freebsd-dev/usr.bin/uniq/uniq.c
Andrey A. Chernov e12155c834 Back out rev 1.19 because
1) It breaks uniq for real life languages when "substitute" directive used in
the collating table.
2) It breaks uniq usage in tool chain with other localized utilities which
use collate.
3) To follow LC_COLLATE it is directly allowed for uniq
by POSIX P1003.1 Draft7 (7.3.2). It means that rev 1.19 gains no additional
POSIX conformance.
2002-06-06 13:44:14 +00:00

270 lines
6.1 KiB
C

/*
* Copyright (c) 1989, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Case Larsen.
*
* 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 const char copyright[] =
"@(#) Copyright (c) 1989, 1993\n\
The Regents of the University of California. All rights reserved.\n";
#endif /* not lint */
#ifndef lint
#if 0
static char sccsid[] = "@(#)uniq.c 8.3 (Berkeley) 5/4/95";
#endif
static const char rcsid[] =
"$FreeBSD$";
#endif /* not lint */
#include <ctype.h>
#include <err.h>
#include <limits.h>
#include <locale.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#define MAXLINELEN (LINE_MAX + 1)
int cflag, dflag, uflag;
int numchars, numfields, repeats;
FILE *file(const char *, const char *);
void show(FILE *, char *);
char *skip(char *);
void obsolete(char *[]);
static void usage(void);
int stricoll(char *, char*);
int
main (argc, argv)
int argc;
char *argv[];
{
register char *t1, *t2;
FILE *ifp, *ofp;
int ch;
char *prevline, *thisline, *p;
int iflag = 0, comp;
(void) setlocale(LC_ALL, "");
obsolete(argv);
while ((ch = getopt(argc, argv, "cdif:s:u")) != -1)
switch (ch) {
case 'c':
cflag = 1;
break;
case 'd':
dflag = 1;
break;
case 'i':
iflag = 1;
break;
case 'f':
numfields = strtol(optarg, &p, 10);
if (numfields < 0 || *p)
errx(1, "illegal field skip value: %s", optarg);
break;
case 's':
numchars = strtol(optarg, &p, 10);
if (numchars < 0 || *p)
errx(1, "illegal character skip value: %s", optarg);
break;
case 'u':
uflag = 1;
break;
case '?':
default:
usage();
}
argc -= optind;
argv +=optind;
/* If no flags are set, default is -d -u. */
if (cflag) {
if (dflag || uflag)
usage();
} else if (!dflag && !uflag)
dflag = uflag = 1;
if (argc > 2)
usage();
ifp = stdin;
ofp = stdout;
if (argc > 0 && strcmp(argv[0], "-") != 0)
ifp = file(argv[0], "r");
if (argc > 1)
ofp = file(argv[1], "w");
prevline = malloc(MAXLINELEN);
thisline = malloc(MAXLINELEN);
if (prevline == NULL || thisline == NULL)
errx(1, "malloc");
if (fgets(prevline, MAXLINELEN, ifp) == NULL)
exit(0);
while (fgets(thisline, MAXLINELEN, ifp)) {
/* If requested get the chosen fields + character offsets. */
if (numfields || numchars) {
t1 = skip(thisline);
t2 = skip(prevline);
} else {
t1 = thisline;
t2 = prevline;
}
/* If different, print; set previous to new value. */
if (iflag)
comp = stricoll(t1, t2);
else
comp = strcoll(t1, t2);
if (comp) {
show(ofp, prevline);
t1 = prevline;
prevline = thisline;
thisline = t1;
repeats = 0;
} else
++repeats;
}
show(ofp, prevline);
exit(0);
}
/*
* show --
* Output a line depending on the flags and number of repetitions
* of the line.
*/
void
show(ofp, str)
FILE *ofp;
char *str;
{
if (cflag && *str)
(void)fprintf(ofp, "%4d %s", repeats + 1, str);
if ((dflag && repeats) || (uflag && !repeats))
(void)fprintf(ofp, "%s", str);
}
char *
skip(str)
register char *str;
{
register int infield, nchars, nfields;
for (nfields = numfields, infield = 0; nfields && *str; ++str)
if (isblank((unsigned char)*str)) {
if (infield) {
infield = 0;
--nfields;
}
} else if (!infield)
infield = 1;
for (nchars = numchars; nchars-- && *str; ++str);
return(str);
}
FILE *
file(name, mode)
const char *name, *mode;
{
FILE *fp;
if ((fp = fopen(name, mode)) == NULL)
err(1, "%s", name);
return(fp);
}
void
obsolete(argv)
char *argv[];
{
int len;
char *ap, *p, *start;
while ((ap = *++argv)) {
/* Return if "--" or not an option of any form. */
if (ap[0] != '-') {
if (ap[0] != '+')
return;
} else if (ap[1] == '-')
return;
if (!isdigit((unsigned char)ap[1]))
continue;
/*
* Digit signifies an old-style option. Malloc space for dash,
* new option and argument.
*/
len = strlen(ap);
if ((start = p = malloc(len + 3)) == NULL)
errx(1, "malloc");
*p++ = '-';
*p++ = ap[0] == '+' ? 's' : 'f';
(void)strcpy(p, ap + 1);
*argv = start;
}
}
static void
usage()
{
(void)fprintf(stderr,
"usage: uniq [-c | -d | -u] [-i] [-f fields] [-s chars] [input [output]]\n");
exit(1);
}
int
stricoll(s1, s2)
char *s1, *s2;
{
char *p, line1[MAXLINELEN], line2[MAXLINELEN];
for (p = line1; *s1; s1++)
*p++ = tolower((unsigned char)*s1);
*p = '\0';
for (p = line2; *s2; s2++)
*p++ = tolower((unsigned char)*s2);
*p = '\0';
return strcoll(line1, line2);
}