blob: 07922af175fb19c2b2a33506eb18176a189942b2 [file] [log] [blame]
Erik Andersenfb002d02000-03-05 08:07:00 +00001/* vi: set sw=4 ts=4: */
2/*
Erik Andersen8f8d6d52000-05-01 22:30:37 +00003 * Mini tr implementation for busybox
Erik Andersenfb002d02000-03-05 08:07:00 +00004 *
Erik Andersen5afc8642000-05-02 00:07:56 +00005 * Copyright (c) Michiel Huisjes
6 *
7 * This version of tr is adapted from Minix tr and was modified
8 * by Erik Andersen <andersee@debian.org> to be used in busybox.
Erik Andersenfb002d02000-03-05 08:07:00 +00009 *
Erik Andersen8f8d6d52000-05-01 22:30:37 +000010 * This program is free software; you can redistribute it and/or modify
11 * it under the terms of the GNU General Public License as published by
12 * the Free Software Foundation; either version 2 of the License, or
13 * (at your option) any later version.
14 *
15 * This program is distributed in the hope that it will be useful,
16 * but WITHOUT ANY WARRANTY; without even the implied warranty of
17 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 * General Public License for more details.
19 *
20 * You should have received a copy of the GNU General Public License
21 * along with this program; if not, write to the Free Software
22 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
23 *
24 * Original copyright notice is retained at the end of this file.
Erik Andersenfb002d02000-03-05 08:07:00 +000025 */
26
Erik Andersenfb002d02000-03-05 08:07:00 +000027#include <stdio.h>
Erik Andersenfb002d02000-03-05 08:07:00 +000028#include <string.h>
Erik Andersen8f8d6d52000-05-01 22:30:37 +000029#include <stdlib.h>
Erik Andersenfb002d02000-03-05 08:07:00 +000030#include <unistd.h>
Erik Andersen8f8d6d52000-05-01 22:30:37 +000031#include <sys/types.h>
Eric Andersencbe31da2001-02-20 06:14:08 +000032#include "busybox.h"
Erik Andersen330fd2b2000-05-19 05:35:19 +000033
Mark Whitley59ab0252001-01-23 22:30:04 +000034static const int ASCII = 0377;
Erik Andersenfb002d02000-03-05 08:07:00 +000035
Mark Whitley8b7a0d82001-05-24 21:31:09 +000036/* some "globals" shared across this file */
Erik Andersen8f8d6d52000-05-01 22:30:37 +000037static char com_fl, del_fl, sq_fl;
Erik Andersen8f8d6d52000-05-01 22:30:37 +000038static short in_index, out_index;
Mark Whitley59ab0252001-01-23 22:30:04 +000039/* these last are pointers to static buffers declared in tr_main */
40static unsigned char *poutput, *pinput;
41static unsigned char *pvector;
42static char *pinvec, *poutvec;
Erik Andersenfb002d02000-03-05 08:07:00 +000043
Erik Andersenfb002d02000-03-05 08:07:00 +000044
Erik Andersen8f8d6d52000-05-01 22:30:37 +000045static void convert()
Erik Andersenfb002d02000-03-05 08:07:00 +000046{
Erik Andersen8f8d6d52000-05-01 22:30:37 +000047 short read_chars = 0;
48 short c, coded;
49 short last = -1;
Erik Andersenfb002d02000-03-05 08:07:00 +000050
Erik Andersen8f8d6d52000-05-01 22:30:37 +000051 for (;;) {
52 if (in_index == read_chars) {
Mark Whitley59ab0252001-01-23 22:30:04 +000053 if ((read_chars = read(0, (char *) pinput, BUFSIZ)) <= 0) {
54 if (write(1, (char *) poutput, out_index) != out_index)
Erik Andersen330fd2b2000-05-19 05:35:19 +000055 write(2, write_error, strlen(write_error));
Erik Andersen8f8d6d52000-05-01 22:30:37 +000056 exit(0);
Erik Andersenfb002d02000-03-05 08:07:00 +000057 }
Erik Andersen8f8d6d52000-05-01 22:30:37 +000058 in_index = 0;
59 }
Mark Whitley59ab0252001-01-23 22:30:04 +000060 c = pinput[in_index++];
61 coded = pvector[c];
62 if (del_fl && pinvec[c])
Erik Andersen8f8d6d52000-05-01 22:30:37 +000063 continue;
Mark Whitley59ab0252001-01-23 22:30:04 +000064 if (sq_fl && last == coded && (pinvec[c] || poutvec[coded]))
Erik Andersen8f8d6d52000-05-01 22:30:37 +000065 continue;
Mark Whitley59ab0252001-01-23 22:30:04 +000066 poutput[out_index++] = last = coded;
Erik Andersen8f8d6d52000-05-01 22:30:37 +000067 if (out_index == BUFSIZ) {
Mark Whitley59ab0252001-01-23 22:30:04 +000068 if (write(1, (char *) poutput, out_index) != out_index) {
