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 #ifndef lint 35 static const char copyright[] = 36 "@(#) Copyright (c) 1987, 1993, 1994\n\ 37 The Regents of the University of California. All rights reserved.\n"; 38 #endif /* not lint */ 39 40 #ifndef lint 41 #if 0 42 static char sccsid[] = "@(#)split.c 8.2 (Berkeley) 4/16/94"; 43 #endif 44 #endif /* not lint */ 45 46 #include <sys/param.h> 47 #include <sys/types.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 long 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 70 void newfile __P((void)); 71 void split1 __P((void)); 72 void split2 __P((void)); 73 static void usage __P((void)); 74 75 int 76 main(argc, argv) 77 int argc; 78 char *argv[]; 79 { 80 int ch; 81 char *ep, *p; 82 83 while ((ch = getopt(argc, argv, "-0123456789b:l:p:")) != -1) 84 switch (ch) { 85 case '0': case '1': case '2': case '3': case '4': 86 case '5': case '6': case '7': case '8': case '9': 87 /* 88 * Undocumented kludge: split was originally designed 89 * to take a number after a dash. 90 */ 91 if (numlines == 0) { 92 p = argv[optind - 1]; 93 if (p[0] == '-' && p[1] == ch && !p[2]) 94 numlines = strtol(++p, &ep, 10); 95 else 96 numlines = 97 strtol(argv[optind] + 1, &ep, 10); 98 if (numlines <= 0 || *ep) 99 errx(EX_USAGE, 100 "%s: illegal line count", optarg); 101 } 102 break; 103 case '-': /* Undocumented: historic stdin flag. */ 104 if (ifd != -1) 105 usage(); 106 ifd = 0; 107 break; 108 case 'b': /* Byte count. */ 109 if ((bytecnt = strtol(optarg, &ep, 10)) <= 0 || 110 (*ep != '\0' && *ep != 'k' && *ep != 'm')) 111 errx(EX_USAGE, 112 "%s: illegal byte count", optarg); 113 if (*ep == 'k') 114 bytecnt *= 1024; 115 else if (*ep == 'm') 116 bytecnt *= 1048576; 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 (ifd == -1) { /* Input file. */ 138 if ((ifd = open(*argv, O_RDONLY, 0)) < 0) 139 err(EX_NOINPUT, "%s", *argv); 140 ++argv; 141 } 142 if (*argv != NULL) /* File name prefix. */ 143 (void)strcpy(fname, *argv++); 144 if (*argv != NULL) 145 usage(); 146 147 if (pflag && (numlines != 0 || bytecnt != 0)) 148 usage(); 149 150 if (numlines == 0) 151 numlines = DEFLINE; 152 else if (bytecnt != 0) 153 usage(); 154 155 if (ifd == -1) /* Stdin by default. */ 156 ifd = 0; 157 158 if (bytecnt) { 159 split1(); 160 exit (0); 161 } 162 split2(); 163 if (pflag) 164 regfree(&rgx); 165 exit(0); 166 } 167 168 /* 169 * split1 -- 170 * Split the input by bytes. 171 */ 172 void 173 split1() 174 { 175 long bcnt; 176 int dist, len; 177 char *C; 178 179 for (bcnt = 0;;) 180 switch ((len = read(ifd, bfr, MAXBSIZE))) { 181 case 0: 182 exit(0); 183 case -1: 184 err(EX_IOERR, "read"); 185 /* NOTREACHED */ 186 default: 187 if (!file_open) 188 newfile(); 189 if (bcnt + len >= bytecnt) { 190 dist = bytecnt - bcnt; 191 if (write(ofd, bfr, dist) != dist) 192 err(EX_IOERR, "write"); 193 len -= dist; 194 for (C = bfr + dist; len >= bytecnt; 195 len -= bytecnt, C += bytecnt) { 196 newfile(); 197 if (write(ofd, 198 C, (int)bytecnt) != bytecnt) 199 err(EX_IOERR, "write"); 200 } 201 if (len != 0) { 202 newfile(); 203 if (write(ofd, C, len) != len) 204 err(EX_IOERR, "write"); 205 } else 206 file_open = 0; 207 bcnt = len; 208 } else { 209 bcnt += len; 210 if (write(ofd, bfr, len) != len) 211 err(EX_IOERR, "write"); 212 } 213 } 214 } 215 216 /* 217 * split2 -- 218 * Split the input by lines. 219 */ 220 void 221 split2() 222 { 223 long lcnt = 0; 224 FILE *infp; 225 226 /* Stick a stream on top of input file descriptor */ 227 if ((infp = fdopen(ifd, "r")) == NULL) 228 err(EX_NOINPUT, "fdopen"); 229 230 /* Process input one line at a time */ 231 while (fgets(bfr, sizeof(bfr), infp) != NULL) { 232 const int len = strlen(bfr); 233 234 /* If line is too long to deal with, just write it out */ 235 if (bfr[len - 1] != '\n') 236 goto writeit; 237 238 /* Check if we need to start a new file */ 239 if (pflag) { 240 regmatch_t pmatch; 241 242 pmatch.rm_so = 0; 243 pmatch.rm_eo = len - 1; 244 if (regexec(&rgx, bfr, 0, &pmatch, REG_STARTEND) == 0) 245 newfile(); 246 } else if (lcnt++ == numlines) { 247 newfile(); 248 lcnt = 1; 249 } 250 251 writeit: 252 /* Open output file if needed */ 253 if (!file_open) 254 newfile(); 255 256 /* Write out line */ 257 if (write(ofd, bfr, len) != len) 258 err(EX_IOERR, "write"); 259 } 260 261 /* EOF or error? */ 262 if (ferror(infp)) 263 err(EX_IOERR, "read"); 264 else 265 exit(0); 266 } 267 268 /* 269 * newfile -- 270 * Open a new output file. 271 */ 272 void 273 newfile() 274 { 275 static long fnum; 276 static int defname; 277 static char *fpnt; 278 279 if (ofd == -1) { 280 if (fname[0] == '\0') { 281 fname[0] = 'x'; 282 fpnt = fname + 1; 283 defname = 1; 284 } else { 285 fpnt = fname + strlen(fname); 286 defname = 0; 287 } 288 ofd = fileno(stdout); 289 } 290 /* 291 * Hack to increase max files; original code wandered through 292 * magic characters. Maximum files is 3 * 26 * 26 == 2028 293 */ 294 #define MAXFILES 676 295 if (fnum == MAXFILES) { 296 if (!defname || fname[0] == 'z') 297 errx(EX_DATAERR, "too many files"); 298 ++fname[0]; 299 fnum = 0; 300 } 301 fpnt[0] = fnum / 26 + 'a'; 302 fpnt[1] = fnum % 26 + 'a'; 303 ++fnum; 304 if (!freopen(fname, "w", stdout)) 305 err(EX_IOERR, "%s", fname); 306 file_open = 1; 307 } 308 309 static void 310 usage() 311 { 312 errx(EX_USAGE, 313 "usage: split [-b byte_count] [-l line_count] [-p pattern] [file [prefix]]"); 314 } 315