Replace uniq with NetBSD version
This commit is contained in:
Vivek Prakash
Arun Thomas
parent
e376fd97ac
commit
1ea07af9da
10 changed files with 395 additions and 242 deletions
|
|
@ -30,7 +30,7 @@ SUBDIR= aal add_route adduser advent arp ash at autil awk \
|
||||||
syslogd tail talk talkd tar tcpd tcpdp tcpstat tee telnet \
|
syslogd tail talk talkd tar tcpd tcpdp tcpstat tee telnet \
|
||||||
telnetd term termcap tget time tinyhalt top touch tr \
|
telnetd term termcap tget time tinyhalt top touch tr \
|
||||||
truncate tsort ttt tty udpstat umount uname unexpand \
|
truncate tsort ttt tty udpstat umount uname unexpand \
|
||||||
uniq unstack update uud uue version vol wc \
|
unstack update uud uue version vol wc \
|
||||||
whereis which who write writeisofs fetch \
|
whereis which who write writeisofs fetch \
|
||||||
xargs yacc yes zdump zic zmodem pkgin_cd \
|
xargs yacc yes zdump zic zmodem pkgin_cd \
|
||||||
mktemp
|
mktemp
|
||||||
|
|
|
||||||
|
|
@ -1,4 +0,0 @@
|
||||||
PROG= uniq
|
|
||||||
MAN=
|
|
||||||
|
|
||||||
.include <bsd.prog.mk>
|
|
||||||
|
|
@ -1,199 +0,0 @@
|
||||||
/* uniq - compact repeated lines Author: John Woods */
|
|
||||||
/* Uniq [-udc] [-n] [+n] [infile [outfile]]
|
|
||||||
*
|
|
||||||
* Written 02/08/86 by John Woods, placed into public domain. Enjoy.
|
|
||||||
*
|
|
||||||
*/
|
|
||||||
|
|
||||||
/* If the symbol WRITE_ERROR is defined, uniq will exit(1) if it gets a
|
|
||||||
* write error on the output. This is not (of course) how V7 uniq does it,
|
|
||||||
* so undefine the symbol if you want to lose your output to a full disk
|
|
||||||
*/
|
|
||||||
|
|
||||||
#define WRITE_ERROR 1
|
|
||||||
#include <ctype.h>
|
|
||||||
#include <errno.h>
|
|
||||||
#include <string.h>
|
|
||||||
#include <stdlib.h>
|
|
||||||
#include <stdio.h>
|
|
||||||
|
|
||||||
char buffer[BUFSIZ];
|
|
||||||
int uflag = 1; /* default is union of -d and -u outputs */
|
|
||||||
int dflag = 1; /* flags are mutually exclusive */
|
|
||||||
int cflag = 0;
|
|
||||||
int fields = 0;
|
|
||||||
int chars = 0;
|
|
||||||
|
|
||||||
#ifdef __NBSD_LIBC
|
|
||||||
#define getline unix_getline
|
|
||||||
#endif
|
|
||||||
|
|
||||||
_PROTOTYPE(int main, (int argc, char **argv));
|
|
||||||
_PROTOTYPE(FILE *xfopen, (char *fn, char *mode));
|
|
||||||
_PROTOTYPE(char *skip, (char *s));
|
|
||||||
_PROTOTYPE(int equal, (char *s1, char *s2));
|
|
||||||
_PROTOTYPE(void show, (char *line, int count));
|
|
||||||
_PROTOTYPE(int uniq, (void));
|
|
||||||
_PROTOTYPE(void usage, (void));
|
|
||||||
_PROTOTYPE(int getline, (char *buf, int count));
|
|
||||||
|
|
||||||
FILE *xfopen(fn, mode)
|
|
||||||
