1 /* 2 * Copyright (c) 1989, 1993, 1994 3 * The Regents of the University of California. All rights reserved. 4 * 5 * This code is derived from software contributed to Berkeley by 6 * Case Larsen. 7 * 8 * Redistribution and use in source and binary forms, with or without 9 * modification, are permitted provided that the following conditions 10 * are met: 11 * 1. Redistributions of source code must retain the above copyright 12 * notice, this list of conditions and the following disclaimer. 13 * 2. Redistributions in binary form must reproduce the above copyright 14 * notice, this list of conditions and the following disclaimer in the 15 * documentation and/or other materials provided with the distribution. 16 * 3. All advertising materials mentioning features or use of this software 17 * must display the following acknowledgement: 18 * This product includes software developed by the University of 19 * California, Berkeley and its contributors. 20 * 4. Neither the name of the University nor the names of its contributors 21 * may be used to endorse or promote products derived from this software 22 * without specific prior written permission. 23 * 24 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 27 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 34 * SUCH DAMAGE. 35 */ 36 37 #ifndef lint 38 static const char copyright[] = 39 "@(#) Copyright (c) 1989, 1993, 1994\n\ 40 The Regents of the University of California. All rights reserved.\n"; 41 #endif 42 43 #if 0 44 #ifndef lint 45 static char sccsid[] = "From: @(#)comm.c 8.4 (Berkeley) 5/4/95"; 46 #endif 47 #endif 48 49 #include <sys/cdefs.h> 50 __FBSDID("$FreeBSD$"); 51 52 #include <err.h> 53 #include <limits.h> 54 #include <locale.h> 55 #include <stdint.h> 56 #include <stdio.h> 57 #include <stdlib.h> 58 #include <string.h> 59 #include <unistd.h> 60 #include <wchar.h> 61 #include <wctype.h> 62 63 #define INITLINELEN (LINE_MAX + 1) 64 #define MAXLINELEN ((SIZE_MAX / sizeof(wchar_t)) / 2) 65 66 const wchar_t *tabs[] = { L"", L"\t", L"\t\t" }; 67 68 FILE *file(const char *); 69 wchar_t *getline(wchar_t *, size_t *, FILE *); 70 void show(FILE *, const char *, const wchar_t *, wchar_t *, size_t *); 71 int wcsicoll(const wchar_t *, const wchar_t *); 72 static void usage(void); 73 74 int 75 main(int argc, char *argv[]) 76 { 77 int comp, read1, read2; 78 int ch, flag1, flag2, flag3, iflag; 79 FILE *fp1, *fp2; 80 const wchar_t *col1, *col2, *col3; 81 size_t line1len, line2len; 82 wchar_t *line1, *line2; 83 const wchar_t **p; 84 85 flag1 = flag2 = flag3 = 1; 86 iflag = 0; 87 88 line1len = INITLINELEN; 89 line2len = INITLINELEN; 90 line1 = malloc(line1len * sizeof(*line1)); 91 line2 = malloc(line2len * sizeof(*line2)); 92 if (line1 == NULL || line2 == NULL) 93 err(1, "malloc"); 94 95 (void) setlocale(LC_ALL, ""); 96 97 while ((ch = getopt(argc, argv, "123i")) != -1) 98 switch(ch) { 99 case '1': 100 flag1 = 0; 101 break; 102 case '2': 103 flag2 = 0; 104 break; 105 case '3': 106 flag3 = 0; 107 break; 108 case 'i': 109 iflag = 1; 110 break; 111 case '?': 112 default: 113 usage(); 114 } 115 argc -= optind; 116 argv += optind; 117 118 if (argc != 2) 119 usage(); 120 121 fp1 = file(argv[0]); 122 fp2 = file(argv[1]); 123 124 /* for each column printed, add another tab offset */ 125 p = tabs; 126 col1 = col2 = col3 = NULL; 127 if (flag1) 128 col1 = *p++; 129 if (flag2) 130 col2 = *p++; 131 if (flag3) 132 col3 = *p; 133 134 for (read1 = read2 = 1;;) { 135 /* read next line, check for EOF */ 136 if (read1) { 137 line1 = getline(line1, &line1len, fp1); 138 if (line1 == NULL && ferror(fp1)) 139 