Annotation of src/usr.bin/split/split.c, Revision 1.8
1.8 ! millert 1: /* $OpenBSD: split.c,v 1.7 2002/12/08 16:50:07 millert Exp $ */
1.1 deraadt 2: /* $NetBSD: split.c,v 1.5 1995/08/31 22:22:05 jtc Exp $ */
3:
4: /*
5: * Copyright (c) 1987, 1993, 1994
6: * The Regents of the University of California. All rights reserved.
7: *
8: * Redistribution and use in source and binary forms, with or without
9: * modification, are permitted provided that the following conditions
10: * are met:
11: * 1. Redistributions of source code must retain the above copyright
12: * notice, this list of conditions and the following disclaimer.
13: * 2. Redistributions in binary form must reproduce the above copyright
14: * notice, this list of conditions and the following disclaimer in the
15: * documentation and/or other materials provided with the distribution.
1.8 ! millert 16: * 3. Neither the name of the University nor the names of its contributors
1.1 deraadt 17: * may be used to endorse or promote products derived from this software
18: * without specific prior written permission.
19: *
20: * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
21: * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
22: * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
23: * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
24: * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
25: * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
26: * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
27: * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
28: * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
29: * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
30: * SUCH DAMAGE.
31: */
32:
33: #ifndef lint
34: static char copyright[] =
35: "@(#) Copyright (c) 1987, 1993, 1994\n\
36: The Regents of the University of California. All rights reserved.\n";
37: #endif /* not lint */
38:
39: #ifndef lint
40: #if 0
41: static char sccsid[] = "@(#)split.c 8.3 (Berkeley) 4/25/94";
1.4 millert 42: #else
1.8 ! millert 43: static char rcsid[] = "$OpenBSD: split.c,v 1.7 2002/12/08 16:50:07 millert Exp $";
1.1 deraadt 44: #endif
45: #endif /* not lint */
46:
47: #include <sys/param.h>
1.4 millert 48: #include <sys/types.h>
1.1 deraadt 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>
1.4 millert 57: #include <regex.h>
58: #include <sysexits.h>
1.1 deraadt 59:
60: #define DEFLINE 1000 /* Default num lines per file. */
61:
62: long bytecnt; /* Byte count to split on. */
63: long numlines; /* Line count to split on. */
64: int file_open; /* If a file open. */
65: int ifd = -1, ofd = -1; /* Input/output file descriptors. */
66: char bfr[MAXBSIZE]; /* I/O buffer. */
67: char fname[MAXPATHLEN]; /* File name prefix. */
1.4 millert 68: regex_t rgx;
69: int pflag;
1.1 deraadt 70:
1.6 millert 71: void newfile(void);
72: void split1(void);
73: void split2(void);
74: void usage(void);
1.1 deraadt 75:
76: int
77: main(argc, argv)
78: int argc;
79: char *argv[];
80: {
81: int ch;
82: char *ep, *p;
83:
1.7 millert 84: while ((ch = getopt(argc, argv, "0123456789b:l:p:-")) != -1)
1.1 deraadt 85: switch (ch) {
86: case '0': case '1': case '2': case '3': case '4':
87: case '5': case '6': case '7': case '8': case '9':
88: /*
89: * Undocumented kludge: split was originally designed
90: * to take a number after a dash.
91: */
92: if (numlines == 0) {
93: p = argv[optind - 1];
94: if (p[0] == '-' && p[1] == ch && !p[2])
95: numlines = strtol(++p, &ep, 10);
96: else
97: numlines =
98: strtol(argv[optind] + 1, &ep, 10);
99: if (numlines <= 0 || *ep)
1.4 millert 100: errx(EX_USAGE,
101: "%s: illegal line count", optarg);
1.1 deraadt 102: }
103: break;
104: case '-': /* Undocumented: historic stdin flag. */
105: if (ifd != -1)
106: usage();
107: ifd = 0;
108: break;
109: case 'b': /* Byte count. */
110: if ((bytecnt = strtol(optarg, &ep, 10)) <= 0 ||
1.4 millert 111: (*ep != '\0' && *ep != 'k' && *ep != 'm'))
112: errx(EX_USAGE,
113: "%s: illegal byte count", optarg);
1.1 deraadt 114: if (*ep == 'k')
115: bytecnt *= 1024;
116: else if (*ep == 'm')
117: bytecnt *= 1048576;
118: break;
1.4 millert 119: case 'p' : /* pattern matching. */
120: if (regcomp(&rgx, optarg, REG_EXTENDED|REG_NOSUB) != 0)
121: errx(EX_USAGE, "%s: illegal regexp", optarg);
122: pflag = 1;
123: break;
1.1 deraadt 124: case 'l': /* Line count. */
125: if (numlines != 0)
126: usage();
127: if ((numlines = strtol(optarg, &ep, 10)) <= 0 || *ep)
1.4 millert 128: errx(EX_USAGE,
129: "%s: illegal line count", optarg);
1.1 deraadt 130: break;
131: default:
132: usage();
133: }
134: argv += optind;
135: argc -= optind;
136:
137: if (*argv != NULL)
138: if (ifd == -1) { /* Input file. */
139: if ((ifd = open(*argv, O_RDONLY, 0)) < 0)
1.4 millert 140: err(EX_NOINPUT, "%s", *argv);
1.1 deraadt 141: ++argv;
142: }
143: if (*argv != NULL) /* File name prefix. */
1.5 deraadt 144: (void)strlcpy(fname, *argv++, sizeof(fname));
1.1 deraadt 145: if (*argv != NULL)
146: usage();
147:
1.4 millert 148: if (pflag && (numlines != 0 || bytecnt != 0))
149: usage();
150:
1.1 deraadt 151: if (numlines == 0)
152: numlines = DEFLINE;
1.4 millert 153: else if (bytecnt != 0)
1.1 deraadt 154: usage();
155:
156: if (ifd == -1) /* Stdin by default. */
157: ifd = 0;
158:
159: if (bytecnt) {
160: split1();
161: exit (0);
162: }
163: split2();
1.4 millert 164: if (pflag)
165: regfree(&rgx);
1.1 deraadt 166: exit(0);
167: }
168:
169: /*
170: * split1 --
171: * Split the input by bytes.