char *fn, *mode;
|
|
||||||
{
|
|
||||||
FILE *p;
|
|
||||||
|
|
||||||
if ((p = fopen(fn, mode)) == NULL) {
|
|
||||||
perror("uniq");
|
|
||||||
fflush(stdout);
|
|
||||||
exit(1);
|
|
||||||
}
|
|
||||||
return(p);
|
|
||||||
}
|
|
||||||
|
|
||||||
int main(argc, argv)
|
|
||||||
int argc;
|
|
||||||
char *argv[];
|
|
||||||
{
|
|
||||||
char *p;
|
|
||||||
int inf = -1, outf;
|
|
||||||
|
|
||||||
setbuf(stdout, buffer);
|
|
||||||
for (--argc, ++argv; argc > 0 && (**argv == '-' || **argv == '+');
|
|
||||||
--argc, ++argv) {
|
|
||||||
if (**argv == '+')
|
|
||||||
chars = atoi(*argv + 1);
|
|
||||||
else if (isdigit(argv[0][1]))
|
|
||||||
fields = atoi(*argv + 1);
|
|
||||||
else if (argv[0][1] == '\0')
|
|
||||||
inf = 0; /* - is stdin */
|
|
||||||
else
|
|
||||||
for (p = *argv + 1; *p; p++) {
|
|
||||||
switch (*p) {
|
|
||||||
case 'd':
|
|
||||||
dflag = 1;
|
|
||||||
uflag = 0;
|
|
||||||
break;
|
|
||||||
case 'u':
|
|
||||||
uflag = 1;
|
|
||||||
dflag = 0;
|
|
||||||
break;
|
|
||||||
case 'c': cflag = 1; break;
|
|
||||||
default: usage();
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
/* Input file */
|
|
||||||
if (argc == 0)
|
|
||||||
inf = 0;
|
|
||||||
else if (inf == -1) { /* if - was not given */
|
|
||||||
fclose(stdin);
|
|
||||||
xfopen(*argv++, "r");
|
|
||||||
argc--;
|
|
||||||
}
|
|
||||||
if (argc == 0)
|
|
||||||
outf = 1;
|
|
||||||
else {
|
|
||||||
fclose(stdout);
|
|
||||||
xfopen(*argv++, "w");
|
|
||||||
argc--;
|
|
||||||
}
|
|
||||||
|
|
||||||
uniq();
|
|
||||||
fflush(stdout);
|
|
||||||
return(0);
|
|
||||||
}
|
|
||||||
|
|
||||||
char *skip(s)
|
|
||||||
char *s;
|
|
||||||
{
|
|
||||||
int n;
|
|
||||||
|
|
||||||
/* Skip fields */
|
|
||||||
for (n = fields; n > 0; --n) {
|
|
||||||
/* Skip blanks */
|
|
||||||
while (*s && (*s == ' ' || *s == '\t')) s++;
|
|
||||||
if (!*s) return s;
|
|
||||||
while (*s && (*s != ' ' && *s != '\t')) s++;
|
|
||||||
if (!*s) return s;
|
|
||||||
}
|
|
||||||
|
|
||||||
/* Skip characters */
|
|
||||||
for (n = chars; n > 0; --n) {
|
|
||||||
if (!*s) return s;
|
|
||||||
s++;
|
|
||||||
}
|
|
||||||
return s;
|
|
||||||
}
|
|
||||||
|
|
||||||
int equal(s1, s2)
|
|
||||||
char *s1, *s2;
|
|
||||||
{
|
|
||||||
return !strcmp(skip(s1), skip(s2));
|
|
||||||
}
|
|
||||||
|
|
||||||
void show(line, count)
|
|
||||||
char *line;
|
|
||||||
int count;
|
|
||||||
{
|
|
||||||
if (cflag)
|
|
||||||
printf("%4d %s", count, line);
|
|
||||||
else {
|
|
||||||
if ((uflag && count == 1) || (dflag && count != 1))
|
|
||||||
printf("%s", line);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
/* The meat of the whole affair */
