cut.c revision 1.22
1 /* $NetBSD: cut.c,v 1.22 2007/02/17 19:10:00 hubertf Exp $ */ 2 3 /* 4 * Copyright (c) 1989, 1993 5 * The Regents of the University of California. All rights reserved. 6 * 7 * This code is derived from software contributed to Berkeley by 8 * Adam S. Moskowitz of Menlo Consulting and Marciano Pitargue. 9 * 10 * Redistribution and use in source and binary forms, with or without 11 * modification, are permitted provided that the following conditions 12 * are met: 13 * 1. Redistributions of source code must retain the above copyright 14 * notice, this list of conditions and the following disclaimer. 15 * 2. Redistributions in binary form must reproduce the above copyright 16 * notice, this list of conditions and the following disclaimer in the 17 * documentation and/or other materials provided with the distribution. 18 * 3. Neither the name of the University nor the names of its contributors 19 * may be used to endorse or promote products derived from this software 20 * without specific prior written permission. 21 * 22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 25 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 32 * SUCH DAMAGE. 33 */ 34 35 #include <sys/cdefs.h> 36 #ifndef lint 37 __COPYRIGHT("@(#) Copyright (c) 1989, 1993\n\ 38 The Regents of the University of California. All rights reserved.\n"); 39 #endif /* not lint */ 40 41 #ifndef lint 42 #if 0 43 static char sccsid[] = "@(#)cut.c 8.3 (Berkeley) 5/4/95"; 44 #endif 45 __RCSID("$NetBSD: cut.c,v 1.22 2007/02/17 19:10:00 hubertf Exp $"); 46 #endif /* not lint */ 47 48 #include <ctype.h> 49 #include <err.h> 50 #include <errno.h> 51 #include <limits.h> 52 #include <locale.h> 53 #include <stdio.h> 54 #include <stdlib.h> 55 #include <string.h> 56 #include <unistd.h> 57 #include <wchar.h> 58 59 int bflag; 60 int cflag; 61 char dchar; 62 int dflag; 63 int fflag; 64 int sflag; 65 66 void b_cut(FILE *, const char *); 67 void c_cut(FILE *, const char *); 68 void f_cut(FILE *, const char *); 69 void get_list(char *); 70 void usage(void); 71 72 int 73 main(int argc, char *argv[]) 74 { 75 FILE *fp; 76 void (*fcn)(FILE *, const char *); 77 int ch; 78 79 fcn = NULL; 80 setlocale (LC_ALL, ""); 81 82 dchar = '\t'; /* default delimiter is \t */ 83 84 /* Since we don't support multi-byte characters, the -c and -b 85 options are equivalent, and the -n option is meaningless. */ 86 while ((ch = getopt(argc, argv, "b:c:d:f:sn")) != -1) 87 switch(ch) { 88 case 'b': 89 fcn = b_cut; 90 get_list(optarg); 91 bflag = 1; 92 break; 93 case 'c': 94 fcn = c_cut; 95 get_list(optarg); 96 cflag = 1; 97 break; 98 case 'd': 99 dchar = *optarg; 100 dflag = 1; 101 break; 102 case 'f': 103 get_list(optarg); 104 fcn = f_cut; 105 fflag = 1; 106 break; 107 case 's': 108 sflag = 1; 109 break; 110 case 'n': 111 break; 112 case '?': 113 default: 114 usage(); 115 } 116 argc -= optind; 117 argv += optind; 118 119 if (fflag) { 120 if (cflag || bflag) 121 usage(); 122 } else if ((!cflag && !bflag) || dflag || sflag) 123 usage(); 124 else if (bflag && cflag) 125 usage(); 126 127 if (*argv) 128 for (; *argv; ++argv) { 129 if (strcmp(*argv, "-") == 0) 130 fcn(stdin, "stdin"); 131 else { 132 if ((fp = fopen(*argv, "r")) == NULL) 133 err(1, "%s", *argv); 134 fcn(fp, *argv); 135 (void)fclose(fp); 136 } 137 } 138 else 139 fcn(stdin, "stdin"); 140 exit(0); 141 } 142 143 int autostart, autostop, maxval; 144 145 char positions[_POSIX2_LINE_MAX + 1]; 146 147 void 148 get_list(char *list) 149 { 150 int setautostart, start, stop; 151 char *pos; 152 char *p; 153 154 /* 155 * set a byte in the positions array to indicate if a field or 156 * column is to be selected; use +1, it's 1-based, not 0-based. 