1 /*
2 * SPDX-License-Identifier: BSD-3-Clause
3 *
4 * Copyright (c) 1995-2022 Wolfram Schneider <[email protected]>
5 * Copyright (c) 1989, 1993
6 * The Regents of the University of California. All rights reserved.
7 *
8 * This code is derived from software contributed to Berkeley by
9 * James A. Woods.
10 *
11 * Redistribution and use in source and binary forms, with or without
12 * modification, are permitted provided that the following conditions
13 * are met:
14 * 1. Redistributions of source code must retain the above copyright
15 * notice, this list of conditions and the following disclaimer.
16 * 2. Redistributions in binary form must reproduce the above copyright
17 * notice, this list of conditions and the following disclaimer in the
18 * documentation and/or other materials provided with the distribution.
19 * 3. Neither the name of the University nor the names of its contributors
20 * may be used to endorse or promote products derived from this software
21 * without specific prior written permission.
22 *
23 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
24 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
26 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
27 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
28 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
29 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
30 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
31 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
32 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
33 * SUCH DAMAGE.
34 */
35
36 #if 0
37 #ifndef lint
38 static char copyright[] =
39 "@(#) Copyright (c) 1989, 1993\n\
40 The Regents of the University of California. All rights reserved.\n";
41 #endif /* not lint */
42
43 #ifndef lint
44 static char sccsid[] = "@(#)locate.code.c 8.1 (Berkeley) 6/6/93";
45 #endif /* not lint */
46 #endif
47
48 /*
49 * PURPOSE: sorted list compressor (works with a modified 'find'
50 * to encode/decode a filename database)
51 *
52 * USAGE: bigram < list > bigrams
53 * process bigrams (see updatedb) > common_bigrams
54 * code common_bigrams < list > squozen_list
55 *
56 * METHOD: Uses 'front compression' (see ";login:", Volume 8, Number 1
57 * February/March 1983, p. 8). Output format is, per line, an
58 * offset differential count byte followed by a partially bigram-
59 * encoded ascii residue. A bigram is a two-character sequence,
60 * the first 128 most common of which are encoded in one byte.
61 *
62 * EXAMPLE: For simple front compression with no bigram encoding,
63 * if the input is... then the output is...
64 *
65 * /usr/src 0 /usr/src
66 * /usr/src/cmd/aardvark.c 8 /cmd/aardvark.c
67 * /usr/src/cmd/armadillo.c 14 armadillo.c
68 * /usr/tmp/zoo 5 tmp/zoo
69 *
70 * The codes are:
71 *
72 * 0-28 likeliest differential counts + offset to make nonnegative
73 * 30 switch code for out-of-range count to follow in next word
74 * 31 an 8 bit char followed
75 * 128-255 bigram codes (128 most common, as determined by 'updatedb')
76 * 32-127 single character (printable) ascii residue (ie, literal)
77 *
78 * The locate database store any character except newline ('\n')
79 * and NUL ('\0'). The 8-bit character support don't wast extra
80 * space until you have characters in file names less than 32
81 * or greather than 127.
