1 /* $NetBSD: uniq.c,v 1.6 1994/12/06 07:51:17 jtc 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 * Case Larsen. 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. All advertising materials mentioning features or use of this software 19 * must display the following acknowledgement: 20 * This product includes software developed by the University of 21 * California, Berkeley and its contributors. 22 * 4. Neither the name of the University nor the names of its contributors 23 * may be used to endorse or promote products derived from this software 24 * without specific prior written permission. 25 * 26 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 27 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 28 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 29 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 30 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 31 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 32 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 33 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 34 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 35 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 36 * SUCH DAMAGE. 37 */ 38 39 #ifndef lint 40 static char copyright[] = 41 "@(#) Copyright (c) 1989, 1993\n\ 42 The Regents of the University of California. All rights reserved.\n"; 43 #endif /* not lint */ 44 45 #ifndef lint 46 #if 0 47 static char sccsid[] = "@(#)uniq.c 8.1 (Berkeley) 6/6/93"; 48 #endif 49 static char rcsid[] = "$NetBSD: uniq.c,v 1.6 1994/12/06 07:51:17 jtc Exp $"; 50 #endif /* not lint */ 51 52 #include <errno.h> 53 #include <stdio.h> 54 #include <ctype.h> 55 #include <stdlib.h> 56 #include <string.h> 57 58 #define MAXLINELEN (8 * 1024) 59 60 int cflag, dflag, uflag; 61 int numchars, numfields, repeats; 62 63 void err __P((const char *, ...)); 64 FILE *file __P((char *, char *)); 65 void show __P((FILE *, char *)); 66 char *skip __P((char *)); 67 void obsolete __P((char *[])); 68 void usage __P((void)); 69 70 int 71 main (argc, argv) 72 int argc; 73 char *argv[]; 74 { 75 register char *t1, *t2; 76 FILE *ifp, *ofp; 77 int ch; 78 char *prevline, *thisline, *p; 79 80 obsolete(argv); 81 while ((ch = getopt(argc, argv, "-cdf:s:u")) != EOF) 82 switch (ch) { 83 case '-': 84 --optind; 85 goto done; 86 case 'c': 87 cflag = 1; 88 break; 89 case 'd': 90 dflag = 1; 91 break; 92 case 'f': 93 numfields = strtol(optarg, &p, 10); 94 if (numfields < 0 || *p) 95 err("illegal field skip value: %s", optarg); 96 break; 97 case 's': 98 numchars = strtol(optarg, &p, 10); 99 if (numchars < 0 || *p) 100 err("illegal character skip value: %s", optarg); 101 break; 102 case 'u': 103 uflag = 1; 104 break; 105 case '?': 106 default: 107 usage(); 108 } 109 110 done: argc -= optind; 111 argv +=optind; 112 113 /* If no flags are set, default is -d -u. */ 114 if (cflag) { 115 if (dflag || uflag) 116 usage(); 117 } else if (!dflag && !uflag) 118 dflag = uflag = 1; 119 120 switch(argc) { 121 case 0: 122 ifp = stdin; 123 ofp = stdout; 124 break; 125 case 1: 126 ifp = file(argv[0], "r"); 127 ofp = stdout; 128 break; 129 case 2: 130 ifp = file(argv[0], "r"); 131 ofp = file(argv[1], "w"); 132 break; 133 default: 134 usage(); 135 } 136 137 prevline = malloc(MAXLINELEN); 138 thisline = malloc(MAXLINELEN); 139 if (prevline == NULL || thisline == NULL) 140 err("%s", strerror(errno)); 141 142 if (fgets(prevline, MAXLINELEN, ifp) == NULL) 143 exit(0); 144 145 while (fgets(thisline, MAXLINELEN, ifp)) { 146 /* If requested get the chosen fields + character offsets. */ 147 if (numfields || numchars) { 148 t1 = skip(thisline); 149 t2 = skip(prevline); 150 } else { 151 t1 = thisline; 152 t2 = prevline; 153 } 154 155 /* If different, print; set previous to new value. */ 156 if (strcmp(t1, t2)) { 157 show(ofp, prevline); 158 t1 = prevline; 159 prevline = thisline; 160 thisline = t1; 161 repeats = 0; 162 } else 163 ++repeats; 164 } 165 show(ofp, prevline); 166 exit(0); 167 } 168 169 /* 170 * show -- 171 * Output a line depending on the flags and number of repetitions 172 * of the line. 173 */ 174 void 175 show(ofp, str) 176 FILE *ofp; 177 char *str; 178 { 179 if (cflag) 180 (void)fprintf(ofp, "%4d %s", repeats + 1, str); 181 if (dflag && repeats || uflag && !repeats) 182 (void)fprintf(ofp, "%s", str); 183 } 184 185 char * 186 skip(str) 187 register char *str; 188 { 189 register int infield, nchars, nfields; 190 191 for (nfields = numfields, infield = 0; nfields && *str; ++str) 192 if (isspace(*str)) { 193 if (infield) { 194 infield = 0; 195 --nfields; 196 } 197 } else if (!infield) 198 infield = 1; 199 for (nchars = numchars; nchars-- && *str; ++str); 200 return(str); 201 } 202 203 FILE * 204 file(name, mode) 205 char *name, *mode; 206 { 207 FILE *fp; 208 209 if ((fp = fopen(name, mode)) == NULL) 210 err("%s: %s", name, strerror(errno)); 211 return(fp); 212 } 213 214 void 215 obsolete(argv) 216 char *argv[]; 217 { 218 int len; 219 char *ap, *p, *start; 220 221 while (ap = *++argv) { 222 /* Return if "--" or not an option of any form. */ 223 if (ap[0] != '-') { 224 if (ap[0] != '+') 225 return; 226 } else if (ap[1] == '-') 227 return; 228 if (!isdigit(ap[1])) 229 continue; 230 /* 231 * Digit signifies an old-style option. Malloc space for dash, 232 * new option and argument. 233 */ 234 len = strlen(ap); 235 if ((start = p = malloc(len + 3)) == NULL) 236 err("%s", strerror(errno)); 237 *p++ = '-'; 238 *p++ = ap[0] == '+' ? 's' : 'f'; 239 (void)strcpy(p, ap + 1); 240 *argv = start; 241 } 242 } 243 244 void 245 usage() 246 { 247 (void)fprintf(stderr, 248 "usage: uniq [-c | -du] [-f fields] [-s chars] [input [output]]\n"); 249 exit(1); 250 } 251 252 #if __STDC__ 253 #include <stdarg.h> 254 #else 255 #include <varargs.h> 256 #endif 257 258 void 259 #if __STDC__ 260 err(const char *fmt, ...) 261 #else 262 err(fmt, va_alist) 263 char *fmt; 264 va_dcl 265 #endif 266 { 267 va_list ap; 268 #if __STDC__ 269 va_start(ap, fmt); 270 #else 271 va_start(ap); 272 #endif 273 (void)fprintf(stderr, "uniq: "); 274 (void)vfprintf(stderr, fmt, ap); 275 va_end(ap); 276 (void)fprintf(stderr, "\n"); 277 exit(1); 278 /* NOTREACHED */ 279 } 280