172: */
173: void
174: split1()
175: {
176: long bcnt;
177: int dist, len;
178: char *C;
179:
180: for (bcnt = 0;;)
1.4 millert 181: switch ((len = read(ifd, bfr, MAXBSIZE))) {
1.1 deraadt 182: case 0:
183: exit(0);
184: case -1:
1.4 millert 185: err(EX_IOERR, "read");
1.1 deraadt 186: /* NOTREACHED */
187: default:
1.4 millert 188: if (!file_open)
1.1 deraadt 189: newfile();
190: if (bcnt + len >= bytecnt) {
191: dist = bytecnt - bcnt;
192: if (write(ofd, bfr, dist) != dist)
1.4 millert 193: err(EX_IOERR, "write");
1.1 deraadt 194: len -= dist;
195: for (C = bfr + dist; len >= bytecnt;
196: len -= bytecnt, C += bytecnt) {
197: newfile();
198: if (write(ofd,
199: C, (int)bytecnt) != bytecnt)
1.4 millert 200: err(EX_IOERR, "write");
1.1 deraadt 201: }
1.4 millert 202: if (len != 0) {
1.1 deraadt 203: newfile();
204: if (write(ofd, C, len) != len)
1.4 millert 205: err(EX_IOERR, "write");
1.1 deraadt 206: } else
207: file_open = 0;
208: bcnt = len;
209: } else {
210: bcnt += len;
211: if (write(ofd, bfr, len) != len)
1.4 millert 212: err(EX_IOERR, "write");
1.1 deraadt 213: }
214: }
215: }
216:
217: /*
218: * split2 --
219: * Split the input by lines.
220: */
221: void
222: split2()
223: {
1.4 millert 224: long lcnt = 0;
225: FILE *infp;
1.1 deraadt 226:
1.4 millert 227: /* Stick a stream on top of input file descriptor */
228: if ((infp = fdopen(ifd, "r")) == NULL)
229: err(EX_NOINPUT, "fdopen");
230:
231: /* Process input one line at a time */
232: while (fgets(bfr, sizeof(bfr), infp) != NULL) {
233: const int len = strlen(bfr);
234:
235: /* If line is too long to deal with, just write it out */
236: if (bfr[len - 1] != '\n')
237: goto writeit;
238:
239: /* Check if we need to start a new file */
240: if (pflag) {
241: regmatch_t pmatch;
242:
243: pmatch.rm_so = 0;
244: pmatch.rm_eo = len - 1;
245: if (regexec(&rgx, bfr, 0, &pmatch, REG_STARTEND) == 0)
1.1 deraadt 246: newfile();
1.4 millert 247: } else if (lcnt++ == numlines) {
248: newfile();
249: lcnt = 1;
1.1 deraadt 250: }
1.4 millert 251:
252: writeit:
253: /* Open output file if needed */
254: if (!file_open)
255: newfile();
256:
257: /* Write out line */
258: if (write(ofd, bfr, len) != len)
259: err(EX_IOERR, "write");
260: }
261:
262: /* EOF or error? */
263: if (ferror(infp))
264: err(EX_IOERR, "read");
265: else
266: exit(0);
1.1 deraadt 267: }
268:
269: /*
270: * newfile --
271: * Open a new output file.
272: */
273: void
274: newfile()
275: {
276: static long fnum;
277: static int defname;
278: static char *fpnt;
279:
280: if (ofd == -1) {
281: if (fname[0] == '\0') {
282: fname[0] = 'x';
283: fpnt = fname + 1;
284: defname = 1;
285: } else {
286: fpnt = fname + strlen(fname);
287: defname = 0;
288: }
289: ofd = fileno(stdout);
290: }
291: /*
292: * Hack to increase max files; original code wandered through
293: * magic characters. Maximum files is 3 * 26 * 26 == 2028
294: */
295: #define MAXFILES 676
296: if (fnum == MAXFILES) {
297: if (!defname || fname[0] == 'z')
1.4 millert 298: errx(EX_DATAERR, "too many files");
1.1 deraadt 299: ++fname[0];
300: fnum = 0;
301: }
302: fpnt[0] = fnum / 26 + 'a';
303: fpnt[1] = fnum % 26 + 'a';
304: ++fnum;
305: if (!freopen(fname, "w", stdout))
1.4 millert 306: err(EX_IOERR, "%s", fname);
307: file_open = 1;
1.1 deraadt 308: }
309:
310: void
311: usage()
312: {
1.4 millert 313: extern char *__progname;
314:
1.1 deraadt 315: (void)fprintf(stderr,
1.4 millert 316: "usage: %s [-b byte_count] [-l line_count] [-p pattern] [file [prefix]]\n",
317: __progname);
318: exit(EX_USAGE);
1.1 deraadt 319: }