[855] | 1 | /**************************************************************************
|
---|
| 2 | *
|
---|
| 3 | * mg_invf_dict_dump.cpp -- Program to printthe various inverted dictionaries
|
---|
| 4 | * Copyright (C) 1999 Rodger McNab
|
---|
| 5 | *
|
---|
| 6 | * This program is free software; you can redistribute it and/or modify
|
---|
| 7 | * it under the terms of the GNU General Public License as published by
|
---|
| 8 | * the Free Software Foundation; either version 2 of the License, or
|
---|
| 9 | * (at your option) any later version.
|
---|
| 10 | *
|
---|
| 11 | * This program is distributed in the hope that it will be useful,
|
---|
| 12 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 13 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 14 | * GNU General Public License for more details.
|
---|
| 15 | *
|
---|
| 16 | * You should have received a copy of the GNU General Public License
|
---|
| 17 | * along with this program; if not, write to the Free Software
|
---|
| 18 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 19 | *
|
---|
| 20 | **************************************************************************/
|
---|
[2468] | 21 |
|
---|
[2442] | 22 | #define _XOPEN_SOURCE 1
|
---|
| 23 | #define _XOPEN_SOURCE_EXTENDED 1
|
---|
[855] | 24 |
|
---|
[2468] | 25 | // need this to avoid bizarre compiler problems under VC++ 6.0
|
---|
| 26 | #if defined (__WIN32__) && !defined (GSDL_USE_IOS_H)
|
---|
| 27 | # include <iostream>
|
---|
| 28 | #endif
|
---|
| 29 |
|
---|
| 30 | #if defined (__WIN32__)
|
---|
| 31 | # include "getopt.h"
|
---|
| 32 | #else
|
---|
| 33 | # include <unistd.h>
|
---|
| 34 | #endif
|
---|
| 35 |
|
---|
[855] | 36 | #include "sysfuncs.h"
|
---|
| 37 | #include "messages.h"
|
---|
| 38 | #include "mg_files.h"
|
---|
| 39 | #include "invf.h"
|
---|
| 40 |
|
---|
| 41 | static void process_files (char *filename,
|
---|
| 42 | bool printHeader,
|
---|
| 43 | bool printWords,
|
---|
| 44 | bool printTags) {
|
---|
| 45 | // open the dictionary
|
---|
| 46 | FILE *dictFile = open_file (filename, INVF_DICT_SUFFIX, "rb",
|
---|
| 47 | MAGIC_STEM_BUILD, MG_ABORT);
|
---|
| 48 | invf_dict_header idh;
|
---|
| 49 | idh.Read (dictFile);
|
---|
| 50 |
|
---|
| 51 | // print the information from the inverted dictionary file header
|
---|
| 52 | if (printHeader) {
|
---|
| 53 | cout << "lookback: " << idh.lookback << "\n";
|
---|
| 54 | cout << "word_dict_start: " << idh.word_dict_start << "\n";
|
---|
| 55 | cout << "word_dict_size: " << idh.word_dict_size << "\n";
|
---|
| 56 | cout << "tag_dict_start: " << idh.tag_dict_start << "\n";
|
---|
| 57 | cout << "tag_dict_size: " << idh.tag_dict_size << "\n";
|
---|
| 58 | cout << "num_docs: " << idh.num_docs << "\n";
|
---|
| 59 | cout << "num_frags: " << idh.num_frags << "\n";
|
---|
| 60 | cout << "num_words: " << idh.num_words << "\n";
|
---|
| 61 | cout << "total_bytes: " << idh.total_bytes << "\n";
|
---|
| 62 | cout << "index_string_bytes: " << idh.index_string_bytes << "\n";
|
---|
| 63 | cout << "num_levels: " << idh.num_levels << "\n";
|
---|
| 64 |
|
---|
| 65 | cout << "\n";
|
---|
| 66 | }
|
---|
| 67 |
|
---|
| 68 |
|
---|
| 69 | if (printWords) {
|
---|
| 70 | fseek (dictFile, idh.word_dict_start, SEEK_SET);
|
---|
| 71 |
|
---|
| 72 | unsigned long wordNum;
|
---|
| 73 | word_dict_el wordEl;
|
---|
| 74 | wordEl.SetNumLevels (idh.num_levels);
|
---|
| 75 | for (wordNum=0; wordNum<idh.word_dict_size; wordNum++) {
|
---|
| 76 | wordEl.Read (dictFile, idh.num_levels);
|
---|
| 77 | cout << "\"" << wordEl.el << "\"\n";// (" << wordNum << ")\n";
|
---|
| 78 | }
|
---|
| 79 |
|
---|
| 80 | cout << "\n";
|
---|
| 81 | }
|
---|
| 82 |
|
---|
| 83 | // write out the tag part of the dictionary
|
---|
| 84 | if (printTags) {
|
---|
| 85 | fseek (dictFile, idh.tag_dict_start, SEEK_SET);
|
---|
| 86 |
|
---|
| 87 | unsigned long tagNum;
|
---|
| 88 | dict_el tagEl;
|
---|
| 89 | for (tagNum=0; tagNum<idh.tag_dict_size; tagNum++) {
|
---|
| 90 | // read in the next tag and inverted file pointer
|
---|
| 91 | tagEl.Read (dictFile);
|
---|
| 92 |
|
---|
| 93 | cout << "\"" << tagEl.el << "\" (" << tagNum << ")\n";
|
---|
| 94 | }
|
---|
| 95 | }
|
---|
| 96 |
|
---|
| 97 | // close open files
|
---|
| 98 | fclose (dictFile);
|
---|
| 99 | }
|
---|
| 100 |
|
---|
| 101 |
|
---|
| 102 | int main (int argc, char **argv) {
|
---|
| 103 | char *filename = "";
|
---|
| 104 | int ch;
|
---|
| 105 | msg_prefix = argv[0];
|
---|
| 106 | opterr = 0;
|
---|
| 107 |
|
---|
| 108 | bool printHeader = false;
|
---|
| 109 | bool printWords = false;
|
---|
| 110 | bool printTags = false;
|
---|
| 111 |
|
---|
| 112 | while ((ch = getopt (argc, argv, "f:d:rwth")) != -1) {
|
---|
| 113 | switch (ch) {
|
---|
| 114 | case 'f': // input file
|
---|
| 115 | filename = optarg;
|
---|
| 116 | break;
|
---|
| 117 | case 'd':
|
---|
| 118 | set_basepath (optarg);
|
---|
| 119 | break;
|
---|
| 120 | case 'r':
|
---|
| 121 | printHeader = true;
|
---|
| 122 | break;
|
---|
| 123 | case 'w':
|
---|
| 124 | printWords = true;
|
---|
| 125 | break;
|
---|
| 126 | case 't':
|
---|
| 127 | printTags = true;
|
---|
| 128 | break;
|
---|
| 129 | case 'h':
|
---|
| 130 | case '?':
|
---|
[1899] | 131 | fprintf (stderr, "usage: %s [-h] [-r] [-w] [-t] [-f input_file] "
|
---|
| 132 | "[-d data directory]\n(-rwt:print header, words, tags)\n",
|
---|
| 133 | argv[0]);
|
---|
[855] | 134 | exit (1);
|
---|
| 135 | }
|
---|
| 136 | }
|
---|
| 137 |
|
---|
| 138 | process_files (filename, printHeader, printWords, printTags);
|
---|
| 139 | return 0;
|
---|
| 140 | }
|
---|