 @@ -1,14 +1,14 @@
-.\"	$NetBSD: wc.1,v 1.13 2003/08/07 11:17:15 agc Exp $
+.\"	$NetBSD: wc.1,v 1.13.40.1 2010/03/06 21:19:11 sborrill Exp $
 .\"
 .\" Copyright (c) 1991, 1993
 .\"	The Regents of the University of California.  All rights reserved.
 .\"
 .\" This code is derived from software contributed to Berkeley by
 .\" the Institute of Electrical and Electronics Engineers, Inc.
 .\"
 .\" Redistribution and use in source and binary forms, with or without
 .\" modification, are permitted provided that the following conditions
 .\" are met:
 .\" 1. Redistributions of source code must retain the above copyright
 .\"    notice, this list of conditions and the following disclaimer.
 .\" 2. Redistributions in binary form must reproduce the above copyright
 @@ -22,111 +22,125 @@
 .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 .\" ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 .\" SUCH DAMAGE.
 .\"
 .\"     from: @(#)wc.1	8.2 (Berkeley) 4/19/94
 .\"
-.Dd April 19, 1994
+.Dd February 18, 2010
 .Dt WC 1
 .Os
 .Sh NAME
 .Nm wc
 .Nd word, line, and byte count
 .Sh SYNOPSIS
 .Nm
 .Op Fl c | Fl m
-.Op Fl lw
+.Op Fl Llw
 .Op Ar file ...
 .Sh DESCRIPTION
 The
 .Nm
 utility displays the number of lines, words, bytes and characters contained in each
 input
 .Ar file
 (or standard input, by default) to the standard output.
 A line is defined as a string of characters delimited by a \*[Lt]newline\*[Gt]
 character,
 and a word is defined as a string of characters delimited by white space
 characters.
 White space characters are the set of characters for which the
 .Xr iswspace 3
 function returns true.
 If more than one input file is specified, a line of cumulative counts
 for all the files is displayed on a separate line after the output for
 the last file.
 .Pp
 The following options are available:
 .Bl -tag -width Ds
 .It Fl c
 The number of bytes in each input file
 is written to the standard output.
 .It Fl L
 The number of characters in the longest line of each input file
 is written to the standard output.
 .It Fl l
 The number of lines in each input file
 is written to the standard output.
 .It Fl m
 The number of characters in each input file
 is written to the standard output.
 .It Fl w
 The number of words in each input file
 is written to the standard output.
 .El
 .Pp
 When an option is specified,
 .Nm
 only
 reports the
-information requested by that option. The
+information requested by that option.
-default action is equivalent to all the
+The default action is equivalent to all the flags
 flags
 .Fl clw
 having been specified.
 .Pp
 The following operands are available:
 .Bl -tag -width Ds
 .It Ar file
 A pathname of an input file.
 .El
 .Pp
 If no file names
 are specified, the standard input is used and
 no file name is displayed.
 .Pp
 By default, the standard output contains a line for each
 input file of the form:
 .Bd -literal -offset indent
 lines	 words	bytes	file_name
 .Ed
-.Pp
+.Sh EXIT STATUS
-The
+.Ex -std wc
 .Nm
 utility exits 0 on success, and \*[Gt]0 if an error occurs.
 .Sh SEE ALSO
 .Xr iswspace 3
 .Sh COMPATIBILITY
 Historically, the
 .Nm
 utility was documented to define a word as a ``maximal string of
-characters delimited by \*[Lt]space\*[Gt], \*[Lt]tab\*[Gt] or \*[Lt]newline\*[Gt] characters''.
+characters delimited by
 .Aq space ,
 .Aq tab
 or
 .Aq newline
 characters''.
 The implementation, however, didn't handle non-printing characters
 correctly so that ``  ^D^E  '' counted as 6 spaces, while ``foo^D^Ebar''
 counted as 8 characters.
 .Bx 4
 systems after
 .Bx 4.3
 modified the implementation to be consistent
 with the documentation.
