📄 mergedb.c
字号:
static char rcsid[] = "mergedb.c,v 1.20 1996/01/04 03:46:44 duane Exp";/* * mergedb.c - Merge Automatic and Manual version of Essence database. * * Usage: mergedb production automatic manual [manual ...] * * This program allows administrators to manually add information about * objects (URLs) to the Essence database. In order to preserve all of * the automatically generated information about objects, the manually- * and automatically-generated information are merged into a new, * production database. All manually-generated information overrides * any automatically-generated information. * * Darren Hardy, hardy@cs.colorado.edu, March 1994 * * ---------------------------------------------------------------------- * Copyright (c) 1994, 1995. All rights reserved. * * The Harvest software was developed by the Internet Research Task * Force Research Group on Resource Discovery (IRTF-RD): * * Mic Bowman of Transarc Corporation. * Peter Danzig of the University of Southern California. * Darren R. Hardy of the University of Colorado at Boulder. * Udi Manber of the University of Arizona. * Michael F. Schwartz of the University of Colorado at Boulder. * Duane Wessels of the University of Colorado at Boulder. * * This copyright notice applies to software in the Harvest * ``src/'' directory only. Users should consult the individual * copyright notices in the ``components/'' subdirectories for * copyright information about other software bundled with the * Harvest source code distribution. * * TERMS OF USE * * The Harvest software may be used and re-distributed without * charge, provided that the software origin and research team are * cited in any use of the system. Most commonly this is * accomplished by including a link to the Harvest Home Page * (http://harvest.cs.colorado.edu/) from the query page of any * Broker you deploy, as well as in the query result pages. These * links are generated automatically by the standard Broker * software distribution. * * The Harvest software is provided ``as is'', without express or * implied warranty, and with no support nor obligation to assist * in its use, correction, modification or enhancement. We assume * no liability with respect to the infringement of copyrights, * trade secrets, or any patents, and are not responsible for * consequential damages. Proper use of the Harvest software is * entirely the responsibility of the user. * * DERIVATIVE WORKS * * Users may make derivative works from the Harvest software, subject * to the following constraints: * * - You must include the above copyright notice and these * accompanying paragraphs in all forms of derivative works, * and any documentation and other materials related to such * distribution and use acknowledge that the software was * developed at the above institutions. * * - You must notify IRTF-RD regarding your distribution of * the derivative work. * * - You must clearly notify users that your are distributing * a modified version and not the original Harvest software. * * - Any derivative product is also subject to these copyright * and use restrictions. * * Note that the Harvest software is NOT in the public domain. We * retain copyright, as specified above. * * HISTORY OF FREE SOFTWARE STATUS * * Originally we required sites to license the software in cases * where they were going to build commercial products/services * around Harvest. In June 1995 we changed this policy. We now * allow people to use the core Harvest software (the code found in * the Harvest ``src/'' directory) for free. We made this change * in the interest of encouraging the widest possible deployment of * the technology. The Harvest software is really a reference * implementation of a set of protocols and formats, some of which * we intend to standardize. We encourage commercial * re-implementations of code complying to this set of standards. * */#include <stdio.h>#include <stdlib.h>#include <string.h>#include <unistd.h>#include <gdbm.h>#include "util.h"#include "template.h"/* Local functions */static void usage();static void mergedb();/* Local variables */static int nreplace = 0;static void usage(){ fprintf(stderr, "Usage: mergedb production automatic manual [manual ...]\n"); exit(1);}static void process_manual_template(proddb, data, key) GDBM_FILE proddb; datum data, key;{ Template *mt; datum k; init_parse_template_string(data.dptr, data.dsize); if ((mt = parse_template()) == NULL) { errorlog("Manual SOIF object is corrupt: %s\n", key.dptr); exit(1); } finish_parse_template(); k.dptr = strdup(mt->url); k.dsize = strlen(k.dptr) + 1; if (gdbm_store(proddb, k, data, GDBM_REPLACE)) errorlog("gdbm_store: %s: %s\n", k.dptr, gdbm_strerror(gdbm_errno)); free_template(mt); free(k.dptr);}static void add_manual_to_production(filename, proddb) char *filename; GDBM_FILE proddb;{ GDBM_FILE dbf; datum k, nk, d; dbf = gdbm_open(filename, 0, GDBM_READER, 0644, NULL); if (dbf == NULL) { errorlog("gdbm_open: %s: %s\n", filename, gdbm_strerror(gdbm_errno)); return; } k = gdbm_firstkey(dbf); while (k.dptr) { nk = gdbm_nextkey(dbf, k); d = gdbm_fetch(dbf, k); process_manual_template(proddb, d, k); free(k.dptr); free(d.dptr); k = nk; } gdbm_close(dbf);}/* * merge_auto_data() - Converts ad and pd to templates, then merges the * pd template into the ad template, then replaces the data for the * proddb with the newly constructed template. */static void merge_auto_data(proddb, k, ad, pd) GDBM_FILE proddb; datum k, ad, pd;{ Template *at, *pt; Buffer *b; datum d; init_parse_template_string(ad.dptr, ad.dsize); at = parse_template(); finish_parse_template(); init_parse_template_string(pd.dptr, pd.dsize); pt = parse_template(); finish_parse_template(); if (at == NULL || pt == NULL) return; merge_AVList(at->list, pt->list); b = init_print_template(NULL); print_template(at); d.dptr = b->data; d.dsize = b->length; gdbm_store(proddb, k, d, GDBM_REPLACE); nreplace++; finish_print_template();}/* * merge_auto() - Merge the automatic information into the production * database. */static void merge_auto(autodb, proddb) GDBM_FILE autodb; GDBM_FILE proddb;{ datum ad, pd, k, nk; if (autodb == NULL) return; k = gdbm_firstkey(autodb); while (k.dptr) { nk = gdbm_nextkey(autodb, k); ad = gdbm_fetch(autodb, k); if (gdbm_exists(proddb, k)) { pd = gdbm_fetch(proddb, k); merge_auto_data(proddb, k, ad, pd); free(pd.dptr); } else { gdbm_store(proddb, k, ad, GDBM_INSERT); } free(k.dptr); free(ad.dptr); k = nk; }}/* * To merge N manual databases with one automatic databases, the N * manual databases are consolidated into the production database. * (Entire Templates are overwritten if they were present in an earlier * manual database). Then each automatic template is merged into * the production database. */int main(argc, argv) int argc; char *argv[];{ GDBM_FILE proddb, autodb; int value = 256; if (argc < 4) usage(); init_log3("mergedb", stdout, stderr); proddb = gdbm_open(*++argv, 0, GDBM_NEWDB, 0644, NULL); if (proddb == NULL) { errorlog("gdbm_open: %s: %s\n", *argv, gdbm_strerror(gdbm_errno)); log_errno(*argv); exit(1); } gdbm_setopt(proddb, GDBM_CACHESIZE, &value, sizeof(int)); autodb = gdbm_open(*++argv, 0, GDBM_READER, 0644, NULL); if (autodb == NULL && gdbm_errno != GDBM_EMPTY_DATABASE) { errorlog("gdbm_open: %s: %s\n", *argv, gdbm_strerror(gdbm_errno)); gdbm_close(proddb); exit(1); } argc -= 2; while (--argc > 0) { add_manual_to_production(*++argv, proddb); } if (autodb != NULL) { merge_auto(autodb, proddb); gdbm_close(autodb); } if (nreplace > 64) { gdbm_sync(proddb); gdbm_reorganize(proddb); } gdbm_close(proddb); exit(0);}
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -