summaryrefslogtreecommitdiffstats
path: root/shell_cmds/hexdump
diff options
context:
space:
mode:
Diffstat (limited to 'shell_cmds/hexdump')
-rw-r--r--shell_cmds/hexdump/conv.c178
-rw-r--r--shell_cmds/hexdump/display.c417
-rw-r--r--shell_cmds/hexdump/hexdump.1342
-rw-r--r--shell_cmds/hexdump/hexdump.c86
-rw-r--r--shell_cmds/hexdump/hexdump.h108
-rw-r--r--shell_cmds/hexdump/hexsyntax.c147
-rw-r--r--shell_cmds/hexdump/od.1267
-rw-r--r--shell_cmds/hexdump/odsyntax.c447
-rw-r--r--shell_cmds/hexdump/parse.c523
9 files changed, 2515 insertions, 0 deletions
diff --git a/shell_cmds/hexdump/conv.c b/shell_cmds/hexdump/conv.c
new file mode 100644
index 0000000..9eebc51
--- /dev/null
+++ b/shell_cmds/hexdump/conv.c
@@ -0,0 +1,178 @@
+/*
+ * Copyright (c) 1989, 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.
+ * 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 sccsid[] = "@(#)conv.c 8.1 (Berkeley) 6/6/93";
+#endif /* not lint */
+#include <sys/cdefs.h>
+__FBSDID("$FreeBSD$");
+
+#include <sys/types.h>
+
+#include <assert.h>
+#include <ctype.h>
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <wchar.h>
+#include <wctype.h>
+#include "hexdump.h"
+
+void
+conv_c(PR *pr, u_char *p, size_t bufsize)
+{
+ char buf[10];
+ char const *str;
+ wchar_t wc;
+ size_t clen, oclen;
+ int converr, pad, width;
+ u_char peekbuf[MB_LEN_MAX];
+
+ if (pr->mbleft > 0) {
+ str = "**";
+ pr->mbleft--;
+ goto strpr;
+ }
+
+ switch(*p) {
+ case '\0':
+ str = "\\0";
+ goto strpr;
+ /* case '\a': */
+ case '\007':
+ str = "\\a";
+ goto strpr;
+ case '\b':
+ str = "\\b";
+ goto strpr;
+ case '\f':
+ str = "\\f";
+ goto strpr;
+ case '\n':
+ str = "\\n";
+ goto strpr;
+ case '\r':
+ str = "\\r";
+ goto strpr;
+ case '\t':
+ str = "\\t";
+ goto strpr;
+ case '\v':
+ str = "\\v";
+ goto strpr;
+ default:
+ break;
+ }
+ /*
+ * Multibyte characters are disabled for hexdump(1) for backwards
+ * compatibility and consistency (none of its other output formats
+ * recognize them correctly).
+ */
+ converr = 0;
+ if (odmode && MB_CUR_MAX > 1) {
+ oclen = 0;
+retry:
+ clen = mbrtowc(&wc, (const char *)p, bufsize, &pr->mbstate);
+ if (clen == 0)
+ clen = 1;
+ else if (clen == (size_t)-1 || (clen == (size_t)-2 &&
+ p == peekbuf)) {
+ memset(&pr->mbstate, 0, sizeof(pr->mbstate));
+ wc = *p;
+ clen = 1;
+ converr = 1;
+ } else if (clen == (size_t)-2) {
+ /*
+ * Incomplete character; peek ahead and see if we
+ * can complete it.
+ */
+ oclen = bufsize;
+ bufsize = peek(p = peekbuf, MB_CUR_MAX);
+ goto retry;
+ }
+ clen += oclen;
+ } else {
+ wc = *p;
+ clen = 1;
+ }
+ if (!converr && iswprint(wc)) {
+ if (!odmode) {
+ *pr->cchar = 'c';
+ (void)printf(pr->fmt, (int)wc);
+ } else {
+ *pr->cchar = 'C';
+ assert(strcmp(pr->fmt, "%3C") == 0);
+ width = wcwidth(wc);
+ assert(width >= 0);
+ pad = 3 - width;
+ if (pad < 0)
+ pad = 0;
+ (void)printf("%*s%C", pad, "", wc);
+ pr->mbleft = clen - 1;
+ }
+ } else {
+ (void)sprintf(buf, "%03o", (int)*p);
+ str = buf;
+strpr: *pr->cchar = 's';
+ (void)printf(pr->fmt, str);
+ }
+}
+
+void
+conv_u(PR *pr, u_char *p)
+{
+ static char const * list[] = {
+ "nul", "soh", "stx", "etx", "eot", "enq", "ack", "bel",
+ "bs", "ht", "lf", "vt", "ff", "cr", "so", "si",
+ "dle", "dc1", "dc2", "dc3", "dc4", "nak", "syn", "etb",
+ "can", "em", "sub", "esc", "fs", "gs", "rs", "us",
+ };
+
+ /* od used nl, not lf */
+ if (*p <= 0x1f) {
+ *pr->cchar = 's';
+ if (odmode && *p == 0x0a)
+ (void)printf(pr->fmt, "nl");
+ else
+ (void)printf(pr->fmt, list[*p]);
+ } else if (*p == 0x7f) {
+ *pr->cchar = 's';
+ (void)printf(pr->fmt, "del");
+ } else if (odmode && *p == 0x20) { /* od replaced space with sp */
+ *pr->cchar = 's';
+ (void)printf(pr->fmt, " sp");
+ } else if (isprint(*p)) {
+ *pr->cchar = 'c';
+ (void)printf(pr->fmt, *p);
+ } else {
+ *pr->cchar = 'x';
+ (void)printf(pr->fmt, (int)*p);
+ }
+}
diff --git a/shell_cmds/hexdump/display.c b/shell_cmds/hexdump/display.c
new file mode 100644
index 0000000..978a50c
--- /dev/null
+++ b/shell_cmds/hexdump/display.c
@@ -0,0 +1,417 @@
+/*
+ * Copyright (c) 1989, 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
+#if 0
+static char sccsid[] = "@(#)display.c 8.1 (Berkeley) 6/6/93";
+#endif
+#endif /* not lint */
+#include <sys/cdefs.h>
+__FBSDID("$FreeBSD: src/usr.bin/hexdump/display.c,v 1.19 2004/07/11 01:11:12 tjr Exp $");
+
+#include <sys/param.h>
+#include <sys/stat.h>
+
+#include <ctype.h>
+#include <err.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include "hexdump.h"
+
+enum _vflag vflag = FIRST;
+
+static off_t address; /* address/offset in stream */
+static off_t eaddress; /* end address */
+
+static __inline void print(PR *, u_char *);
+
+void
+display(void)
+{
+ FS *fs;
+ FU *fu;
+ PR *pr;
+ int cnt;
+ u_char *bp;
+ off_t saveaddress;
+ u_char savech=0, *savebp;
+
+ while ((bp = get()))
+ for (fs = fshead, savebp = bp, saveaddress = address; fs;
+ fs = fs->nextfs, bp = savebp, address = saveaddress)
+ for (fu = fs->nextfu; fu; fu = fu->nextfu) {
+ if (fu->flags&F_IGNORE)
+ break;
+ for (cnt = fu->reps; cnt; --cnt)
+ for (pr = fu->nextpr; pr; address += pr->bcnt,
+ bp += pr->bcnt, pr = pr->nextpr) {
+ if (eaddress && address >= eaddress &&
+ !(pr->flags & (F_TEXT|F_BPAD)))
+ bpad(pr);
+ if (cnt == 1 && pr->nospace) {
+ savech = *pr->nospace;
+ *pr->nospace = '\0';
+ }
+ print(pr, bp);
+ if (cnt == 1 && pr->nospace)
+ *pr->nospace = savech;
+ }
+ }
+ if (endfu) {
+ /*
+ * If eaddress not set, error or file size was multiple of
+ * blocksize, and no partial block ever found.
