locate/locate/util.c

/* $MidnightBSD$ */
/*
 * Copyright (c) 1995 Wolfram Schneider <wosch@FreeBSD.org>. Berlin.
 * Copyright (c) 1989, 1993
 *      The Regents of the University of California.  All rights reserved.
 *
 * This code is derived from software contributed to Berkeley by
 * James A. Woods.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *      This product includes software developed by the University of
 *      California, Berkeley and its contributors.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 * $FreeBSD: stable/10/usr.bin/locate/locate/util.c 275034 2014-11-25 12:45:31Z dim $
 */


#include <stdlib.h>
#include <string.h>
#include <err.h>
#include <sys/param.h>
#include <arpa/inet.h>
#include <stdio.h>

#include "locate.h"

char    **colon(char **, char*, char*);
char    *patprep(char *);
void print_matches(u_int);
u_char  *tolower_word(u_char *);
int     getwm(caddr_t);
int     getwf(FILE *);
int     check_bigram_char(int);

/* 
 * Validate bigram chars. If the test failed the database is corrupt 
 * or the database is obviously not a locate database.
 */
int
check_bigram_char(ch)
        int ch;
{
        /* legal bigram: 0, ASCII_MIN ... ASCII_MAX */
        if (ch == 0 ||
            (ch >= ASCII_MIN && ch <= ASCII_MAX))
                return(ch);

        errx(1,
                "locate database header corrupt, bigram char outside 0, %d-%d: %d",  
                ASCII_MIN, ASCII_MAX, ch);
        exit(1);
}

/* split a colon separated string into a char vector
 *
 * "bla:foo" -> {"foo", "bla"}
 * "bla:"    -> {"foo", dot}
 * "bla"     -> {"bla"}
 * ""        -> do nothing
 *
 */
char **
colon(dbv, path, dot)
        char **dbv;
        char *path;
        char *dot; /* default for single ':' */
{
        int vlen, slen;
        char *c, *ch, *p;
        char **pv;

        if (dbv == NULL) {
                if ((dbv = malloc(sizeof(char **))) == NULL)
                        err(1, "malloc");
                *dbv = NULL;
        }

        /* empty string */
        if (*path == '\0') {
                warnx("empty database name, ignored");
                return(dbv);
        }

        /* length of string vector */
        for(vlen = 0, pv = dbv; *pv != NULL; pv++, vlen++);

        for (ch = c = path; ; ch++) {
                if (*ch == ':' ||
                    (!*ch && !(*(ch - 1) == ':' && ch == 1+ path))) {
                        /* single colon -> dot */
                        if (ch == c)
                                p = dot;
                        else {
                                /* a string */
                                slen = ch - c;
                                if ((p = malloc(sizeof(char) * (slen + 1))) 
                                    == NULL)
                                        err(1, "malloc");
                                bcopy(c, p, slen);
                                *(p + slen) = '\0';
                        }
                        /* increase dbv with element p */
                        if ((dbv = realloc(dbv, sizeof(char **) * (vlen + 2)))
                            == NULL)
                                err(1, "realloc");
                        *(dbv + vlen) = p;
                        *(dbv + ++vlen) = NULL;
                        c = ch + 1;
                }
                if (*ch == '\0')
                        break;
        }
        return (dbv);
}

void 
print_matches(counter)
        u_int counter;
{
        (void)printf("%d\n", counter);
}


/*
 * extract last glob-free subpattern in name for fast pre-match; prepend
 * '\0' for backwards match; return end of new pattern
 */
static char globfree[100];

char *
patprep(name)
        char *name;
{
        register char *endmark, *p, *subp;

        subp = globfree;
        *subp++ = '\0';   /* set first element to '\0' */
        p = name + strlen(name) - 1;

        /* skip trailing metacharacters */
        for (; p >= name; p--)
                if (strchr(LOCATE_REG, *p) == NULL)
                        break;

        /* 
         * check if maybe we are in a character class
         *
         * 'foo.[ch]'
         *        |----< p
         */
        if (p >= name && 
            (strchr(p, '[') != NULL || strchr(p, ']') != NULL)) {
                for (p = name; *p != '\0'; p++)
                        if (*p == ']' || *p == '[')
                                break;
                p--;

                /* 
                 * cannot find a non-meta character, give up
                 * '*\*[a-z]'
                 *    |-------< p
                 */
                if (p >= name && strchr(LOCATE_REG, *p) != NULL)
                        p = name - 1;
        }
        
        if (p < name)                   
                /* only meta chars: "???", force '/' search */
                *subp++ = '/';

        else {
                for (endmark = p; p >= name; p--)
                        if (strchr(LOCATE_REG, *p) != NULL)
                                break;
                for (++p;
                    (p <= endmark) && subp < (globfree + sizeof(globfree));)
                        *subp++ = *p++;
        }
        *subp = '\0';
        return(--subp);
}

