aboutsummaryrefslogtreecommitdiffstats
path: root/text_cmds/wc
diff options
context:
space:
mode:
authorCameron Katri <me@cameronkatri.com>2021-05-09 14:20:58 -0400
committerCameron Katri <me@cameronkatri.com>2021-05-09 14:20:58 -0400
commit5fd83771641d15c418f747bd343ba6738d3875f7 (patch)
tree5abf0f78f680d9837dbd93d4d4c3933bb7509599 /text_cmds/wc
downloadapple_cmds-5fd83771641d15c418f747bd343ba6738d3875f7.tar.gz
apple_cmds-5fd83771641d15c418f747bd343ba6738d3875f7.tar.zst
apple_cmds-5fd83771641d15c418f747bd343ba6738d3875f7.zip
Import macOS userland
adv_cmds-176 basic_cmds-55 bootstrap_cmds-116.100.1 developer_cmds-66 diskdev_cmds-667.40.1 doc_cmds-53.60.1 file_cmds-321.40.3 mail_cmds-35 misc_cmds-34 network_cmds-606.40.1 patch_cmds-17 remote_cmds-63 shell_cmds-216.60.1 system_cmds-880.60.2 text_cmds-106
Diffstat (limited to 'text_cmds/wc')
-rw-r--r--text_cmds/wc/wc.1163
-rw-r--r--text_cmds/wc/wc.c294
2 files changed, 457 insertions, 0 deletions
diff --git a/text_cmds/wc/wc.1 b/text_cmds/wc/wc.1
new file mode 100644
index 0000000..d0902e9
--- /dev/null
+++ b/text_cmds/wc/wc.1
@@ -0,0 +1,163 @@
+.\" 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
+.\" notice, this list of conditions and the following disclaimer in the
+.\" documentation and/or other materials provided with the distribution.
+.\" 3. All advertising materials mentioning features or use of this software
+.\" must display the following acknowledgement:
+.\" This product includes software developed by the University of
+.\" California, Berkeley and its contributors.
+.\" 4. Neither the name of the University nor the names of its contributors
+.\" may be used to endorse or promote products derived from this software
+.\" without specific prior written permission.
+.\"
+.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+.\" 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.
+.\"
+.\" @(#)wc.1 8.2 (Berkeley) 4/19/94
+.\" $FreeBSD: src/usr.bin/wc/wc.1,v 1.23 2005/02/26 04:14:20 trhodes Exp $
+.\"
+.Dd February 23, 2005
+.Dt WC 1
+.Os
+.Sh NAME
+.Nm wc
+.Nd word, line, character, and byte count
+.Sh SYNOPSIS
+.Nm
+.Op Fl clmw
+.Op Ar
+.Sh DESCRIPTION
+The
+.Nm
+utility displays the number of lines, words, and bytes contained in each
+input
+.Ar file ,
+or standard input (if no file is specified) to the standard output.
+A line is defined as a string of characters delimited by a
+.Aq newline
+character.
+Characters beyond the final
+.Aq newline
+character will not be included
+in the line count.
+.Pp
+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.
+This will cancel out any prior usage of the
+.Fl m
+option.
+.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.
+If the current locale does not support multibyte characters, this
+is equivalent to the
+.Fl c
+option.
+This will cancel out any prior usage of the
+.Fl c
+option.
+.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 order of output always takes the form of line, word,
+byte, and file name.
+The default action is equivalent to specifying the
+.Fl c , l
+and
+.Fl w
+options.
+.Pp
+If no files are specified, the standard input is used and no
+file name is displayed.
+The prompt will accept input until receiving EOF, or
+.Bq ^D
+in most environments.
+.Sh ENVIRONMENT
+The
+.Ev LANG , LC_ALL
+and
+.Ev LC_CTYPE
+environment variables affect the execution of
+.Nm
+as described in
+.Xr environ 7 .
+.Sh EXIT STATUS
+.Ex -std
+.Sh EXAMPLES
+Count the number of characters, words and lines in each of the files
+.Pa report1
+and
+.Pa report2
+as well as the totals for both:
+.Pp
+.Dl "wc -mlw report1 report2"
+.Sh COMPATIBILITY
+Historically, the
+.Nm
+utility was documented to define a word as a ``maximal string of
+characters delimited by <space>, <tab> or <newline> characters''.
