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
|
/* ================================================================= *\
biblook -- look up references in a bibindexed BibTeX file
This program was specifically developed for use with the
computational geometry bibliographic database. The database
can be obtained by anonymous ftp from cs.usask.ca in the file
`pub/geometry/geombib.tar.Z'.
Version 1.0 written by Jeff Erickson <jeff@ics.uci.edu>, 27 Mar 92
Version 2.0 written by Jeff Erickson <jeff@ics.uci.edu>, 17 Jun 92
This program is in the public domain. You may use it or modify
it to your heart's content, at your own risk. Bouquets, brickbats,
and bug fixes may be sent to Jeff Erickson, jeffe@cs.berkeley.edu.
%Make% gcc -O -o biblook biblook.c
Usage: biblook bibfile [savefile]
-----------------------------------------------------------------
HOW IT WORKS:
The user can enter any of the following commands:
f[ind] [not] <field> <words>
Find the entries containing the given words in any field
with a prefix matching the <field> argument. For example,
`a' matches both `author' and `address', and `au' matches
`author' only. If the <field> argument is `-' (or any
string with no letters or numbers), match any field.
If `not' appears before the <field>, the sense of the search
is reversed. The symbols `~' and `!' can be used in place
of `not'.
Each word is a contiguous sequence of letters and digits.
Case is ignored; accents should be omitted; apostrophes are
not required. Single characters and a few common words are
also ignored. Any word ending with an asterisk is treated
as a prefix. Thus, `point*' matches `point', `points',
`pointer', etc.
and [not] <field> <words>
or [not] <field> <words>
Intersect (resp. union) the results of the given search
with the previous search. Several of these commands may be
combined on a single line. Commands are handled in the order
in which they appear; there is no precedence. Unlike other
commands, and like `not', these must be spelled out
completely. `&' can be used in place of `and', and `|' can
be used in place of `or'.
d[isplay]
Display the results of the previous search.
s[ave] [<filename>]
Save the results of the previous results into the specified
file. If <filename> is omitted, the previous save file is
used. If no save file has ever been specified, results are
saved in the file specified on the command line. If no such
file is specified, `save.bib' is used. If the save file
exists, results are appended to it.
w[hatis] <abbrev>
Display the definition of the abbreviation <abbrev>.
q[uit]/EOF
Quit.
Several commands can be combined on a single line by separating
them with semicolons. For example, the following command displays
all STOC papers cowritten by Erdo"s without `Voronoi diagrams' in
the title:
f b stoc* | b symp* theory comp* & au erdos & ~t voronoi diagrams ; d
-----------------------------------------------------------------
Version history
1.0 <jge> 3/29/92 Initial version complete
1.1 <jge> 4/3/92 Fixed GetToken bug.
Prompts and feedback messages sent to stderr
instead of stdout, so results can be
redirected to a file.
2.0 <jge> 6/17/92 Major change in file format and commands.
1. Allow searching on any field or all fields.
2. More extensive boolean queries (and, or, not)
3. New command to save results to a file
4. New command to display results, rather than displaying
them automatically.
5. Allow searching for prefixes
6. Pipe display results through $PAGER or /usr/ucb/more
2.1 <jge> 7/8/92 Minor bug fixes.
2.3 Bill Jones <jones@cs.usask.ca> 93/01/29
1. Declarations common to bibindex.c and biblook.c factored out
to new file biblook.h.
2. Index type of (signed) short overflows early; created typedef
Index_t, defined as unsigned short.
2.4 Nelson H. F. Beebe <beebe@math.utah.edu> [01-Jun-1993]
1. Remove some mixed-mode arithmetic.
2. Add cast to return value of fork().
3. Correct use and type of numoffsets so that code works
if Index_t is "unsigned int" or "unsigned long".
2.5 Erik Schoenfelder <schoenfr@ibr.cs.tu-bs.de> [14-Aug-1993]
1. Add support for network byte order I/O, so that index files
can be shared between big-endian and little-endian systems.
This option is selected when HAVE_NETINET_IN_H is defined
at compile time (default on UNIX).
Nelson H. F. Beebe <beebe@math.utah.edu> [14-Aug-1993]
2. Add typecast (int) in bibindex:OutputTables() array reference
to eliminate compiler warnings.
3. Correct code in biblook:SetComplement() to check for zero
setmask; otherwise, a .bib file with a number of entries
which is an exact multiple of setsize (commonly 32) will
result in failing searches for the last setsize entries!
2.6 <jge> 8/29/93
1. Simplified "help" output so it fits in one screen.
2. Made help command act like a COMMAND -- "find help" no
longer displays the help message followed by an error
message.
3. Fixed error with not -- "f not" followed by "f a erdos"
no longer finds all entries NOT written by Erdos!
4. Added "safemalloc" routine from bibindex.
5. Added "whatis" command to look up @strings. Since @strings
are now indexed as if "@string" were a field, it's now
trivial to look up all abbreviations containing a given set
of words.
6. Index lists are now read in only when they are required for
a search. Only the CACHESIZE most recently accessed lists
are kept; older ones are freed.
7. Added support for BIBLOOK environment variable, which
stores a search path for bib/bix files. Defaults to
BIBINPUTS, or just the current directory if neither of
those exist.
Nelson H. F. Beebe <beebe@math.utah.edu> [12-Sep-1993]
8. Restore long form of help, offering short form first,
then long form if help is asked for a second time. The
"telnet biblio" service on siggraph.org needs the long
form, since remote users cannot be expected to have a
biblook manual page. Telling users to go read the manual
is unfriendly.
9. Change "/usr/ucb/more" and "more" to compile-time settable
MOREPATH and MORE, and set Makefile to use "less" when available.
10. Change type of numfields from char to unsigned char, and
use sizeof numfields instead of sizeof(type of numfields).
11. Change all exit() calls to use Standard C EXIT_xxx symbols.
12. Put (void) casts on printf() family calls to avoid compiler
warnings about discarded returned values.
13. Change safemalloc() to request non-zero size when zero size
is requested; some systems reject a malloc(0) request (e.g.
IBM RS/6000 AIX 3.2).
