No empty .Rs/.Re
[netbsd-mini2440.git] / usr.bin / wc / wc.c
blob60baf32f62755fc91b6a141efd55b5374c24bd10
1 /* $NetBSD: wc.c,v 1.31 2008/07/21 14:19:28 lukem Exp $ */
3 /*
4 * Copyright (c) 1980, 1987, 1991, 1993
5 * The Regents of the University of California. All rights reserved.
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.
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.
32 #include <sys/cdefs.h>
33 #ifndef lint
34 __COPYRIGHT("@(#) Copyright (c) 1980, 1987, 1991, 1993\
35 The Regents of the University of California. All rights reserved.");
36 #endif /* not lint */
38 #ifndef lint
39 #if 0
40 static char sccsid[] = "@(#)wc.c 8.2 (Berkeley) 5/2/95";
41 #else
42 __RCSID("$NetBSD: wc.c,v 1.31 2008/07/21 14:19:28 lukem Exp $");
43 #endif
44 #endif /* not lint */
46 /* wc line, word and char count */
48 #include <sys/param.h>
49 #include <sys/file.h>
50 #include <sys/stat.h>
52 #include <ctype.h>
53 #include <fcntl.h>
54 #include <err.h>
55 #include <errno.h>
56 #include <locale.h>
57 #include <stdio.h>
58 #include <stdlib.h>
59 #include <string.h>
60 #include <unistd.h>
61 #include <wchar.h>
62 #include <wctype.h>
64 #ifdef NO_QUAD
65 typedef u_long wc_count_t;
66 # define WCFMT " %7lu"
67 # define WCCAST unsigned long
68 #else
69 typedef u_quad_t wc_count_t;
70 # define WCFMT " %7llu"
71 # define WCCAST unsigned long long
72 #endif
74 static wc_count_t tlinect, twordct, tcharct;
75 static int doline, doword, dobyte, dochar;
76 static int rval = 0;
78 static void cnt(const char *);
79 static void print_counts(wc_count_t, wc_count_t, wc_count_t, const char *);
80 static void usage(void);
81 static size_t do_mb(wchar_t *, const char *, size_t, mbstate_t *,
82 size_t *, const char *);
83 int main(int, char *[]);
85 int
86 main(int argc, char *argv[])
88 int ch;
90 setlocale(LC_ALL, "");
92 while ((ch = getopt(argc, argv, "lwcm")) != -1)
93 switch (ch) {
94 case 'l':
95 doline = 1;
96 break;
97 case 'w':
98 doword = 1;
99 break;
100 case 'm':
101 dochar = 1;
102 dobyte = 0;
103 break;
104 case 'c':
105 dochar = 0;
106 dobyte = 1;
107 break;
108 case '?':
109 default:
110 usage();
112 argv += optind;
113 argc -= optind;
115 /* Wc's flags are on by default. */
116 if (doline + doword + dobyte + dochar == 0)
117 doline = doword = dobyte = 1;
119 if (!*argv) {
120 cnt(NULL);
121 } else {
122 int dototal = (argc > 1);
124 do {
125 cnt(*argv);
126 } while(*++argv);
128 if (dototal)
129 print_counts(tlinect, twordct, tcharct, "total");
132 exit(rval);
135 static size_t
136 do_mb(wchar_t *wc, const char *p, size_t len, mbstate_t *st,
137 size_t *retcnt, const char *file)
139 size_t r;
140 size_t c = 0;
142 do {
143 r = mbrtowc(wc, p, len, st);
144 if (r == (size_t)-1) {
145 warnx("%s: invalid byte sequence", file);
146 rval = 1;
148 /* XXX skip 1 byte */
149 len--;
150 p++;
151 memset(st, 0, sizeof(*st));
152 continue;
153 } else if (r == (size_t)-2)
154 break;
155 else if (r == 0)
156 r = 1;
157 c++;
158 if (wc)
159 wc++;
160 len -= r;
161 p += r;
162 } while (len > 0);
164 *retcnt = c;
166 return (r);
169 static void
170 cnt(const char *file)
172 u_char buf[MAXBSIZE];
173 wchar_t wbuf[MAXBSIZE];
174 struct stat sb;
175 wc_count_t charct, linect, wordct;
176 mbstate_t st;
177 u_char *C;
178 wchar_t *WC;
179 const char *name; /* filename or <stdin> */
180 size_t r = 0;
181 int fd, gotsp, len = 0;
183 linect = wordct = charct = 0;
184 if (file) {
185 if ((fd = open(file, O_RDONLY, 0)) < 0) {
186 warn("%s", file);
187 rval = 1;
188 return;
190 name = file;
191 } else {
192 fd = STDIN_FILENO;
193 name = "<stdin>";
196 if (dochar || doword)
197 memset(&st, 0, sizeof(st));
199 if (!doword) {
201 * line counting is split out because it's a lot
202 * faster to get lines than to get words, since
203 * the word count requires some logic.
