1 | /**************************************************************************
|
---|
2 | *
|
---|
3 | * mgdictlist.c -- Program to list a dictionary
|
---|
4 | * Copyright (C) 1994 Neil Sharman
|
---|
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 | * $Id: mgdictlist.c 3745 2003-02-20 21:20:24Z mdewsnip $
|
---|
21 | *
|
---|
22 | **************************************************************************/
|
---|
23 |
|
---|
24 | #include "sysfuncs.h"
|
---|
25 |
|
---|
26 | #include "messages.h"
|
---|
27 | #include "memlib.h"
|
---|
28 | #include "local_strings.h"
|
---|
29 | #include "netorder.h" /* [RPAP - Jan 97: Endian Ordering] */
|
---|
30 |
|
---|
31 | #include "mg_files.h"
|
---|
32 | #include "text.h"
|
---|
33 | #include "invf.h"
|
---|
34 | #include "locallib.h"
|
---|
35 | #include "words.h"
|
---|
36 |
|
---|
37 | /*
|
---|
38 | $Log$
|
---|
39 | Revision 1.1 2003/02/20 21:18:24 mdewsnip
|
---|
40 | Addition of MG package for search and retrieval
|
---|
41 |
|
---|
42 | Revision 1.1 1999/08/10 21:18:17 sjboddie
|
---|
43 | renamed mg-1.3d directory mg
|
---|
44 |
|
---|
45 | Revision 1.2 1998/11/25 07:55:49 rjmcnab
|
---|
46 |
|
---|
47 | Modified mg to that you can specify the stemmer you want
|
---|
48 | to use via a command line option. You specify it to
|
---|
49 | mg_passes during the build process. The number of the
|
---|
50 | stemmer that you used is stored within the inverted
|
---|
51 | dictionary header and the stemmed dictionary header so
|
---|
52 | the correct stemmer is used in later stages of building
|
---|
53 | and querying.
|
---|
54 |
|
---|
55 | Revision 1.1 1998/11/17 09:35:24 rjmcnab
|
---|
56 | *** empty log message ***
|
---|
57 |
|
---|
58 | * Revision 1.4 1994/11/29 00:32:07 tes
|
---|
59 | * Committing the new merged files and changes.
|
---|
60 | *
|
---|
61 | * Revision 1.3 1994/10/20 03:57:01 tes
|
---|
62 | * I have rewritten the boolean query optimiser and abstracted out the
|
---|
63 | * components of the boolean query.
|
---|
64 | *
|
---|
65 | * Revision 1.2 1994/09/20 04:41:56 tes
|
---|
66 | * For version 1.1
|
---|
67 | *
|
---|
68 | */
|
---|
69 |
|
---|
70 | static char *RCSID = "$Id: mgdictlist.c 3745 2003-02-20 21:20:24Z mdewsnip $";
|
---|
71 |
|
---|
72 |
|
---|
73 | int quick = 0;
|
---|
74 | int no_of_words[2];
|
---|
75 | u_long maxcodelen[2];
|
---|
76 |
|
---|
77 | char *dictname = "";
|
---|
78 |
|
---|
79 |
|
---|
80 |
|
---|
81 |
|
---|
82 | void
|
---|
83 | DumpStemDict (FILE * f)
|
---|
84 | {
|
---|
85 | struct invf_dict_header idh;
|
---|
86 | int i;
|
---|
87 | u_char prev[MAXSTEMLEN + 1];
|
---|
88 |
|
---|
