summary refs log tree commit diff
path: root/manual/string.texi
blob: b8810d66b763dab3c431a38c083b8cb2cfac2da8 (plain) (blame)
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
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
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
@node String and Array Utilities, Character Set Handling, Character Handling, Top
@c %MENU% Utilities for copying and comparing strings and arrays
@chapter String and Array Utilities

Operations on strings (null-terminated byte sequences) are an important part of
many programs.  @Theglibc{} provides an extensive set of string
utility functions, including functions for copying, concatenating,
comparing, and searching strings.  Many of these functions can also
operate on arbitrary regions of storage; for example, the @code{memcpy}
function can be used to copy the contents of any kind of array.

It's fairly common for beginning C programmers to ``reinvent the wheel''
by duplicating this functionality in their own code, but it pays to
become familiar with the library functions and to make use of them,
since this offers benefits in maintenance, efficiency, and portability.

For instance, you could easily compare one string to another in two
lines of C code, but if you use the built-in @code{strcmp} function,
you're less likely to make a mistake.  And, since these library
functions are typically highly optimized, your program may run faster
too.

@menu
* Representation of Strings::   Introduction to basic concepts.
* String/Array Conventions::    Whether to use a string function or an
				 arbitrary array function.
* String Length::               Determining the length of a string.
* Copying Strings and Arrays::  Functions to copy strings and arrays.
* Concatenating Strings::       Functions to concatenate strings while copying.
* Truncating Strings::          Functions to truncate strings while copying.
* String/Array Comparison::     Functions for byte-wise and character-wise
				 comparison.
* Collation Functions::         Functions for collating strings.
* Search Functions::            Searching for a specific element or substring.
* Finding Tokens in a String::  Splitting a string into tokens by looking
				 for delimiters.
* Erasing Sensitive Data::      Clearing memory which contains sensitive
                                 data, after it's no longer needed.
* strfry::                      Function for flash-cooking a string.
* Trivial Encryption::          Obscuring data.
* Encode Binary Data::          Encoding and Decoding of Binary Data.
* Argz and Envz Vectors::       Null-separated string vectors.
@end menu

@node Representation of Strings
@section Representation of Strings
@cindex string, representation of

This section is a quick summary of string concepts for beginning C
programmers.  It describes how strings are represented in C
and some common pitfalls.  If you are already familiar with this
material, you can skip this section.

@cindex string
A @dfn{string} is a null-terminated array of bytes of type @code{char},
including the terminating null byte.  String-valued
variables are usually declared to be pointers of type @code{char *}.
Such variables do not include space for the text of a string; that has
to be stored somewhere else---in an array variable, a string constant,
or dynamically allocated memory (@pxref{Memory Allocation}).  It's up to
you to store the address of the chosen memory space into the pointer
variable.  Alternatively you can store a @dfn{null pointer} in the
pointer variable.  The null pointer does not point anywhere, so
attempting to reference the string it points to gets an error.

@cindex multibyte character
@cindex multibyte string
@cindex wide string
A @dfn{multibyte character} is a sequence of one or more bytes that
represents a single character using the locale's encoding scheme; a
null byte always represents the null character.  A @dfn{multibyte
string} is a string that consists entirely of multibyte
characters.  In contrast, a @dfn{wide string} is a null-terminated
sequence of @code{wchar_t} objects.  A wide-string variable is usually
declared to be a pointer of type @code{wchar_t *}, by analogy with
string variables and @code{char *}.  @xref{Extended Char Intro}.

@cindex null byte
@cindex null wide character
By convention, the @dfn{null byte}, @code{'\0'},
marks the end of a string and the @dfn{null wide character},
@code{L'\0'}, marks the end of a wide string.  For example, in
testing to see whether the @code{char *} variable @var{p} points to a
null byte marking the end of a string, you can write
@code{!*@var{p}} or @code{*@var{p} == '\0'}.

A null byte is quite different conceptually from a null pointer,
although both are represented by the integer constant @code{0}.

@cindex string literal
A @dfn{string literal} appears in C program source as a multibyte
string between double-quote characters (@samp{"}).  If the
initial double-quote character is immediately preceded by a capital
@samp{L} (ell) character (as in @code{L"foo"}), it is a wide string
literal.  String literals can also contribute to @dfn{string
concatenation}: @code{"a" "b"} is the same as @code{"ab"}.
For wide strings one can use either
@code{L"a" L"b"} or @code{L"a" "b"}.  Modification of string literals is
not allowed by the GNU C compiler, because literals are placed in
read-only storage.

Arrays that are declared @code{const} cannot be modified
either.  It's generally good style to declare non-modifiable string
pointers to be of type @code{const char *}, since this often allows the
C compiler to detect accidental modifications as well as providing some
amount of documentation about what your program intends to do with the
string.

The amount of memory allocated for a byte array may extend past the null byte
that marks the end of the string that the array contains.  In this
document, the term @dfn{allocated size} is always used to refer to the
total amount of memory allocated for an array, while the term
@dfn{length} refers to the number of bytes up to (but not including)
the terminating null byte.  Wide strings are similar, except their
sizes and lengths count wide characters, not bytes.
@cindex length of string
@cindex allocation size of string
@cindex size of string
@cindex string length
@cindex string allocation

A notorious source of program bugs is trying to put more bytes into a
string than fit in its allocated size.  When writing code that extends
strings or moves bytes into a pre-allocated array, you should be
very careful to keep track of the length of the text and make explicit
checks for overflowing the array.  Many of the library functions
@emph{do not} do this for you!  Remember also that you need to allocate
an extra byte to hold the null byte that marks the end of the
string.

@cindex single-byte string
@cindex multibyte string
Originally strings were sequences of bytes where each byte represented a
single character.  This is still true today if the strings are encoded
using a single-byte character encoding.  Things are different if the
strings are encoded using a multibyte encoding (for more information on
encodings see @ref{Extended Char Intro}).  There is no difference in
the programming interface for these two kind of strings; the programmer
has to be aware of this and interpret the byte sequences accordingly.

But since there is no separate interface taking care of these
differences the byte-based string functions are sometimes hard to use.
Since the count parameters of these functions specify bytes a call to
@code{memcpy} could cut a multibyte character in the middle and put an
incomplete (and therefore unusable) byte sequence in the target buffer.

@cindex wide string
To avoid these problems later versions of the @w{ISO C} standard
introduce a second set of functions which are operating on @dfn{wide
characters} (@pxref{Extended Char Intro}).  These functions don't have
the problems the single-byte versions have since every wide character is
a legal, interpretable value.  This does not mean that cutting wide
strings at arbitrary points is without problems.  It normally
is for alphabet-based languages (except for non-normalized text) but
languages based on syllables still have the problem that more than one
wide character is necessary to complete a logical unit.  This is a
higher level problem which the @w{C library} functions are not designed
to solve.  But it is at least good that no invalid byte sequences can be
created.  Also, the higher level functions can also much more easily operate
on wide characters than on multibyte characters so that a common strategy
is to use wide characters internally whenever text is more than simply
copied.

The remaining of this chapter will discuss the functions for handling
wide strings in parallel with the discussion of
strings since there is almost always an exact equivalent
available.

@node String/Array Conventions
@section String and Array Conventions

This chapter describes both functions that work on arbitrary arrays or
blocks of memory, and functions that are specific to strings and wide
strings.

Functions that operate on arbitrary blocks of memory have names
beginning with @samp{mem} and @samp{wmem} (such as @code{memcpy} and
@code{wmemcpy}) and invariably take an argument which specifies the size
(in bytes and wide characters respectively) of the block of memory to
operate on.  The array arguments and return values for these functions
have type @code{void *} or @code{wchar_t}.  As a matter of style, the
elements of the arrays used with the @samp{mem} functions are referred
to as ``bytes''.  You can pass any kind of pointer to these functions,
and the @code{sizeof} operator is useful in computing the value for the
size argument.  Parameters to the @samp{wmem} functions must be of type
@code{wchar_t *}.  These functions are not really usable with anything
but arrays of this type.

In contrast, functions that operate specifically on strings and wide
strings have names beginning with @samp{str} and @samp{wcs}
respectively (such as @code{strcpy} and @code{wcscpy}) and look for a
terminating null byte or null wide character instead of requiring an explicit
size argument to be passed.  (Some of these functions accept a specified
maximum length, but they also check for premature termination.)
The array arguments and return values for these
functions have type @code{char *} and @code{wchar_t *} respectively, and
the array elements are referred to as ``bytes'' and ``wide
characters''.

In many cases, there are both @samp{mem} and @samp{str}/@samp{wcs}
versions of a function.  The one that is more appropriate to use depends
on the exact situation.  When your program is manipulating arbitrary
arrays or blocks of storage, then you should always use the @samp{mem}
functions.  On the other hand, when you are manipulating
strings it is usually more convenient to use the @samp{str}/@samp{wcs}
functions, unless you already know the length of the string in advance.
The @samp{wmem} functions should be used for wide character arrays with
known size.

@cindex wint_t
@cindex parameter promotion
Some of the memory and string functions take single characters as
arguments.  Since a value of type @code{char} is automatically promoted
into a value of type @code{int} when used as a parameter, the functions
are declared with @code{int} as the type of the parameter in question.
In case of the wide character functions the situation is similar: the
parameter type for a single wide character is @code{wint_t} and not
@code{wchar_t}.  This would for many implementations not be necessary
since @code{wchar_t} is large enough to not be automatically
promoted, but since the @w{ISO C} standard does not require such a
choice of types the @code{wint_t} type is used.

@node String Length
@section String Length

You can get the length of a string using the @code{strlen} function.
This function is declared in the header file @file{string.h}.
@pindex string.h

@comment string.h
@comment ISO
@deftypefun size_t strlen (const char *@var{s})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{strlen} function returns the length of the
string @var{s} in bytes.  (In other words, it returns the offset of the
terminating null byte within the array.)

For example,
@smallexample
strlen ("hello, world")
    @result{} 12
@end smallexample

When applied to an array, the @code{strlen} function returns
the length of the string stored there, not its allocated size.  You can
get the allocated size of the array that holds a string using
the @code{sizeof} operator:

@smallexample
char string[32] = "hello, world";
sizeof (string)
    @result{} 32
strlen (string)
    @result{} 12
@end smallexample

But beware, this will not work unless @var{string} is the
array itself, not a pointer to it.  For example:

@smallexample
char string[32] = "hello, world";
char *ptr = string;
sizeof (string)
    @result{} 32
sizeof (ptr)
    @result{} 4  /* @r{(on a machine with 4 byte pointers)} */
@end smallexample

This is an easy mistake to make when you are working with functions that
take string arguments; those arguments are always pointers, not arrays.

It must also be noted that for multibyte encoded strings the return
value does not have to correspond to the number of characters in the
string.  To get this value the string can be converted to wide
characters and @code{wcslen} can be used or something like the following
code can be used:

@smallexample
/* @r{The input is in @code{string}.}
   @r{The length is expected in @code{n}.}  */
@{
  mbstate_t t;
  char *scopy = string;
  /* In initial state.  */
  memset (&t, '\0', sizeof (t));
  /* Determine number of characters.  */
  n = mbsrtowcs (NULL, &scopy, strlen (scopy), &t);
@}
@end smallexample

This is cumbersome to do so if the number of characters (as opposed to
bytes) is needed often it is better to work with wide characters.
@end deftypefun

The wide character equivalent is declared in @file{wchar.h}.

@comment wchar.h
@comment ISO
@deftypefun size_t wcslen (const wchar_t *@var{ws})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{wcslen} function is the wide character equivalent to
@code{strlen}.  The return value is the number of wide characters in the
wide string pointed to by @var{ws} (this is also the offset of
the terminating null wide character of @var{ws}).

Since there are no multi wide character sequences making up one wide
character the return value is not only the offset in the array, it is
also the number of wide characters.

This function was introduced in @w{Amendment 1} to @w{ISO C90}.
@end deftypefun

@comment string.h
@comment GNU
@deftypefun size_t strnlen (const char *@var{s}, size_t @var{maxlen})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
If the array @var{s} of size @var{maxlen} contains a null byte,
the @code{strnlen} function returns the length of the string @var{s} in
bytes.  Otherwise it
returns @var{maxlen}.  Therefore this function is equivalent to
@code{(strlen (@var{s}) < @var{maxlen} ? strlen (@var{s}) : @var{maxlen})}
but it
is more efficient and works even if @var{s} is not null-terminated so
long as @var{maxlen} does not exceed the size of @var{s}'s array.

@smallexample
char string[32] = "hello, world";
strnlen (string, 32)
    @result{} 12
strnlen (string, 5)
    @result{} 5
@end smallexample

This function is a GNU extension and is declared in @file{string.h}.
@end deftypefun

@comment wchar.h
@comment GNU
@deftypefun size_t wcsnlen (const wchar_t *@var{ws}, size_t @var{maxlen})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
@code{wcsnlen} is the wide character equivalent to @code{strnlen}.  The
@var{maxlen} parameter specifies the maximum number of wide characters.

