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 <fcntl.h> 52 #include <stdio.h> 53 #include <stdlib.h> 54 #include <string.h> 55 #include <unistd.h> 56 #include <regex.h> 57 #include <sysexits.h> 58 59 #define DEFLINE 1000 /* Default num lines per file. */ 60 61 int bytecnt; /* Byte count to split on. */ 62 long numlines; /* Line count to split on. */ 63 int file_open; /* If a file open. */ 64 int ifd = -1, ofd = -1; /* Input/output file descriptors. */ 65 char bfr[MAXBSIZE]; /* I/O buffer. */ 66 char fname[MAXPATHLEN]; /* File name prefix. */ 67 regex_t rgx; 68 int pflag; 69 long sufflen = 2; /* File name suffix length. */ 70 71 void newfile(void); 72 void split1(void); 73 void split2(void); 74 static void usage(void); 75 76 int 77 main(int argc, char **argv) 78 { 79 int ch; 80 char *ep, *p; 81 82 while ((ch = getopt(argc, argv, "-0123456789a:b:l:p:")) != -1) 83 switch (ch) { 84 case '0': case '1': case '2': case '3': case '4': 85 case '5': case '6': case '7': case '8': case '9': 86 /* 87 * Undocumented kludge: split was originally designed 88 * to take a number after a dash. 89 */ 90 if (numlines == 0) { 91 p = argv[optind - 1]; 92 if (p[0] == '-' && p[1] == ch && !p[2]) 93 numlines = strtol(++p, &ep, 10); 94 else 95 numlines = 96 strtol(argv[optind] + 1, &ep, 10); 97 if (numlines <= 0 || *ep) 98 errx(EX_USAGE, 99 "%s: illegal line count", optarg); 100 } 101 break; 102 case '-': /* Undocumented: historic stdin flag. */ 103 if (ifd != -1) 104 usage(); 105 ifd = 0; 106 break; 107 case 'a': /* Suffix length */ 108 if ((sufflen = strtol(optarg, &ep, 10)) <= 0 || *ep) 109 errx(EX_USAGE, 110 "%s: illegal suffix length", optarg); 111 break; 112 case 'b': /* Byte count. */ 113 if ((bytecnt = strtoq(optarg, &ep, 10)) <= 0 || 114 (*ep != '\0' && *ep != 'k' && *ep != 'm')) 115 errx(EX_USAGE, 116 "%s: illegal byte count", optarg); 117 if (*ep == 'k') 118 bytecnt *= 1024; 119 else if (*ep == 'm') 120 bytecnt *= 1048576; 121 break; 122 case 'p' : /* pattern matching. */ 123 if (regcomp(&rgx, optarg, REG_EXTENDED|REG_NOSUB) != 0) 124 errx(EX_USAGE, "%s: illegal regexp", optarg); 125 pflag = 1; 126 break; 127 case 'l': /* Line count. */ 128 if (numlines != 0) 129 usage(); 130 if ((numlines = strtol(optarg, &ep, 10)) <= 0 || *ep) 131 errx(EX_USAGE, 132 "%s: illegal line count", optarg); 133 break; 134 default: 135 usage(); 136 } 137 argv += optind; 138 argc -= optind; 139 140 if (*argv != NULL) 141 if (ifd == -1) { /* Input file. */ 142 if (strcmp(*argv, "-") == 0) 143 ifd = STDIN_FILENO; 144 else if ((ifd = open(*argv, O_RDONLY, 0)) < 0) 145 err(EX_NOINPUT, "%s", *argv); 146 ++argv; 147 } 148 if (*argv != NULL) /* File name prefix. */ 149 if (strlcpy(fname, *argv++, sizeof(fname)) >= sizeof(fname)) 150 errx(EX_USAGE, "file name prefix is too long"); 151 if (*argv != NULL) 152 usage(); 153 154 if (strlen(fname) + (unsigned long)sufflen >= sizeof(fname)) 155 errx(EX_USAGE, "suffix is too long"); 156 if (pflag && (numlines != 0 || bytecnt != 0)) 157 usage(); 158 159 if (numlines == 0) 160 numlines = DEFLINE; 161 else if (bytecnt != 0) 162 usage(); 163 164 if (ifd == -1) /* Stdin by default. */ 165 ifd = 0; 166 167 if (bytecnt) { 168 split1(); 169 exit (0); 170 } 171 split2(); 172 if (pflag) 173 regfree(&rgx); 174 exit(0); 175 } 176 177 /* 178 * split1 -- 179 * Split the input by bytes. 