summaryrefslogtreecommitdiffstats
path: root/usr.bin/split/split.c
blob: 22818e41cd6d67fd6c09eaf05b85844b49862b3e (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
/*
 * 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 <sys/types.h>
#include <sys/stat.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. */
off_t	 chunks = 0;			/* Chunks count to split into. */
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. */

static void newfile(void);
static void split1(void);
static void split2(void);
static void split3(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:n: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 'n':		/* Chunks. */
			if (!isdigit((unsigned char)optarg[0]) ||
			    (chunks = (size_t)strtoul(optarg, &ep, 10)) == 0 ||
			    *ep != '\0') {
				errx(EX_USAGE, "%s: illegal number of chunks",
				     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 || chunks != 0))
		usage();

	if (numlines == 0)
		numlines = DEFLINE;
	else if (bytecnt != 0 || chunks != 0)
		usage();

	if (bytecnt && chunks)
		usage();

	if (ifd == -1)				/* Stdin by default. */
		ifd = 0;

	if (bytecnt) {
		split1();
		exit (0);
	} else if (chunks) {
		split3();
		exit (0);
	}
	split2();
	if (pflag)
		regfree(&rgx);
	exit(0);
}

/*
 * split1 --
 *	Split the input by bytes.
 */
static void
split1(void)
{
	off_t bcnt;
	char *C;
	ssize_t dist, len;
	int nfiles;

	nfiles = 0;

	for (bcnt = 0;;)
		switch ((len = read(ifd, bfr, MAXBSIZE))) {
		case 0:
			exit(0);
		case -1:
			err(EX_IOERR, "read");
			/* NOTREACHED */
		default:
			if (!file_open) {
				if (!chunks || (nfiles < chunks)) {
					newfile();
					nfiles++;
				}
			}
			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) {
					if (!chunks || (nfiles < chunks)) {
					newfile();
						nfiles++;
					}
					if (write(ofd,
					    C, bytecnt) != bytecnt)
						err(EX_IOERR, "write");
				}
				if (len != 0) {
					if (!chunks || (nfiles < chunks)) {
					newfile();
						nfiles++;
					}
					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.
 */
static 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);
}

/*
 * split3 --
 *	Split the input into specified number of chunks
 */
static void
split3(void)
{
	struct stat sb;

	if (fstat(ifd, &sb) == -1) {
		err(1, "stat");
		/* NOTREACHED */
	}

	if (chunks > sb.st_size) {
		errx(1, "can't split into more than %d files",
		    (int)sb.st_size);
		/* NOTREACHED */
	}

	bytecnt = sb.st_size / chunks;
	split1();
}


/*
 * newfile --
 *	Open a new output file.
 */
static 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 -n chunk_count [-a suffix_length] [file [prefix]]\n"
"       split -p pattern [-a suffix_length] [file [prefix]]\n");
	exit(EX_USAGE);
}
OpenPOWER on IntegriCloud