logo

utils-std

Collection of commonly available Unix tools git clone https://anongit.hacktivis.me/git/utils-std.git/

tr.c (7773B)

    

  1. // SPDX-License-Identifier: BSD-3-Clause
  2. /*	$OpenBSD: tr.c,v 1.22 2022/12/04 23:50:49 cheloha Exp $	*/
  3. /*	$NetBSD: tr.c,v 1.5 1995/08/31 22:13:48 jtc Exp $	*/
  4. /*
  5.  * Copyright (c) 1988, 1993
  6.  *	The Regents of the University of California.  All rights reserved.
  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. Neither the name of the University nor the names of its contributors
  17.  *    may be used to endorse or promote products derived from this software
  18.  *    without specific prior written permission.
  19.  *
  20.  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  21.  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  22.  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  23.  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  24.  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  25.  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  26.  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  27.  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  28.  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  29.  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  30.  * SUCH DAMAGE.
  31.  */
  33. #define _DEFAULT_SOURCE
  35. #include "../config.h"
  36. #include "../lib/tr_str.h"
  37. #include "../libutils/err.h"
  38. #include "../libutils/getopt_nolong.h"
  40. #include <stdio.h>
  41. #include <stdlib.h>
  42. #include <string.h>
  43. #include <strings.h> // bzero
  44. #include <sys/types.h>
  45. #include <unistd.h>
  46. #ifdef HAS_GETOPT_LONG
  47. #include <getopt.h>
  48. #endif
  50. int delete[NCHARS], squeeze[NCHARS];
  51. int translate[NCHARS] = {
  52.     0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* ASCII */
  53.     0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
  54.     0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
  55.     0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
  56.     0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
  57.     0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
  58.     0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
  59.     0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
  60.     0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
  61.     0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
  62.     0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7,
  63.     0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7,
  64.     0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7,
  65.     0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7,
  66.     0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7,
  67.     0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7,
  68.     0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff,
  69. };
  71. STR s1 = {STRING1, NORMAL, 0, OOBCH, {0, OOBCH}, NULL, NULL};
  72. STR s2 = {STRING2, NORMAL, 0, OOBCH, {0, OOBCH}, NULL, NULL};
  74. const char *argv0 = "tr";
  76. static void setup(int *, char *, STR *, int);
  77. static void usage(void);
  79. int
  80. main(int argc, char *argv[])
  81. {
  82. 	int cflag, dflag, sflag;
  84. 	cflag = dflag = sflag = 0;
  85. #ifdef HAS_GETOPT_LONG
  86. 	// Strictly for GNUisms compatibility so no long-only options
  87. 	// clang-format off
  88. 	static struct option opts[] = {
  89. 		{"complement", no_argument, NULL, 'c'},
  90. 		{"delete", no_argument, NULL, 'd'},
  91. 		{"squeeze-repeats", no_argument, NULL, 's'},
  92. 		{0, 0, 0, 0},
  93. 	};
  94. 	// clang-format on
  96. 	// Need + as first character to get POSIX-style option parsing
  97. 	for(int c = -1; (c = getopt_long(argc, argv, "+:Ccds", opts, NULL)) != -1;)
  98. #else
  99. 	for(int c = -1; (c = getopt_nolong(argc, argv, ":Ccds")) != -1;)
  100. #endif
  101. 	{
  102. 		switch(c)
  103. 		{
  104. 		case 'C':
  105. 		case 'c':
  106. 			cflag = 1;