Erik Andersen330fd2b2000-05-19 05:35:19 +000069 write(2, write_error, strlen(write_error));
Erik Andersen8f8d6d52000-05-01 22:30:37 +000070 exit(1);
Erik Andersenfb002d02000-03-05 08:07:00 +000071 }
Erik Andersen8f8d6d52000-05-01 22:30:37 +000072 out_index = 0;
73 }
Erik Andersenfb002d02000-03-05 08:07:00 +000074 }
75
Erik Andersenfb002d02000-03-05 08:07:00 +000076 /* NOTREACHED */
Erik Andersen8f8d6d52000-05-01 22:30:37 +000077}
78
Eric Andersen00143ba2000-07-13 16:40:41 +000079static void map(register unsigned char *string1, unsigned int string1_len,
80 register unsigned char *string2, unsigned int string2_len)
Erik Andersen8f8d6d52000-05-01 22:30:37 +000081{
82 unsigned char last = '0';
Eric Andersen00143ba2000-07-13 16:40:41 +000083 unsigned int i, j;
Erik Andersen8f8d6d52000-05-01 22:30:37 +000084
Eric Andersen00143ba2000-07-13 16:40:41 +000085 for (j = 0, i = 0; i < string1_len; i++) {
86 if (string2_len <= j)
Mark Whitley59ab0252001-01-23 22:30:04 +000087 pvector[string1[i]] = last;
Erik Andersen8f8d6d52000-05-01 22:30:37 +000088 else
Mark Whitley59ab0252001-01-23 22:30:04 +000089 pvector[string1[i]] = last = string2[j++];
Erik Andersen8f8d6d52000-05-01 22:30:37 +000090 }
91}
92
Mark Whitley8b7a0d82001-05-24 21:31:09 +000093/* supported constructs:
94 * Ranges, e.g., [0-9] ==> 0123456789
95 * Escapes, e.g., \a ==> Control-G
96 */
Eric Andersene5dfced2001-04-09 22:48:12 +000097static unsigned int expand(const char *arg, register unsigned char *buffer)
Erik Andersen8f8d6d52000-05-01 22:30:37 +000098{
Eric Andersen00143ba2000-07-13 16:40:41 +000099 unsigned char *buffer_start = buffer;
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000100 int i, ac;
101
102 while (*arg) {
103 if (*arg == '\\') {
104 arg++;
Eric Andersenf7cf2f72000-07-05 17:26:35 +0000105 *buffer++ = process_escape_sequence(&arg);
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000106 } else if (*arg == '[') {
107 arg++;
108 i = *arg++;
109 if (*arg++ != '-') {
110 *buffer++ = '[';
111 arg -= 2;
112 continue;
113 }
114 ac = *arg++;
115 while (i <= ac)
116 *buffer++ = i++;
Mark Whitley8b7a0d82001-05-24 21:31:09 +0000117 arg++; /* Skip the assumed ']' */
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000118 } else
119 *buffer++ = *arg++;
120 }
Eric Andersen00143ba2000-07-13 16:40:41 +0000121
122 return (buffer - buffer_start);
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000123}
124
Eric Andersenfad04fd2000-07-14 06:49:52 +0000125static int complement(unsigned char *buffer, int buffer_len)
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000126{
Eric Andersen1ca20a72001-03-21 07:34:27 +0000127 register short i, j, ix;
Eric Andersenfad04fd2000-07-14 06:49:52 +0000128 char conv[ASCII + 2];
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000129
Eric Andersen1ca20a72001-03-21 07:34:27 +0000130 ix = 0;
Eric Andersen00143ba2000-07-13 16:40:41 +0000131 for (i = 0; i <= ASCII; i++) {
132 for (j = 0; j < buffer_len; j++)
133 if (buffer[j] == i)
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000134 break;
Eric Andersen00143ba2000-07-13 16:40:41 +0000135 if (j == buffer_len)
Eric Andersen1ca20a72001-03-21 07:34:27 +0000136 conv[ix++] = i & ASCII;
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000137 }
Eric Andersen1ca20a72001-03-21 07:34:27 +0000138 memcpy(buffer, conv, ix);
139 return ix;
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000140}
141
142extern int tr_main(int argc, char **argv)
143{
144 register unsigned char *ptr;
Eric Andersenfad04fd2000-07-14 06:49:52 +0000145 int output_length=0, input_length;
Eric Andersenf6aa13d2001-03-23 17:08:21 +0000146 int idx = 1;
Eric Andersenfad04fd2000-07-14 06:49:52 +0000147 int i;
Eric Andersend35c2152001-01-25 23:49:09 +0000148 RESERVE_BB_BUFFER(output, BUFSIZ);
149 RESERVE_BB_BUFFER(input, BUFSIZ);
150 RESERVE_BB_UBUFFER(vector, ASCII+1);
151 RESERVE_BB_BUFFER(invec, ASCII+1);
152 RESERVE_BB_BUFFER(outvec, ASCII+1);
Mark Whitley59ab0252001-01-23 22:30:04 +0000153
