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
|
/*
* This source file is part of the bstring string library. This code was
* written by Paul Hsieh in 2002-2004, and is covered by the BSD open source
* license. Refer to the accompanying documentation for details on usage and
* license.
*/
/*
* bstrlib.c
*
* This file is the core module for implementing the bstring functions.
*/
#include <stdio.h>
#include <stdarg.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include "bstrlib.h"
/* Optionally include a mechanism for debugging memory */
#if defined(MEMORY_DEBUG) || defined(BSTRLIB_MEMORY_DEBUG)
#include "memdbg.h"
#endif
/* Just a length safe wrapper for memmove. */
#define bBlockCopy(D,S,L) { if ((L) > 0) memmove ((D),(S),(L)); }
/* Compute the snapped size for a given requested size. By snapping to powers
of 2 like this, repeated reallocations are avoided. */
static int snapUpSize (int i) {
if (i < 8) {
i = 8;
} else {
unsigned int j;
j = i;
/* Assumes your system is at least 32 bits, and your string is
at most 4GB is size. */
j |= (j >> 1);
j |= (j >> 2);
j |= (j >> 4);
j |= (j >> 8);
j |= (j >> 16);
i = j + 1; /* Least power of two greater than i */
}
return i;
}
/* int balloc (bstring b, int len)
*
* Increase the size of the memory backing the bstring b to at least len.
*/
int balloc (bstring b, int len) {
if (b == NULL || b->data == NULL || b->slen < 0 || b->mlen < 0 ||
b->mlen < b->slen || len <= 0) {
return BSTR_ERR;
}
if (len >= b->mlen) {
unsigned char * x;
len = snapUpSize (len);
/* Assume probability of a non-moving realloc is 0.125 */
if (7 * b->mlen < 8 * b->slen) {
/* If slen is close to mlen in size then use realloc to reduce
the memory defragmentation */
x = (unsigned char *) realloc (b->data, len);
if (x == NULL) return BSTR_ERR;
} else {
/* If slen is not close to mlen then avoid the penalty of copying
the extra bytes that are allocated, but not considered part of
the string */
x = (unsigned char *) malloc (len);
if (x == NULL) {
x = (unsigned char *) realloc (b->data, len);
if (x == NULL) return BSTR_ERR;
} else {
if (b->slen) memcpy ((char *) x, (char *) b->data, b->slen);
free (b->data);
}
}
b->data = x;
b->mlen = len;
b->data[b->slen] = '\0';
}
return BSTR_OK;
}
/* bstring bfromcstr (const char * str)
*
* Create a bstring which contains the content of the '\0' terminated char *
* buffer str.
*/
bstring bfromcstr (const char * str) {
bstring b;
int i,j;
if (str == NULL) return NULL;
b = (bstring) malloc (sizeof (struct tagbstring));
if (b == NULL) return NULL;
j = (int) (strlen) (str);
b->slen = j;
i = j + (2 - (j != 0));
i = snapUpSize (i);
b->mlen = i;
b->data = (unsigned char *) malloc (b->mlen);
if (b->data == NULL) {
free (b);
return NULL;
}
memcpy (b->data, str, j+1);
return b;
}
/* bstring blk2bstr (const void * blk, int len)
*
* Create a bstring which contains the content of the block blk of length
* len.
*/
bstring blk2bstr (const void * blk, int len) {
bstring b;
int i;
if (blk == NULL || len < 0) return NULL;
b = (bstring) malloc (sizeof (struct tagbstring));
if (b == NULL) return NULL;
b->slen = len;
i = len + (2 - (len != 0));
i = snapUpSize (i);
b->mlen = i;
b->data = (unsigned char *) malloc (b->mlen) ;
if (b->data == NULL) {
free (b);
return NULL;
}
if (len > 0) memcpy (b->data, blk, len);
b->data[len] = '\0';
return b;
}
/* char * bstr2cstr (const bstring s, char z)
*
* Create a '\0' terminated char * buffer which is equal to the contents of
* the bstring s, except that any contained '\0' characters are converted to
* the character in z. This returned value should be freed with a free()
* call, by the calling application.
*/
char * bstr2cstr (const bstring b, char z) {
int i,l;
char * r;
if (b == NULL || b->slen < 0 || b->data == NULL) return NULL;
l = b->slen;
r = (char *) malloc (l + 1);
if (r == NULL) return r;
for (i=0; i < l; i ++) {
r[i] = (char) ((b->data[i] == '\0') ? z : (char) (b->data[i]));
}
r[l] = '\0';
return r;
}
/* int bcstrfree (const char * s)
*
* Frees a C-string generated by bstr2cstr (). This is normally unnecessary
* since it just wraps a call to free (), however, if malloc () and free ()
* have been redefined as a macros within the bstrlib module (via defining
* them in memdbg.h after defining BSTRLIB_MEMORY_DEBUG) with some
* difference in behaviour from the std library functions, then this allows
* a correct way of freeing the memory that allows higher level code to be
* independent from these macro redefinitions.
*/
int bcstrfree (char * s) {
if (s) {
free (s);
return BSTR_OK;
}
return BSTR_ERR;
}
/* int bconcat (bstring b0, const bstring b1)
*
* Concatenate the bstring b1 to the bstring b0.
*/
int bconcat (bstring b0, const bstring b1) {
int len, d;
if (b0 == NULL || b1 == NULL) return BSTR_ERR;
d = b0->slen;
len = b1->slen;
if ((d | (b0->mlen - d) | len) < 0) return BSTR_ERR;
if (balloc (b0, d + len + 1) != BSTR_OK) return BSTR_ERR;
bBlockCopy (&b0->data[d], &b1->data[0], len);
b0->data[d + len] = '\0';
b0->slen += len;
return 0;
}
/* int bconchar (bstring b, char c)
*
* Concatenate the single character c to the bstring b.
*/
int bconchar (bstring b, char c) {
int d;
if (b == NULL) return BSTR_ERR;
d = b->slen;
if ((d | (b->mlen - d)) < 0 || balloc (b, d + 2) != BSTR_OK) return BSTR_ERR;
b->data[d] = (unsigned char) c;
b->data[d + 1] = '\0';
b->slen++;
return 0;
}
/* int bcatcstr (bstring b, const char * s)
*
* Concatenate a char * string to a bstring.
*/
int bcatcstr (bstring b, const char * s) {
struct tagbstring t;
char * d;
int i, l;
if (b == NULL || b->data == NULL || b->slen < 0 || s == NULL) return BSTR_ERR;
/* Optimistically concatenate directly */
l = b->mlen - b->slen;
d = (char *) &b->data[b->slen];
for (i=0; i < l; i++) {
if ((*d++ = *s++) == '\0') {
b->slen += i;
return BSTR_OK;
}
}
b->slen += i;
/* Need to explicitely resize and concatenate tail */
cstr2tbstr (t, s);
return bconcat (b, &t);
}
/* int bcatblk (bstring b, unsigned char * s, int len)
*
* Concatenate a fixed length buffer to a bstring.
*/
int bcatblk (bstring b, const unsigned char * s, int len) {
struct tagbstring t;
if (s == NULL || len < 0) return BSTR_ERR;
blk2tbstr (t, s, len);
return bconcat (b, &t);
}
/* bstring bstrcpy (const bstring b)
*
* Create a copy of the bstring b.
*/
bstring bstrcpy (const bstring b) {
bstring b0;
int i,j;
/* Attempted to copy an invalid string? */
if (b == NULL || b->slen < 0 || b->data == NULL) return NULL;
b0 = (bstring) malloc (sizeof (struct tagbstring));
if (b0 == NULL) {
/* Unable to allocate memory for string header */
return NULL;
}
i = b->slen;
j = snapUpSize (i + 1);
b0->data = (unsigned char *) malloc (j);
if (b0->data == NULL) {
j = i + 1;
b0->data = (unsigned char *) malloc (j);
if (b0->data == NULL) {
/* Unable to allocate memory for string data */
free (b0);
return NULL;
}
}
b0->mlen = j;
b0->slen = i;
if (i) memcpy ((char *) b0->data, (char *) b->data, i);
b0->data[b0->slen] = '\0';
return b0;
}
/* int bassign (bstring a, const bstring b)
*
* Overwrite the string a with the contents of string b.
