commit bf86ecbe9208f5f8b8007fe4e70c2e3777cbe365
parent 39ff613ae2a7e3a9a075035e039cf4b413203f02
Author: sin <sin@2f30.org>
Date: Tue, 18 Nov 2014 16:42:59 +0000
Add hexdump/od
Diffstat:
| M | Makefile | | | 2 | +- |
| A | hexdump/Makefile | | | 10 | ++++++++++ |
| A | hexdump/conv.c | | | 120 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | hexdump/display.c | | | 366 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | hexdump/fgetln.c | | | 69 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | hexdump/hexdump.1 | | | 374 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | hexdump/hexdump.c | | | 78 | ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | hexdump/hexdump.h | | | 107 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | hexdump/hexsyntax.c | | | 132 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | hexdump/od.1 | | | 336 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | hexdump/odsyntax.c | | | 412 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | hexdump/parse.c | | | 527 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | hexdump/util.h | | | 4 | ++++ |
13 files changed, 2536 insertions(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
@@ -1,4 +1,4 @@
-TARG = awk sed
+TARG = awk hexdump sed
all:
@echo "CFLAGS = $(CFLAGS)"
diff --git a/hexdump/Makefile b/hexdump/Makefile
@@ -0,0 +1,10 @@
+OBJ = conv.o display.o fgetln.o hexdump.o hexsyntax.o odsyntax.o parse.o
+BIN = hexdump
+
+all: $(BIN)
+
+$(BIN): $(OBJ)
+ $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJ)
+
+clean:
+ rm -f $(BIN) $(OBJ)
diff --git a/hexdump/conv.c b/hexdump/conv.c
@@ -0,0 +1,120 @@
+/* $OpenBSD: conv.c,v 1.10 2014/04/19 09:28:20 sobrado Exp $ */
+/* $NetBSD: conv.c,v 1.7 2001/12/07 15:14:29 bjh21 Exp $ */
+
+/*
+ * 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. 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.
+ */
+
+#include <sys/types.h>
+
+#include <stdio.h>
+#include <ctype.h>
+
+#include "hexdump.h"
+
+void
+conv_c(PR *pr, u_char *p)
+{
+ char buf[10];
+ char const *str;
+
+ switch(*p) {
+ case '\0':
+ str = "\\0";
+ goto strpr;
+ /* case '\a': */
+ case '\007':
+ if (odmode) /* od didn't know about \a */
+ break;
+ 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':
+ if (odmode)
+ break;
+ str = "\\v";
+ goto strpr;
+ default:
+ break;
+ }
+ if (isprint(*p)) {
+ *pr->cchar = 'c';
+ (void)printf(pr->fmt, *p);
+ } else {
+ (void)snprintf(buf, sizeof buf, "%03o", (int)*p);
+ str = buf;
+strpr: *pr->cchar = 's';
+ (void)printf(pr->fmt, str);
+ }
+}
+
+void
+conv_u(PR *pr, u_char *p)
+{
+ static const char *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/hexdump/display.c b/hexdump/display.c
@@ -0,0 +1,366 @@
+/* $OpenBSD: display.c,v 1.20 2010/10/22 14:04:24 millert Exp $ */
+/* $NetBSD: display.c,v 1.12 2001/12/07 15:14:29 bjh21 Exp $ */
+
+/*
+ * 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. 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.
