1/*-
2 * SPDX-License-Identifier: BSD-3-Clause
3 *
4 * Copyright (c) 1980, 1987, 1991, 1993
5 *	The Regents of the University of California.  All rights reserved.
6 *
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
10 * 1. Redistributions of source code must retain the above copyright
11 *    notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 *    notice, this list of conditions and the following disclaimer in the
14 *    documentation and/or other materials provided with the distribution.
15 * 3. Neither the name of the University nor the names of its contributors
16 *    may be used to endorse or promote products derived from this software
17 *    without specific prior written permission.
18 *
19 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
20 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
21 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
22 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
23 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
24 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
25 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
26 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
27 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
28 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
29 * SUCH DAMAGE.
30 */
31
32#ifndef lint
33static const char copyright[] =
34"@(#) Copyright (c) 1980, 1987, 1991, 1993\n\
35	The Regents of the University of California.  All rights reserved.\n";
36#endif /* not lint */
37
38#if 0
39#ifndef lint
40static char sccsid[] = "@(#)wc.c	8.1 (Berkeley) 6/6/93";
41#endif /* not lint */
42#endif
43
44#include <sys/cdefs.h>
45__FBSDID("$FreeBSD$");
46
47#include <sys/capsicum.h>
48#include <sys/param.h>
49#include <sys/stat.h>
50
51#include <capsicum_helpers.h>
52#include <ctype.h>
53#include <err.h>
54#include <errno.h>
55#include <fcntl.h>
56#include <locale.h>
57#include <stdint.h>
58#include <stdio.h>
59#include <stdlib.h>
60#include <string.h>
61#include <unistd.h>
62#include <wchar.h>
63#include <wctype.h>
64#include <libxo/xo.h>
65
66#include <libcasper.h>
67#include <casper/cap_fileargs.h>
68
69static fileargs_t *fa;
70static uintmax_t tlinect, twordct, tcharct, tlongline;
71static int doline, doword, dochar, domulti, dolongline;
72static volatile sig_atomic_t siginfo;
73static xo_handle_t *stderr_handle;
74
75static void	show_cnt(const char *file, uintmax_t linect, uintmax_t wordct,
76		    uintmax_t charct, uintmax_t llct);
77static int	cnt(const char *);
78static void	usage(void);
79
80static void
81siginfo_handler(int sig __unused)
82{
83
84	siginfo = 1;
85}
86
87static void
88reset_siginfo(void)
89{
90
91	signal(SIGINFO, SIG_DFL);
92	siginfo = 0;
93}
94
95int
96main(int argc, char *argv[])
97{
98	int ch, errors, total;
99	cap_rights_t rights;
100
101	(void) setlocale(LC_CTYPE, "");
102
103	argc = xo_parse_args(argc, argv);
104	if (argc < 0)
105		return (argc);
106
107	while ((ch = getopt(argc, argv, "clmwL")) != -1)
108		switch((char)ch) {
109		case 'l':
110			doline = 1;
111			break;
112		case 'w':
113			doword = 1;
114			break;
115		case 'c':
116			dochar = 1;
117			domulti = 0;
118			break;
119		case 'L':
120			dolongline = 1;
121			break;
122		case 'm':
123			domulti = 1;
124			dochar = 0;
125			break;
126		case '?':
127		default:
128			usage();
129		}
130	argv += optind;
131	argc -= optind;
132
133	(void)signal(SIGINFO, siginfo_handler);
134
135	fa = fileargs_init(argc, argv, O_RDONLY, 0,
136	    cap_rights_init(&rights, CAP_READ, CAP_FSTAT), FA_OPEN);
137	if (fa == NULL) {
138		xo_warn("Unable to init casper");
139		exit(1);
140	}
141
142	caph_cache_catpages();
143	if (caph_limit_stdio() < 0) {
144		xo_warn("Unable to limit stdio");
145		fileargs_free(fa);
146		exit(1);
147	}
148
149	if (caph_enter_casper() < 0) {
150		xo_warn("Unable to enter capability mode");
151		fileargs_free(fa);
152		exit(1);
153	}
154
155	/* Wc's flags are on by default. */
156	if (doline + doword + dochar + domulti + dolongline == 0)
157		doline = doword = dochar = 1;
158
159	stderr_handle = xo_create_to_file(stderr, XO_STYLE_TEXT, 0);
160	xo_open_container("wc");
161	xo_open_list("file");
162
163	errors = 0;
164	total = 0;
165	if (!*argv) {
166	 	xo_open_instance("file");
167		if (cnt((char *)NULL) != 0)
168			++errors;
169	 	xo_close_instance("file");
170	} else {
171		do {
172	 		xo_open_instance("file");
173			if (cnt(*argv) != 0)
174				++errors;
175	 		xo_close_instance("file");
176			++total;
177		} while(*++argv);
178	}
179
180	xo_close_list("file");
181
182	if (total > 1) {
183		xo_open_container("total");
184		show_cnt("total", tlinect, twordct, tcharct, tlongline);
185		xo_close_container("total");
186	}
187
188	fileargs_free(fa);
189	xo_close_container("wc");
190	xo_finish();
191	exit(errors == 0 ? 0 : 1);
192}
193
194static void
195show_cnt(const char *file, uintmax_t linect, uintmax_t wordct,
196    uintmax_t charct, uintmax_t llct)
197{
198	xo_handle_t *xop;
199
200	if (!siginfo)
201		xop = NULL;
202	else {
203		xop = stderr_handle;
204		siginfo = 0;
205	}
206
207	if (doline)
208		xo_emit_h(xop, " {:lines/%7ju/%ju}", linect);
209	if (doword)
210		xo_emit_h(xop, " {:words/%7ju/%ju}", wordct);
211	if (dochar || domulti)
212		xo_emit_h(xop, " {:characters/%7ju/%ju}", charct);
213	if (dolongline)
214		xo_emit_h(xop, " {:long-lines/%7ju/%ju}", llct);
215	if (file != NULL)
216		xo_emit_h(xop, " {:filename/%s}\n", file);
217	else
218		xo_emit_h(xop, "\n");
219}
220
221static int
222cnt(const char *file)
223{
224	struct stat sb;
225	uintmax_t linect, wordct, charct, llct, tmpll;
226	int fd, len, warned;
227	size_t clen;
228	short gotsp;
229	u_char *p;
230	u_char buf[MAXBSIZE];
231	wchar_t wch;
232	mbstate_t mbs;
233
234	linect = wordct = charct = llct = tmpll = 0;
235	if (file == NULL)
236		fd = STDIN_FILENO;
237	else if ((fd = fileargs_open(fa, file)) < 0) {
238		xo_warn("%s: open", file);
239		return (1);
240	}
241	if (doword || (domulti && MB_CUR_MAX != 1))
242		goto word;
243	/*
244	 * If all we need is the number of characters and it's a regular file,
245	 * just stat it.