This function is a GNU extension and is declared in @file{wchar.h}.
@end deftypefun

@node Copying Strings and Arrays
@section Copying Strings and Arrays

You can use the functions described in this section to copy the contents
of strings, wide strings, and arrays.  The @samp{str} and @samp{mem}
functions are declared in @file{string.h} while the @samp{w} functions
are declared in @file{wchar.h}.
@pindex string.h
@pindex wchar.h
@cindex copying strings and arrays
@cindex string copy functions
@cindex array copy functions
@cindex concatenating strings
@cindex string concatenation functions

A helpful way to remember the ordering of the arguments to the functions
in this section is that it corresponds to an assignment expression, with
the destination array specified to the left of the source array.  Most
of these functions return the address of the destination array; a few
return the address of the destination's terminating null, or of just
past the destination.

Most of these functions do not work properly if the source and
destination arrays overlap.  For example, if the beginning of the
destination array overlaps the end of the source array, the original
contents of that part of the source array may get overwritten before it
is copied.  Even worse, in the case of the string functions, the null
byte marking the end of the string may be lost, and the copy
function might get stuck in a loop trashing all the memory allocated to
your program.

All functions that have problems copying between overlapping arrays are
explicitly identified in this manual.  In addition to functions in this
section, there are a few others like @code{sprintf} (@pxref{Formatted
Output Functions}) and @code{scanf} (@pxref{Formatted Input
Functions}).

@comment string.h
@comment ISO
@deftypefun {void *} memcpy (void *restrict @var{to}, const void *restrict @var{from}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{memcpy} function copies @var{size} bytes from the object
beginning at @var{from} into the object beginning at @var{to}.  The
behavior of this function is undefined if the two arrays @var{to} and
@var{from} overlap; use @code{memmove} instead if overlapping is possible.

The value returned by @code{memcpy} is the value of @var{to}.

Here is an example of how you might use @code{memcpy} to copy the
contents of an array:

@smallexample
struct foo *oldarray, *newarray;
int arraysize;
@dots{}
memcpy (new, old, arraysize * sizeof (struct foo));
@end smallexample
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wmemcpy (wchar_t *restrict @var{wto}, const wchar_t *restrict @var{wfrom}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{wmemcpy} function copies @var{size} wide characters from the object
beginning at @var{wfrom} into the object beginning at @var{wto}.  The
behavior of this function is undefined if the two arrays @var{wto} and
@var{wfrom} overlap; use @code{wmemmove} instead if overlapping is possible.

The following is a possible implementation of @code{wmemcpy} but there
are more optimizations possible.

@smallexample
wchar_t *
wmemcpy (wchar_t *restrict wto, const wchar_t *restrict wfrom,
         size_t size)
@{
  return (wchar_t *) memcpy (wto, wfrom, size * sizeof (wchar_t));
@}
@end smallexample

The value returned by @code{wmemcpy} is the value of @var{wto}.

This function was introduced in @w{Amendment 1} to @w{ISO C90}.
@end deftypefun

@comment string.h
@comment GNU
@deftypefun {void *} mempcpy (void *restrict @var{to}, const void *restrict @var{from}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{mempcpy} function is nearly identical to the @code{memcpy}
function.  It copies @var{size} bytes from the object beginning at
@code{from} into the object pointed to by @var{to}.  But instead of
returning the value of @var{to} it returns a pointer to the byte
following the last written byte in the object beginning at @var{to}.
I.e., the value is @code{((void *) ((char *) @var{to} + @var{size}))}.

This function is useful in situations where a number of objects shall be
copied to consecutive memory positions.

@smallexample
void *
combine (void *o1, size_t s1, void *o2, size_t s2)
@{
  void *result = malloc (s1 + s2);
  if (result != NULL)
    mempcpy (mempcpy (result, o1, s1), o2, s2);
  return result;
@}
@end smallexample

This function is a GNU extension.
@end deftypefun

@comment wchar.h
@comment GNU
@deftypefun {wchar_t *} wmempcpy (wchar_t *restrict @var{wto}, const wchar_t *restrict @var{wfrom}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{wmempcpy} function is nearly identical to the @code{wmemcpy}
function.  It copies @var{size} wide characters from the object
beginning at @code{wfrom} into the object pointed to by @var{wto}.  But
instead of returning the value of @var{wto} it returns a pointer to the
wide character following the last written wide character in the object
beginning at @var{wto}.  I.e., the value is @code{@var{wto} + @var{size}}.

This function is useful in situations where a number of objects shall be
copied to consecutive memory positions.

The following is a possible implementation of @code{wmemcpy} but there
are more optimizations possible.

@smallexample
wchar_t *
wmempcpy (wchar_t *restrict wto, const wchar_t *restrict wfrom,
          size_t size)
@{
  return (wchar_t *) mempcpy (wto, wfrom, size * sizeof (wchar_t));
@}
@end smallexample

This function is a GNU extension.
@end deftypefun

@comment string.h
@comment ISO
@deftypefun {void *} memmove (void *@var{to}, const void *@var{from}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
@code{memmove} copies the @var{size} bytes at @var{from} into the
@var{size} bytes at @var{to}, even if those two blocks of space
overlap.  In the case of overlap, @code{memmove} is careful to copy the
original values of the bytes in the block at @var{from}, including those
bytes which also belong to the block at @var{to}.

The value returned by @code{memmove} is the value of @var{to}.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wmemmove (wchar_t *@var{wto}, const wchar_t *@var{wfrom}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
@code{wmemmove} copies the @var{size} wide characters at @var{wfrom}
into the @var{size} wide characters at @var{wto}, even if those two
blocks of space overlap.  In the case of overlap, @code{wmemmove} is
careful to copy the original values of the wide characters in the block
at @var{wfrom}, including those wide characters which also belong to the
block at @var{wto}.

The following is a possible implementation of @code{wmemcpy} but there
are more optimizations possible.

@smallexample
wchar_t *
wmempcpy (wchar_t *restrict wto, const wchar_t *restrict wfrom,
          size_t size)
@{
  return (wchar_t *) mempcpy (wto, wfrom, size * sizeof (wchar_t));
@}
@end smallexample

The value returned by @code{wmemmove} is the value of @var{wto}.

This function is a GNU extension.
@end deftypefun

@comment string.h
@comment SVID
@deftypefun {void *} memccpy (void *restrict @var{to}, const void *restrict @var{from}, int @var{c}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function copies no more than @var{size} bytes from @var{from} to
@var{to}, stopping if a byte matching @var{c} is found.  The return
value is a pointer into @var{to} one byte past where @var{c} was copied,
or a null pointer if no byte matching @var{c} appeared in the first
@var{size} bytes of @var{from}.
@end deftypefun

@comment string.h
@comment ISO
@deftypefun {void *} memset (void *@var{block}, int @var{c}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function copies the value of @var{c} (converted to an
@code{unsigned char}) into each of the first @var{size} bytes of the
object beginning at @var{block}.  It returns the value of @var{block}.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wmemset (wchar_t *@var{block}, wchar_t @var{wc}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function copies the value of @var{wc} into each of the first
@var{size} wide characters of the object beginning at @var{block}.  It
returns the value of @var{block}.
@end deftypefun

@comment string.h
@comment ISO
@deftypefun {char *} strcpy (char *restrict @var{to}, const char *restrict @var{from})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This copies bytes from the string @var{from} (up to and including
the terminating null byte) into the string @var{to}.  Like
@code{memcpy}, this function has undefined results if the strings
overlap.  The return value is the value of @var{to}.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wcscpy (wchar_t *restrict @var{wto}, const wchar_t *restrict @var{wfrom})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This copies wide characters from the wide string @var{wfrom} (up to and
including the terminating null wide character) into the string
@var{wto}.  Like @code{wmemcpy}, this function has undefined results if
the strings overlap.  The return value is the value of @var{wto}.
@end deftypefun

@comment SVID
@deftypefun {char *} strdup (const char *@var{s})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
This function copies the string @var{s} into a newly
allocated string.  The string is allocated using @code{malloc}; see
@ref{Unconstrained Allocation}.  If @code{malloc} cannot allocate space
for the new string, @code{strdup} returns a null pointer.  Otherwise it
returns a pointer to the new string.
@end deftypefun

@comment wchar.h
@comment GNU
@deftypefun {wchar_t *} wcsdup (const wchar_t *@var{ws})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
This function copies the wide string @var{ws}
into a newly allocated string.  The string is allocated using
@code{malloc}; see @ref{Unconstrained Allocation}.  If @code{malloc}
cannot allocate space for the new string, @code{wcsdup} returns a null
pointer.  Otherwise it returns a pointer to the new wide string.

This function is a GNU extension.
@end deftypefun

@comment string.h
@comment Unknown origin
@deftypefun {char *} stpcpy (char *restrict @var{to}, const char *restrict @var{from})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function is like @code{strcpy}, except that it returns a pointer to
the end of the string @var{to} (that is, the address of the terminating
null byte @code{to + strlen (from)}) rather than the beginning.

For example, this program uses @code{stpcpy} to concatenate @samp{foo}
and @samp{bar} to produce @samp{foobar}, which it then prints.

@smallexample
@include stpcpy.c.texi
@end smallexample

This function is part of POSIX.1-2008 and later editions, but was
available in @theglibc{} and other systems as an extension long before
it was standardized.

Its behavior is undefined if the strings overlap.  The function is
declared in @file{string.h}.
@end deftypefun

@comment wchar.h
@comment GNU
@deftypefun {wchar_t *} wcpcpy (wchar_t *restrict @var{wto}, const wchar_t *restrict @var{wfrom})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function is like @code{wcscpy}, except that it returns a pointer to
the end of the string @var{wto} (that is, the address of the terminating
null wide character @code{wto + wcslen (wfrom)}) rather than the beginning.

This function is not part of ISO or POSIX but was found useful while
developing @theglibc{} itself.

The behavior of @code{wcpcpy} is undefined if the strings overlap.

@code{wcpcpy} is a GNU extension and is declared in @file{wchar.h}.
@end deftypefun

@comment string.h
@comment GNU
@deftypefn {Macro} {char *} strdupa (const char *@var{s})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This macro is similar to @code{strdup} but allocates the new string
using @code{alloca} instead of @code{malloc} (@pxref{Variable Size
Automatic}).  This means of course the returned string has the same
limitations as any block of memory allocated using @code{alloca}.

For obvious reasons @code{strdupa} is implemented only as a macro;
you cannot get the address of this function.  Despite this limitation
it is a useful function.  The following code shows a situation where
using @code{malloc} would be a lot more expensive.

@smallexample
@include strdupa.c.texi
@end smallexample

Please note that calling @code{strtok} using @var{path} directly is
invalid.  It is also not allowed to call @code{strdupa} in the argument
list of @code{strtok} since @code{strdupa} uses @code{alloca}
(@pxref{Variable Size Automatic}) can interfere with the parameter
passing.

This function is only available if GNU CC is used.
@end deftypefn

@comment string.h
@comment BSD
@deftypefun void bcopy (const void *@var{from}, void *@var{to}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This is a partially obsolete alternative for @code{memmove}, derived from
BSD.  Note that it is not quite equivalent to @code{memmove}, because the
arguments are not in the same order and there is no return value.
@end deftypefun

@comment string.h
@comment BSD
@deftypefun void bzero (void *@var{block}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This is a partially obsolete alternative for @code{memset}, derived from
BSD.  Note that it is not as general as @code{memset}, because the only
value it can store is zero.
@end deftypefun

@node Concatenating Strings
@section Concatenating Strings
@pindex string.h
@pindex wchar.h
@cindex concatenating strings
@cindex string concatenation functions

The functions described in this section concatenate the contents of a
string or wide string to another.  They follow the string-copying
functions in their conventions.  @xref{Copying Strings and Arrays}.
@samp{strcat} is declared in the header file @file{string.h} while
@samp{wcscat} is declared in @file{wchar.h}.

@comment string.h
@comment ISO
@deftypefun {char *} strcat (char *restrict @var{to}, const char *restrict @var{from})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{strcat} function is similar to @code{strcpy}, except that the
bytes from @var{from} are concatenated or appended to the end of
@var{to}, instead of overwriting it.  That is, the first byte from
@var{from} overwrites the null byte marking the end of @var{to}.

An equivalent definition for @code{strcat} would be:

@smallexample
char *
strcat (char *restrict to, const char *restrict from)
@{
  strcpy (to + strlen (to), from);
  return to;
@}
@end smallexample

This function has undefined results if the strings overlap.

As noted below, this function has significant performance issues.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wcscat (wchar_t *restrict @var{wto}, const wchar_t *restrict @var{wfrom})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{wcscat} function is similar to @code{wcscpy}, except that the
wide characters from @var{wfrom} are concatenated or appended to the end of
@var{wto}, instead of overwriting it.  That is, the first wide character from
@var{wfrom} overwrites the null wide character marking the end of @var{wto}.

An equivalent definition for @code{wcscat} would be:

@smallexample
wchar_t *
wcscat (wchar_t *wto, const wchar_t *wfrom)
@{
  wcscpy (wto + wcslen (wto), wfrom);
  return wto;
@}
@end smallexample

This function has undefined results if the strings overlap.