14. Change &abbrevlocs to abbrevlocs in GetTables(). This error
went undetected on 23 O/S-compiler combinations, but was
caught on DECstation ULTRIX with both gcc and g++, the only
one of these systems which is little-endian. Network byte
order is big-endian, so ConvertToHostOrder() is a no-op
on such systems.
Bill Jones <jones@cs.usask.ca> 93/09/29
15. CACHESIZE of 8192 seems to keep runtime size within ~2.5 MB.
16. MAXRESULTS limit on set display can be enabled if wanted.
17. bixfile kept open all the time.
2.7 Bill Jones <jones@cs.usask.ca> 94/02/10
1. Changes for MSDOS use, from Guenter Rote.
2.8 Bill Jones <jones@cs.usask.ca> 95/01/19
1. Renovations for Index_t compression, and for 64-bit-long
portability typedefs and casts -- see bibindex for more details.
\* ================================================================= */
#include "biblook.h"
static char bibfile[FILENAME_MAX+1];
static char bixfile[FILENAME_MAX+1];
/* ======================= UTILITY FUNCTIONS ======================= */
/* ----------------------------------------------------------------- *\
| void die(const char *msg1, const char *msg2)
|
| print an error message and die
\* ----------------------------------------------------------------- */
void die(const char *msg1, const char *msg2)
{
(void)fprintf(stderr, "Error: %s %s\n", msg1, msg2);
exit(EXIT_FAILURE);
}
/* ----------------------------------------------------------------- *\
| void pdie(const char *msg1, const char *msg2)
|
| Print a custom error message and a system error message, then die.
\* ----------------------------------------------------------------- */
void pdie(const char *msg1, const char *msg2)
{
char msg[256];
(void)sprintf(msg, "%s %s", msg1, msg2);
perror(msg);
exit(EXIT_FAILURE);
}
/* ----------------------------------------------------------------- *\
| void safefread(void *ptr, size_t size, size_t num, FILE *fp)
|
| Read from the file, but die if there's an error.
\* ----------------------------------------------------------------- */
void safefread(void *ptr, size_t size, size_t num, FILE *fp)
{
if (fread(ptr, size, num, fp) < num)
pdie("Error reading", bixfile);
}
/* ----------------------------------------------------------------- *\
| char safegetc(FILE *fp)
|
| Get the next character safely. Used by routines that assume that
| they won't run into the end of file.
\* ----------------------------------------------------------------- */
char safegetc(FILE *fp)
{
if (feof(fp))
pdie("Error reading", bibfile);
return getc(fp);
}
/* ----------------------------------------------------------------- *\
| void *safemalloc(unsigned howmuch, const char *msg1, const char *msg2)
|
| Allocate memory safely. Used by routines that assume they won't
| run out of memory.
\* ----------------------------------------------------------------- */
void *safemalloc(unsigned howmuch, const char *msg1, const char *msg2)
{
register void *tmp = NULL;
tmp = (void*)malloc((howmuch > 0) ? howmuch : 1);
/* some malloc's fail with zero size request */
if (tmp == NULL)
pdie(msg1, msg2);
return tmp;
}
/* ----------------------------------------------------------------- *\
| void ConvertToHostOrder(int n, int s, void *xx)
|
| Convert n elements of size s to host-byteorder
\* ----------------------------------------------------------------- */
static void ConvertToHostOrder(size_t n, size_t s, void *xx)
{
uint16 *x = (uint16 *)xx;
uint32 *y = (uint32 *)xx;
if (s == sizeof(uint16))
{
while (n-- > 0)
{
*x = ntohs(*x);
x++;
}
}
else /* assume s == sizeof(uint32) */
{
while (n-- > 0)
{
*y = ntohl(*y);
y++;
}
}
}
/* ----------------------------------------------------------------- *\
| void UncompressRefs(Index_t *list, char *p, Index_t length)
|
| Uncompress a sequence of Index_t. See bibindex for algorithm.
\* ----------------------------------------------------------------- */
void UncompressRefs(Index_t *list, char *p, Index_t length)
{
Index_t prevref = (Index_t)-1;
Index_t diff;
char bits, highbit;
int shift;
while (length-- > 0)
{
diff = 0;
shift = 0;
do {
bits = *p++;
highbit = bits & CHAR_HIGHBIT;
bits &= ~CHAR_HIGHBIT;
diff |= bits << shift;
shift += CHAR_BIT - 1;
} while (highbit);
*list = prevref + diff;
prevref = *list++;
}
}
/* ============================== CACHE ============================ *\
In the interest of saving memory, starting with version 2.6,
index lists are now cached. The cache is a priority queue,
implemented as a simple binary heap, stored in an array. The cache
contains pointers to the real lists, and each list contains its
rank in the heap. The heap is prioritized by least recent use.
Making the rank field an unsigned char almost certainly doesn't
save anything, since the data will almost certainly have to be
word- or long-aligned. [2.6 [NHFB]: change rank type to int, and
reorder struct to have largest items first, because of
memory-alignment requirements of many architectures.]
\* ================================================================= */
#define CACHESIZE 8192
typedef struct
{
long offset; /* offset into index file */
Index_s length; /* length of the list */
Index_s bytes; /* length when compressed */
char *list; /* compressed list or NULL */
int rank; /* back pointer into cache */
} CachedList;
typedef struct
{
long stamp; /* time stamp */
CachedList *clist; /* the cached list */
} CacheElement;
CacheElement cache[CACHESIZE];
long curstamp; /* current "time stamp" */
int cachenum; /* number of elements in the cache */
/* ----------------------------------------------------------------- *\
| void InitCache(VOID)
|
| Initialize the cache.
\* ----------------------------------------------------------------- */
void InitCache(VOID)
{
int i;
for (i=0; i<CACHESIZE; i++)
{
cache[i].stamp = -1;
cache[i].clist = NULL;
}
curstamp = 0;
}
/* ----------------------------------------------------------------- *\
| void InitCachedList(CachedList *clist, FILE *ifp)
|
| Initialize the cached list. Read the lengths of the list from the
| file, record the position of the list within the file, and skip
| over the list itself.