 This implementation defines a ``word'' in terms of the
 .Xr iswspace 3
 function, as required by
 .St -p1003.2 .
 .Pp
 The
 .Fl L
 option is a non-standard extension, compatible with the
 .Fl L
 option of the GNU and
 .Fx
 .Nm
 utilities.
 .Sh STANDARDS
 The
 .Nm
 utility conforms to
 .St -p1003.2-92 .

 @@ -1,14 +1,14 @@
-/*	$NetBSD: wc.c,v 1.31 2008/07/21 14:19:28 lukem Exp $	*/
+/*	$NetBSD: wc.c,v 1.31.4.1 2010/03/06 21:19:11 sborrill Exp $	*/
 /*
  * Copyright (c) 1980, 1987, 1991, 1993
  *	The Regents of the University of California.  All rights reserved.
+ *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions
  * are met:
  * 1. Redistributions of source code must retain the above copyright
  *    notice, this list of conditions and the following disclaimer.
  * 2. Redistributions in binary form must reproduce the above copyright
  *    notice, this list of conditions and the following disclaimer in the
  *    documentation and/or other materials provided with the distribution.
 @@ -29,203 +29,212 @@
  * SUCH DAMAGE.
  */
 #include <sys/cdefs.h>
 #ifndef lint
 __COPYRIGHT("@(#) Copyright (c) 1980, 1987, 1991, 1993\
  The Regents of the University of California.  All rights reserved.");
 #endif /* not lint */
 #ifndef lint
 #if 0
 static char sccsid[] = "@(#)wc.c	8.2 (Berkeley) 5/2/95";
 #else
-__RCSID("$NetBSD: wc.c,v 1.31 2008/07/21 14:19:28 lukem Exp $");
+__RCSID("$NetBSD: wc.c,v 1.31.4.1 2010/03/06 21:19:11 sborrill Exp $");
 #endif
 #endif /* not lint */
-/* wc line, word and char count */
+/* wc line, word, char count and optionally longest line. */
 #include <sys/param.h>
 #include <sys/file.h>
 #include <sys/stat.h>
 #include <ctype.h>
 #include <fcntl.h>
 #include <err.h>
 #include <errno.h>
 #include <locale.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
 #include <wchar.h>
 #include <wctype.h>
 #ifdef NO_QUAD
 typedef u_long wc_count_t;
 # define WCFMT	" %7lu"
 # define WCCAST unsigned long
 #else
 typedef u_quad_t wc_count_t;
 # define WCFMT	" %7llu"
 # define WCCAST	unsigned long long
 #endif
-static wc_count_t	tlinect, twordct, tcharct;
+static wc_count_t	tlinect, twordct, tcharct, tlongest;
-static int		doline, doword, dobyte, dochar;
+static bool		doline, doword, dobyte, dochar, dolongest;
 static int 		rval = 0;
-static void	cnt(char *);
+static void	cnt(const char *);
-static void	print_counts(wc_count_t, wc_count_t, wc_count_t, char *);
+static void	print_counts(wc_count_t, wc_count_t, wc_count_t, wc_count_t,
 		    const char *);
 static void	usage(void);
 static size_t	do_mb(wchar_t *, const char *, size_t, mbstate_t *,
 		    size_t *, const char *);
 int	main(int, char *[]);
 int
 main(int argc, char *argv[])
+{
 	int ch;
 	setlocale(LC_ALL, "");
-	while ((ch = getopt(argc, argv, "lwcm")) != -1)
+	while ((ch = getopt(argc, argv, "lwcmL")) != -1)
 		switch (ch) {
 		case 'l':
-			doline = 1;
+			doline = true;
 			break;
 		case 'w':
-			doword = 1;
+			doword = true;
 			break;
 		case 'm':
-			dochar = 1;
+			dochar = true;
 			dobyte = 0;
 			break;
 		case 'c':
 			dochar = 0;
-			dobyte = 1;
+			dobyte = true;
 			break;