+ */
+ if (!eaddress) {
+ if (!address) {
+ return;
+ }
+ eaddress = address;
+ }
+ for (pr = endfu->nextpr; pr; pr = pr->nextpr)
+ switch(pr->flags) {
+ case F_ADDRESS:
+ (void)printf(pr->fmt, (quad_t)eaddress);
+ break;
+ case F_TEXT:
+ (void)printf("%s", pr->fmt);
+ break;
+ default:
+ break;
+ }
+ }
+}
+
+static __inline void
+print(PR *pr, u_char *bp)
+{
+ long double ldbl;
+ double f8;
+ float f4;
+ int16_t s2;
+ int8_t s8;
+ int32_t s4;
+ u_int16_t u2;
+ u_int32_t u4;
+ u_int64_t u8;
+
+ switch(pr->flags) {
+ case F_ADDRESS:
+ (void)printf(pr->fmt, (quad_t)address);
+ break;
+ case F_BPAD:
+ (void)printf(pr->fmt, "");
+ break;
+ case F_C:
+ conv_c(pr, bp, eaddress ? eaddress - address :
+ blocksize - address % blocksize);
+ break;
+ case F_CHAR:
+ (void)printf(pr->fmt, *bp);
+ break;
+ case F_DBL:
+ switch(pr->bcnt) {
+ case 4:
+ bcopy(bp, &f4, sizeof(f4));
+ (void)printf(pr->fmt, f4);
+ break;
+ case 8:
+ bcopy(bp, &f8, sizeof(f8));
+ (void)printf(pr->fmt, f8);
+ break;
+ default:
+ if (pr->bcnt == sizeof(long double)) {
+ bcopy(bp, &ldbl, sizeof(ldbl));
+ (void)printf(pr->fmt, ldbl);
+ }
+ break;
+ }
+ break;
+ case F_INT:
+ switch(pr->bcnt) {
+ case 1:
+ (void)printf(pr->fmt, (quad_t)(signed char)*bp);
+ break;
+ case 2:
+ bcopy(bp, &s2, sizeof(s2));
+ (void)printf(pr->fmt, (quad_t)s2);
+ break;
+ case 4:
+ bcopy(bp, &s4, sizeof(s4));
+ (void)printf(pr->fmt, (quad_t)s4);
+ break;
+ case 8:
+ bcopy(bp, &s8, sizeof(s8));
+ (void)printf(pr->fmt, s8);
+ break;
+ }
+ break;
+ case F_P:
+ (void)printf(pr->fmt, isprint(*bp) && isascii(*bp) ? *bp : '.');
+ break;
+ case F_STR:
+ (void)printf(pr->fmt, (char *)bp);
+ break;
+ case F_TEXT:
+ (void)printf("%s", pr->fmt);
+ break;
+ case F_U:
+ conv_u(pr, bp);
+ break;
+ case F_UINT:
+ switch(pr->bcnt) {
+ case 1:
+ (void)printf(pr->fmt, (u_quad_t)*bp);
+ break;
+ case 2:
+ bcopy(bp, &u2, sizeof(u2));
+ (void)printf(pr->fmt, (u_quad_t)u2);
+ break;
+ case 4:
+ bcopy(bp, &u4, sizeof(u4));
+ (void)printf(pr->fmt, (u_quad_t)u4);
+ break;
+ case 8:
+ bcopy(bp, &u8, sizeof(u8));
+ (void)printf(pr->fmt, u8);
+ break;
+ }
+ break;
+ }
+}
+
+void
+bpad(PR *pr)
+{
+ static char const *spec = " -0+#";
+ char *p1, *p2;
+
+ /*
+ * Remove all conversion flags; '-' is the only one valid
+ * with %s, and it's not useful here.
+ */
+ pr->flags = F_BPAD;
+ pr->cchar[0] = 's';
+ pr->cchar[1] = '\0';
+ for (p1 = pr->fmt; *p1 != '%'; ++p1);
+ for (p2 = ++p1; *p1 && index(spec, *p1); ++p1);
+ while ((*p2++ = *p1++));
+}
+
+static char **_argv;
+
+u_char *
+get(void)
+{
+ static int ateof = 1;
+ static u_char *curp, *savp;
+ int n;
+ int need, nread;
+ int valid_save = 0;
+ u_char *tmpp;
+
+ if (!curp) {
+ if ((curp = calloc(1, blocksize)) == NULL)
+ err(1, NULL);
+ if ((savp = calloc(1, blocksize)) == NULL)
+ err(1, NULL);
+ } else {
+ tmpp = curp;
+ curp = savp;
+ savp = tmpp;
+ address += blocksize;
+ valid_save = 1;
+ }
+ for (need = blocksize, nread = 0;;) {
+ /*
+ * if read the right number of bytes, or at EOF for one file,
+ * and no other files are available, zero-pad the rest of the
+ * block and set the end flag.
+ */
+ if (!length || (ateof && !next((char **)NULL))) {
+ if (odmode && address < skip)
+ errx(1, "cannot skip past end of input");
+ if (need == blocksize)
+ return((u_char *)NULL);
+ /*
+ * XXX bcmp() is not quite right in the presence
+ * of multibyte characters.
+ */
+#ifdef __APPLE__
+ /* 5650060 */
+ if (!need && vflag != ALL &&
+#else
+ if (vflag != ALL &&
+#endif
+ valid_save &&
+ bcmp(curp, savp, nread) == 0) {
+ if (vflag != DUP)
+ (void)printf("*\n");
+ return((u_char *)NULL);
+ }
+ bzero((char *)curp + nread, need);
+ eaddress = address + nread;
+ if (length == 0)
+ lseek(STDIN_FILENO, ftell(stdin), SEEK_SET); /* rewind stdin for next process */
+ return(curp);
+ }
+ n = fread((char *)curp + nread, sizeof(u_char),
+ length == -1 ? need : MIN(length, need), stdin);
+ if (!n) {
+ if (ferror(stdin))
+ warn("%s", _argv[-1]);
+ ateof = 1;
+ continue;
+ }
+ ateof = 0;
+ if (length != -1)
+ length -= n;
+ if (!(need -= n)) {
+ /*
+ * XXX bcmp() is not quite right in the presence
+ * of multibyte characters.
+ */
+ if (vflag == ALL || vflag == FIRST ||
+ valid_save == 0 ||
+ bcmp(curp, savp, blocksize) != 0) {
+ if (vflag == DUP || vflag == FIRST)
+ vflag = WAIT;
+ return(curp);
+ }
+ if (vflag == WAIT)
+ (void)printf("*\n");
+ vflag = DUP;
+ address += blocksize;
+ need = blocksize;
+ nread = 0;
+ }
+ else
+ nread += n;
+ }
+}
+
+size_t
+peek(u_char *buf, size_t nbytes)
+{
+ size_t n, nread;
+ int c;
+
+ if (length != -1 && nbytes > length)
+ nbytes = length;
+ nread = 0;
+ while (nread < nbytes && (c = getchar()) != EOF) {
+ *buf++ = c;
+ nread++;
+ }
+ n = nread;
+ while (n-- > 0) {
+ c = *--buf;
+ ungetc(c, stdin);
+ }
+ return (nread);
+}
+
+int
+next(char **argv)
+{
+ static int done;
+ int statok;
+
+ if (argv) {
+ _argv = argv;
+ return(1);
+ }
+ for (;;) {
+ if (*_argv) {
+ if (!(freopen(*_argv, "r", stdin))) {
+ warn("%s", *_argv);
+ exitval = 1;
+ ++_argv;
+ continue;
+ }
+ statok = done = 1;
+ } else {
+ if (done++)
+ return(0);
+ statok = 0;
+ }
+ if (skip)
+ doskip(statok ? *_argv : "stdin", statok);
+ if (*_argv)
+ ++_argv;
+ if (!skip)
+ return(1);
+ }
+ /* NOTREACHED */
+}
+
+void
+doskip(const char *fname, int statok)
+{
+ int cnt;
+ struct stat sb;
+
+ if (statok) {
+ if (fstat(fileno(stdin), &sb))
+ err(1, "%s", fname);
+ if (S_ISREG(sb.st_mode) && skip >= sb.st_size) {
+ address += sb.st_size;
+ skip -= sb.st_size;
+ return;
+ }
+ }
+#ifdef __APPLE__
+ /* try to seek first; fall back on ESPIPE */
+ if (fseeko(stdin, skip, SEEK_SET) == 0) {
+#else /* !__APPLE__ */
+ if (S_ISREG(sb.st_mode)) {
+ if (fseeko(stdin, skip, SEEK_SET))
+ err(1, "%s", fname);
+#endif /* __APPLE__ */
+ address += skip;
+ skip = 0;
+ } else {
+#ifdef __APPLE__
+ if (errno != ESPIPE)
+ err(1, "%s", fname);
+#endif /* __APPLE__ */
+ for (cnt = 0; cnt < skip; ++cnt)
+ if (getchar() == EOF)
+ break;
+ address += cnt;
+ skip -= cnt;
+ }
+}
diff --git a/shell_cmds/hexdump/hexdump.1 b/shell_cmds/hexdump/hexdump.1
new file mode 100644
index 0000000..5e49a64
--- /dev/null
+++ b/shell_cmds/hexdump/hexdump.1
@@ -0,0 +1,342 @@
+.\" Copyright (c) 1989, 1990, 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.