  107. 			break;
  108. 		case 'd':
  109. 			dflag = 1;
  110. 			break;
  111. 		case 's':
  112. 			sflag = 1;
  113. 			break;
  114. 		case ':':
  115. 			fprintf(stderr, "%s: error: Option '-%c' requires an operand\n", argv0, optopt);
  116. 			usage();
  117. 			return 1;
  118. 		case '?':
  119. 			GETOPT_UNKNOWN_OPT
  120. 			usage();
  121. 			return 1;
  122. 		default:
  123. 			fprintf(stderr, "%s: error: Unhandled getopt case '%c'\n", argv0, c);
  124. 			usage();
  125. 			abort();
  126. 		}
  127. 	}
  128. 	argc -= optind;
  129. 	argv += optind;
  131. 	if(argc < 1 || argc > 2) usage();
  133. 	int ch, cnt, lastch, *p;
  135. 	/*
  136. 	 * tr -ds [-Cc] string1 string2
  137. 	 * Delete all characters (or complemented characters) in string1.
  138. 	 * Squeeze all characters in string2.
  139. 	 */
  140. 	if(dflag && sflag)
  141. 	{
  142. 		if(argc != 2) usage();
  144. 		setup(delete, argv[0], &s1, cflag);
  145. 		setup(squeeze, argv[1], &s2, 0);
  147. 		for(lastch = OOBCH; (ch = getchar()) != EOF;)
  148. 			if(!delete[ch] && (!squeeze[ch] || lastch != ch))
  149. 			{
  150. 				lastch = ch;
  151. 				(void)putchar(ch);
  152. 			}
  153. 		exit(0);
  154. 	}
  156. 	/*
  157. 	 * tr -d [-Cc] string1
  158. 	 * Delete all characters (or complemented characters) in string1.
  159. 	 */
  160. 	if(dflag)
  161. 	{
  162. 		if(argc != 1) usage();
  164. 		setup(delete, argv[0], &s1, cflag);
  166. 		while((ch = getchar()) != EOF)
  167. 			if(!delete[ch]) (void)putchar(ch);
  168. 		exit(0);
  169. 	}
  171. 	/*
  172. 	 * tr -s [-Cc] string1
  173. 	 * Squeeze all characters (or complemented characters) in string1.
  174. 	 */
  175. 	if(sflag && argc == 1)
  176. 	{
  177. 		setup(squeeze, argv[0], &s1, cflag);
  179. 		for(lastch = OOBCH; (ch = getchar()) != EOF;)
  180. 			if(!squeeze[ch] || lastch != ch)
  181. 			{
  182. 				lastch = ch;
  183. 				(void)putchar(ch);
  184. 			}
  185. 		exit(0);
  186. 	}
  188. 	/*
  189. 	 * tr [-Ccs] string1 string2
  190. 	 * Replace all characters (or complemented characters) in string1 with
  191. 	 * the character in the same position in string2.  If the -s option is
  192. 	 * specified, squeeze all the characters in string2.
  193. 	 */
  194. 	if(argc != 2) usage();
  196. 	s1.str = (unsigned char *)argv[0];
  197. 	s2.str = (unsigned char *)argv[1];
  199. 	if(cflag)
  200. 		for(cnt = NCHARS, p = translate; cnt--;)
  201. 			*p++ = OOBCH;
  203. 	if(!next(&s2)) utils_errx(1, "empty string2");
  205. 	/* If string2 runs out of characters, use the last one specified. */
  206. 	ch = s2.lastch;
  207. 	if(sflag)
  208. 		while(next(&s1))
  209. 		{
  210. 			translate[s1.lastch] = ch = s2.lastch;
  211. 			squeeze[ch] = 1;
  212. 			(void)next(&s2);
  213. 		}
  214. 	else
  215. 		while(next(&s1))
  216. 		{
  217. 			translate[s1.lastch] = ch = s2.lastch;
  218. 			(void)next(&s2);
  219. 		}
  221. 	if(cflag)
  222. 		for(cnt = 0, p = translate; cnt < NCHARS; ++p, ++cnt)
  223. 			*p = *p == OOBCH ? ch : cnt;
  225. 	if(sflag)
  226. 		for(lastch = OOBCH; (ch = getchar()) != EOF;)
  227. 		{
  228. 			ch = translate[ch];
  229. 			if(!squeeze[ch] || lastch != ch)
  230. 			{
  231. 				lastch = ch;
  232. 				(void)putchar(ch);
  233. 			}
  234. 		}
  235. 	else
  236. 		while((ch = getchar()) != EOF)
  237. 			(void)putchar(translate[ch]);
  238. 	exit(0);
  239. }
  241. static void
  242. setup(int *table, char *arg, STR *str, int cflag)
  243. {
  244. 	int cnt, *p;
  246. 	str->str = (unsigned char *)arg;
  247. 	bzero(table, NCHARS * sizeof(int));
  248. 	while(next(str))
  249. 		table[str->lastch] = 1;
  250. 	if(cflag)
  251. 		for(p = table, cnt = NCHARS; cnt--; ++p)
  252. 			*p = !*p;
  253. }
  255. static void
  256. usage(void)
  257. {
  258. 	fprintf(stderr,
  259. 	        "usage: tr [-Ccs] string1 string2\n"
  260. 	        "       tr [-Cc] -d string1\n"
  261. 	        "       tr [-Cc] -s string1\n"
  262. 	        "       tr [-Cc] -ds string1 string2\n");
  263. 	exit(1);
  264. }