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("$FreeBSD$"); 36 37 #ifndef lint 38 static 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 44 static 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 66 off_t bytecnt; /* Byte count to split on. */ 67 long numlines; /* Line count to split on. */ 68 int file_open; /* If a file open. */ 69 int ifd = -1, ofd = -1; /* Input/output file descriptors. */ 70 char bfr[MAXBSIZE]; /* I/O buffer. */ 71 char fname[MAXPATHLEN]; /* File name prefix. */ 72 regex_t rgx; 73 int pflag; 74 long sufflen = 2; /* File name suffix length. */ 75 76 void newfile(void); 77 void split1(void); 78 void split2(void); 79 static void usage(void); 80 81 int 82 main(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) 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; 155 156 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 } 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 */ 197 void 198 split1(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 */ 245 void 246 split2(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 } 275 276 writeit: 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 */ 297 void 298 newfile(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 /* 323 * Hack to increase max files; original code wandered through 324 * magic characters. 325 */ 326 if (fnum == maxfiles) { 327 if (!defname || fname[0] == 'z') 328 errx(EX_DATAERR, "too many files"); 329 ++fname[0]; 330 fnum = 0; 331 } 332 333 /* Generate suffix of sufflen letters */ 334 tfnum = fnum; 335 i = sufflen - 1; 336 do { 337 fpnt[i] = tfnum % 26 + 'a'; 338 tfnum /= 26; 339 } while (i-- > 0); 340 fpnt[sufflen] = '\0'; 341 342 ++fnum; 343 if (!freopen(fname, "w", stdout)) 344 err(EX_IOERR, "%s", fname); 345 file_open = 1; 346 } 347 348 static void 349 usage(void) 350 { 351 (void)fprintf(stderr, 352 "usage: split [-a sufflen] [-b byte_count] [-l line_count] [-p pattern]\n"); 353 (void)fprintf(stderr, 354 " [file [prefix]]\n"); 355 exit(EX_USAGE); 356 } 357