|
|
||||||
char *nowline, *prevline, buf1[1024], buf2[1024];
|
|
||||||
|
|
||||||
int uniq()
|
|
||||||
{
|
|
||||||
char *p;
|
|
||||||
int seen;
|
|
||||||
|
|
||||||
/* Setup */
|
|
||||||
prevline = buf1;
|
|
||||||
if (getline(prevline, 1024) < 0) return(0);
|
|
||||||
seen = 1;
|
|
||||||
nowline = buf2;
|
|
||||||
|
|
||||||
/* Get nowline and compare if not equal, dump prevline and swap
|
|
||||||
* pointers else continue, bumping seen count */
|
|
||||||
while (getline(nowline, 1024) > 0) {
|
|
||||||
if (!equal(prevline, nowline)) {
|
|
||||||
show(prevline, seen);
|
|
||||||
seen = 1;
|
|
||||||
p = nowline;
|
|
||||||
nowline = prevline;
|
|
||||||
prevline = p;
|
|
||||||
} else
|
|
||||||
seen += 1;
|
|
||||||
}
|
|
||||||
show(prevline, seen);
|
|
||||||
return 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
void usage()
|
|
||||||
{
|
|
||||||
fprintf(stderr, "Usage: uniq [-udc] [+n] [-n] [input [output]]\n");
|
|
||||||
}
|
|
||||||
|
|
||||||
int getline(buf, count)
|
|
||||||
char *buf;
|
|
||||||
int count;
|
|
||||||
{
|
|
||||||
int c;
|
|
||||||
int ct = 0;
|
|
||||||
|
|
||||||
while (ct++ < count) {
|
|
||||||
c = getc(stdin);
|
|
||||||
if (c < 0) return(-1);
|
|
||||||
*buf++ = c;
|
|
||||||
if (c == '\n') {
|
|
||||||
*buf++ = 0;
|
|
||||||
return(ct);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return(ct);
|
|
||||||
}
|
|
||||||
|
|
@ -21,7 +21,7 @@ MAN= acd.1 anm.1 ar.1 ash.1 asize.1 at.1 banner.1 basename.1 \
|
||||||
split.1 strip.1 stty.1 su.1 sum.1 svc.1 \
|
split.1 strip.1 stty.1 su.1 sum.1 svc.1 \
|
||||||
synctree.1 sysenv.1 sz.1 tail.1 tee.1 telnet.1 template.1 \
|
synctree.1 sysenv.1 sz.1 tail.1 tee.1 telnet.1 template.1 \
|
||||||
term.1 termcap.1 tget.1 time.1 top.1 tr.1 true.1 \
|
term.1 termcap.1 tget.1 time.1 top.1 tr.1 true.1 \
|
||||||
truncate.1 tsort.1 tty.1 umount.1 uname.1 unexpand.1 uniq.1 \
|
truncate.1 tsort.1 tty.1 umount.1 uname.1 unexpand.1 \
|
||||||
uud.1 uue.1 vol.1 wc.1 whereis.1 which.1 \
|
uud.1 uue.1 vol.1 wc.1 whereis.1 which.1 \
|
||||||
who.1 write.1 xargs.1 yap.1 yes.1 linkfarm.1 pkg_view.1
|
who.1 write.1 xargs.1 yap.1 yes.1 linkfarm.1 pkg_view.1
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -1,36 +0,0 @@
|
||||||
.TH UNIQ 1
|
|
||||||
.SH NAME
|
|
||||||
uniq \- delete consecutive identical lines in a file
|
|
||||||
.SH SYNOPSIS
|
|
||||||
\fBuniq\fR [\fB\-cdu\fR]\fR [\fB\-\fIn\fR] [\fB+\fIn\fR] [\fIinput [\fIoutput\fR]\fR]\fR
|
|
||||||
.br
|
|
||||||
.de FL
|
|
||||||
.TP
|
|
||||||
\\fB\\$1\\fR
|
|
||||||
\\$2
|
|
||||||
..
|
|
||||||
.de EX
|
|
||||||
.TP 20
|
|
||||||
\\fB\\$1\\fR
|
|
||||||
# \\$2
|
|
||||||
..
