cut.c revision 43532
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"; 41#endif /* not lint */ 42 43#ifndef lint 44static const char sccsid[] = "@(#)cut.c 8.3 (Berkeley) 5/4/95"; 45#endif /* not lint */ 46 47#include <ctype.h> 48#include <err.h> 49#include <errno.h> 50#include <limits.h> 51#include <locale.h> 52#include <stdio.h> 53#include <stdlib.h> 54#include <string.h> 55#include <unistd.h> 56 57int cflag; 58char dchar; 59int dflag; 60int fflag; 61int sflag; 62 63void c_cut __P((FILE *, char *)); 64void f_cut __P((FILE *, char *)); 65void get_list __P((char *)); 66static void usage __P((void)); 67 68int 69main(argc, argv) 70 int argc; 71 char *argv[]; 72{ 73 FILE *fp; 74 void (*fcn) __P((FILE *, char *)) = NULL; 75 int ch; 76 77 setlocale (LC_ALL, ""); 78 79 dchar = '\t'; /* default delimiter is \t */ 80 81 /* Since we don't support multi-byte characters, the -c and -b 82 options are equivalent, and the -n option is meaningless. */ 83 while ((ch = getopt(argc, argv, "b:c:d:f:sn")) != -1) 84 switch(ch) { 85 case 'b': 86 case 'c': 87 fcn = c_cut; 88 get_list(optarg); 89 cflag = 1; 90 break; 91 case 'd': 92 dchar = *optarg; 93 dflag = 1; 94 break; 95 case 'f': 96 get_list(optarg); 97 fcn = f_cut; 98 fflag = 1; 99 break; 100 case 's': 101 sflag = 1; 102 break; 103 case 'n': 104 break; 105 case '?': 106 default: 107 usage(); 108 } 109 argc -= optind; 110 argv += optind; 111 112 if (fflag) { 113 if (cflag) 114 usage(); 115 } else if (!cflag || dflag || sflag) 116 usage(); 117 118 if (*argv) 119 for (; *argv; ++argv) { 120 if (!(fp = fopen(*argv, "r"))) 121 err(1, "%s", *argv); 122 fcn(fp, *argv); 123 (void)fclose(fp); 124 } 125 else 126 fcn(stdin, "stdin"); 127 exit(0); 128} 129 130int autostart, autostop, maxval; 131 132char positions[_POSIX2_LINE_MAX + 1]; 133 134void 135get_list(list) 136 char *list; 137{ 138 register int setautostart, start, stop; 139 register char *pos; 140 char *p; 141 142 /* 143 * set a byte in the positions array to indicate if a field or 144 * column is to be selected; use +1, it's 1-based, not 0-based. 145 * This parser is less restrictive than the Draft 9 POSIX spec. 146 * POSIX doesn't allow lists that aren't in increasing order or 147 * overlapping lists. We also handle "-3-5" although there's no 148 * real reason too. 149 */ 150 for (; (p = strsep(&list, ", \t"));) { 151 setautostart = start = stop = 0; 152 if (*p == '-') { 153 ++p; 154 setautostart = 1; 155 } 156 if (isdigit(*p)) { 157 start = stop = strtol(p, &p, 10); 158 if (setautostart && start > autostart) 159 autostart = start; 160 } 161 if (*p == '-') { 162 if (isdigit(p[1])) 163 stop = strtol(p + 1, &p, 10); 164 if (*p == '-') { 165 ++p; 166 if (!autostop || autostop > stop) 167 autostop = stop; 168 } 169 } 170 if (*p) 171 errx(1, "[-cf] list: illegal list value"); 172 if (!stop || !start) 173 errx(1, "[-cf] list: values may not include zero"); 174 if (stop > _POSIX2_LINE_MAX) 175 errx(1, "[-cf] list: %d too large (max %d)", 176 stop, _POSIX2_LINE_MAX); 177 if (maxval < stop) 178 maxval = stop; 179 for (pos = positions + start; start++ <= stop; *pos++ = 1); 180 } 181 182 /* overlapping ranges */ 183 if (autostop && maxval > autostop) 184 maxval = autostop; 185 186 /* set autostart */ 187 if (autostart) 188 memset(positions + 1, '1', autostart); 189} 190 191/* ARGSUSED */ 192void 193c_cut(fp, fname) 194 FILE *fp; 195 char *fname; 196{ 197 register int ch = 0, col; 198 register char *pos; 199 200 for (;;) { 201 pos = positions + 1; 202 for (col = maxval; col; --col) { 203 if ((ch = getc(fp)) == EOF) 204 return; 205 if (ch == '\n') 206 break; 207 if (*pos++) 208 (void)putchar(ch); 209 } 210 if (ch != '\n') 211 if (autostop) 212 while ((ch = getc(fp)) != EOF && ch != '\n') 213 (void)putchar(ch); 214 else 215 while ((ch = getc(fp)) != EOF && ch != '\n'); 216 (void)putchar('\n'); 217 } 218} 219 220void 221f_cut(fp, fname) 222 FILE *fp; 223 char *fname; 224{ 225 register int ch, field, isdelim; 226 register char *pos, *p, sep; 227 int output; 228 char lbuf[_POSIX2_LINE_MAX + 1]; 229 230 for (sep = dchar; fgets(lbuf, sizeof(lbuf), fp);) { 231 output = 0; 232 for (isdelim = 0, p = lbuf;; ++p) { 233 if (!(ch = *p)) 234 errx(1, "%s: line too long.", fname); 235 /* this should work if newline is delimiter */ 236 if (ch == sep) 237 isdelim = 1; 238 if (ch == '\n') { 239 if (!isdelim && !sflag) 240 (void)printf("%s", lbuf); 241 break; 242 } 243 } 244 if (!isdelim) 245 continue; 246 247 pos = positions + 1; 248 for (field = maxval, p = lbuf; field; --field, ++pos) { 249 if (*pos) { 250 if (output++) 251 (void)putchar(sep); 252 while ((ch = *p++) != '\n' && ch != sep) 253 (void)putchar(ch); 254 } else 255 while ((ch = *p++) != '\n' && ch != sep); 256 if (ch == '\n') 257 break; 258 } 259 if (ch != '\n') 260 if (autostop) { 261 if (output) 262 (void)putchar(sep); 263 for (; (ch = *p) != '\n'; ++p) 264 (void)putchar(ch); 265 } else 266 for (; (ch = *p) != '\n'; ++p); 267 (void)putchar('\n'); 268 } 269} 270 271static void 272usage() 273{ 274 (void)fprintf(stderr, "%s\n%s\n%s\n", 275 "usage: cut -b list [-n] [file ...]", 276 " cut -c list [file ...]", 277 " cut -f list [-s] [-d delim] [file ...]"); 278 exit(1); 279} 280