As noted below, this function has significant performance issues.
@end deftypefun

Programmers using the @code{strcat} or @code{wcscat} function (or the
@code{strncat} or @code{wcsncat} functions defined in
a later section, for that matter)
can easily be recognized as lazy and reckless.  In almost all situations
the lengths of the participating strings are known (it better should be
since how can one otherwise ensure the allocated size of the buffer is
sufficient?)  Or at least, one could know them if one keeps track of the
results of the various function calls.  But then it is very inefficient
to use @code{strcat}/@code{wcscat}.  A lot of time is wasted finding the
end of the destination string so that the actual copying can start.
This is a common example:

@cindex va_copy
@smallexample
/* @r{This function concatenates arbitrarily many strings.  The last}
   @r{parameter must be @code{NULL}.}  */
char *
concat (const char *str, @dots{})
@{
  va_list ap, ap2;
  size_t total = 1;
  const char *s;
  char *result;

  va_start (ap, str);
  va_copy (ap2, ap);

  /* @r{Determine how much space we need.}  */
  for (s = str; s != NULL; s = va_arg (ap, const char *))
    total += strlen (s);

  va_end (ap);

  result = (char *) malloc (total);
  if (result != NULL)
    @{
      result[0] = '\0';

      /* @r{Copy the strings.}  */
      for (s = str; s != NULL; s = va_arg (ap2, const char *))
        strcat (result, s);
    @}

  va_end (ap2);

  return result;
@}
@end smallexample

This looks quite simple, especially the second loop where the strings
are actually copied.  But these innocent lines hide a major performance
penalty.  Just imagine that ten strings of 100 bytes each have to be
concatenated.  For the second string we search the already stored 100
bytes for the end of the string so that we can append the next string.
For all strings in total the comparisons necessary to find the end of
the intermediate results sums up to 5500!  If we combine the copying
with the search for the allocation we can write this function more
efficiently:

@smallexample
char *
concat (const char *str, @dots{})
@{
  va_list ap;
  size_t allocated = 100;
  char *result = (char *) malloc (allocated);

  if (result != NULL)
    @{
      char *newp;
      char *wp;
      const char *s;

      va_start (ap, str);

      wp = result;
      for (s = str; s != NULL; s = va_arg (ap, const char *))
        @{
          size_t len = strlen (s);

          /* @r{Resize the allocated memory if necessary.}  */
          if (wp + len + 1 > result + allocated)
            @{
              allocated = (allocated + len) * 2;
              newp = (char *) realloc (result, allocated);
              if (newp == NULL)
                @{
                  free (result);
                  return NULL;
                @}
              wp = newp + (wp - result);
              result = newp;
            @}

          wp = mempcpy (wp, s, len);
        @}

      /* @r{Terminate the result string.}  */
      *wp++ = '\0';

      /* @r{Resize memory to the optimal size.}  */
      newp = realloc (result, wp - result);
      if (newp != NULL)
        result = newp;

      va_end (ap);
    @}

  return result;
@}
@end smallexample

With a bit more knowledge about the input strings one could fine-tune
the memory allocation.  The difference we are pointing to here is that
we don't use @code{strcat} anymore.  We always keep track of the length
of the current intermediate result so we can save ourselves the search for the
end of the string and use @code{mempcpy}.  Please note that we also
don't use @code{stpcpy} which might seem more natural since we are handling
strings.  But this is not necessary since we already know the
length of the string and therefore can use the faster memory copying
function.  The example would work for wide characters the same way.

Whenever a programmer feels the need to use @code{strcat} she or he
should think twice and look through the program to see whether the code cannot
be rewritten to take advantage of already calculated results.  Again: it
is almost always unnecessary to use @code{strcat}.

@node Truncating Strings
@section Truncating Strings while Copying
@cindex truncating strings
@cindex string truncation

The functions described in this section copy or concatenate the
possibly-truncated contents of a string or array to another, and
similarly for wide strings.  They follow the string-copying functions
in their header conventions.  @xref{Copying Strings and Arrays}.  The
@samp{str} functions are declared in the header file @file{string.h}
and the @samp{wc} functions are declared in the file @file{wchar.h}.

@comment string.h
@deftypefun {char *} strncpy (char *restrict @var{to}, const char *restrict @var{from}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function is similar to @code{strcpy} but always copies exactly
@var{size} bytes into @var{to}.

If @var{from} does not contain a null byte in its first @var{size}
bytes, @code{strncpy} copies just the first @var{size} bytes.  In this
case no null terminator is written into @var{to}.

Otherwise @var{from} must be a string with length less than
@var{size}.  In this case @code{strncpy} copies all of @var{from},
followed by enough null bytes to add up to @var{size} bytes in all.

The behavior of @code{strncpy} is undefined if the strings overlap.

This function was designed for now-rarely-used arrays consisting of
non-null bytes followed by zero or more null bytes.  It needs to set
all @var{size} bytes of the destination, even when @var{size} is much
greater than the length of @var{from}.  As noted below, this function
is generally a poor choice for processing text.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wcsncpy (wchar_t *restrict @var{wto}, const wchar_t *restrict @var{wfrom}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function is similar to @code{wcscpy} but always copies exactly
@var{size} wide characters into @var{wto}.

If @var{wfrom} does not contain a null wide character in its first
@var{size} wide characters, then @code{wcsncpy} copies just the first
@var{size} wide characters.  In this case no null terminator is
written into @var{wto}.

Otherwise @var{wfrom} must be a wide string with length less than
@var{size}.  In this case @code{wcsncpy} copies all of @var{wfrom},
followed by enough null wide characters to add up to @var{size} wide
characters in all.

The behavior of @code{wcsncpy} is undefined if the strings overlap.

This function is the wide-character counterpart of @code{strncpy} and
suffers from most of the problems that @code{strncpy} does.  For
example, as noted below, this function is generally a poor choice for
processing text.
@end deftypefun

@comment string.h
@comment GNU
@deftypefun {char *} strndup (const char *@var{s}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
This function is similar to @code{strdup} but always copies at most
@var{size} bytes into the newly allocated string.

If the length of @var{s} is more than @var{size}, then @code{strndup}
copies just the first @var{size} bytes and adds a closing null byte.
Otherwise all bytes are copied and the string is terminated.

This function differs from @code{strncpy} in that it always terminates
the destination string.

As noted below, this function is generally a poor choice for
processing text.

@code{strndup} is a GNU extension.
@end deftypefun

@comment string.h
@comment GNU
@deftypefn {Macro} {char *} strndupa (const char *@var{s}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function is similar to @code{strndup} but like @code{strdupa} it
allocates the new string using @code{alloca} @pxref{Variable Size
Automatic}.  The same advantages and limitations of @code{strdupa} are
valid for @code{strndupa}, too.

This function is implemented only as a macro, just like @code{strdupa}.
Just as @code{strdupa} this macro also must not be used inside the
parameter list in a function call.

As noted below, this function is generally a poor choice for
processing text.

@code{strndupa} is only available if GNU CC is used.
@end deftypefn

@comment string.h
@comment GNU
@deftypefun {char *} stpncpy (char *restrict @var{to}, const char *restrict @var{from}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function is similar to @code{stpcpy} but copies always exactly
@var{size} bytes into @var{to}.

If the length of @var{from} is more than @var{size}, then @code{stpncpy}
copies just the first @var{size} bytes and returns a pointer to the
byte directly following the one which was copied last.  Note that in
this case there is no null terminator written into @var{to}.

If the length of @var{from} is less than @var{size}, then @code{stpncpy}
copies all of @var{from}, followed by enough null bytes to add up
to @var{size} bytes in all.  This behavior is rarely useful, but it
is implemented to be useful in contexts where this behavior of the
@code{strncpy} is used.  @code{stpncpy} returns a pointer to the
@emph{first} written null byte.

This function is not part of ISO or POSIX but was found useful while
developing @theglibc{} itself.

Its behavior is undefined if the strings overlap.  The function is
declared in @file{string.h}.

As noted below, this function is generally a poor choice for
processing text.
@end deftypefun

@comment wchar.h
@comment GNU
@deftypefun {wchar_t *} wcpncpy (wchar_t *restrict @var{wto}, const wchar_t *restrict @var{wfrom}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function is similar to @code{wcpcpy} but copies always exactly
@var{wsize} wide characters into @var{wto}.

If the length of @var{wfrom} is more than @var{size}, then
@code{wcpncpy} copies just the first @var{size} wide characters and
returns a pointer to the wide character directly following the last
non-null wide character which was copied last.  Note that in this case
there is no null terminator written into @var{wto}.

If the length of @var{wfrom} is less than @var{size}, then @code{wcpncpy}
copies all of @var{wfrom}, followed by enough null wide characters to add up
to @var{size} wide characters in all.  This behavior is rarely useful, but it
is implemented to be useful in contexts where this behavior of the
@code{wcsncpy} is used.  @code{wcpncpy} returns a pointer to the
@emph{first} written null wide character.

This function is not part of ISO or POSIX but was found useful while
developing @theglibc{} itself.

Its behavior is undefined if the strings overlap.

As noted below, this function is generally a poor choice for
processing text.

@code{wcpncpy} is a GNU extension.
@end deftypefun

@comment string.h
@comment ISO
@deftypefun {char *} strncat (char *restrict @var{to}, const char *restrict @var{from}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function is like @code{strcat} except that not more than @var{size}
bytes from @var{from} are appended to the end of @var{to}, and
@var{from} need not be null-terminated.  A single null byte is also
always appended to @var{to}, so the total
allocated size of @var{to} must be at least @code{@var{size} + 1} bytes
longer than its initial length.

The @code{strncat} function could be implemented like this:

@smallexample
@group
char *
strncat (char *to, const char *from, size_t size)
@{
  size_t len = strlen (to);
  memcpy (to + len, from, strnlen (from, size));
  to[len + strnlen (from, size)] = '\0';
  return to;
@}
@end group
@end smallexample

The behavior of @code{strncat} is undefined if the strings overlap.

As a companion to @code{strncpy}, @code{strncat} was designed for
now-rarely-used arrays consisting of non-null bytes followed by zero
or more null bytes.  As noted below, this function is generally a poor
choice for processing text.  Also, this function has significant
performance issues.  @xref{Concatenating Strings}.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wcsncat (wchar_t *restrict @var{wto}, const wchar_t *restrict @var{wfrom}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function is like @code{wcscat} except that not more than @var{size}
wide characters from @var{from} are appended to the end of @var{to},
and @var{from} need not be null-terminated.  A single null wide
character is also always appended to @var{to}, so the total allocated
size of @var{to} must be at least @code{wcsnlen (@var{wfrom},
@var{size}) + 1} wide characters longer than its initial length.

The @code{wcsncat} function could be implemented like this:

@smallexample
@group
wchar_t *
wcsncat (wchar_t *restrict wto, const wchar_t *restrict wfrom,
         size_t size)
@{
  size_t len = wcslen (wto);
  memcpy (wto + len, wfrom, wcsnlen (wfrom, size) * sizeof (wchar_t));
  wto[len + wcsnlen (wfrom, size)] = L'\0';
  return wto;
@}
@end group
@end smallexample

The behavior of @code{wcsncat} is undefined if the strings overlap.

As noted below, this function is generally a poor choice for
processing text.  Also, this function has significant performance
issues.  @xref{Concatenating Strings}.
@end deftypefun

Because these functions can abruptly truncate strings or wide strings,
they are generally poor choices for processing text.  When coping or
concatening multibyte strings, they can truncate within a multibyte
character so that the result is not a valid multibyte string.  When
combining or concatenating multibyte or wide strings, they may
truncate the output after a combining character, resulting in a
corrupted grapheme.  They can cause bugs even when processing
single-byte strings: for example, when calculating an ASCII-only user
name, a truncated name can identify the wrong user.

Although some buffer overruns can be prevented by manually replacing
calls to copying functions with calls to truncation functions, there
are often easier and safer automatic techniques that cause buffer
overruns to reliably terminate a program, such as GCC's
@option{-fcheck-pointer-bounds} and @option{-fsanitize=address}
options.  @xref{Debugging Options,, Options for Debugging Your Program
or GCC, gcc.info, Using GCC}.  Because truncation functions can mask
application bugs that would otherwise be caught by the automatic
techniques, these functions should be used only when the application's
underlying logic requires truncation.

@strong{Note:} GNU programs should not truncate strings or wide
strings to fit arbitrary size limits.  @xref{Semantics, , Writing
Robust Programs, standards, The GNU Coding Standards}.  Instead of
string-truncation functions, it is usually better to use dynamic
memory allocation (@pxref{Unconstrained Allocation}) and functions
such as @code{strdup} or @code{asprintf} to construct strings.

@node String/Array Comparison
@section String/Array Comparison
@cindex comparing strings and arrays
@cindex string comparison functions
@cindex array comparison functions
@cindex predicates on strings
@cindex predicates on arrays

You can use the functions in this section to perform comparisons on the
contents of strings and arrays.  As well as checking for equality, these
functions can also be used as the ordering functions for sorting
operations.  @xref{Searching and Sorting}, for an example of this.

Unlike most comparison operations in C, the string comparison functions
return a nonzero value if the strings are @emph{not} equivalent rather
than if they are.  The sign of the value indicates the relative ordering
of the first part of the strings that are not equivalent:  a
negative value indicates that the first string is ``less'' than the
second, while a positive value indicates that the first string is
``greater''.

The most common use of these functions is to check only for equality.
This is canonically done with an expression like @w{@samp{! strcmp (s1, s2)}}.