/* tolower word */
u_char *
tolower_word(word)
        u_char *word;
{
        register u_char *p;

        for(p = word; *p != '\0'; p++)
                *p = TOLOWER(*p);

        return(word);
}


/*
 * Read integer from mmap pointer.
 * Essentially a simple ``return *(int *)p'' but avoids sigbus
 * for integer alignment (SunOS 4.x, 5.x).
 *
 * Convert network byte order to host byte order if necessary.
 * So we can read a locate database on FreeBSD/i386 (little endian)
 * which was built on SunOS/sparc (big endian).
 */

int
getwm(p)
        caddr_t p;
{
        union {
                char buf[INTSIZE];
                int i;
        } u;
        register int i, hi;

        for (i = 0; i < (int)INTSIZE; i++)
                u.buf[i] = *p++;

        i = u.i;

        if (i > MAXPATHLEN || i < -(MAXPATHLEN)) {
                hi = ntohl(i);
                if (hi > MAXPATHLEN || hi < -(MAXPATHLEN))
                        errx(1, "integer out of +-MAXPATHLEN (%d): %u",
                            MAXPATHLEN, abs(i) < abs(hi) ? i : hi);
                return(hi);
        }
        return(i);
}

/*
 * Read integer from stream.
 *
 * Convert network byte order to host byte order if necessary.
 * So we can read on FreeBSD/i386 (little endian) a locate database
 * which was built on SunOS/sparc (big endian).
 */

int
getwf(fp)
        FILE *fp;
{
        register int word, hword;

        word = getw(fp);

