1 | /**************************************************************************
|
---|
2 | *
|
---|
3 | * mg_files.h -- Routines for handling files for the auxillary programs
|
---|
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 | **************************************************************************/
|
---|
21 |
|
---|
22 | #ifndef MG_FILES_H
|
---|
23 | #define MG_FILES_H
|
---|
24 |
|
---|
25 | #include "sysfuncs.h"
|
---|
26 |
|
---|
27 | /* Magic numbers for the different types of files */
|
---|
28 |
|
---|
29 | #define GEN_MAGIC(a,b,c,d) ((unsigned long)(((a)<<24) + ((b)<<16) + \
|
---|
30 | ((c)<<8) + (d)))
|
---|
31 |
|
---|
32 | #define MAGIC_XXXX GEN_MAGIC('M','G', 0 , 0)
|
---|
33 | #define MAGIC_STATS_DICT GEN_MAGIC('M','G','S','D')
|
---|
34 | #define MAGIC_AUX_DICT GEN_MAGIC('M','G','A','D')
|
---|
35 | #define MAGIC_FAST_DICT GEN_MAGIC('M','G','F','D')
|
---|
36 | #define MAGIC_DICT GEN_MAGIC('M','G','D', 0 )
|
---|
37 | #define MAGIC_STEM_BUILD GEN_MAGIC('M','G','S', 0 )
|
---|
38 | #define MAGIC_HASH GEN_MAGIC('M','G','H', 0 )
|
---|
39 | #define MAGIC_STEM GEN_MAGIC('M','G','s', 0 )
|
---|
40 | #define MAGIC_CHUNK GEN_MAGIC('M','G','C', 0 )
|
---|
41 | #define MAGIC_CHUNK_TRANS GEN_MAGIC('M','G','c', 0 )
|
---|
42 | #define MAGIC_TEXT GEN_MAGIC('M','G','T', 0 )
|
---|
43 | #define MAGIC_TEXI GEN_MAGIC('M','G','t', 0 )
|
---|
44 | #define MAGIC_TEXT_LEVELS GEN_MAGIC('M','G','t','L')
|
---|
45 | #define MAGIC_TEXI_WGT GEN_MAGIC('M','G','t','W')
|
---|
46 | #define MAGIC_INVF GEN_MAGIC('M','G','I', 0 )
|
---|
47 | #define MAGIC_INVF_LEVELS GEN_MAGIC('M','G','I','L')
|
---|
48 | #define MAGIC_INVI GEN_MAGIC('M','G','i', 0 )
|
---|
49 | #define MAGIC_WGHT GEN_MAGIC('M','G','W', 0 )
|
---|
50 | #define MAGIC_WGHT_APPROX GEN_MAGIC('M','G','w', 0 )
|
---|
51 | #define MAGIC_PARAGRAPH GEN_MAGIC('M','G','P', 0 )
|
---|
52 | /* [RPAP - Jan 97: Stem Index Change] */
|
---|
53 | #define MAGIC_STEM_1 GEN_MAGIC('M','G','s','1')
|
---|
54 | #define MAGIC_STEM_2 GEN_MAGIC('M','G','s','2')
|
---|
55 | #define MAGIC_STEM_3 GEN_MAGIC('M','G','s','3')
|
---|
56 |
|
---|
57 | #define IS_MAGIC(a) ((((u_long)(a)) & 0xffff0000) == MAGIC_XXXX)
|
---|
58 |
|
---|
59 |
|
---|
60 | /* err_mode values for open_file and create_file */
|
---|
61 | #define MG_ABORT 0
|
---|
62 | #define MG_MESSAGE 1
|
---|
63 | #define MG_CONTINUE 2
|
---|
64 |
|
---|
65 |
|
---|
66 |
|
---|
67 |
|
---|
68 |
|
---|
69 | /* File suffixes */
|
---|
70 |
|
---|
71 |
|
---|
72 | /* The compression dictionary built by txt.pass1 */
|
---|
73 | #ifdef SHORT_SUFFIX
|
---|
74 | # define TEXT_STATS_DICT_SUFFIX ".tsd"
|
---|
75 | #else
|
---|
76 | # define TEXT_STATS_DICT_SUFFIX ".text.stats"
|
---|
77 | #endif
|
---|
78 |
|
---|
79 | /* The compression dictionary built by text.pass1 and comp_dict.process */
|
---|
80 | #ifdef SHORT_SUFFIX
|
---|
81 | # define TEXT_DICT_SUFFIX ".td"
|
---|
82 | #else
|
---|
83 | # define TEXT_DICT_SUFFIX ".text.dict"
|
---|
84 | #endif
|
---|
85 |
|
---|
86 | /* The compression dictionary built by mg_make_fast_dict */
|
---|
87 | #ifdef SHORT_SUFFIX
|
---|
88 | # define TEXT_DICT_FAST_SUFFIX ".tdf"
|
---|
89 | #else
|
---|
90 | # define TEXT_DICT_FAST_SUFFIX ".text.dict.fast"
|
---|
91 | #endif
|
---|
92 |
|
---|