\* ----------------------------------------------------------------- */
void InitCachedList(CachedList *clist, FILE *ifp)
{
Index_s num;
clist->list = NULL;
safefread((void *) &num, sizeof(Index_s), 1, ifp);
ConvertToHostOrder(1, sizeof (Index_s), &num);
clist->length = num;
safefread((void *) &num, sizeof(Index_s), 1, ifp);
ConvertToHostOrder(1, sizeof (Index_s), &num);
clist->bytes = num;
clist->offset = ftell(ifp);
if (fseek(ifp, (long)num, SEEK_CUR) != 0)
pdie("Error reading", bixfile);
}
/* ----------------------------------------------------------------- *\
| void FreeCache(void)
|
| Free everything in the cache.
\* ----------------------------------------------------------------- */
void FreeCache(VOID)
{
int i;
for (i=0; i<cachenum; i++)
free(cache[i].clist->list);
}
/* ----------------------------------------------------------------- *\
| void CheckStamp(void)
|
| Avoid emacs's timestamp wraparound bug!!
\* ----------------------------------------------------------------- */
void CheckStamp(VOID)
{
int i;
if (curstamp < 0)
{
for (i=0; i<cachenum; i++)
cache[i].stamp = i; /* Changes time stamp order! */
curstamp = cachenum;
(void)printf("You've been running biblook a long time, haven't you?\n");
}
}
/* ----------------------------------------------------------------- *\
| void HeapBubble(int which)
|
| Bubble the given element down into its place in the heap.
\* ----------------------------------------------------------------- */
void HeapBubble(int which)
{
register int i;
CacheElement tmp;
i = which;
tmp = cache[i];
while (2*i+1 < cachenum) /* while I still have children */
{
if ((2*i+2 == cachenum) ||
(cache[2*i+1].stamp < cache[2*i+2].stamp))
{
cache[i] = cache[2*i+1]; /* go to left child */
cache[i].clist->rank = i;
i = 2*i+1;
}
else
{
cache[i] = cache[2*i+2]; /* go to right child */
cache[i].clist->rank = i;
i = 2*i+2;
}
}
cache[i] = tmp;
cache[i].clist->rank = i;
}
/* ----------------------------------------------------------------- *\
| void Access(CachedList *clist, FILE *ifp)
|
| Make sure clist is in memory. Make sure the given element is in
| its rightful place in the cache. If it's already there, just move
| it. Otherwise, insert it into the heap, deleting the oldest
| element if the cache is already full.
\* ----------------------------------------------------------------- */
void Access(CachedList *clist, FILE *ifp)
{
if (clist->list == NULL)
{
if (fseek(ifp, clist->offset, SEEK_SET) != 0)
pdie("Error reading", bixfile);
clist->list = (char *)safemalloc(clist->bytes,
"Can't allocate index list.", "");
safefread((void *)clist->list, sizeof(char), clist->bytes, ifp);
if (cachenum == CACHESIZE) /* if cache is full... */
{
free(cache[0].clist->list); /* delete oldest element */
cache[0].clist->list = NULL;
cache[0] = cache[CACHESIZE-1];
cache[CACHESIZE-1].clist = NULL;
cachenum--;
HeapBubble(0);
}
cache[cachenum].stamp = curstamp++;
cache[cachenum].clist = clist;
clist->rank = cachenum++;
}
else
{
cache[clist->rank].stamp = curstamp++;
HeapBubble(clist->rank);
}
CheckStamp();
}
/* ========================== INDEX TABLES ========================= */
typedef struct
{
Word theword;
CachedList refs;
} Index, *IndexPtr;
typedef struct
{
Word thefield;
Index_t numwords;
IndexPtr words;
} IndexTable;
Index_s numfields;
IndexTable *fieldtable;
Index_t numabbrevs;
Word *abbrevs;
Index_t *abbrevlocs;
Index_t numoffsets;
Off_t *offsets;
/* ----------------------------------------------------------------- *\
| void ReadWord(FILE *ifp, Word word)
|
| Read a "pascal" string into the given buffer
\* ----------------------------------------------------------------- */
void ReadWord(FILE *ifp, Word word)
{
unsigned char length;
safefread((void *)&length, sizeof(unsigned char), 1, ifp);
if (length > MAXWORD)
die("Index file is corrupt", "(word too long).");
safefread((void *)word, sizeof(char), length, ifp);
word[length] = 0;
#if DEBUG
(void)printf("word:%02d = [%s]\n", (int)length, word);
#endif /* DEBUG */
}
/* ----------------------------------------------------------------- *\
| void GetOneTable(FILE *ifp, IndexTable *table)
|
| Get one index table from the file
\* ----------------------------------------------------------------- */
void GetOneTable(FILE *ifp, IndexTable *table)
{
Index_t i;
safefread((void *)&table->numwords, sizeof(Index_t), 1, ifp);
ConvertToHostOrder(1, sizeof(Index_t), &table->numwords);
table->words = (IndexPtr)safemalloc(table->numwords*sizeof(Index),
"Can't create index table for", table->thefield);
for (i=0; i<table->numwords; i++)
{
ReadWord(ifp, table->words[i].theword);
InitCachedList(&(table->words[i].refs), ifp);
}
}
FILE *bixfp;
/* ----------------------------------------------------------------- *\
| void GetTables(VOID)
|
| Get the tables from the index file.