        if (word > MAXPATHLEN || word < -(MAXPATHLEN)) {
                hword = ntohl(word);
                if (hword > MAXPATHLEN || hword < -(MAXPATHLEN))
                        errx(1, "integer out of +-MAXPATHLEN (%d): %u",
                            MAXPATHLEN, abs(word) < abs(hword) ? word : hword);
                return(hword);
        }
        return(word);
}
Revision:	11534
Committed:	Sat Jul 7 20:33:14 2018 UTC (5 years, 9 months ago) by laffer1
Content type:	text/plain
File size:	6785 byte(s)
Log Message:	sync with freebsd.
#	Content
1	/* $MidnightBSD$ */
2	/*
3	* Copyright (c) 1995 Wolfram Schneider <wosch@FreeBSD.org>. Berlin.
4	* Copyright (c) 1989, 1993
5	* The Regents of the University of California. All rights reserved.
6	*
7	* This code is derived from software contributed to Berkeley by
8	* James A. Woods.
9	*
10	* Redistribution and use in source and binary forms, with or without
11	* modification, are permitted provided that the following conditions
12	* are met:
13	* 1. Redistributions of source code must retain the above copyright
14	* notice, this list of conditions and the following disclaimer.
15	* 2. Redistributions in binary form must reproduce the above copyright
16	* notice, this list of conditions and the following disclaimer in the
17	* documentation and/or other materials provided with the distribution.
18	* 3. All advertising materials mentioning features or use of this software
19	* must display the following acknowledgement:
20	* This product includes software developed by the University of
21	* California, Berkeley and its contributors.
22	* 4. Neither the name of the University nor the names of its contributors
23	* may be used to endorse or promote products derived from this software
24	* without specific prior written permission.
25	*
26	* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
27	* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
28	* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
29	* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
30	* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
31	* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
32	* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
33	* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
34	* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
35	* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
36	* SUCH DAMAGE.
37	*
38	* $FreeBSD: stable/10/usr.bin/locate/locate/util.c 275034 2014-11-25 12:45:31Z dim $
39	*/
40
41
42	#include <stdlib.h>
43	#include <string.h>
44	#include <err.h>
45	#include <sys/param.h>
46	#include <arpa/inet.h>
47	#include <stdio.h>
48
49	#include "locate.h"
50
51	char colon(char , char, char);
52	char patprep(char );
53	void print_matches(u_int);
54	u_char tolower_word(u_char );
55	int getwm(caddr_t);
56	int getwf(FILE *);
57	int check_bigram_char(int);
58
59	/*
60	* Validate bigram chars. If the test failed the database is corrupt
61	* or the database is obviously not a locate database.
62	*/
63	int
64	check_bigram_char(ch)
65	int ch;
66	{
67	/* legal bigram: 0, ASCII_MIN ... ASCII_MAX */
68	if (ch == 0 \|\|
69	(ch >= ASCII_MIN && ch <= ASCII_MAX))
70	return(ch);
71
72	errx(1,
73	"locate database header corrupt, bigram char outside 0, %d-%d: %d",
74	ASCII_MIN, ASCII_MAX, ch);
75	exit(1);
76	}
77
78	/* split a colon separated string into a char vector
79	*
80	* "bla:foo" -> {"foo", "bla"}
81	* "bla:" -> {"foo", dot}
82	* "bla" -> {"bla"}
83	* "" -> do nothing
84	*
85	*/
86	char **
87	colon(dbv, path, dot)
88	char **dbv;
89	char *path;
90	char dot; / default for single ':' */
91	{
92	int vlen, slen;
93	char c, ch, *p;
94	char **pv;
95
96	if (dbv == NULL) {
97	if ((dbv = malloc(sizeof(char **))) == NULL)
98	err(1, "malloc");
99	*dbv = NULL;
100	}
101
102	/* empty string */
103	if (*path == '\0') {
104	warnx("empty database name, ignored");
105	return(dbv);
106	}
107
108	/* length of string vector */
109	for(vlen = 0, pv = dbv; *pv != NULL; pv++, vlen++);
110
111	for (ch = c = path; ; ch++) {
112	if (*ch == ':' \|\|
113	(!ch && !((ch - 1) == ':' && ch == 1+ path))) {
114	/* single colon -> dot */
115	if (ch == c)
116	p = dot;
117	else {
118	/* a string */
119	slen = ch - c;
120	if ((p = malloc(sizeof(char) * (slen + 1)))
121	== NULL)
122	err(1, "malloc");
123	bcopy(c, p, slen);
124	*(p + slen) = '\0';
125	}
126	/* increase dbv with element p */
127	if ((dbv = realloc(dbv, sizeof(char *) (vlen + 2)))
128	== NULL)
129	err(1, "realloc");
130	*(dbv + vlen) = p;
131	*(dbv + ++vlen) = NULL;
132	c = ch + 1;
133	}
134	if (*ch == '\0')
135	break;
136	}
137	return (dbv);
138	}
139
140	void
141	print_matches(counter)
142	u_int counter;
143	{
144	(void)printf("%d\n", counter);
145	}
146
147
148	/*
149	* extract last glob-free subpattern in name for fast pre-match; prepend
150	* '\0' for backwards match; return end of new pattern
151	*/
152	static char globfree[100];
153
154	char *
155	patprep(name)
156	char *name;
157	{
158	register char endmark, p, *subp;
159
160	subp = globfree;
161	subp++ = '\0'; / set first element to '\0' */
162	p = name + strlen(name) - 1;
163
164	/* skip trailing metacharacters */
165	for (; p >= name; p--)
166	if (strchr(LOCATE_REG, *p) == NULL)
167	break;
168
169	/*
170	* check if maybe we are in a character class
171	*
172	* 'foo.[ch]'
173	* \|----< p
174	*/
175	if (p >= name &&
176	(strchr(p, '[') != NULL \|\| strchr(p, ']') != NULL)) {
177	for (p = name; *p != '\0'; p++)
178	if (p == ']' \|\| p == '[')
179	break;
180	p--;
181
182	/*
183	* cannot find a non-meta character, give up
184	* '\[a-z]'
185	* \|-------< p
186	*/
187	if (p >= name && strchr(LOCATE_REG, *p) != NULL)
188	p = name - 1;
189	}
190
191	if (p < name)
192	/* only meta chars: "???", force '/' search */
193	*subp++ = '/';
194
195	else {
196	for (endmark = p; p >= name; p--)
197	if (strchr(LOCATE_REG, *p) != NULL)
198	break;
199	for (++p;
200	(p <= endmark) && subp < (globfree + sizeof(globfree));)
201	subp++ = p++;
202	}
203	*subp = '\0';
204	return(--subp);
205	}
206
207	/* tolower word */
208	u_char *
209	tolower_word(word)
210	u_char *word;
211	{
212	register u_char *p;
213
214	for(p = word; *p != '\0'; p++)
215	p = TOLOWER(p);
216
217	return(word);
218	}
219
220
221	/*
222	* Read integer from mmap pointer.
223	* Essentially a simple ``return (int )p'' but avoids sigbus
224	* for integer alignment (SunOS 4.x, 5.x).
225	*
226	* Convert network byte order to host byte order if necessary.
227	* So we can read a locate database on FreeBSD/i386 (little endian)
228	* which was built on SunOS/sparc (big endian).
229	*/
230
231	int
232	getwm(p)
233	caddr_t p;
234	{
235	union {
236	char buf[INTSIZE];
237	int i;
238	} u;
239	register int i, hi;
240
241	for (i = 0; i < (int)INTSIZE; i++)
242	u.buf[i] = *p++;
243
244	i = u.i;
245
246	if (i > MAXPATHLEN \|\| i < -(MAXPATHLEN)) {
247	hi = ntohl(i);
248	if (hi > MAXPATHLEN \|\| hi < -(MAXPATHLEN))
249	errx(1, "integer out of +-MAXPATHLEN (%d): %u",
250	MAXPATHLEN, abs(i) < abs(hi) ? i : hi);
251	return(hi);
252	}
253	return(i);
254	}
255
256	/*
257	* Read integer from stream.
258	*
259	* Convert network byte order to host byte order if necessary.
260	* So we can read on FreeBSD/i386 (little endian) a locate database
261	* which was built on SunOS/sparc (big endian).
262	*/
263
264	int
265	getwf(fp)
266	FILE *fp;
267	{
268	register int word, hword;
269
270	word = getw(fp);
271
272	if (word > MAXPATHLEN \|\| word < -(MAXPATHLEN)) {
273	hword = ntohl(word);
274	if (hword > MAXPATHLEN \|\| hword < -(MAXPATHLEN))
275	errx(1, "integer out of +-MAXPATHLEN (%d): %u",
276	MAXPATHLEN, abs(word) < abs(hword) ? word : hword);
277	return(hword);
278	}
279	return(word);
280	}