93 | /* The auxilary dictionary built by text.pass2 */
|
---|
94 | #ifdef SHORT_SUFFIX
|
---|
95 | # define TEXT_DICT_AUX_SUFFIX ".tda"
|
---|
96 | #else
|
---|
97 | # define TEXT_DICT_AUX_SUFFIX ".text.dict.aux"
|
---|
98 | #endif
|
---|
99 |
|
---|
100 | /* The compressed text build by text.pass2 */
|
---|
101 | #ifdef SHORT_SUFFIX
|
---|
102 | # define TEXT_SUFFIX ".t"
|
---|
103 | #else
|
---|
104 | # define TEXT_SUFFIX ".text"
|
---|
105 | #endif
|
---|
106 |
|
---|
107 | /* The combined compressed text index and document weight file */
|
---|
108 | #ifdef SHORT_SUFFIX
|
---|
109 | # define TEXT_IDX_WGT_SUFFIX ".tiw"
|
---|
110 | #else
|
---|
111 | # define TEXT_IDX_WGT_SUFFIX ".text.idx.wgt"
|
---|
112 | #endif
|
---|
113 |
|
---|
114 | /* The compressed text index file */
|
---|
115 | #ifdef SHORT_SUFFIX
|
---|
116 | # define TEXT_IDX_SUFFIX ".ti"
|
---|
117 | #else
|
---|
118 | # define TEXT_IDX_SUFFIX ".text.idx"
|
---|
119 | #endif
|
---|
120 |
|
---|
121 | /* The document levels in the text */
|
---|
122 | #ifdef SHORT_SUFFIX
|
---|
123 | # define TEXT_LEVEL_SUFFIX ".tl"
|
---|
124 | #else
|
---|
125 | # define TEXT_LEVEL_SUFFIX ".text.level"
|
---|
126 | #endif
|
---|
127 |
|
---|
128 | /* The dictionary of stemmed words build by invf.pass1 and ivf.pass1 */
|
---|
129 | #ifdef SHORT_SUFFIX
|
---|
130 | # define INVF_DICT_SUFFIX ".id"
|
---|
131 | #else
|
---|
132 | # define INVF_DICT_SUFFIX ".invf.dict"
|
---|
133 | #endif
|
---|
134 |
|
---|
135 | /* The dictionary of stemmed words build by stem.process */
|
---|
136 | #ifdef SHORT_SUFFIX
|
---|
137 | # define INVF_DICT_BLOCKED_SUFFIX ".idb"
|
---|
138 | #else
|
---|
139 | # define INVF_DICT_BLOCKED_SUFFIX ".invf.dict.blocked"
|
---|
140 | #endif
|
---|
141 |
|
---|
142 | /* The exact document weights file build by make.weights, invf.pass2,
|
---|
143 | or ivf.pass2 */
|
---|
144 | #ifdef SHORT_SUFFIX
|
---|
145 | # define WEIGHTS_SUFFIX ".w"
|
---|
146 | #else
|
---|
147 | # define WEIGHTS_SUFFIX ".weight"
|
---|
148 | #endif
|
---|
149 |
|
---|
150 | /* The approximate weights file built by make.weights */
|
---|
151 | #ifdef SHORT_SUFFIX
|
---|
152 | # define APPROX_WEIGHTS_SUFFIX ".wa"
|
---|
153 | #else
|
---|
154 | # define APPROX_WEIGHTS_SUFFIX ".weight.approx"
|
---|
155 | #endif
|
---|
156 |
|
---|
157 | /* The inverted file build by invf.pass2 or ivf.pass2 */
|
---|
158 | #ifdef SHORT_SUFFIX
|
---|
159 | # define INVF_SUFFIX ".i"
|
---|
160 | #else
|
---|
161 | # define INVF_SUFFIX ".invf"
|
---|
162 | #endif
|
---|
163 |
|
---|
164 | /* The level information for the inverted text */
|
---|
165 | #ifdef SHORT_SUFFIX
|
---|
166 | # define INVF_LEVEL_SUFFIX ".il"
|
---|
167 | #else
|
---|
168 | # define INVF_LEVEL_SUFFIX ".invf.level"
|
---|
169 | #endif
|
---|
170 |
|
---|
171 | /* The inverted file index build by invf.pass2 or ivf.pass2 */
|
---|
172 | #ifdef SHORT_SUFFIX
|
---|
173 | # define INVF_IDX_SUFFIX ".ii"
|
---|
174 | #else
|
---|
175 | # define INVF_IDX_SUFFIX ".invf.idx"
|
---|
176 | #endif
|
---|
177 |
|
---|
178 | /* The inverted file chunk descriptor built by ivf.pass1 */
|
---|
179 | #ifdef SHORT_SUFFIX
|
---|
180 | # define INVF_CHUNK_SUFFIX ".ic"
|
---|
181 | #else
|
---|
182 | # define INVF_CHUNK_SUFFIX ".invf.chunk"
|
---|
183 | #endif
|