+ */
+
+#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, *savebp;
+
+ savech = 0;
+ while ((bp = get()) != NULL)
+ 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;
+ }
+ }
+}
+
+static __inline void
+print(PR *pr, u_char *bp)
+{
+ double f8;
+ float f4;
+ int16_t s2;
+ int32_t s4;
+ int64_t s8;
+ 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);
+ break;
+ case F_CHAR:
+ (void)printf(pr->fmt, *bp);
+ break;
+ case F_DBL:
+ switch(pr->bcnt) {
+ case 4:
+ memmove(&f4, bp, sizeof(f4));
+ (void)printf(pr->fmt, f4);
+ break;
+ case 8:
+ memmove(&f8, bp, sizeof(f8));
+ (void)printf(pr->fmt, f8);
+ break;
+ }
+ break;
+ case F_INT:
+ switch(pr->bcnt) {
+ case 1:
+ (void)printf(pr->fmt, (quad_t)*bp);
+ break;
+ case 2:
+ memmove(&s2, bp, sizeof(s2));
+ (void)printf(pr->fmt, (quad_t)s2);
+ break;
+ case 4:
+ memmove(&s4, bp, sizeof(s4));
+ (void)printf(pr->fmt, (quad_t)s4);
+ break;
+ case 8:
+ memmove(&s8, bp, sizeof(s8));
+ (void)printf(pr->fmt, s8);
+ break;
+ }
+ break;
+ case F_P:
+ (void)printf(pr->fmt, isprint(*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:
+ memmove(&u2, bp, sizeof(u2));
+ (void)printf(pr->fmt, (u_quad_t)u2);
+ break;
+ case 4:
+ memmove(&u4, bp, sizeof(u4));
+ (void)printf(pr->fmt, (u_quad_t)u4);
+ break;
+ case 8:
+ memmove(&u8, bp, sizeof(u8));
+ (void)printf(pr->fmt, u8);
+ break;
+ }
+ break;
+ }
+}
+
+void
+bpad(PR *pr)
+{
+ static const char *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 && strchr(spec, *p1); ++p1);
+ while ((*p2++ = *p1++) != '\0');
+}
+
+static char **_argv;
+
+u_char *
+get(void)
+{
+ static int ateof = 1;
+ static u_char *curp, *savp;
+ int n;
+ int need, nread;
+ u_char *tmpp;
+
+ if (!curp) {
+ curp = emalloc(blocksize);
+ savp = emalloc(blocksize);
+ } else {
+ tmpp = curp;
+ curp = savp;
+ savp = tmpp;
+ address += blocksize;
+ }
+ 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(NULL))) {
+ if (need == blocksize)
+ return(NULL);
+ if (!need && vflag != ALL &&
+ !memcmp(curp, savp, nread)) {
+ if (vflag != DUP)
+ (void)printf("*\n");
+ return(NULL);
+ }
+ memset((char *)curp + nread, 0, need);
+ eaddress = address + nread;
+ 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)) {
+ if (vflag == ALL || vflag == FIRST ||
+ memcmp(curp, savp, blocksize)) {
+ 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;
+ }
+}
+
+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 = done = 1;
+ ++_argv;
+ continue;
+ }
+ statok = done = 1;
+ } else {
+ if (done++)
+ return(0);
+ statok = 0;
+ }
+ if (iobuf != NULL)
+ setvbuf(stdin, iobuf, _IOFBF, iobufsiz);
+ if (skip)
+ doskip(statok ? *_argv : "stdin", statok);
+ if (*_argv)
+ ++_argv;
+ if (!skip)
+ return(1);
+ }
+ /* NOTREACHED */
+}
+
+void
+doskip(const char *fname, int statok)
+{
+ off_t cnt;
+ struct stat sb;
+
+ if (statok) {
+ if (fstat(fileno(stdin), &sb))
+ err(1, "fstat %s", fname);
+ if (S_ISREG(sb.st_mode)) {
+ if (skip >= sb.st_size) {
+ address += sb.st_size;
+ skip -= sb.st_size;
+ } else {
+ if (fseeko(stdin, skip, SEEK_SET))
+ err(1, "fseeko %s", fname);
+ address += skip;
+ skip = 0;
+ }
+ return;
+ }
+ }
+
+ for (cnt = 0; cnt < skip; ++cnt)
+ if (getchar() == EOF)
+ break;
+ address += cnt;
+ skip -= cnt;
+}
+
+void *
+emalloc(int allocsize)
+{
+ void *p;
+
+ if ((p = malloc((u_int)allocsize)) == NULL)
+ nomem();
+ memset(p, 0, allocsize);
+ return(p);
+}
+
+void
+nomem(void)
+{
+ err(1, NULL);
+}
diff --git a/hexdump/fgetln.c b/hexdump/fgetln.c
@@ -0,0 +1,69 @@
+/*
+ * Copyright © 2005 Hector Garcia Alvarez
+ * Copyright © 2005, 2008-2012 Guillem Jover <guillem@hadrons.org>
+ *
+ * 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. The name of the author may not be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED ``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 AUTHOR 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.
+ */
+
+#include <stdio.h>
+#include <sys/cdefs.h>
+#include <sys/types.h>
+#include <string.h>
+
+struct filebuf {
+ FILE *fp;
+ char *buf;
+ size_t len;
+};
+
+#define FILEBUF_POOL_ITEMS 32
+
+static struct filebuf fb_pool[FILEBUF_POOL_ITEMS];
+static int fb_pool_cur;
+
+char *
+fgetln(FILE *stream, size_t *len)
+{
+ struct filebuf *fb;
+ ssize_t nread;
+
+ /* Try to diminish the possibility of several fgetln() calls being
+ * used on different streams, by using a pool of buffers per file. */
+ fb = &fb_pool[fb_pool_cur];
+ if (fb->fp != stream && fb->fp != NULL) {
+ fb_pool_cur++;
+ fb_pool_cur %= FILEBUF_POOL_ITEMS;
+ fb = &fb_pool[fb_pool_cur];
+ }
+ fb->fp = stream;
+
+ nread = getline(&fb->buf, &fb->len, stream);
+ /* Note: the getdelim/getline API ensures nread != 0. */
+ if (nread == -1) {
+ *len = 0;
+ return NULL;
+ } else {
+ *len = (size_t)nread;
+ return fb->buf;
+ }
+}
diff --git a/hexdump/hexdump.1 b/hexdump/hexdump.1
@@ -0,0 +1,374 @@
+.\" $OpenBSD: hexdump.1,v 1.24 2011/05/06 18:11:43 otto Exp $
+.\" $NetBSD: hexdump.1,v 1.14 2001/12/07 14:46:24 bjh21 Exp $
+.\"
+.\" 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. 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.