*/
int bassign (bstring a, const bstring b) {
if (b == NULL || b->data == NULL || b->slen < 0 )
return BSTR_ERR;
if (b->slen != 0) {
if (balloc (a, b->slen) != BSTR_OK) return BSTR_ERR;
memmove (a->data, b->data, b->slen);
} else {
if (a == NULL || a->data == NULL || a->mlen < a->slen ||
a->slen < 0 || a->mlen == 0)
return BSTR_ERR;
}
a->data[b->slen] = '\0';
a->slen = b->slen;
return BSTR_OK;
}
#define ascii(c) ((unsigned char)(c) < 128)
#define upcase(c) ((c) + (((ascii(c) && islower(c)) ? ('A'-'a') : 0)))
#define downcase(c) ((c) + (((ascii(c) && isupper(c)) ? ('a'-'A') : 0)))
/* int btoupper (bstring b)
*
* Convert contents of bstring to upper case.
*/
int btoupper (bstring b) {
int i, len;
if (b == NULL || b->data == NULL || b->mlen < b->slen ||
b->slen < 0) return BSTR_ERR;
for (i=0, len = b->slen; i < len; i++) {
b->data[i] = (unsigned char) upcase (b->data[i]);
}
return BSTR_OK;
}
/* int btolower (bstring b)
*
* Convert contents of bstring to lower case.
*/
int btolower (bstring b) {
int i, len;
if (b == NULL || b->data == NULL || b->mlen < b->slen ||
b->slen < 0) return BSTR_ERR;
for (i=0, len = b->slen; i < len; i++) {
b->data[i] = (unsigned char) downcase (b->data[i]);
}
return 0;
}
/* int bstricmp (const bstring b0, const bstring b1)
*
* Compare two strings without differentiating between case. The return
* value is the difference of the values of the characters where the two
* strings first differ, (taking a '\0' to be the character at the end of
* any bstring) otherwise 0 is returned indicating that the strings are
* equal.
*/
int bstricmp (const bstring b0, const bstring b1) {
int i, v, n;
if (bdata (b0) == NULL || b0->slen < 0 ||
bdata (b1) == NULL || b1->slen < 0) return SHRT_MIN;
n = b0->slen; if (n > b1->slen) n = b1->slen;
if (b0->slen == b1->slen && b0->data == b1->data) return 0;
for (i = 0; i < n; i ++) {
v = ((char) downcase (b0->data[i]));
v -= ((char) downcase (b1->data[i]));
if (v != 0) return v;
if (b0->data[i] == '\0') return 0;
}
if (b0->slen > n) return ((char) downcase (b0->data[n]));
if (b1->slen > n) return - ((char) downcase (b1->data[n]));
return 0;
}
/* int bstrnicmp (const bstring b0, const bstring b1, int n)
*
* Compare two strings without differentiating between case for at most n
* characters. If the position where the two strings first differ is
* before the nth position, the return value is the difference of the values
* of the characters, (taking a '\0' to be the character at the end of any
* bstring) otherwise 0 is returned.
*/
int bstrnicmp (const bstring b0, const bstring b1, int n) {
int i, v, m;
if (bdata (b0) == NULL || b0->slen < 0 ||
bdata (b1) == NULL || b1->slen < 0 || n < 0) return SHRT_MIN;
m = n;
if (m > b0->slen) m = b0->slen;
if (m > b1->slen) m = b1->slen;
if (b0->data != b1->data) {
for (i = 0; i < m; i ++) {
v = ((char) downcase (b0->data[i]));
v -= ((char) downcase (b1->data[i]));
if (v != 0) return v;
if (b0->data[i] == '\0') return 0;
}
}
if (n == m || b0->slen == b1->slen) return 0;
if (b0->slen > m) return (char) downcase (b0->data[m]);
return - (char) downcase (b1->data[m]);
}
/* int biseqcaseless (const bstring b0, const bstring b1)
*
* Compare two strings for equality without differentiating between case.
* If the strings differ other than in case, 0 is returned, if the strings
* are the same, 1 is returned, if there is an error, -1 is returned. If
* the length of the strings are different, this function is O(1). '\0'
* termination characters are not treated in any special way.
*/
int biseqcaseless (const bstring b0, const bstring b1) {
int i, n;
if (bdata (b0) == NULL || b0->slen < 0 ||
bdata (b1) == NULL || b1->slen < 0) return BSTR_ERR;
if (b0->slen != b1->slen) return 0;
if (b0->data == b1->data || b0->slen == 0) return 1;
for (i=0, n=b0->slen; i < n; i++) {
if (b0->data[i] != b1->data[i]) {
unsigned char c = (unsigned char) downcase (b0->data[i]);
if (c != (unsigned char) downcase (b1->data[i])) return 0;
}
}
return 1;
}
/* int biseq (const bstring b0, const bstring b1)
*
* Compare the string b0 and b1. If the strings differ, 0 is returned, if
* the strings are the same, 1 is returned, if there is an error, -1 is
* returned. If the length of the strings are different, this function is
* O(1). '\0' termination characters are not treated in any special way.
*/
int biseq (const bstring b0, const bstring b1) {
if (b0 == NULL || b1 == NULL || b0->data == NULL || b1->data == NULL ||
b0->slen < 0 || b1->slen < 0) return BSTR_ERR;
if (b0->slen != b1->slen) return 0;
if (b0->data == b1->data || b0->slen == 0) return 1;
return !memcmp (b0->data, b1->data, b0->slen);
}
/* int biseqcstr (const bstring b, const char *s)
*
* Compare the bstring b and char * string s. The C string s must be '\0'
* terminated at exactly the length of the bstring b, and the contents
* between the two must be identical with the bstring b with no '\0'
* characters for the two contents to be considered equal. This is
* equivalent to the condition that their current contents will be always be
* equal when comparing them in the same format after converting one or the
* other. If the strings are equal 1 is returned, if they are unequal 0 is
* returned and if there is a detectable error BSTR_ERR is returned.
*/
int biseqcstr (const bstring b, const char * s) {
int i;
if (b == NULL || s == NULL || b->data == NULL || b->slen < 0) return BSTR_ERR;
for (i=0; i < b->slen; i++) {
if (s[i] == '\0' || b->data[i] != s[i]) return 0;
}
return s[i] == '\0';
}
/* int bstrcmp (const bstring b0, const bstring b1)
*
* Compare the string b0 and b1. If there is an error, SHRT_MIN is returned,
* otherwise a value less than or greater than zero, indicating that the
* string pointed to by b0 is lexicographically less than or greater than
* the string pointed to by b1 is returned. If the the string lengths are
* unequal but the characters up until the length of the shorter are equal
* then a value less than, or greater than zero, indicating that the string
* pointed to by b0 is shorter or longer than the string pointed to by b1 is
* returned. 0 is returned if and only if the two strings are the same. If
* the length of the strings are different, this function is O(n). Like its
* standard C library counter part strcmp, the comparison does not proceed
* past any '\0' termination characters encountered.
*/
int bstrcmp (const bstring b0, const bstring b1) {
int i, v, n;
if (b0 == NULL || b1 == NULL || b0->data == NULL || b1->data == NULL ||
b0->slen < 0 || b1->slen < 0) return SHRT_MIN;
n = b0->slen; if (n > b1->slen) n = b1->slen;
if (b0->slen == b1->slen && (b0->data == b1->data || b0->slen == 0))
return 0;
for (i = 0; i < n; i ++) {
v = ((char) b0->data[i]) - ((char) b1->data[i]);
if (v != 0) return v;
if (b0->data[i] == '\0') return 0;
}
if (b0->slen > n) return 1;
if (b1->slen > n) return -1;
return 0;
}
/* int bstrncmp (const bstring b0, const bstring b1, int n)
*
* Compare the string b0 and b1 for at most n characters. If there is an
* error, SHRT_MIN is returned, otherwise a value is returned as if b0 and
* b1 were first truncated to at most n characters then bstrcmp was called
* with these new strings are paremeters. If the length of the strings are
* different, this function is O(n). Like its standard C library counter
* part strcmp, the comparison does not proceed past any '\0' termination
* characters encountered.
