split.c revision 97332 
1/*
2 * Copyright (c) 1987, 1993, 1994
3 *	The Regents of the University of California.  All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
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 * 3. All advertising materials mentioning features or use of this software
14 *    must display the following acknowledgement:
15 *	This product includes software developed by the University of
16 *	California, Berkeley and its contributors.
17 * 4. Neither the name of the University nor the names of its contributors
18 *    may be used to endorse or promote products derived from this software
19 *    without specific prior written permission.
20 *
21 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
22 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
23 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
24 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
25 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
26 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
27 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
28 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
29 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
30 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
31 * SUCH DAMAGE.
32 */
33
34#include <sys/cdefs.h>
35__FBSDID("$FreeBSD: head/usr.bin/split/split.c 97332 2002-05-27 04:59:46Z tjr $");
36
37#ifndef lint
38static const char copyright[] =
39"@(#) Copyright (c) 1987, 1993, 1994\n\
40	The Regents of the University of California.  All rights reserved.\n";
41#endif
42
43#ifndef lint
44static const char sccsid[] = "@(#)split.c	8.2 (Berkeley) 4/16/94";
45#endif
46
47#include <sys/param.h>
48#include <sys/types.h>
49
50#include <ctype.h>
51#include <err.h>
52#include <fcntl.h>
53#include <stdio.h>
54#include <stdlib.h>
55#include <string.h>
56#include <unistd.h>
57#include <regex.h>
58#include <sysexits.h>
59
60#define DEFLINE	1000			/* Default num lines per file. */
61
62int	 bytecnt;			/* Byte count to split on. */
63long	 numlines;			/* Line count to split on. */
64int	 file_open;			/* If a file open. */
65int	 ifd = -1, ofd = -1;		/* Input/output file descriptors. */
66char	 bfr[MAXBSIZE];			/* I/O buffer. */
67char	 fname[MAXPATHLEN];		/* File name prefix. */
68regex_t	 rgx;
69int	 pflag;
70long	 sufflen = 2;			/* File name suffix length. */
71
72void newfile(void);
73void split1(void);
74void split2(void);
75static void usage(void);
76
77int
78main(argc, argv)
79	int argc;
80	char *argv[];
81{
82	int ch;
83	char *ep, *p;
84
85	while ((ch = getopt(argc, argv, "-0123456789a:b:l:p:")) != -1)
86		switch (ch) {
87		case '0': case '1': case '2': case '3': case '4':
88		case '5': case '6': case '7': case '8': case '9':
89			/*
90			 * Undocumented kludge: split was originally designed
91			 * to take a number after a dash.
92			 */
93			if (numlines == 0) {
94				p = argv[optind - 1];
95				if (p[0] == '-' && p[1] == ch && !p[2])
96					numlines = strtol(++p, &ep, 10);
97				else
98					numlines =
99					    strtol(argv[optind] + 1, &ep, 10);
100				if (numlines <= 0 || *ep)
101					errx(EX_USAGE,
102					    "%s: illegal line count", optarg);
103			}
104			break;
105		case '-':		/* Undocumented: historic stdin flag. */
106			if (ifd != -1)
107				usage();
108			ifd = 0;
109			break;
110		case 'a':		/* Suffix length */
111			if ((sufflen = strtol(optarg, &ep, 10)) <= 0 || *ep)
112				errx(EX_USAGE,
113				    "%s: illegal suffix length", optarg);
114			break;
115		case 'b':		/* Byte count. */
116			if ((bytecnt = strtoq(optarg, &ep, 10)) <= 0 ||
117			    (*ep != '\0' && *ep != 'k' && *ep != 'm'))
118				errx(EX_USAGE,
119				    "%s: illegal byte count", optarg);
120			if (*ep == 'k')
121				bytecnt *= 1024;
122			else if (*ep == 'm')
123				bytecnt *= 1048576;
124			break;
125		case 'p' :      /* pattern matching. */
126			if (regcomp(&rgx, optarg, REG_EXTENDED|REG_NOSUB) != 0)
127				errx(EX_USAGE, "%s: illegal regexp", optarg);
128			pflag = 1;
129			break;
130		case 'l':		/* Line count. */
131			if (numlines != 0)
132				usage();
133			if ((numlines = strtol(optarg, &ep, 10)) <= 0 || *ep)
134				errx(EX_USAGE,
135				    "%s: illegal line count", optarg);
136			break;
137		default:
138			usage();
139		}
140	argv += optind;
141	argc -= optind;
142
143	if (*argv != NULL)
144		if (ifd == -1) {		/* Input file. */
145			if ((ifd = open(*argv, O_RDONLY, 0)) < 0)
146				err(EX_NOINPUT, "%s", *argv);
147			++argv;
148		}
149	if (*argv != NULL)			/* File name prefix. */
150		if (strlcpy(fname, *argv++, sizeof(fname)) >= sizeof(fname))
151			errx(EX_USAGE, "file name prefix is too long");
152	if (*argv != NULL)
153		usage();
154
155	if (strlen(fname) + (unsigned long)sufflen >= sizeof(fname))
156		errx(EX_USAGE, "suffix is too long");
157	if (pflag && (numlines != 0 || bytecnt != 0))
158		usage();
159
160	if (numlines == 0)
161		numlines = DEFLINE;
162	else if (bytecnt != 0)
163		usage();
164
165	if (ifd == -1)				/* Stdin by default. */
166		ifd = 0;
167
168	if (bytecnt) {
169		split1();
170		exit (0);
171	}
172	split2();
173	if (pflag)
174		regfree(&rgx);
175	exit(0);
176}
177
178/*
179 * split1 --
180 *	Split the input by bytes.
