2 * Copyright (c) 1991, 1993
3 * The Regents of the University of California. All rights reserved.
5 * This code is derived from software contributed to Berkeley by
6 * David Hitz of Auspex Systems, Inc.
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
11 * 1. Redistributions of source code must retain the above copyright
12 * notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 * notice, this list of conditions and the following disclaimer in the
15 * documentation and/or other materials provided with the distribution.
16 * 3. All advertising materials mentioning features or use of this software
17 * must display the following acknowledgement:
18 * This product includes software developed by the University of
19 * California, Berkeley and its contributors.
20 * 4. Neither the name of the University nor the names of its contributors
21 * may be used to endorse or promote products derived from this software
22 * without specific prior written permission.
24 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
27 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
38 static const char copyright[] =
39 "@(#) Copyright (c) 1991, 1993\n\
40 The Regents of the University of California. All rights reserved.\n";
45 static char sccsid[] = "@(#)look.c 8.2 (Berkeley) 5/4/95";
47 static const char rcsid[] =
52 * look -- find lines in a sorted list.
54 * The man page said that TABs and SPACEs participate in -d comparisons.
55 * In fact, they were ignored. This implements historic practice, not
59 #include <sys/types.h>
74 #include "pathnames.h"
77 * FOLD and DICT convert characters to a normal form for comparison,
78 * according to the user specified flags.
80 * DICT expects integers because it uses a non-character value to
81 * indicate a character which should not participate in comparisons.
86 #define NO_COMPARE (-2)
88 #define FOLD(c) (isupper(c) ? tolower(c) : (unsigned char) (c))
89 #define DICT(c) (isalnum(c) ? (c) & 0xFF /* int */ : NO_COMPARE)
93 char *binary_search(unsigned char *, unsigned char *, unsigned char *);
94 int compare(unsigned char *, unsigned char *, unsigned char *);
95 char *linear_search(unsigned char *, unsigned char *, unsigned char *);
96 int look(unsigned char *, unsigned char *, unsigned char *);
97 void print_from(unsigned char *, unsigned char *, unsigned char *);
99 static void usage(void);
107 int ch, fd, termchar, match;
108 unsigned char *back, *front, *string, *p;
109 unsigned const char *file;
111 (void) setlocale(LC_CTYPE, "");
115 while ((ch = getopt(argc, argv, "dft:")) != -1)
135 if (argc == 1) /* But set -df by default. */
141 if (termchar != '\0' && (p = strchr(string, termchar)) != NULL)
146 if ((fd = open(file, O_RDONLY, 0)) < 0 || fstat(fd, &sb))
148 if (sb.st_size > SIZE_T_MAX)
149 errx(2, "%s: %s", file, strerror(EFBIG));
150 if ((front = mmap(NULL, (size_t)sb.st_size, PROT_READ, MAP_SHARED, fd, (off_t)0)) == MAP_FAILED)
152 back = front + sb.st_size;
153 match *= (look(string, front, back));
155 } while (argc-- > 2 && (file = *argv++));
161 look(string, front, back)
162 unsigned char *string, *front, *back;
165 register unsigned char *readp, *writep;
167 /* Reformat string string to avoid doing it multiple times later. */
168 for (readp = writep = string; (ch = *readp++);) {
173 if (ch != NO_COMPARE)
178 front = binary_search(string, front, back);
179 front = linear_search(string, front, back);
182 print_from(string, front, back);
183 return (front ? 0 : 1);
188 * Binary search for "string" in memory between "front" and "back".
190 * This routine is expected to return a pointer to the start of a line at
191 * *or before* the first word matching "string". Relaxing the constraint
192 * this way simplifies the algorithm.
195 * front points to the beginning of a line at or before the first
198 * back points to the beginning of a line at or after the first
201 * Base of the Invariants.
205 * Advancing the Invariants:
207 * p = first newline after halfway point from front to back.
209 * If the string at "p" is not greater than the string to match,
210 * p is the new front. Otherwise it is the new back.
214 * The definition of the routine allows it return at any point,
215 * since front is always at or before the line to print.
217 * In fact, it returns when the chosen "p" equals "back". This
218 * implies that there exists a string is least half as long as
219 * (back - front), which in turn implies that a linear search will
220 * be no more expensive than the cost of simply printing a string or two.
222 * Trying to continue with binary search at this point would be
223 * more trouble than it's worth.
225 #define SKIP_PAST_NEWLINE(p, back) \
226 while (p < back && *p++ != '\n');
229 binary_search(string, front, back)
230 register unsigned char *string, *front, *back;
232 register unsigned char *p;
234 p = front + (back - front) / 2;
235 SKIP_PAST_NEWLINE(p, back);
238 * If the file changes underneath us, make sure we don't
241 while (p < back && back > front) {
242 if (compare(string, p, back) == GREATER)
246 p = front + (back - front) / 2;
247 SKIP_PAST_NEWLINE(p, back);
253 * Find the first line that starts with string, linearly searching from front
256 * Return NULL for no such line.
258 * This routine assumes:
260 * o front points at the first character in a line.
261 * o front is before or at the first line to be printed.
264 linear_search(string, front, back)
265 unsigned char *string, *front, *back;
267 while (front < back) {
268 switch (compare(string, front, back)) {
269 case EQUAL: /* Found it. */
272 case LESS: /* No such string. */
275 case GREATER: /* Keep going. */
278 SKIP_PAST_NEWLINE(front, back);
284 * Print as many lines as match string, starting at front.
287 print_from(string, front, back)
288 register unsigned char *string, *front, *back;
290 for (; front < back && compare(string, front, back) == EQUAL; ++front) {
291 for (; front < back && *front != '\n'; ++front)
292 if (putchar(*front) == EOF)
294 if (putchar('\n') == EOF)
300 * Return LESS, GREATER, or EQUAL depending on how the string1 compares with
301 * string2 (s1 ??? s2).
303 * o Matches up to len(s1) are EQUAL.
304 * o Matches up to len(s2) are GREATER.
306 * Compare understands about the -f and -d flags, and treats comparisons
309 * The string "s1" is null terminated. The string s2 is '\n' terminated (or
310 * "back" terminated).
313 compare(s1, s2, back)
314 register unsigned char *s1, *s2, *back;
318 for (; *s1 && s2 < back && *s2 != '\n'; ++s1, ++s2) {
325 if (ch == NO_COMPARE) {
326 ++s2; /* Ignore character in comparison. */
330 return (*s1 < ch ? LESS : GREATER);
332 return (*s1 ? GREATER : EQUAL);
338 (void)fprintf(stderr, "usage: look [-df] [-t char] string [file ...]\n");