1 /*- 2 * SPDX-License-Identifier: BSD-3-Clause 3 * 4 * Copyright (c) 1989, 1993, 1994 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 <err.h> 36 #include <limits.h> 37 #include <locale.h> 38 #include <stdint.h> 39 #include <stdio.h> 40 #include <stdlib.h> 41 #include <string.h> 42 #include <unistd.h> 43 #include <wchar.h> 44 #include <wctype.h> 45 46 static int iflag; 47 static const char *tabs[] = { "", "\t", "\t\t" }; 48 49 static FILE *file(const char *); 50 static wchar_t *convert(const char *); 51 static void show(FILE *, const char *, const char *, char **, size_t *); 52 static void usage(void); 53 54 int 55 main(int argc, char *argv[]) 56 { 57 int comp, read1, read2; 58 int ch, flag1, flag2, flag3; 59 FILE *fp1, *fp2; 60 const char *col1, *col2, *col3; 61 size_t line1len, line2len; 62 char *line1, *line2; 63 ssize_t n1, n2; 64 wchar_t *tline1, *tline2; 65 const char **p; 66 67 (void) setlocale(LC_ALL, ""); 68 69 flag1 = flag2 = flag3 = 1; 70 71 while ((ch = getopt(argc, argv, "123i")) != -1) 72 switch(ch) { 73 case '1': 74 flag1 = 0; 75 break; 76 case '2': 77 flag2 = 0; 78 break; 79 case '3': 80 flag3 = 0; 81 break; 82 case 'i': 83 iflag = 1; 84 break; 85 case '?': 86 default: 87 usage(); 88 } 89 argc -= optind; 90 argv += optind; 91 92 if (argc != 2) 93 usage(); 94 95 fp1 = file(argv[0]); 96 fp2 = file(argv[1]); 97 98 /* for each column printed, add another tab offset */ 99 p = tabs; 100 col1 = col2 = col3 = NULL; 101 if (flag1) 102 col1 = *p++; 103 if (flag2) 104 col2 = *p++; 105 if (flag3) 106 col3 = *p; 107 108 line1len = line2len = 0; 109 line1 = line2 = NULL; 110 n1 = n2 = -1; 111 112 for (read1 = read2 = 1;;) { 113 /* read next line, check for EOF */ 114 if (read1) { 115 n1 = getline(&line1, &line1len, fp1); 116 if (n1 < 0 && ferror(fp1)) 117 err(1, "%s", argv[0]); 118 if (n1 > 0 && line1[n1 - 1] == '\n') 119 line1[n1 - 1] = '\0'; 120 121 } 122 if (read2) { 123 n2 = getline(&line2, &line2len, fp2); 124 if (n2 < 0 && ferror(fp2)) 125 err(1, "%s", argv[1]); 126 if (n2 > 0 && line2[n2 - 1] == '\n') 127 line2[n2 - 1] = '\0'; 128 } 129 130 /* if one file done, display the rest of the other file */ 131 if (n1 < 0) { 132 if (n2 >= 0) 133 show(fp2, argv[1], col2, &line2, &line2len); 134 break; 135 } 136 if (n2 < 0) { 137 if (n1 >= 0) 138 show(fp1, argv[0], col1, &line1, &line1len); 139 break; 140 } 141 142 tline2 = NULL; 143 if ((tline1 = convert(line1)) != NULL) 144 tline2 = convert(line2); 145 if (tline1 == NULL || tline2 == NULL) 146 comp = strcmp(line1, line2); 147 else 148 comp = wcscoll(tline1, tline2); 149 if (tline1 != NULL) 150 free(tline1); 151 if (tline2 != NULL) 152 free(tline2); 153 154 /* lines are the same */ 155 if (!comp) { 156 read1 = read2 = 1; 157 if (col3 != NULL) 158 (void)printf("%s%s\n", col3, line1); 159 continue; 160 } 161 162 /* lines are different */ 163 if (comp < 0) { 164 read1 = 1; 165 read2 = 0; 166 if (col1 != NULL) 167 (void)printf("%s%s\n", col1, line1); 168 } else { 169 read1 = 0; 170 read2 = 1; 171 if (col2 != NULL) 172 (void)printf("%s%s\n", col2, line2); 173 } 174 } 175 if (ferror(stdout) != 0 || fflush(stdout) != 0) 176 err(1, "stdout"); 177 exit(0); 178 } 179 180 static wchar_t * 181 convert(const char *str) 182 { 183 size_t n; 184 wchar_t *buf, *p; 185 186 if ((n = mbstowcs(NULL, str, 0)) == (size_t)-1) 187 return (NULL); 188 if (SIZE_MAX / sizeof(*buf) < n + 1) 189 errx(1, "conversion buffer length overflow"); 190 if ((buf = malloc((n + 1) * sizeof(*buf))) == NULL) 191 err(1, "malloc"); 192 if (mbstowcs(buf, str, n + 1) != n) 193 errx(1, "internal mbstowcs() error"); 194 195 if (iflag) { 196 for (p = buf; *p != L'\0'; p++) 197 *p = towlower(*p); 198 } 199 200 return (buf); 201 } 202 203 static void 204 show(FILE *fp, const char *fn, const char *offset, char **bufp, size_t *buflenp) 205 { 206 ssize_t n; 207 208 do { 209 /* offset is NULL when draining fp, not printing */ 210 if (offset != NULL) 211 (void)printf("%s%s\n", offset, *bufp); 212 if ((n = getline(bufp, buflenp, fp)) < 0) 213 break; 214 if (n > 0 && offset != NULL && (*bufp)[n - 1] == '\n') 215 (*bufp)[n - 1] = '\0'; 216 } while (1); 217 if (ferror(fp)) 218 err(1, "%s", fn); 219 } 220 221 static FILE * 222 file(const char *name) 223 { 224 FILE *fp; 225 226 if (!strcmp(name, "-")) 227 return (stdin); 228 if ((fp = fopen(name, "r")) == NULL) { 229 err(1, "%s", name); 230 } 231 return (fp); 232 } 233 234 static void 235 usage(void) 236 { 237 (void)fprintf(stderr, "usage: comm [-123i] file1 file2\n"); 238 exit(1); 239 } 240