\* ----------------------------------------------------------------- */
void GetTables(VOID)
{
int version, i;
Index_t k;
if (fscanf(bixfp, "bibindex %d %*[^\n]%*c", &version) < 1)
die(bixfile, "is not a bibindex file!");
if (version < FILE_VERSION)
die(bixfile, "is the wrong version.\n\tPlease rerun bibindex.");
if (version > FILE_VERSION)
die(bixfile, "is the wrong version.\n\tPlease recompile biblook.");
InitCache();
safefread((void *) &numoffsets, sizeof(Index_t), 1, bixfp);
ConvertToHostOrder(1, sizeof(Index_t), &numoffsets);
offsets = (Off_t *) safemalloc(numoffsets * sizeof(Off_t),
"Can't create offset table", "");
safefread((void *) offsets, sizeof(Off_t), numoffsets, bixfp);
ConvertToHostOrder(numoffsets, sizeof(Off_t), offsets);
safefread((void *) &numfields, sizeof numfields, 1, bixfp);
ConvertToHostOrder(1, sizeof numfields, &numfields);
fieldtable = (IndexTable *) safemalloc(numfields * sizeof(IndexTable),
"Can't create field table", "");
for (i=0; i < (int)numfields; i++)
ReadWord(bixfp, fieldtable[i].thefield);
for (i=0; i < (int)numfields; i++)
GetOneTable(bixfp, fieldtable+i);
safefread((void *) &numabbrevs, sizeof(Index_t), 1, bixfp);
ConvertToHostOrder(1, sizeof(Index_t), &numabbrevs);
abbrevs = (Word *) safemalloc(numabbrevs * sizeof(Word),
"Can't create abbreviation table", "");
for (k=0; k<numabbrevs; k++)
ReadWord(bixfp, abbrevs[k]);
abbrevlocs =
(Index_t *) safemalloc(numabbrevs * sizeof(Index_t),
"Can't create abbrev offset table", "");
safefread((void *) abbrevlocs, sizeof(Index_t), numabbrevs, bixfp);
ConvertToHostOrder(numabbrevs, sizeof(Index_t), abbrevlocs);
}
/* ----------------------------------------------------------------- *\
| void FreeTables(void)
|
| Free the index tables.
\* ----------------------------------------------------------------- */
void FreeTables(VOID)
{
register int i;
FreeCache(); /* free all index lists in memory */
for (i=0; i < (int)numfields; i++)
free(fieldtable[i].words);
free(fieldtable);
free(offsets);
}
/* ----------------------------------------------------------------- *\
| Index_t FindIndex(IndexTable table, char *word, char prefix)
|
| Find the index of a word in a table. Return INDEX_NAN if the word
| isn't there. If prefix is true, return the index of the first
| matching word.
\* ----------------------------------------------------------------- */
Index_t FindIndex(IndexTable table, char *word, char prefix)
{
register IndexPtr words = table.words;
register int hi, lo, mid; /* must be signed */
register int cmp;
hi = table.numwords-1;
lo = 0;
while (hi>=lo)
{
mid = (hi+lo)/2;
cmp = strcmp(word, words[mid].theword);
if (cmp == 0)
return (Index_t)mid;
else if (cmp < 0)
hi = mid-1;
else if (cmp > 0)
lo = mid+1;
}
if (prefix && !strncmp(word, words[lo].theword, strlen(word)))
return (Index_t)lo;
else
return (Index_t)INDEX_NAN;
}
/* ----------------------------------------------------------------- *\
| Index_t FindAbbrev(char *word)
|
| Find the index of an abbrev in the abbrev table. Return INDEX_NAN
| if the abbrev isn't there.
\* ----------------------------------------------------------------- */
Index_t FindAbbrev(register char *word)
{
register int hi, lo, mid; /* must be signed */
register int cmp;
hi = numabbrevs-1;
lo = 0;
while (hi>=lo)
{
mid = (hi+lo)/2;
cmp = strcmp(word, abbrevs[mid]);
if (cmp == 0)
return (Index_t)mid;
else if (cmp < 0)
hi = mid-1;
else if (cmp > 0)
lo = mid+1;
}
return (Index_t)INDEX_NAN;
}
/* =================== SET MANIPULATION ROUTINES =================== */
static Index_t setsize;
typedef unsigned long Set_t, *Set;
static Set_t setmask; /* used to erase extra bits */
#define SETSCALE (sizeof(Set_t)*8)
/* ----------------------------------------------------------------- *\
| Set NewSet(void)
|
| Get a new variable to hold sets of integers in the range
| [0, numoffsets]. Set setsize and setmask.
\* ----------------------------------------------------------------- */
Set NewSet(VOID)
{
setsize = (numoffsets + SETSCALE - 1)/SETSCALE; /* HACK */
setmask = ((Set_t)1<<(numoffsets%SETSCALE)) - 1; /* KLUDGE */
return (Set) safemalloc(setsize * SETSCALE,
"Can't create new result list", "");
}
/* ----------------------------------------------------------------- *\
| void EmptySet(Set theset)
|
| Empty the set.
\* ----------------------------------------------------------------- */
void EmptySet(Set theset)
{
register Index_t i;
for (i=0; i<setsize; i++)
theset[i] = 0;
}
/* ----------------------------------------------------------------- *\
| void SetUnion(Set src1, Set src2, Set result)
|
| Get the union of two sets
\* ----------------------------------------------------------------- */
void SetUnion(Set src1, Set src2, Set result)
{
register Index_t i;
for (i=0; i<setsize; i++)
result[i] = src1[i] | src2[i];
}
/* ----------------------------------------------------------------- *\
| void SetIntersection(Set src1, Set src2, Set result)
|
| Get the intersection of two sets
\* ----------------------------------------------------------------- */
void SetIntersection(Set src1, Set src2, Set result)
{
register Index_t i;
for (i=0; i<setsize; i++)
result[i] = src1[i] & src2[i];
}
/* ----------------------------------------------------------------- *\
| void SetComplement(Set src, Set result)
|
| Get the complement of a set
\* ----------------------------------------------------------------- */
void SetComplement(Set src, Set result)
{
register Index_t i;
for (i=0; i<setsize; i++)
result[i] = ~src[i];
/* Bug fixed at version 2.5: setmask == 0 if numoffsets is */
/* a multiple of setsize, so the set contains no partial words, */
/* The clearing of trailing bits must then be omitted. */
if (setmask)
result[setsize-1] &= setmask; /* clear those last few bits */
}
/* ----------------------------------------------------------------- *\
| void CopySet(Set src, Set result)
|
| Copy one set into another
\* ----------------------------------------------------------------- */
void CopySet(Set src, Set result)
{
