1 /* 2 * Copyright (c) 1987 Regents of the University of California. 3 * All rights reserved. 4 * 5 * Redistribution and use in source and binary forms, with or without 6 * modification, are permitted provided that the following conditions 7 * are met: 8 * 1. Redistributions of source code must retain the above copyright 9 * notice, this list of conditions and the following disclaimer. 10 * 2. Redistributions in binary form must reproduce the above copyright 11 * notice, this list of conditions and the following disclaimer in the 12 * documentation and/or other materials provided with the distribution. 13 * 3. All advertising materials mentioning features or use of this software 14 * must display the following acknowledgement: 15 * This product includes software developed by the University of 16 * California, Berkeley and its contributors. 17 * 4. Neither the name of the University nor the names of its contributors 18 * may be used to endorse or promote products derived from this software 19 * without specific prior written permission. 20 * 21 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 22 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 23 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 24 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 25 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 26 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 27 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 28 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 29 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 30 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 31 * SUCH DAMAGE. 32 */ 33 34 #ifndef lint 35 char copyright[] = 36 "@(#) Copyright (c) 1987, 1990 Regents of the University of California.\n\ 37 All rights reserved.\n"; 38 #endif /* not lint */ 39 40 #ifndef lint 41 /*static char sccsid[] = "from: @(#)cmp.c 5.3 (Berkeley) 6/1/90";*/ 42 static char rcsid[] = "$Id: cmp.c,v 1.6 1994/03/25 17:07:02 mycroft Exp $"; 43 #endif /* not lint */ 44 45 #include <sys/param.h> 46 #include <sys/file.h> 47 #include <sys/stat.h> 48 #include <stdio.h> 49 #include <stdlib.h> 50 #include <string.h> 51 #include <ctype.h> 52 #include <errno.h> 53 #include <locale.h> 54 #include <unistd.h> 55 56 #define EXITNODIFF 0 57 #define EXITDIFF 1 58 #define EXITERR 2 59 60 void skip __P(()); 61 __dead void cmp __P(()); 62 __dead void error __P(()); 63 __dead void endoffile __P(()); 64 __dead void usage __P(()); 65 66 int all, fd1, fd2, silent; 67 u_char buffer1[MAXBSIZE], buffer2[MAXBSIZE]; 68 char *file1, *file2; 69 70 int 71 main(argc, argv) 72 int argc; 73 char **argv; 74 { 75 int ch; 76 77 setlocale(LC_ALL, ""); 78 79 while ((ch = getopt(argc, argv, "ls")) != -1) 80 switch (ch) { 81 case 'l': /* print all differences */ 82 all = 1; 83 break; 84 case 's': /* silent run */ 85 silent = 1; 86 break; 87 case '?': 88 default: 89 usage(); 90 } 91 argv += optind; 92 argc -= optind; 93 94 if (argc < 2 || argc > 4) 95 usage(); 96 97 if (all && silent) 98 usage (); 99 100 if (strcmp(file1 = argv[0], "-") == 0) 101 fd1 = 0; 102 else if ((fd1 = open(file1, O_RDONLY, 0)) < 0) 103 error(file1); 104 if (strcmp(file2 = argv[1], "-") == 0) 105 fd2 = 0; 106 else if ((fd2 = open(file2, O_RDONLY, 0)) < 0) 107 error(file2); 108 if (fd1 == fd2) { 109 fprintf(stderr, 110 "cmp: standard input may only be specified once.