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 * @(#) Copyright (c) 1987, 1993, 1994 The Regents of the University of California. All rights reserved. 34 * @(#)split.c 8.2 (Berkeley) 4/16/94 35 * $FreeBSD: src/usr.bin/split/split.c,v 1.6.2.2 2002/07/25 12:46:36 tjr Exp $ 36 * $DragonFly: src/usr.bin/split/split.c,v 1.6 2005/08/30 21:19:13 liamfoy Exp $ 37 */ 38 39 #include <sys/param.h> 40 41 #include <ctype.h> 42 #include <err.h> 43 #include <errno.h> 44 #include <fcntl.h> 45 #include <limits.h> 46 #include <stdio.h> 47 #include <stdlib.h> 48 #include <string.h> 49 #include <unistd.h> 50 #include <regex.h> 51 #include <sysexits.h> 52 53 #define DEFLINE 1000 /* Default num lines per file. */ 54 55 off_t bytecnt; /* Byte count to split on. */ 56 long numlines; /* Line count to split on. */ 57 int file_open; /* If a file open. */ 58 int ifd = -1, ofd = -1; /* Input/output file descriptors. */ 59 char *bfr; /* I/O buffer. */ 60 char fname[MAXPATHLEN]; /* File name prefix. */ 61 regex_t rgx; 62 int pflag; 63 long sufflen = 2; /* File name suffix length. */ 64 65 void newfile(void); 66 void split1(void); 67 void split2(void); 68 static void usage(void); 69 70 int 71 main(int argc, char **argv) 72 { 73 long long bytecnti; 74 long scale; 75 int ch; 76 char *ep, *p; 77 78 while ((ch = getopt(argc, argv, "0123456789a:b:l:p:")) != -1) 79 switch (ch) { 80 case '0': case '1': case '2': case '3': case '4': 81 case '5': case '6': case '7': case '8': case '9': 82 /* 83 * Undocumented kludge: split was originally designed 84 * to take a number after a dash. 85 */ 86 if (numlines == 0) { 87 p = argv[optind - 1]; 88 if (p[0] == '-' && p[1] == ch && !p[2]) 89 numlines = strtol(++p, &ep, 10); 90 else 91 numlines = 92 strtol(argv[optind] + 1, &ep, 10); 93 if (numlines <= 0 || *ep) 94 errx(EX_USAGE, 95 "%s: illegal line count", optarg); 96 } 97 break; 98 case 'a': /* Suffix length */ 99 if ((sufflen = strtol(optarg, &ep, 10)) <= 0 || *ep) 100 errx(EX_USAGE, 101 "%s: illegal suffix length", optarg); 102 break; 103 case 'b': /* Byte count. */ 104 errno = 0; 105 if ((bytecnti = strtoll(optarg, &ep, 10)) <= 0 || 106 (*ep != '\0' && *ep != 'k' && *ep != 'm') || 107 errno != 0) 108 errx(EX_USAGE, 109 "%s: illegal byte count", optarg); 110 if (*ep == 'k') 111 scale = 1024; 112 else if (*ep == 'm') 113 scale = 1024 * 1024; 114 else 115 scale = 1; 116 bytecnt = (off_t)(bytecnti * scale); 117 break; 118 case 'p' : /* pattern matching. */ 119 if (regcomp(&rgx, optarg, REG_EXTENDED|REG_NOSUB) != 0) 120 errx(EX_USAGE, "%s: illegal regexp", optarg); 121 pflag = 1; 122 break; 123 case 'l': /* Line count. */ 124 if (numlines != 0) 125 usage(); 126 if ((numlines = strtol(optarg, &ep, 10)) <= 0 || *ep) 127 errx(EX_USAGE, 128 "%s: illegal line count", optarg); 129 break; 130 default: 131 usage(); 132 } 133 argv += optind; 134 argc -= optind; 135 136 if (*argv != NULL) { 137 if (strcmp(*argv, "-") == 0) 138 ifd = STDIN_FILENO; 139 else if ((ifd = open(*argv, O_RDONLY, 0)) < 0) 140 err(EX_NOINPUT, "%s", *argv); 141 ++argv; 142 } 143 144 if (*argv != NULL) /* File name prefix. */ 145 if (strlcpy(fname, *argv++, sizeof(fname)) >= sizeof(fname)) 146 errx(EX_USAGE, "file name prefix is too long"); 147 if (*argv != NULL) 148 usage(); 149 150 if (strlen(fname) + (unsigned long)sufflen >= sizeof(fname)) 151 errx(EX_USAGE, "suffix is too long"); 152 if (pflag && (numlines != 0 || bytecnt != 0)) 153 usage(); 154 155 if (numlines == 0) 156 numlines = DEFLINE; 157 else if (bytecnt != 0) 158 usage(); 159 160 if (ifd == -1) /* Stdin by default. */ 161 ifd = 0; 162 163 if (bytecnt) { 164 split1(); 165 exit (0); 166 } 167 split2(); 168 if (pflag) 169 regfree(&rgx); 170 exit(0); 171 } 172 173 /* 174 * split1 -- 175 * Split the input by bytes. 