 		case 'L':
 			dolongest = true;
 			break;
 		case '?':
 		default:
 			usage();
+		}
 	argv += optind;
 	argc -= optind;
 	/* Wc's flags are on by default. */
-	if (doline + doword + dobyte + dochar == 0)
+	if (!(doline || doword || dobyte || dochar || dolongest))
-		doline = doword = dobyte = 1;
+		doline = doword = dobyte = true;
-	if (!*argv) {
+	if (*argv == NULL) {
 		cnt(NULL);
 	} else {
-		int dototal = (argc > 1);
+		bool dototal = (argc > 1);
 		do {
 			cnt(*argv);
 		} while(*++argv);
-		if (dototal)
+		if (dototal) {
-			print_counts(tlinect, twordct, tcharct, "total");
+			print_counts(tlinect, twordct, tcharct, tlongest,
 			    "total");
+		}
+	}
 	exit(rval);
+}
 static size_t
-do_mb(wchar_t *wc, const char *p, size_t mblen, mbstate_t *st,
+do_mb(wchar_t *wc, const char *p, size_t len, mbstate_t *st,
-    size_t *cnt, const char *file)
+    size_t *retcnt, const char *file)
+{
 	size_t r;
 	size_t c = 0;
 	do {
-		r = mbrtowc(wc, p, mblen, st);
+		r = mbrtowc(wc, p, len, st);
 		if (r == (size_t)-1) {
 			warnx("%s: invalid byte sequence", file);
 			rval = 1;
 			/* XXX skip 1 byte */
-			mblen--;
+			len--;
 			p++;
 			memset(st, 0, sizeof(*st));
 			continue;
 		} else if (r == (size_t)-2)
 			break;
 		else if (r == 0)
 			r = 1;
 		c++;
 		if (wc)
 			wc++;
-		mblen -= r;
+		len -= r;
 		p += r;
-	} while (mblen > 0);
+	} while (len > 0);
-	*cnt = c;
+	*retcnt = c;
 	return (r);
+}
 static void
-cnt(char *file)
+cnt(const char *file)
+{
 	u_char buf[MAXBSIZE];
 	wchar_t wbuf[MAXBSIZE];
 	struct stat sb;
-	wc_count_t charct, linect, wordct;
+	wc_count_t charct, linect, wordct, longest;
 	mbstate_t st;
 	u_char *C;
 	wchar_t *WC;
-	char *name;				/* filename or <stdin> */
+	const char *name;			/* filename or <stdin> */
 	size_t r = 0;
-	int fd, gotsp, len = 0;
+	int fd, len = 0;
-	linect = wordct = charct = 0;
+	linect = wordct = charct = longest = 0;
-	if (file) {
+	if (file != NULL) {
 		if ((fd = open(file, O_RDONLY, 0)) < 0) {
 			warn("%s", file);
 			rval = 1;
 			return;
+		}
 		name = file;
 	} else {
 		fd = STDIN_FILENO;
 		name = "<stdin>";
+	}
-	if (dochar || doword)
+	if (dochar || doword || dolongest)
-		memset(&st, 0, sizeof(st));
+		(void)memset(&st, 0, sizeof(st));
-	if (!doword) {
+	if (!(doword || dolongest)) {
 		/*
 		 * line counting is split out because it's a lot
 		 * faster to get lines than to get words, since
 		 * the word count requires some logic.
 		 */
 		if (doline || dochar) {
 			while ((len = read(fd, buf, MAXBSIZE)) > 0) {
 				if (dochar) {
 					size_t wlen;
 					r = do_mb(0, (char *)buf, (size_t)len,
 					    &st, &wlen, name);
 					charct += wlen;
 				} else if (dobyte)
 					charct += len;
-				if (doline)
+				if (doline) {
-					for (C = buf; len--; ++C)
+					for (C = buf; len--; ++C) {
 						if (*C == '\n')
 							++linect;
+					}
+				}
+			}
+		}
 		/*
 		 * if all we need is the number of characters and
 		 * it's a directory or a regular or linked file, just
 		 * stat the puppy.  We avoid testing for it not being
 		 * a special device in case someone adds a new type
 		 * of inode.