*/
int bstrncmp (const bstring b0, const bstring b1, int n) {
int i, v, m;
if (b0 == NULL || b1 == NULL || b0->data == NULL || b1->data == NULL ||
b0->slen < 0 || b1->slen < 0) return SHRT_MIN;
m = n;
if (m > b0->slen) m = b0->slen;
if (m > b1->slen) m = b1->slen;
if (b0->data != b1->data) {
for (i = 0; i < m; i ++) {
v = ((char) b0->data[i]) - ((char) b1->data[i]);
if (v != 0) return v;
if (b0->data[i] == '\0') return 0;
}
}
if (n == m || b0->slen == b1->slen) return 0;
if (b0->slen > m) return 1;
return -1;
}
/* bstring bmidstr (const bstring b, int left, int len)
*
* Create a bstring which is the substring of b starting from position left
* and running for a length len (clamped by the end of the bstring b.) If
* b is detectably invalid, then NULL is returned. The section described
* by (left, len) is clamped to the boundaries of b.
*/
bstring bmidstr (const bstring b, int left, int len) {
if (b == NULL || b->slen < 0 || b->data == NULL) return NULL;
if (left < 0) {
len += left;
left = 0;
}
if (len > b->slen - left) len = b->slen - left;
if (len <= 0) return bfromcstr ("");
return blk2bstr (b->data + left, len);
}
/* int bdelete (bstring b, int pos, int len)
*
* Removes characters from pos to pos+len-1 inclusive and shifts the tail of
* the bstring starting from pos+len to pos. len must be positive for this
* call to have any effect. The section of the string described by (pos,
* len) is clamped to boundaries of the bstring b.
*/
int bdelete (bstring b, int pos, int len) {
/* Clamp to left side of bstring */
if (pos < 0) {
len += pos;
pos = 0;
}
if (len < 0 || b == NULL || b->data == NULL || b->slen < 0 || b->mlen < b->slen)
return BSTR_ERR;
if (len > 0 && pos < b->slen) {
if (pos + len >= b->slen) {
b->slen = pos;
} else {
bBlockCopy ((char *) (b->data + pos),
(char *) (b->data + pos + len),
b->slen - (pos+len));
b->slen -= len;
}
b->data[b->slen] = '\0';
}
return BSTR_OK;
}
/* int bdestroy (bstring b)
*
* free up the bstring. Note that if b is detectably invalid or not writable
* then no action is performed and BSTR_ERR is returned. Like a freed memory
* allocation, dereferences, writes or any other action on b after it has
* been bdestroyed is undefined.
*/
int bdestroy (bstring b) {
if (b == NULL || b->slen < 0 || b->mlen <= 0 || b->data == NULL)
return BSTR_ERR;
free (b->data);
/* In case there is any stale usage, there is one more chance to
notice this error. */
b->slen = -1;
b->mlen = -__LINE__;
b->data = NULL;
free (b);
return 0;
}
/* int binstr (const bstring b1, int pos, const bstring b2)
*
* Search for the bstring b2 in b1 starting from position pos, and searching
* forward. If it is found then return with the first position where it is
* found, otherwise return BSTR_ERR. Note that this is just a brute force
* string searcher that does not attempt clever things like the Boyer-Moore
* search algorithm. Because of this there are many degenerate cases where
* this can take much longer than it needs to.
*/
int binstr (const bstring b1, int pos, const bstring b2) {
int j, i, l, ll;
unsigned char * d0, * d1;
if (b1 == NULL || b1->data == NULL || b1->slen < 0 ||
b2 == NULL || b2->data == NULL || b2->slen < 0) return BSTR_ERR;
if (b1->slen == pos) return (b2->slen == 0)?pos:BSTR_ERR;
if (b1->slen < pos || pos < 0) return BSTR_ERR;
if (b2->slen == 0) return pos;
l = b1->slen - b2->slen + 1;
/* No space to find such a string? */
if (l <= pos) return BSTR_ERR;
/* An obvious alias case */
if (b1->data == b2->data && pos == 0) return 0;
i = pos;
j = 0;
d0 = b2->data;
d1 = b1->data;
ll = b2->slen;
for (;;) {
if (d0[j] == d1[i + j]) {
j ++;
if (j >= ll) return i;
} else {
i ++;
if (i >= l) break;
j=0;
}
}
return BSTR_ERR;
}
/* int binstrr (const bstring b1, int pos, const bstring b2)
*
* Search for the bstring b2 in b1 starting from position pos, and searching
* backward. If it is found then return with the first position where it is
* found, otherwise return BSTR_ERR. Note that this is just a brute force
* string searcher that does not attempt clever things like the Boyer-Moore
* search algorithm. Because of this there are many degenerate cases where
* this can take much longer than it needs to.
*/
int binstrr (const bstring b1, int pos, const bstring b2) {
int j, i, l;
unsigned char * d0, * d1;
if (b1 == NULL || b1->data == NULL || b1->slen < 0 ||
b2 == NULL || b2->data == NULL || b2->slen < 0) return BSTR_ERR;
if (b1->slen == pos && b2->slen == 0) return pos;
if (b1->slen < pos || pos < 0) return BSTR_ERR;
if (b2->slen == 0) return pos;
/* Obvious alias case */
if (b1->data == b2->data && pos == 0 && b2->slen <= b1->slen) return 0;
i = pos;
if ((l = b1->slen - b2->slen) < 0) return BSTR_ERR;
/* If no space to find such a string then snap back */
if (l + 1 <= i) i = l;
j = 0;
d0 = b2->data;
d1 = b1->data;
l = b2->slen;
for (;;) {
if (d0[j] == d1[i + j]) {
j ++;
if (j >= l) return i;
} else {
i --;
if (i < 0) break;
j=0;
}
}
return BSTR_ERR;
}
/* int bstrchr (const bstring b, int c)
*
* Search for the character c in b forwards from the start of the string.
*/
int bstrchr (const bstring b, int c) {
unsigned char * p;
if (b == NULL || b->data == NULL || b->slen <= 0) return BSTR_ERR;
p = memchr (b->data, (unsigned char) c, b->slen);
if (p) return (int) (p - b->data);
return BSTR_ERR;
}
/* int bstrrchr (const bstring b, int c)
*
* Search for the character c in b backwards from the end of the string.
*/
int bstrrchr (const bstring b, int c) {
int i;
if (b == NULL || b->data == NULL || b->slen <= 0) return BSTR_ERR;
for (i=b->slen-1; i >= 0; i--) {
if (b->data[i] == (unsigned char) c) return i;
}
return BSTR_ERR;
}
#define LONG_LOG_BITS_QTY (5)
#define LONG_BITS_QTY (1 << LONG_LOG_BITS_QTY)
#define LONG_TYPE unsigned long
struct charField { LONG_TYPE content[(1 << CHAR_BIT) / LONG_BITS_QTY]; };
#define testInCharField(cf,c) ((cf)->content[(c) >> LONG_LOG_BITS_QTY] & (((long)1) << ((c) & (LONG_BITS_QTY-1))))
/* Convert a bstring to charField */
static int buildCharField (struct charField * cf, const bstring b1) {
int i;
if (b1 == NULL || b1->data == NULL || b1->slen <= 0) return BSTR_ERR;
memset ((void *) &cf->content, 0, sizeof (struct charField));
for (i=0; i < b1->slen; i++) {
unsigned int c = (unsigned int) b1->data[i];
cf->content[c >> LONG_LOG_BITS_QTY] |= ((LONG_TYPE) 1) << (c & (LONG_BITS_QTY-1));
}
return 0;
}
static void invertCharField (struct charField * cf) {
int i;
for (i=0; i < ((1 << CHAR_BIT) / LONG_BITS_QTY); i++) cf->content[i] = ~cf->content[i];
}
/* Inner engine for binchr */
static int binchrCF (const unsigned char * data, int len, int pos, const struct charField * cf) {
int i;
for (i=pos; i < len; i++) {
unsigned int c = (unsigned int) data[i];
if (testInCharField (cf, c)) return i;
}
return BSTR_ERR;
}
/* int binchr (const bstring b0, int pos, const bstring b1);
*
* Search for the first position in b0 starting from pos or after, in which
* one of the characters in b1 is found and return it. If such a position
* does not exist in b0, then BSTR_ERR is returned.