All of these functions are declared in the header file @file{string.h}.
@pindex string.h

@comment string.h
@comment ISO
@deftypefun int memcmp (const void *@var{a1}, const void *@var{a2}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The function @code{memcmp} compares the @var{size} bytes of memory
beginning at @var{a1} against the @var{size} bytes of memory beginning
at @var{a2}.  The value returned has the same sign as the difference
between the first differing pair of bytes (interpreted as @code{unsigned
char} objects, then promoted to @code{int}).

If the contents of the two blocks are equal, @code{memcmp} returns
@code{0}.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun int wmemcmp (const wchar_t *@var{a1}, const wchar_t *@var{a2}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The function @code{wmemcmp} compares the @var{size} wide characters
beginning at @var{a1} against the @var{size} wide characters beginning
at @var{a2}.  The value returned is smaller than or larger than zero
depending on whether the first differing wide character is @var{a1} is
smaller or larger than the corresponding wide character in @var{a2}.

If the contents of the two blocks are equal, @code{wmemcmp} returns
@code{0}.
@end deftypefun

On arbitrary arrays, the @code{memcmp} function is mostly useful for
testing equality.  It usually isn't meaningful to do byte-wise ordering
comparisons on arrays of things other than bytes.  For example, a
byte-wise comparison on the bytes that make up floating-point numbers
isn't likely to tell you anything about the relationship between the
values of the floating-point numbers.

@code{wmemcmp} is really only useful to compare arrays of type
@code{wchar_t} since the function looks at @code{sizeof (wchar_t)} bytes
at a time and this number of bytes is system dependent.

You should also be careful about using @code{memcmp} to compare objects
that can contain ``holes'', such as the padding inserted into structure
objects to enforce alignment requirements, extra space at the end of
unions, and extra bytes at the ends of strings whose length is less
than their allocated size.  The contents of these ``holes'' are
indeterminate and may cause strange behavior when performing byte-wise
comparisons.  For more predictable results, perform an explicit
component-wise comparison.

For example, given a structure type definition like:

@smallexample
struct foo
  @{
    unsigned char tag;
    union
      @{
        double f;
        long i;
        char *p;
      @} value;
  @};
@end smallexample

@noindent
you are better off writing a specialized comparison function to compare
@code{struct foo} objects instead of comparing them with @code{memcmp}.

@comment string.h
@comment ISO
@deftypefun int strcmp (const char *@var{s1}, const char *@var{s2})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{strcmp} function compares the string @var{s1} against
@var{s2}, returning a value that has the same sign as the difference
between the first differing pair of bytes (interpreted as
@code{unsigned char} objects, then promoted to @code{int}).

If the two strings are equal, @code{strcmp} returns @code{0}.

A consequence of the ordering used by @code{strcmp} is that if @var{s1}
is an initial substring of @var{s2}, then @var{s1} is considered to be
``less than'' @var{s2}.

@code{strcmp} does not take sorting conventions of the language the
strings are written in into account.  To get that one has to use
@code{strcoll}.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun int wcscmp (const wchar_t *@var{ws1}, const wchar_t *@var{ws2})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}

The @code{wcscmp} function compares the wide string @var{ws1}
against @var{ws2}.  The value returned is smaller than or larger than zero
depending on whether the first differing wide character is @var{ws1} is
smaller or larger than the corresponding wide character in @var{ws2}.

If the two strings are equal, @code{wcscmp} returns @code{0}.

A consequence of the ordering used by @code{wcscmp} is that if @var{ws1}
is an initial substring of @var{ws2}, then @var{ws1} is considered to be
``less than'' @var{ws2}.

@code{wcscmp} does not take sorting conventions of the language the
strings are written in into account.  To get that one has to use
@code{wcscoll}.
@end deftypefun

@comment string.h
@comment BSD
@deftypefun int strcasecmp (const char *@var{s1}, const char *@var{s2})
@safety{@prelim{}@mtsafe{@mtslocale{}}@assafe{}@acsafe{}}
@c Although this calls tolower multiple times, it's a macro, and
@c strcasecmp is optimized so that the locale pointer is read only once.
@c There are some asm implementations too, for which the single-read
@c from locale TLS pointers also applies.
This function is like @code{strcmp}, except that differences in case are
ignored, and its arguments must be multibyte strings.
How uppercase and lowercase characters are related is
determined by the currently selected locale.  In the standard @code{"C"}
locale the characters @"A and @"a do not match but in a locale which
regards these characters as parts of the alphabet they do match.

@noindent
@code{strcasecmp} is derived from BSD.
@end deftypefun

@comment wchar.h
@comment GNU
@deftypefun int wcscasecmp (const wchar_t *@var{ws1}, const wchar_t *@var{ws2})
@safety{@prelim{}@mtsafe{@mtslocale{}}@assafe{}@acsafe{}}
@c Since towlower is not a macro, the locale object may be read multiple
@c times.
This function is like @code{wcscmp}, except that differences in case are
ignored.  How uppercase and lowercase characters are related is
determined by the currently selected locale.  In the standard @code{"C"}
locale the characters @"A and @"a do not match but in a locale which
regards these characters as parts of the alphabet they do match.

@noindent
@code{wcscasecmp} is a GNU extension.
@end deftypefun

@comment string.h
@comment ISO
@deftypefun int strncmp (const char *@var{s1}, const char *@var{s2}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function is the similar to @code{strcmp}, except that no more than
@var{size} bytes are compared.  In other words, if the two
strings are the same in their first @var{size} bytes, the
return value is zero.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun int wcsncmp (const wchar_t *@var{ws1}, const wchar_t *@var{ws2}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function is similar to @code{wcscmp}, except that no more than
@var{size} wide characters are compared.  In other words, if the two
strings are the same in their first @var{size} wide characters, the
return value is zero.
@end deftypefun

@comment string.h
@comment BSD
@deftypefun int strncasecmp (const char *@var{s1}, const char *@var{s2}, size_t @var{n})
@safety{@prelim{}@mtsafe{@mtslocale{}}@assafe{}@acsafe{}}
This function is like @code{strncmp}, except that differences in case
are ignored, and the compared parts of the arguments should consist of
valid multibyte characters.
Like @code{strcasecmp}, it is locale dependent how
uppercase and lowercase characters are related.

@noindent
@code{strncasecmp} is a GNU extension.
@end deftypefun

@comment wchar.h
@comment GNU
@deftypefun int wcsncasecmp (const wchar_t *@var{ws1}, const wchar_t *@var{s2}, size_t @var{n})
@safety{@prelim{}@mtsafe{@mtslocale{}}@assafe{}@acsafe{}}
This function is like @code{wcsncmp}, except that differences in case
are ignored.  Like @code{wcscasecmp}, it is locale dependent how
uppercase and lowercase characters are related.

@noindent
@code{wcsncasecmp} is a GNU extension.
@end deftypefun

Here are some examples showing the use of @code{strcmp} and
@code{strncmp} (equivalent examples can be constructed for the wide
character functions).  These examples assume the use of the ASCII
character set.  (If some other character set---say, EBCDIC---is used
instead, then the glyphs are associated with different numeric codes,
and the return values and ordering may differ.)

@smallexample
strcmp ("hello", "hello")
    @result{} 0    /* @r{These two strings are the same.} */
strcmp ("hello", "Hello")
    @result{} 32   /* @r{Comparisons are case-sensitive.} */
strcmp ("hello", "world")
    @result{} -15  /* @r{The byte @code{'h'} comes before @code{'w'}.} */
strcmp ("hello", "hello, world")
    @result{} -44  /* @r{Comparing a null byte against a comma.} */
strncmp ("hello", "hello, world", 5)
    @result{} 0    /* @r{The initial 5 bytes are the same.} */
strncmp ("hello, world", "hello, stupid world!!!", 5)
    @result{} 0    /* @r{The initial 5 bytes are the same.} */
@end smallexample

@comment string.h
@comment GNU
@deftypefun int strverscmp (const char *@var{s1}, const char *@var{s2})
@safety{@prelim{}@mtsafe{@mtslocale{}}@assafe{}@acsafe{}}
@c Calls isdigit multiple times, locale may change in between.
The @code{strverscmp} function compares the string @var{s1} against
@var{s2}, considering them as holding indices/version numbers.  The
return value follows the same conventions as found in the
@code{strcmp} function.  In fact, if @var{s1} and @var{s2} contain no
digits, @code{strverscmp} behaves like @code{strcmp}
(in the sense that the sign of the result is the same).

The comparison algorithm which the @code{strverscmp} function implements
differs slightly from other version-comparison algorithms.  The
implementation is based on a finite-state machine, whose behavior is
approximated below.

@itemize @bullet
@item
The input strings are each split into sequences of non-digits and
digits.  These sequences can be empty at the beginning and end of the
string.  Digits are determined by the @code{isdigit} function and are
thus subject to the current locale.

@item
Comparison starts with a (possibly empty) non-digit sequence.  The first
non-equal sequences of non-digits or digits determines the outcome of
the comparison.

@item
Corresponding non-digit sequences in both strings are compared
lexicographically if their lengths are equal.  If the lengths differ,
the shorter non-digit sequence is extended with the input string
character immediately following it (which may be the null terminator),
the other sequence is truncated to be of the same (extended) length, and
these two sequences are compared lexicographically.  In the last case,
the sequence comparison determines the result of the function because
the extension character (or some character before it) is necessarily
different from the character at the same offset in the other input
string.

@item
For two sequences of digits, the number of leading zeros is counted (which
can be zero).  If the count differs, the string with more leading zeros
in the digit sequence is considered smaller than the other string.

@item
If the two sequences of digits have no leading zeros, they are compared
as integers, that is, the string with the longer digit sequence is
deemed larger, and if both sequences are of equal length, they are
compared lexicographically.

@item
If both digit sequences start with a zero and have an equal number of
leading zeros, they are compared lexicographically if their lengths are
the same.  If the lengths differ, the shorter sequence is extended with
the following character in its input string, and the other sequence is
truncated to the same length, and both sequences are compared
lexicographically (similar to the non-digit sequence case above).
@end itemize

The treatment of leading zeros and the tie-breaking extension characters
(which in effect propagate across non-digit/digit sequence boundaries)
differs from other version-comparison algorithms.

@smallexample
strverscmp ("no digit", "no digit")
    @result{} 0    /* @r{same behavior as strcmp.} */
strverscmp ("item#99", "item#100")
    @result{} <0   /* @r{same prefix, but 99 < 100.} */
strverscmp ("alpha1", "alpha001")
    @result{} >0   /* @r{different number of leading zeros (0 and 2).} */
strverscmp ("part1_f012", "part1_f01")
    @result{} >0   /* @r{lexicographical comparison with leading zeros.} */
strverscmp ("foo.009", "foo.0")
    @result{} <0   /* @r{different number of leading zeros (2 and 1).} */
@end smallexample

@code{strverscmp} is a GNU extension.
@end deftypefun

@comment string.h
@comment BSD
@deftypefun int bcmp (const void *@var{a1}, const void *@var{a2}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This is an obsolete alias for @code{memcmp}, derived from BSD.
@end deftypefun

@node Collation Functions
@section Collation Functions

@cindex collating strings
@cindex string collation functions

In some locales, the conventions for lexicographic ordering differ from
the strict numeric ordering of character codes.  For example, in Spanish
most glyphs with diacritical marks such as accents are not considered
distinct letters for the purposes of collation.  On the other hand, the
two-character sequence @samp{ll} is treated as a single letter that is
collated immediately after @samp{l}.

You can use the functions @code{strcoll} and @code{strxfrm} (declared in
the headers file @file{string.h}) and @code{wcscoll} and @code{wcsxfrm}
(declared in the headers file @file{wchar}) to compare strings using a
collation ordering appropriate for the current locale.  The locale used
by these functions in particular can be specified by setting the locale
for the @code{LC_COLLATE} category; see @ref{Locales}.
@pindex string.h
@pindex wchar.h

In the standard C locale, the collation sequence for @code{strcoll} is
the same as that for @code{strcmp}.  Similarly, @code{wcscoll} and
@code{wcscmp} are the same in this situation.

Effectively, the way these functions work is by applying a mapping to
transform the characters in a multibyte string to a byte
sequence that represents
the string's position in the collating sequence of the current locale.
Comparing two such byte sequences in a simple fashion is equivalent to
comparing the strings with the locale's collating sequence.

The functions @code{strcoll} and @code{wcscoll} perform this translation
implicitly, in order to do one comparison.  By contrast, @code{strxfrm}
and @code{wcsxfrm} perform the mapping explicitly.  If you are making
multiple comparisons using the same string or set of strings, it is
likely to be more efficient to use @code{strxfrm} or @code{wcsxfrm} to
transform all the strings just once, and subsequently compare the
transformed strings with @code{strcmp} or @code{wcscmp}.

@comment string.h
@comment ISO
@deftypefun int strcoll (const char *@var{s1}, const char *@var{s2})
@safety{@prelim{}@mtsafe{@mtslocale{}}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
@c Calls strcoll_l with the current locale, which dereferences only the
@c LC_COLLATE data pointer.
The @code{strcoll} function is similar to @code{strcmp} but uses the
collating sequence of the current locale for collation (the
@code{LC_COLLATE} locale).  The arguments are multibyte strings.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun int wcscoll (const wchar_t *@var{ws1}, const wchar_t *@var{ws2})
@safety{@prelim{}@mtsafe{@mtslocale{}}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
@c Same as strcoll, but calling wcscoll_l.
The @code{wcscoll} function is similar to @code{wcscmp} but uses the
collating sequence of the current locale for collation (the
@code{LC_COLLATE} locale).
@end deftypefun

Here is an example of sorting an array of strings, using @code{strcoll}
to compare them.  The actual sort algorithm is not written here; it
comes from @code{qsort} (@pxref{Array Sort Function}).  The job of the
code shown here is to say how to compare the strings while sorting them.
(Later on in this section, we will show a way to do this more
efficiently using @code{strxfrm}.)