register Index_t i;
for (i=0; i<setsize; i++)
result[i] = src[i];
}
/* ----------------------------------------------------------------- *\
| int CountSet(Set theset)
|
| Get the cardinality of the set
\* ----------------------------------------------------------------- */
int CountSet(Set theset)
{
register Index_t i, count;
register unsigned int j;
count = 0;
for (i=0; i<setsize; i++)
for (j=0; j<SETSCALE; j++)
if (theset[i] & ((Set_t)1<<j))
count++;
return count;
}
/* ----------------------------------------------------------------- *\
| void BuildSet(Set theset, Index_t *thelist, Index_t length)
|
| Build a set out of a list of integers
\* ----------------------------------------------------------------- */
void BuildSet(Set theset, Index_t *thelist, Index_t length)
{
register Index_t i;
EmptySet(theset);
for (i=0; i<length; i++)
theset[thelist[i]/SETSCALE] |= (Set_t)1 << (thelist[i] % SETSCALE);
}
/* ----------------------------------------------------------------- *\
| void DoForSet(Set theset, void (*action)(int, void *), void *arg)
|
| Do something to every element in a set
\* ----------------------------------------------------------------- */
void DoForSet(Set theset, void (*action)(int, void *), void *arg)
{
register Index_t i;
register unsigned int j;
for (i=0; i<setsize; i++)
for (j=0; j<SETSCALE; j++)
if (theset[i] & ((Set_t)1<<j))
(*action)((int)(SETSCALE*i + j), arg);
}
/* ======================== SEARCH ROUTINES ======================== */
Set results, oldresults, oneword, onefield;
short firstfield, lastfield; /* indices into fieldtable */
/* ----------------------------------------------------------------- *\
| void InitSearch(void)
|
| Initialize the search lists
\* ----------------------------------------------------------------- */
void InitSearch(VOID)
{
results = NewSet();
oldresults = NewSet();
oneword = NewSet();
onefield = NewSet();
firstfield = lastfield = -1;
}
/* ----------------------------------------------------------------- *\
| void FreeSearch(void)
|
| Free the search list
\* ----------------------------------------------------------------- */
void FreeSearch(VOID)
{
free(results);
free(oldresults);
free(oneword);
free(onefield);
}
/* ----------------------------------------------------------------- *\
| void ClearResults(void)
|
| Clear the current and old results
\* ----------------------------------------------------------------- */
void ClearResults(VOID)
{
EmptySet(results);
SetComplement(results, results);
CopySet(results, oldresults);
}
/* ----------------------------------------------------------------- *\
| void SaveResults(void)
|
| Save and clear the current results
\* ----------------------------------------------------------------- */
void SaveResults(VOID)
{
CopySet(results, oldresults);
EmptySet(results);
SetComplement(results, results);
}
/* ----------------------------------------------------------------- *\
| void CombineResults(char invert, char intersect)
|
| Combine current results with old results
\* ----------------------------------------------------------------- */
void CombineResults(char invert, char intersect)
{
if (invert)
SetComplement(results, results);
if (intersect)
SetIntersection(results, oldresults, results);
else
SetUnion(results, oldresults, results);
}
/* ----------------------------------------------------------------- *\
| char SetUpField(char *field)
|
| Set up the search fields. Return the number of searchable fields.
\* ----------------------------------------------------------------- */
char SetUpField(char *field)
{
int i, len;
firstfield = -1;
len = strlen(field);
for (i=0; i < (int)numfields; i++)
{
if (!strncmp(field, fieldtable[i].thefield, len))
{
if (firstfield == -1)
firstfield = i;
lastfield = i;
}
}
if (firstfield == -1)
{
(void)printf("\tNo searchable fields matching \"%s\".\n", field);
return 0;
}
else
return lastfield - firstfield + 1;
}
const char *badwords[] = BADWORDS;
/* ----------------------------------------------------------------- *\
| void FindWord(char *word, char prefix)
|
| Find a word in the currently active field and update `results'.
| If the prefix flag is set, find all words having the given prefix.
\* ----------------------------------------------------------------- */
void FindWord(register char *word, char prefix)
{
register IndexPtr words;
Index_t win, len;
int i;
if (!prefix)
{
if (!word[0])
{
(void)printf("\t[ignoring empty string]\n");
return;
}
if (!word[1])
{
(void)printf("\t[ignoring single letter \"%s\"]\n", word);
return;
}
#if !IGNORENONE
for (i=0; badwords[i]; i++)
{
if (!strcmp(badwords[i], word))
{
(void)printf("\t[ignoring common word \"%s\"]\n", word);
return;
}
}
#endif
}
EmptySet(oneword);
len = strlen(word);
for (i=firstfield; i<=lastfield; i++)
{
words = fieldtable[i].words;
win = FindIndex(fieldtable[i], word, prefix);
if (win != INDEX_NAN)
{
do {
CachedList *clist = &(words[win].refs);
Index_t *p;
Access(clist, bixfp);
p = (Index_t *)safemalloc(clist->length * sizeof(Index_t),
"Can't allocate entry list.", "");
UncompressRefs(p, clist->list, clist->length);
BuildSet(onefield, p, clist->length);
SetUnion(oneword, onefield, oneword);
free(p);
} while (prefix && ++win < fieldtable[i].numwords &&
!strncmp(words[win].theword, word, len));
}
}
SetIntersection(oneword, results, results);
}
/* ============================= OUTPUT ============================ */
FILE *bibfp;
/* ----------------------------------------------------------------- *\
| void ReportResults(void)
|
| Report the results of the previous search.
\* ----------------------------------------------------------------- */
void ReportResults(VOID)
{
int numresults;
numresults = CountSet(results);
if (numresults == 0)
(void)printf("\tNo matches found.\n");
else if (numresults == 1)
(void)printf("\t1 match found.\n");
else
(void)printf("\t%d matches found.\n", numresults);
}
/* ----------------------------------------------------------------- *\
| void PrintEntry(int entry, FILE *ofp)
|
| Print the entry.