*/
int binchr (const bstring b0, int pos, const bstring b1) {
struct charField chrs;
if (pos < 0 || b0 == NULL || b0->data == NULL ||
b0->slen <= pos) return BSTR_ERR;
if (buildCharField (&chrs, b1) < 0) return BSTR_ERR;
return binchrCF (b0->data, b0->slen, pos, &chrs);
}
/* Inner engine for binchrr */
static int binchrrCF (const unsigned char * data, int pos, const struct charField * cf) {
int i;
for (i=pos; i >= 0; i--) {
unsigned int c = (unsigned int) data[i];
if (testInCharField (cf, c)) return i;
}
return BSTR_ERR;
}
/* int binchrr (const bstring b0, int pos, const bstring b1);
*
* Search for the last position in b0 no greater than pos, in which one of
* the characters in b1 is found and return it. If such a position does not
* exist in b0, then BSTR_ERR is returned.
*/
int binchrr (const bstring b0, int pos, const bstring b1) {
struct charField chrs;
if (pos < 0 || b0 == NULL || b0->data == NULL ||
b0->slen < pos) return BSTR_ERR;
if (pos == b0->slen) pos--;
if (buildCharField (&chrs, b1) < 0) return BSTR_ERR;
return binchrrCF (b0->data, pos, &chrs);
}
/* int bninchr (const bstring b0, int pos, const bstring b1);
*
* Search for the first position in b0 starting from pos or after, in which
* none of the characters in b1 is found and return it. If such a position
* does not exist in b0, then BSTR_ERR is returned.
*/
int bninchr (const bstring b0, int pos, const bstring b1) {
struct charField chrs;
if (pos < 0 || b0 == NULL || b0->data == NULL ||
b0->slen <= pos) return BSTR_ERR;
if (buildCharField (&chrs, b1) < 0) return BSTR_ERR;
invertCharField (&chrs);
return binchrCF (b0->data, b0->slen, pos, &chrs);
}
/* int bninchrr (const bstring b0, int pos, const bstring b1);
*
* Search for the last position in b0 no greater than pos, in which none of
* the characters in b1 is found and return it. If such a position does not
* exist in b0, then BSTR_ERR is returned.
*/
int bninchrr (const bstring b0, int pos, const bstring b1) {
struct charField chrs;
if (pos < 0 || b0 == NULL || b0->data == NULL ||
b0->slen < pos) return BSTR_ERR;
if (pos == b0->slen) pos--;
if (buildCharField (&chrs, b1) < 0) return BSTR_ERR;
invertCharField (&chrs);
return binchrrCF (b0->data, pos, &chrs);
}
/* int bsetstr (bstring b0, int pos, bstring b1, unsigned char fill)
*
* Overwrite the string b0 starting at position pos with the string b1. If
* the position pos is past the end of b0, then the character "fill" is
* appended as necessary to make up the gap between the end of b0 and pos.
* If b1 is NULL, it behaves as if it were a 0-length string.
*/
int bsetstr (bstring b0, int pos, const bstring b1, unsigned char fill) {
int d;
int newlen;
if (pos < 0 || b0 == NULL || b0->slen < 0 || b0->mlen < b0->slen) return BSTR_ERR;
if (b1 != NULL && (b1->slen < 0 || b1->data == NULL)) return BSTR_ERR;
/* Aliasing case */
if ((b1 != NULL) && (b0->data == b1->data) && (pos < b0->slen)) {
bstring tmp = bstrcpy (b1);
if (tmp == NULL) return BSTR_ERR;
d = bsetstr (b0, pos, tmp, fill);
bdestroy (tmp);
return d;
}
/* Increase memory size if necessary */
d = pos + blength (b1);
if (balloc (b0, d + 1) != BSTR_OK) return BSTR_ERR;
newlen = b0->slen;
/* Fill in "fill" character as necessary */
if (pos > newlen) {
int i;
for (i = b0->slen; i < pos; i ++) b0->data[i] = fill;
newlen = pos;
}
/* Copy b1 to position pos in b0. */
if (b1 != NULL) {
bBlockCopy ((char *) (b0->data + pos), (char *) b1->data, b1->slen);
}
/* Indicate the potentially increased size of b0 */
if (d > newlen) newlen = d;
b0->slen = newlen;
b0->data[newlen] = '\0';
return BSTR_OK;
}
/* int binsert (bstring b1, int pos, bstring b2, unsigned char fill)
*
* Inserts the string b2 into b1 at position pos. If the position pos is
* past the end of b1, then the character "fill" is appended as necessary to
* make up the gap between the end of b1 and pos. Unlike bsetstr, binsert
* does not allow b2 to be NULL.
*/
int binsert (bstring b1, int pos, const bstring b2, unsigned char fill) {
int d, l;
if (pos < 0 || b1 == NULL || b2 == NULL || b1->slen < 0 ||
b2->slen < 0 || b1->mlen < b1->slen) return BSTR_ERR;
/* Aliasing case */
if ((unsigned int)(b2->data - b1->data) < (unsigned int)b1->slen) {
bstring tmp;
d = binsert (b1, pos, tmp = bstrcpy (b2), fill);
bdestroy (tmp);
return d;
}
/* Compute the two possible end pointers */
d = b1->slen + b2->slen;
l = pos + b2->slen;
if (l > d) {
/* Inserting past the end of the string */
if (balloc (b1, l + 1) != BSTR_OK) return BSTR_ERR;
for (d = b1->slen; d < pos; d++) b1->data[d] = fill;
b1->slen = l;
} else {
/* Inserting in the middle of the string */
if (balloc (b1, d + 1) != BSTR_OK) return BSTR_ERR;
for (l = d - 1; l >= pos + b2->slen; l--) {
b1->data[l] = b1->data[l - b2->slen];
}
b1->slen = d;
}
bBlockCopy (b1->data + pos, b2->data, b2->slen);
b1->data[b1->slen] = '\0';
return 0;
}
/* int breplace (bstring b1, int pos, int len, bstring b2,
* unsigned char fill)
*
* Replace a section of a string from pos for a length len with the string b2.
* fill is used is pos > b1->slen.
*/
int breplace (bstring b1, int pos, int len, const bstring b2,
unsigned char fill) {
int ret;
if (pos < 0 || len < 0 || b1 == NULL || b2 == NULL ||
b1->data == NULL || b2->data == NULL || b1->slen < 0 ||
b2->slen < 0 || b1->mlen < b1->slen) return BSTR_ERR;
/* Straddles the end? */
if (pos + len >= b1->slen) {
if ((ret = bsetstr (b1, pos, b2, fill)) < 0) return ret;
if (pos + b2->slen < b1->slen) {
b1->slen = pos + b2->slen;
b1->data[b1->slen] = '\0';
}
return ret;
}
/* Aliasing case */
if ((unsigned int)(b2->data - b1->data) < (unsigned int)b1->slen) {
bstring tmp;
ret = breplace (b1, pos, len, tmp = bstrcpy (b2), fill);
bdestroy (tmp);
return ret;
}
if (b2->slen > len) {
if (balloc (b1, b1->slen + b2->slen - len) != BSTR_OK) return BSTR_ERR;
}
if (b2->slen != len) memmove (b1->data + pos + b2->slen, b1->data + pos + len, b1->slen - (pos + len));
memcpy (b1->data + pos, b2->data, b2->slen);
b1->slen += b2->slen - len;
b1->data[b1->slen] = '\0';
return BSTR_OK;
}
/* int bfindreplace (bstring b, const bstring find, const bstring repl,
* int pos)
*
* Replace all occurrences of a find string with a replace string after a
* given point in a bstring.