154 /* ... but make them available globally */
155 poutput = output;
156 pinput = input;
157 pvector = vector;
158 pinvec = invec;
159 poutvec = outvec;
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000160
Eric Andersenf6aa13d2001-03-23 17:08:21 +0000161 if (argc > 1 && argv[idx][0] == '-') {
162 for (ptr = (unsigned char *) &argv[idx][1]; *ptr; ptr++) {
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000163 switch (*ptr) {
164 case 'c':
165 com_fl = TRUE;
166 break;
167 case 'd':
168 del_fl = TRUE;
169 break;
170 case 's':
171 sq_fl = TRUE;
172 break;
173 default:
Eric Andersen67991cf2001-02-14 21:23:06 +0000174 show_usage();
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000175 }
176 }
Eric Andersenf6aa13d2001-03-23 17:08:21 +0000177 idx++;
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000178 }
179 for (i = 0; i <= ASCII; i++) {
180 vector[i] = i;
181 invec[i] = outvec[i] = FALSE;
182 }
183
Eric Andersenf6aa13d2001-03-23 17:08:21 +0000184 if (argv[idx] != NULL) {
185 input_length = expand(argv[idx++], input);
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000186 if (com_fl)
Eric Andersen00143ba2000-07-13 16:40:41 +0000187 input_length = complement(input, input_length);
Eric Andersenf6aa13d2001-03-23 17:08:21 +0000188 if (argv[idx] != NULL) {
189 if (*argv[idx] == '\0')
Matt Kraaidd19c692001-01-31 19:00:21 +0000190 error_msg_and_die("STRING2 cannot be empty");
Eric Andersenf6aa13d2001-03-23 17:08:21 +0000191 output_length = expand(argv[idx], output);
Eric Andersen00143ba2000-07-13 16:40:41 +0000192 map(input, input_length, output, output_length);
Eric Andersena03d86c2000-07-10 16:38:50 +0000193 }
Eric Andersen00143ba2000-07-13 16:40:41 +0000194 for (i = 0; i < input_length; i++)
Eric Andersened3ef502001-01-27 08:24:39 +0000195 invec[(int)input[i]] = TRUE;
Eric Andersen00143ba2000-07-13 16:40:41 +0000196 for (i = 0; i < output_length; i++)
Eric Andersened3ef502001-01-27 08:24:39 +0000197 outvec[(int)output[i]] = TRUE;
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000198 }
199 convert();
Erik Andersenfb002d02000-03-05 08:07:00 +0000200 return (0);
201}
202
Erik Andersenfb002d02000-03-05 08:07:00 +0000203/*
Erik Andersen8f8d6d52000-05-01 22:30:37 +0000204 * Copyright (c) 1987,1997, Prentice Hall
205 * All rights reserved.
206 *
207 * Redistribution and use of the MINIX operating system in source and
208 * binary forms, with or without modification, are permitted provided
209 * that the following conditions are met:
210 *
211 * Redistributions of source code must retain the above copyright
212 * notice, this list of conditions and the following disclaimer.
213 *
214 * Redistributions in binary form must reproduce the above
215 * copyright notice, this list of conditions and the following
216 * disclaimer in the documentation and/or other materials provided
217 * with the distribution.
218 *
219 * Neither the name of Prentice Hall nor the names of the software
220 * authors or contributors may be used to endorse or promote
221 * products derived from this software without specific prior
222 * written permission.
223 *
224 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS, AUTHORS, AND
225 * CONTRIBUTORS ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES,
226 * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
227 * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
228 * IN NO EVENT SHALL PRENTICE HALL OR ANY AUTHORS OR CONTRIBUTORS BE
229 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
230 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
231 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
232 * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
233 * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
234 * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
235 * EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
236 *
Erik Andersenfb002d02000-03-05 08:07:00 +0000237 */
Erik Andersenfb002d02000-03-05 08:07:00 +0000238