@smallexample
/* @r{This is the comparison function used with @code{qsort}.} */

int
compare_elements (const void *v1, const void *v2)
@{
  char * const *p1 = v1;
  char * const *p2 = v2;

  return strcoll (*p1, *p2);
@}

/* @r{This is the entry point---the function to sort}
   @r{strings using the locale's collating sequence.} */

void
sort_strings (char **array, int nstrings)
@{
  /* @r{Sort @code{temp_array} by comparing the strings.} */
  qsort (array, nstrings,
         sizeof (char *), compare_elements);
@}
@end smallexample

@cindex converting string to collation order
@comment string.h
@comment ISO
@deftypefun size_t strxfrm (char *restrict @var{to}, const char *restrict @var{from}, size_t @var{size})
@safety{@prelim{}@mtsafe{@mtslocale{}}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
The function @code{strxfrm} transforms the multibyte string
@var{from} using the
collation transformation determined by the locale currently selected for
collation, and stores the transformed string in the array @var{to}.  Up
to @var{size} bytes (including a terminating null byte) are
stored.

The behavior is undefined if the strings @var{to} and @var{from}
overlap; see @ref{Copying Strings and Arrays}.

The return value is the length of the entire transformed string.  This
value is not affected by the value of @var{size}, but if it is greater
or equal than @var{size}, it means that the transformed string did not
entirely fit in the array @var{to}.  In this case, only as much of the
string as actually fits was stored.  To get the whole transformed
string, call @code{strxfrm} again with a bigger output array.

The transformed string may be longer than the original string, and it
may also be shorter.

If @var{size} is zero, no bytes are stored in @var{to}.  In this
case, @code{strxfrm} simply returns the number of bytes that would
be the length of the transformed string.  This is useful for determining
what size the allocated array should be.  It does not matter what
@var{to} is if @var{size} is zero; @var{to} may even be a null pointer.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun size_t wcsxfrm (wchar_t *restrict @var{wto}, const wchar_t *@var{wfrom}, size_t @var{size})
@safety{@prelim{}@mtsafe{@mtslocale{}}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
The function @code{wcsxfrm} transforms wide string @var{wfrom}
using the collation transformation determined by the locale currently
selected for collation, and stores the transformed string in the array
@var{wto}.  Up to @var{size} wide characters (including a terminating null
wide character) are stored.

The behavior is undefined if the strings @var{wto} and @var{wfrom}
overlap; see @ref{Copying Strings and Arrays}.

The return value is the length of the entire transformed wide
string.  This value is not affected by the value of @var{size}, but if
it is greater or equal than @var{size}, it means that the transformed
wide string did not entirely fit in the array @var{wto}.  In
this case, only as much of the wide string as actually fits
was stored.  To get the whole transformed wide string, call
@code{wcsxfrm} again with a bigger output array.

The transformed wide string may be longer than the original
wide string, and it may also be shorter.

If @var{size} is zero, no wide characters are stored in @var{to}.  In this
case, @code{wcsxfrm} simply returns the number of wide characters that
would be the length of the transformed wide string.  This is
useful for determining what size the allocated array should be (remember
to multiply with @code{sizeof (wchar_t)}).  It does not matter what
@var{wto} is if @var{size} is zero; @var{wto} may even be a null pointer.
@end deftypefun

Here is an example of how you can use @code{strxfrm} when
you plan to do many comparisons.  It does the same thing as the previous
example, but much faster, because it has to transform each string only
once, no matter how many times it is compared with other strings.  Even
the time needed to allocate and free storage is much less than the time
we save, when there are many strings.

@smallexample
struct sorter @{ char *input; char *transformed; @};

/* @r{This is the comparison function used with @code{qsort}}
   @r{to sort an array of @code{struct sorter}.} */

int
compare_elements (const void *v1, const void *v2)
@{
  const struct sorter *p1 = v1;
  const struct sorter *p2 = v2;

  return strcmp (p1->transformed, p2->transformed);
@}

/* @r{This is the entry point---the function to sort}
   @r{strings using the locale's collating sequence.} */

void
sort_strings_fast (char **array, int nstrings)
@{
  struct sorter temp_array[nstrings];
  int i;

  /* @r{Set up @code{temp_array}.  Each element contains}
     @r{one input string and its transformed string.} */
  for (i = 0; i < nstrings; i++)
    @{
      size_t length = strlen (array[i]) * 2;
      char *transformed;
      size_t transformed_length;

      temp_array[i].input = array[i];

      /* @r{First try a buffer perhaps big enough.}  */
      transformed = (char *) xmalloc (length);

      /* @r{Transform @code{array[i]}.}  */
      transformed_length = strxfrm (transformed, array[i], length);

      /* @r{If the buffer was not large enough, resize it}
         @r{and try again.}  */
      if (transformed_length >= length)
        @{
          /* @r{Allocate the needed space. +1 for terminating}
             @r{@code{'\0'} byte.}  */
          transformed = (char *) xrealloc (transformed,
                                           transformed_length + 1);

          /* @r{The return value is not interesting because we know}
             @r{how long the transformed string is.}  */
          (void) strxfrm (transformed, array[i],
                          transformed_length + 1);
        @}

      temp_array[i].transformed = transformed;
    @}

  /* @r{Sort @code{temp_array} by comparing transformed strings.} */
  qsort (temp_array, nstrings,
         sizeof (struct sorter), compare_elements);

  /* @r{Put the elements back in the permanent array}
     @r{in their sorted order.} */
  for (i = 0; i < nstrings; i++)
    array[i] = temp_array[i].input;

  /* @r{Free the strings we allocated.} */
  for (i = 0; i < nstrings; i++)
    free (temp_array[i].transformed);
@}
@end smallexample

The interesting part of this code for the wide character version would
look like this:

@smallexample
void
sort_strings_fast (wchar_t **array, int nstrings)
@{
  @dots{}
      /* @r{Transform @code{array[i]}.}  */
      transformed_length = wcsxfrm (transformed, array[i], length);

      /* @r{If the buffer was not large enough, resize it}
         @r{and try again.}  */
      if (transformed_length >= length)
        @{
          /* @r{Allocate the needed space. +1 for terminating}
             @r{@code{L'\0'} wide character.}  */
          transformed = (wchar_t *) xrealloc (transformed,
                                              (transformed_length + 1)
                                              * sizeof (wchar_t));

          /* @r{The return value is not interesting because we know}
             @r{how long the transformed string is.}  */
          (void) wcsxfrm (transformed, array[i],
                          transformed_length + 1);
        @}
  @dots{}
@end smallexample

@noindent
Note the additional multiplication with @code{sizeof (wchar_t)} in the
@code{realloc} call.

@strong{Compatibility Note:} The string collation functions are a new
feature of @w{ISO C90}.  Older C dialects have no equivalent feature.
The wide character versions were introduced in @w{Amendment 1} to @w{ISO
C90}.

@node Search Functions
@section Search Functions

This section describes library functions which perform various kinds
of searching operations on strings and arrays.  These functions are
declared in the header file @file{string.h}.
@pindex string.h
@cindex search functions (for strings)
@cindex string search functions

@comment string.h
@comment ISO
@deftypefun {void *} memchr (const void *@var{block}, int @var{c}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function finds the first occurrence of the byte @var{c} (converted
to an @code{unsigned char}) in the initial @var{size} bytes of the
object beginning at @var{block}.  The return value is a pointer to the
located byte, or a null pointer if no match was found.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wmemchr (const wchar_t *@var{block}, wchar_t @var{wc}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function finds the first occurrence of the wide character @var{wc}
in the initial @var{size} wide characters of the object beginning at
@var{block}.  The return value is a pointer to the located wide
character, or a null pointer if no match was found.
@end deftypefun

@comment string.h
@comment GNU
@deftypefun {void *} rawmemchr (const void *@var{block}, int @var{c})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
Often the @code{memchr} function is used with the knowledge that the
byte @var{c} is available in the memory block specified by the
parameters.  But this means that the @var{size} parameter is not really
needed and that the tests performed with it at runtime (to check whether
the end of the block is reached) are not needed.

The @code{rawmemchr} function exists for just this situation which is
surprisingly frequent.  The interface is similar to @code{memchr} except
that the @var{size} parameter is missing.  The function will look beyond
the end of the block pointed to by @var{block} in case the programmer
made an error in assuming that the byte @var{c} is present in the block.
In this case the result is unspecified.  Otherwise the return value is a
pointer to the located byte.

This function is of special interest when looking for the end of a
string.  Since all strings are terminated by a null byte a call like

@smallexample
   rawmemchr (str, '\0')
@end smallexample

@noindent
will never go beyond the end of the string.

This function is a GNU extension.
@end deftypefun

@comment string.h
@comment GNU
@deftypefun {void *} memrchr (const void *@var{block}, int @var{c}, size_t @var{size})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The function @code{memrchr} is like @code{memchr}, except that it searches
backwards from the end of the block defined by @var{block} and @var{size}
(instead of forwards from the front).

This function is a GNU extension.
@end deftypefun

@comment string.h
@comment ISO
@deftypefun {char *} strchr (const char *@var{string}, int @var{c})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{strchr} function finds the first occurrence of the byte
@var{c} (converted to a @code{char}) in the string
beginning at @var{string}.  The return value is a pointer to the located
byte, or a null pointer if no match was found.

For example,
@smallexample
strchr ("hello, world", 'l')
    @result{} "llo, world"
strchr ("hello, world", '?')
    @result{} NULL
@end smallexample

The terminating null byte is considered to be part of the string,
so you can use this function get a pointer to the end of a string by
specifying zero as the value of the @var{c} argument.

When @code{strchr} returns a null pointer, it does not let you know
the position of the terminating null byte it has found.  If you
need that information, it is better (but less portable) to use
@code{strchrnul} than to search for it a second time.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wcschr (const wchar_t *@var{wstring}, int @var{wc})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{wcschr} function finds the first occurrence of the wide
character @var{wc} in the wide string
beginning at @var{wstring}.  The return value is a pointer to the
located wide character, or a null pointer if no match was found.

The terminating null wide character is considered to be part of the wide
string, so you can use this function get a pointer to the end
of a wide string by specifying a null wide character as the
value of the @var{wc} argument.  It would be better (but less portable)
to use @code{wcschrnul} in this case, though.
@end deftypefun

@comment string.h
@comment GNU
@deftypefun {char *} strchrnul (const char *@var{string}, int @var{c})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
@code{strchrnul} is the same as @code{strchr} except that if it does
not find the byte, it returns a pointer to string's terminating
null byte rather than a null pointer.

This function is a GNU extension.
@end deftypefun

@comment wchar.h
@comment GNU
@deftypefun {wchar_t *} wcschrnul (const wchar_t *@var{wstring}, wchar_t @var{wc})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
@code{wcschrnul} is the same as @code{wcschr} except that if it does not
find the wide character, it returns a pointer to the wide string's
terminating null wide character rather than a null pointer.

This function is a GNU extension.
@end deftypefun

One useful, but unusual, use of the @code{strchr}
function is when one wants to have a pointer pointing to the null byte
terminating a string.  This is often written in this way:

@smallexample
  s += strlen (s);
@end smallexample

@noindent
This is almost optimal but the addition operation duplicated a bit of
the work already done in the @code{strlen} function.  A better solution
is this:

@smallexample
  s = strchr (s, '\0');
@end smallexample

There is no restriction on the second parameter of @code{strchr} so it
could very well also be zero.  Those readers thinking very
hard about this might now point out that the @code{strchr} function is
more expensive than the @code{strlen} function since we have two abort
criteria.  This is right.  But in @theglibc{} the implementation of
@code{strchr} is optimized in a special way so that @code{strchr}
actually is faster.

@comment string.h
@comment ISO
@deftypefun {char *} strrchr (const char *@var{string}, int @var{c})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The function @code{strrchr} is like @code{strchr}, except that it searches
backwards from the end of the string @var{string} (instead of forwards
from the front).

For example,
@smallexample
strrchr ("hello, world", 'l')
    @result{} "ld"
@end smallexample
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wcsrchr (const wchar_t *@var{wstring}, wchar_t @var{c})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The function @code{wcsrchr} is like @code{wcschr}, except that it searches
backwards from the end of the string @var{wstring} (instead of forwards
from the front).
@end deftypefun

@comment string.h
@comment ISO
@deftypefun {char *} strstr (const char *@var{haystack}, const char *@var{needle})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This is like @code{strchr}, except that it searches @var{haystack} for a
substring @var{needle} rather than just a single byte.  It
returns a pointer into the string @var{haystack} that is the first
byte of the substring, or a null pointer if no match was found.  If
@var{needle} is an empty string, the function returns @var{haystack}.

