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