freebsd-skq/usr.bin/split/split.c
keramida cd184a0ca1 Add support for splitting at gigabyte boundaries. [1]
Also make both lowercase and uppercase suffix letters work
as byte-count suffixes, i.e. the following two commands are
equivalent now:

    % split -b 4m foo
    % split -b 4M foo

Submitted by:		Roman Divacky [1]
Lots of help by:	cperciva
Reviewed by:		cperciva
MFC after:		1 week
2006-08-10 10:41:47 +00:00

344 lines
8.4 KiB
C

/*
* Copyright (c) 1987, 1993, 1994
* The Regents of the University of California. All rights reserved.
*
* 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.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#ifndef lint
static const char copyright[] =
"@(#) Copyright (c) 1987, 1993, 1994\n\
The Regents of the University of California. All rights reserved.\n";
#endif
#ifndef lint
static const char sccsid[] = "@(#)split.c 8.2 (Berkeley) 4/16/94";
#endif
#include <sys/param.h>
#include <ctype.h>
#include <err.h>
#include <errno.h>
#include <fcntl.h>
#include <inttypes.h>
#include <limits.h>
#include <locale.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <regex.h>
#include <sysexits.h>
#define DEFLINE 1000 /* Default num lines per file. */
off_t bytecnt; /* Byte count to split on. */
long numlines; /* Line count to split on. */
int file_open; /* If a file open. */
int ifd = -1, ofd = -1; /* Input/output file descriptors. */
char bfr[MAXBSIZE]; /* I/O buffer. */
char fname[MAXPATHLEN]; /* File name prefix. */
regex_t rgx;
int pflag;
long sufflen = 2; /* File name suffix length. */
void newfile(void);
void split1(void);
void split2(void);
static void usage(void);
int
main(int argc, char **argv)
{
intmax_t bytecnti;
long scale;
int ch;
char *ep, *p;
setlocale(LC_ALL, "");
while ((ch = getopt(argc, argv, "0123456789a:b:l:p:")) != -1)
switch (ch) {
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
/*
* Undocumented kludge: split was originally designed
* to take a number after a dash.
*/
if (numlines == 0) {
p = argv[optind - 1];
if (p[0] == '-' && p[1] == ch && !p[2])
numlines = strtol(++p, &ep, 10);
else
numlines =
strtol(argv[optind] + 1, &ep, 10);
if (numlines <= 0 || *ep)
errx(EX_USAGE,
"%s: illegal line count", optarg);
}
break;
case 'a': /* Suffix length */
if ((sufflen = strtol(optarg, &ep, 10)) <= 0 || *ep)
errx(EX_USAGE,
"%s: illegal suffix length", optarg);
break;
case 'b': /* Byte count. */
errno = 0;
if ((bytecnti = strtoimax(optarg, &ep, 10)) <= 0 ||
strchr("kKmMgG", *ep) == NULL || errno != 0)
errx(EX_USAGE,
"%s: illegal byte count", optarg);
if (*ep == 'k' || *ep == 'K')
scale = 1024;
else if (*ep == 'm' || *ep == 'M')
scale = 1024 * 1024;
else if (*ep == 'g' || *ep == 'G')
scale = 1024 * 1024 * 1024;
else
scale = 1;
if (bytecnti > OFF_MAX / scale)
errx(EX_USAGE, "%s: offset too large", optarg);
bytecnt = (off_t)(bytecnti * scale);
break;
case 'l': /* Line count. */
if (numlines != 0)
usage();
if ((numlines = strtol(optarg, &ep, 10)) <= 0 || *ep)
errx(EX_USAGE,
"%s: illegal line count", optarg);
break;
case 'p': /* pattern matching. */
if (regcomp(&rgx, optarg, REG_EXTENDED|REG_NOSUB) != 0)
errx(EX_USAGE, "%s: illegal regexp", optarg);
pflag = 1;
break;
default:
usage();
}
argv += optind;
argc -= optind;
if (*argv != NULL) { /* Input file. */
if (strcmp(*argv, "-") == 0)
ifd = STDIN_FILENO;