157 * This parser is less restrictive than the Draft 9 POSIX spec. 158 * POSIX doesn't allow lists that aren't in increasing order or 159 * overlapping lists. We also handle "-3-5" although there's no 160 * real reason too. 161 */ 162 for (; (p = strtok(list, ", \t")) != NULL; list = NULL) { 163 setautostart = start = stop = 0; 164 if (*p == '-') { 165 ++p; 166 setautostart = 1; 167 } 168 if (isdigit((unsigned char)*p)) { 169 start = stop = strtol(p, &p, 10); 170 if (setautostart && start > autostart) 171 autostart = start; 172 } 173 if (*p == '-') { 174 if (isdigit((unsigned char)p[1])) 175 stop = strtol(p + 1, &p, 10); 176 if (*p == '-') { 177 ++p; 178 if (!autostop || autostop > stop) 179 autostop = stop; 180 } 181 } 182 if (*p) 183 errx(1, "[-cf] list: illegal list value"); 184 if (!stop || !start) 185 errx(1, "[-cf] list: values may not include zero"); 186 if (stop > _POSIX2_LINE_MAX) 187 errx(1, "[-cf] list: %d too large (max %d)", 188 stop, _POSIX2_LINE_MAX); 189 if (maxval < stop) 190 maxval = stop; 191 for (pos = positions + start; start++ <= stop; *pos++ = 1); 192 } 193 194 /* overlapping ranges */ 195 if (autostop && maxval > autostop) 196 maxval = autostop; 197 198 /* set autostart */ 199 if (autostart) 200 memset(positions + 1, '1', autostart); 201 } 202 203 void 204 f_cut(FILE *fp, const char *fname) 205 { 206 int ch, field, isdelim; 207 char *pos, *p, sep; 208 int output; 209 size_t len; 210 char *lbuf, *tbuf; 211 212 for (sep = dchar, tbuf = NULL; (lbuf = fgetln(fp, &len));) { 213 output = 0; 214 if (lbuf[len - 1] != '\n') { 215 /* no newline at the end of the last line so add one */ 216 if ((tbuf = (char *)malloc(len + 1)) == NULL) 217 err(1, NULL); 218 memcpy(tbuf, lbuf, len); 219 tbuf[len++] = '\n'; 220 lbuf = tbuf; 221 } 222 for (isdelim = 0, p = lbuf;; ++p) { 223 ch = *p; 224 /* this should work if newline is delimiter */ 225 if (ch == sep) 226 isdelim = 1; 227 if (ch == '\n') { 228 if (!isdelim && !sflag) 229 (void)fwrite(lbuf, len, 1, stdout); 230 break; 231 } 232 } 233 if (!isdelim) 234 continue; 235 236 pos = positions + 1; 237 for (field = maxval, p = lbuf; field; --field, ++pos) { 238 if (*pos) { 239 if (output++) 240 (void)putchar(sep); 241 while ((ch = *p++) != '\n' && ch != sep) 242 (void)putchar(ch); 243 } else { 244 while ((ch = *p++) != '\n' && ch != sep) 245 continue; 246 } 247 if (ch == '\n') 248 break; 249 } 250 if (ch != '\n') { 251 if (autostop) { 252 if (output) 253 (void)putchar(sep); 254 for (; (ch = *p) != '\n'; ++p) 255 (void)putchar(ch); 256 } else 257 for (; (ch = *p) != '\n'; ++p); 258 } 259 (void)putchar('\n'); 260 if (tbuf) { 261 free(tbuf); 262 tbuf = NULL; 263 } 264 } 265 if (tbuf) 266 free(tbuf); 267 } 268 269 void 270 usage(void) 271 { 272 (void)fprintf(stderr, "usage:\tcut -b list [-n] [file ...]\n" 273 "\tcut -c list [file1 ...]\n" 274 "\tcut -f list [-d delim] [-s] [file ...]\n"); 275 exit(1); 276 } 277 278 /* make b_put(): */ 279 #define CUT_BYTE 1 280 #include "x_cut.c" 281 #undef CUT_BYTE 282 283 /* make c_put(): */ 284 #define CUT_BYTE 0 285 #include "x_cut.c" 286 #undef CUT_BYTE 287
Indexes created Thu Sep 25 02:09:54 GMT 2025