1/*-
2 * Copyright (c) 1980, 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 * 4. Neither the name of the University nor the names of its contributors
14 *    may be used to endorse or promote products derived from this software
15 *    without specific prior written permission.
16 *
17 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
18 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
19 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
20 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
21 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
22 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
23 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
24 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
25 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
26 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
27 * SUCH DAMAGE.
28 */
29
30#include <sys/cdefs.h>
31
32__FBSDID("$FreeBSD$");
33
34#ifndef lint
35static const char copyright[] =
36"@(#) Copyright (c) 1980, 1993\n\
37	The Regents of the University of California.  All rights reserved.\n";
38#endif
39
40#ifndef lint
41static const char sccsid[] = "@(#)unexpand.c	8.1 (Berkeley) 6/6/93";
42#endif
43
44/*
45 * unexpand - put tabs into a file replacing blanks
46 */
47#include <ctype.h>
48#include <err.h>
49#include <limits.h>
50#include <locale.h>
51#include <stdio.h>
52#include <stdlib.h>
53#include <string.h>
54#include <unistd.h>
55#include <wchar.h>
56#include <wctype.h>
57
58static int	all;
59static int	nstops;
60static int	tabstops[100];
61
62static void getstops(const char *);
63static void usage(void);
64static int tabify(const char *);
65
66int
67main(int argc, char *argv[])
68{
69	int ch, failed;
70	char *filename;
71
72	setlocale(LC_CTYPE, "");
73
74	nstops = 1;
75	tabstops[0] = 8;
76	while ((ch = getopt(argc, argv, "at:")) != -1) {
77		switch (ch) {
78		case 'a':	/* Un-expand all spaces, not just leading. */
79			all = 1;
80			break;
81		case 't':	/* Specify tab list, implies -a. */
82			getstops(optarg);
83			all = 1;
84			break;
85		default:
86			usage();
87			/*NOTREACHED*/
88		}
89	}
90	argc -= optind;
91	argv += optind;
92
93	failed = 0;
94	if (argc == 0)
95		failed |= tabify("stdin");
96	else {
97		while ((filename = *argv++) != NULL) {
98			if (freopen(filename, "r", stdin) == NULL) {
99				warn("%s", filename);
100				failed = 1;
101			} else
102				failed |= tabify(filename);
103		}
104	}
105	exit(failed != 0);
106}
107
108static void
109usage(void)
110{
111	fprintf(stderr, "usage: unexpand [-a | -t tablist] [file ...]\n");
112	exit(1);
113}
114
115static int
116tabify(const char *curfile)
117{
118	int dcol, doneline, limit, n, ocol, width;
119	wint_t ch;
120
121	limit = nstops == 1 ? INT_MAX : tabstops[nstops - 1] - 1;
122
123	doneline = ocol = dcol = 0;
124	while ((ch = getwchar()) != WEOF) {
125		if (ch == ' ' && !doneline) {
126			if (++dcol >= limit)
127				doneline = 1;
128			continue;
129		} else if (ch == '\t') {
130			if (nstops == 1) {
131				dcol = (1 + dcol / tabstops[0]) *
132				    tabstops[0];
133				continue;
134			} else {
135				for (n = 0; tabstops[n] - 1 < dcol &&
136				    n < nstops; n++)
137					;
138				if (n < nstops - 1 && tabstops[n] - 1 < limit) {
139					dcol = tabstops[n];
140					continue;
141				}
142				doneline = 1;
143			}
144		}
145
146		/* Output maximal number of tabs. */
147		if (nstops == 1) {
148			while (((ocol + tabstops[0]) / tabstops[0])
149			    <= (dcol / tabstops[0])) {
150				if (dcol - ocol < 2)
151					break;
152				putwchar('\t');
153				ocol = (1 + ocol / tabstops[0]) *
154				    tabstops[0];
155			}
156		} else {
157			for (n = 0; tabstops[n] - 1 < ocol && n < nstops; n++)
158				;
159			while (ocol < dcol && n < nstops && ocol < limit) {
160				putwchar('\t');
161				ocol = tabstops[n++];
162			}
163		}
164
165		/* Then spaces. */
166		while (ocol < dcol && ocol < limit) {
167			putwchar(' ');
168			ocol++;
169		}
170
171		if (ch == '\b') {
172			putwchar('\b');
173			if (ocol > 0)
174				ocol--, dcol--;
175		} else if (ch == '\n') {
176			putwchar('\n');
177			doneline = ocol = dcol = 0;
178			continue;
179		} else if (ch != ' ' || dcol > limit) {
180			putwchar(ch);
181			if ((width = wcwidth(ch)) > 0)
182				ocol += width, dcol += width;
183		}
184
185		/*
186		 * Only processing leading blanks or we've gone past the
187		 * last tab stop. Emit remainder of this line unchanged.
188		 */
189		if (!all || dcol >= limit) {
190			while ((ch = getwchar()) != '\n' && ch != WEOF)
191				putwchar(ch);
192			if (ch == '\n')
193				putwchar('\n');
194			doneline = ocol = dcol = 0;
195		}
196	}
197	if (ferror(stdin)) {
198		warn("%s", curfile);
199		return (1);
200	}
201	return (0);
202}
203
204static void
205getstops(const char *cp)
206{
207	int i;
208
209	nstops = 0;
210	for (;;) {
211		i = 0;
212		while (*cp >= '0' && *cp <= '9')
213			i = i * 10 + *cp++ - '0';
214		if (i <= 0)
215			errx(1, "bad tab stop spec");
216		if (nstops > 0 && i <= tabstops[nstops-1])
217			errx(1, "bad tab stop spec");
218		if (nstops == sizeof(tabstops) / sizeof(*tabstops))
219			errx(1, "too many tab stops");
220		tabstops[nstops++] = i;
221		if (*cp == 0)
222			break;
223		if (*cp != ',' && !isblank((unsigned char)*cp))
224			errx(1, "bad tab stop spec");
225		cp++;
226	}
227}
228