+.\"
+.\" from: @(#)hexdump.1 8.2 (Berkeley) 4/18/94
+.\"
+.Dd $Mdocdate: May 6 2011 $
+.Dt HEXDUMP 1
+.Os
+.Sh NAME
+.Nm hexdump
+.Nd ascii, decimal, hexadecimal, octal dump
+.Sh SYNOPSIS
+.Nm hexdump
+.Bk -words
+.Op Fl bCcdovx
+.Op Fl e Ar format_string
+.Op Fl f Ar format_file
+.Op Fl n Ar length
+.Op Fl s Ar offset
+.Op Ar
+.Ek
+.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 Ds
+.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
+.Pq Ql #
+are ignored.
+.It Fl n Ar length
+Interpret only
+.Ar length
+bytes of input.
+By default,
+.Ar length
+is interpreted as a decimal number.
+With a leading
+.Cm 0x
+or
+.Cm 0X ,
+.Ar length
+is interpreted as a hexadecimal number,
+otherwise, with a leading
+.Cm 0 ,
+.Ar length
+is interpreted as an octal number.
+.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 ,
+or
+.Cm m
+to
+.Ar offset
+causes it to be interpreted as a multiple of
+.Li 512 ,
+.Li 1024 ,
+or
+.Li 1048576 ,
+respectively.
+.It Fl v
+The
+.Fl v
+option causes hexdump 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
+.Pq Ql * .
+.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
+.Pq Sq /
+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
+.Pq \&"\& \&"
+marks
+(the quote mark is a special character in many shell programs,
+and may have to be escaped from the shell).
+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
+.Sq s
+conversion character (unlike the
+.Xr fprintf 3
+default which prints the entire string if the precision is unspecified).
+.It
+The conversion characters
+.Sq h ,
+.Sq l ,
+.Sq n ,
+.Sq p ,
+and
+.Sq q
+are not supported.
+.It
+The single character escape sequences
+described in the C standard are supported:
+.Pp
+.Bl -tag -width "Xalert characterXXX" -offset indent -compact
+.It NUL
+\e0
+.It Aq alert character
+\ea
+.It Aq backspace
+\eb
+.It Aq form-feed
+\ef
+.It Aq newline
+\en
+.It Aq carriage return
+\er
+.It Aq tab
+\et
+.It Aq vertical tab
+\ev
+.El
+.El
+.Pp
+.Nm
+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 default character set.
+Nonprinting characters are displayed as a single dot
+.Ql \&. .
+.It Cm _u
+Output US ASCII characters, with the exception that control characters are
+displayed using the following, lower-case, names.
+Other non-printable characters are displayed as hexadecimal strings.
+.Bd -literal -offset 3n
+000 nul 001 soh 002 stx 003 etx 004 eot 005 enq
+006 ack 007 bel 008 bs 009 ht 00A lf 00B vt
+00C ff 00D cr 00E so 00F si 010 dle 011 dc1
+012 dc2 013 dc3 014 dc4 015 nak 016 syn 017 etb
+018 can 019 em 01A sub 01B esc 01C fs 01D gs
+01E rs 01F us 07F del
+.Ed
+.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, four and eight byte counts supported.
+.It Xo
+.Li \&%E , \&%e , \&%f ,
+.Li \&%G , \&%g
+.Xc
+Eight byte default, four 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
+.Dq 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 hexdump 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
+.Ql + ,
+.Ql \&\ \& ,
+.Ql #
+conversion flag characters
+removed, and referencing a NULL string.
+.Pp
+If no format strings are specified, the default display is equivalent
+to specifying the
+.Fl x
+option.
