>s2</var>)</i>
<a name="IDX113"></a>
</dt>
<dt><u>Function:</u> int <b>u32_strcoll</b><i> (const uint32_t *<var>s1</var>, const uint32_t *<var>s2</var>)</i>
<a name="IDX114"></a>
</dt>
<dd><p>Compares <var>s1</var> and <var>s2</var> using the collation rules of the current
locale.
Returns -1 if <var>s1</var> < <var>s2</var>, 0 if <var>s1</var> = <var>s2</var>, 1 if
<var>s1</var> > <var>s2</var>. Upon failure, sets <code>errno</code> and returns any value.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strcoll.html"><code>strcoll</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcscoll.html"><code>wcscoll</code></a>, except
that it operates on Unicode strings.
</p>
<p>Note that this function may consider different canonical normalizations
of the same string as having a large distance. It is therefore better to
use the function <code>u8_normcoll</code> instead of this one; see <a href="libunistring_13.html#SEC63">Normalization forms (composition and decomposition) <code><uninorm.h></code></a>.
</p></dd></dl>
<dl>
<dt><u>Function:</u> int <b>u8_strncmp</b><i> (const uint8_t *<var>s1</var>, const uint8_t *<var>s2</var>, size_t <var>n</var>)</i>
<a name="IDX115"></a>
</dt>
<dt><u>Function:</u> int <b>u16_strncmp</b><i> (const uint16_t *<var>s1</var>, const uint16_t *<var>s2</var>, size_t <var>n</var>)</i>
<a name="IDX116"></a>
</dt>
<dt><u>Function:</u> int <b>u32_strncmp</b><i> (const uint32_t *<var>s1</var>, const uint32_t *<var>s2</var>, size_t <var>n</var>)</i>
<a name="IDX117"></a>
</dt>
<dd><p>Compares no more than <var>n</var> units of <var>s1</var> and <var>s2</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strncmp.html"><code>strncmp</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcsncmp.html"><code>wcsncmp</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<hr size="6">
<a name="Duplicating-a-NUL-terminated-Unicode-string"></a>
<a name="SEC26"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC26">4.5.5 Duplicating a NUL terminated Unicode string</a> </h3>
<p>The following function allocates a duplicate of a Unicode string.
</p>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_strdup</b><i> (const uint8_t *<var>s</var>)</i>
<a name="IDX118"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_strdup</b><i> (const uint16_t *<var>s</var>)</i>
<a name="IDX119"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_strdup</b><i> (const uint32_t *<var>s</var>)</i>
<a name="IDX120"></a>
</dt>
<dd><p>Duplicates <var>s</var>, returning an identical malloc'd string.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strdup.html"><code>strdup</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcsdup.html"><code>wcsdup</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<hr size="6">
<a name="Searching-for-a-character-in-a-NUL-terminated-Unicode-string"></a>
<a name="SEC27"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC27">4.5.6 Searching for a character in a NUL terminated Unicode string</a> </h3>
<p>The following functions search for a given Unicode character.
</p>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_strchr</b><i> (const uint8_t *<var>str</var>, ucs4_t <var>uc</var>)</i>
<a name="IDX121"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_strchr</b><i> (const uint16_t *<var>str</var>, ucs4_t <var>uc</var>)</i>
<a name="IDX122"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_strchr</b><i> (const uint32_t *<var>str</var>, ucs4_t <var>uc</var>)</i>
<a name="IDX123"></a>
</dt>
<dd><p>Finds the first occurrence of <var>uc</var> in <var>str</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strchr.html"><code>strchr</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcschr.html"><code>wcschr</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_strrchr</b><i> (const uint8_t *<var>str</var>, ucs4_t <var>uc</var>)</i>
<a name="IDX124"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_strrchr</b><i> (const uint16_t *<var>str</var>, ucs4_t <var>uc</var>)</i>
<a name="IDX125"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_strrchr</b><i> (const uint32_t *<var>str</var>, ucs4_t <var>uc</var>)</i>
<a name="IDX126"></a>
</dt>
<dd><p>Finds the last occurrence of <var>uc</var> in <var>str</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strrchr.html"><code>strrchr</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcsrchr.html"><code>wcsrchr</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<p>The following functions search for the first occurrence of some Unicode
character in or outside a given set of Unicode characters.
