1
0
mirror of https://git.FreeBSD.org/src.git synced 2024-12-17 10:26:15 +00:00
freebsd/usr.bin/look/look.c

358 lines
8.9 KiB
C
Raw Normal View History

1994-05-27 12:33:43 +00:00
/*-
* Copyright (c) 1991, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* David Hitz of Auspex Systems, Inc.
*
* 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.
*/
#ifndef lint
static char copyright[] =
"@(#) Copyright (c) 1991, 1993\n\
The Regents of the University of California. All rights reserved.\n";
#endif /* not lint */
#ifndef lint
static char sccsid[] = "@(#)look.c 8.1 (Berkeley) 6/14/93";
#endif /* not lint */
/*
* look -- find lines in a sorted list.
1995-05-30 06:41:30 +00:00
*
1994-05-27 12:33:43 +00:00
* The man page said that TABs and SPACEs participate in -d comparisons.
* In fact, they were ignored. This implements historic practice, not
* the manual page.
*/
#include <sys/types.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <limits.h>
#include <errno.h>
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include "pathnames.h"
/*
* FOLD and DICT convert characters to a normal form for comparison,
* according to the user specified flags.
1995-05-30 06:41:30 +00:00
*
1994-05-27 12:33:43 +00:00
* DICT expects integers because it uses a non-character value to
* indicate a character which should not participate in comparisons.
*/
#define EQUAL 0
#define GREATER 1
#define LESS (-1)
#define NO_COMPARE (-2)
#define FOLD(c) (isascii(c) && isupper(c) ? tolower(c) : (c))
#define DICT(c) (isascii(c) && isalnum(c) ? (c) : NO_COMPARE)
int dflag, fflag;
char *binary_search __P((char *, char *, char *));
int compare __P((char *, char *, char *));
void err __P((const char *fmt, ...));
char *linear_search __P((char *, char *, char *));
int look __P((char *, char *, char *));
void print_from __P((char *, char *, char *));
static void usage __P((void));
main(argc, argv)
int argc;
char *argv[];
{
struct stat sb;
int ch, fd, termchar;
char *back, *file, *front, *string, *p;
file = _PATH_WORDS;
termchar = '\0';
while ((ch = getopt(argc, argv, "dft:")) != EOF)
switch(ch) {
case 'd':
dflag = 1;
break;
case 'f':
fflag = 1;
break;
case 't':
termchar = *optarg;
break;
case '?':
default:
usage();
}
argc -= optind;
argv += optind;
switch (argc) {
case 2: /* Don't set -df for user. */
string = *argv++;
file = *argv;
break;
case 1: /* But set -df by default. */
dflag = fflag = 1;
string = *argv;
break;
default:
usage();
}
if (termchar != '\0' && (p = strchr(string, termchar)) != NULL)
*++p = '\0';
if ((fd = open(file, O_RDONLY, 0)) < 0 || fstat(fd, &sb))
err("%s: %s", file, strerror(errno));
if (sb.st_size > SIZE_T_MAX)
err("%s: %s", file, strerror(EFBIG));
if ((front = mmap(NULL,
(size_t)sb.st_size, PROT_READ, 0, fd, (off_t)0)) == NULL)
err("%s: %s", file, strerror(errno));
back = front + sb.st_size;
exit(look(string, front, back));
}
look(string, front, back)
char *string, *front, *back;
{
register int ch;
register char *readp, *writep;
/* Reformat string string to avoid doing it multiple times later. */
for (readp = writep = string; ch = *readp++;) {
if (fflag)
ch = FOLD(ch);
if (dflag)
ch = DICT(ch);
if (ch != NO_COMPARE)
*(writep++) = ch;
}
*writep = '\0';
front = binary_search(string, front, back);
front = linear_search(string, front, back);
if (front)
print_from(string, front, back);
return (front ? 0 : 1);
}
/*
* Binary search for "string" in memory between "front" and "back".
1995-05-30 06:41:30 +00:00
*
1994-05-27 12:33:43 +00:00
* This routine is expected to return a pointer to the start of a line at
* *or before* the first word matching "string". Relaxing the constraint
* this way simplifies the algorithm.
1995-05-30 06:41:30 +00:00
*
1994-05-27 12:33:43 +00:00
* Invariants:
1995-05-30 06:41:30 +00:00
* front points to the beginning of a line at or before the first
1994-05-27 12:33:43 +00:00
* matching string.
1995-05-30 06:41:30 +00:00
*
* back points to the beginning of a line at or after the first
1994-05-27 12:33:43 +00:00
* matching line.
1995-05-30 06:41:30 +00:00
*
1994-05-27 12:33:43 +00:00
* Base of the Invariants.
1995-05-30 06:41:30 +00:00
* front = NULL;
1994-05-27 12:33:43 +00:00
* back = EOF;
1995-05-30 06:41:30 +00:00
*
1994-05-27 12:33:43 +00:00
* Advancing the Invariants:
1995-05-30 06:41:30 +00:00
*
1994-05-27 12:33:43 +00:00
* p = first newline after halfway point from front to back.