+The implementation, however, did not handle non-printing characters
+correctly so that
+.Dq Li " ^D^E "
+counted as 6 spaces, while
+.Dq Li 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 .
+.Sh SEE ALSO
+.Xr iswspace 3
+.Sh STANDARDS
+The
+.Nm
+utility conforms to
+.St -p1003.1-2001 .
+.Sh HISTORY
+A
+.Nm
+command appeared in
+.At v1 .
diff --git a/text_cmds/wc/wc.c b/text_cmds/wc/wc.c
new file mode 100644
index 0000000..cb25729
--- /dev/null
+++ b/text_cmds/wc/wc.c
@@ -0,0 +1,294 @@
+/*
+ * 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.
+ * 3. All advertising materials mentioning features or use of this software
+ * must display the following acknowledgement:
+ * This product includes software developed by the University of
+ * California, Berkeley and its contributors.
+ * 4. Neither the name of the University nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+ * 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.
+ */
+
+#ifndef lint
+static const char copyright[] =
+"@(#) Copyright (c) 1980, 1987, 1991, 1993\n\
+ The Regents of the University of California. All rights reserved.\n";
+#endif /* not lint */
+
+#if 0
+#ifndef lint
+static char sccsid[] = "@(#)wc.c 8.1 (Berkeley) 6/6/93";
+#endif /* not lint */
+#endif
+
+#include <sys/cdefs.h>
+__FBSDID("$FreeBSD: src/usr.bin/wc/wc.c,v 1.21 2004/12/27 22:27:56 josef Exp $");
+
+#include <sys/param.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+
+#include <ctype.h>
+#include <err.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <locale.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <wchar.h>
+#include <wctype.h>
+
+/* We allocte this much memory statically, and use it as a fallback for
+ malloc failure, or statfs failure. So it should be small, but not
+ "too small" */
+#define SMALL_BUF_SIZE (1024 * 8)
+
+uintmax_t tlinect, twordct, tcharct;
+int doline, doword, dochar, domulti;
+
+static int cnt(const char *);
+static void usage(void);
+
+int
+main(int argc, char *argv[])
+{
+ int ch, errors, total;
+
+ (void) setlocale(LC_CTYPE, "");
+
+ while ((ch = getopt(argc, argv, "clmw")) != -1)
+ switch((char)ch) {
+ case 'l':
+ doline = 1;
+ break;
+ case 'w':
+ doword = 1;
+ break;
+ case 'c':
+ dochar = 1;
+ domulti = 0;
+ break;
+ case 'm':
+ domulti = 1;
+ dochar = 0;
+ break;
+ case '?':
+ default:
+ usage();
+ }
+ argv += optind;
+ argc -= optind;
+
+ /* Wc's flags are on by default. */
+ if (doline + doword + dochar + domulti == 0)
+ doline = doword = dochar = 1;
+
+ errors = 0;
+ total = 0;
+ if (!*argv) {
+ if (cnt((char *)NULL) != 0)
+ ++errors;
+ else
+ (void)printf("\n");
+ }
+ else do {
+ if (cnt(*argv) != 0)
+ ++errors;
+ else
+ (void)printf(" %s\n", *argv);
+ ++total;
+ } while(*++argv);
+
+ if (total > 1) {
+ if (doline)
+ (void)printf(" %7ju", tlinect);
+ if (doword)
+ (void)printf(" %7ju", twordct);
+ if (dochar || domulti)
+ (void)printf(" %7ju", tcharct);
+ (void)printf(" total\n");
+ }
+ exit(errors == 0 ? 0 : 1);
+}
+