</p>
<dl>
<dt><u>Function:</u> size_t <b>u8_strcspn</b><i> (const uint8_t *<var>str</var>, const uint8_t *<var>reject</var>)</i>
<a name="IDX127"></a>
</dt>
<dt><u>Function:</u> size_t <b>u16_strcspn</b><i> (const uint16_t *<var>str</var>, const uint16_t *<var>reject</var>)</i>
<a name="IDX128"></a>
</dt>
<dt><u>Function:</u> size_t <b>u32_strcspn</b><i> (const uint32_t *<var>str</var>, const uint32_t *<var>reject</var>)</i>
<a name="IDX129"></a>
</dt>
<dd><p>Returns the length of the initial segment of <var>str</var> which consists entirely
of Unicode characters not in <var>reject</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strcspn.html"><code>strcspn</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcscspn.html"><code>wcscspn</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<dl>
<dt><u>Function:</u> size_t <b>u8_strspn</b><i> (const uint8_t *<var>str</var>, const uint8_t *<var>accept</var>)</i>
<a name="IDX130"></a>
</dt>
<dt><u>Function:</u> size_t <b>u16_strspn</b><i> (const uint16_t *<var>str</var>, const uint16_t *<var>accept</var>)</i>
<a name="IDX131"></a>
</dt>
<dt><u>Function:</u> size_t <b>u32_strspn</b><i> (const uint32_t *<var>str</var>, const uint32_t *<var>accept</var>)</i>
<a name="IDX132"></a>
</dt>
<dd><p>Returns the length of the initial segment of <var>str</var> which consists entirely
of Unicode characters in <var>accept</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strspn.html"><code>strspn</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcsspn.html"><code>wcsspn</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_strpbrk</b><i> (const uint8_t *<var>str</var>, const uint8_t *<var>accept</var>)</i>
<a name="IDX133"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_strpbrk</b><i> (const uint16_t *<var>str</var>, const uint16_t *<var>accept</var>)</i>
<a name="IDX134"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_strpbrk</b><i> (const uint32_t *<var>str</var>, const uint32_t *<var>accept</var>)</i>
<a name="IDX135"></a>
</dt>
<dd><p>Finds the first occurrence in <var>str</var> of any character in <var>accept</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strpbrk.html"><code>strpbrk</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcspbrk.html"><code>wcspbrk</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<hr size="6">
<a name="Searching-for-a-substring"></a>
<a name="SEC28"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC28">4.5.7 Searching for a substring in a NUL terminated Unicode string</a> </h3>
<p>The following functions search whether a given Unicode string is a substring
of another Unicode string.
</p>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_strstr</b><i> (const uint8_t *<var>haystack</var>, const uint8_t *<var>needle</var>)</i>
<a name="IDX136"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_strstr</b><i> (const uint16_t *<var>haystack</var>, const uint16_t *<var>needle</var>)</i>
<a name="IDX137"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_strstr</b><i> (const uint32_t *<var>haystack</var>, const uint32_t *<var>needle</var>)</i>
<a name="IDX138"></a>
</dt>
<dd><p>Finds the first occurrence of <var>needle</var> in <var>haystack</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strstr.html"><code>strstr</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcsstr.html"><code>wcsstr</code></a>, except
that it operates on Unicode strings.
</p></dd></dl>
<dl>
<dt><u>Function:</u> bool <b>u8_startswith</b><i> (const uint8_t *<var>str</var>, const uint8_t *<var>prefix</var>)</i>
<a name="IDX139"></a>
</dt>
<dt><u>Function:</u> bool <b>u16_startswith</b><i> (const uint16_t *<var>str</var>, const uint16_t *<var>prefix</var>)</i>
<a name="IDX140"></a>
</dt>
<dt><u>Function:</u> bool <b>u32_startswith</b><i> (const uint32_t *<var>str</var>, const uint32_t *<var>prefix</var>)</i>
<a name="IDX141"></a>
</dt>
<dd><p>Tests whether <var>str</var> starts with <var>prefix</var>.