|
|
||||||
.SH OPTIONS
|
|
||||||
.FL "\-c" "Give count of identical lines in the input"
|
|
||||||
.FL "\-d" "Only duplicate lines are written to output"
|
|
||||||
.FL "\-u" "Only unique lines are written to output"
|
|
||||||
.FL "\-\fIn\fR" "Skip the first \fIn\fR columns when matching"
|
|
||||||
.FL "+\fIn\fR" "Skip the first \fIn\fR fields when matching"
|
|
||||||
.SH EXAMPLES
|
|
||||||
.EX "uniq +2 file" "Ignore first 2 fields when comparing"
|
|
||||||
.EX "uniq \-d inf outf" "Write duplicate lines to \fIoutf\fP"
|
|
||||||
.SH DESCRIPTION
|
|
||||||
.PP
|
|
||||||
.I Uniq
|
|
||||||
examines a file for consecutive lines that are identical.
|
|
||||||
All but duplicate entries are deleted, and the file is written to output.
|
|
||||||
The +\fIn\fR option skips the first \fIn\fR fields, where a field is defined
|
|
||||||
as a run of characters separated by white space.
|
|
||||||
The \-\fIn\fP option skips the first \fIn\fR spaces.
|
|
||||||
Fields are skipped first.
|
|
||||||
.SH "SEE ALSO"
|
|
||||||
.BR sort (1).
|
|
||||||
|
|
@ -10,3 +10,4 @@ usr.bin/sed src/usr.bin/sed
|
||||||
usr.bin/stat src/usr.bin/stat
|
usr.bin/stat src/usr.bin/stat
|
||||||
usr.bin/tic src/usr.bin/tic
|
usr.bin/tic src/usr.bin/tic
|
||||||
usr.bin/mkdep src/usr.bin/mkdep
|
usr.bin/mkdep src/usr.bin/mkdep
|
||||||
|
usr.bin/uniq src/usr.bin/uniq
|
||||||
|
|
|
||||||
|
|
@ -3,7 +3,7 @@
|
||||||
.include <bsd.own.mk>
|
.include <bsd.own.mk>
|
||||||
|
|
||||||
# NetBSD imports
|
# NetBSD imports
|
||||||
SUBDIR= indent m4 stat tic sed mkdep
|
SUBDIR= indent m4 stat tic sed mkdep uniq
|
||||||
|
|
||||||
# Non-NetBSD imports
|
# Non-NetBSD imports
|
||||||
SUBDIR+= ministat mkimage
|
SUBDIR+= ministat mkimage
|
||||||
|
|
|
||||||
6
usr.bin/uniq/Makefile
Normal file
6
usr.bin/uniq/Makefile
Normal file
|
|
@ -0,0 +1,6 @@
|
||||||
|
# $NetBSD: Makefile,v 1.5 2009/04/14 22:15:28 lukem Exp $
|
||||||
|
# @(#)Makefile 8.1 (Berkeley) 6/6/93
|
||||||
|
|
||||||
|
PROG= uniq
|
||||||
|
|
||||||
|
.include <bsd.prog.mk>
|
||||||
128
usr.bin/uniq/uniq.1
Normal file
128
usr.bin/uniq/uniq.1
Normal file
|
|
@ -0,0 +1,128 @@
|
||||||
|
.\" $NetBSD: uniq.1,v 1.12 2010/10/06 06:43:26 dholland Exp $
|
||||||
|
.\"
|
||||||
|
.\" Copyright (c) 1991, 1993
|
||||||
|
.\" The Regents of the University of California. All rights reserved.
|
||||||
|
.\"
|
||||||
|
.\" This code is derived from software contributed to Berkeley by
|
||||||
|
.\" the Institute of Electrical and Electronics Engineers, 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. 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.
|
||||||
|
.\"
|
||||||
|
.\" @(#)uniq.1 8.1 (Berkeley) 6/6/93
|
||||||
|
.\"
|
||||||
|
.Dd January 6, 2007
|
||||||
|
.Dt UNIQ 1
|
||||||
|
.Os
|
||||||
|
.Sh NAME
|
||||||
|
.Nm uniq
|
||||||
|
.Nd report or filter out repeated lines in a file
|
||||||
|
.Sh SYNOPSIS
|
||||||
|
.Nm
|
||||||
|
.Op Fl cdu
|
||||||
|
.Op Fl f Ar fields
|
||||||
|
.Op Fl s Ar chars
|
||||||
|
.Oo
|
||||||
|
.Ar input_file
|
||||||
|
.Op Ar output_file
|
||||||
|
.Oc
|
||||||
|
.Sh DESCRIPTION
|
||||||
|
The
|
||||||
|
.Nm
|
||||||
|
utility reads the standard input comparing adjacent lines, and writes
|
||||||
|
a copy of each unique input line to the standard output.
