cut.c revision 97234
1/* 2 * Copyright (c) 1989, 1993 3 * The Regents of the University of California. All rights reserved. 4 * 5 * This code is derived from software contributed to Berkeley by 6 * Adam S. Moskowitz of Menlo Consulting and Marciano Pitargue. 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. 16 * 3. All advertising materials mentioning features or use of this software 17 * must display the following acknowledgement: 18 * This product includes software developed by the University of 19 * California, Berkeley and its contributors. 20 * 4. Neither the name of the University nor the names of its contributors 21 * may be used to endorse or promote products derived from this software 22 * without specific prior written permission. 23 * 24 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 27 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 34 * SUCH DAMAGE. 35 */ 36 37#ifndef lint 38static const char copyright[] = 39"@(#) Copyright (c) 1989, 1993\n\ 40 The Regents of the University of California. All rights reserved.\n"; 41static const char sccsid[] = "@(#)cut.c 8.3 (Berkeley) 5/4/95"; 42static const char rcsid[] = 43 "$FreeBSD: head/usr.bin/cut/cut.c 97234 2002-05-24 09:11:18Z tjr $"; 44#endif /* not lint */ 45 46#include <ctype.h> 47#include <err.h> 48#include <limits.h> 49#include <locale.h> 50#include <stdio.h> 51#include <stdlib.h> 52#include <string.h> 53#include <unistd.h> 54 55int cflag; 56char dchar; 57int dflag; 58int fflag; 59int sflag; 60 61void c_cut (FILE *, const char *); 62void f_cut (FILE *, const char *); 63void get_list (char *); 64int main (int, char **); 65void needpos(size_t); 66static void usage (void); 67 68int 69main(argc, argv) 70 int argc; 71 char *argv[]; 72{ 73 FILE *fp; 74 void (*fcn) (FILE *, const char *) = NULL; 75 int ch, rval; 76 77 fcn = NULL; 78 setlocale (LC_ALL, ""); 79 80 dchar = '\t'; /* default delimiter is \t */ 81 82 /* Since we don't support multi-byte characters, the -c and -b 83 options are equivalent, and the -n option is meaningless. */ 84 while ((ch = getopt(argc, argv, "b:c:d:f:sn")) != -1) 85 switch(ch) { 86 case 'b': 87 case 'c': 88 fcn = c_cut; 89 get_list(optarg); 90 cflag = 1; 91 break; 92 case 'd': 93 dchar = *optarg; 94 dflag = 1; 95 break; 96 case 'f': 97 get_list(optarg); 98 fcn = f_cut; 99 fflag = 1; 100 break; 101 case 's': 102 sflag = 1; 103 break; 104 case 'n': 105 break; 106 case '?': 107 default: 108 usage(); 109 } 110 argc -= optind; 111 argv += optind; 112 113 if (fflag) { 114 if (cflag) 115 usage(); 116 } else if (!cflag || dflag || sflag) 117 usage(); 118 119 rval = 0; 120 if (*argv) 121 for (; *argv; ++argv) { 122 if (!(fp = fopen(*argv, "r"))) { 123 warn("%s", *argv); 124 rval = 1; 125 continue; 126 } 127 fcn(fp, *argv); 128 (void)fclose(fp); 129 } 130 else 131 fcn(stdin, "stdin"); 132 exit(rval); 133} 134 135size_t autostart, autostop, maxval; 136 137char *positions; 138 139void 140get_list(list) 141 char *list; 142{ 143 size_t setautostart, start, stop; 144 char *pos; 145 char *p; 146 147 /* 148 * set a byte in the positions array to indicate if a field or 149 * column is to be selected; use +1, it's 1-based, not 0-based. 