---|
184 |
|
---|
185 | /* The word index translation file built by ivf.pass1 */
|
---|
186 | #ifdef SHORT_SUFFIX
|
---|
187 | # define INVF_CHUNK_TRANS_SUFFIX ".ict"
|
---|
188 | #else
|
---|
189 | # define INVF_CHUNK_TRANS_SUFFIX ".invf.chunk.trans"
|
---|
190 | #endif
|
---|
191 |
|
---|
192 | /* The hashed stemmed dictionary built by make.perf_hash */
|
---|
193 | #ifdef SHORT_SUFFIX
|
---|
194 | # define INVF_DICT_HASH_SUFFIX ".idh"
|
---|
195 | #else
|
---|
196 | # define INVF_DICT_HASH_SUFFIX ".invf.dict.hash"
|
---|
197 | #endif
|
---|
198 |
|
---|
199 | /* The paragraph descriptior file built by invf.pass1 or ivf.pass1 */
|
---|
200 | #ifdef SHORT_SUFFIX
|
---|
201 | # define INVF_PARAGRAPH_SUFFIX ".ip"
|
---|
202 | #else
|
---|
203 | # define INVF_PARAGRAPH_SUFFIX ".invf.paragraph"
|
---|
204 | #endif
|
---|
205 |
|
---|
206 | /* The trace file build by mg.builder. */
|
---|
207 | #ifdef SHORT_SUFFIX
|
---|
208 | # define TRACE_SUFFIX ".trc"
|
---|
209 | #else
|
---|
210 | # define TRACE_SUFFIX ".trace"
|
---|
211 | #endif
|
---|
212 |
|
---|
213 | /* The compression stats file build by mg.builder. */
|
---|
214 | #ifdef SHORT_SUFFIX
|
---|
215 | # define COMPRESSION_STATS_SUFFIX ".cs"
|
---|
216 | #else
|
---|
217 | # define COMPRESSION_STATS_SUFFIX ".compression.stats"
|
---|
218 | #endif
|
---|
219 |
|
---|
220 | /* [RPAP - Jan 97: Stem Index Change] */
|
---|
221 | /* The casefolded index into the stemmed dictionary */
|
---|
222 | #ifdef SHORT_SUFFIX
|
---|
223 | # define INVF_DICT_BLOCKED_1_SUFFIX ".ib1"
|
---|
224 | #else
|
---|
225 | # define INVF_DICT_BLOCKED_1_SUFFIX ".invf.dict.blocked.1"
|
---|
226 | #endif
|
---|
227 |
|
---|
228 | /* [RPAP - Jan 97: Stem Index Change] */
|
---|
229 | /* The stemmed index into the stemmed dictionary */
|
---|
230 | #ifdef SHORT_SUFFIX
|
---|
231 | # define INVF_DICT_BLOCKED_2_SUFFIX ".ib2"
|
---|
232 | #else
|
---|
233 | # define INVF_DICT_BLOCKED_2_SUFFIX ".invf.dict.blocked.2"
|
---|
234 | #endif
|
---|
235 |
|
---|
236 | /* [RPAP - Jan 97: Stem Index Change] */
|
---|
237 | /* The casefolded and stemmed index into the stemmed dictionary */
|
---|
238 | #ifdef SHORT_SUFFIX
|
---|
239 | # define INVF_DICT_BLOCKED_3_SUFFIX ".ib3"
|
---|
240 | #else
|
---|
241 | # define INVF_DICT_BLOCKED_3_SUFFIX ".invf.dict.blocked.3"
|
---|
242 | #endif
|
---|
243 |
|
---|
244 | /* [RPAP - Feb 97: WIN32 Port] */
|
---|
245 | #ifdef __WIN32__
|
---|
246 | #define FILE_NAME_FORMAT "%s%s%s"
|
---|
247 | #else
|
---|
248 | #define FILE_NAME_FORMAT "%s/%s%s"
|
---|
249 | #endif
|
---|
250 |
|
---|
251 |
|
---|
252 | /* This sets the base path for all file operations */
|
---|
253 | void set_basepath (const char *bp);
|
---|
254 |
|
---|
255 |
|
---|
256 | /* return the currently defined basepath */
|
---|
257 | char *get_basepath (void);
|
---|
258 |
|
---|
259 |
|
---|
260 |
|
---|
261 |
|
---|
262 | /* This generates the name of a file. It places the name in the buffer
|
---|
263 | specified or if that is NULL it uses a static buffer. */
|
---|
264 | char *make_name (const char *name, const char *suffix, char *buffer);
|
---|
265 |
|
---|
266 |
|
---|
267 |
|
---|
268 |
|
---|
269 |
|
---|
270 |
|
---|
271 |
|
---|
272 | /* This will open the specified file and check its magic number.