+.Sh EXIT STATUS
+.Ex -std hexdump
+.Sh EXAMPLES
+Display characters using a fieldwidth of 4,
+and using special names for control characters:
+.Pp
+.Dl $ hexdump -e '"%4_u"' file
+.Pp
+An example file for use with the
+.Fl f
+option, to display the input in perusal format:
+.Bd -literal -offset indent
+"%06.6_ao " 12/1 "%3_u "
+"\et\et" "%_p "
+"\en"
+.Ed
+.Pp
+An example file for use with the
+.Fl f
+option, which implements the equivalent of the
+.Fl x
+option:
+.Bd -literal -offset indent
+"%07.7_Ax\en"
+"%07.7_ax " 8/2 " %04x " "\en"
+.Ed
+.Sh SEE ALSO
+.Xr od 1
diff --git a/hexdump/hexdump.c b/hexdump/hexdump.c
@@ -0,0 +1,78 @@
+/* $OpenBSD: hexdump.c,v 1.16 2011/09/22 09:09:42 stsp Exp $ */
+/* $NetBSD: hexdump.c,v 1.7 1997/10/19 02:34:06 lukem Exp $ */
+
+/*
+ * 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. 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.
+ */
+
+#include <sys/param.h>
+#include <err.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "hexdump.h"
+
+FS *fshead; /* head of format strings */
+int blocksize; /* data block size */
+int exitval; /* final exit value */
+long length = -1; /* max bytes to read */
+char *iobuf; /* stdio I/O buffer */
+size_t iobufsiz; /* size of stdio I/O buffer */
+
+int main(int, char **);
+
+int
+main(int argc, char *argv[])
+{
+ FS *tfs;
+ char *p;
+
+ if (!(p = strrchr(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;
+ }
+ if (length != -1) {
+ iobufsiz = MIN(length, blocksize);
+ if ((iobuf = malloc(iobufsiz)) == NULL)
+ err(1, NULL);
+ }
+ /* rewrite the rules, do syntax checking */
+ for (tfs = fshead; tfs; tfs = tfs->nextfs)
+ rewrite(tfs);
+
+ (void)next(argv);
+ display();
+ exit(exitval);
+}
diff --git a/hexdump/hexdump.h b/hexdump/hexdump.h
@@ -0,0 +1,107 @@
+/* $OpenBSD: hexdump.h,v 1.10 2014/04/19 09:28:20 sobrado Exp $ */
+/* $NetBSD: hexdump.h,v 1.7 2001/12/07 15:14:29 bjh21 Exp $ */
+
+/*
+ * 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. 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.
+ *
+ * from: @(#)hexdump.h 8.1 (Berkeley) 6/6/93
+ */
+
+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 */
+} 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;
+
+enum _vflag { ALL, DUP, FIRST, WAIT }; /* -v values */
+
+extern int blocksize; /* data block size */
+extern int odmode; /* od compatibility */
+extern FU *endfu; /* format at end-of-data */
+extern int exitval; /* final exit value */
+extern FS *fshead; /* head of format strings list */
+extern long length; /* max bytes to read */
+extern off_t skip; /* bytes to skip */
+extern char *iobuf; /* stdio I/O buffer */
+extern size_t iobufsiz; /* size of stdio I/O buffer */
+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 *);
+void conv_u(PR *, u_char *);
+void display(void);
+void doskip(const char *, int);
+/*void err(const char *, ...);*/
+void *emalloc(int);
+void escape(char *);
+u_char *get(void);
+void newsyntax(int, char ***);
+int next(char **);
+void nomem(void);
+void oldsyntax(int, char ***);
+void rewrite(FS *);
+int size(FS *);
+void usage(void);
+void oldusage(void);
diff --git a/hexdump/hexsyntax.c b/hexdump/hexsyntax.c
@@ -0,0 +1,132 @@
+/* $OpenBSD: hexsyntax.c,v 1.12 2011/05/06 15:46:29 otto Exp $ */
+/* $NetBSD: hexsyntax.c,v 1.8 1998/04/08 23:48:57 jeremy Exp $ */
+
+/*-
+ * 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. 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.
+ */
+
+#include <sys/types.h>
+
+#include <err.h>
+#include <errno.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;
+ 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':
+ errno = 0;
+ if ((length = strtol(optarg, NULL, 0)) < 0 ||
+ errno != 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':
+ errno = 0;
+ if ((skip = (off_t)strtoll(optarg, &p, 0)) < 0 ||
+ errno != 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;
+ }
+ 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 \" 8/2 \" %04x \" \"\\n\"");
+ }
+
+ *argvp += optind;
+}
+
+void
+usage(void)
+{
+ extern char *__progname;
+ fprintf(stderr, "usage: %s [-bCcdovx] [-e format_string] "
+ "[-f format_file] [-n length]\n"
+ "\t[-s offset] [file ...]\n", __progname);
+ exit(1);
+}
diff --git a/hexdump/od.1 b/hexdump/od.1
@@ -0,0 +1,336 @@
+.\" $OpenBSD: od.1,v 1.30 2014/04/19 09:24:28 sobrado Exp $
+.\" $NetBSD: od.1,v 1.16 2001/12/07 01:23:42 bjh21 Exp $
+.\"
+.\" Copyright (c) 2001 The NetBSD Foundation, Inc.