+.\"
+.\" @(#)hexdump.1 8.2 (Berkeley) 4/18/94
+.\" $FreeBSD: src/usr.bin/hexdump/hexdump.1,v 1.21 2004/07/10 13:11:00 tjr Exp $
+.\"
+.Dd July 10, 2004
+.Dt HEXDUMP 1
+.Os
+.Sh NAME
+.Nm hexdump
+.Nd ASCII, decimal, hexadecimal, octal dump
+.Sh SYNOPSIS
+.Nm
+.Op Fl bcCdovx
+.Op Fl e Ar format_string
+.Op Fl f Ar format_file
+.Op Fl n Ar length
+.Bk -words
+.Op Fl s Ar skip
+.Ek
+.Ar
+.Sh DESCRIPTION
+The
+.Nm
+utility is a filter which displays the specified files, or
+the standard input, if no files are specified, in a user specified
+format.
+.Pp
+The options are as follows:
+.Bl -tag -width indent
+.It Fl b
+.Em One-byte octal display .
+Display the input offset in hexadecimal, followed by sixteen
+space-separated, three column, zero-filled, bytes of input data,
+in octal, per line.
+.It Fl C
+.Em Canonical hex+ASCII display .
+Display the input offset in hexadecimal, followed by sixteen
+space-separated, two column, hexadecimal bytes, followed by the
+same sixteen bytes in %_p format enclosed in ``|'' characters.
+.It Fl c
+.Em One-byte character display .
+Display the input offset in hexadecimal, followed by sixteen
+space-separated, three column, space-filled, characters of input
+data per line.
+.It Fl d
+.Em Two-byte decimal display .
+Display the input offset in hexadecimal, followed by eight
+space-separated, five column, zero-filled, two-byte units
+of input data, in unsigned decimal, per line.
+.It Fl e Ar format_string
+Specify a format string to be used for displaying data.
+.It Fl f Ar format_file
+Specify a file that contains one or more newline separated format strings.
+Empty lines and lines whose first non-blank character is a hash mark
+.Pf ( Cm \&# )
+are ignored.
+.It Fl n Ar length
+Interpret only
+.Ar length
+bytes of input.
+.It Fl o
+.Em Two-byte octal display .
+Display the input offset in hexadecimal, followed by eight
+space-separated, six column, zero-filled, two byte quantities of
+input data, in octal, per line.
+.It Fl s Ar offset
+Skip
+.Ar offset
+bytes from the beginning of the input.
+By default,
+.Ar offset
+is interpreted as a decimal number.
+With a leading
+.Cm 0x
+or
+.Cm 0X ,
+.Ar offset
+is interpreted as a hexadecimal number,
+otherwise, with a leading
+.Cm 0 ,
+.Ar offset
+is interpreted as an octal number.
+Appending the character
+.Cm b ,
+.Cm k ,
+.Cm m ,
+or
+.Cm g
+to
+.Ar offset
+causes it to be interpreted as a multiple of
+.Li 512 ,
+.Li 1024 ,
+.Li 1048576 ,
+or
+.Li 1073741824 ,
+respectively.
+.It Fl v
+Cause
+.Nm
+to display all input data.
+Without the
+.Fl v
+option, any number of groups of output lines, which would be
+identical to the immediately preceding group of output lines (except
+for the input offsets), are replaced with a line comprised of a
+single asterisk.
+.It Fl x
+.Em Two-byte hexadecimal display .
+Display the input offset in hexadecimal, followed by eight, space
+separated, four column, zero-filled, two-byte quantities of input
+data, in hexadecimal, per line.
+.El
+.Pp
+For each input file,
+.Nm
+sequentially copies the input to standard output, transforming the
+data according to the format strings specified by the
+.Fl e
+and
+.Fl f
+options, in the order that they were specified.
+.Ss Formats
+A format string contains any number of format units, separated by
+whitespace.
+A format unit contains up to three items: an iteration count, a byte
+count, and a format.
+.Pp
+The iteration count is an optional positive integer, which defaults to
+one.
+Each format is applied iteration count times.
+.Pp
+The byte count is an optional positive integer.
+If specified it defines the number of bytes to be interpreted by
+each iteration of the format.
+.Pp
+If an iteration count and/or a byte count is specified, a single slash
+must be placed after the iteration count and/or before the byte count
+to disambiguate them.
+Any whitespace before or after the slash is ignored.
+.Pp
+The format is required and must be surrounded by double quote
+(" ") marks.
+It is interpreted as a fprintf-style format string (see
+.Xr fprintf 3 ) ,
+with the
+following exceptions:
+.Bl -bullet -offset indent
+.It
+An asterisk (*) may not be used as a field width or precision.
+.It
+A byte count or field precision
+.Em is
+required for each ``s'' conversion
+character (unlike the
+.Xr fprintf 3
+default which prints the entire string if the precision is unspecified).
+.It
+The conversion characters ``h'', ``l'', ``n'', ``p'' and ``q'' are
+not supported.
+.It
+The single character escape sequences
+described in the C standard are supported:
+.Bd -ragged -offset indent -compact
+.Bl -column <alert_character>
+.It "NUL \e0
+.It "<alert character> \ea
+.It "<backspace> \eb
+.It "<form-feed> \ef
+.It "<newline> \en
+.It "<carriage return> \er
+.It "<tab> \et
+.It "<vertical tab> \ev
+.El
+.Ed
+.El
+.Pp
+The
+.Nm
+utility also supports the following additional conversion strings:
+.Bl -tag -width Fl
+.It Cm \&_a Ns Op Cm dox
+Display the input offset, cumulative across input files, of the
+next byte to be displayed.
+The appended characters
+.Cm d ,
+.Cm o ,
+and
+.Cm x
+specify the display base
+as decimal, octal or hexadecimal respectively.
+.It Cm \&_A Ns Op Cm dox
+Identical to the
+.Cm \&_a
+conversion string except that it is only performed
+once, when all of the input data has been processed.
+.It Cm \&_c
+Output characters in the default character set.
+Nonprinting characters are displayed in three character, zero-padded
+octal, except for those representable by standard escape notation
+(see above),
+which are displayed as two character strings.
+.It Cm _p
+Output characters in the ASCII character set.
+Non-ASCII characters are displayed as a single
+.Dq Cm \&. .
+.It Cm _u
+Output US
+.Tn ASCII
+characters, with the exception that control characters are
+displayed using the following, lower-case, names.
+Characters greater than 0xff, hexadecimal, are displayed as hexadecimal
+strings.
+.Bl -column \&000_nu \&001_so \&002_st \&003_et \&004_eo
+.It "\&000\ NUL\t001\ SOH\t002\ STX\t003\ ETX\t004\ EOT\t005\ ENQ
+.It "\&006\ ACK\t007\ BEL\t008\ BS\t009\ HT\t00A\ LF\t00B\ VT
+.It "\&00C\ FF\t00D\ CR\t00E\ SO\t00F\ SI\t010\ DLE\t011\ DC1
+.It "\&012\ DC2\t013\ DC3\t014\ DC4\t015\ NAK\t016\ SYN\t017\ ETB
+.It "\&018\ CAN\t019\ EM\t01A\ SUB\t01B\ ESC\t01C\ FS\t01D\ GS
+.It "\&01E\ RS\t01F\ US\t0FF\ DEL
+.El
+.El
+.Pp
+The default and supported byte counts for the conversion characters
+are as follows:
+.Bl -tag -width "Xc,_Xc,_Xc,_Xc,_Xc,_Xc" -offset indent
+.It Li \&%_c , \&%_p , \&%_u , \&%c
+One byte counts only.
+.It Xo
+.Li \&%d , \&%i , \&%o ,
+.Li \&%u , \&%X , \&%x
+.Xc
+Four byte default, one, two and four byte counts supported.
+.It Xo
+.Li \&%E , \&%e , \&%f ,
+.Li \&%G , \&%g
+.Xc
+Eight byte default, four and twelve byte counts supported.
+.El
+.Pp
+The amount of data interpreted by each format string is the sum of the
+data required by each format unit, which is the iteration count times the
+byte count, or the iteration count times the number of bytes required by
+the format if the byte count is not specified.
+.Pp
+The input is manipulated in ``blocks'', where a block is defined as the
+largest amount of data specified by any format string.
+Format strings interpreting less than an input block's worth of data,
+whose last format unit both interprets some number of bytes and does
+not have a specified iteration count, have the iteration count
+incremented until the entire input block has been processed or there
+is not enough data remaining in the block to satisfy the format string.
+.Pp
+If, either as a result of user specification or
+.Nm
+modifying
+the iteration count as described above, an iteration count is
+greater than one, no trailing whitespace characters are output
+during the last iteration.
+.Pp
+It is an error to specify a byte count as well as multiple conversion
+characters or strings unless all but one of the conversion characters
+or strings is
+.Cm \&_a
+or
+.Cm \&_A .
+.Pp
+If, as a result of the specification of the
+.Fl n
+option or end-of-file being reached, input data only partially
+satisfies a format string, the input block is zero-padded sufficiently
+to display all available data (i.e., any format units overlapping the
+end of data will display some number of the zero bytes).
