1 /* $NetBSD: uniq.c,v 1.11 2003/08/07 11:16:56 agc 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. 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[] = "@(#)uniq.c 8.3 (Berkeley) 5/4/95"; 44 #endif 45 __RCSID("$NetBSD: uniq.c,v 1.11 2003/08/07 11:16:56 agc Exp $"); 46 #endif /* not lint */ 47 48 #include <err.h> 49 #include <errno.h> 50 #include <stdio.h> 51 #include <ctype.h> 52 #include <stdlib.h> 53 #include <string.h> 54 #include <unistd.h> 55 56 #define MAXLINELEN (8 * 1024) 57 58 int cflag, dflag, uflag; 59 int numchars, numfields, repeats; 60 61 FILE *file __P((char *, char *)); 62 int main __P((int, char **)); 63 void show __P((FILE *, char *)); 64 char *skip __P((char *)); 65 void obsolete __P((char *[])); 66 void usage __P((void)); 67 68 int 69 main (argc, argv) 70 int argc; 71 char *argv[]; 72 { 73 char *t1, *t2; 74 FILE *ifp, *ofp; 75 int ch; 76 char *prevline, *thisline, *p; 77 78 ifp = ofp = NULL; 79 obsolete(argv); 80 while ((ch = getopt(argc, argv, "-cdf:s:u")) != -1) 81 switch (ch) { 82 case '-': 83 --optind; 84 goto done; 85 case 'c': 86 cflag = 1; 87 break; 88 case 'd': 89 dflag = 1; 90 break; 91 case 'f': 92 numfields = strtol(optarg, &p, 10); 93 if (numfields < 0 || *p) 94 errx(1, "illegal field skip value: %s", optarg); 95 break; 96 case 's': 97 numchars = strtol(optarg, &p, 10); 98 if (numchars < 0 || *p) 99 errx(1, "illegal character skip value: %s", 100 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(1, "malloc"); 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 { 179 180 if (cflag && *str) 181 (void)fprintf(ofp, "%4d %s", repeats + 1, str); 182 if ((dflag && repeats) || (uflag && !repeats)) 183 (void)fprintf(ofp, "%s", str); 184 } 185 186 char * 187 skip(str) 188 char *str; 189 { 190 int infield, nchars, nfields; 191 192 for (nfields = numfields, infield = 0; nfields && *str; ++str) 193 if (isspace((unsigned char)*str)) { 194 if (infield) { 195 infield = 0; 196 --nfields; 197 } 198 } else if (!infield) 199 infield = 1; 200 for (nchars = numchars; nchars-- && *str; ++str); 201 return(str); 202 } 203 204 FILE * 205 file(name, mode) 206 char *name, *mode; 207 { 208 FILE *fp; 209 210 if ((fp = fopen(name, mode)) == NULL) 211 err(1, "%s", name); 212 return(fp); 213 } 214 215 void 216 obsolete(argv) 217 char *argv[]; 218 { 219 char *ap, *p, *start; 220 221 while ((ap = *++argv) != NULL) { 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((unsigned char)ap[1])) 229 continue; 230 /* 231 * Digit signifies an old-style option. Malloc space for dash, 232 * new option and argument. 233 */ 234 asprintf(&p, "-%c%s", ap[0] == '+' ? 's' : 'f', ap + 1); 235 if (!p) 236 err(1, "malloc"); 237 start = p; 238 *argv = start; 239 } 240 } 241 242 void 243 usage() 244 { 245 (void)fprintf(stderr, 246 "usage: uniq [-c | -du] [-f fields] [-s chars] [input [output]]\n"); 247 exit(1); 248 } 249