|
---|
273 | Mode may take on the following values
|
---|
274 | MG_ABORT : causes an error message to be generated and the
|
---|
275 | program aborted if there is an error.
|
---|
276 | MG_MESSAGE : causes a message to be generated and a NULL value to
|
---|
277 | be returned if there is an error.
|
---|
278 | MG_CONTINUE : causes a NULL value to be returned if there is an error.
|
---|
279 |
|
---|
280 | On success if returns the FILE *. On failure it will return a NULL value
|
---|
281 | and possibly generate an error message, or it will exit the program with
|
---|
282 | an error message. */
|
---|
283 | FILE *open_named_file (const char *name, const char *mode,
|
---|
284 | u_long magic_num, int err_mode);
|
---|
285 |
|
---|
286 |
|
---|
287 |
|
---|
288 |
|
---|
289 | /* This will open the specified file and check its magic number.
|
---|
290 |
|
---|
291 | err_mode may take on the following values
|
---|
292 | MG_ABORT : causes an error message to be generated and the
|
---|
293 | program aborted if there is an error.
|
---|
294 | MG_MESSAGE : causes a message to be generated and a NULL value to
|
---|
295 | be returned if there is an error.
|
---|
296 | MG_CONTINUE : causes a NULL value to be returned if there is an error.
|
---|
297 |
|
---|
298 | On success if returns the FILE *. On failure it will return a NULL value
|
---|
299 | and possibly generate an error message, or it will exit the program with
|
---|
300 | an error message. */
|
---|
301 | FILE *open_file (const char *name, const char *suffix, const char *mode,
|
---|
302 | u_long magic_num, int err_mode);
|
---|
303 |
|
---|
304 |
|
---|
305 |
|
---|
306 |
|
---|
307 |
|
---|
308 | /* This will create the specified file and set its magic number.
|
---|
309 |
|
---|
310 | Mode may take on the following values
|
---|
311 | MG_ABORT : causes an error message to be generated and the
|
---|
312 | program aborted if there is an error.
|
---|
313 | MG_MESSAGE : causes a message to be generated and a NULL value to
|
---|
314 | be returned if there is an error.
|
---|
315 | MG_CONTINUE : causes a NULL value to be returned if there is an error.
|
---|
316 |
|
---|
317 | On success if returns the FILE *. On failure it will return a NULL value
|
---|
318 | and possibly generate an error message, or it will exit the program with
|
---|
319 | an error message. */
|
---|
320 | FILE *create_named_file (const char *name, const char *mode,
|
---|
321 | u_long magic_num, int err_mode);
|
---|
322 |
|
---|
323 |
|
---|
324 |
|
---|
325 | /* This will create the specified file and set its magic number.
|
---|
326 |
|
---|
327 | err_mode may take on the following values
|
---|
328 | MG_ABORT : causes an error message to be generated and the
|
---|
329 | program aborted if there is an error.
|
---|
330 | MG_MESSAGE : causes a message to be generated and a NULL value to
|
---|
331 | be returned if there is an error.
|
---|
332 | MG_CONTINUE : causes a NULL value to be returned if there is an error.
|
---|
333 |
|
---|
334 | On success if returns the FILE *. On failure it will return a NULL value
|
---|
335 | and possibly generate an error message, or it will exit the program with
|
---|
336 | an error message. */
|
---|
337 | FILE *create_file (const char *name, const char *suffix, const char *mode,
|
---|
338 | u_long magic_num, int err_mode);
|
---|
339 |
|
---|
340 |
|
---|
341 |
|
---|
342 |
|
---|
343 | #endif
|
---|