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>
| 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 149345 2005-08-21 06:35:02Z tjr $");
| 35__FBSDID("$FreeBSD: head/usr.bin/split/split.c 149616 2005-08-30 12:32:18Z 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
49#include <ctype.h>
50#include <err.h>
51#include <errno.h>
52#include <fcntl.h>
53#include <inttypes.h>
54#include <limits.h>
55#include <locale.h>
56#include <stdint.h>
57#include <stdio.h>
58#include <stdlib.h>
59#include <string.h>
60#include <unistd.h>
61#include <regex.h>
62#include <sysexits.h>
63
64#define DEFLINE 1000 /* Default num lines per file. */
65
66off_t bytecnt; /* Byte count to split on. */
67long numlines; /* Line count to split on. */
68int file_open; /* If a file open. */
69int ifd = -1, ofd = -1; /* Input/output file descriptors. */
70char bfr[MAXBSIZE]; /* I/O buffer. */
71char fname[MAXPATHLEN]; /* File name prefix. */
72regex_t rgx;
73int pflag;
74long sufflen = 2; /* File name suffix length. */
75
76void newfile(void);
77void split1(void);
78void split2(void);
79static void usage(void);
80
81int
82main(int argc, char **argv)
83{
84 intmax_t bytecnti;
85 long scale;
86 int ch;
87 char *ep, *p;
88
89 setlocale(LC_ALL, "");
90
| 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
49#include <ctype.h>
50#include <err.h>
51#include <errno.h>
52#include <fcntl.h>
53#include <inttypes.h>
54#include <limits.h>
55#include <locale.h>
56#include <stdint.h>
57#include <stdio.h>
58#include <stdlib.h>
59#include <string.h>
60#include <unistd.h>
61#include <regex.h>
62#include <sysexits.h>
63
64#define DEFLINE 1000 /* Default num lines per file. */
65
66off_t bytecnt; /* Byte count to split on. */
67long numlines; /* Line count to split on. */
68int file_open; /* If a file open. */
69int ifd = -1, ofd = -1; /* Input/output file descriptors. */
70char bfr[MAXBSIZE]; /* I/O buffer. */
71char fname[MAXPATHLEN]; /* File name prefix. */
72regex_t rgx;
73int pflag;
74long sufflen = 2; /* File name suffix length. */
75
76void newfile(void);
77void split1(void);
78void split2(void);
79static void usage(void);
80
81int
82main(int argc, char **argv)
83{
84 intmax_t bytecnti;
85 long scale;
86 int ch;
87 char *ep, *p;
88
89 setlocale(LC_ALL, "");
90
|
91 while ((ch = getopt(argc, argv, "-0123456789a:b:l:p:")) != -1)
| 91 while ((ch = getopt(argc, argv, "0123456789a:b:l:p:")) != -1)
|
92 switch (ch) {
93 case '0': case '1': case '2': case '3': case '4':
94 case '5': case '6': case '7': case '8': case '9':
95 /*
96 * Undocumented kludge: split was originally designed
97 * to take a number after a dash.
98 */
99 if (numlines == 0) {
100 p = argv[optind - 1];
101 if (p[0] == '-' && p[1] == ch && !p[2])
102 numlines = strtol(++p, &ep, 10);
103 else
104 numlines =
105 strtol(argv[optind] + 1, &ep, 10);
106 if (numlines <= 0 || *ep)
107 errx(EX_USAGE,
108 "%s: illegal line count", optarg);
109 }
110 break;
| 92 switch (ch) {
93 case '0': case '1': case '2': case '3': case '4':
94 case '5': case '6': case '7': case '8': case '9':
95 /*
96 * Undocumented kludge: split was originally designed
97 * to take a number after a dash.