+.Pp
+Further output by such format strings is replaced by an equivalent
+number of spaces.
+An equivalent number of spaces is defined as the number of spaces
+output by an
+.Cm s
+conversion character with the same field width
+and precision as the original conversion character or conversion
+string but with any
+.Dq Li \&+ ,
+.Dq \&\ \& ,
+.Dq Li \&#
+conversion flag characters
+removed, and referencing a NULL string.
+.Pp
+If no format strings are specified, the default display is a
+one-byte hexadecimal display.
+.Sh DIAGNOSTICS
+.Ex -std
+.Sh EXAMPLES
+Note that the following format strings, used with
+.Fl e ,
+must be enclosed in single quotes.
+.Pp
+Display the input in perusal format:
+.Bd -literal -offset indent
+"%06.6_ao " 12/1 "%3_u "
+"\et\et" "%_p "
+"\en"
+.Ed
+.Pp
+Implement the \-x option:
+.Bd -literal -offset indent
+"%07.7_Ax\en"
+"%07.7_ax " 8/2 "%04x " "\en"
+.Ed
+.Sh SEE ALSO
+.Xr gdb 1 ,
+.Xr od 1
diff --git a/shell_cmds/hexdump/hexdump.c b/shell_cmds/hexdump/hexdump.c
new file mode 100644
index 0000000..78df723
--- /dev/null
+++ b/shell_cmds/hexdump/hexdump.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright (c) 1989, 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) 1989, 1993\n\
+ The Regents of the University of California. All rights reserved.\n";
+#endif /* not lint */
+
+#ifndef lint
+#if 0
+static char sccsid[] = "@(#)hexdump.c 8.1 (Berkeley) 6/6/93";
+#endif
+#endif /* not lint */
+#include <sys/cdefs.h>
+__FBSDID("$FreeBSD: src/usr.bin/hexdump/hexdump.c,v 1.7 2002/09/04 23:29:01 dwmalone Exp $");
+
+#include <sys/types.h>
+#include <locale.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include "hexdump.h"
+
+FS *fshead; /* head of format strings */
+int blocksize; /* data block size */
+int exitval; /* final exit value */
+int length = -1; /* max bytes to read */
+
+int
+main(int argc, char *argv[])
+{
+ FS *tfs;
+ char *p;
+
+ (void)setlocale(LC_ALL, "");
+
+ if (!(p = rindex(argv[0], 'o')) || strcmp(p, "od"))
+ newsyntax(argc, &argv);
+ else
+ oldsyntax(argc, &argv);
+
+ /* figure out the data block size */
+ for (blocksize = 0, tfs = fshead; tfs; tfs = tfs->nextfs) {
+ tfs->bcnt = size(tfs);
+ if (blocksize < tfs->bcnt)
+ blocksize = tfs->bcnt;
+ }
+ /* rewrite the rules, do syntax checking */
+ for (tfs = fshead; tfs; tfs = tfs->nextfs)
+ rewrite(tfs);
+
+ (void)next(argv);
+ display();
+ exit(exitval);
+}
diff --git a/shell_cmds/hexdump/hexdump.h b/shell_cmds/hexdump/hexdump.h
new file mode 100644
index 0000000..a984287
--- /dev/null
+++ b/shell_cmds/hexdump/hexdump.h
@@ -0,0 +1,108 @@
+/*
+ * Copyright (c) 1989, 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.
+ *
+ * @(#)hexdump.h 8.1 (Berkeley) 6/6/93
+ * $FreeBSD: src/usr.bin/hexdump/hexdump.h,v 1.9 2004/07/11 01:11:12 tjr Exp $
+ */
+
+#include <wchar.h>
+
+typedef struct _pr {
+ struct _pr *nextpr; /* next print unit */
+#define F_ADDRESS 0x001 /* print offset */
+#define F_BPAD 0x002 /* blank pad */
+#define F_C 0x004 /* %_c */
+#define F_CHAR 0x008 /* %c */
+#define F_DBL 0x010 /* %[EefGf] */
+#define F_INT 0x020 /* %[di] */
+#define F_P 0x040 /* %_p */
+#define F_STR 0x080 /* %s */
+#define F_U 0x100 /* %_u */
+#define F_UINT 0x200 /* %[ouXx] */
+#define F_TEXT 0x400 /* no conversions */
+ u_int flags; /* flag values */
+ int bcnt; /* byte count */
+ char *cchar; /* conversion character */
+ char *fmt; /* printf format */
+ char *nospace; /* no whitespace version */
+ int mbleft; /* bytes left of multibyte char. */
+ mbstate_t mbstate; /* conversion state */
+} PR;
+
+typedef struct _fu {
+ struct _fu *nextfu; /* next format unit */
+ struct _pr *nextpr; /* next print unit */
+#define F_IGNORE 0x01 /* %_A */
+#define F_SETREP 0x02 /* rep count set, not default */
+ u_int flags; /* flag values */
+ int reps; /* repetition count */
+ int bcnt; /* byte count */
+ char *fmt; /* format string */
+} FU;
+
+typedef struct _fs { /* format strings */
+ struct _fs *nextfs; /* linked list of format strings */
+ struct _fu *nextfu; /* linked list of format units */
+ int bcnt;
+} FS;
+
+extern FS *fshead; /* head of format strings list */
+extern FU *endfu; /* format at end-of-data */
+extern int blocksize; /* data block size */
+extern int exitval; /* final exit value */
+extern int odmode; /* are we acting as od(1)? */
+extern int length; /* amount of data to read */
+extern off_t skip; /* amount of data to skip at start */
+enum _vflag { ALL, DUP, FIRST, WAIT }; /* -v values */
+extern enum _vflag vflag;
+
+void add(const char *);
+void addfile(char *);
+void badcnt(char *);
+void badconv(char *);
+void badfmt(const char *);
+void badsfmt(void);
+void bpad(PR *);
+void conv_c(PR *, u_char *, size_t);
+void conv_u(PR *, u_char *);
+void display(void);
+void doskip(const char *, int);
+void escape(char *);
+u_char *get(void);
+void newsyntax(int, char ***);
+int next(char **);
+void nomem(void);
+void oldsyntax(int, char ***);
+size_t peek(u_char *, size_t);
+void rewrite(FS *);
+int size(FS *);
+void usage(void);
diff --git a/shell_cmds/hexdump/hexsyntax.c b/shell_cmds/hexdump/hexsyntax.c
new file mode 100644
index 0000000..9961f2f
--- /dev/null
+++ b/shell_cmds/hexdump/hexsyntax.c
@@ -0,0 +1,147 @@
+/*-
+ * Copyright (c) 1990, 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
+#if 0
+static char sccsid[] = "@(#)hexsyntax.c 8.2 (Berkeley) 5/4/95";
+#endif
+#endif /* not lint */
+#include <sys/cdefs.h>
+__FBSDID("$FreeBSD: src/usr.bin/hexdump/hexsyntax.c,v 1.12 2002/09/04 23:29:01 dwmalone Exp $");
+
+#include <sys/types.h>
+
+#include <err.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "hexdump.h"
+
+off_t skip; /* bytes to skip */
+
+void
+newsyntax(int argc, char ***argvp)
+{
+ int ch;
+ char *p, **argv;
+
+ argv = *argvp;
+ if ((p = rindex(argv[0], 'h')) != NULL &&
+ strcmp(p, "hd") == 0) {
+ /* "Canonical" format, implies -C. */
+ add("\"%08.8_Ax\n\"");
+ add("\"%08.8_ax \" 8/1 \"%02x \" \" \" 8/1 \"%02x \" ");
+ add("\" |\" 16/1 \"%_p\" \"|\\n\"");
+ }
+ while ((ch = getopt(argc, argv, "bcCde:f:n:os:vx")) != -1)
+ switch (ch) {
+ case 'b':
+ add("\"%07.7_Ax\n\"");
+ add("\"%07.7_ax \" 16/1 \"%03o \" \"\\n\"");
+ break;
+ case 'c':
+ add("\"%07.7_Ax\n\"");
+ add("\"%07.7_ax \" 16/1 \"%3_c \" \"\\n\"");
+ break;
+ case 'C':
+ add("\"%08.8_Ax\n\"");
+ add("\"%08.8_ax \" 8/1 \"%02x \" \" \" 8/1 \"%02x \" ");
+ add("\" |\" 16/1 \"%_p\" \"|\\n\"");
+ break;
+ case 'd':
+ add("\"%07.7_Ax\n\"");
+ add("\"%07.7_ax \" 8/2 \" %05u \" \"\\n\"");
+ break;
+ case 'e':
+ add(optarg);
+ break;
+ case 'f':
+ addfile(optarg);
+ break;
+ case 'n':
+ if ((length = atoi(optarg)) < 0)
+ errx(1, "%s: bad length value", optarg);
+ break;
+ case 'o':
+ add("\"%07.7_Ax\n\"");
+ add("\"%07.7_ax \" 8/2 \" %06o \" \"\\n\"");
+ break;
+ case 's':
+ if ((skip = strtoll(optarg, &p, 0)) < 0)
+ errx(1, "%s: bad skip value", optarg);
+ switch(*p) {
+ case 'b':
+ skip *= 512;
+ break;
+ case 'k':
+ skip *= 1024;
+ break;
+ case 'm':
+ skip *= 1048576;
+ break;
+ case 'g':
+ skip *= 1073741824;
+ break;
+ }
+ break;
+ case 'v':
+ vflag = ALL;
+ break;
+ case 'x':
+ add("\"%07.7_Ax\n\"");
+ add("\"%07.7_ax \" 8/2 \" %04x \" \"\\n\"");
+ break;
+ case '?':
+ usage();
+ }
+
+ if (!fshead) {
+ add("\"%07.7_Ax\n\"");
+ add("\"%07.7_ax \" 16/1 \"%02x \" \"\\n\"");
+ }
+
+ *argvp += optind;
+}
+
+void
+usage(void)
+{
+ (void)fprintf(stderr, "%s\n%s\n%s\n%s\n",
+"usage: hexdump [-bcCdovx] [-e fmt] [-f fmt_file] [-n length]",
+" [-s skip] [file ...]",
+" hd [-bcdovx] [-e fmt] [-f fmt_file] [-n length]",
+" [-s skip] [file ...]");
+ exit(1);
+}
diff --git a/shell_cmds/hexdump/od.1 b/shell_cmds/hexdump/od.1
new file mode 100644
index 0000000..f827f6c
--- /dev/null
+++ b/shell_cmds/hexdump/od.1
@@ -0,0 +1,267 @@
+.\" Copyright (c) 1990, 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.