181 */
182void
183split1()
184{
185	size_t bcnt;
186	char *C;
187	int dist, len;
188
189	for (bcnt = 0;;)
190		switch ((len = read(ifd, bfr, MAXBSIZE))) {
191		case 0:
192			exit(0);
193		case -1:
194			err(EX_IOERR, "read");
195			/* NOTREACHED */
196		default:
197			if (!file_open)
198				newfile();
199			if (bcnt + len >= (u_int)bytecnt) {
200				dist = bytecnt - bcnt;
201				if (write(ofd, bfr, dist) != dist)
202					err(EX_IOERR, "write");
203				len -= dist;
204				for (C = bfr + dist; len >= bytecnt;
205				    len -= bytecnt, C += bytecnt) {
206					newfile();
207					if (write(ofd,
208					    C, bytecnt) != bytecnt)
209						err(EX_IOERR, "write");
210				}
211				if (len != 0) {
212					newfile();
213					if (write(ofd, C, len) != len)
214						err(EX_IOERR, "write");
215				} else
216					file_open = 0;
217				bcnt = len;
218			} else {
219				bcnt += len;
220				if (write(ofd, bfr, len) != len)
221					err(EX_IOERR, "write");
222			}
223		}
224}
225
226/*
227 * split2 --
228 *	Split the input by lines.
229 */
230void
231split2()
232{
233	long lcnt = 0;
234	FILE *infp;
235
236	/* Stick a stream on top of input file descriptor */
237	if ((infp = fdopen(ifd, "r")) == NULL)
238		err(EX_NOINPUT, "fdopen");
239
240	/* Process input one line at a time */
241	while (fgets(bfr, sizeof(bfr), infp) != NULL) {
242		const int len = strlen(bfr);
243
244		/* If line is too long to deal with, just write it out */
245		if (bfr[len - 1] != '\n')
246			goto writeit;
247
248		/* Check if we need to start a new file */
249		if (pflag) {
250			regmatch_t pmatch;
251
252			pmatch.rm_so = 0;
253			pmatch.rm_eo = len - 1;
254			if (regexec(&rgx, bfr, 0, &pmatch, REG_STARTEND) == 0)
255				newfile();
256		} else if (lcnt++ == numlines) {
257			newfile();
258			lcnt = 1;
259		}
260
261writeit:
262		/* Open output file if needed */
263		if (!file_open)
264			newfile();
265
266		/* Write out line */
267		if (write(ofd, bfr, len) != len)
268			err(EX_IOERR, "write");
269	}
270
271	/* EOF or error? */
272	if (ferror(infp))
273		err(EX_IOERR, "read");
274	else
275		exit(0);
276}
277
278/*
279 * newfile --
280 *	Open a new output file.
281 */
282void
283newfile()
284{
285	long i, maxfiles, tfnum;
286	static long fnum;
287	static int defname;
288	static char *fpnt;
289
290	if (ofd == -1) {
291		if (fname[0] == '\0') {
292			fname[0] = 'x';
293			fpnt = fname + 1;
294			defname = 1;
295		} else {
296			fpnt = fname + strlen(fname);
297			defname = 0;
298		}
299		ofd = fileno(stdout);
300	}
301
302	/* maxfiles = 26^sufflen, but don't use libm. */
303	for (maxfiles = 1, i = 0; i < sufflen; i++)
304		if ((maxfiles *= 26) <= 0)
305			errx(EX_USAGE, "suffix is too long (max %ld)", i);
306
307	/*
308	 * Hack to increase max files; original code wandered through
309	 * magic characters.
310	 */
311	if (fnum == maxfiles) {
312		if (!defname || fname[0] == 'z')
313			errx(EX_DATAERR, "too many files");
314		++fname[0];
315		fnum = 0;
316	}
317
318	/* Generate suffix of sufflen letters */
319	tfnum = fnum;
320	i = sufflen - 1;
321	do {
322		fpnt[i] = tfnum % 26 + 'a';
323		tfnum /= 26;
324	} while (i-- > 0);
325	fpnt[sufflen] = '\0';
326
327	++fnum;
328	if (!freopen(fname, "w", stdout))
329		err(EX_IOERR, "%s", fname);
330	file_open = 1;
331}
332
333static void
334usage()
335{
336	(void)fprintf(stderr,
337"usage: split [-a sufflen] [-b byte_count] [-l line_count] [-p pattern]\n");
338	(void)fprintf(stderr,
339"             [file [prefix]]\n");
340	exit(EX_USAGE);
341}
342