|
||||||
|
The second and succeeding copies of identical adjacent input lines are
|
||||||
|
not written.
|
||||||
|
Repeated lines in the input will not be detected if they are not adjacent,
|
||||||
|
so it may be necessary to sort the files first.
|
||||||
|
.Pp
|
||||||
|
The following options are available:
|
||||||
|
.Bl -tag -width Ds
|
||||||
|
.It Fl c
|
||||||
|
Precede each output line with the count of the number of times the line
|
||||||
|
occurred in the input, followed by a single space.
|
||||||
|
.It Fl d
|
||||||
|
Don't output lines that are not repeated in the input.
|
||||||
|
.It Fl f Ar fields
|
||||||
|
Ignore the first
|
||||||
|
.Ar fields
|
||||||
|
in each input line when doing comparisons.
|
||||||
|
A field is a string of non-blank characters separated from adjacent fields
|
||||||
|
by blanks.
|
||||||
|
Field numbers are one based, i.e. the first field is field one.
|
||||||
|
.It Fl s Ar chars
|
||||||
|
Ignore the first
|
||||||
|
.Ar chars
|
||||||
|
characters in each input line when doing comparisons.
|
||||||
|
If specified in conjunction with the
|
||||||
|
.Fl f
|
||||||
|
option, the first
|
||||||
|
.Ar chars
|
||||||
|
characters after the first
|
||||||
|
.Ar fields
|
||||||
|
fields will be ignored.
|
||||||
|
Character numbers are one based, i.e. the first character is character one.
|
||||||
|
.It Fl u
|
||||||
|
Don't output lines that are repeated in the input.
|
||||||
|
.\".It Fl Ns Ar n
|
||||||
|
.\"(Deprecated; replaced by
|
||||||
|
.\".Fl f ) .
|
||||||
|
.\"Ignore the first n
|
||||||
|
.\"fields on each input line when doing comparisons,
|
||||||
|
.\"where n is a number.
|
||||||
|
.\"A field is a string of non-blank
|
||||||
|
.\"characters separated from adjacent fields
|
||||||
|
.\"by blanks.
|
||||||
|
.\".It Cm \&\(pl Ns Ar n
|
||||||
|
.\"(Deprecated; replaced by
|
||||||
|
.\".Fl s ) .
|
||||||
|
.\"Ignore the first
|
||||||
|
.\".Ar m
|
||||||
|
.\"characters when doing comparisons, where
|
||||||
|
.\".Ar m
|
||||||
|
.\"is a
|
||||||
|
.\"number.
|
||||||
|
.El
|
||||||
|
.Pp
|
||||||
|
If additional arguments are specified on the command line, the first
|
||||||
|
such argument is used as the name of an input file, the second is used
|
||||||
|
as the name of an output file.
|
||||||
|
.Pp
|
||||||
|
The
|
||||||
|
.Nm
|
||||||
|
utility exits 0 on success, and \*[Gt]0 if an error occurs.
|
||||||
|
.Sh COMPATIBILITY
|
||||||
|
The historic
|
||||||
|
.Cm \&\(pl Ns Ar number
|
||||||
|
and
|
||||||
|
.Fl Ns Ar number
|
||||||
|
options have been deprecated but are still supported in this implementation.
|
||||||
|
.Sh SEE ALSO
|
||||||
|
.Xr sort 1
|
||||||
|
.Sh STANDARDS
|
||||||
|
The
|
||||||
|
.Nm
|
||||||
|
utility is expected to be
|
||||||
|
.St -p1003.2
|
||||||
|
compatible.