\* ----------------------------------------------------------------- */
void PrintEntry(int entry, FILE *ofp)
{
char ch;
char braces;
char quotes;
if (entry >= (int)numoffsets) /* extra bits might be set */
return;
putc('\n', ofp);
if (fseek(bibfp, offsets[entry], 0))
die("Index file is corrupt.", "");
ch = safegetc(bibfp);
while (ch != '@')
{
putc(ch, ofp);
ch = safegetc(bibfp);
}
while ((ch != '{') && (ch != '('))
{
putc(ch, ofp);
ch = safegetc(bibfp);
}
braces = quotes = 0;
putc(ch, ofp);
ch = safegetc(bibfp);
while (braces || quotes || ((ch != '}') && (ch != ')')))
{
if (ch == '{')
braces++;
else if (ch == '}')
braces--;
else if ((ch == '"') && !braces)
quotes = !quotes;
putc(ch, ofp);
ch = safegetc(bibfp);
}
putc(ch, ofp);
putc('\n', ofp);
}
/* ----------------------------------------------------------------- *\
| void PrintResults(char *filename)
|
| Print the current search results into the given file. If the
| filename is NULL, pipe the output through $PAGER.
\* ----------------------------------------------------------------- */
void PrintResults(char *filename)
{
int numresults;
FILE *ofp;
char *pager;
char *the_tmpfile = (char*)NULL;
#if unix
int childpid;
#else
char *command, *command_fname;
#endif
numresults = CountSet(results);
if (numresults == 0)
(void)printf("\tNothing to display!\n");
#if MAXRESULTS
else if (numresults > MAXRESULTS)
(void)printf("\tI can't display that many results!\n");
#endif
else
{
if (filename)
{
ofp = fopen(filename, "a");
if (!ofp)
{
(void)printf("\tCan't open %s: ", filename);
perror(NULL);
return;
}
}
else
{
the_tmpfile = (char*)tempnam(NULL, "bibl.");
ofp = fopen(the_tmpfile, "w");
if (!ofp)
{
perror("\tCan't open temp file");
return;
}
}
if (filename)
{
time_t now = time(0);
(void)fprintf(ofp, "%% Retrieved by biblook %d.%d at %s",
MAJOR_VERSION, MINOR_VERSION, ctime(&now));
}
DoForSet(results, (void (*)(int, void *)) PrintEntry,
(void *) ofp);
fclose(ofp);
if (filename)
(void)printf("\tResults saved in \"%s\"\n", filename);
else
{
pager = (char*)getenv("PAGER");
#if unix
if ((childpid = (int)fork()) != 0)
waitpid(childpid, (int *) 0, 0);
else if (pager)
{
execlp(pager, pager, the_tmpfile, (char *) 0);
perror(pager); /* should never get here! */
exit(EXIT_SUCCESS);
}
else
{
/* try absolute path first */
execl(MOREPATH, MORE, the_tmpfile, (char *) 0);
/* next try to find it in PATH list */
execlp(MORE, MORE, the_tmpfile, (char *) 0);
/* no pager available, so give up */
perror(MOREPATH);
exit(EXIT_SUCCESS);
}
#elif MSDOS
if (pager)
{
command = (char *) malloc(strlen(pager) + 2 + strlen(the_tmpfile));
strcpy(command, pager);
strcat(command, " ");
}
else
{
command = (char *) malloc(7 + strlen(the_tmpfile));
strcpy(command, "MORE <");
}
command_fname = command + strlen(command);
strcat(command, the_tmpfile);
for (; *command_fname != '\0' ; command_fname++)
if (*command_fname == '/')
*command_fname = '\\';
if (system(command))
perror( (pager? pager : "MORE") );
free(command);
#else /* ? other systems ? */
#endif
unlink(the_tmpfile);
free(the_tmpfile); /* malloc'ed by tempnam() */
putchar('\n');
}
}
}
/* ----------------------------------------------------------------- *\
| void DisplayAbbrev(char *theabbrev)
|
| Display the definition of the given abbreviation.
\* ----------------------------------------------------------------- */
void DisplayAbbrev(char *theabbrev)
{
Index_t the_index = FindAbbrev(theabbrev);
if (the_index == INDEX_NAN)
(void)printf("\tThe abbreviation \"%s\" is not defined.\n", theabbrev);
else if (abbrevlocs[the_index] == INDEX_BUILTIN)
(void)printf("\tThe abbreviation \"%s\" is builtin.\n", theabbrev);
else
{
PrintEntry((int)abbrevlocs[the_index], stdout);
putchar('\n');
}
}
/* ======================== USER INTERFACE ========================= */
typedef enum {
T_Find, T_Whatis, T_Display, T_Save, T_Quit, T_Word,
T_And, T_Or, T_Not, T_Semi, T_Return, T_Help
} Token;
/* ----------------------------------------------------------------- *\
| Token GetToken(char *tokenstr)
|
| Get the next input token.
\* ----------------------------------------------------------------- */
Token GetToken(char *tokenstr)
{
static char line[256];
static short pos;
static char neednew = 1;
short tlen = 0;
*tokenstr = 0;
if (neednew)
{
(void)printf("biblook: ");
if (!fgets(line, 254, stdin))
return T_Quit;
pos = 0;
neednew = 0;
}
while ((line[pos] == ' ') || (line[pos] == '\t'))
pos++;
switch (line[pos])
{
case '\n':
pos++;
neednew = 1;
return T_Return;
case '&':
pos++;
return T_And;
case '|':
pos++;
return T_Or;
case '~':
case '!':
pos++;
return T_Not;
case ';':
pos++;
return T_Semi;
case '?':
pos++;
return T_Help;
default:
tokenstr[tlen++] = tolower(line[pos++]);
while (!isspace(line[pos]) && (line[pos] != ';') &&
(line[pos] != '&') && (line[pos] != '|'))
{
tokenstr[tlen++] = tolower(line[pos++]);
}
tokenstr[tlen] = 0;
/* I really ought to use a hash table here. */
if (!strncmp(tokenstr, "find", tlen))
return T_Find;
else if (!strncmp(tokenstr, "display", tlen))
return T_Display;
else if (!strncmp(tokenstr, "help", tlen))
return T_Help;
else if (!strncmp(tokenstr, "save", tlen))
return T_Save;
else if (!strncmp(tokenstr, "whatis", tlen))
return T_Whatis;
else if (!strncmp(tokenstr, "quit", tlen))
return T_Quit;
else if (!strcmp(tokenstr, "and"))
return T_And;
else if (!strcmp(tokenstr, "or"))
return T_Or;
else if (!strcmp(tokenstr, "not"))
return T_Not;
else
return T_Word;
}
}
/* ----------------------------------------------------------------- *\
| char Strip(char *string)
|
| Strip all but alphanumeric characters out of the string. Return
| true if the original string ended with the prefix character '*'.