+.\" All rights reserved.
+.\"
+.\" This code is derived from software contributed to The NetBSD Foundation
+.\" by Andrew Brown.
+.\"
+.\" 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.
+.\"
+.\" THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. 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 FOUNDATION 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.
+.\"/
+.Dd $Mdocdate: April 19 2014 $
+.Dt OD 1
+.Os
+.Sh NAME
+.Nm od
+.Nd octal, decimal, hex, ascii dump
+.Sh SYNOPSIS
+.Nm od
+.Bk -words
+.Op Fl aBbcDdeFfHhIiLlOosvXx
+.Op Fl A Ar base
+.Op Fl j Ar offset
+.Op Fl N Ar length
+.Op Fl t Ar type_string
+.Sm off
+.Oo
+.Op Cm \&+
+.Li offset
+.Op Cm \&.
+.Op Cm Bb
+.Sm on
+.Oc
+.Op Ar
+.Ek
+.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
+.It Fl A Ar base
+Specify the input address base.
+The argument
+.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
+.Em One-byte character display .
+Display the input offset in octal, followed by sixteen
+space-separated, three column, space-filled, characters of input data
+per line.
+Control characters are printed as their names instead of as C-style escapes.
+.It Fl B
+Same as
+.Fl o .
+.It Fl b
+.Em One-byte octal display .
+Display the input offset in octal, followed by sixteen
+space-separated, three column, zero-filled, bytes of input data, in
+octal, per line.
+This is the default output style if no other is selected.
+.It Fl c
+.Em One-byte character display .
+Display the input offset in octal, followed by sixteen
+space-separated, three column, space-filled, characters of input data
+per line.
+Control characters are printed as c style escapes, or as three octal digits,
+if no c escape exists for the character.
+.It Fl D
+.Em Four-byte octal display .
+Display the input offset in octal, followed by four space-separated,
+ten column, space filled, four-byte units of input data, in octal, per line.
+.It Fl d
+.Em Two-byte unsigned decimal display .
+Display the input offset in octal, followed by eight
+space-separated, five column, zero-filled, two-byte units
+of input data, in unsigned decimal, per line.
+.It Fl e
+.Em Eight-byte floating point display .
+Display the input offset in octal, followed by two space-separated,
+twenty-one column, space filled, eight-byte units of input data, in
+floating point, per line.
+.It Fl F
+Same as
+.Fl e .
+.It Fl f
+.Em Four-byte floating point display .
+Display the input offset in octal, followed by four space-separated,
+14 column, space filled, four-byte units of input data, in floating
+point, per line.
+.It Fl H
+.Em Four-byte hex display .
+Display the input offset in octal, followed by four space-separated,
+eight column, zero filled, four-byte units of input data, in hex,
+per line.
+.It Fl h
+.Em Two-byte hex display .
+Display the input offset in octal, followed by eight space-separated,
+four column, zero filled, two-byte units of input data, in hex,
+per line.
+.It Fl I
+.Em Four-byte decimal display .
+Display the input offset in octal, followed by four space-separated,
+eleven column, space filled, four-byte units of input data, in
+decimal, per line.
+.It Fl i
+.Em Two-byte decimal display .
+Display the input offset in octal, followed by eight space-separated,
+six column, space filled, two-byte units of input data, in decimal,
+per line.
+.It Fl j 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 ,
+or
+.Cm m
+to
+.Ar offset
+causes it to be interpreted as a multiple of
+.Li 512 ,
+.Li 1024 ,
+or
+.Li 1048576 ,
+respectively.
+.It Fl L
+Same as
+.Fl I .
+.It Fl l
+Same as
+.Fl I .
+.It Fl N Ar length
+Interpret only
+.Ar length
+bytes of input.
+.It Fl O
+.Em Four-byte octal display .
+Display the input offset in octal, followed by four
+space-separated, eleven column, zero-filled, four-byte units
+of input data, in octal, per line.
+.It Fl o
+.Em Two-byte octal display .
+Display the input offset in octal, followed by eight
+space-separated, six column, zero-filled, two-byte units
+of input data, in octal, per line.
+.It Fl s
+.Em Two-byte signed decimal display .
