1 /* 2 * Copyright (c) 1988, 1993 3 * The Regents of the University of California. 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 #include <sys/cdefs.h> 35 36 __FBSDID("$FreeBSD$"); 37 38 #ifndef lint 39 static const char copyright[] = 40 "@(#) Copyright (c) 1988, 1993\n\ 41 The Regents of the University of California. All rights reserved.\n"; 42 #endif 43 44 #ifndef lint 45 static const char sccsid[] = "@(#)tr.c 8.2 (Berkeley) 5/4/95"; 46 #endif 47 48 #include <sys/types.h> 49 50 #include <ctype.h> 51 #include <err.h> 52 #include <locale.h> 53 #include <stdio.h> 54 #include <stdlib.h> 55 #include <string.h> 56 #include <unistd.h> 57 58 #include "extern.h" 59 60 /* 61 * For -C option: determine whether a byte is a valid character in the 62 * current character set (as defined by LC_CTYPE). 63 */ 64 #define ISCHAR(c) (iscntrl(c) || isprint(c)) 65 66 static int string1[NCHARS] = { 67 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* ASCII */ 68 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, 69 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 70 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 71 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 72 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, 73 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 74 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, 75 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 76 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, 77 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 78 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, 79 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 80 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, 81 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 82 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, 83 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 84 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, 85 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 86 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, 87 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, 88 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, 89 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, 90 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, 91 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 92 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, 93 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 94 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, 95 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 96 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 97 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 98 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 99 }, string2[NCHARS]; 100 101 STR s1 = { STRING1, NORMAL, 0, OOBCH, { 0, OOBCH }, NULL, NULL }; 102 STR s2 = { STRING2, NORMAL, 0, OOBCH, { 0, OOBCH }, NULL, NULL }; 103 104 static int charcoll(const void *, const void *); 105 static void setup(int *, char *, STR *, int, int); 106 static void usage(void); 107 108 int 109 main(argc, argv) 110 int argc; 111 char **argv; 112 { 113 static int collorder[NCHARS], tmpmap[NCHARS]; 114 int ch, cnt, lastch, *p; 115 int Cflag, cflag, dflag, sflag, isstring2; 116 117 (void)setlocale(LC_ALL, ""); 118 119 Cflag = cflag = dflag = sflag = 0; 120 while ((ch = getopt(argc, argv, "Ccdsu")) != -1) 121 switch((char)ch) { 122 case 'C': 123 Cflag = 1; 124 cflag = 0; 125 break; 126 case 'c': 127 cflag = 1; 128 Cflag = 0; 129 break; 130 case 'd': 131 dflag = 1; 132 break; 133 case 's': 134 sflag = 1; 135 break; 136 case 'u': 137 setbuf(stdout, (char *)NULL); 138 break; 139 case '?': 140 default: 141 usage(); 142 } 143 argc -= optind; 144 argv += optind; 145 146 switch(argc) { 147 case 0: 148 default: 149 usage(); 150 /* NOTREACHED */ 151 case 1: 152 isstring2 = 0; 153 break; 154 case 2: 155 isstring2 = 1; 156 break; 157 } 158 159 /* 160 * tr -ds [-Cc] string1 string2 161 * Delete all characters (or complemented characters) in string1. 