\* ----------------------------------------------------------------- */
char Strip(char *string)
{
char prefix = 0;
char *src = string;
while (*src)
{
prefix = (*src == '*');
if (isalnum(*src))
*string++ = *src;
src++;
}
*string = 0;
return prefix;
}
/* ----------------------------------------------------------------- *\
| void CmdError(void)
|
| Print syntax error message
\* ----------------------------------------------------------------- */
void CmdError(VOID)
{
(void)printf("\t?? Syntax error ??\n");
}
static const char* shorthelplines[] =
{
"------------------------------------------------------------",
"help Print this message",
"find <field> <words> Find entries with <words> in <field>",
"and <field> <words> Narrow search",
"or <field> <words> Widen search",
"display Display search results",
"save <file> Save search results to <file>",
"whatis <abbrev> Find and display an abbreviation",
"quit Quit biblook",
"------------------------------------------------------------",
"Type `help' or `?' again for more details.",
(const char *) NULL,
};
static const char* longhelplines[] =
{
"biblook permits rapid lookup in a BibTeX bibliography data",
"base, using a compact binary index file prepared by bibindex(1).",
"",
"Available commands:",
"? or h[elp]",
" Display this help message.",
"",
"f[ind] [not] <field> <words>",
" Find the entries containing the given words in any",
" field with a prefix matching the <field> argument. For",
" example, `a' matches both `author' and `address', and",
" `au' matches `author' only. If the <field> argument is",
" `-' (or any string with no letters or numbers), match",
" any field.",
"",
" If `not' appears before the <field>, the sense of the",
" search is reversed. The symbols `~' and `!' can be",
" used in place of `not'.",
"",
" Each word is a contiguous sequence of letters and",
" digits. Case is ignored; accents should be omitted;",
" apostrophes are not required. Single characters and a",
" few common words are also ignored. Any word ending",
" with an asterisk is treated as a prefix. Thus,",
" `point*' matches `point', `points', `pointer', etc.",
"",
"and [not] <field> <words>",
"or [not] <field> <words>",
" Intersect (resp. union) the results of the given search",
" with the previous search. Several of these commands",
" may be combined on a single line. Commands are handled",
" in the order in which they appear; there is no pre-",
" cedence. Unlike other commands, and like `not', these",
" must be spelled out completely. `&' can be used in",
" place of `and', and `|' can be used in place of `or'.",
"",
"d[isplay]",
" Display the results of the previous search.",
"",
"s[ave] [<filename>]",
" Save the results of the previous results into the",
" specified file. If <filename> is omitted, the previous",
" save file is used. If no save file has ever been",
" specified, results are saved in the file specified on",
" the command line. If no such file is specified,",
" `save.bib' is used. If the save file exists, results",
" are appended to it.",
"",
"w[hatis] <abbrev>",
" Display the definition of the abbreviation <abbrev>.",
"",
"q[uit]/EOF",
" Quit.",
"",
"Several commands can be combined on a single line by",
"separating them with semicolons. For example, the following",
"command displays all STOC papers cowritten by Erdo\"s",
"without `Voronoi diagrams' in the title:",
"",
"f b stoc* | b symp* theory comp* & au erdos & ~t voronoi diagrams ; d",
"",
(const char*)NULL,
};
/* ----------------------------------------------------------------- *\
| void GiveHelp(int verbose)
|
| Print a help message. Lines are stored as separate strings to
| avoid hitting compiler limits.
\* ----------------------------------------------------------------- */
void GiveHelp(int verbose)
{
int k;
#if 0
/* This fails on IBM RS/6000 AIX 3.2 cc with bogus error:
"Operands must be pointers to compatible types." */
const char **help = verbose ? &longhelplines[0] : &shorthelplines[0];
#else
const char **help;
if (verbose)
help = &longhelplines[0];
else
help = &shorthelplines[0];
#endif
for (k = 0; help[k]; ++k)
(void)printf("\t%s\n", help[k]);
}
/* ----------------------------------------------------------------- *\
| States for Lookup()
\* ----------------------------------------------------------------- */
typedef enum {
Wait, /* nothing yet */
Find, /* "find" */
FindN, /* "find not" */
FindF, /* "find [not] <field>" */
FindW, /* "find [not] <field> <words>" */
Display, /* "display" */
Save, /* "save" */
SaveF, /* "save <file>" */
Whatis, /* "whatis" */
WhatisA, /* "whatis <abbrev>" */
Help, /* "help" */
Error /* anything else */
} CmdState;
/* ----------------------------------------------------------------- *\
| void Lookup(const char *defsave)
|
| Execute commands until the user quits. Defsave is the default
| save file name. This is one big finite state machine. It's long
| and boring, but that's interface code for ya!