82 *
83 *
84 * SEE ALSO: updatedb.sh, ../bigram/locate.bigram.c
85 *
86 * AUTHOR: James A. Woods, Informatics General Corp.,
87 * NASA Ames Research Center, 10/82
88 * 8-bit file names characters:
89 * Wolfram Schneider, Berlin September 1996
90 */
91
92 #include <sys/param.h>
93 #include <err.h>
94 #include <errno.h>
95 #include <stdlib.h>
96 #include <string.h>
97 #include <stdio.h>
98 #include <unistd.h>
99 #include "locate.h"
100
101 #define BGBUFSIZE (NBG * 2) /* size of bigram buffer */
102
103 u_char buf1[LOCATE_PATH_MAX] = " ";
104 u_char buf2[LOCATE_PATH_MAX];
105 u_char bigrams[BGBUFSIZE + 1] = { 0 };
106
107 /* use a lookup array instead a function, 3x faster than linear search */
108 int big [UCHAR_MAX + 1][UCHAR_MAX + 1];
109 #define BGINDEX(x) (big[(u_char)*x][(u_char)*(x + 1)])
110
111 void usage(void);
112
113 int
main(int argc,char * argv[])114 main(int argc, char *argv[])
115 {
116 u_char *cp, *oldpath, *path;
117 int ch, code, count, diffcount, oldcount;
118 u_int i, j;
119 FILE *fp;
120
121 while ((ch = getopt(argc, argv, "")) != -1)
122 switch(ch) {
123 default:
124 usage();
125 }
126 argc -= optind;
127 argv += optind;
128
129 if (argc != 1)
130 usage();
131
132 if ((fp = fopen(argv[0], "r")) == NULL)
133 err(1, "%s", argv[0]);
134
135 /* First copy bigram array to stdout. */
136 if (fgets(bigrams, BGBUFSIZE + 1, fp) == NULL) {
137 if (!feof(fp) || ferror(fp))
138 err(1, "get bigram array");
139 }
140
141 if (fwrite(bigrams, 1, BGBUFSIZE, stdout) != BGBUFSIZE)
142 err(1, "stdout");
143 (void)fclose(fp);
144
145 /* init lookup table */
146 for (i = 0; i < UCHAR_MAX + 1; i++)
147 for (j = 0; j < UCHAR_MAX + 1; j++)
148 big[i][j] = -1;
149
150 for (cp = bigrams, i = 0; *cp != '\0'; i += 2, cp += 2)
151 big[(u_char)*cp][(u_char)*(cp + 1)] = i;
152
153 oldpath = buf1;
154 path = buf2;
155 oldcount = 0;
156
157 while (fgets(path, sizeof(buf2), stdin) != NULL) {
158
159 /* skip empty lines */
160 if (*path == '\n')
161 continue;
162
163 /* remove newline */
164 for (cp = path; *cp != '\0'; cp++) {
165 /* chop newline */
166 if (*cp == '\n')
167 *cp = '\0';
168 }
169
170 /* Skip longest common prefix. */
171 for (cp = path; *cp == *oldpath; cp++, oldpath++)
172 if (*cp == '\0')
173 break;
174
175 count = cp - path;
176 diffcount = count - oldcount + OFFSET;
177 oldcount = count;
178 if (diffcount < 0 || diffcount > 2 * OFFSET) {
179 if (putchar(SWITCH) == EOF ||
180 putw(diffcount, stdout) == EOF)
181 err(1, "stdout");
182 } else
183 if (putchar(diffcount) == EOF)
184 err(1, "stdout");
185
186 while (*cp != '\0') {
187 /* print *two* characters */
188
189 if ((code = BGINDEX(cp)) != -1) {
190 /*
191 * print *one* as bigram
192 * Found, so mark byte with
193 * parity bit.
194 */
195 if (putchar((code / 2) | PARITY) == EOF)
196 err(1, "stdout");
197 cp += 2;
198 }
199
200 else {
201 for (i = 0; i < 2; i++) {
202 if (*cp == '\0')
203 break;
204
205 /* print umlauts in file names */
206 if (*cp < ASCII_MIN ||
207 *cp > ASCII_MAX) {
208 if (putchar(UMLAUT) == EOF ||
209 putchar(*cp++) == EOF)
210 err(1, "stdout");
211 }
212
213 else {
214 /* normal character */
215 if(putchar(*cp++) == EOF)
216 err(1, "stdout");
217 }
218 }
219
220 }
221 }
222
223 if (path == buf1) { /* swap pointers */
224 path = buf2;
225 oldpath = buf1;
226 } else {
227 path = buf1;
228 oldpath = buf2;
229 }
230 }
231
232 /* Non-zero status if there were errors */
233 if (fflush(stdout) != 0 || ferror(stdout))
234 errx(1, "stdout");
235
236 exit(0);
237 }
238
239 void
usage(void)240 usage(void)
241 {
242 (void)fprintf(stderr,
243 "usage: locate.code common_bigrams < list > squozen_list\n");
244 exit(1);
245 }
246