+.\"
+.\" @(#)od.1 8.1 (Berkeley) 6/6/93
+.\" $FreeBSD: src/usr.bin/hexdump/od.1,v 1.17 2004/07/11 01:11:12 tjr Exp $
+.\"
+.Dd July 11, 2004
+.Os
+.Dt OD 1
+.Sh NAME
+.Nm od
+.Nd octal, decimal, hex, ASCII dump
+.Sh SYNOPSIS
+.Nm
+.Op Fl aBbcDdeFfHhIiLlOosvXx
+.Op Fl A Ar base
+.Op Fl j Ar skip
+.Op Fl N Ar length
+.Op Fl t Ar type
+.Sm off
+.Oo
+.Op Cm \&+
+.Li offset
+.Op Cm \&.
+.Op Cm Bb
+.Oc
+.Sm on
+.Op Ar
+.Sh DESCRIPTION
+The
+.Nm
+utility is a filter which displays the specified files, or standard
+input if no files are specified, in a user specified format.
+.Pp
+The options are as follows:
+.Bl -tag -width ".Fl I , L , l"
+.It Fl A Ar base
+Specify the input address base.
+.Ar base
+may be one of
+.Cm d ,
+.Cm o ,
+.Cm x
+or
+.Cm n ,
+which specify decimal, octal, hexadecimal
+addresses or no address, respectively.
+.It Fl a
+Output named characters.
+Equivalent to
+.Fl t Ar a .
+.It Fl B , o
+Output octal shorts.
+Equivalent to
+.Fl t Ar o2 .
+.It Fl b
+Output octal bytes.
+Equivalent to
+.Fl t Ar o1 .
+.It Fl c
+Output C-style escaped characters.
+Equivalent to
+.Fl t Ar c .
+.It Fl D
+Output unsigned decimal ints.
+Equivalent to
+.Fl t Ar u4 .
+.It Fl e , F
+Output double-precision floating point numbers.
+Equivalent to
+.Fl t Ar fD .
+.It Fl f
+Output single-precision floating point numbers.
+Equivalent to
+.Fl t Ar fF .
+.It Fl H , X
+Output hexadecimal ints.
+Equivalent to
+.Fl t Ar x4 .
+.It Fl h , x
+Output hexadecimal shorts.
+Equivalent to
+.Fl t Ar x2 .
+.It Fl I , L , l
+Output signed decimal longs.
+Equivalent to
+.Fl t Ar dL .
+.It Fl i
+Output signed decimal ints.
+Equivalent to
+.Fl t Ar dI .
+.It Fl j Ar skip
+Skip
+.Ar skip
+bytes of the combined input before dumping.
+The number may be followed by one
+of
+.Cm b , k
+or
+.Cm m
+which specify the units of the number as blocks (512 bytes), kilobytes and
+megabytes, respectively.
+.It Fl N Ar length
+Dump at most
+.Ar length
+bytes of input.
+.It Fl O
+Output octal ints.
+Equivalent to
+.Fl t Ar o4 .
+.It Fl s
+Output signed decimal shorts.
+Equivalent to
+.Fl t Ar d2 .
+.It Fl t Ar type
+Specify the output format.
+.Ar type
+is a string containing one or more of the following kinds of type specifiers:
+.Bl -tag -width indent
+.It Cm a
+Named characters
+.Pq Tn ASCII .
+Control characters are displayed using the following names:
+.Bl -column "000 NUL" "001 SOH" "002 STX" "003 ETX" "004 EOT" "005 ENQ"
+.It "000 NUL 001 SOH 002 STX 003 ETX 004 EOT 005 ENQ"
+.It "006 ACK 007 BEL 008 BS 009 HT 00a NL 00b VT"
+.It "00c FF 00d CR 00e SO 00f SI 010 DLE 011 DC1"
+.It "012 DC2 013 DC3 014 DC4 015 NAK 016 SYN 017 ETB"
+.It "018 CAN 019 EM 01a SUB 01b ESC 01c FS 01d GS"
+.It "01e RS 01f US 020 SP 0ff DEL"
+.El
+.It Cm c
+Characters in the default character set.
+Non-printing characters are
+represented as 3-digit octal character codes, except the following
+characters, which are represented as C escapes:
+.Pp
+.Bl -tag -width carriage-return -compact
+.It NUL
+\e0
+.It alert
+\ea
+.It backspace
+\eb
+.It newline
+\en
+.It carriage-return
+\er
+.It tab
+\et
+.It vertical tab
+\ev
+.El
+.Pp
+Multi-byte characters are displayed in the area corresponding to the first
+byte of the character. The remaining bytes are shown as
+.Ql ** .
+.It Xo
+.Sm off
+.Op Cm d | o | u | x
+.Op Cm C | S | I | L | Ar n
+.Sm on
+.Xc
+Signed decimal
+.Pq Cm d ,
+octal
+.Pq Cm o ,
+unsigned decimal
+.Pq Cm u
+or
+hexadecimal
+.Pq Cm x .
+Followed by an optional size specifier, which may be either
+.Cm C
+.Pq Vt char ,
+.Cm S
+.Pq Vt short ,
+.Cm I
+.Pq Vt int ,
+.Cm L
+.Pq Vt long ,
+or a byte count as a decimal integer.
+.It Xo
+.Sm off
+.Cm f
+.Op Cm F | D | L | Ar n
+.Sm on
+.Xc
+Floating-point number.
+Followed by an optional size specifier, which may be either
+.Cm F
+.Pq Vt float ,
+.Cm D
+.Pq Vt double
+or
+.Cm L
+.Pq Vt "long double" .
+.El
+.It Fl v
+Write all input data, instead of replacing lines of duplicate values with a
+.Ql * .
+.El
+.Pp
+Multiple options that specify output format may be used; the output will
+contain one line for each format.
+.Pp
+If no output format is specified,
+.Fl t Ar oS
+is assumed.
+.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 DIAGNOSTICS
+.Ex -std
+.Sh COMPATIBILITY
+The traditional
+.Fl s
+option to extract string constants is not supported; consider using
+.Xr strings 1
+instead.
+.Sh SEE ALSO
+.Xr hexdump 1 ,
+.Xr strings 1
+.Sh STANDARDS
+The
+.Nm
+utility conforms to
+.St -p1003.1-2001 .