162 * Squeeze all characters in string2. 163 */ 164 if (dflag && sflag) { 165 if (!isstring2) 166 usage(); 167 168 setup(string1, argv[0], &s1, cflag, Cflag); 169 setup(string2, argv[1], &s2, 0, 0); 170 171 for (lastch = OOBCH; (ch = getchar()) != EOF;) 172 if (!string1[ch] && (!string2[ch] || lastch != ch)) { 173 lastch = ch; 174 (void)putchar(ch); 175 } 176 exit(0); 177 } 178 179 /* 180 * tr -d [-Cc] string1 181 * Delete all characters (or complemented characters) in string1. 182 */ 183 if (dflag) { 184 if (isstring2) 185 usage(); 186 187 setup(string1, argv[0], &s1, cflag, Cflag); 188 189 while ((ch = getchar()) != EOF) 190 if (!string1[ch]) 191 (void)putchar(ch); 192 exit(0); 193 } 194 195 /* 196 * tr -s [-Cc] string1 197 * Squeeze all characters (or complemented characters) in string1. 198 */ 199 if (sflag && !isstring2) { 200 setup(string1, argv[0], &s1, cflag, Cflag); 201 202 for (lastch = OOBCH; (ch = getchar()) != EOF;) 203 if (!string1[ch] || lastch != ch) { 204 lastch = ch; 205 (void)putchar(ch); 206 } 207 exit(0); 208 } 209 210 /* 211 * tr [-Ccs] string1 string2 212 * Replace all characters (or complemented characters) in string1 with 213 * the character in the same position in string2. If the -s option is 214 * specified, squeeze all the characters in string2. 215 */ 216 if (!isstring2) 217 usage(); 218 219 s1.str = argv[0]; 220 s2.str = argv[1]; 221 222 if (cflag || Cflag) 223 for (cnt = NCHARS, p = string1; cnt--;) 224 *p++ = OOBCH; 225 226 if (!next(&s2)) 227 errx(1, "empty string2"); 228 229 ch = s2.lastch; 230 /* If string2 runs out of characters, use the last one specified. */ 231 if (sflag) 232 while (next(&s1)) { 233 string1[s1.lastch] = ch = s2.lastch; 234 string2[ch] = 1; 235 (void)next(&s2); 236 } 237 else 238 while (next(&s1)) { 239 string1[s1.lastch] = ch = s2.lastch; 240 (void)next(&s2); 241 } 242 243 if (cflag || Cflag) { 244 s2.str = argv[1]; 245 s2.state = NORMAL; 246 for (cnt = 0, p = string1; cnt < NCHARS; ++p, ++cnt) { 247 if (*p == OOBCH && (!Cflag || ISCHAR(cnt))) { 248 (void)next(&s2); 249 *p = s2.lastch; 250 } else 251 *p = cnt; 252 } 253 } 254 if (Cflag) { 255 /* 256 * Generate a table for locale single-byte collating element 257 * ordering and use it to reorder string1 as required by 258 * IEEE Std. 1003.1-2001. 259 */ 260 for (ch = 0; ch < NCHARS; ch++) 261 collorder[ch] = ch; 262 mergesort(collorder, NCHARS, sizeof(*collorder), charcoll); 263 for (ch = 0; ch < NCHARS; ch++) 264 tmpmap[ch] = string1[collorder[ch]]; 265 memcpy(string1, tmpmap, sizeof(tmpmap)); 266 } 267 268 if (sflag) 269 for (lastch = OOBCH; (ch = getchar()) != EOF;) { 270 ch = string1[ch]; 271 if (!string2[ch] || lastch != ch) { 272 lastch = ch; 273 (void)putchar(ch); 274 } 275 } 276 else 277 while ((ch = getchar()) != EOF) 278 (void)putchar(string1[ch]); 279 exit (0); 280 } 281 282 static void 283 setup(string, arg, str, cflag, Cflag) 284 int *string; 285 char *arg; 286 STR *str; 287 int cflag; 288 int Cflag; 289 { 290 int cnt, *p; 291 292 str->str = arg; 293 bzero(string, NCHARS * sizeof(int)); 294 while (next(str)) 295 string[str->lastch] = 1; 296 if (cflag) 297 for (p = string, cnt = NCHARS; cnt--; ++p) 298 *p = !*p; 299 else if (Cflag) 300 for (cnt = 0; cnt < NCHARS; cnt++) 301 string[cnt] = !string[cnt] && ISCHAR(cnt); 302 } 303 304 static int 305 charcoll(const void *a, const void *b) 306 { 307 char sa[2], sb[2]; 308 309 sa[0] = *(const int *)a; 310 sb[0] = *(const int *)b; 311 sa[1] = sb[1] = '\0'; 312 return (strcoll(sa, sb)); 313 } 314 315 static void 316 usage() 317 { 318 (void)fprintf(stderr, "%s\n%s\n%s\n%s\n", 319 "usage: tr [-Ccsu] string1 string2", 320 " tr [-Ccu] -d string1", 321 " tr [-Ccu] -s string1", 322 " tr [-Ccu] -ds string1 string2"); 323 exit(1); 324 } 325