205 if (doline || dochar) {
206 while ((len = read(fd, buf, MAXBSIZE)) > 0) {
207 if (dochar) {
208 size_t wlen;
210 r = do_mb(0, (char *)buf, (size_t)len,
211 &st, &wlen, name);
212 charct += wlen;
213 } else if (dobyte)
214 charct += len;
215 if (doline)
216 for (C = buf; len--; ++C)
217 if (*C == '\n')
218 ++linect;
223 * if all we need is the number of characters and
224 * it's a directory or a regular or linked file, just
225 * stat the puppy. We avoid testing for it not being
226 * a special device in case someone adds a new type
227 * of inode.
229 else if (dobyte) {
230 if (fstat(fd, &sb)) {
231 warn("%s", name);
232 rval = 1;
233 } else {
234 if (S_ISREG(sb.st_mode) ||
235 S_ISLNK(sb.st_mode) ||
236 S_ISDIR(sb.st_mode)) {
237 charct = sb.st_size;
238 } else {
239 while ((len =
240 read(fd, buf, MAXBSIZE)) > 0)
241 charct += len;
245 } else {
246 /* do it the hard way... */
247 gotsp = 1;
248 while ((len = read(fd, buf, MAXBSIZE)) > 0) {
249 size_t wlen;
251 r = do_mb(wbuf, (char *)buf, (size_t)len, &st, &wlen,
252 name);
253 if (dochar) {
254 charct += wlen;
255 } else if (dobyte)
256 charct += len;
257 for (WC = wbuf; wlen--; ++WC) {
258 if (iswspace(*WC)) {
259 gotsp = 1;
260 if (*WC == L'\n') {
261 ++linect;
263 } else {
265 * This line implements the POSIX
266 * spec, i.e. a word is a "maximal
267 * string of characters delimited by
268 * whitespace." Notice nothing was
269 * said about a character being
270 * printing or non-printing.
272 if (gotsp) {
273 gotsp = 0;
274 ++wordct;
281 if (len == -1) {
282 warn("%s", name);
283 rval = 1;
285 if (dochar && r == (size_t)-2) {
286 warnx("%s: incomplete multibyte character", name);
287 rval = 1;
290 print_counts(linect, wordct, charct, file);
293 * don't bother checkint doline, doword, or dobyte --- speeds
294 * up the common case
296 tlinect += linect;
297 twordct += wordct;
298 tcharct += charct;
300 if (close(fd)) {
301 warn("%s", name);
302 rval = 1;
306 static void
307 print_counts(wc_count_t lines, wc_count_t words, wc_count_t chars,
308 const char *name)
311 if (doline)
312 printf(WCFMT, (WCCAST)lines);
313 if (doword)
314 printf(WCFMT, (WCCAST)words);
315 if (dobyte || dochar)
316 printf(WCFMT, (WCCAST)chars);
318 if (name)
319 printf(" %s\n", name);
320 else
321 printf("\n");
324 static void
325 usage(void)
328 (void)fprintf(stderr, "usage: wc [-c | -m] [-lw] [file ...]\n");
329 exit(1);