*/
int bfindreplace (bstring b, const bstring find, const bstring repl, int pos) {
int i, ret, slen, mlen, delta, acc;
int * d;
if (b == NULL || b->data == NULL || find == NULL ||
find->data == NULL || repl == NULL || repl->data == NULL ||
pos < 0 || find->slen <= 0 || b->mlen < 0 || b->slen > b->mlen ||
b->slen < 0 || repl->slen < 0) return BSTR_ERR;
if (pos > b->slen - find->slen) return 0;
/* Alias with find string */
i = find->data - b->data;
if (pos - find->slen < i && i < b->slen) {
bstring t;
i = bfindreplace (b, t = bstrcpy (find), repl, pos);
bdestroy (t);
return i;
}
/* Alias with repl string */
i = repl->data - b->data;
if (pos - repl->slen < i && i < b->slen) {
bstring t;
i = bfindreplace (b, find, t = bstrcpy (repl), pos);
bdestroy (t);
return i;
}
delta = find->slen - repl->slen;
/* in-place replacement since find and replace strings are of equal
length */
if (delta == 0) {
while ((pos = binstr (b, pos, find)) >= 0) {
memcpy (b->data + pos, repl->data, repl->slen);
pos += find->slen;
}
return 0;
}
/* shrinking replacement since find->slen > repl->slen */
if (delta > 0) {
acc = 0;
while ((i = binstr (b, pos, find)) >= 0) {
if (acc && i > pos) {
memmove (b->data + pos - acc, b->data + pos,
i - pos);
}
if (repl->slen) {
memmove (b->data + i - acc, repl->data,
repl->slen);
}
acc += delta;
pos = i + find->slen;
}
if (acc) {
i = b->slen;
if (i > pos) {
memmove (b->data + pos - acc, b->data + pos,
i - pos);
}
b->slen -= acc;
b->data[b->slen] = '\0';
}
return 0;
}
/* expanding replacement since find->slen < repl->slen. Its a lot
more complicated. */
mlen = 8;
d = (int *) malloc (sizeof (int *) * mlen);
if (d == NULL) return BSTR_ERR;
slen = 0;
while ((pos = binstr (b, pos, find)) >= 0) {
int * t;
if (slen + 1 >= mlen) {
mlen += mlen;
t = (int *) realloc (d, sizeof (int *) * mlen);
if (t == NULL) {
free (d);
return BSTR_ERR;
}
d = t;
}
d[slen] = pos;
slen++;
pos += find->slen;
}
d[slen] = b->slen;
acc = slen * (-delta);
if (BSTR_OK == (ret = balloc (b, b->slen + acc + 1))) {
b->slen += acc;
for (i = slen-1; i >= 0; i--) {
int s, l;
s = d[i] + find->slen;
l = d[i+1] - s;
if (l) {
memmove (b->data + s + acc, b->data + s, l);
}
if (repl->slen) {
memmove (b->data + s + acc - repl->slen,
repl->data, repl->slen);
}
acc += delta;
}
b->data[b->slen] = '\0';
}
free (d);
return ret;
}
/* int binsertch (bstring b, int pos, int len, unsigned char fill)
*
* Inserts the character fill repeatedly into b at position pos for a
* length len. If the position pos is past the end of b, then the
* character "fill" is appended as necessary to make up the gap between the
* end of b and the position pos + len.
*/
int binsertch (bstring b, int pos, int len, unsigned char fill) {
int d, l;
if (pos < 0 || b == NULL || b->slen < 0 || b->mlen < b->slen ||
len < 0) return BSTR_ERR;
/* Compute the two possible end pointers */
d = b->slen + len;
l = pos + len;
if (l > d) {
/* Inserting past the end of the string */
if (balloc (b, l + 1) != BSTR_OK) return BSTR_ERR;
len += pos - b->slen;
pos = b->slen;
b->slen = l;
} else {
/* Inserting in the middle of the string */
if (balloc (b, d + 1) != BSTR_OK) return BSTR_ERR;
for (l = d - 1; l >= pos + len; l--) {
b->data[l] = b->data[l - len];
}
b->slen = d;
}
d = pos + len;
for (l=pos; l < d; l++) b->data[l] = fill;
b->data[b->slen] = '\0';
return 0;
}
/* int bpattern (bstring b, int len)
*
* Replicate the starting bstring, b, end to end repeatedly until it surpasses
* len characters, then chop the result to exactly len characters. This
* function operates in-place. The function will return with BSTR_ERR if b
* is NULL or of length 0, otherwise BSTR_OK is returned.
*/
int bpattern (bstring b, int len) {
int i, d;
d = blength (b);
if (d <= 0 || len < 0 || balloc (b, len + 1) != BSTR_OK) return BSTR_ERR;
if (len > 0) {
if (d == 1) return bsetstr (b, len, NULL, b->data[0]);
for (i = d; i < len; i++) b->data[i] = b->data[i - d];
}
b->data[len] = '\0';
b->slen = len;
return 0;
}
/* bstring bgets (bNgetc getcPtr, void * parm, char terminator)
*
* Use an fgetc-like single character stream reading function (getcPtr) to
* obtain a sequence of characters which are concatenated into a bstring.
* The stream read is terminated by the passed in terminator function.
*
* If getcPtr returns with a negative number, or the terminator character
* (which is appended) is read, then the stream reading is halted as the
* result obtained thus far is returned. If no characters are read, or
* there is some other detectable error, NULL is returned.
*/
bstring bgets (bNgetc getcPtr, void * parm, char terminator) {
int c, d, e;
bstring buff;
if (getcPtr == NULL) return NULL;
buff = bfromcstr ("");
if (buff == NULL) return NULL;
d = 0;
e = buff->mlen - 2;
while ((c = getcPtr (parm)) >= 0) {
if (d > e) {
buff->slen = d;
if (balloc (buff, d + 2) != BSTR_OK) {
bdestroy (buff);
return NULL;
}
e = buff->mlen - 2;
}
buff->data[d] = (unsigned char) c;
d++;
if (c == terminator) break;
}
buff->data[d] = '\0';
buff->slen = d;
if (d == 0) {
bdestroy (buff);
buff = NULL;
}
return buff;
}
#define BS_BUFF_SZ (1024)
/* bstring bread (bNread readPtr, void * parm)
*
* Translate a finite buffer fread-like function into something which can
* fill in a bstring in a roughly efficient way.
*/
bstring bread (bNread readPtr, void * parm) {
int i, l, n;
bstring buff;
if (readPtr == NULL) return NULL;
buff = bfromcstr ("");
if (buff == NULL) return NULL;
for (i=0, n=16; ; n += ((n < BS_BUFF_SZ) ? n : BS_BUFF_SZ)) {
if (BSTR_OK != balloc (buff, n + 1)) {
bdestroy (buff);
return NULL;
}
l = (int) readPtr ((void *) (buff->data + i), 1, n - i, parm);
i += l;
buff->slen = i;
if (i < n) break;
}
buff->data[i] = '\0';
return buff;
}
struct bStream {
bstring buff; /* Buffer for over-reads */
void * parm; /* The stream handle for core stream */
bNread readFnPtr; /* fread compatible fnptr for core stream */
int isEOF; /* track file's EOF state */
int maxBuffSz;
};
/* struct bStream * bsopen (bNread readPtr, void * parm)
*
* Wrap a given open stream (described by a fread compatible function
* pointer and stream handle) into an open bStream suitable for the bstring
* library streaming functions.