+.Sh HISTORY
+An
+.Nm
+command appeared in
+.At v1 .
diff --git a/shell_cmds/hexdump/odsyntax.c b/shell_cmds/hexdump/odsyntax.c
new file mode 100644
index 0000000..6b9202e
--- /dev/null
+++ b/shell_cmds/hexdump/odsyntax.c
@@ -0,0 +1,447 @@
+/*-
+ * Copyright (c) 1990, 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
+#if 0
+static char sccsid[] = "@(#)odsyntax.c 8.2 (Berkeley) 5/4/95";
+#endif
+#endif /* not lint */
+#include <sys/cdefs.h>
+__FBSDID("$FreeBSD: src/usr.bin/hexdump/odsyntax.c,v 1.16 2002/09/04 23:29:01 dwmalone Exp $");
+
+#include <sys/types.h>
+
+#include <ctype.h>
+#include <err.h>
+#include <errno.h>
+#include <float.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "hexdump.h"
+
+#define PADDING " "
+
+int odmode;
+
+static void odadd(const char *);
+static void odformat(const char *);
+static const char *odformatfp(char, const char *);
+static const char *odformatint(char, const char *);
+static void odoffset(int, char ***);
+static void odusage(void);
+
+void
+oldsyntax(int argc, char ***argvp)
+{
+ static char _n[] = "%_n", padding[] = PADDING;
+ int ch;
+ char **argv, *end;
+
+ /* Add initial (default) address format. -A may change it later. */
+#define TYPE_OFFSET 7
+ add("\"%07.7_Ao\n\"");
+ add("\"%07.7_ao \"");
+
+ odmode = 1;
+ argv = *argvp;
+ while ((ch = getopt(argc, argv, "A:aBbcDdeFfHhIij:LlN:Oost:vXx")) != -1)
+ switch (ch) {
+ case 'A':
+ switch (*optarg) {
+ case 'd': case 'o': case 'x':
+ fshead->nextfu->fmt[TYPE_OFFSET] = *optarg;
+ fshead->nextfs->nextfu->fmt[TYPE_OFFSET] =
+ *optarg;
+ break;
+ case 'n':
+ fshead->nextfu->fmt = _n; /* mimic regular output */
+ fshead->nextfs->nextfu->fmt = padding;
+ break;
+ default:
+ errx(1, "%s: invalid address base", optarg);
+ }
+ break;
+ case 'a':
+ odformat("a");
+ break;
+ case 'B':
+ case 'o':
+ odformat("o2");
+ break;
+ case 'b':
+ odformat("o1");
+ break;
+ case 'c':
+ odformat("c");
+ break;
+ case 'd':
+ odformat("u2");
+ break;
+ case 'D':
+ odformat("u4");
+ break;
+ case 'e': /* undocumented in od */
+ case 'F':
+ odformat("fD");
+ break;
+ case 'f':
+ odformat("fF");
+ break;
+ case 'H':
+ case 'X':
+ odformat("x4");
+ break;
+ case 'h':
+ case 'x':
+ odformat("x2");
+ break;
+ case 'I':
+ case 'L':
+ case 'l':
+ odformat("dL");
+ break;
+ case 'i':
+ odformat("dI");
+ break;
+ case 'j':
+ errno = 0;
+ skip = strtoll(optarg, &end, 0);
+ if (*end == 'b')
+ skip *= 512;
+ else if (*end == 'k')
+ skip *= 1024;
+ else if (*end == 'm')
+ skip *= 1048576L;
+ else if (*end == 'g')
+ skip *= 1073741824;
+ else if (*end != '\0')
+ skip = -1;
+ if (errno != 0 || skip < 0 || strlen(end) > 1)
+ errx(1, "%s: invalid skip amount", optarg);
+ break;
+ case 'N':
+ if ((length = atoi(optarg)) <= 0)
+ errx(1, "%s: invalid length", optarg);
+ break;
+ case 'O':
+ odformat("o4");
+ break;
+ case 's':
+ odformat("d2");
+ break;
+ case 't':
+ odformat(optarg);
+ break;
+ case 'v':
+ vflag = ALL;
+ break;
+ case '?':
+ default:
+ odusage();
+ }
+
+ if (fshead->nextfs->nextfs == NULL)
+ odformat("oS");
+
+ argc -= optind;
+ *argvp += optind;
+
+ if (argc)
+ odoffset(argc, argvp);
+}
+
+static void
+odusage(void)
+{
+
+ fprintf(stderr,
+"usage: od [-aBbcDdeFfHhIiLlOosvXx] [-A base] [-j skip] [-N length] [-t type]\n");
+ fprintf(stderr,
+" [[+]offset[.][Bb]] [file ...]\n");
+ exit(1);
+}
+
+static void
+odoffset(int argc, char ***argvp)
+{
+ unsigned char *p, *q, *num, *end;
+ int base;
+
+ /*
+ * The offset syntax of od(1) was genuinely bizarre. First, if
+ * it started with a plus it had to be an offset. Otherwise, if
+ * there were at least two arguments, a number or lower-case 'x'
+ * followed by a number makes it an offset. By default it was
+ * octal; if it started with 'x' or '0x' it was hex. If it ended
+ * in a '.', it was decimal. If a 'b' or 'B' was appended, it
+ * multiplied the number by 512 or 1024 byte units. There was
+ * no way to assign a block count to a hex offset.
+ *
+ * We assume it's a file if the offset is bad.
+ */
+ p = (unsigned char *)(argc == 1 ? (*argvp)[0] : (*argvp)[1]);
+
+ if (*p != '+' && (argc < 2 ||
+ (!isdigit(p[0]) && (p[0] != 'x' || !isxdigit(p[1])))))
+ return;
+
+ base = 0;
+ /*
+ * skip over leading '+', 'x[0-9a-fA-f]' or '0x', and
+ * set base.
+ */
+ if (p[0] == '+')
+ ++p;
+ if (p[0] == 'x' && isxdigit(p[1])) {
+ ++p;
+ base = 16;
+ } else if (p[0] == '0' && p[1] == 'x') {
+ p += 2;
+ base = 16;
+ }
+
+ /* skip over the number */
+ if (base == 16)
+ for (num = p; isxdigit(*p); ++p);
+ else
+ for (num = p; isdigit(*p); ++p);
+
+ /* check for no number */
+ if (num == p)
+ return;
+ q = p;
+ /* if terminates with a '.', base is decimal */
+ if (*q == '.') {
+ if (base)
+ return;
+ base = 10;
+ q++;
+ }
+
+ skip = strtoll((const char *)num, (char **)&end, base ? base : 8);
+
+ /* if end isn't the same as p, we got a non-octal digit */
+ if (end != p) {
+ skip = 0;
+ return;
+ }
+
+ if (*q) {
+ if (*q == 'B') {
+ skip *= 1024;
+ ++p;
+ } else if (*q == 'b') {
+ skip *= 512;
+ ++q;
+ }
+ }
+
+ if (*q) {
+ skip = 0;
+ return;
+ }
+
+ /*
+ * If the offset uses a non-octal base, the base of the offset
+ * is changed as well. This isn't pretty, but it's easy.
+ */
+ if (base == 16) {
+ fshead->nextfu->fmt[TYPE_OFFSET] = 'x';
+ fshead->nextfs->nextfu->fmt[TYPE_OFFSET] = 'x';
+ } else if (base == 10) {
+ fshead->nextfu->fmt[TYPE_OFFSET] = 'd';
+ fshead->nextfs->nextfu->fmt[TYPE_OFFSET] = 'd';
+ }
+
+ /* Terminate file list. */
+ (*argvp)[1] = NULL;
+}
+
+static void
+odformat(const char *fmt)
+{
+ char fchar;
+
+ while (*fmt != '\0') {
+ switch ((fchar = *fmt++)) {
+ case 'a':
+ odadd("16/1 \"%3_u \" \"\\n\"");
+ break;
+ case 'c':
+ odadd("16/1 \"%3_c \" \"\\n\"");
+ break;
+ case 'o': case 'u': case 'd': case 'x':
+ fmt = odformatint(fchar, fmt);
+ break;
+ case 'f':
+ fmt = odformatfp(fchar, fmt);
+ break;
+ default:
+ errx(1, "%c: unrecognised format character", fchar);
+ }
+ }
+}
+
+static const char *
+odformatfp(char fchar __unused, const char *fmt)
+{
+ size_t isize;
+ int digits;
+ char *end, *hdfmt;
+
+ isize = sizeof(double);
+ switch (*fmt) {
+ case 'F':
+ isize = sizeof(float);
+ fmt++;
+ break;
+ case 'D':
+ isize = sizeof(double);
+ fmt++;
+ break;
+ case 'L':
+ isize = sizeof(long double);
+ fmt++;
+ break;
+ default:
+ if (isdigit((unsigned char)*fmt)) {
+ errno = 0;
+ isize = (size_t)strtoul(fmt, &end, 10);
+ if (errno != 0 || isize == 0)
+ errx(1, "%s: invalid size", fmt);
+ fmt = (const char *)end;
+ }
+ }
+ switch (isize) {
+ case sizeof(float):
+ digits = FLT_DIG;
+ break;
+ case sizeof(double):
+ digits = DBL_DIG;
+ break;
+ default:
+ if (isize == sizeof(long double))
+ digits = LDBL_DIG;
+ else
+ errx(1, "unsupported floating point size %lu",
+ (u_long)isize);
+ }
+
+ asprintf(&hdfmt, "%lu/%lu \" %%%d.%de \" \"\\n\"",
+ 16UL / (u_long)isize, (u_long)isize, digits + 8, digits);
+ if (hdfmt == NULL)
+ err(1, NULL);
+ odadd(hdfmt);
+ free(hdfmt);
+
+ return (fmt);
+}
+
+static const char *
+odformatint(char fchar, const char *fmt)
+{
+ unsigned long long n;
+ size_t isize;
+ int digits;
+ char *end, *hdfmt;
+
+ isize = sizeof(int);
+ switch (*fmt) {
+ case 'C':
+ isize = sizeof(char);
+ fmt++;
+ break;
+ case 'I':
+ isize = sizeof(int);
+ fmt++;
+ break;
+ case 'L':
+ isize = sizeof(long);
+ fmt++;
+ break;
+ case 'S':
+ isize = sizeof(short);
+ fmt++;
+ break;
+ default:
+ if (isdigit((unsigned char)*fmt)) {
+ errno = 0;
+ isize = (size_t)strtoul(fmt, &end, 10);
+ if (errno != 0 || isize == 0)
+ errx(1, "%s: invalid size", fmt);
+ if (isize != sizeof(char) && isize != sizeof(short) &&
+ isize != sizeof(int) && isize != sizeof(long))
+ errx(1, "unsupported int size %lu",
+ (u_long)isize);
+ fmt = (const char *)end;
+ }
+ }
+
+ /*
+ * Calculate the maximum number of digits we need to
+ * fit the number. Overestimate for decimal with log
+ * base 8. We need one extra space for signed numbers
+ * to store the sign.