err(1, "%s", argv[0]); 140 } 141 if (read2) { 142 line2 = getline(line2, &line2len, fp2); 143 if (line2 == NULL && ferror(fp2)) 144 err(1, "%s", argv[1]); 145 } 146 147 /* if one file done, display the rest of the other file */ 148 if (line1 == NULL) { 149 if (line2 != NULL && col2 != NULL) 150 show(fp2, argv[1], col2, line2, &line2len); 151 break; 152 } 153 if (line2 == NULL) { 154 if (line1 != NULL && col1 != NULL) 155 show(fp1, argv[0], col1, line1, &line1len); 156 break; 157 } 158 159 /* lines are the same */ 160 if(iflag) 161 comp = wcsicoll(line1, line2); 162 else 163 comp = wcscoll(line1, line2); 164 165 if (!comp) { 166 read1 = read2 = 1; 167 if (col3 != NULL) 168 (void)printf("%ls%ls\n", col3, line1); 169 continue; 170 } 171 172 /* lines are different */ 173 if (comp < 0) { 174 read1 = 1; 175 read2 = 0; 176 if (col1 != NULL) 177 (void)printf("%ls%ls\n", col1, line1); 178 } else { 179 read1 = 0; 180 read2 = 1; 181 if (col2 != NULL) 182 (void)printf("%ls%ls\n", col2, line2); 183 } 184 } 185 exit(0); 186 } 187 188 wchar_t * 189 getline(wchar_t *buf, size_t *buflen, FILE *fp) 190 { 191 size_t bufpos; 192 wint_t ch; 193 194 bufpos = 0; 195 while ((ch = getwc(fp)) != WEOF && ch != '\n') { 196 if (bufpos + 1 >= *buflen) { 197 *buflen = *buflen * 2; 198 if (*buflen > MAXLINELEN) 199 errx(1, 200 "Maximum line buffer length (%zu) exceeded", 201 MAXLINELEN); 202 buf = reallocf(buf, *buflen * sizeof(*buf)); 203 if (buf == NULL) 204 err(1, "reallocf"); 205 } 206 buf[bufpos++] = ch; 207 } 208 buf[bufpos] = '\0'; 209 210 return (bufpos != 0 || ch == '\n' ? buf : NULL); 211 } 212 213 void 214 show(FILE *fp, const char *fn, const wchar_t *offset, wchar_t *buf, size_t *buflen) 215 { 216 217 do { 218 (void)printf("%ls%ls\n", offset, buf); 219 } while ((buf = getline(buf, buflen, fp)) != NULL); 220 if (ferror(fp)) 221 err(1, "%s", fn); 222 } 223 224 FILE * 225 file(const char *name) 226 { 227 FILE *fp; 228 229 if (!strcmp(name, "-")) 230 return (stdin); 231 if ((fp = fopen(name, "r")) == NULL) { 232 err(1, "%s", name); 233 } 234 return (fp); 235 } 236 237 static void 238 usage(void) 239 { 240 (void)fprintf(stderr, "usage: comm [-123i] file1 file2\n"); 241 exit(1); 242 } 243 244 static size_t wcsicoll_l1_buflen = 0, wcsicoll_l2_buflen = 0; 245 static wchar_t *wcsicoll_l1_buf = NULL, *wcsicoll_l2_buf = NULL; 246 247 int 248 wcsicoll(const wchar_t *s1, const wchar_t *s2) 249 { 250 wchar_t *p; 251 size_t l1, l2; 252 size_t new_l1_buflen, new_l2_buflen; 253 254 l1 = wcslen(s1) + 1; 255 l2 = wcslen(s2) + 1; 256 new_l1_buflen = wcsicoll_l1_buflen; 257 new_l2_buflen = wcsicoll_l2_buflen; 258 while (new_l1_buflen < l1) { 259 if (new_l1_buflen == 0) 260 new_l1_buflen = INITLINELEN; 261 else 262 new_l1_buflen *= 2; 263 } 264 while (new_l2_buflen < l2) { 265 if (new_l2_buflen == 0) 266 new_l2_buflen = INITLINELEN; 267 else 268 new_l2_buflen *= 2; 269 } 270 if (new_l1_buflen > wcsicoll_l1_buflen) { 271 wcsicoll_l1_buf = reallocf(wcsicoll_l1_buf, new_l1_buflen * sizeof(*wcsicoll_l1_buf)); 272 if (wcsicoll_l1_buf == NULL) 273 err(1, "reallocf"); 274 wcsicoll_l1_buflen = new_l1_buflen; 275 } 276 if (new_l2_buflen > wcsicoll_l2_buflen) { 277 wcsicoll_l2_buf = reallocf(wcsicoll_l2_buf, new_l2_buflen * sizeof(*wcsicoll_l2_buf)); 278 if (wcsicoll_l2_buf == NULL) 279 err(1, "reallocf"); 280 wcsicoll_l2_buflen = new_l2_buflen; 281 } 282 283 for (p = wcsicoll_l1_buf; *s1; s1++) 284 *p++ = towlower(*s1); 285 *p = '\0'; 286 for (p = wcsicoll_l2_buf; *s2; s2++) 287 *p++ = towlower(*s2); 288 *p = '\0'; 289 290 return (wcscoll(wcsicoll_l1_buf, wcsicoll_l2_buf)); 291 } 292