*/
struct bStream * bsopen (bNread readPtr, void * parm) {
struct bStream * s;
if (readPtr == NULL) return NULL;
s = (struct bStream *) malloc (sizeof (struct bStream));
if (s == NULL) return NULL;
s->parm = parm;
s->buff = bfromcstr ("");
s->readFnPtr = readPtr;
s->maxBuffSz = BS_BUFF_SZ;
s->isEOF = 0;
return s;
}
/* int bsbufflength (struct bStream * s, int sz)
*
* Set the length of the buffer used by the bsStream. If sz is zero, the
* length is not set. This function returns with the previous length.
*/
int bsbufflength (struct bStream * s, int sz) {
int oldSz;
if (s == NULL || sz < 0) return BSTR_ERR;
oldSz = s->maxBuffSz;
if (sz > 0) s->maxBuffSz = sz;
return oldSz;
}
int bseof (const struct bStream * s) {
if (s == NULL || s->readFnPtr == NULL) return BSTR_ERR;
return s->isEOF && (s->buff->slen == 0);
}
/* void * bsclose (struct bStream * s)
*
* Close the bStream, and return the handle to the stream that was originally
* used to open the given stream.
*/
void * bsclose (struct bStream * s) {
void * parm;
if (s == NULL) return NULL;
s->readFnPtr = NULL;
if (s->buff) bdestroy (s->buff);
s->buff = NULL;
parm = s->parm;
s->parm = NULL;
s->isEOF = 1;
free (s);
return parm;
}
/* int bsreadlna (bstring r, struct bStream * s, char terminator)
*
* Read a bstring terminated by the terminator character or the end of the
* stream from the bStream (s) and return it into the parameter r. This
* function may read additional characters from the core stream that are not
* returned, but will be retained for subsequent read operations.
*/
int bsreadlna (bstring r, struct bStream * s, char terminator) {
int i, l;
char * b;
struct tagbstring x;
if (s == NULL || s->buff == NULL || r == NULL || r->mlen <= 0)
return BSTR_ERR;
l = s->buff->slen;
if (BSTR_OK != balloc (s->buff, s->maxBuffSz + 1)) return BSTR_ERR;
b = (char *) s->buff->data;
x.data = (unsigned char *) b;
/* First check if the current buffer holds the terminator */
b[l] = terminator;
for (i=0; b[i] != terminator; i++) ;
if (i < l) {
int ret;
x.slen = i + 1;
ret = bconcat (r, &x);
s->buff->slen = l;
if (BSTR_OK == ret) bdelete (s->buff, 0, i + 1);
return BSTR_ERR & -(r->slen == 0);
}
/* If not then just concatenate the entire buffer to the output */
x.slen = l;
if (BSTR_OK != bconcat (r, &x)) return BSTR_ERR;
/* Perform direct in-place reads into the destination to allow for
the minimum of data-copies */
for (;;) {
balloc (r, r->slen + s->maxBuffSz + 1);
b = (char *) (r->data + r->slen);
l = (int) s->readFnPtr (b, 1, s->maxBuffSz, s->parm);
if (l <= 0) {
r->data[r->slen] = '\0';
s->buff->slen = 0;
s->isEOF = 1;
/* If nothing was read return with an error message */
return BSTR_ERR & -(r->slen == 0);
}
b[l] = terminator;
for (i=0; b[i] != terminator; i++) ;
if (i < l) {
/* Terminator found, push over-read back to buffer */
i++;
r->slen += i;
s->buff->slen = l - i;
memcpy (s->buff->data, b + i, l - i);
r->data[r->slen] = '\0';
return BSTR_OK;
}
r->slen += l;
}
}
/* int bsreadlnsa (bstring r, struct bStream * s, bstring term)
*
* Read a bstring terminated by any character in the term string or the end
* of the stream from the bStream (s) and return it into the parameter r.
* This function may read additional characters from the core stream that
* are not returned, but will be retained for subsequent read operations.
*/
int bsreadlnsa (bstring r, struct bStream * s, const bstring term) {
int i, l;
unsigned char * b;
struct tagbstring x;
struct charField cf;
if (s == NULL || s->buff == NULL || r == NULL || term == NULL
|| term->data == NULL || r->mlen <= 0) return BSTR_ERR;
if (term->slen == 1) return bsreadlna (r, s, term->data[0]);
if (term->slen < 1 || buildCharField (&cf, term)) return BSTR_ERR;
l = s->buff->slen;
if (BSTR_OK != balloc (s->buff, s->maxBuffSz + 1)) return BSTR_ERR;
b = (unsigned char *) s->buff->data;
x.data = b;
/* First check if the current buffer holds the terminator */
b[l] = term->data[0];
for (i=0; !testInCharField (&cf, b[i]); i++) ;
if (i < l) {
int ret;
x.slen = i + 1;
ret = bconcat (r, &x);
s->buff->slen = l;
if (BSTR_OK == ret) bdelete (s->buff, 0, i + 1);
return BSTR_ERR & -(r->slen == 0);
}
/* If not then just concatenate the entire buffer to the output */
x.slen = l;
if (BSTR_OK != bconcat (r, &x)) return BSTR_ERR;
/* Perform direct in-place reads into the destination to allow for
the minimum of data-copies */
for (;;) {
balloc (r, r->slen + s->maxBuffSz + 1);
b = (unsigned char *) (r->data + r->slen);
l = (int) s->readFnPtr (b, 1, s->maxBuffSz, s->parm);
if (l <= 0) {
r->data[r->slen] = '\0';
s->buff->slen = 0;
s->isEOF = 1;
/* If nothing was read return with an error message */
return BSTR_ERR & -(r->slen == 0);
}
b[l] = term->data[0];
for (i=0; !testInCharField (&cf, b[i]); i++) ;
if (i < l) {
/* Terminator found, push over-read back to buffer */
i++;
r->slen += i;
s->buff->slen = l - i;
memcpy (s->buff->data, b + i, l - i);
r->data[r->slen] = '\0';
return BSTR_OK;
}
r->slen += l;
}
}
/* int bsreada (bstring r, struct bStream * s, int n)
*
* Read a bstring of length n (or, if it is fewer, as many bytes as is
* remaining) from the bStream. This function may read additional
* characters from the core stream that are not returned, but will be
* retained for subsequent read operations. This function will not read
* additional characters from the core stream beyond virtual stream pointer.
*/
int bsreada (bstring r, struct bStream * s, int n) {
int l;
char * b;
struct tagbstring x;
if (s == NULL || s->buff == NULL || r == NULL || r->mlen <= 0
|| r->slen < 0 || n <= 0) return BSTR_ERR;
n += r->slen;
if (n <= 0) return BSTR_ERR;
l = s->buff->slen;
if (BSTR_OK != balloc (s->buff, s->maxBuffSz + 1)) return BSTR_ERR;
b = (char *) s->buff->data;
x.data = (unsigned char *) b;
do {
if (l + r->slen >= n) {
int ret;
x.slen = n - r->slen;
ret = bconcat (r, &x);
s->buff->slen = l;
if (BSTR_OK == ret) bdelete (s->buff, 0, x.slen);
return BSTR_ERR & -(r->slen == 0);
}
x.slen = l;
if (BSTR_OK != bconcat (r, &x)) break;
l = n - r->slen;
if (l > s->maxBuffSz) l = s->maxBuffSz;
l = (int) s->readFnPtr (b, 1, l, s->parm);
} while (l > 0);
if (l < 0) l = 0;
if (l == 0) s->isEOF = 1;
s->buff->slen = l;
return BSTR_ERR & -(r->slen == 0);
}
/* int bsreadln (bstring r, struct bStream * s, char terminator)
*
* Read a bstring terminated by the terminator character or the end of the
* stream from the bStream (s) and return it into the parameter r. This
* function may read additional characters from the core stream that are not
* returned, but will be retained for subsequent read operations.