For example,
@smallexample
strstr ("hello, world", "l")
    @result{} "llo, world"
strstr ("hello, world", "wo")
    @result{} "world"
@end smallexample
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wcsstr (const wchar_t *@var{haystack}, const wchar_t *@var{needle})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This is like @code{wcschr}, except that it searches @var{haystack} for a
substring @var{needle} rather than just a single wide character.  It
returns a pointer into the string @var{haystack} that is the first wide
character of the substring, or a null pointer if no match was found.  If
@var{needle} is an empty string, the function returns @var{haystack}.
@end deftypefun

@comment wchar.h
@comment XPG
@deftypefun {wchar_t *} wcswcs (const wchar_t *@var{haystack}, const wchar_t *@var{needle})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
@code{wcswcs} is a deprecated alias for @code{wcsstr}.  This is the
name originally used in the X/Open Portability Guide before the
@w{Amendment 1} to @w{ISO C90} was published.
@end deftypefun


@comment string.h
@comment GNU
@deftypefun {char *} strcasestr (const char *@var{haystack}, const char *@var{needle})
@safety{@prelim{}@mtsafe{@mtslocale{}}@assafe{}@acsafe{}}
@c There may be multiple calls of strncasecmp, each accessing the locale
@c object independently.
This is like @code{strstr}, except that it ignores case in searching for
the substring.   Like @code{strcasecmp}, it is locale dependent how
uppercase and lowercase characters are related, and arguments are
multibyte strings.


For example,
@smallexample
strcasestr ("hello, world", "L")
    @result{} "llo, world"
strcasestr ("hello, World", "wo")
    @result{} "World"
@end smallexample
@end deftypefun


@comment string.h
@comment GNU
@deftypefun {void *} memmem (const void *@var{haystack}, size_t @var{haystack-len},@*const void *@var{needle}, size_t @var{needle-len})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This is like @code{strstr}, but @var{needle} and @var{haystack} are byte
arrays rather than strings.  @var{needle-len} is the
length of @var{needle} and @var{haystack-len} is the length of
@var{haystack}.@refill

This function is a GNU extension.
@end deftypefun

@comment string.h
@comment ISO
@deftypefun size_t strspn (const char *@var{string}, const char *@var{skipset})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{strspn} (``string span'') function returns the length of the
initial substring of @var{string} that consists entirely of bytes that
are members of the set specified by the string @var{skipset}.  The order
of the bytes in @var{skipset} is not important.

For example,
@smallexample
strspn ("hello, world", "abcdefghijklmnopqrstuvwxyz")
    @result{} 5
@end smallexample

In a multibyte string, characters consisting of
more than one byte are not treated as single entities.  Each byte is treated
separately.  The function is not locale-dependent.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun size_t wcsspn (const wchar_t *@var{wstring}, const wchar_t *@var{skipset})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{wcsspn} (``wide character string span'') function returns the
length of the initial substring of @var{wstring} that consists entirely
of wide characters that are members of the set specified by the string
@var{skipset}.  The order of the wide characters in @var{skipset} is not
important.
@end deftypefun

@comment string.h
@comment ISO
@deftypefun size_t strcspn (const char *@var{string}, const char *@var{stopset})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{strcspn} (``string complement span'') function returns the length
of the initial substring of @var{string} that consists entirely of bytes
that are @emph{not} members of the set specified by the string @var{stopset}.
(In other words, it returns the offset of the first byte in @var{string}
that is a member of the set @var{stopset}.)

For example,
@smallexample
strcspn ("hello, world", " \t\n,.;!?")
    @result{} 5
@end smallexample

In a multibyte string, characters consisting of
more than one byte are not treated as a single entities.  Each byte is treated
separately.  The function is not locale-dependent.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun size_t wcscspn (const wchar_t *@var{wstring}, const wchar_t *@var{stopset})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{wcscspn} (``wide character string complement span'') function
returns the length of the initial substring of @var{wstring} that
consists entirely of wide characters that are @emph{not} members of the
set specified by the string @var{stopset}.  (In other words, it returns
the offset of the first wide character in @var{string} that is a member of
the set @var{stopset}.)
@end deftypefun

@comment string.h
@comment ISO
@deftypefun {char *} strpbrk (const char *@var{string}, const char *@var{stopset})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{strpbrk} (``string pointer break'') function is related to
@code{strcspn}, except that it returns a pointer to the first byte
in @var{string} that is a member of the set @var{stopset} instead of the
length of the initial substring.  It returns a null pointer if no such
byte from @var{stopset} is found.

@c @group  Invalid outside the example.
For example,

@smallexample
strpbrk ("hello, world", " \t\n,.;!?")
    @result{} ", world"
@end smallexample
@c @end group

In a multibyte string, characters consisting of
more than one byte are not treated as single entities.  Each byte is treated
separately.  The function is not locale-dependent.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wcspbrk (const wchar_t *@var{wstring}, const wchar_t *@var{stopset})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{wcspbrk} (``wide character string pointer break'') function is
related to @code{wcscspn}, except that it returns a pointer to the first
wide character in @var{wstring} that is a member of the set
@var{stopset} instead of the length of the initial substring.  It
returns a null pointer if no such wide character from @var{stopset} is found.
@end deftypefun


@subsection Compatibility String Search Functions

@comment string.h
@comment BSD
@deftypefun {char *} index (const char *@var{string}, int @var{c})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
@code{index} is another name for @code{strchr}; they are exactly the same.
New code should always use @code{strchr} since this name is defined in
@w{ISO C} while @code{index} is a BSD invention which never was available
on @w{System V} derived systems.
@end deftypefun

@comment string.h
@comment BSD
@deftypefun {char *} rindex (const char *@var{string}, int @var{c})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
@code{rindex} is another name for @code{strrchr}; they are exactly the same.
New code should always use @code{strrchr} since this name is defined in
@w{ISO C} while @code{rindex} is a BSD invention which never was available
on @w{System V} derived systems.
@end deftypefun

@node Finding Tokens in a String
@section Finding Tokens in a String

@cindex tokenizing strings
@cindex breaking a string into tokens
@cindex parsing tokens from a string
It's fairly common for programs to have a need to do some simple kinds
of lexical analysis and parsing, such as splitting a command string up
into tokens.  You can do this with the @code{strtok} function, declared
in the header file @file{string.h}.
@pindex string.h

@comment string.h
@comment ISO
@deftypefun {char *} strtok (char *restrict @var{newstring}, const char *restrict @var{delimiters})
@safety{@prelim{}@mtunsafe{@mtasurace{:strtok}}@asunsafe{}@acsafe{}}
A string can be split into tokens by making a series of calls to the
function @code{strtok}.

The string to be split up is passed as the @var{newstring} argument on
the first call only.  The @code{strtok} function uses this to set up
some internal state information.  Subsequent calls to get additional
tokens from the same string are indicated by passing a null pointer as
the @var{newstring} argument.  Calling @code{strtok} with another
non-null @var{newstring} argument reinitializes the state information.
It is guaranteed that no other library function ever calls @code{strtok}
behind your back (which would mess up this internal state information).

The @var{delimiters} argument is a string that specifies a set of delimiters
that may surround the token being extracted.  All the initial bytes
that are members of this set are discarded.  The first byte that is
@emph{not} a member of this set of delimiters marks the beginning of the
next token.  The end of the token is found by looking for the next
byte that is a member of the delimiter set.  This byte in the
original string @var{newstring} is overwritten by a null byte, and the
pointer to the beginning of the token in @var{newstring} is returned.

On the next call to @code{strtok}, the searching begins at the next
byte beyond the one that marked the end of the previous token.
Note that the set of delimiters @var{delimiters} do not have to be the
same on every call in a series of calls to @code{strtok}.

If the end of the string @var{newstring} is reached, or if the remainder of
string consists only of delimiter bytes, @code{strtok} returns
a null pointer.

In a multibyte string, characters consisting of
more than one byte are not treated as single entities.  Each byte is treated
separately.  The function is not locale-dependent.
@end deftypefun

@comment wchar.h
@comment ISO
@deftypefun {wchar_t *} wcstok (wchar_t *@var{newstring}, const wchar_t *@var{delimiters}, wchar_t **@var{save_ptr})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
A string can be split into tokens by making a series of calls to the
function @code{wcstok}.

The string to be split up is passed as the @var{newstring} argument on
the first call only.  The @code{wcstok} function uses this to set up
some internal state information.  Subsequent calls to get additional
tokens from the same wide string are indicated by passing a
null pointer as the @var{newstring} argument, which causes the pointer
previously stored in @var{save_ptr} to be used instead.

The @var{delimiters} argument is a wide string that specifies
a set of delimiters that may surround the token being extracted.  All
the initial wide characters that are members of this set are discarded.
The first wide character that is @emph{not} a member of this set of
delimiters marks the beginning of the next token.  The end of the token
is found by looking for the next wide character that is a member of the
delimiter set.  This wide character in the original wide
string @var{newstring} is overwritten by a null wide character, the
pointer past the overwritten wide character is saved in @var{save_ptr},
and the pointer to the beginning of the token in @var{newstring} is
returned.

On the next call to @code{wcstok}, the searching begins at the next
wide character beyond the one that marked the end of the previous token.
Note that the set of delimiters @var{delimiters} do not have to be the
same on every call in a series of calls to @code{wcstok}.

If the end of the wide string @var{newstring} is reached, or
if the remainder of string consists only of delimiter wide characters,
@code{wcstok} returns a null pointer.
@end deftypefun

@strong{Warning:} Since @code{strtok} and @code{wcstok} alter the string
they is parsing, you should always copy the string to a temporary buffer
before parsing it with @code{strtok}/@code{wcstok} (@pxref{Copying Strings
and Arrays}).  If you allow @code{strtok} or @code{wcstok} to modify
a string that came from another part of your program, you are asking for
trouble; that string might be used for other purposes after
@code{strtok} or @code{wcstok} has modified it, and it would not have
the expected value.

The string that you are operating on might even be a constant.  Then
when @code{strtok} or @code{wcstok} tries to modify it, your program
will get a fatal signal for writing in read-only memory.  @xref{Program
Error Signals}.  Even if the operation of @code{strtok} or @code{wcstok}
would not require a modification of the string (e.g., if there is
exactly one token) the string can (and in the @glibcadj{} case will) be
modified.

This is a special case of a general principle: if a part of a program
does not have as its purpose the modification of a certain data
structure, then it is error-prone to modify the data structure
temporarily.

The function @code{strtok} is not reentrant, whereas @code{wcstok} is.
@xref{Nonreentrancy}, for a discussion of where and why reentrancy is
important.

Here is a simple example showing the use of @code{strtok}.

@comment Yes, this example has been tested.
@smallexample
#include <string.h>
#include <stddef.h>

@dots{}

const char string[] = "words separated by spaces -- and, punctuation!";
const char delimiters[] = " .,;:!-";
char *token, *cp;

@dots{}

cp = strdupa (string);                /* Make writable copy.  */
token = strtok (cp, delimiters);      /* token => "words" */
token = strtok (NULL, delimiters);    /* token => "separated" */
token = strtok (NULL, delimiters);    /* token => "by" */
token = strtok (NULL, delimiters);    /* token => "spaces" */
token = strtok (NULL, delimiters);    /* token => "and" */
token = strtok (NULL, delimiters);    /* token => "punctuation" */
token = strtok (NULL, delimiters);    /* token => NULL */
@end smallexample

@Theglibc{} contains two more functions for tokenizing a string
which overcome the limitation of non-reentrancy.  They are not
available available for wide strings.

@comment string.h
@comment POSIX
@deftypefun {char *} strtok_r (char *@var{newstring}, const char *@var{delimiters}, char **@var{save_ptr})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
Just like @code{strtok}, this function splits the string into several
tokens which can be accessed by successive calls to @code{strtok_r}.
The difference is that, as in @code{wcstok}, the information about the
next token is stored in the space pointed to by the third argument,
@var{save_ptr}, which is a pointer to a string pointer.  Calling
@code{strtok_r} with a null pointer for @var{newstring} and leaving
@var{save_ptr} between the calls unchanged does the job without
hindering reentrancy.

This function is defined in POSIX.1 and can be found on many systems
which support multi-threading.
@end deftypefun

@comment string.h
@comment BSD
@deftypefun {char *} strsep (char **@var{string_ptr}, const char *@var{delimiter})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This function has a similar functionality as @code{strtok_r} with the
@var{newstring} argument replaced by the @var{save_ptr} argument.  The
initialization of the moving pointer has to be done by the user.
Successive calls to @code{strsep} move the pointer along the tokens
separated by @var{delimiter}, returning the address of the next token
and updating @var{string_ptr} to point to the beginning of the next
token.

One difference between @code{strsep} and @code{strtok_r} is that if the
input string contains more than one byte from @var{delimiter} in a
row @code{strsep} returns an empty string for each pair of bytes
from @var{delimiter}.  This means that a program normally should test
for @code{strsep} returning an empty string before processing it.

This function was introduced in 4.3BSD and therefore is widely available.
@end deftypefun

Here is how the above example looks like when @code{strsep} is used.