else if ((ifd = open(*argv, O_RDONLY, 0)) < 0)
err(EX_NOINPUT, "%s", *argv);
++argv;
}
if (*argv != NULL) /* File name prefix. */
if (strlcpy(fname, *argv++, sizeof(fname)) >= sizeof(fname))
errx(EX_USAGE, "file name prefix is too long");
if (*argv != NULL)
usage();
if (strlen(fname) + (unsigned long)sufflen >= sizeof(fname))
errx(EX_USAGE, "suffix is too long");
if (pflag && (numlines != 0 || bytecnt != 0))
usage();
if (numlines == 0)
numlines = DEFLINE;
else if (bytecnt != 0)
usage();
if (ifd == -1) /* Stdin by default. */
ifd = 0;
if (bytecnt) {
split1();
exit (0);
}
split2();
if (pflag)
regfree(&rgx);
exit(0);
}
/*
* split1 --
* Split the input by bytes.
*/
void
split1(void)
{
off_t bcnt;
char *C;
ssize_t dist, len;
for (bcnt = 0;;)
switch ((len = read(ifd, bfr, MAXBSIZE))) {
case 0:
exit(0);
case -1:
err(EX_IOERR, "read");
/* NOTREACHED */
default:
if (!file_open)
newfile();
if (bcnt + len >= bytecnt) {
dist = bytecnt - bcnt;
if (write(ofd, bfr, dist) != dist)
err(EX_IOERR, "write");
len -= dist;
for (C = bfr + dist; len >= bytecnt;
len -= bytecnt, C += bytecnt) {
newfile();
if (write(ofd,
C, bytecnt) != bytecnt)
err(EX_IOERR, "write");
}
if (len != 0) {
newfile();
if (write(ofd, C, len) != len)
err(EX_IOERR, "write");
} else
file_open = 0;
bcnt = len;
} else {
bcnt += len;
if (write(ofd, bfr, len) != len)
err(EX_IOERR, "write");
}
}
}
/*
* split2 --
* Split the input by lines.
*/
void
split2(void)
{
long lcnt = 0;
FILE *infp;
/* Stick a stream on top of input file descriptor */
if ((infp = fdopen(ifd, "r")) == NULL)
err(EX_NOINPUT, "fdopen");
/* Process input one line at a time */
while (fgets(bfr, sizeof(bfr), infp) != NULL) {
const int len = strlen(bfr);
/* If line is too long to deal with, just write it out */
if (bfr[len - 1] != '\n')
goto writeit;
/* Check if we need to start a new file */
if (pflag) {
regmatch_t pmatch;
pmatch.rm_so = 0;
pmatch.rm_eo = len - 1;
if (regexec(&rgx, bfr, 0, &pmatch, REG_STARTEND) == 0)
newfile();
} else if (lcnt++ == numlines) {
newfile();
lcnt = 1;
}
writeit:
/* Open output file if needed */
if (!file_open)
newfile();
/* Write out line */
if (write(ofd, bfr, len) != len)
err(EX_IOERR, "write");
}
/* EOF or error? */
if (ferror(infp))
err(EX_IOERR, "read");
else
exit(0);
}
/*
* newfile --
* Open a new output file.
*/
void
newfile(void)
{
long i, maxfiles, tfnum;
static long fnum;
static int defname;
static char *fpnt;
if (ofd == -1) {
if (fname[0] == '\0') {
fname[0] = 'x';
fpnt = fname + 1;
defname = 1;
} else {
fpnt = fname + strlen(fname);
defname = 0;
}
ofd = fileno(stdout);
}
/* maxfiles = 26^sufflen, but don't use libm. */
for (maxfiles = 1, i = 0; i < sufflen; i++)
if ((maxfiles *= 26) <= 0)
errx(EX_USAGE, "suffix is too long (max %ld)", i);
if (fnum == maxfiles)
errx(EX_DATAERR, "too many files");
/* Generate suffix of sufflen letters */
tfnum = fnum;
i = sufflen - 1;
do {
fpnt[i] = tfnum % 26 + 'a';
tfnum /= 26;
} while (i-- > 0);
fpnt[sufflen] = '\0';
++fnum;
if (!freopen(fname, "w", stdout))
err(EX_IOERR, "%s", fname);
file_open = 1;
}
static void
usage(void)
{
(void)fprintf(stderr,
"usage: split [-l line_count] [-a suffix_length] [file [prefix]]\n"
" split -b byte_count[K|k|M|m|G|g] [-a suffix_length] [file [prefix]]\n"
" split -p pattern [-a suffix_length] [file [prefix]]\n");
exit(EX_USAGE);
}