*/
int bsreadln (bstring r, struct bStream * s, char terminator) {
if (s == NULL || s->buff == NULL || r == NULL || r->mlen <= 0)
return BSTR_ERR;
if (BSTR_OK != balloc (s->buff, s->maxBuffSz + 1)) return BSTR_ERR;
r->slen = 0;
return bsreadlna (r, s, terminator);
}
/* int bsreadlns (bstring r, struct bStream * s, bstring term)
*
* Read a bstring terminated by any character in the term string or the end
* of the stream from the bStream (s) and return it into the parameter r.
* This function may read additional characters from the core stream that
* are not returned, but will be retained for subsequent read operations.
*/
int bsreadlns (bstring r, struct bStream * s, const bstring term) {
if (s == NULL || s->buff == NULL || r == NULL || term == NULL
|| term->data == NULL || r->mlen <= 0) return BSTR_ERR;
if (term->slen == 1) return bsreadln (r, s, term->data[0]);
if (term->slen < 1) return BSTR_ERR;
if (BSTR_OK != balloc (s->buff, s->maxBuffSz + 1)) return BSTR_ERR;
r->slen = 0;
return bsreadlnsa (r, s, term);
}
/* int bsread (bstring r, struct bStream * s, int n)
*
* Read a bstring of length n (or, if it is fewer, as many bytes as is
* remaining) from the bStream. This function may read additional
* characters from the core stream that are not returned, but will be
* retained for subsequent read operations. This function will not read
* additional characters from the core stream beyond virtual stream pointer.
*/
int bsread (bstring r, struct bStream * s, int n) {
if (s == NULL || s->buff == NULL || r == NULL || r->mlen <= 0
|| n <= 0) return BSTR_ERR;
if (BSTR_OK != balloc (s->buff, s->maxBuffSz + 1)) return BSTR_ERR;
r->slen = 0;
return bsreada (r, s, n);
}
/* int bsunread (struct bStream * s, const bstring b)
*
* Insert a bstring into the bStream at the current position. These
* characters will be read prior to those that actually come from the core
* stream.
*/
int bsunread (struct bStream * s, const bstring b) {
if (s == NULL || s->buff == NULL) return BSTR_ERR;
return binsert (s->buff, 0, b, '?');
}
/* int bspeek (bstring r, const struct bStream * s)
*
* Return the currently buffered characters from the bStream that will be
* read prior to reads from the core stream.
*/
int bspeek (bstring r, const struct bStream * s) {
if (s == NULL || s->buff == NULL || r == NULL || r->slen > r->mlen || r->slen < 0) return BSTR_ERR;
r->slen = 0;
return bconcat (r, s->buff);
}
/* bstring bjoin (const struct bstrList * bl, const bstring sep);
*
* Join the entries of a bstrList into one bstring by sequentially
* concatenating them with the sep string in between. If there is an error
* NULL is returned, otherwise a bstring with the correct result is returned.
*/
bstring bjoin (const struct bstrList * bl, const bstring sep) {
bstring b;
int i, c, v;
if (bl == NULL || bl->qty < 0) return NULL;
if (sep != NULL && (sep->slen < 0 || sep->data == NULL)) return NULL;
b = (bstring) malloc (sizeof (struct tagbstring));
if (b == NULL) return NULL; /* Out of memory */
for (i = 0, c = 1; i < bl->qty; i++) {
v = bl->entry[i]->slen;
if (v < 0) return NULL; /* Invalid input */
c += v;
if (c < 0) return NULL; /* Wrap around ?? */
}
if (sep != NULL) c += (bl->qty - 1) * sep->slen;
b->data = (unsigned char *) malloc (c);
if (b->data == NULL) return NULL;
b->mlen = c;
b->slen = c-1;
for (i = 0, c = 0; i < bl->qty; i++) {
if (i > 0 && sep != NULL) {
memcpy (b->data + c, sep->data, sep->slen);
c += sep->slen;
}
v = bl->entry[i]->slen;
memcpy (b->data + c, bl->entry[i]->data, v);
c += v;
}
b->data[c] = '\0';
return b;
}
#define BSSSC_BUFF_LEN (256)
/* int bssplitscb (struct bStream * s, const bstring splitStr,
* int (* cb) (void * parm, int ofs, const bstring entry), void * parm)
*
* Iterate the set of disjoint sequential substrings read from a stream
* divided by any of the characters in splitStr. An empty splitStr causes
* the whole stream to be iterated once.
*
* Note: At the point of calling the cb function, the bStream pointer is
* pointed exactly at the position right after having read the split
* character. The cb function can act on the stream by causing the bStream
* pointer to move, and bssplitscb will continue by starting the next split
* at the position of the pointer after the return from cb.
*
* However, if the cb causes the bStream s to be destroyed then the cb must
* return with a negative value, otherwise bssplitscb will continue in an
* undefined manner.
*/
int bssplitscb (struct bStream * s, const bstring splitStr,
int (* cb) (void * parm, int ofs, const bstring entry), void * parm) {
struct charField chrs;
bstring buff;
int i, p, ret;
if (cb == NULL || s == NULL || s->readFnPtr == NULL
|| splitStr == NULL || splitStr->slen < 0) return BSTR_ERR;
if (NULL == (buff = bfromcstr (""))) return BSTR_ERR;
if (splitStr->slen == 0) {
while (bsreada (buff, s, BSSSC_BUFF_LEN) >= 0) ;
if ((ret = cb (parm, 0, buff)) > 0)
ret = 0;
} else {
buildCharField (&chrs, splitStr);
ret = p = i = 0;
for (;;) {
if (i >= buff->slen) {
bsreada (buff, s, BSSSC_BUFF_LEN);
if (i >= buff->slen) {
if ((ret = cb (parm, p, buff)) > 0) ret = 0;
break;
}
}
if (testInCharField (&chrs, buff->data[i])) {
struct tagbstring t;
blk2tbstr (t, buff->data + i + 1, buff->slen - (i + 1));
if ((ret = bsunread (s, &t)) < 0) break;
buff->slen = i;
if ((ret = cb (parm, p, buff)) < 0) break;
buff->slen = 0;
p += i + 1;
i = -1;
}
i++;
}
}
bdestroy (buff);
return ret;
}
/* int bstrListDestroy (struct bstrList * sl)
*
* Destroy a bstrList that has been created by bsplit or bsplits.
*/
int bstrListDestroy (struct bstrList * sl) {
int i;
if (sl == NULL) return BSTR_ERR;
for (i=0; i < sl->qty; i++) {
if (sl->entry[i]) {
bdestroy (sl->entry[i]);
sl->entry[i] = NULL;
}
}
sl->qty = -1;
free (sl);
return BSTR_OK;
}
/* int bsplitcb (const bstring str, unsigned char splitChar, int pos,
* int (* cb) (void * parm, int ofs, int len), void * parm)
*
* Iterate the set of disjoint sequential substrings over str divided by the
* character in splitChar.
*
* Note: Non-destructive modification of str from within the cb function
* while performing this split is not undefined. bsplitcb behaves in
* sequential lock step with calls to cb. I.e., after returning from a cb
* that return a non-negative integer, bsplitcb continues from the position
* 1 character after the last detected split character and it will halt
* immediately if the length of str falls below this point. However, if the
* cb function destroys str, then it *must* return with a negative value,
* otherwise bsplitcb will continue in an undefined manner.
*/
int bsplitcb (const bstring str, unsigned char splitChar, int pos,
int (* cb) (void * parm, int ofs, int len), void * parm) {
int i, p, ret;
if (cb == NULL || str == NULL || pos < 0 || pos > str->slen)
return BSTR_ERR;
p = pos;
do {
for (i=p; i < str->slen; i++) {
if (str->data[i] == splitChar) break;
}
if ((ret = cb (parm, p, i - p)) < 0) return ret;
p = i + 1;
} while (p < str->slen);
return 0;
}
/* int bsplitscb (const bstring str, const bstring splitStr, int pos,
* int (* cb) (void * parm, int ofs, int len), void * parm)
*
* Iterate the set of disjoint sequential substrings over str divided by any
* of the characters in splitStr. An empty splitStr causes the whole str to
* be iterated once.