@comment Yes, this example has been tested.
@smallexample
#include <string.h>
#include <stddef.h>

@dots{}

const char string[] = "words separated by spaces -- and, punctuation!";
const char delimiters[] = " .,;:!-";
char *running;
char *token;

@dots{}

running = strdupa (string);
token = strsep (&running, delimiters);    /* token => "words" */
token = strsep (&running, delimiters);    /* token => "separated" */
token = strsep (&running, delimiters);    /* token => "by" */
token = strsep (&running, delimiters);    /* token => "spaces" */
token = strsep (&running, delimiters);    /* token => "" */
token = strsep (&running, delimiters);    /* token => "" */
token = strsep (&running, delimiters);    /* token => "" */
token = strsep (&running, delimiters);    /* token => "and" */
token = strsep (&running, delimiters);    /* token => "" */
token = strsep (&running, delimiters);    /* token => "punctuation" */
token = strsep (&running, delimiters);    /* token => "" */
token = strsep (&running, delimiters);    /* token => NULL */
@end smallexample

@comment string.h
@comment GNU
@deftypefun {char *} basename (const char *@var{filename})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The GNU version of the @code{basename} function returns the last
component of the path in @var{filename}.  This function is the preferred
usage, since it does not modify the argument, @var{filename}, and
respects trailing slashes.  The prototype for @code{basename} can be
found in @file{string.h}.  Note, this function is overridden by the XPG
version, if @file{libgen.h} is included.

Example of using GNU @code{basename}:

@smallexample
#include <string.h>

int
main (int argc, char *argv[])
@{
  char *prog = basename (argv[0]);

  if (argc < 2)
    @{
      fprintf (stderr, "Usage %s <arg>\n", prog);
      exit (1);
    @}

  @dots{}
@}
@end smallexample

@strong{Portability Note:} This function may produce different results
on different systems.

@end deftypefun

@comment libgen.h
@comment XPG
@deftypefun {char *} basename (char *@var{path})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
This is the standard XPG defined @code{basename}.  It is similar in
spirit to the GNU version, but may modify the @var{path} by removing
trailing '/' bytes.  If the @var{path} is made up entirely of '/'
bytes, then "/" will be returned.  Also, if @var{path} is
@code{NULL} or an empty string, then "." is returned.  The prototype for
the XPG version can be found in @file{libgen.h}.

Example of using XPG @code{basename}:

@smallexample
#include <libgen.h>

int
main (int argc, char *argv[])
@{
  char *prog;
  char *path = strdupa (argv[0]);

  prog = basename (path);

  if (argc < 2)
    @{
      fprintf (stderr, "Usage %s <arg>\n", prog);
      exit (1);
    @}

  @dots{}

@}
@end smallexample
@end deftypefun

@comment libgen.h
@comment XPG
@deftypefun {char *} dirname (char *@var{path})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{dirname} function is the compliment to the XPG version of
@code{basename}.  It returns the parent directory of the file specified
by @var{path}.  If @var{path} is @code{NULL}, an empty string, or
contains no '/' bytes, then "." is returned.  The prototype for this
function can be found in @file{libgen.h}.
@end deftypefun

@node Erasing Sensitive Data
@section Erasing Sensitive Data

Sensitive data, such as cryptographic keys, should be erased from
memory after use, to reduce the risk that a bug will expose it to the
outside world.  However, compiler optimizations may determine that an
erasure operation is ``unnecessary,'' and remove it from the generated
code, because no @emph{correct} program could access the variable or
heap object containing the sensitive data after it's deallocated.
Since erasure is a precaution against bugs, this optimization is
inappropriate.

The function @code{explicit_bzero} erases a block of memory, and
guarantees that the compiler will not remove the erasure as
``unnecessary.''

@smallexample
@group
#include <string.h>

extern void encrypt (const char *key, const char *in,
                     char *out, size_t n);
extern void genkey (const char *phrase, char *key);

void encrypt_with_phrase (const char *phrase, const char *in,
                          char *out, size_t n)
@{
  char key[16];
  genkey (phrase, key);
  encrypt (key, in, out, n);
  explicit_bzero (key, 16);
@}
@end group
@end smallexample

@noindent
In this example, if @code{memset}, @code{bzero}, or a hand-written
loop had been used, the compiler might remove them as ``unnecessary.''

@strong{Warning:} @code{explicit_bzero} does not guarantee that
sensitive data is @emph{completely} erased from the computer's memory.
There may be copies in temporary storage areas, such as registers and
``scratch'' stack space; since these are invisible to the source code,
a library function cannot erase them.

Also, @code{explicit_bzero} only operates on RAM.  If a sensitive data
object never needs to have its address taken other than to call
@code{explicit_bzero}, it might be stored entirely in CPU registers
@emph{until} the call to @code{explicit_bzero}.  Then it will be
copied into RAM, the copy will be erased, and the original will remain
intact.  Data in RAM is more likely to be exposed by a bug than data
in registers, so this creates a brief window where the data is at
greater risk of exposure than it would have been if the program didn't
try to erase it at all.

Declaring sensitive variables as @code{volatile} will make both the
above problems @emph{worse}; a @code{volatile} variable will be stored
in memory for its entire lifetime, and the compiler will make
@emph{more} copies of it than it would otherwise have.  Attempting to
erase a normal variable ``by hand'' through a
@code{volatile}-qualified pointer doesn't work at all---because the
variable itself is not @code{volatile}, some compilers will ignore the
qualification on the pointer and remove the erasure anyway.

Having said all that, in most situations, using @code{explicit_bzero}
is better than not using it.  At present, the only way to do a more
thorough job is to write the entire sensitive operation in assembly
language.  We anticipate that future compilers will recognize calls to
@code{explicit_bzero} and take appropriate steps to erase all the
copies of the affected data, whereever they may be.

@comment string.h
@comment BSD
@deftypefun void explicit_bzero (void *@var{block}, size_t @var{len})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}

@code{explicit_bzero} writes zero into @var{len} bytes of memory
beginning at @var{block}, just as @code{bzero} would.  The zeroes are
always written, even if the compiler could determine that this is
``unnecessary'' because no correct program could read them back.

@strong{Note:} The @emph{only} optimization that @code{explicit_bzero}
disables is removal of ``unnecessary'' writes to memory.  The compiler
can perform all the other optimizations that it could for a call to
@code{memset}.  For instance, it may replace the function call with
inline memory writes, and it may assume that @var{block} cannot be a
null pointer.

@strong{Portability Note:} This function first appeared in OpenBSD 5.5
and has not been standardized.  Other systems may provide the same
functionality under a different name, such as @code{explicit_memset},
@code{memset_s}, or @code{SecureZeroMemory}.

@Theglibc{} declares this function in @file{string.h}, but on other
systems it may be in @file{strings.h} instead.
@end deftypefun

@node strfry
@section strfry

The function below addresses the perennial programming quandary: ``How do
I take good data in string form and painlessly turn it into garbage?''
This is actually a fairly simple task for C programmers who do not use
@theglibc{} string functions, but for programs based on @theglibc{},
the @code{strfry} function is the preferred method for
destroying string data.

The prototype for this function is in @file{string.h}.

@comment string.h
@comment GNU
@deftypefun {char *} strfry (char *@var{string})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
@c Calls initstate_r, time, getpid, strlen, and random_r.

@code{strfry} creates a pseudorandom anagram of a string, replacing the
input with the anagram in place.  For each position in the string,
@code{strfry} swaps it with a position in the string selected at random
(from a uniform distribution).  The two positions may be the same.

The return value of @code{strfry} is always @var{string}.

@strong{Portability Note:}  This function is unique to @theglibc{}.

@end deftypefun


@node Trivial Encryption
@section Trivial Encryption
@cindex encryption


The @code{memfrob} function converts an array of data to something
unrecognizable and back again.  It is not encryption in its usual sense
since it is easy for someone to convert the encrypted data back to clear
text.  The transformation is analogous to Usenet's ``Rot13'' encryption
method for obscuring offensive jokes from sensitive eyes and such.
Unlike Rot13, @code{memfrob} works on arbitrary binary data, not just
text.
@cindex Rot13

For true encryption, @xref{Cryptographic Functions}.

This function is declared in @file{string.h}.
@pindex string.h

@comment string.h
@comment GNU
@deftypefun {void *} memfrob (void *@var{mem}, size_t @var{length})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}

@code{memfrob} transforms (frobnicates) each byte of the data structure
at @var{mem}, which is @var{length} bytes long, by bitwise exclusive
oring it with binary 00101010.  It does the transformation in place and
its return value is always @var{mem}.

Note that @code{memfrob} a second time on the same data structure
returns it to its original state.

This is a good function for hiding information from someone who doesn't
want to see it or doesn't want to see it very much.  To really prevent
people from retrieving the information, use stronger encryption such as
that described in @xref{Cryptographic Functions}.

@strong{Portability Note:}  This function is unique to @theglibc{}.

@end deftypefun

@node Encode Binary Data
@section Encode Binary Data

To store or transfer binary data in environments which only support text
one has to encode the binary data by mapping the input bytes to
bytes in the range allowed for storing or transferring.  SVID
systems (and nowadays XPG compliant systems) provide minimal support for
this task.

@comment stdlib.h
@comment XPG
@deftypefun {char *} l64a (long int @var{n})
@safety{@prelim{}@mtunsafe{@mtasurace{:l64a}}@asunsafe{}@acsafe{}}
This function encodes a 32-bit input value using bytes from the
basic character set.  It returns a pointer to a 7 byte buffer which
contains an encoded version of @var{n}.  To encode a series of bytes the
user must copy the returned string to a destination buffer.  It returns
the empty string if @var{n} is zero, which is somewhat bizarre but
mandated by the standard.@*
@strong{Warning:} Since a static buffer is used this function should not
be used in multi-threaded programs.  There is no thread-safe alternative
to this function in the C library.@*
@strong{Compatibility Note:} The XPG standard states that the return
value of @code{l64a} is undefined if @var{n} is negative.  In the GNU
implementation, @code{l64a} treats its argument as unsigned, so it will
return a sensible encoding for any nonzero @var{n}; however, portable
programs should not rely on this.

To encode a large buffer @code{l64a} must be called in a loop, once for
each 32-bit word of the buffer.  For example, one could do something
like this:

@smallexample
char *
encode (const void *buf, size_t len)
@{
  /* @r{We know in advance how long the buffer has to be.} */
  unsigned char *in = (unsigned char *) buf;
  char *out = malloc (6 + ((len + 3) / 4) * 6 + 1);
  char *cp = out, *p;

  /* @r{Encode the length.} */
  /* @r{Using `htonl' is necessary so that the data can be}
     @r{decoded even on machines with different byte order.}
     @r{`l64a' can return a string shorter than 6 bytes, so }
     @r{we pad it with encoding of 0 (}'.'@r{) at the end by }
     @r{hand.} */

  p = stpcpy (cp, l64a (htonl (len)));
  cp = mempcpy (p, "......", 6 - (p - cp));

  while (len > 3)
    @{
      unsigned long int n = *in++;
      n = (n << 8) | *in++;
      n = (n << 8) | *in++;
      n = (n << 8) | *in++;
      len -= 4;
      p = stpcpy (cp, l64a (htonl (n)));
      cp = mempcpy (p, "......", 6 - (p - cp));
    @}
  if (len > 0)
    @{
      unsigned long int n = *in++;
      if (--len > 0)
        @{
          n = (n << 8) | *in++;
          if (--len > 0)
            n = (n << 8) | *in;
        @}
      cp = stpcpy (cp, l64a (htonl (n)));
    @}
  *cp = '\0';
  return out;
@}
@end smallexample

It is strange that the library does not provide the complete
functionality needed but so be it.

@end deftypefun

To decode data produced with @code{l64a} the following function should be
used.

@comment stdlib.h
@comment XPG
@deftypefun {long int} a64l (const char *@var{string})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The parameter @var{string} should contain a string which was produced by
a call to @code{l64a}.  The function processes at least 6 bytes of
this string, and decodes the bytes it finds according to the table
below.  It stops decoding when it finds a byte not in the table,
rather like @code{atoi}; if you have a buffer which has been broken into
lines, you must be careful to skip over the end-of-line bytes.

The decoded number is returned as a @code{long int} value.
@end deftypefun

The @code{l64a} and @code{a64l} functions use a base 64 encoding, in
which each byte of an encoded string represents six bits of an
input word.  These symbols are used for the base 64 digits:

@multitable {xxxxx} {xxx} {xxx} {xxx} {xxx} {xxx} {xxx} {xxx} {xxx}
@item              @tab 0 @tab 1 @tab 2 @tab 3 @tab 4 @tab 5 @tab 6 @tab 7
@item       0      @tab @code{.} @tab @code{/} @tab @code{0} @tab @code{1}
                   @tab @code{2} @tab @code{3} @tab @code{4} @tab @code{5}
@item       8      @tab @code{6} @tab @code{7} @tab @code{8} @tab @code{9}
                   @tab @code{A} @tab @code{B} @tab @code{C} @tab @code{D}
@item       16     @tab @code{E} @tab @code{F} @tab @code{G} @tab @code{H}
                   @tab @code{I} @tab @code{J} @tab @code{K} @tab @code{L}
@item       24     @tab @code{M} @tab @code{N} @tab @code{O} @tab @code{P}
                   @tab @code{Q} @tab @code{R} @tab @code{S} @tab @code{T}
@item       32     @tab @code{U} @tab @code{V} @tab @code{W} @tab @code{X}
                   @tab @code{Y} @tab @code{Z} @tab @code{a} @tab @code{b}
@item       40     @tab @code{c} @tab @code{d} @tab @code{e} @tab @code{f}
                   @tab @code{g} @tab @code{h} @tab @code{i} @tab @code{j}
@item       48     @tab @code{k} @tab @code{l} @tab @code{m} @tab @code{n}
                   @tab @code{o} @tab @code{p} @tab @code{q} @tab @code{r}
@item       56     @tab @code{s} @tab @code{t} @tab @code{u} @tab @code{v}
                   @tab @code{w} @tab @code{x} @tab @code{y} @tab @code{z}
@end multitable

This encoding scheme is not standard.  There are some other encoding
methods which are much more widely used (UU encoding, MIME encoding).
Generally, it is better to use one of these encodings.