|
||||||
257
usr.bin/uniq/uniq.c
Normal file
257
usr.bin/uniq/uniq.c
Normal file
|
|
@ -0,0 +1,257 @@
|
||||||
|
/* $NetBSD: uniq.c,v 1.17 2010/10/06 07:59:18 wiz Exp $ */
|
||||||
|
|
||||||
|
/*
|
||||||
|
* 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. 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.
|
||||||
|
*/
|
||||||
|
|
||||||
|
#include <sys/cdefs.h>
|
||||||
|
#ifndef lint
|
||||||
|
__COPYRIGHT("@(#) Copyright (c) 1989, 1993\
|
||||||
|
The Regents of the University of California. All rights reserved.");
|
||||||
|
#endif /* not lint */
|
||||||
|
|
||||||
|
#ifndef lint
|
||||||
|
#if 0
|
||||||
|
static char sccsid[] = "@(#)uniq.c 8.3 (Berkeley) 5/4/95";
|
||||||
|
#endif
|
||||||
|
__RCSID("$NetBSD: uniq.c,v 1.17 2010/10/06 07:59:18 wiz Exp $");
|
||||||
|
#endif /* not lint */
|
||||||
|
|
||||||
|
#include <err.h>
|
||||||
|
#include <errno.h>
|
||||||
|
#include <stdio.h>
|
||||||
|
#include <ctype.h>
|
||||||
|
#include <stdlib.h>
|
||||||
|
#include <string.h>
|
||||||
|
#include <unistd.h>
|
||||||
|
|
||||||
|
static int cflag, dflag, uflag;
|
||||||
|
static int numchars, numfields, repeats;
|
||||||
|
|
||||||
|
static FILE *file(const char *, const char *);
|
||||||
|
static void show(FILE *, const char *);
|
||||||
|
static const char *skip(const char *);
|
||||||
|
static void obsolete(char *[]);
|
||||||
|
static void usage(void) __dead;
|
||||||
|
|
||||||
|
int
|
||||||
|
main (int argc, char *argv[])
|
||||||
|
{
|
||||||
|
const char *t1, *t2;
|
||||||
|
FILE *ifp, *ofp;
|
||||||
|
int ch;
|
||||||
|
char *prevline, *thisline, *p;
|
||||||
|
size_t prevlinesize, thislinesize, psize;
|
||||||
|
|
||||||
|
setprogname(argv[0]);
|
||||||
|
ifp = ofp = NULL;
|
||||||
|
obsolete(argv);
|
||||||
|
while ((ch = getopt(argc, argv, "-cdf:s:u")) != -1)
|
||||||
|
switch (ch) {
|
||||||
|
case '-':
|
||||||
|
--optind;
|
||||||
|
goto done;
|
||||||
|
case 'c':
|
||||||
|
cflag = 1;
|
||||||
|
break;
|
||||||
|
case 'd':
|
||||||
|
dflag = 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();
|
||||||
|
}
|
||||||
|
|
||||||
|
done: argc -= optind;
|
||||||
|
argv +=optind;
|
||||||
|
|
||||||
|
switch(argc) {
|
||||||
|
case 0:
|
||||||
|
ifp = stdin;
|
||||||
|
ofp = stdout;
|
||||||
|
break;
|
||||||
|
case 1:
|
||||||
|
ifp = file(argv[0], "r");
|
||||||
|
ofp = stdout;
|
||||||
|
break;
|
||||||
|
case 2:
|
||||||
|
ifp = file(argv[0], "r");
|
||||||
|
ofp = file(argv[1], "w");
|
||||||
|
break;
|
||||||
|
default:
|
||||||
|
usage();
|
||||||
|
}
|
||||||
|
|
||||||
|
if ((p = fgetln(ifp, &psize)) == NULL)
|
||||||
|
return 0;
|
||||||
|
prevlinesize = psize;
|
||||||
|
if ((prevline = malloc(prevlinesize + 1)) == NULL)
|
||||||
|
err(1, "malloc");
|
||||||
|
(void)memcpy(prevline, p, prevlinesize);
|
||||||
|
prevline[prevlinesize] = '\0';
|
||||||
|
|
||||||
|
thislinesize = psize;
|
||||||
|
if ((thisline = malloc(thislinesize + 1)) == NULL)
