Annotation of src/usr.bin/uniq/uniq.c, Revision 1.14
1.14 ! millert 1: /* $OpenBSD: uniq.c,v 1.13 2003/04/05 16:17:26 deraadt Exp $ */
1.1 deraadt 2: /* $NetBSD: uniq.c,v 1.7 1995/08/31 22:03:48 jtc Exp $ */
3:
4: /*
5: * Copyright (c) 1989, 1993
6: * The Regents of the University of California. All rights reserved.
7: *
8: * This code is derived from software contributed to Berkeley by
9: * Case Larsen.
10: *
11: * Redistribution and use in source and binary forms, with or without
12: * modification, are permitted provided that the following conditions
13: * are met:
14: * 1. Redistributions of source code must retain the above copyright
15: * notice, this list of conditions and the following disclaimer.
16: * 2. Redistributions in binary form must reproduce the above copyright
17: * notice, this list of conditions and the following disclaimer in the
18: * documentation and/or other materials provided with the distribution.
1.14 ! millert 19: * 3. Neither the name of the University nor the names of its contributors
1.1 deraadt 20: * may be used to endorse or promote products derived from this software
21: * without specific prior written permission.
22: *
23: * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
24: * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
25: * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
26: * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
27: * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
28: * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
29: * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
30: * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
31: * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
32: * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
33: * SUCH DAMAGE.
34: */
35:
36: #ifndef lint
37: static char copyright[] =
38: "@(#) Copyright (c) 1989, 1993\n\
39: The Regents of the University of California. All rights reserved.\n";
40: #endif /* not lint */
41:
42: #ifndef lint
43: #if 0
44: static char sccsid[] = "@(#)uniq.c 8.3 (Berkeley) 5/4/95";
45: #endif
1.14 ! millert 46: static char rcsid[] = "$OpenBSD: uniq.c,v 1.13 2003/04/05 16:17:26 deraadt Exp $";
1.1 deraadt 47: #endif /* not lint */
48:
49: #include <errno.h>
50: #include <stdio.h>
51: #include <ctype.h>
52: #include <stdlib.h>
53: #include <string.h>
54: #include <unistd.h>
1.5 mickey 55: #include <err.h>
1.1 deraadt 56:
57: #define MAXLINELEN (8 * 1024)
58:
59: int cflag, dflag, uflag;
60: int numchars, numfields, repeats;
61:
1.9 millert 62: FILE *file(char *, char *);
63: void show(FILE *, char *);
64: char *skip(char *);
65: void obsolete(char *[]);
66: void usage(void);
1.1 deraadt 67:
68: int
1.10 deraadt 69: main(int argc, char *argv[])
1.1 deraadt 70: {
1.8 mpech 71: char *t1, *t2;
1.10 deraadt 72: FILE *ifp = NULL, *ofp = NULL;
1.1 deraadt 73: int ch;
74: char *prevline, *thisline, *p;
75:
76: obsolete(argv);
1.11 millert 77: while ((ch = getopt(argc, argv, "cdf:s:u")) != -1)
1.1 deraadt 78: switch (ch) {
79: case 'c':
80: cflag = 1;
81: break;
82: case 'd':
83: dflag = 1;
84: break;
85: case 'f':
86: numfields = strtol(optarg, &p, 10);
87: if (numfields < 0 || *p)
1.5 mickey 88: errx(1, "illegal field skip value: %s", optarg);
1.1 deraadt 89: break;
90: case 's':
91: numchars = strtol(optarg, &p, 10);
92: if (numchars < 0 || *p)
1.5 mickey 93: errx(1, "illegal character skip value: %s", optarg);
1.1 deraadt 94: break;
95: case 'u':
