1/*
2 * SPDX-License-Identifier: BSD-3-Clause
3 *
4 * Copyright (c) 1995-2022 Wolfram Schneider <wosch@FreeBSD.org>
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/*
37 * PURPOSE:	sorted list compressor (works with a modified 'find'
38 *		to encode/decode a filename database)
39 *
40 * USAGE:	bigram < list > bigrams
41 *		process bigrams (see updatedb) > common_bigrams
42 *		code common_bigrams < list > squozen_list
43 *
44 * METHOD:	Uses 'front compression' (see ";login:", Volume 8, Number 1
45 *		February/March 1983, p. 8).  Output format is, per line, an
46 *		offset differential count byte followed by a partially bigram-
47 *		encoded ascii residue.  A bigram is a two-character sequence,
48 *		the first 128 most common of which are encoded in one byte.
49 *
50 * EXAMPLE:	For simple front compression with no bigram encoding,
51 *		if the input is...		then the output is...
52 *
53 *		/usr/src			 0 /usr/src
54 *		/usr/src/cmd/aardvark.c		 8 /cmd/aardvark.c
55 *		/usr/src/cmd/armadillo.c	14 armadillo.c
56 *		/usr/tmp/zoo			 5 tmp/zoo
57 *
58 *	The codes are:
59 *
60 *	0-28	likeliest differential counts + offset to make nonnegative
61 *	30	switch code for out-of-range count to follow in next word
62 *      31      an 8 bit char followed
63 *	128-255 bigram codes (128 most common, as determined by 'updatedb')
64 *	32-127  single character (printable) ascii residue (ie, literal)
65 *
66 * The locate database store any character except newline ('\n')
67 * and NUL ('\0'). The 8-bit character support don't wast extra
68 * space until you have characters in file names less than 32
69 * or greather than 127.
70 *
71 *
72 * SEE ALSO:	updatedb.sh, ../bigram/locate.bigram.c
73 *
74 * AUTHOR:	James A. Woods, Informatics General Corp.,
75 *		NASA Ames Research Center, 10/82
76 *              8-bit file names characters:
77 *              	Wolfram Schneider, Berlin September 1996
78 */
79
80#include <sys/param.h>
81#include <err.h>
82#include <errno.h>
83#include <stdlib.h>
84#include <string.h>
85#include <stdio.h>
86#include <unistd.h>
87#include "locate.h"
88
89#define	BGBUFSIZE	(NBG * 2)	/* size of bigram buffer */
90
91u_char buf1[LOCATE_PATH_MAX] = " ";
92u_char buf2[LOCATE_PATH_MAX];
93u_char bigrams[BGBUFSIZE + 1] = { 0 };
94
95/* use a lookup array instead a function, 3x faster than linear search */
96int big [UCHAR_MAX + 1][UCHAR_MAX + 1];
97#define BGINDEX(x) (big[(u_char)*x][(u_char)*(x + 1)])
98
99void   usage(void);
100
101int
102main(int argc, char *argv[])
103{
104	u_char *cp, *oldpath, *path;
105	int ch, code, count, diffcount, oldcount;
106	u_int i, j;
107	FILE *fp;
108
109	while ((ch = getopt(argc, argv, "")) != -1)
110		switch(ch) {
111		default:
112			usage();
113		}
114	argc -= optind;
115	argv += optind;
116
117	if (argc != 1)
118		usage();
119
120	if ((fp = fopen(argv[0], "r")) == NULL)
121		err(1, "%s", argv[0]);
122
123	/* First copy bigram array to stdout. */
124	if (fgets(bigrams, BGBUFSIZE + 1, fp) == NULL) {
125		if (!feof(fp) || ferror(fp))
126			err(1, "get bigram array");
127	}
128
129	if (fwrite(bigrams, 1, BGBUFSIZE, stdout) != BGBUFSIZE)
130		err(1, "stdout");
131	(void)fclose(fp);
132
133	/* init lookup table */
134	for (i = 0; i < UCHAR_MAX + 1; i++)
135	    	for (j = 0; j < UCHAR_MAX + 1; j++)
136			big[i][j] = -1;
137
138	for (cp = bigrams, i = 0; *cp != '\0'; i += 2, cp += 2)
139	        big[(u_char)*cp][(u_char)*(cp + 1)] = i;
140
141	oldpath = buf1;
142	path = buf2;
143	oldcount = 0;
144
145	while (fgets(path, sizeof(buf2), stdin) != NULL) {
146
147		/* skip empty lines */
148		if (*path == '\n')
149			continue;
150
151		/* remove newline */
152		for (cp = path; *cp != '\0'; cp++) {
153			/* chop newline */
154			if (*cp == '\n')
155				*cp = '\0';
156		}
157
158		/* Skip longest common prefix. */
159		for (cp = path; *cp == *oldpath; cp++, oldpath++)
160			if (*cp == '\0')
161				break;
162
163		count = cp - path;
164		diffcount = count - oldcount + OFFSET;
165		oldcount = count;
166		if (diffcount < 0 || diffcount > 2 * OFFSET) {
167			if (putchar(SWITCH) == EOF ||
168			    putw(diffcount, stdout) == EOF)
169				err(1, "stdout");
170		} else
171			if (putchar(diffcount) == EOF)
172				err(1, "stdout");
173
174		while (*cp != '\0') {
175			/* print *two* characters */
176
177			if ((code = BGINDEX(cp)) != -1) {
178				/*
179				 * print *one* as bigram
180				 * Found, so mark byte with
181				 *  parity bit.
182				 */
183				if (putchar((code / 2) | PARITY) == EOF)
184					err(1, "stdout");
185				cp += 2;
186			}
187
188			else {
189				for (i = 0; i < 2; i++) {
190					if (*cp == '\0')
191						break;
192
193					/* print umlauts in file names */
194					if (*cp < ASCII_MIN ||
195					    *cp > ASCII_MAX) {
196						if (putchar(UMLAUT) == EOF ||
197						    putchar(*cp++) == EOF)
198							err(1, "stdout");
199					}
200
201					else {
202						/* normal character */
203						if(putchar(*cp++) == EOF)
204							err(1, "stdout");
205					}
206				}
207
208			}
209		}
210
211		if (path == buf1) {		/* swap pointers */
212			path = buf2;
213			oldpath = buf1;
214		} else {
215			path = buf1;
216			oldpath = buf2;
217		}
218	}
219
220	/* Non-zero status if there were errors */
221	if (fflush(stdout) != 0 || ferror(stdout))
222		errx(1, "stdout");
223
224	exit(0);
225}
226
227void
228usage(void)
229{
230	(void)fprintf(stderr,
231	    "usage: locate.code common_bigrams < list > squozen_list\n");
232	exit(1);
233}
234