89 | fread (&idh, sizeof (idh), 1, f);
|
---|
90 |
|
---|
91 | /* [RPAP - Jan 97: Endian Ordering] */
|
---|
92 | NTOHUL(idh.lookback);
|
---|
93 | NTOHUL(idh.dict_size);
|
---|
94 | NTOHUL(idh.total_bytes);
|
---|
95 | NTOHUL(idh.index_string_bytes);
|
---|
96 | NTOHD(idh.input_bytes); /* [RJM 07/97: 4G limit] */
|
---|
97 | NTOHUL(idh.num_of_docs);
|
---|
98 | NTOHUL(idh.static_num_of_docs);
|
---|
99 | NTOHUL(idh.num_of_words);
|
---|
100 | NTOHUL(idh.stemmer_num);
|
---|
101 | NTOHUL(idh.stem_method);
|
---|
102 |
|
---|
103 | if (quick)
|
---|
104 | printf ("%ld\n", idh.dict_size);
|
---|
105 | else
|
---|
106 | {
|
---|
107 | printf ("# lookback = %lu\n", idh.lookback);
|
---|
108 | printf ("# dict size = %lu\n", idh.dict_size);
|
---|
109 | printf ("# total bytes = %lu\n", idh.total_bytes);
|
---|
110 | printf ("# index string bytes = %lu\n", idh.index_string_bytes);
|
---|
111 | printf ("# input bytes = %.0f\n", idh.input_bytes); /* [RJM 07/97: 4G limit] */
|
---|
112 | printf ("# num of docs = %lu\n", idh.num_of_docs);
|
---|
113 | printf ("# static num of docs = %lu\n", idh.static_num_of_docs);
|
---|
114 | printf ("# num of words = %lu\n", idh.num_of_words);
|
---|
115 | printf ("#\n");
|
---|
116 | }
|
---|
117 |
|
---|
118 | for (i = 0; i < idh.dict_size; i++)
|
---|
119 | {
|
---|
120 | register unsigned long copy, suff;
|
---|
121 | unsigned long wcnt, fcnt;
|
---|
122 |
|
---|
123 | /* build a new word on top of prev */
|
---|
124 | copy = getc (f);
|
---|
125 | suff = getc (f);
|
---|
126 | *prev = copy + suff;
|
---|
127 | fread (prev + copy + 1, sizeof (u_char), suff, f);
|
---|
128 |
|
---|
129 | /* read other data, but no need to store it */
|
---|
130 | fread (&fcnt, sizeof (fcnt), 1, f);
|
---|
131 | fread (&wcnt, sizeof (wcnt), 1, f);
|
---|
132 |
|
---|
133 | /* [RPAP - Jan 97: Endian Ordering] */
|
---|
134 | NTOHUL(fcnt);
|
---|
135 | NTOHUL(wcnt);
|
---|
136 |
|
---|
137 | if (!quick)
|
---|
138 | {
|
---|
139 | printf ("%d: %8ld ", i, wcnt);
|
---|
140 | printf ("/ %5ld ", fcnt);
|
---|
141 | printf ("%2d %2ld\t\"", *prev, copy);
|
---|
142 | }
|
---|
143 | printf ("%s", word2str (prev));
|
---|
144 | if (quick)
|
---|
145 | printf (" %ld %ld\n", wcnt, fcnt);
|
---|
146 | else
|
---|
147 | {
|
---|
148 | putchar ('"');
|
---|
149 | putchar ('\n');
|
---|
150 | }
|
---|
151 | }
|
---|
152 | }
|
---|
153 |
|
---|
154 |
|
---|
155 |
|
---|
156 |
|
---|
157 | void
|
---|
158 | ReadInWords (FILE * f)
|
---|
159 | {
|
---|
160 | comp_frags_header cfh;
|
---|
161 | u_long *codes;
|
---|
162 | u_char prev[MAXSTEMLEN + 1];
|
---|
163 | int i;
|
---|
164 |
|
---|
165 | if (Read_cfh (f, &cfh, NULL, NULL) == -1)