96: uflag = 1;
97: break;
98: case '?':
99: default:
100: usage();
101: }
102:
1.11 millert 103: argc -= optind;
1.1 deraadt 104: argv +=optind;
105:
106: /* If no flags are set, default is -d -u. */
107: if (cflag) {
108: if (dflag || uflag)
109: usage();
110: } else if (!dflag && !uflag)
111: dflag = uflag = 1;
112:
113: switch(argc) {
114: case 0:
115: ifp = stdin;
116: ofp = stdout;
117: break;
118: case 1:
119: ifp = file(argv[0], "r");
120: ofp = stdout;
121: break;
122: case 2:
123: ifp = file(argv[0], "r");
124: ofp = file(argv[1], "w");
125: break;
126: default:
127: usage();
128: }
129:
130: prevline = malloc(MAXLINELEN);
131: thisline = malloc(MAXLINELEN);
132: if (prevline == NULL || thisline == NULL)
1.5 mickey 133: err(1, "malloc");
1.1 deraadt 134:
135: if (fgets(prevline, MAXLINELEN, ifp) == NULL)
136: exit(0);
137:
138: while (fgets(thisline, MAXLINELEN, ifp)) {
139: /* If requested get the chosen fields + character offsets. */
140: if (numfields || numchars) {
141: t1 = skip(thisline);
142: t2 = skip(prevline);
143: } else {
144: t1 = thisline;
145: t2 = prevline;
146: }
147:
148: /* If different, print; set previous to new value. */
149: if (strcmp(t1, t2)) {
150: show(ofp, prevline);
151: t1 = prevline;
152: prevline = thisline;
153: thisline = t1;
154: repeats = 0;
155: } else
156: ++repeats;
157: }
158: show(ofp, prevline);
159: exit(0);
160: }
161:
162: /*
163: * show --
164: * Output a line depending on the flags and number of repetitions
165: * of the line.
166: */
167: void
1.10 deraadt 168: show(FILE *ofp, char *str)
1.1 deraadt 169: {
170:
171: if (cflag && *str)
172: (void)fprintf(ofp, "%4d %s", repeats + 1, str);
173: if (dflag && repeats || uflag && !repeats)
174: (void)fprintf(ofp, "%s", str);
175: }
176:
177: char *
1.10 deraadt 178: skip(char *str)
1.1 deraadt 179: {
1.8 mpech 180: int infield, nchars, nfields;
1.1 deraadt 181:
182: for (nfields = numfields, infield = 0; nfields && *str; ++str)
183: if (isspace(*str)) {
184: if (infield) {
185: infield = 0;
186: --nfields;
187: }
188: } else if (!infield)
189: infield = 1;
190: for (nchars = numchars; nchars-- && *str; ++str);
191: return(str);
192: }
193:
194: FILE *
1.10 deraadt 195: file(char *name, char *mode)
1.1 deraadt 196: {
197: FILE *fp;
198:
1.12 millert 199: if (strcmp(name, "-") == 0)
200: return(*mode == 'r' ? stdin : stdout);
1.1 deraadt 201: if ((fp = fopen(name, mode)) == NULL)
1.6 millert 202: err(1, "%s", name);
1.1 deraadt 203: return(fp);
204: }
205:
206: void
1.10 deraadt 207: obsolete(char *argv[])
1.1 deraadt 208: {
209: int len;
210: char *ap, *p, *start;
211:
1.7 deraadt 212: while ((ap = *++argv)) {
1.1 deraadt 213: /* Return if "--" or not an option of any form. */
214: if (ap[0] != '-') {
215: if (ap[0] != '+')
216: return;
217: } else if (ap[1] == '-')
218: return;
219: if (!isdigit(ap[1]))
220: continue;
221: /*
222: * Digit signifies an old-style option. Malloc space for dash,
223: * new option and argument.
224: */
1.13 deraadt 225: len = strlen(ap) + 3;
226: if ((start = p = malloc(len)) == NULL)
1.5 mickey 227: err(1, "malloc");
1.1 deraadt 228: *p++ = '-';
229: *p++ = ap[0] == '+' ? 's' : 'f';
1.13 deraadt 230: (void)strlcpy(p, ap + 1, len - 2);
1.1 deraadt 231: *argv = start;
232: }
233: }
234:
235: void
1.10 deraadt 236: usage(void)
1.1 deraadt 237: {
238: (void)fprintf(stderr,
239: "usage: uniq [-c | -du] [-f fields] [-s chars] [input [output]]\n");
240: exit(1);
241: }