|
||||||
|
err(1, "malloc");
|
||||||
|
|
||||||
|
while ((p = fgetln(ifp, &psize)) != NULL) {
|
||||||
|
if (psize > thislinesize) {
|
||||||
|
if ((thisline = realloc(thisline, psize + 1)) == NULL)
|
||||||
|
err(1, "realloc");
|
||||||
|
thislinesize = psize;
|
||||||
|
}
|
||||||
|
(void)memcpy(thisline, p, psize);
|
||||||
|
thisline[psize] = '\0';
|
||||||
|
|
||||||
|
/* 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 (strcmp(t1, t2)) {
|
||||||
|
char *t;
|
||||||
|
size_t ts;
|
||||||
|
|
||||||
|
show(ofp, prevline);
|
||||||
|
t = prevline;
|
||||||
|
prevline = thisline;
|
||||||
|
thisline = t;
|
||||||
|
ts = prevlinesize;
|
||||||
|
prevlinesize = thislinesize;
|
||||||
|
thislinesize = ts;
|
||||||
|
repeats = 0;
|
||||||
|
} else
|
||||||
|
++repeats;
|
||||||
|
}
|
||||||
|
show(ofp, prevline);
|
||||||
|
free(prevline);
|
||||||
|
free(thisline);
|
||||||
|
return 0;
|
||||||
|
}
|
||||||
|
|
||||||
|
/*
|
||||||
|
* show --
|
||||||
|
* Output a line depending on the flags and number of repetitions
|
||||||
|
* of the line.
|
||||||
|
*/
|
||||||
|
static void
|
||||||
|
show(FILE *ofp, const char *str)
|
||||||
|
{
|
||||||
|
|
||||||
|
if ((dflag && repeats == 0) || (uflag && repeats > 0))
|
||||||
|
return;
|
||||||
|
if (cflag) {
|
||||||
|
(void)fprintf(ofp, "%4d %s", repeats + 1, str);
|
||||||
|
} else {
|
||||||
|
(void)fprintf(ofp, "%s", str);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
static const char *
|
||||||
|
skip(const char *str)
|
||||||
|
{
|
||||||
|
int infield, nchars, nfields;
|
||||||
|
|
||||||
|
for (nfields = numfields, infield = 0; nfields && *str; ++str)
|
||||||
|
if (isspace((unsigned char)*str)) {
|
||||||
|
if (infield) {
|
||||||
|
infield = 0;
|
||||||
|
--nfields;
|
||||||
|
}
|
||||||
|
} else if (!infield)
|
||||||
|
infield = 1;
|
||||||
|
for (nchars = numchars; nchars-- && *str; ++str)
|
||||||
|
continue;
|
||||||
|
return str;
|
||||||
|
}
|
||||||
|
|
||||||
|
static FILE *
|
||||||
|
file(const char *name, const char *mode)
|
||||||
|
{
|
||||||
|
FILE *fp;
|
||||||
|
|
||||||
|
if ((fp = fopen(name, mode)) == NULL)
|
||||||
|
err(1, "%s", name);
|
||||||
|
return(fp);
|
||||||
|
}
|
||||||
|
|
||||||
|
static void
|
||||||
|
obsolete(char *argv[])
|
||||||
|
{
|
||||||
|
char *ap, *p, *start;
|
||||||
|
|
||||||
|
while ((ap = *++argv) != NULL) {
|
||||||
|
/* 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.
|
||||||
|
*/
|
||||||
|
(void)asprintf(&p, "-%c%s", ap[0] == '+' ? 's' : 'f', ap + 1);
|
||||||
|
if (!p)
|
||||||
|
err(1, "malloc");
|
||||||
|
start = p;
|
||||||
|
*argv = start;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
static void
|
||||||
|
usage(void)
|
||||||
|
{
|
||||||
|
(void)fprintf(stderr, "Usage: %s [-cdu] [-f fields] [-s chars] "
|
||||||
|
"[input [output]]\n", getprogname());
|
||||||
|
exit(1);
|
||||||
|
}
|
||||||
Loading…
Reference in a new issue