+Display the input offset in octal, followed by eight
+space-separated, five column, zero-filled, two-byte units
+of input data, in signed decimal, per line.
+.It Fl t Ar type_string
+Specify one or more output types.
+The
+.Em type_string
+option-argument must be a string specifying the types to be used when
+writing the input data.
+The string must consist of the type specification characters:
+.Pp
+.Cm a
+selects US-ASCII output, with control characters replaced with their
+names instead of as c escape sequences.
+See also the
+.Cm _u
+conversion provided by
+.Xr hexdump 1 .
+.Pp
+.Cm c
+selects a standard character based conversion.
+See also the
+.Cm _c
+conversion provided by
+.Xr hexdump 1 .
+.Pp
+.Cm f
+selects the floating point output format.
+This type character can be optionally followed by the characters
+.Cm 4
+or
+.Cm F
+to specify four-byte floating point output, or
+.Cm 8
+or
+.Cm L
+to specify eight-byte floating point output.
+The default output format is eight-byte floats.
+See also the
+.Cm e
+conversion provided by
+.Xr hexdump 1 .
+.Pp
+.Cm d ,
+.Cm o ,
+.Cm u ,
+or
+.Cm x
+select decimal, octal, unsigned decimal, or hex output respectively.
+These types can optionally be followed by
+.Cm C
+to specify
+.Em char Ns -sized
+output,
+.Cm S
+to specify
+.Em short Ns -sized
+output,
+.Cm I
+to specify
+.Em int Ns -sized
+output,
+.Cm L
+to specify
+.Em long Ns -sized
+output,
+.Cm 1
+to specify one-byte output,
+.Cm 2
+to specify two-byte output,
+.Cm 4
+to specify four-byte output, or
+.Cm 8
+to specify eight-byte output.
+The default output format is in four-byte quantities.
+See also the
+.Cm d ,
+.Cm o ,
+.Cm u ,
+and
+.Cm x
+conversions provided by
+.Xr hexdump 1 .
+.\"(a|c|f[FLD]?|[doux][C1S2I4L8]?)*
+.It Fl v
+The
+.Fl v
+option causes
+.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
+Same as
+.Fl H .
+.It Fl x
+Same as
+.Fl h .
+.El
+.Pp
+For each input file,
+.Nm
+sequentially copies the input to standard output, transforming the
+data according to the options given.
+If no options are specified, the default display is equivalent to
+specifying the
+.Fl o
+option.
+.Sh EXIT STATUS
+.Ex -std od
+.Sh SEE ALSO
+.Xr hexdump 1
+.Sh STANDARDS
+The
+.Nm
+utility is compliant with the
+.St -p1003.1-2008
+specification.
+.Pp
+The flags
+.Op Fl bcdosx
+as well as the
+.Ar offset
+specifier are marked by
+.St -p1003.1-2008
+as being an
+X/Open System Interfaces
+option.
+.Pp
+The flags
+.Op Fl aBDeFfHhIiLlOX
+are extensions to that specification.
+.Sh HISTORY
+An
+.Nm
+command appears in
+.At v1 .
+.Pp
+This man page was written in February 2001 by Andrew Brown, shortly
+after he augmented the
+.Nm
+syntax to include things he felt had been missing for a long time.
diff --git a/hexdump/odsyntax.c b/hexdump/odsyntax.c
@@ -0,0 +1,412 @@
+/* $OpenBSD: odsyntax.c,v 1.25 2014/04/19 09:28:20 sobrado Exp $ */
+/* $NetBSD: odsyntax.c,v 1.15 2001/12/07 15:14:29 bjh21 Exp $ */
+
+/*-
+ * 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. 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.