\n"); 111 exit(EXITERR); 112 } 113 114 /* handle skip arguments */ 115 if (argc > 2) { 116 skip(strtoul(argv[2], NULL, 0), fd1, file1); 117 if (argc == 4) 118 skip(strtoul(argv[3], NULL, 0), fd2, file2); 119 } 120 cmp(); 121 /*NOTREACHED*/ 122 } 123 124 /* 125 * skip -- 126 * skip first part of file 127 */ 128 void 129 skip(dist, fd, fname) 130 register u_long dist; 131 register int fd; 132 char *fname; 133 { 134 register int rlen, nread; 135 136 for (; dist; dist -= rlen) { 137 rlen = MIN(dist, sizeof(buffer1)); 138 if ((nread = read(fd, buffer1, rlen)) != rlen) { 139 if (nread < 0) 140 error(fname); 141 else 142 endoffile(fname); 143 } 144 } 145 } 146 147 void 148 cmp() 149 { 150 register u_char *p1, *p2; 151 u_char *buf1, *buf2; 152 register int cnt; 153 int len = 0, len1 = 0, len2 = 0; 154 register long byte, line; 155 int dfound = 0; 156 157 for (byte = 0, line = 1; ; ) { 158 len1 -= len; 159 len2 -= len; 160 if (len1) 161 buf1 += len; 162 else 163 switch (len1 = read(fd1, buf1 = buffer1, MAXBSIZE)) { 164 case -1: 165 error(file1); 166 case 0: 167 if (len2) 168 endoffile(file1); 169 /* 170 * read of file 1 just failed, find out 171 * if there's anything left in file 2 172 */ 173 switch (read(fd2, buf2 = buffer2, 1)) { 174 case -1: 175 error(file2); 176 /* NOTREACHED */ 177 case 0: 178 exit(dfound ? EXITDIFF : EXITNODIFF); 179 /* NOTREACHED */ 180 default: 181 endoffile(file1); 182 break; 183 } 184 } 185 if (len2) 186 buf2 += len; 187 else 188 switch (len2 = read(fd2, buf2 = buffer2, MAXBSIZE)) { 189 case -1: 190 error(file2); 191 case 0: 192 /* 193 * read of file 2 just failed; we know there is 194 * data left in file 1 if we got this far 195 */ 196 endoffile(file2); 197 break; 198 } 199 /* 200 * Either file might be stdio. We compare only the minimum 201 * number of bytes we know are common, then loop back to the 202 * top. This avoids blocking on input if a difference is 203 * found early. 204 */ 205 if (len1 < len2) 206 len = len1; 207 else 208 len = len2; 209 if (memcmp(buf1, buf2, len)) { 210 if (silent) 211 exit(EXITDIFF); 212 if (all) { 213 dfound = 1; 214 for (p1 = buf1, p2 = buf2, cnt = len; cnt--; 215 ++p1, ++p2) { 216 ++byte; 217 if (*p1 != *p2) 218 printf("%6ld %3o %3o\n", 219 byte, *p1, *p2); 220 } 221 } else for (p1 = buf1, p2 = buf2; ; ++p1, ++p2) { 222 ++byte; 223 if (*p1 != *p2) { 224 printf("%s %s differ: char %ld, line %ld\n", file1, file2, byte, line); 225 exit(EXITDIFF); 226 } 227 if (*p1 == '\n') 228 ++line; 229 } 230 } else { 231 byte += len; 232 /* 233 * here's the real performance problem, we've got to 234 * count the stupid lines, which means that -l is a 235 * *much* faster version, i.e., unless you really 236 * *want* to know the line number, run -s or -l. 237 */ 238 if (!silent && !all) 239 for (p1 = buf1, cnt = len; cnt--; ) 240 if (*p1++ == '\n') 241 ++line; 242 } 243 } 244 } 245 246 /* 247 * error -- 248 * print I/O error message and die 249 */ 250 void 251 error(filename) 252 char *filename; 253 { 254 extern int errno; 255 char *strerror(); 256 257 if (!silent) 258 (void) fprintf(stderr, "cmp: %s: %s\n", 259 filename, strerror(errno)); 260 exit(EXITERR); 261 } 262 263 /* 264 * endoffile -- 265 * print end-of-file message and exit indicating the files were different 266 */ 267 void 268 endoffile(filename) 269 char *filename; 270 { 271 if (!silent) 272 (void) fprintf(stderr, "cmp: EOF on %s\n", filename); 273 exit(EXITDIFF); 274 } 275 276 /* 277 * usage -- 278 * print usage and die 279 */ 280 void 281 usage() 282 { 283 fputs("usage: cmp [-l | -s] file1 file2 [skip1] [skip2]\n", stderr); 284 exit(EXITERR); 285 } 286