+ */
+ n = (1ULL << (8 * isize)) - 1;
+ digits = 0;
+ while (n != 0) {
+ digits++;
+ n >>= (fchar == 'x') ? 4 : 3;
+ }
+ if (fchar == 'd')
+ digits++;
+ asprintf(&hdfmt, "%lu/%lu \"%*s%%%s%d%c\" \"\\n\"",
+ 16UL / (u_long)isize, (u_long)isize, (int)(4 * isize - digits),
+ "", (fchar == 'd' || fchar == 'u') ? "" : "0", digits, fchar);
+ if (hdfmt == NULL)
+ err(1, NULL);
+ odadd(hdfmt);
+ free(hdfmt);
+
+ return (fmt);
+}
+
+static void
+odadd(const char *fmt)
+{
+ static int needpad;
+
+ if (needpad)
+ add("\""PADDING"\"");
+ add(fmt);
+ needpad = 1;
+}
diff --git a/shell_cmds/hexdump/parse.c b/shell_cmds/hexdump/parse.c
new file mode 100644
index 0000000..5445f18
--- /dev/null
+++ b/shell_cmds/hexdump/parse.c
@@ -0,0 +1,523 @@
+/*
+ * Copyright (c) 1989, 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
+#if 0
+static char sccsid[] = "@(#)parse.c 8.1 (Berkeley) 6/6/93";
+#endif
+#endif /* not lint */
+#include <sys/cdefs.h>
+__FBSDID("$FreeBSD: src/usr.bin/hexdump/parse.c,v 1.12 2002/09/04 23:29:01 dwmalone Exp $");
+
+#include <sys/types.h>
+
+#include <err.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <ctype.h>
+#include <string.h>
+#include "hexdump.h"
+
+FU *endfu; /* format at end-of-data */
+
+void
+addfile(char *name)
+{
+ unsigned char *p;
+ FILE *fp;
+ int ch;
+ char buf[2048 + 1];
+
+ if ((fp = fopen(name, "r")) == NULL)
+ err(1, "%s", name);
+ while (fgets(buf, sizeof(buf), fp)) {
+ if (!(p = (unsigned char *)index(buf, '\n'))) {
+ warnx("line too long");
+ while ((ch = getchar()) != '\n' && ch != EOF);
+ continue;
+ }
+ *p = '\0';
+ for (p = (unsigned char *)buf; *p && isspace(*p); ++p);
+ if (!*p || *p == '#')
+ continue;
+ add((const char *)p);
+ }
+ (void)fclose(fp);
+}
+
+void
+add(const char *fmt)
+{
+ unsigned const char *p, *savep;
+ static FS **nextfs;
+ FS *tfs;
+ FU *tfu, **nextfu;
+
+ /* start new linked list of format units */
+ if ((tfs = calloc(1, sizeof(FS))) == NULL)
+ err(1, NULL);
+ if (!fshead)
+ fshead = tfs;
+ else
+ *nextfs = tfs;
+ nextfs = &tfs->nextfs;
+ nextfu = &tfs->nextfu;
+
+ /* take the format string and break it up into format units */
+ for (p = (unsigned const char *)fmt;;) {
+ /* skip leading white space */
+ for (; isspace(*p); ++p);
+ if (!*p)
+ break;
+
+ /* allocate a new format unit and link it in */
+ if ((tfu = calloc(1, sizeof(FU))) == NULL)
+ err(1, NULL);
+ *nextfu = tfu;
+ nextfu = &tfu->nextfu;
+ tfu->reps = 1;
+
+ /* if leading digit, repetition count */
+ if (isdigit(*p)) {
+ for (savep = p; isdigit(*p); ++p);
+ if (!isspace(*p) && *p != '/')
+ badfmt(fmt);
+ /* may overwrite either white space or slash */
+ tfu->reps = atoi((const char *)savep);
+ tfu->flags = F_SETREP;
+ /* skip trailing white space */
+ for (++p; isspace(*p); ++p);
+ }
+
+ /* skip slash and trailing white space */
+ if (*p == '/')
+ while (isspace(*++p));
+
+ /* byte count */
+ if (isdigit(*p)) {
+ for (savep = p; isdigit(*p); ++p);
+ if (!isspace(*p))
+ badfmt(fmt);
+ tfu->bcnt = atoi((const char *)savep);
+ /* skip trailing white space */
+ for (++p; isspace(*p); ++p);
+ }
+
+ /* format */
+ if (*p != '"')
+ badfmt(fmt);
+ for (savep = ++p; *p != '"';)
+ if (*p++ == 0)
+ badfmt(fmt);
+ if (!(tfu->fmt = malloc(p - savep + 1)))
+ err(1, NULL);
+ (void) strncpy(tfu->fmt, (const char *)savep, p - savep);
+ tfu->fmt[p - savep] = '\0';
+ escape(tfu->fmt);
+ p++;
+ }
+}
+
+static const char *spec = ".#-+ 0123456789";
+
+int
+size(FS *fs)
+{
+ FU *fu;
+ int bcnt, cursize;
+ unsigned char *fmt;
+ int prec;
+
+ /* figure out the data block size needed for each format unit */
+ for (cursize = 0, fu = fs->nextfu; fu; fu = fu->nextfu) {
+ if (fu->bcnt) {
+ cursize += fu->bcnt * fu->reps;
+ continue;
+ }
+ for (bcnt = prec = 0, fmt = (unsigned char *)fu->fmt; *fmt; ++fmt) {
+ if (*fmt != '%')
+ continue;
+ /*
+ * skip any special chars -- save precision in
+ * case it's a %s format.
+ */
+ while (index(spec + 1, *++fmt));
+ if (*fmt == '.' && isdigit(*++fmt)) {
+ prec = atoi((const char *)fmt);
+ while (isdigit(*++fmt));
+ }
+ switch(*fmt) {
+ case 'c':
+ bcnt += 1;
+ break;
+ case 'd': case 'i': case 'o': case 'u':
+ case 'x': case 'X':
+ bcnt += 4;
+ break;
+ case 'e': case 'E': case 'f': case 'g': case 'G':
+ bcnt += 8;
+ break;
+ case 's':
+ bcnt += prec;
+ break;
+ case '_':
+ switch(*++fmt) {
+ case 'c': case 'p': case 'u':
+ bcnt += 1;
+ break;
+ }
+ }
+ }
+ cursize += bcnt * fu->reps;
+ }
+ return (cursize);
+}
+
+void
+rewrite(FS *fs)
+{
+ enum { NOTOKAY, USEBCNT, USEPREC } sokay;
+ PR *pr, **nextpr = NULL;
+ FU *fu;
+ unsigned char *p1, *p2, *fmtp;
+ char savech, cs[3];
+ int nconv, prec = 0;
+
+ for (fu = fs->nextfu; fu; fu = fu->nextfu) {
+ /*
+ * Break each format unit into print units; each conversion
+ * character gets its own.