176 */ 177 void 178 split1(void) 179 { 180 off_t bcnt; 181 char *C; 182 ssize_t dist, len; 183 184 if((bfr = (char *)malloc(bytecnt)) == NULL) 185 err(EX_OSERR, "malloc"); 186 187 for (bcnt = 0;;) 188 switch ((len = read(ifd, bfr, bytecnt))) { 189 case 0: 190 free(bfr); 191 exit(0); 192 case -1: 193 free(bfr); 194 err(EX_IOERR, "read"); 195 /* NOTREACHED */ 196 default: 197 if (!file_open) 198 newfile(); 199 if (bcnt + len >= 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, (int)bytecnt) != bytecnt) { 209 free(bfr); 210 err(EX_IOERR, "write"); 211 } 212 } 213 if (len != 0) { 214 newfile(); 215 if (write(ofd, C, len) != len) { 216 free(bfr); 217 err(EX_IOERR, "write"); 218 } 219 } else 220 file_open = 0; 221 bcnt = len; 222 } else { 223 bcnt += len; 224 if (write(ofd, bfr, len) != len) { 225 free(bfr); 226 err(EX_IOERR, "write"); 227 } 228 } 229 } 230 free(bfr); 231 } 232 233 /* 234 * split2 -- 235 * Split the input by lines. 236 */ 237 void 238 split2(void) 239 { 240 int startofline = 1; 241 long lcnt = 0; 242 FILE *infp; 243 244 /* Stick a stream on top of input file descriptor */ 245 if ((infp = fdopen(ifd, "r")) == NULL) 246 err(EX_NOINPUT, "fdopen"); 247 248 if((bfr = (char *)malloc(MAXBSIZE)) == NULL) 249 err(EX_OSERR, "malloc"); 250 251 /* Process input one line at a time */ 252 while (fgets(bfr, MAXBSIZE, infp) != NULL) { 253 const int len = strlen(bfr); 254 255 /* Consider starting a new file only when at beginning of a line */ 256 if (startofline) { 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 } 270 271 if (bfr[len - 1] != '\n') 272 startofline = 0; 273 else 274 startofline = 1; 275 276 /* Open output file if needed */ 277 if (!file_open) 278 newfile(); 279 280 /* Write out line */ 281 if (write(ofd, bfr, len) != len) { 282 free(bfr); 283 err(EX_IOERR, "write"); 284 } 285 } 286 287 free(bfr); 288 289 /* EOF or error? */ 290 if (ferror(infp)) 291 err(EX_IOERR, "read"); 292 else 293 exit(0); 294 } 295 296 /* 297 * newfile -- 298 * Open a new output file. 299 */ 300 void 301 newfile(void) 302 { 303 long i, maxfiles, tfnum; 304 static long fnum; 305 static int defname; 306 static char *fpnt; 307 308 if (ofd == -1) { 309 if (fname[0] == '\0') { 310 fname[0] = 'x'; 311 fpnt = fname + 1; 312 defname = 1; 313 } else { 314 fpnt = fname + strlen(fname); 315 defname = 0; 316 } 317 ofd = fileno(stdout); 318 } 319 320 /* maxfiles = 26^sufflen, but don't use libm. */ 321 for (maxfiles = 1, i = 0; i < sufflen; i++) 322 if ((maxfiles *= 26) <= 0) 323 errx(EX_USAGE, "suffix is too long (max %ld)", i); 324 325 if (fnum == maxfiles) 326 errx(EX_DATAERR, "too many files"); 327 328 /* Generate suffix of sufflen letters */ 329 tfnum = fnum; 330 i = sufflen - 1; 331 do { 332 fpnt[i] = tfnum % 26 + 'a'; 333 tfnum /= 26; 334 } while (i-- > 0); 335 fpnt[sufflen] = '\0'; 336 337 ++fnum; 338 if (!freopen(fname, "w", stdout)) 339 err(EX_IOERR, "%s", fname); 340 file_open = 1; 341 } 342 343 static void 344 usage(void) 345 { 346 (void)fprintf(stderr, 347 "usage: split [-a sufflen] [-b byte_count] [-l line_count] [-p pattern]\n"); 348 (void)fprintf(stderr, 349 " [file [prefix]]\n"); 350 exit(EX_USAGE); 351 } 352