1995-05-30 06:41:30 +00:00
*
* If the string at "p" is not greater than the string to match,
1994-05-27 12:33:43 +00:00
* p is the new front. Otherwise it is the new back.
1995-05-30 06:41:30 +00:00
*
1994-05-27 12:33:43 +00:00
* Termination:
1995-05-30 06:41:30 +00:00
*
* The definition of the routine allows it return at any point,
1994-05-27 12:33:43 +00:00
* since front is always at or before the line to print.
1995-05-30 06:41:30 +00:00
*
* In fact, it returns when the chosen "p" equals "back". This
* implies that there exists a string is least half as long as
* (back - front), which in turn implies that a linear search will
1994-05-27 12:33:43 +00:00
* be no more expensive than the cost of simply printing a string or two.
1995-05-30 06:41:30 +00:00
*
* Trying to continue with binary search at this point would be
1994-05-27 12:33:43 +00:00
* more trouble than it's worth.
*/
#define SKIP_PAST_NEWLINE(p, back) \
while (p < back && *p++ != '\n');
char *
binary_search(string, front, back)
register char *string, *front, *back;
{
register char *p;
p = front + (back - front) / 2;
SKIP_PAST_NEWLINE(p, back);
/*
* If the file changes underneath us, make sure we don't
* infinitely loop.
*/
while (p < back && back > front) {
if (compare(string, p, back) == GREATER)
front = p;
else
back = p;
p = front + (back - front) / 2;
SKIP_PAST_NEWLINE(p, back);
}
return (front);
}
/*
* Find the first line that starts with string, linearly searching from front
* to back.
1995-05-30 06:41:30 +00:00
*
1994-05-27 12:33:43 +00:00
* Return NULL for no such line.
1995-05-30 06:41:30 +00:00
*
1994-05-27 12:33:43 +00:00
* This routine assumes:
1995-05-30 06:41:30 +00:00
*
* o front points at the first character in a line.
1994-05-27 12:33:43 +00:00
* o front is before or at the first line to be printed.
*/
char *
linear_search(string, front, back)
char *string, *front, *back;
{
while (front < back) {
switch (compare(string, front, back)) {
case EQUAL: /* Found it. */
return (front);
break;
case LESS: /* No such string. */
return (NULL);
break;
case GREATER: /* Keep going. */
break;
}
SKIP_PAST_NEWLINE(front, back);
}
return (NULL);
}
/*
* Print as many lines as match string, starting at front.
*/
1995-05-30 06:41:30 +00:00
void
1994-05-27 12:33:43 +00:00
print_from(string, front, back)
register char *string, *front, *back;
{
for (; front < back && compare(string, front, back) == EQUAL; ++front) {
for (; front < back && *front != '\n'; ++front)
if (putchar(*front) == EOF)
err("stdout: %s", strerror(errno));
if (putchar('\n') == EOF)
err("stdout: %s", strerror(errno));
}
}
/*
* Return LESS, GREATER, or EQUAL depending on how the string1 compares with
* string2 (s1 ??? s2).
1995-05-30 06:41:30 +00:00
*
* o Matches up to len(s1) are EQUAL.
1994-05-27 12:33:43 +00:00
* o Matches up to len(s2) are GREATER.
1995-05-30 06:41:30 +00:00
*
1994-05-27 12:33:43 +00:00
* Compare understands about the -f and -d flags, and treats comparisons
* appropriately.
1995-05-30 06:41:30 +00:00
*
1994-05-27 12:33:43 +00:00
* The string "s1" is null terminated. The string s2 is '\n' terminated (or
* "back" terminated).
*/
int
compare(s1, s2, back)
register char *s1, *s2, *back;
{
register int ch;
for (; *s1 && s2 < back && *s2 != '\n'; ++s1, ++s2) {
ch = *s2;
if (fflag)
ch = FOLD(ch);
if (dflag)
ch = DICT(ch);
if (ch == NO_COMPARE) {
++s2; /* Ignore character in comparison. */
continue;
}
if (*s1 != ch)
return (*s1 < ch ? LESS : GREATER);
}
return (*s1 ? GREATER : EQUAL);
}
static void
usage()
{
(void)fprintf(stderr, "usage: look [-df] [-t char] string [file]\n");
exit(2);
}
#if __STDC__
#include <stdarg.h>
#else
#include <varargs.h>
#endif
void
#if __STDC__
err(const char *fmt, ...)
#else
err(fmt, va_alist)
char *fmt;
va_dcl
#endif
{
va_list ap;
#if __STDC__
va_start(ap, fmt);
#else
va_start(ap);
#endif
(void)fprintf(stderr, "look: ");
(void)vfprintf(stderr, fmt, ap);
va_end(ap);
(void)fprintf(stderr, "\n");
exit(2);
/* NOTREACHED */
}