|
---|
166 | FatalError (1, "Unable to read in the dictionary");
|
---|
167 |
|
---|
168 | printf ("#\n");
|
---|
169 | printf ("# max code len = %u\n", cfh.hd.maxcodelen);
|
---|
170 | printf ("# total bytes = %lu\n", cfh.uncompressed_size);
|
---|
171 | printf ("#\n");
|
---|
172 |
|
---|
173 | if (!(codes = Generate_Huffman_Codes (&cfh.hd, NULL)))
|
---|
174 | FatalError (1, "no memory for huffman codes\n");
|
---|
175 |
|
---|
176 | for (i = 0; i < cfh.hd.num_codes; i++)
|
---|
177 | {
|
---|
178 | register int val, copy, j, k;
|
---|
179 | char code[33];
|
---|
180 | val = fgetc (f);
|
---|
181 | copy = (val >> 4) & 0xf;
|
---|
182 | val &= 0xf;
|
---|
183 |
|
---|
184 | fread (prev + copy + 1, sizeof (u_char), val, f);
|
---|
185 | *prev = val + copy;
|
---|
186 |
|
---|
187 | for (k = 0, j = cfh.hd.clens[i] - 1; j >= 0; j--, k++)
|
---|
188 | code[k] = '0' + ((codes[i] >> j) & 1);
|
---|
189 | code[k] = '\0';
|
---|
190 |
|
---|
191 | printf ("%d: %2d : %*s : \"%s\"\n", i, cfh.hd.clens[i],
|
---|
192 | cfh.hd.maxcodelen, code, word2str (prev));
|
---|
193 | }
|
---|
194 | Xfree (codes);
|
---|
195 | Xfree (cfh.hd.clens);
|
---|
196 | }
|
---|
197 |
|
---|
198 |
|
---|
199 | void
|
---|
200 | ReadCharHuffman (FILE * f, char *title)
|
---|
201 | {
|
---|
202 | int i;
|
---|
203 | huff_data hd;
|
---|
204 | u_long *codes;
|
---|
205 |
|
---|
206 | if (Read_Huffman_Data (f, &hd, NULL, NULL) == -1)
|
---|
207 | FatalError (1, "Unable to read huffman data");
|
---|
208 |
|
---|
209 | if (!(codes = Generate_Huffman_Codes (&hd, NULL)))
|
---|
210 | FatalError (1, "no memory for huffman codes\n");
|
---|
211 |
|
---|
212 | printf ("#\n# %s\n#\n", title);
|
---|
213 | for (i = 0; i < hd.num_codes; i++)
|
---|
214 | if (hd.clens[i])
|
---|
215 | {
|
---|
216 | int j, k;
|
---|
217 | char code[33];
|
---|
218 | for (k = 0, j = hd.clens[i] - 1; j >= 0; j--, k++)
|
---|
219 | code[k] = '0' + ((codes[i] >> j) & 1);
|
---|
220 | code[k] = '\0';
|
---|
221 | printf ("%2d : %*s : \"%s\"\n", hd.clens[i],
|
---|
222 | hd.maxcodelen, code, char2str (i));
|
---|
223 | }
|
---|
224 | Xfree (codes);
|
---|
225 | Xfree (hd.clens);
|
---|
226 | }
|
---|
227 |
|
---|
228 |
|
---|
229 | void
|
---|
230 | ReadLenHuffman (FILE * f, char *title)
|
---|
231 | {
|
---|
232 | int i;
|
---|
233 | huff_data hd;
|
---|
234 | u_long *codes;
|
---|
235 |
|
---|
236 | if (Read_Huffman_Data (f, &hd, NULL, NULL) == -1)
|
---|
237 | FatalError (1, "Unable to read huffman data");
|
---|
238 |
|
---|
239 | if (!(codes = Generate_Huffman_Codes (&hd, NULL)))
|
---|
240 | FatalError (1, "no memory for huffman codes\n");
|
---|
241 |
|