@node Argz and Envz Vectors
@section Argz and Envz Vectors

@cindex argz vectors (string vectors)
@cindex string vectors, null-byte separated
@cindex argument vectors, null-byte separated
@dfn{argz vectors} are vectors of strings in a contiguous block of
memory, each element separated from its neighbors by null bytes
(@code{'\0'}).

@cindex envz vectors (environment vectors)
@cindex environment vectors, null-byte separated
@dfn{Envz vectors} are an extension of argz vectors where each element is a
name-value pair, separated by a @code{'='} byte (as in a Unix
environment).

@menu
* Argz Functions::              Operations on argz vectors.
* Envz Functions::              Additional operations on environment vectors.
@end menu

@node Argz Functions, Envz Functions, , Argz and Envz Vectors
@subsection Argz Functions

Each argz vector is represented by a pointer to the first element, of
type @code{char *}, and a size, of type @code{size_t}, both of which can
be initialized to @code{0} to represent an empty argz vector.  All argz
functions accept either a pointer and a size argument, or pointers to
them, if they will be modified.

The argz functions use @code{malloc}/@code{realloc} to allocate/grow
argz vectors, and so any argz vector created using these functions may
be freed by using @code{free}; conversely, any argz function that may
grow a string expects that string to have been allocated using
@code{malloc} (those argz functions that only examine their arguments or
modify them in place will work on any sort of memory).
@xref{Unconstrained Allocation}.

All argz functions that do memory allocation have a return type of
@code{error_t}, and return @code{0} for success, and @code{ENOMEM} if an
allocation error occurs.

@pindex argz.h
These functions are declared in the standard include file @file{argz.h}.

@comment argz.h
@comment GNU
@deftypefun {error_t} argz_create (char *const @var{argv}[], char **@var{argz}, size_t *@var{argz_len})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
The @code{argz_create} function converts the Unix-style argument vector
@var{argv} (a vector of pointers to normal C strings, terminated by
@code{(char *)0}; @pxref{Program Arguments}) into an argz vector with
the same elements, which is returned in @var{argz} and @var{argz_len}.
@end deftypefun

@comment argz.h
@comment GNU
@deftypefun {error_t} argz_create_sep (const char *@var{string}, int @var{sep}, char **@var{argz}, size_t *@var{argz_len})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
The @code{argz_create_sep} function converts the string
@var{string} into an argz vector (returned in @var{argz} and
@var{argz_len}) by splitting it into elements at every occurrence of the
byte @var{sep}.
@end deftypefun

@comment argz.h
@comment GNU
@deftypefun {size_t} argz_count (const char *@var{argz}, size_t @var{argz_len})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
Returns the number of elements in the argz vector @var{argz} and
@var{argz_len}.
@end deftypefun

@comment argz.h
@comment GNU
@deftypefun {void} argz_extract (const char *@var{argz}, size_t @var{argz_len}, char **@var{argv})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{argz_extract} function converts the argz vector @var{argz} and
@var{argz_len} into a Unix-style argument vector stored in @var{argv},
by putting pointers to every element in @var{argz} into successive
positions in @var{argv}, followed by a terminator of @code{0}.
@var{Argv} must be pre-allocated with enough space to hold all the
elements in @var{argz} plus the terminating @code{(char *)0}
(@code{(argz_count (@var{argz}, @var{argz_len}) + 1) * sizeof (char *)}
bytes should be enough).  Note that the string pointers stored into
@var{argv} point into @var{argz}---they are not copies---and so
@var{argz} must be copied if it will be changed while @var{argv} is
still active.  This function is useful for passing the elements in
@var{argz} to an exec function (@pxref{Executing a File}).
@end deftypefun

@comment argz.h
@comment GNU
@deftypefun {void} argz_stringify (char *@var{argz}, size_t @var{len}, int @var{sep})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{argz_stringify} converts @var{argz} into a normal string with
the elements separated by the byte @var{sep}, by replacing each
@code{'\0'} inside @var{argz} (except the last one, which terminates the
string) with @var{sep}.  This is handy for printing @var{argz} in a
readable manner.
@end deftypefun

@comment argz.h
@comment GNU
@deftypefun {error_t} argz_add (char **@var{argz}, size_t *@var{argz_len}, const char *@var{str})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
@c Calls strlen and argz_append.
The @code{argz_add} function adds the string @var{str} to the end of the
argz vector @code{*@var{argz}}, and updates @code{*@var{argz}} and
@code{*@var{argz_len}} accordingly.
@end deftypefun

@comment argz.h
@comment GNU
@deftypefun {error_t} argz_add_sep (char **@var{argz}, size_t *@var{argz_len}, const char *@var{str}, int @var{delim})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
The @code{argz_add_sep} function is similar to @code{argz_add}, but
@var{str} is split into separate elements in the result at occurrences of
the byte @var{delim}.  This is useful, for instance, for
adding the components of a Unix search path to an argz vector, by using
a value of @code{':'} for @var{delim}.
@end deftypefun

@comment argz.h
@comment GNU
@deftypefun {error_t} argz_append (char **@var{argz}, size_t *@var{argz_len}, const char *@var{buf}, size_t @var{buf_len})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
The @code{argz_append} function appends @var{buf_len} bytes starting at
@var{buf} to the argz vector @code{*@var{argz}}, reallocating
@code{*@var{argz}} to accommodate it, and adding @var{buf_len} to
@code{*@var{argz_len}}.
@end deftypefun

@comment argz.h
@comment GNU
@deftypefun {void} argz_delete (char **@var{argz}, size_t *@var{argz_len}, char *@var{entry})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
@c Calls free if no argument is left.
If @var{entry} points to the beginning of one of the elements in the
argz vector @code{*@var{argz}}, the @code{argz_delete} function will
remove this entry and reallocate @code{*@var{argz}}, modifying
@code{*@var{argz}} and @code{*@var{argz_len}} accordingly.  Note that as
destructive argz functions usually reallocate their argz argument,
pointers into argz vectors such as @var{entry} will then become invalid.
@end deftypefun

@comment argz.h
@comment GNU
@deftypefun {error_t} argz_insert (char **@var{argz}, size_t *@var{argz_len}, char *@var{before}, const char *@var{entry})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
@c Calls argz_add or realloc and memmove.
The @code{argz_insert} function inserts the string @var{entry} into the
argz vector @code{*@var{argz}} at a point just before the existing
element pointed to by @var{before}, reallocating @code{*@var{argz}} and
updating @code{*@var{argz}} and @code{*@var{argz_len}}.  If @var{before}
is @code{0}, @var{entry} is added to the end instead (as if by
@code{argz_add}).  Since the first element is in fact the same as
@code{*@var{argz}}, passing in @code{*@var{argz}} as the value of
@var{before} will result in @var{entry} being inserted at the beginning.
@end deftypefun

@comment argz.h
@comment GNU
@deftypefun {char *} argz_next (const char *@var{argz}, size_t @var{argz_len}, const char *@var{entry})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{argz_next} function provides a convenient way of iterating
over the elements in the argz vector @var{argz}.  It returns a pointer
to the next element in @var{argz} after the element @var{entry}, or
@code{0} if there are no elements following @var{entry}.  If @var{entry}
is @code{0}, the first element of @var{argz} is returned.

This behavior suggests two styles of iteration:

@smallexample
    char *entry = 0;
    while ((entry = argz_next (@var{argz}, @var{argz_len}, entry)))
      @var{action};
@end smallexample

(the double parentheses are necessary to make some C compilers shut up
about what they consider a questionable @code{while}-test) and:

@smallexample
    char *entry;
    for (entry = @var{argz};
         entry;
         entry = argz_next (@var{argz}, @var{argz_len}, entry))
      @var{action};
@end smallexample

Note that the latter depends on @var{argz} having a value of @code{0} if
it is empty (rather than a pointer to an empty block of memory); this
invariant is maintained for argz vectors created by the functions here.
@end deftypefun

@comment argz.h
@comment GNU
@deftypefun error_t argz_replace (@w{char **@var{argz}, size_t *@var{argz_len}}, @w{const char *@var{str}, const char *@var{with}}, @w{unsigned *@var{replace_count}})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
Replace any occurrences of the string @var{str} in @var{argz} with
@var{with}, reallocating @var{argz} as necessary.  If
@var{replace_count} is non-zero, @code{*@var{replace_count}} will be
incremented by the number of replacements performed.
@end deftypefun

@node Envz Functions, , Argz Functions, Argz and Envz Vectors
@subsection Envz Functions

Envz vectors are just argz vectors with additional constraints on the form
of each element; as such, argz functions can also be used on them, where it
makes sense.

Each element in an envz vector is a name-value pair, separated by a @code{'='}
byte; if multiple @code{'='} bytes are present in an element, those
after the first are considered part of the value, and treated like all other
non-@code{'\0'} bytes.

If @emph{no} @code{'='} bytes are present in an element, that element is
considered the name of a ``null'' entry, as distinct from an entry with an
empty value: @code{envz_get} will return @code{0} if given the name of null
entry, whereas an entry with an empty value would result in a value of
@code{""}; @code{envz_entry} will still find such entries, however.  Null
entries can be removed with the @code{envz_strip} function.

As with argz functions, envz functions that may allocate memory (and thus
fail) have a return type of @code{error_t}, and return either @code{0} or
@code{ENOMEM}.

@pindex envz.h
These functions are declared in the standard include file @file{envz.h}.

@comment envz.h
@comment GNU
@deftypefun {char *} envz_entry (const char *@var{envz}, size_t @var{envz_len}, const char *@var{name})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{envz_entry} function finds the entry in @var{envz} with the name
@var{name}, and returns a pointer to the whole entry---that is, the argz
element which begins with @var{name} followed by a @code{'='} byte.  If
there is no entry with that name, @code{0} is returned.
@end deftypefun

@comment envz.h
@comment GNU
@deftypefun {char *} envz_get (const char *@var{envz}, size_t @var{envz_len}, const char *@var{name})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{envz_get} function finds the entry in @var{envz} with the name
@var{name} (like @code{envz_entry}), and returns a pointer to the value
portion of that entry (following the @code{'='}).  If there is no entry with
that name (or only a null entry), @code{0} is returned.
@end deftypefun

@comment envz.h
@comment GNU
@deftypefun {error_t} envz_add (char **@var{envz}, size_t *@var{envz_len}, const char *@var{name}, const char *@var{value})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
@c Calls envz_remove, which calls enz_entry and argz_delete, and then
@c argz_add or equivalent code that reallocs and appends name=value.
The @code{envz_add} function adds an entry to @code{*@var{envz}}
(updating @code{*@var{envz}} and @code{*@var{envz_len}}) with the name
@var{name}, and value @var{value}.  If an entry with the same name
already exists in @var{envz}, it is removed first.  If @var{value} is
@code{0}, then the new entry will be the special null type of entry
(mentioned above).
@end deftypefun

@comment envz.h
@comment GNU
@deftypefun {error_t} envz_merge (char **@var{envz}, size_t *@var{envz_len}, const char *@var{envz2}, size_t @var{envz2_len}, int @var{override})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
The @code{envz_merge} function adds each entry in @var{envz2} to @var{envz},
as if with @code{envz_add}, updating @code{*@var{envz}} and
@code{*@var{envz_len}}.  If @var{override} is true, then values in @var{envz2}
will supersede those with the same name in @var{envz}, otherwise not.

Null entries are treated just like other entries in this respect, so a null
entry in @var{envz} can prevent an entry of the same name in @var{envz2} from
being added to @var{envz}, if @var{override} is false.
@end deftypefun

@comment envz.h
@comment GNU
@deftypefun {void} envz_strip (char **@var{envz}, size_t *@var{envz_len})
@safety{@prelim{}@mtsafe{}@assafe{}@acsafe{}}
The @code{envz_strip} function removes any null entries from @var{envz},
updating @code{*@var{envz}} and @code{*@var{envz_len}}.
@end deftypefun

@comment envz.h
@comment GNU
@deftypefun {void} envz_remove (char **@var{envz}, size_t *@var{envz_len}, const char *@var{name})
@safety{@prelim{}@mtsafe{}@asunsafe{@ascuheap{}}@acunsafe{@acsmem{}}}
The @code{envz_remove} function removes an entry named @var{name} from
@var{envz}, updating @code{*@var{envz}} and @code{*@var{envz_len}}.
@end deftypefun

@c FIXME this are undocumented:
@c strcasecmp_l @safety{@mtsafe{}@assafe{}@acsafe{}} see strcasecmp