246	 */
247	if (doline == 0 && dolongline == 0) {
248		if (fstat(fd, &sb)) {
249			xo_warn("%s: fstat", file != NULL ? file : "stdin");
250			(void)close(fd);
251			return (1);
252		}
253		if (S_ISREG(sb.st_mode)) {
254			reset_siginfo();
255			charct = sb.st_size;
256			show_cnt(file, linect, wordct, charct, llct);
257			tcharct += charct;
258			(void)close(fd);
259			return (0);
260		}
261	}
262	/*
263	 * For files we can't stat, or if we need line counting, slurp the
264	 * file.  Line counting is split out because it's a lot faster to get
265	 * lines than to get words, since the word count requires locale
266	 * handling.
267	 */
268	while ((len = read(fd, buf, MAXBSIZE))) {
269		if (len == -1) {
270			xo_warn("%s: read", file != NULL ? file : "stdin");
271			(void)close(fd);
272			return (1);
273		}
274		if (siginfo)
275			show_cnt(file, linect, wordct, charct, llct);
276		charct += len;
277		if (doline || dolongline) {
278			for (p = buf; len--; ++p)
279				if (*p == '\n') {
280					if (tmpll > llct)
281						llct = tmpll;
282					tmpll = 0;
283					++linect;
284				} else
285					tmpll++;
286		}
287	}
288	reset_siginfo();
289	if (doline)
290		tlinect += linect;
291	if (dochar)
292		tcharct += charct;
293	if (dolongline && llct > tlongline)
294		tlongline = llct;
295	show_cnt(file, linect, wordct, charct, llct);
296	(void)close(fd);
297	return (0);
298
299	/* Do it the hard way... */
300word:	gotsp = 1;
301	warned = 0;
302	memset(&mbs, 0, sizeof(mbs));
303	while ((len = read(fd, buf, MAXBSIZE)) != 0) {
304		if (len == -1) {
305			xo_warn("%s: read", file != NULL ? file : "stdin");
306			(void)close(fd);
307			return (1);
308		}
309		p = buf;
310		while (len > 0) {
311			if (siginfo)
312				show_cnt(file, linect, wordct, charct, llct);
313			if (!domulti || MB_CUR_MAX == 1) {
314				clen = 1;
315				wch = (unsigned char)*p;
316			} else if ((clen = mbrtowc(&wch, p, len, &mbs)) ==
317			    (size_t)-1) {
318				if (!warned) {
319					errno = EILSEQ;
320					xo_warn("%s",
321					    file != NULL ? file : "stdin");
322					warned = 1;
323				}
324				memset(&mbs, 0, sizeof(mbs));
325				clen = 1;
326				wch = (unsigned char)*p;
327			} else if (clen == (size_t)-2)
328				break;
329			else if (clen == 0)
330				clen = 1;
331			charct++;
332			if (wch != L'\n')
333				tmpll++;
334			len -= clen;
335			p += clen;
336			if (wch == L'\n') {
337				if (tmpll > llct)
338					llct = tmpll;
339				tmpll = 0;
340				++linect;
341			}
342			if (iswspace(wch))
343				gotsp = 1;
344			else if (gotsp) {
345				gotsp = 0;
346				++wordct;
347			}
348		}
349	}
350	reset_siginfo();
351	if (domulti && MB_CUR_MAX > 1)
352		if (mbrtowc(NULL, NULL, 0, &mbs) == (size_t)-1 && !warned)
353			xo_warn("%s", file != NULL ? file : "stdin");
354	if (doline)
355		tlinect += linect;
356	if (doword)
357		twordct += wordct;
358	if (dochar || domulti)
359		tcharct += charct;
360	if (dolongline && llct > tlongline)
361		tlongline = llct;
362	show_cnt(file, linect, wordct, charct, llct);
363	(void)close(fd);
364	return (0);
365}
366
367static void
368usage(void)
369{
370	xo_error("usage: wc [-Lclmw] [file ...]\n");
371	exit(1);
372}
373