2 * Copyright (c) 1987, 1993, 1994
3 * The Regents of the University of California. All rights reserved.
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
8 * 1. Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 * notice, this list of conditions and the following disclaimer in the
12 * documentation and/or other materials provided with the distribution.
13 * 4. Neither the name of the University nor the names of its contributors
14 * may be used to endorse or promote products derived from this software
15 * without specific prior written permission.
17 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
18 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
19 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
20 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
21 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
22 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
23 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
24 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
25 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
26 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
29 * @(#) Copyright (c) 1987, 1993, 1994 The Regents of the University of California. All rights reserved.
30 * @(#)split.c 8.2 (Berkeley) 4/16/94
31 * $FreeBSD: src/usr.bin/split/split.c,v 1.6.2.2 2002/07/25 12:46:36 tjr Exp $
34 #include <sys/param.h>
48 #define DEFLINE 1000 /* Default num lines per file. */
50 off_t bytecnt
; /* Byte count to split on. */
51 long numlines
; /* Line count to split on. */
52 int file_open
; /* If a file open. */
53 int ifd
= -1, ofd
= -1; /* Input/output file descriptors. */
54 char *bfr
; /* I/O buffer. */
55 char fname
[MAXPATHLEN
]; /* File name prefix. */
58 long sufflen
= 2; /* File name suffix length. */
63 static void usage(void);
66 main(int argc
, char **argv
)
73 while ((ch
= getopt(argc
, argv
, "0123456789a:b:l:p:")) != -1)
75 case '0': case '1': case '2': case '3': case '4':
76 case '5': case '6': case '7': case '8': case '9':
78 * Undocumented kludge: split was originally designed
79 * to take a number after a dash.
83 if (p
[0] == '-' && p
[1] == ch
&& !p
[2])
84 numlines
= strtol(++p
, &ep
, 10);
87 strtol(argv
[optind
] + 1, &ep
, 10);
88 if (numlines
<= 0 || *ep
)
90 "%s: illegal line count", optarg
);
93 case 'a': /* Suffix length */
94 if ((sufflen
= strtol(optarg
, &ep
, 10)) <= 0 || *ep
)
96 "%s: illegal suffix length", optarg
);
98 case 'b': /* Byte count. */
100 if ((bytecnti
= strtoll(optarg
, &ep
, 10)) <= 0 ||
101 (*ep
!= '\0' && *ep
!= 'k' && *ep
!= 'm') ||
104 "%s: illegal byte count", optarg
);
111 bytecnt
= (off_t
)(bytecnti
* scale
);
113 case 'p' : /* pattern matching. */
114 if (regcomp(&rgx
, optarg
, REG_EXTENDED
|REG_NOSUB
) != 0)
115 errx(EX_USAGE
, "%s: illegal regexp", optarg
);
118 case 'l': /* Line count. */
121 if ((numlines
= strtol(optarg
, &ep
, 10)) <= 0 || *ep
)
123 "%s: illegal line count", optarg
);
132 if (strcmp(*argv
, "-") == 0)
134 else if ((ifd
= open(*argv
, O_RDONLY
, 0)) < 0)
135 err(EX_NOINPUT
, "%s", *argv
);
139 if (*argv
!= NULL
) /* File name prefix. */
140 if (strlcpy(fname
, *argv
++, sizeof(fname
)) >= sizeof(fname
))
141 errx(EX_USAGE
, "file name prefix is too long");
145 if (strlen(fname
) + (unsigned long)sufflen
>= sizeof(fname
))
146 errx(EX_USAGE
, "suffix is too long");
147 if (pflag
&& (numlines
!= 0 || bytecnt
!= 0))
152 else if (bytecnt
!= 0)
155 if (ifd
== -1) /* Stdin by default. */
170 * Split the input by bytes.
179 if((bfr
= (char *)malloc(bytecnt
)) == NULL
)
180 err(EX_OSERR
, "malloc");
183 switch ((len
= read(ifd
, bfr
, bytecnt
))) {
189 err(EX_IOERR
, "read");
194 if (bcnt
+ len
>= bytecnt
) {
195 dist
= bytecnt
- bcnt
;
196 if (write(ofd
, bfr
, dist
) != dist
)
197 err(EX_IOERR
, "write");
199 for (C
= bfr
+ dist
; len
>= bytecnt
;
200 len
-= bytecnt
, C
+= bytecnt
) {
203 C
, (int)bytecnt
) != bytecnt
) {
205 err(EX_IOERR
, "write");
210 if (write(ofd
, C
, len
) != len
) {
212 err(EX_IOERR
, "write");
219 if (write(ofd
, bfr
, len
) != len
) {
221 err(EX_IOERR
, "write");
230 * Split the input by lines.
239 /* Stick a stream on top of input file descriptor */
240 if ((infp
= fdopen(ifd
, "r")) == NULL
)
241 err(EX_NOINPUT
, "fdopen");
243 if((bfr
= (char *)malloc(MAXBSIZE
)) == NULL
)
244 err(EX_OSERR
, "malloc");
246 /* Process input one line at a time */
247 while (fgets(bfr
, MAXBSIZE
, infp
) != NULL
) {
248 const int len
= strlen(bfr
);
250 /* Consider starting a new file only when at beginning of a line */
252 /* Check if we need to start a new file */
257 pmatch
.rm_eo
= len
- 1;
258 if (regexec(&rgx
, bfr
, 0, &pmatch
, REG_STARTEND
) == 0)
260 } else if (lcnt
++ == numlines
) {
266 if (bfr
[len
- 1] != '\n')
271 /* Open output file if needed */
276 if (write(ofd
, bfr
, len
) != len
) {
278 err(EX_IOERR
, "write");
286 err(EX_IOERR
, "read");
293 * Open a new output file.
298 long i
, maxfiles
, tfnum
;
303 if (fname
[0] == '\0') {
307 fpnt
= fname
+ strlen(fname
);
309 ofd
= fileno(stdout
);
312 /* maxfiles = 26^sufflen, but don't use libm. */
313 for (maxfiles
= 1, i
= 0; i
< sufflen
; i
++)
314 if ((maxfiles
*= 26) <= 0)
315 errx(EX_USAGE
, "suffix is too long (max %ld)", i
);
317 if (fnum
== maxfiles
)
318 errx(EX_DATAERR
, "too many files");
320 /* Generate suffix of sufflen letters */
324 fpnt
[i
] = tfnum
% 26 + 'a';
327 fpnt
[sufflen
] = '\0';
330 if (!freopen(fname
, "w", stdout
))
331 err(EX_IOERR
, "%s", fname
);
338 (void)fprintf(stderr
,
339 "usage: split [-a sufflen] [-b byte_count] [-l line_count] [-p pattern]\n");
340 (void)fprintf(stderr
,
341 " [file [prefix]]\n");