+static int
+cnt(const char *file)
+{
+ struct stat sb;
+ struct statfs fsb;
+ uintmax_t linect, wordct, charct;
+ int fd, len, warned;
+ int stat_ret;
+ size_t clen;
+ short gotsp;
+ u_char *p;
+ static u_char small_buf[SMALL_BUF_SIZE];
+ static u_char *buf = small_buf;
+ static off_t buf_size = SMALL_BUF_SIZE;
+ wchar_t wch;
+ mbstate_t mbs;
+
+ linect = wordct = charct = 0;
+ if (file == NULL) {
+ file = "stdin";
+ fd = STDIN_FILENO;
+ } else {
+ if ((fd = open(file, O_RDONLY, 0)) < 0) {
+ warn("%s: open", file);
+ return (1);
+ }
+ }
+
+ if (fstatfs(fd, &fsb)) {
+ fsb.f_iosize = SMALL_BUF_SIZE;
+ }
+ if (fsb.f_iosize != buf_size) {
+ if (buf != small_buf) {
+ free(buf);
+ }
+ if (fsb.f_iosize == SMALL_BUF_SIZE || !(buf = malloc(fsb.f_iosize))) {
+ buf = small_buf;
+ buf_size = SMALL_BUF_SIZE;
+ } else {
+ buf_size = fsb.f_iosize;
+ }
+ }
+
+ if (doword || (domulti && MB_CUR_MAX != 1))
+ goto word;
+ /*
+ * 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) {
+ while ((len = read(fd, buf, buf_size))) {
+ if (len == -1) {
+ warn("%s: read", file);
+ (void)close(fd);
+ return (1);
+ }
+ charct += len;
+ for (p = buf; len--; ++p)
+ if (*p == '\n')
+ ++linect;
+ }
+ tlinect += linect;
+ (void)printf(" %7ju", linect);
+ if (dochar) {
+ tcharct += charct;
+ (void)printf(" %7ju", charct);
+ }
+ (void)close(fd);
+ return (0);
+ }
+ /*
+ * If all we need is the number of characters and it's a
+ * regular file, just stat the puppy.
+ */
+ if (dochar || domulti) {
+ if (fstat(fd, &sb)) {
+ warn("%s: fstat", file);
+ (void)close(fd);
+ return (1);
+ }
+ if (S_ISREG(sb.st_mode)) {
+ (void)printf(" %7lld", (long long)sb.st_size);
+ tcharct += sb.st_size;
+ (void)close(fd);
+ return (0);
+ }
+ }
+
+ /* Do it the hard way... */
+word: gotsp = 1;
+ warned = 0;
+ memset(&mbs, 0, sizeof(mbs));
+ while ((len = read(fd, buf, buf_size)) != 0) {
+ if (len == -1) {
+ warn("%s: read", file);
+ (void)close(fd);
+ return (1);
+ }
+ p = buf;
+ while (len > 0) {
+ if (!domulti || MB_CUR_MAX == 1) {
+ clen = 1;
+ wch = (unsigned char)*p;
+ } else if ((clen = mbrtowc(&wch, p, len, &mbs)) ==
+ (size_t)-1) {
+ if (!warned) {
+ errno = EILSEQ;
+ warn("%s", file);
+ warned = 1;
+ }
+ memset(&mbs, 0, sizeof(mbs));
+ clen = 1;
+ wch = (unsigned char)*p;
+ } else if (clen == (size_t)-2)
+ break;
+ else if (clen == 0)
+ clen = 1;
+ charct++;
+ len -= clen;
+ p += clen;
+ if (wch == L'\n')
+ ++linect;
+ if (iswspace(wch))
+ gotsp = 1;
+ else if (gotsp) {
+ gotsp = 0;
+ ++wordct;
+ }
+ }
+ }
+ if (domulti && MB_CUR_MAX > 1)
+ if (mbrtowc(NULL, NULL, 0, &mbs) == (size_t)-1 && !warned)
+ warn("%s", file);
+ if (doline) {
+ tlinect += linect;
+ (void)printf(" %7ju", linect);
+ }
+ if (doword) {
+ twordct += wordct;
+ (void)printf(" %7ju", wordct);
+ }
+ if (dochar || domulti) {
+ tcharct += charct;
+ (void)printf(" %7ju", charct);
+ }
+ (void)close(fd);
+ return (0);
+}
+
+static void
+usage()
+{
+ (void)fprintf(stderr, "usage: wc [-clmw] [file ...]\n");
+ exit(1);
+}