\* ----------------------------------------------------------------- */
void Lookup(const char *defsave)
{
char tokenstr[256];
char savestr[256];
CmdState state = Wait;
static CmdState last_state = Wait;
Token thetoken;
char intersect = 1; /* 1 = intersect, 0 = union */
char invert = 0; /* 1 = invert */
char prefix; /* 1 = word is really a prefix */
ClearResults();
strcpy(savestr, defsave);
for (;;)
{
thetoken = GetToken(tokenstr);
if ((thetoken == T_Quit) && !tokenstr[0])
return;
switch (state)
{
case Wait:
switch (thetoken)
{
case T_Quit:
return;
case T_Find:
state = Find;
invert = 0;
ClearResults();
break;
case T_And:
state = Find;
invert = 0;
SaveResults();
break;
case T_Or:
state = Find;
invert = 0;
intersect = 0;
SaveResults();
break;
case T_Display:
state = Display;
break;
case T_Save:
state = Save;
break;
case T_Help:
state = Help;
break;
case T_Whatis:
state = Whatis;
break;
case T_Return:
case T_Semi:
break;
default:
state = Error;
CmdError();
break;
}
break;
case Find:
if (thetoken == T_Not)
{
last_state = state;
state = FindN;
invert = 1;
}
else
{
if (tokenstr[0])
{
state = FindF;
Strip(tokenstr);
if (!SetUpField(tokenstr))
state = Error;
else
last_state = Find;
}
else
{
state = (thetoken == T_Return) ? Wait : Error;
CmdError();
}
}
break;
case FindN:
if (tokenstr[0])
{
state = FindF;
Strip(tokenstr);
if (!SetUpField(tokenstr))
state = Error;
else
last_state = FindN;
}
else
{
state = (thetoken == T_Return) ? Wait : Error;
CmdError();
}
break;
case FindF:
if (tokenstr[0])
{
last_state = state;
state = FindW;
prefix = Strip(tokenstr);
FindWord(tokenstr, prefix);
}
else
{
state = (thetoken == T_Return) ? Wait : Error;
CmdError();
}
break;
case FindW:
switch (thetoken)
{
case T_And:
last_state = state;
state = Find;
CombineResults(invert, intersect);
SaveResults();
invert = 0;
intersect = 1;
break;
case T_Or:
last_state = state;
state = Find;
CombineResults(invert, intersect);
SaveResults();
invert = 0;
intersect = 0;
break;
case T_Semi:
last_state = state;
state = Wait;
CombineResults(invert, intersect);
invert = 0;
intersect = 1;
break;
case T_Return:
last_state = state;
state = Wait;
CombineResults(invert, intersect);
ReportResults();
invert = 0;
intersect = 1;
break;
default:
if (tokenstr[0])
{
last_state = state;
state = FindW;
prefix = Strip(tokenstr);
FindWord(tokenstr, prefix);
}
else
{
state = Error;
CmdError();
}
break;
}
break;
case Display:
if ((thetoken == T_Semi) || (thetoken == T_Return))
{
last_state = state;
state = Wait;
PrintResults(NULL);
}
else
{
state = Error;
CmdError();
}
break;
case Save:
if (tokenstr[0])
{
last_state = state;
state = SaveF;
strcpy(savestr, tokenstr);
}
else if ((thetoken == T_Semi) || (thetoken == T_Return))
{
state = Wait;
PrintResults(savestr);
}
else
{
state = Error;
CmdError();
}
break;
case SaveF:
if ((thetoken == T_Semi) || (thetoken == T_Return))
{
last_state = state;
state = Wait;
PrintResults(savestr);
}
else
{
state = Error;
CmdError();
}
break;
case Whatis:
if (tokenstr[0])
{
last_state = state;
state = WhatisA;
strcpy(savestr, tokenstr);
}
else
{
state = (thetoken == T_Return) ? Wait : Error;
CmdError();
}
break;
case WhatisA:
if ((thetoken == T_Semi) || (thetoken == T_Return))
{
last_state = state;
state = Wait;
DisplayAbbrev(savestr);
}
else
{
state = Error;
CmdError();
}
break;
case Help:
if ((thetoken == T_Semi) || (thetoken == T_Return))
{
state = Wait;
GiveHelp(last_state == Help);
last_state = Help;
}
break;
case Error:
switch (thetoken)
{
case T_Quit:
return;
case T_Return:
state = Wait;
break;
default:
break;
}
break;
} /* end switch(state) */
} /* end for(;;) */
}
/* ================================================================= *\
| The main program
\* ================================================================= */
int main(int argc, char **argv)
{
register char *path, *tmp;
char gotit;
struct stat bibstat, bixstat;
char *p;
(void)printf("biblook version %d.%d file version %d\n",
(int)MAJOR_VERSION, (int)MINOR_VERSION, (int)FILE_VERSION);
(void)printf("Type ? or h for help\n");
if ((argc != 2) && (argc != 3))
{
(void)fprintf(stderr, "Usage: biblook bib [savefile]\n");
exit(EXIT_FAILURE);
}
if (((p = strrchr(argv[1],'.')) != (char*)NULL) &&
(strcmp(p, ".bib") == 0))
{
*p = '\0'; /* remove any .bib extension */
}
/* ---- Search BIBLOOKPATH or BIBINPUTS for the files ---- */
path = (char *)getenv("BIBLOOKPATH");
if (path == NULL)
path = (char *)getenv("BIBINPUTS");
if ((path == NULL) || (argv[1][0] == '/'))
{
(void)sprintf(bibfile, "%s.bib", argv[1]);
(void)sprintf(bixfile, "%s.bix", argv[1]);
}
else
{
tmp = path;
gotit = 0;
while ((tmp != NULL) && !gotit)
{
tmp = strchr(path, ':');
if (tmp != NULL)
*tmp = 0;
if (strcmp(path, "."))
{
(void)sprintf(bibfile, "%s/%s.bib", path, argv[1]);
(void)sprintf(bixfile, "%s/%s.bix", path, argv[1]);
}
else
{
(void)sprintf(bibfile, "%s.bib", argv[1]);
(void)sprintf(bixfile, "%s.bix", argv[1]);
}
if (stat(bibfile, &bibstat) != 0)
{
if (errno != ENOENT)
pdie("Can't open", bibfile);
}
else
gotit = 1;
if (tmp != NULL)
path = tmp + 1;
}
if (!gotit)
{
(void)sprintf(bibfile, "%s.bib", argv[1]);
pdie("Can't find", bibfile);
}
}
/* ---- Now that we've found the files, open them and do the job ---- */
if (stat(bibfile, &bibstat) != 0)
pdie("Can't open", bibfile);
if (stat(bixfile, &bixstat) != 0)
pdie("Can't open", bixfile);
if (bibstat.st_mtime > bixstat.st_mtime)
die(bixfile, "is out of date.\n\tPlease rerun bibindex.");
bibfp = fopen(bibfile, "r");
if (!bibfp)
pdie("Can't read", bibfile);
#if MSDOS
bixfp = fopen(bixfile, "rb");
#else
bixfp = fopen(bixfile, "r");
#endif
if (!bixfp)
pdie("Can't read", bixfile);
GetTables();
InitSearch();
if (argc == 3)
Lookup(argv[2]);
else
Lookup("save.bib");
FreeSearch();
FreeTables();
fclose(bibfp);
fclose(bixfp);
exit(EXIT_SUCCESS);
return(0);
}
|