98 */
99 if (numlines == 0) {
100 p = argv[optind - 1];
101 if (p[0] == '-' && p[1] == ch && !p[2])
102 numlines = strtol(++p, &ep, 10);
103 else
104 numlines =
105 strtol(argv[optind] + 1, &ep, 10);
106 if (numlines <= 0 || *ep)
107 errx(EX_USAGE,
108 "%s: illegal line count", optarg);
109 }
110 break;
|
111 case '-': /* Undocumented: historic stdin flag. */
112 if (ifd != -1)
113 usage();
114 ifd = 0;
115 break;
| |
116 case 'a': /* Suffix length */
117 if ((sufflen = strtol(optarg, &ep, 10)) <= 0 || *ep)
118 errx(EX_USAGE,
119 "%s: illegal suffix length", optarg);
120 break;
121 case 'b': /* Byte count. */
122 errno = 0;
123 if ((bytecnti = strtoimax(optarg, &ep, 10)) <= 0 ||
124 (*ep != '\0' && *ep != 'k' && *ep != 'm') ||
125 errno != 0)
126 errx(EX_USAGE,
127 "%s: illegal byte count", optarg);
128 if (*ep == 'k')
129 scale = 1024;
130 else if (*ep == 'm')
131 scale = 1024 * 1024;
132 else
133 scale = 1;
134 if (bytecnti > OFF_MAX / scale)
135 errx(EX_USAGE, "%s: offset too large", optarg);
136 bytecnt = (off_t)(bytecnti * scale);
137 break;
138 case 'p' : /* pattern matching. */
139 if (regcomp(&rgx, optarg, REG_EXTENDED|REG_NOSUB) != 0)
140 errx(EX_USAGE, "%s: illegal regexp", optarg);
141 pflag = 1;
142 break;
143 case 'l': /* Line count. */
144 if (numlines != 0)
145 usage();
146 if ((numlines = strtol(optarg, &ep, 10)) <= 0 || *ep)
147 errx(EX_USAGE,
148 "%s: illegal line count", optarg);
149 break;
150 default:
151 usage();
152 }
153 argv += optind;
154 argc -= optind;
155
| 111 case 'a': /* Suffix length */
112 if ((sufflen = strtol(optarg, &ep, 10)) <= 0 || *ep)
113 errx(EX_USAGE,
114 "%s: illegal suffix length", optarg);
115 break;
116 case 'b': /* Byte count. */
117 errno = 0;
118 if ((bytecnti = strtoimax(optarg, &ep, 10)) <= 0 ||
119 (*ep != '\0' && *ep != 'k' && *ep != 'm') ||
120 errno != 0)
121 errx(EX_USAGE,
122 "%s: illegal byte count", optarg);
123 if (*ep == 'k')
124 scale = 1024;
125 else if (*ep == 'm')
126 scale = 1024 * 1024;
127 else
128 scale = 1;
129 if (bytecnti > OFF_MAX / scale)
130 errx(EX_USAGE, "%s: offset too large", optarg);
131 bytecnt = (off_t)(bytecnti * scale);
132 break;
133 case 'p' : /* pattern matching. */
134 if (regcomp(&rgx, optarg, REG_EXTENDED|REG_NOSUB) != 0)
135 errx(EX_USAGE, "%s: illegal regexp", optarg);
136 pflag = 1;
137 break;
138 case 'l': /* Line count. */
139 if (numlines != 0)
140 usage();
141 if ((numlines = strtol(optarg, &ep, 10)) <= 0 || *ep)
142 errx(EX_USAGE,
143 "%s: illegal line count", optarg);
144 break;
145 default:
146 usage();
147 }
148 argv += optind;
149 argc -= optind;
150
|
156 if (*argv != NULL)
157 if (ifd == -1) { /* Input file. */
158 if (strcmp(*argv, "-") == 0)
159 ifd = STDIN_FILENO;
160 else if ((ifd = open(*argv, O_RDONLY, 0)) < 0)
161 err(EX_NOINPUT, "%s", *argv);
162 ++argv;
163 }
| 151 if (*argv != NULL) { /* Input file. */
152 if (strcmp(*argv, "-") == 0)
153 ifd = STDIN_FILENO;
154 else if ((ifd = open(*argv, O_RDONLY, 0)) < 0)
155 err(EX_NOINPUT, "%s", *argv);
156 ++argv;
157 }
|
164 if (*argv != NULL) /* File name prefix. */
165 if (strlcpy(fname, *argv++, sizeof(fname)) >= sizeof(fname))
166 errx(EX_USAGE, "file name prefix is too long");
167 if (*argv != NULL)
168 usage();
169
170 if (strlen(fname) + (unsigned long)sufflen >= sizeof(fname))
171 errx(EX_USAGE, "suffix is too long");
172 if (pflag && (numlines != 0 || bytecnt != 0))
173 usage();
174
175 if (numlines == 0)
176 numlines = DEFLINE;
177 else if (bytecnt != 0)
178 usage();
179
180 if (ifd == -1) /* Stdin by default. */
181 ifd = 0;
182
183 if (bytecnt) {
184 split1();
185 exit (0);
186 }
187 split2();
188 if (pflag)
189 regfree(&rgx);
190 exit(0);
191}
192
193/*
194 * split1 --
195 * Split the input by bytes.