+ */
+ for (nconv = 0, fmtp = (unsigned char *)fu->fmt; *fmtp; nextpr = &pr->nextpr) {
+ if ((pr = calloc(1, sizeof(PR))) == NULL)
+ err(1, NULL);
+ if (!fu->nextpr)
+ fu->nextpr = pr;
+ else
+ *nextpr = pr;
+
+ /* Skip preceding text and up to the next % sign. */
+ for (p1 = fmtp; *p1 && *p1 != '%'; ++p1);
+
+ /* Only text in the string. */
+ if (!*p1) {
+ pr->fmt = (char *)fmtp;
+ pr->flags = F_TEXT;
+ break;
+ }
+
+ /*
+ * Get precision for %s -- if have a byte count, don't
+ * need it.
+ */
+ if (fu->bcnt) {
+ sokay = USEBCNT;
+ /* Skip to conversion character. */
+ for (++p1; index(spec, *p1); ++p1);
+ } else {
+ /* Skip any special chars, field width. */
+ while (index(spec + 1, *++p1));
+ if (*p1 == '.' && isdigit(*++p1)) {
+ sokay = USEPREC;
+ prec = atoi((const char *)p1);
+ while (isdigit(*++p1));
+ } else
+ sokay = NOTOKAY;
+ }
+
+ p2 = p1 + 1; /* Set end pointer. */
+ cs[0] = *p1; /* Set conversion string. */
+ cs[1] = '\0';
+
+ /*
+ * Figure out the byte count for each conversion;
+ * rewrite the format as necessary, set up blank-
+ * padding for end of data.
+ */
+ switch(cs[0]) {
+ case 'c':
+ pr->flags = F_CHAR;
+ switch(fu->bcnt) {
+ case 0: case 1:
+ pr->bcnt = 1;
+ break;
+ default:
+ p1[1] = '\0';
+ badcnt((char *)p1);
+ }
+ break;
+ case 'd': case 'i':
+ pr->flags = F_INT;
+ goto isint;
+ case 'o': case 'u': case 'x': case 'X':
+ pr->flags = F_UINT;
+isint: cs[2] = '\0';
+ cs[1] = cs[0];
+ cs[0] = 'q';
+ switch(fu->bcnt) {
+ case 0: case 4:
+ pr->bcnt = 4;
+ break;
+ case 1:
+ pr->bcnt = 1;
+ break;
+ case 2:
+ pr->bcnt = 2;
+ break;
+#ifdef __APPLE__
+ case 8:
+ pr->bcnt = 8;
+ break;
+#endif /* __APPLE__ */
+ default:
+ p1[1] = '\0';
+ badcnt((char *)p1);
+ }
+ break;
+ case 'e': case 'E': case 'f': case 'g': case 'G':
+ pr->flags = F_DBL;
+ switch(fu->bcnt) {
+ case 0: case 8:
+ pr->bcnt = 8;
+ break;
+ case 4:
+ pr->bcnt = 4;
+ break;
+ default:
+ if (fu->bcnt == sizeof(long double)) {
+ cs[2] = '\0';
+ cs[1] = cs[0];
+ cs[0] = 'L';
+ pr->bcnt = sizeof(long double);
+ } else {
+ p1[1] = '\0';
+ badcnt((char *)p1);
+ }
+ }
+ break;
+ case 's':
+ pr->flags = F_STR;
+ switch(sokay) {
+ case NOTOKAY:
+ badsfmt();
+ case USEBCNT:
+ pr->bcnt = fu->bcnt;
+ break;
+ case USEPREC:
+ pr->bcnt = prec;
+ break;
+ }
+ break;
+ case '_':
+ ++p2;
+ switch(p1[1]) {
+ case 'A':
+ endfu = fu;
+ fu->flags |= F_IGNORE;
+ /* FALLTHROUGH */
+ case 'a':
+ pr->flags = F_ADDRESS;
+ ++p2;
+ switch(p1[2]) {
+ case 'd': case 'o': case'x':
+ cs[0] = 'q';
+ cs[1] = p1[2];
+ cs[2] = '\0';
+ break;
+ default:
+ p1[3] = '\0';
+ badconv((char *)p1);
+ }
+ break;
+ case 'c':
+ pr->flags = F_C;
+ /* cs[0] = 'c'; set in conv_c */
+ goto isint2;
+ case 'p':
+ pr->flags = F_P;
+ cs[0] = 'c';
+ goto isint2;
+ case 'u':
+ pr->flags = F_U;
+ /* cs[0] = 'c'; set in conv_u */
+isint2: switch(fu->bcnt) {
+ case 0: case 1:
+ pr->bcnt = 1;
+ break;
+ default:
+ p1[2] = '\0';
+ badcnt((char *)p1);
+ }
+ break;
+ case 'n': /* Force -A n to dump extra blank line like default od behavior */
+ endfu = fu;
+ fu->flags = F_IGNORE;
+ pr->flags = F_TEXT;
+ fmtp = (unsigned char *)"\n";
+ cs[0] = '\0';
+ break;
+ default:
+ p1[2] = '\0';
+ badconv((char *)p1);
+ }
+ break;
+ default:
+ p1[1] = '\0';
+ badconv((char *)p1);
+ }
+
+ /*
+ * Copy to PR format string, set conversion character
+ * pointer, update original.
+ */
+ savech = *p2;
+ p1[0] = '\0';
+ if ((pr->fmt = calloc(1, strlen((const char *)fmtp) + 2)) == NULL)
+ err(1, NULL);
+ (void)strcpy(pr->fmt, (const char *)fmtp);
+ (void)strcat(pr->fmt, cs);
+ *p2 = savech;
+ pr->cchar = pr->fmt + (p1 - fmtp);
+ fmtp = p2;
+
+ /* Only one conversion character if byte count. */
+ if (!(pr->flags&F_ADDRESS) && fu->bcnt && nconv++)
+ errx(1, "byte count with multiple conversion characters");
+ }
+ /*
+ * If format unit byte count not specified, figure it out
+ * so can adjust rep count later.
+ */
+ if (!fu->bcnt)
+ for (pr = fu->nextpr; pr; pr = pr->nextpr)
+ fu->bcnt += pr->bcnt;
+ }
+ /*
+ * If the format string interprets any data at all, and it's
+ * not the same as the blocksize, and its last format unit
+ * interprets any data at all, and has no iteration count,
+ * repeat it as necessary.
+ *
+ * If, rep count is greater than 1, no trailing whitespace
+ * gets output from the last iteration of the format unit.
+ */
+ for (fu = fs->nextfu; fu; fu = fu->nextfu) {
+ if (!fu->nextfu && fs->bcnt < blocksize &&
+ !(fu->flags&F_SETREP) && fu->bcnt)
+ fu->reps += (blocksize - fs->bcnt) / fu->bcnt;
+ if (fu->reps > 1) {
+ for (pr = fu->nextpr;; pr = pr->nextpr)
+ if (!pr->nextpr)
+ break;
+ for (p1 = (unsigned char *)pr->fmt, p2 = NULL; *p1; ++p1)
+ p2 = isspace(*p1) ? p1 : NULL;
+ if (p2)
+ pr->nospace = (char *)p2;
+ }
+ }
+#ifdef DEBUG
+ for (fu = fs->nextfu; fu; fu = fu->nextfu) {
+ (void)printf("fmt:");
+ for (pr = fu->nextpr; pr; pr = pr->nextpr)
+ (void)printf(" {%s}", pr->fmt);
+ (void)printf("\n");
+ }
+#endif
+}
+
+void
+escape(char *p1)
+{
+ char *p2;
+
+ /* alphabetic escape sequences have to be done in place */
+ for (p2 = p1;; ++p1, ++p2) {
+ if (!*p1) {
+ *p2 = *p1;
+ break;
+ }
+ if (*p1 == '\\')
+ switch(*++p1) {
+ case 'a':
+ /* *p2 = '\a'; */
+ *p2 = '\007';
+ break;
+ case 'b':
+ *p2 = '\b';
+ break;
+ case 'f':
+ *p2 = '\f';
+ break;
+ case 'n':
+ *p2 = '\n';
+ break;
+ case 'r':
+ *p2 = '\r';
+ break;
+ case 't':
+ *p2 = '\t';
+ break;
+ case 'v':
+ *p2 = '\v';
+ break;
+ default:
+ *p2 = *p1;
+ break;
+ }
+ }
+}
+
+void
+badcnt(char *s)
+{
+ errx(1, "%s: bad byte count", s);
+}
+
+void
+badsfmt(void)
+{
+ errx(1, "%%s: requires a precision or a byte count");
+}
+
+void
+badfmt(const char *fmt)
+{
+ errx(1, "\"%s\": bad format", fmt);
+}
+
+void
+badconv(char *ch)
+{
+ errx(1, "%%%s: bad conversion character", ch);
+}