*
* Note: Non-destructive modification of str from within the cb function
* while performing this split is not undefined. bsplitscb behaves in
* sequential lock step with calls to cb. I.e., after returning from a cb
* that return a non-negative integer, bsplitscb continues from the position
* 1 character after the last detected split character and it will halt
* immediately if the length of str falls below this point. However, if the
* cb function destroys str, then it *must* return with a negative value,
* otherwise bsplitscb will continue in an undefined manner.
*/
int bsplitscb (const bstring str, const bstring splitStr, int pos,
int (* cb) (void * parm, int ofs, int len), void * parm) {
struct charField chrs;
int i, p, ret;
if (cb == NULL || str == NULL || pos < 0 || pos > str->slen
|| splitStr == NULL || splitStr->slen < 0) return BSTR_ERR;
if (splitStr->slen == 0) {
if ((ret = cb (parm, 0, str->slen)) > 0) ret = 0;
return ret;
}
if (splitStr->slen == 1)
return bsplitcb (str, splitStr->data[0], pos, cb, parm);
buildCharField (&chrs, splitStr);
p = pos;
do {
for (i=p; i < str->slen; i++) {
if (testInCharField (&chrs, str->data[i])) break;
}
if ((ret = cb (parm, p, i - p)) < 0) return ret;
p = i + 1;
} while (p < str->slen);
return 0;
}
#include <stddef.h>
#ifdef offsetof
#define BLE_SZ (offsetof (struct bstrList, entry))
#else
#define BLE_SZ (sizeof (struct bstrList))
#endif
struct genBstrList {
bstring b;
struct bstrList * bl;
int mlen;
};
static int bscb (void * parm, int ofs, int len) {
struct genBstrList * g = (struct genBstrList *)parm;
if (g->bl->qty >= g->mlen) {
int mlen = g->mlen * 2;
struct bstrList * tbl;
while (g->bl->qty >= mlen) mlen += mlen;
tbl = (struct bstrList *) realloc (g->bl, BLE_SZ + sizeof (bstring) * (mlen));
if (tbl == NULL) return BSTR_ERR;
g->bl = tbl;
g->mlen = mlen;
}
g->bl->entry[g->bl->qty] = bmidstr (g->b, ofs, len);
g->bl->qty++;
return 0;
}
/* struct bstrList * bsplit (const bstring str, unsigned char splitChar)
*
* Create an array of sequential substrings from str divided by the character
* splitChar.
*/
struct bstrList * bsplit (const bstring str, unsigned char splitChar) {
struct genBstrList g;
if (str == NULL || str->data == NULL || str->slen < 0) return NULL;
g.b = str;
g.mlen = 4;
g.bl = (struct bstrList *) malloc (BLE_SZ + sizeof (bstring) * g.mlen);
if (g.bl == NULL) return NULL;
g.bl->qty = 0;
if (bsplitcb (str, splitChar, 0, bscb, &g) < 0) {
bstrListDestroy (g.bl);
return NULL;
}
return g.bl;
}
/* struct bstrList * bsplits (const bstring str, bstring splitStr)
*
* Create an array of sequential substrings from str divided by any of the
* characters in splitStr. An empty splitStr causes a single entry bstrList
* containing a copy of str to be returned.
*/
struct bstrList * bsplits (const bstring str, const bstring splitStr) {
struct genBstrList g;
if ( str == NULL || str->slen < 0 || str->data == NULL ||
splitStr == NULL || splitStr->slen < 0 || splitStr->data == NULL)
return NULL;
g.b = str;
g.mlen = 4;
g.bl = (struct bstrList *) malloc (BLE_SZ + sizeof (bstring) * g.mlen);
if (g.bl == NULL) return NULL;
g.bl->qty = 0;
if (bsplitscb (str, splitStr, 0, bscb, &g) < 0) {
bstrListDestroy (g.bl);
return NULL;
}
return g.bl;
}
#if defined(__TURBOC__)
# ifndef BSTRLIB_NOVSNP
# define BSTRLIB_NOVSNP
# endif
#endif
/* Give WATCOM C/C++, MSVC some latitude for their non-support of vsnprintf */
#if defined(__WATCOMC__) || defined(_MSC_VER)
#define exvsnprintf(r,b,n,f,a) {r = _vsnprintf (b,n,f,a);}
#else
#ifdef BSTRLIB_NOVSNP
/* This is just a hack. If you are using a system without a vsnprintf, it is
not recommended that bformat be used at all. */
#define exvsnprintf(r,b,n,f,a) {vsprintf (b,f,a); r = -1;}
#define START_VSNBUFF (256)
#else
#ifdef __GNUC__
/* Something is making gcc complain about this prototype not being here, so
I've just gone ahead and put it in. */
extern int vsnprintf (char *buf, size_t count, const char *format, va_list arg);
#endif
#define exvsnprintf(r,b,n,f,a) {r = vsnprintf (b,n,f,a);}
#endif
#endif
#ifndef START_VSNBUFF
#define START_VSNBUFF (16)
#endif
/* On IRIX vsnprintf returns n-1 when the operation would overflow the target
buffer, WATCOM and MSVC both return -1, while C99 requires that the
returned value be exactly what the length would be if the buffer would be
large enough. This leads to the idea that if the return value is larger
than n, then changing n to the return value will reduce the number of
iterations required. */
/* bstring bformata (bstring b, const char * fmt, ...)
*
* Takes the same parameters as printf (), but rather than outputting results
* to stdio, it forms appends the results to a bstring which contains what
* would have been output. Note that if there is an early generation of a
* '\0' character, the bstring will be truncated to this end point.
*/
int bformata (bstring b, const char * fmt, ...) {
va_list arglist;
int n, slen, r;
if (b == NULL || fmt == NULL || b->data == NULL || b->mlen <= 0
|| b->slen < 0 || b->slen > b->mlen) return BSTR_ERR;
/* Since the length is not determinable beforehand, a search is
performed using the truncating "vsnprintf" call (to avoid buffer
overflows) on increasing potential sizes for the output result. */
slen = b->slen;
if ((n = 2*strlen (fmt)) < START_VSNBUFF) n = START_VSNBUFF;
for (;;) {
if (BSTR_OK != balloc (b, n + 2 + slen)) return BSTR_ERR;
va_start (arglist, fmt);
exvsnprintf (r, (char *) b->data + slen, n + 1, fmt, arglist);
va_end (arglist);
b->data[n + slen] = '\0';
b->slen = slen + (int) (strlen) ((char *) b->data + slen);
if (b->slen - slen < n) break;
if (r > n) n = r; else n += n;
}
return 0;
}
/* bstring bformat (const char * fmt, ...)
*
* Takes the same parameters as printf (), but rather than outputting results
* to stdio, it forms a bstring which contains what would have been output.
* Note that if there is an early generation of a '\0' character, the
* bstring will be truncated to this end point.
*/
bstring bformat (const char * fmt, ...) {
va_list arglist;
bstring buff;
int n, r;
if (fmt == NULL) return NULL;
/* Since the length is not determinable beforehand, a search is
performed using the truncating "vsnprintf" call (to avoid buffer
overflows) on increasing potential sizes for the output result. */
if ((n = 2*strlen (fmt)) < START_VSNBUFF) n = START_VSNBUFF;
buff = bfromcstr ("");
for (;;) {
if (BSTR_OK != balloc (buff, n + 2)) {
bdestroy (buff);
return NULL;
}
va_start (arglist, fmt);
exvsnprintf (r, (char *) buff->data, n + 1, fmt, arglist);
va_end (arglist);
buff->data[n] = '\0';
buff->slen = (int) (strlen) ((char *) buff->data);
if (buff->slen < n) break;
if (r > n) n = r; else n += n;
}
return buff;
}
|