+ */
+
+#include <sys/types.h>
+
+#include <ctype.h>
+#include <err.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "hexdump.h"
+
+#define PADDING " "
+
+int odmode;
+
+static void odoffset(int, char ***);
+static void posixtypes(char *);
+static void odadd(const char *);
+
+
+/*
+ * formats used for -t
+ */
+static const char *fmt[4][4] = {
+ {
+ "16/1 \"%3d \" \"\\n\"",
+ "8/2 \" %05d \" \"\\n\"",
+ "4/4 \" %010d \" \"\\n\"",
+ "2/8 \" %019d \" \"\\n\""
+ }, {
+ "16/1 \"%03o \" \"\\n\"",
+ "8/2 \" %06o \" \"\\n\"",
+ "4/4 \" %011o\" \"\\n\"",
+ "2/8 \" %022o \" \"\\n\""
+ }, {
+ "16/1 \"%03u \" \"\\n\"",
+ "8/2 \" %05u \" \"\\n\"",
+ "4/4 \" %010u \" \"\\n\"",
+ "2/8 \" %020u \" \"\\n\""
+ }, {
+ "16/1 \" %02x \" \"\\n\"",
+ "8/2 \" %04x \" \"\\n\"",
+ "4/4 \" %08x \" \"\\n\"",
+ "2/8 \" %16x \" \"\\n\""
+ }
+};
+
+void
+oldsyntax(int argc, char ***argvp)
+{
+ static char empty[] = "", padding[] = PADDING;
+ int ch;
+ char *p, **argv;
+
+#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 = empty;
+ fshead->nextfs->nextfu->fmt = padding;
+ break;
+ default:
+ errx(1, "%s: invalid address base", optarg);
+ }
+ break;
+ case 'a':
+ odadd("16/1 \"%3_u \" \"\\n\"");
+ break;
+ case 'B':
+ case 'o':
+ odadd("8/2 \" %06o \" \"\\n\"");
+ break;
+ case 'b':
+ odadd("16/1 \"%03o \" \"\\n\"");
+ break;
+ case 'c':
+ odadd("16/1 \"%3_c \" \"\\n\"");
+ break;
+ case 'd':
+ odadd("8/2 \" %05u \" \"\\n\"");
+ break;
+ case 'D':
+ odadd("4/4 \" %010u \" \"\\n\"");
+ break;
+ case 'e':
+ case 'F':
+ odadd("2/8 \" %21.14e \" \"\\n\"");
+ break;
+ case 'f':
+ odadd("4/4 \" %14.7e \" \"\\n\"");
+ break;
+ case 'H':
+ case 'X':
+ odadd("4/4 \" %08x \" \"\\n\"");
+ break;
+ case 'h':
+ case 'x':
+ odadd("8/2 \" %04x \" \"\\n\"");
+ break;
+ case 'I':
+ case 'L':
+ case 'l':
+ odadd("4/4 \" %11d \" \"\\n\"");
+ break;
+ case 'i':
+ odadd("8/2 \" %6d \" \"\\n\"");
+ break;
+ case 'j':
+ if ((skip = strtol(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;
+ }
+ break;
+ case 'N':
+ if ((length = atoi(optarg)) < 0)
+ errx(1, "%s: bad length value", optarg);
+ break;
+ case 'O':
+ odadd("4/4 \" %011o \" \"\\n\"");
+ break;
+ case 's':
+ odadd("8/2 \" %05d \" \"\\n\"");
+ break;
+ case 't':
+ posixtypes(optarg);
+ break;
+ case 'v':
+ vflag = ALL;
+ break;
+ default:
+ oldusage();
+ }
+
+ if (fshead->nextfs->nextfs == NULL)
+ odadd(" 8/2 \"%06o \" \"\\n\"");
+
+ argc -= optind;
+ *argvp += optind;
+
+ if (argc)
+ odoffset(argc, argvp);
+}
+
+/*
+ * Interpret a POSIX-style -t argument.
+ */
+static void
+posixtypes(char *type_string)
+{
+ int x, y, nbytes;
+
+ while (*type_string) {
+ switch (*type_string) {
+ case 'a':
+ type_string++;
+ odadd("16/1 \"%3_u \" \"\\n\"");
+ break;
+ case 'c':
+ type_string++;
+ odadd("16/1 \"%3_c \" \"\\n\"");
+ break;
+ case 'f':
+ type_string++;
+ if (*type_string == 'F' ||
+ *type_string == '4') {
+ type_string++;
+ odadd("4/4 \" %14.7e\" \"\\n\"");
+ } else if (*type_string == 'L' ||
+ *type_string == '8') {
+ type_string++;
+ odadd("2/8 \" %16.14e\" \"\\n\"");
+ } else if (*type_string == 'D')
+ /* long doubles vary in size */
+ oldusage();
+ else
+ odadd("2/8 \" %16.14e\" \"\\n\"");
+ break;
+ case 'd':
+ x = 0;
+ goto extensions;
+ case 'o':
+ x = 1;
+ goto extensions;
+ case 'u':
+ x = 2;
+ goto extensions;
+ case 'x':
+ x = 3;
+ extensions:
+ type_string++;
+ y = 2;
+ if (isupper((unsigned char)*type_string)) {
+ switch(*type_string) {
+ case 'C':
+ nbytes = sizeof(char);
+ break;
+ case 'S':
+ nbytes = sizeof(short);
+ break;
+ case 'I':
+ nbytes = sizeof(int);
+ break;
+ case 'L':