 		 */
 		else if (dobyte) {
 			if (fstat(fd, &sb)) {
 				warn("%s", name);
 @@ -234,96 +243,113 @@ cnt(char *file)
 				if (S_ISREG(sb.st_mode) ||
 				    S_ISLNK(sb.st_mode) ||
 				    S_ISDIR(sb.st_mode)) {
 					charct = sb.st_size;
 				} else {
 					while ((len =
 					    read(fd, buf, MAXBSIZE)) > 0)
 						charct += len;
+				}
+			}
+		}
 	} else {
 		/* do it the hard way... */
-		gotsp = 1;
+		wc_count_t linelen;
                 bool       gotsp;
 		linelen = 0;
 		gotsp = true;
 		while ((len = read(fd, buf, MAXBSIZE)) > 0) {
 			size_t wlen;
 			r = do_mb(wbuf, (char *)buf, (size_t)len, &st, &wlen,
 			    name);
 			if (dochar) {
 				charct += wlen;
-			} else if (dobyte)
+			} else if (dobyte) {
 				charct += len;
+			}
 			for (WC = wbuf; wlen--; ++WC) {
 				if (iswspace(*WC)) {
-					gotsp = 1;
+					gotsp = true;
 					if (*WC == L'\n') {
 						++linect;
 						if (linelen > longest)
 							longest = linelen;
 						linelen = 0;
 					} else {
 						linelen++;
+					}
 				} else {
 					/*
 					 * This line implements the POSIX
 					 * spec, i.e. a word is a "maximal
 					 * string of characters delimited by
 					 * whitespace."  Notice nothing was
 					 * said about a character being
 					 * printing or non-printing.
 					 */
 					if (gotsp) {
-						gotsp = 0;
+						gotsp = false;
 						++wordct;
+					}
 					linelen++;
+				}
+			}
+		}
+	}
 	if (len == -1) {
 		warn("%s", name);
 		rval = 1;
+	}
 	if (dochar && r == (size_t)-2) {
 		warnx("%s: incomplete multibyte character", name);
 		rval = 1;
+	}
-	print_counts(linect, wordct, charct, file);
+	print_counts(linect, wordct, charct, longest, file);
 	/*
 	 * don't bother checkint doline, doword, or dobyte --- speeds
 	 * up the common case
 	 */
 	tlinect += linect;
 	twordct += wordct;
 	tcharct += charct;
 	if (dolongest && longest > tlongest)
 		tlongest = longest;
 	if (close(fd)) {
 		warn("%s", name);
 		rval = 1;
+	}
+}
 static void
-print_counts(wc_count_t lines, wc_count_t words, wc_count_t chars, char *name)
+print_counts(wc_count_t lines, wc_count_t words, wc_count_t chars,
     wc_count_t longest, const char *name)
+{
 	if (doline)
-		printf(WCFMT, (WCCAST)lines);
+		(void)printf(WCFMT, (WCCAST)lines);
 	if (doword)
-		printf(WCFMT, (WCCAST)words);
+		(void)printf(WCFMT, (WCCAST)words);
 	if (dobyte || dochar)
-		printf(WCFMT, (WCCAST)chars);
+		(void)printf(WCFMT, (WCCAST)chars);
 	if (dolongest)
 		(void)printf(WCFMT, (WCCAST)longest);
-	if (name)
+	if (name != NULL)
-		printf(" %s\n", name);
+		(void)printf(" %s\n", name);
 	else
-		printf("\n");
+		(void)putchar('\n');
+}
 static void
 usage(void)
+{
-	(void)fprintf(stderr, "usage: wc [-c | -m] [-lw] [file ...]\n");
+	(void)fprintf(stderr, "usage: wc [-c | -m] [-Llw] [file ...]\n");
 	exit(1);
+}