180 */ 181 void 182 split1(void) 183 { 184 size_t bcnt; 185 char *C; 186 int dist, len; 187 188 for (bcnt = 0;;) 189 switch ((len = read(ifd, bfr, MAXBSIZE))) { 190 case 0: 191 exit(0); 192 case -1: 193 err(EX_IOERR, "read"); 194 /* NOTREACHED */ 195 default: 196 if (!file_open) 197 newfile(); 198 if (bcnt + len >= (u_int)bytecnt) { 199 dist = bytecnt - bcnt; 200 if (write(ofd, bfr, dist) != dist) 201 err(EX_IOERR, "write"); 202 len -= dist; 203 for (C = bfr + dist; len >= bytecnt; 204 len -= bytecnt, C += bytecnt) { 205 newfile(); 206 if (write(ofd, 207 C, bytecnt) != bytecnt) 208 err(EX_IOERR, "write"); 209 } 210 if (len != 0) { 211 newfile(); 212 if (write(ofd, C, len) != len) 213 err(EX_IOERR, "write"); 214 } else 215 file_open = 0; 216 bcnt = len; 217 } else { 218 bcnt += len; 219 if (write(ofd, bfr, len) != len) 220 err(EX_IOERR, "write"); 221 } 222 } 223 } 224 225 /* 226 * split2 -- 227 * Split the input by lines. 228 */ 229 void 230 split2(void) 231 { 232 long lcnt = 0; 233 FILE *infp; 234 235 /* Stick a stream on top of input file descriptor */ 236 if ((infp = fdopen(ifd, "r")) == NULL) 237 err(EX_NOINPUT, "fdopen"); 238 239 /* Process input one line at a time */ 240 while (fgets(bfr, sizeof(bfr), infp) != NULL) { 241 const int len = strlen(bfr); 242 243 /* If line is too long to deal with, just write it out */ 244 if (bfr[len - 1] != '\n') 245 goto writeit; 246 247 /* Check if we need to start a new file */ 248 if (pflag) { 249 regmatch_t pmatch; 250 251 pmatch.rm_so = 0; 252 pmatch.rm_eo = len - 1; 253 if (regexec(&rgx, bfr, 0, &pmatch, REG_STARTEND) == 0) 254 newfile(); 255 } else if (lcnt++ == numlines) { 256 newfile(); 257 lcnt = 1; 258 } 259 260 writeit: 261 /* Open output file if needed */ 262 if (!file_open) 263 newfile(); 264 265 /* Write out line */ 266 if (write(ofd, bfr, len) != len) 267 err(EX_IOERR, "write"); 268 } 269 270 /* EOF or error? */ 271 if (ferror(infp)) 272 err(EX_IOERR, "read"); 273 else 274 exit(0); 275 } 276 277 /* 278 * newfile -- 279 * Open a new output file. 280 */ 281 void 282 newfile(void) 283 { 284 long i, maxfiles, tfnum; 285 static long fnum; 286 static int defname; 287 static char *fpnt; 288 289 if (ofd == -1) { 290 if (fname[0] == '\0') { 291 fname[0] = 'x'; 292 fpnt = fname + 1; 293 defname = 1; 294 } else { 295 fpnt = fname + strlen(fname); 296 defname = 0; 297 } 298 ofd = fileno(stdout); 299 } 300 301 /* maxfiles = 26^sufflen, but don't use libm. */ 302 for (maxfiles = 1, i = 0; i < sufflen; i++) 303 if ((maxfiles *= 26) <= 0) 304 errx(EX_USAGE, "suffix is too long (max %ld)", i); 305 306 /* 307 * Hack to increase max files; original code wandered through 308 * magic characters. 309 */ 310 if (fnum == maxfiles) { 311 if (!defname || fname[0] == 'z') 312 errx(EX_DATAERR, "too many files"); 313 ++fname[0]; 314 fnum = 0; 315 } 316 317 /* Generate suffix of sufflen letters */ 318 tfnum = fnum; 319 i = sufflen - 1; 320 do { 321 fpnt[i] = tfnum % 26 + 'a'; 322 tfnum /= 26; 323 } while (i-- > 0); 324 fpnt[sufflen] = '\0'; 325 326 ++fnum; 327 if (!freopen(fname, "w", stdout)) 328 err(EX_IOERR, "%s", fname); 329 file_open = 1; 330 } 331 332 static void 333 usage(void) 334 { 335 (void)fprintf(stderr, 336 "usage: split [-a sufflen] [-b byte_count] [-l line_count] [-p pattern]\n"); 337 (void)fprintf(stderr, 338 " [file [prefix]]\n"); 339 exit(EX_USAGE); 340 } 341