---|
242 | printf ("#\n# %s\n#\n", title);
|
---|
243 | for (i = 0; i < hd.num_codes; i++)
|
---|
244 | if (hd.clens[i])
|
---|
245 | {
|
---|
246 | int j, k;
|
---|
247 | char code[33];
|
---|
248 | for (k = 0, j = hd.clens[i] - 1; j >= 0; j--, k++)
|
---|
249 | code[k] = '0' + ((codes[i] >> j) & 1);
|
---|
250 | code[k] = '\0';
|
---|
251 | printf ("%2d : %*s : %d\n", hd.clens[i],
|
---|
252 | hd.maxcodelen, code, i);
|
---|
253 | }
|
---|
254 | Xfree (codes);
|
---|
255 | Xfree (hd.clens);
|
---|
256 | }
|
---|
257 |
|
---|
258 |
|
---|
259 |
|
---|
260 |
|
---|
261 |
|
---|
262 | void
|
---|
263 | DumpTextDict (FILE * f)
|
---|
264 | {
|
---|
265 | struct compression_dict_header cdh;
|
---|
266 | int which;
|
---|
267 |
|
---|
268 | if (Read_cdh (f, &cdh, NULL, NULL) == -1)
|
---|
269 | FatalError (1, "Unable to read dictionary header");
|
---|
270 | switch (cdh.dict_type)
|
---|
271 | {
|
---|
272 | case MG_COMPLETE_DICTIONARY:
|
---|
273 | printf ("# COMPLETE DICTIONARY\n");
|
---|
274 | break;
|
---|
275 | case MG_PARTIAL_DICTIONARY:
|
---|
276 | printf ("# PARTIAL DICTIONARY\n");
|
---|
277 | break;
|
---|
278 | case MG_SEED_DICTIONARY:
|
---|
279 | printf ("# SEED DICTIONARY\n");
|
---|
280 | break;
|
---|
281 | }
|
---|
282 | printf ("# num words = %lu\n", cdh.num_words[1]);
|
---|
283 | printf ("# num word chars = %lu\n", cdh.num_word_chars[1]);
|
---|
284 | printf ("# num non-words = %lu\n", cdh.num_words[0]);
|
---|
285 | printf ("# num non-word chars = %lu\n", cdh.num_word_chars[0]);
|
---|
286 | printf ("# lookback = %lu\n", cdh.lookback);
|
---|
287 |
|
---|
288 | for (which = 0; which < 2; which++)
|
---|
289 | switch (cdh.dict_type)
|
---|
290 | {
|
---|
291 | case MG_COMPLETE_DICTIONARY:
|
---|
292 | {
|
---|
293 | ReadInWords (f);
|
---|
294 | }
|
---|
295 | break;
|
---|
296 | case MG_PARTIAL_DICTIONARY:
|
---|
297 | {
|
---|
298 | if (cdh.num_words[which])
|
---|
299 | ReadInWords (f);
|
---|
300 |
|
---|
301 | ReadCharHuffman (f, "Characters");
|
---|
302 | ReadLenHuffman (f, "Lengths");
|
---|
303 | }
|
---|
304 | break;
|
---|
305 | case MG_SEED_DICTIONARY:
|
---|
306 | {
|
---|
307 | if (cdh.num_words[which])
|
---|
308 | ReadInWords (f);
|
---|
309 |
|
---|
310 | ReadCharHuffman (f, "Characters");
|
---|
311 | ReadLenHuffman (f, "Lengths");
|
---|
312 | }
|
---|
313 | break;
|
---|
314 | }
|
---|
315 | }
|
---|
316 |
|
---|
317 |
|
---|
318 |
|
---|
319 |
|
---|
320 | void
|
---|
321 | DumpStatsDict (FILE * f)
|
---|
322 | {
|
---|
323 | int i;
|
---|
324 | compression_stats_header csh;
|
---|
325 |
|
---|
326 | fread (&csh, sizeof (csh), 1, f);
|
---|
327 |
|
---|