</p></dd></dl>
<dl>
<dt><u>Function:</u> bool <b>u8_endswith</b><i> (const uint8_t *<var>str</var>, const uint8_t *<var>suffix</var>)</i>
<a name="IDX142"></a>
</dt>
<dt><u>Function:</u> bool <b>u16_endswith</b><i> (const uint16_t *<var>str</var>, const uint16_t *<var>suffix</var>)</i>
<a name="IDX143"></a>
</dt>
<dt><u>Function:</u> bool <b>u32_endswith</b><i> (const uint32_t *<var>str</var>, const uint32_t *<var>suffix</var>)</i>
<a name="IDX144"></a>
</dt>
<dd><p>Tests whether <var>str</var> ends with <var>suffix</var>.
</p></dd></dl>
<hr size="6">
<a name="Tokenizing"></a>
<a name="SEC29"></a>
<h3 class="subsection"> <a href="libunistring_toc.html#TOC29">4.5.8 Tokenizing a NUL terminated Unicode string</a> </h3>
<p>The following function does one step in tokenizing a Unicode string.
</p>
<dl>
<dt><u>Function:</u> uint8_t * <b>u8_strtok</b><i> (uint8_t *<var>str</var>, const uint8_t *<var>delim</var>, uint8_t **<var>ptr</var>)</i>
<a name="IDX145"></a>
</dt>
<dt><u>Function:</u> uint16_t * <b>u16_strtok</b><i> (uint16_t *<var>str</var>, const uint16_t *<var>delim</var>, uint16_t **<var>ptr</var>)</i>
<a name="IDX146"></a>
</dt>
<dt><u>Function:</u> uint32_t * <b>u32_strtok</b><i> (uint32_t *<var>str</var>, const uint32_t *<var>delim</var>, uint32_t **<var>ptr</var>)</i>
<a name="IDX147"></a>
</dt>
<dd><p>Divides <var>str</var> into tokens separated by characters in <var>delim</var>.
</p>
<p>This function is similar to <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/strtok_r.html"><code>strtok_r</code></a> and <a href="http://pubs.opengroup.org/onlinepubs/9699919799/functions/wcstok.html"><code>wcstok</code></a>, except
that it operates on Unicode strings. Its interface is actually more similar to
<code>wcstok</code> than to <code>strtok</code>.
</p></dd></dl>
<hr size="6">
<table cellpadding="1" cellspacing="1" border="0">
<tr><td valign="middle" align="left">[<a href="#SEC10" title="Beginning of this chapter or previous chapter"> << </a>]</td>
<td valign="middle" align="left">[<a href="libunistring_5.html#SEC30" title="Next chapter"> >> </a>]</td>
<td valign="middle" align="left"> </td>
<td valign="middle" align="left"> </td>
<td valign="middle" align="left"> </td>
<td valign="middle" align="left"> </td>
<td valign="middle" align="left"> </td>
<td valign="middle" align="left">[<a href="libunistring_toc.html#SEC_Top" title="Cover (top) of document">Top</a>]</td>
<td valign="middle" align="left">[<a href="libunistring_toc.html#SEC_Contents" title="Table of contents">Contents</a>]</td>
<td valign="middle" align="left">[<a href="libunistring_21.html#SEC94" title="Index">Index</a>]</td>
<td valign="middle" align="left">[<a href="libunistring_abt.html#SEC_About" title="About (help)"> ? </a>]</td>
</tr></table>
<p>
<font size="-1">
This document was generated by <em>Bruno Haible</em> on <em>February, 24 2024</em> using <a href="https://www.nongnu.org/texi2html/"><em>texi2html 1.78a</em></a>.
</font>
<br>
</p>
</body>
</html>
|