196 */
197void
198split1(void)
199{
200 off_t bcnt;
201 char *C;
202 ssize_t dist, len;
203
204 for (bcnt = 0;;)
205 switch ((len = read(ifd, bfr, MAXBSIZE))) {
206 case 0:
207 exit(0);
208 case -1:
209 err(EX_IOERR, "read");
210 /* NOTREACHED */
211 default:
212 if (!file_open)
213 newfile();
214 if (bcnt + len >= bytecnt) {
215 dist = bytecnt - bcnt;
216 if (write(ofd, bfr, dist) != dist)
217 err(EX_IOERR, "write");
218 len -= dist;
219 for (C = bfr + dist; len >= bytecnt;
220 len -= bytecnt, C += bytecnt) {
221 newfile();
222 if (write(ofd,
223 C, bytecnt) != bytecnt)
224 err(EX_IOERR, "write");
225 }
226 if (len != 0) {
227 newfile();
228 if (write(ofd, C, len) != len)
229 err(EX_IOERR, "write");
230 } else
231 file_open = 0;
232 bcnt = len;
233 } else {
234 bcnt += len;
235 if (write(ofd, bfr, len) != len)
236 err(EX_IOERR, "write");
237 }
238 }
239}
240
241/*
242 * split2 --
243 * Split the input by lines.
244 */
245void
246split2(void)
247{
248 long lcnt = 0;
249 FILE *infp;
250
251 /* Stick a stream on top of input file descriptor */
252 if ((infp = fdopen(ifd, "r")) == NULL)
253 err(EX_NOINPUT, "fdopen");
254
255 /* Process input one line at a time */
256 while (fgets(bfr, sizeof(bfr), infp) != NULL) {
257 const int len = strlen(bfr);
258
259 /* If line is too long to deal with, just write it out */
260 if (bfr[len - 1] != '\n')
261 goto writeit;
262
263 /* Check if we need to start a new file */
264 if (pflag) {
265 regmatch_t pmatch;
266
267 pmatch.rm_so = 0;
268 pmatch.rm_eo = len - 1;
269 if (regexec(&rgx, bfr, 0, &pmatch, REG_STARTEND) == 0)
270 newfile();
271 } else if (lcnt++ == numlines) {
272 newfile();
273 lcnt = 1;
274 }
275
276writeit:
277 /* Open output file if needed */
278 if (!file_open)
279 newfile();
280
281 /* Write out line */
282 if (write(ofd, bfr, len) != len)
283 err(EX_IOERR, "write");
284 }
285
286 /* EOF or error? */
287 if (ferror(infp))
288 err(EX_IOERR, "read");
289 else
290 exit(0);
291}
292
293/*
294 * newfile --
295 * Open a new output file.
296 */
297void
298newfile(void)
299{
300 long i, maxfiles, tfnum;
301 static long fnum;
302 static int defname;
303 static char *fpnt;
304
305 if (ofd == -1) {
306 if (fname[0] == '\0') {
307 fname[0] = 'x';
308 fpnt = fname + 1;
309 defname = 1;
310 } else {
311 fpnt = fname + strlen(fname);
312 defname = 0;
313 }
314 ofd = fileno(stdout);
315 }
316
317 /* maxfiles = 26^sufflen, but don't use libm. */
318 for (maxfiles = 1, i = 0; i < sufflen; i++)
319 if ((maxfiles *= 26) <= 0)
320 errx(EX_USAGE, "suffix is too long (max %ld)", i);
321
322 if (fnum == maxfiles)
323 errx(EX_DATAERR, "too many files");
324
325 /* Generate suffix of sufflen letters */
326 tfnum = fnum;
327 i = sufflen - 1;
328 do {
329 fpnt[i] = tfnum % 26 + 'a';
330 tfnum /= 26;
331 } while (i-- > 0);
332 fpnt[sufflen] = '\0';
333
334 ++fnum;
335 if (!freopen(fname, "w", stdout))
336 err(EX_IOERR, "%s", fname);
337 file_open = 1;
338}
339
340static void
341usage(void)
342{
343 (void)fprintf(stderr,
344"usage: split [-a sufflen] [-b byte_count] [-l line_count] [-p pattern]\n");
345 (void)fprintf(stderr,
346" [file [prefix]]\n");
347 exit(EX_USAGE);
348}
| 158 if (*argv != NULL) /* File name prefix. */
159 if (strlcpy(fname, *argv++, sizeof(fname)) >= sizeof(fname))
160 errx(EX_USAGE, "file name prefix is too long");
161 if (*argv != NULL)
162 usage();
163
164 if (strlen(fname) + (unsigned long)sufflen >= sizeof(fname))
165 errx(EX_USAGE, "suffix is too long");
166 if (pflag && (numlines != 0 || bytecnt != 0))
167 usage();
168
169 if (numlines == 0)
170 numlines = DEFLINE;
171 else if (bytecnt != 0)
172 usage();
173
174 if (ifd == -1) /* Stdin by default. */
175 ifd = 0;
176
177 if (bytecnt) {
178 split1();
179 exit (0);
180 }
181 split2();
182 if (pflag)
183 regfree(&rgx);
184 exit(0);
185}
186
187/*
188 * split1 --
189 * Split the input by bytes.