328 | for (i = 0; i < 2; i++)
|
---|
329 | {
|
---|
330 | int j;
|
---|
331 | frags_stats_header fsh;
|
---|
332 |
|
---|
333 | fread (&fsh, sizeof (fsh), 1, f);
|
---|
334 |
|
---|
335 | /* [RPAP - Jan 97: Endian Ordering] */
|
---|
336 | NTOHUL(fsh.num_frags);
|
---|
337 | NTOHUL(fsh.mem_for_frags);
|
---|
338 |
|
---|
339 | if (!quick)
|
---|
340 | printf ("#\n# num %9s = %lu\n#\n", i ? "words" : "non-words",
|
---|
341 | fsh.num_frags);
|
---|
342 |
|
---|
343 | for (j = 0; j < fsh.num_frags; j++)
|
---|
344 | {
|
---|
345 | u_char Word[16];
|
---|
346 | u_long freq, occur_num;
|
---|
347 |
|
---|
348 | fread (&freq, sizeof (freq), 1, f);
|
---|
349 | fread (&occur_num, sizeof (occur_num), 1, f);
|
---|
350 |
|
---|
351 | /* [RPAP - Jan 97: Endian Ordering] */
|
---|
352 | NTOHUL(freq);
|
---|
353 | NTOHUL(occur_num);
|
---|
354 |
|
---|
355 | Word[0] = fgetc (f);
|
---|
356 | fread (Word + 1, Word[0], 1, f);
|
---|
357 | printf ("%d: %7ld : %7ld : \"%s\"\n", j, freq,
|
---|
358 | occur_num, word2str (Word));
|
---|
359 | }
|
---|
360 | }
|
---|
361 | }
|
---|
362 |
|
---|
363 |
|
---|
364 | int main (int argc, char **argv)
|
---|
365 | {
|
---|
366 | FILE *fp;
|
---|
367 | unsigned long magic = 0;
|
---|
368 |
|
---|
369 | if (argc < 2)
|
---|
370 | FatalError (1, "A file name must be specified");
|
---|
371 | dictname = argv[1];
|
---|
372 | if (strcmp (dictname, "-q") == 0)
|
---|
373 | {
|
---|
374 | quick = 1;
|
---|
375 | if (argc < 3)
|
---|
376 | FatalError (1, "A file name must be specified");
|
---|
377 | dictname = argv[2];
|
---|
378 | }
|
---|
379 | if (!(fp = fopen (dictname, "rb"))) /* [RPAP - Feb 97: WIN32 Port] */
|
---|
380 | FatalError (1, "Unable to open \"%s\"", dictname);
|
---|
381 |
|
---|
382 | fread (&magic, sizeof (magic), 1, fp);
|
---|
383 |
|
---|
384 | NTOHUL(magic); /* [RPAP - Jan 97: Endian Ordering] */
|
---|
385 |
|
---|
386 | switch (magic)
|
---|
387 | {
|
---|
388 | case MAGIC_STEM_BUILD:
|
---|
389 | if (!quick)
|
---|
390 | printf ("# Contents of STEM file \"%s\"\n#\n", dictname);
|
---|
391 | DumpStemDict (fp);
|
---|
392 | break;
|
---|
393 | case MAGIC_DICT:
|
---|
394 | if (!quick)
|
---|
395 | printf ("# Contents of DICT file \"%s\"\n#\n", dictname);
|
---|
396 | DumpTextDict (fp);
|
---|
397 | break;
|
---|
398 | case MAGIC_STATS_DICT:
|
---|
399 | if (!quick)
|
---|
400 | printf ("# Contents of STATS file \"%s\"\n#\n", dictname);
|
---|
401 | DumpStatsDict (fp);
|
---|
402 | break;
|
---|
403 | default:
|
---|
404 | FatalError (1, "Bad magic number. \"%s\" cannot be dumped", dictname);
|
---|
405 | }
|
---|
406 | fclose (fp);
|
---|
407 | return 0;
|
---|
408 | }
|
---|