150 * This parser is less restrictive than the Draft 9 POSIX spec. 151 * POSIX doesn't allow lists that aren't in increasing order or 152 * overlapping lists. We also handle "-3-5" although there's no 153 * real reason too. 154 */ 155 for (; (p = strsep(&list, ", \t")) != NULL;) { 156 setautostart = start = stop = 0; 157 if (*p == '-') { 158 ++p; 159 setautostart = 1; 160 } 161 if (isdigit((unsigned char)*p)) { 162 start = stop = strtol(p, &p, 10); 163 if (setautostart && start > autostart) 164 autostart = start; 165 } 166 if (*p == '-') { 167 if (isdigit((unsigned char)p[1])) 168 stop = strtol(p + 1, &p, 10); 169 if (*p == '-') { 170 ++p; 171 if (!autostop || autostop > stop) 172 autostop = stop; 173 } 174 } 175 if (*p) 176 errx(1, "[-cf] list: illegal list value"); 177 if (!stop || !start) 178 errx(1, "[-cf] list: values may not include zero"); 179 if (maxval < stop) { 180 maxval = stop; 181 needpos(maxval + 1); 182 } 183 for (pos = positions + start; start++ <= stop; *pos++ = 1); 184 } 185 186 /* overlapping ranges */ 187 if (autostop && maxval > autostop) { 188 maxval = autostop; 189 needpos(maxval + 1); 190 } 191 192 /* set autostart */ 193 if (autostart) 194 memset(positions + 1, '1', autostart); 195} 196 197void 198needpos(size_t n) 199{ 200 static size_t npos; 201 202 /* Grow the positions array to at least the specified size. */ 203 if (n > npos) { 204 if (npos == 0) 205 npos = n; 206 while (n > npos) 207 npos *= 2; 208 if ((positions = realloc(positions, npos)) == NULL) 209 err(1, "realloc"); 210 } 211} 212 213/* ARGSUSED */ 214void 215c_cut(fp, fname) 216 FILE *fp; 217 const char *fname; 218{ 219 int ch, col; 220 char *pos; 221 fname = NULL; 222 223 ch = 0; 224 for (;;) { 225 pos = positions + 1; 226 for (col = maxval; col; --col) { 227 if ((ch = getc(fp)) == EOF) 228 return; 229 if (ch == '\n') 230 break; 231 if (*pos++) 232 (void)putchar(ch); 233 } 234 if (ch != '\n') { 235 if (autostop) 236 while ((ch = getc(fp)) != EOF && ch != '\n') 237 (void)putchar(ch); 238 else 239 while ((ch = getc(fp)) != EOF && ch != '\n'); 240 } 241 (void)putchar('\n'); 242 } 243} 244 245void 246f_cut(fp, fname) 247 FILE *fp; 248 const char *fname __unused; 249{ 250 int ch, field, isdelim; 251 char *pos, *p, sep; 252 int output; 253 char *lbuf, *mlbuf = NULL; 254 size_t lbuflen; 255 256 for (sep = dchar; (lbuf = fgetln(fp, &lbuflen)) != NULL;) { 257 /* Assert EOL has a newline. */ 258 if (*(lbuf + lbuflen - 1) != '\n') { 259 /* Can't have > 1 line with no trailing newline. */ 260 mlbuf = malloc(lbuflen + 1); 261 if (mlbuf == NULL) 262 err(1, "malloc"); 263 memcpy(mlbuf, lbuf, lbuflen); 264 *(mlbuf + lbuflen) = '\n'; 265 lbuf = mlbuf; 266 } 267 output = 0; 268 for (isdelim = 0, p = lbuf;; ++p) { 269 ch = *p; 270 /* this should work if newline is delimiter */ 271 if (ch == sep) 272 isdelim = 1; 273 if (ch == '\n') { 274 if (!isdelim && !sflag) 275 (void)fwrite(lbuf, lbuflen, 1, stdout); 276 break; 277 } 278 } 279 if (!isdelim) 280 continue; 281 282 pos = positions + 1; 283 for (field = maxval, p = lbuf; field; --field, ++pos) { 284 if (*pos) { 285 if (output++) 286 (void)putchar(sep); 287 while ((ch = *p++) != '\n' && ch != sep) 288 (void)putchar(ch); 289 } else { 290 while ((ch = *p++) != '\n' && ch != sep) 291 continue; 292 } 293 if (ch == '\n') 294 break; 295 } 296 if (ch != '\n') { 297 if (autostop) { 298 if (output) 299 (void)putchar(sep); 300 for (; (ch = *p) != '\n'; ++p) 301 (void)putchar(ch); 302 } else 303 for (; (ch = *p) != '\n'; ++p); 304 } 305 (void)putchar('\n'); 306 } 307 if (mlbuf != NULL) 308 free(mlbuf); 309} 310 311static void 312usage() 313{ 314 (void)fprintf(stderr, "%s\n%s\n%s\n", 315 "usage: cut -b list [-n] [file ...]", 316 " cut -c list [file ...]", 317 " cut -f list [-s] [-d delim] [file ...]"); 318 exit(1); 319} 320