190 */
191void
192split1(void)
193{
194 off_t bcnt;
195 char *C;
196 ssize_t dist, len;
197
198 for (bcnt = 0;;)
199 switch ((len = read(ifd, bfr, MAXBSIZE))) {
200 case 0:
201 exit(0);
202 case -1:
203 err(EX_IOERR, "read");
204 /* NOTREACHED */
205 default:
206 if (!file_open)
207 newfile();
208 if (bcnt + len >= bytecnt) {
209 dist = bytecnt - bcnt;
210 if (write(ofd, bfr, dist) != dist)
211 err(EX_IOERR, "write");
212 len -= dist;
213 for (C = bfr + dist; len >= bytecnt;
214 len -= bytecnt, C += bytecnt) {
215 newfile();
216 if (write(ofd,
217 C, bytecnt) != bytecnt)
218 err(EX_IOERR, "write");
219 }
220 if (len != 0) {
221 newfile();
222 if (write(ofd, C, len) != len)
223 err(EX_IOERR, "write");
224 } else
225 file_open = 0;
226 bcnt = len;
227 } else {
228 bcnt += len;
229 if (write(ofd, bfr, len) != len)
230 err(EX_IOERR, "write");
231 }
232 }
233}
234
235/*
236 * split2 --
237 * Split the input by lines.
238 */
239void
240split2(void)
241{
242 long lcnt = 0;
243 FILE *infp;
244
245 /* Stick a stream on top of input file descriptor */
246 if ((infp = fdopen(ifd, "r")) == NULL)
247 err(EX_NOINPUT, "fdopen");
248
249 /* Process input one line at a time */
250 while (fgets(bfr, sizeof(bfr), infp) != NULL) {
251 const int len = strlen(bfr);
252
253 /* If line is too long to deal with, just write it out */
254 if (bfr[len - 1] != '\n')
255 goto writeit;
256
257 /* Check if we need to start a new file */
258 if (pflag) {
259 regmatch_t pmatch;
260
261 pmatch.rm_so = 0;
262 pmatch.rm_eo = len - 1;
263 if (regexec(&rgx, bfr, 0, &pmatch, REG_STARTEND) == 0)
264 newfile();
265 } else if (lcnt++ == numlines) {
266 newfile();
267 lcnt = 1;
268 }
269
270writeit:
271 /* Open output file if needed */
272 if (!file_open)
273 newfile();
274
275 /* Write out line */
276 if (write(ofd, bfr, len) != len)
277 err(EX_IOERR, "write");
278 }
279
280 /* EOF or error? */
281 if (ferror(infp))
282 err(EX_IOERR, "read");
283 else
284 exit(0);
285}
286
287/*
288 * newfile --
289 * Open a new output file.
290 */
291void
292newfile(void)
293{
294 long i, maxfiles, tfnum;
295 static long fnum;
296 static int defname;
297 static char *fpnt;
298
299 if (ofd == -1) {
300 if (fname[0] == '\0') {
301 fname[0] = 'x';
302 fpnt = fname + 1;
303 defname = 1;
304 } else {
305 fpnt = fname + strlen(fname);
306 defname = 0;
307 }
308 ofd = fileno(stdout);
309 }
310
311 /* maxfiles = 26^sufflen, but don't use libm. */
312 for (maxfiles = 1, i = 0; i < sufflen; i++)
313 if ((maxfiles *= 26) <= 0)
314 errx(EX_USAGE, "suffix is too long (max %ld)", i);
315
316 if (fnum == maxfiles)
317 errx(EX_DATAERR, "too many files");
318
319 /* Generate suffix of sufflen letters */
320 tfnum = fnum;
321 i = sufflen - 1;
322 do {
323 fpnt[i] = tfnum % 26 + 'a';
324 tfnum /= 26;
325 } while (i-- > 0);
326 fpnt[sufflen] = '\0';
327
328 ++fnum;
329 if (!freopen(fname, "w", stdout))
330 err(EX_IOERR, "%s", fname);
331 file_open = 1;
332}
333
334static void
335usage(void)
336{
337 (void)fprintf(stderr,
338"usage: split [-a sufflen] [-b byte_count] [-l line_count] [-p pattern]\n");
339 (void)fprintf(stderr,
340" [file [prefix]]\n");
341 exit(EX_USAGE);
342}
|