+ nbytes = sizeof(long);
+ break;
+ default:
+ warnx("Bad type-size qualifier '%c'",
+ *type_string);
+ oldusage();
+ }
+ type_string++;
+ } else if (isdigit((unsigned char)*type_string))
+ nbytes = strtol(type_string, &type_string, 10);
+ else
+ nbytes = 4;
+
+ switch (nbytes) {
+ case 1:
+ y = 0;
+ break;
+ case 2:
+ y = 1;
+ break;
+ case 4:
+ y = 2;
+ break;
+ case 8:
+ y = 3;
+ break;
+ default:
+ warnx("%d-byte integer formats are not "
+ "supported", nbytes);
+ oldusage();
+ }
+ odadd(fmt[x][y]);
+ break;
+ default:
+ oldusage();
+ }
+ }
+}
+
+void
+oldusage(void)
+{
+ extern char *__progname;
+ fprintf(stderr, "usage: %s [-aBbcDdeFfHhIiLlOosvXx] [-A base] "
+ "[-j offset] [-N length]\n"
+ "\t[-t type_string] [[+]offset[.][Bb]] [file ...]\n", __progname);
+ exit(1);
+}
+
+static void
+odoffset(int argc, char ***argvp)
+{
+ char *num, *p;
+ int base;
+ char *end;
+
+ /*
+ * 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 = argc == 1 ? (*argvp)[0] : (*argvp)[1];
+ if (!p)
+ return;
+
+ if (*p != '+' && (argc < 2 ||
+ (!isdigit((unsigned char)p[0]) &&
+ (p[0] != 'x' || !isxdigit((unsigned char)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((unsigned char)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((unsigned char)*p); ++p);
+ else
+ for (num = p; isdigit((unsigned char)*p); ++p);
+
+ /* check for no number */
+ if (num == p)
+ return;
+
+ /* if terminates with a '.', base is decimal */
+ if (*p == '.') {
+ if (base)
+ return;
+ base = 10;
+ }
+
+ skip = strtol(num, &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 (*p) {
+ if (*p == 'B') {
+ skip *= 1024;
+ ++p;
+ } else if (*p == 'b') {
+ skip *= 512;
+ ++p;
+ }
+ }
+ if (*p) {
+ 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
+odadd(const char *fmt)
+{
+ static int needpad;
+
+ if (needpad)
+ add("\""PADDING"\"");
+ add(fmt);
+ needpad = 1;
+}
diff --git a/hexdump/parse.c b/hexdump/parse.c
@@ -0,0 +1,527 @@
+/* $OpenBSD: parse.c,v 1.17 2009/10/27 23:59:39 deraadt Exp $ */
+/* $NetBSD: parse.c,v 1.12 2001/12/07 13:37:39 bjh21 Exp $ */
+
+/*
+ * 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. 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.
+ */
+
+#include <sys/types.h>
+#include <sys/file.h>
+
+#include <ctype.h>
+#include <err.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "hexdump.h"
+#include "util.h"
+
+FU *endfu; /* format at end-of-data */
+
+void
+addfile(char *name)
+{
+ FILE *fp;
+ size_t len;
+ char *buf, *lbuf, *p;
+
+ if ((fp = fopen(name, "r")) == NULL)
+ err(1, "fopen %s", name);
+
+ lbuf = NULL;
+ while ((buf = fgetln(fp, &len))) {
+ if (buf[len - 1] == '\n')
+ buf[len - 1] = '\0';
+ else {
+ /* EOF without EOL, copy and add the NUL */
+ if ((lbuf = malloc(len + 1)) == NULL)
+ err(1, NULL);
+ memcpy(lbuf, buf, len);
+ lbuf[len] = '\0';
+ buf = lbuf;
+ }
+ for (p = buf; isspace((unsigned char)*p); ++p);
+ if (!*p || *p == '#')
+ continue;
+ add(p);
+ }
+ free(lbuf);
+ (void)fclose(fp);
+}
+
+void
+add(const char *fmt)
+{
+ const char *p;
+ static FS **nextfs;
+ FS *tfs;
+ FU *tfu, **nextfu;
+ const char *savep;
+
+ /* start new linked list of format units */
+ tfs = emalloc(sizeof(FS));
+ 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 = fmt;;) {
+ /* skip leading white space */
+ for (; isspace((unsigned char)*p); ++p);
+ if (!*p)
+ break;
+
+ /* allocate a new format unit and link it in */
+ tfu = emalloc(sizeof(FU));
+ *nextfu = tfu;
+ nextfu = &tfu->nextfu;
+ tfu->reps = 1;
+
+ /* if leading digit, repetition count */
+ if (isdigit((unsigned char)*p)) {
+ for (savep = p; isdigit((unsigned char)*p); ++p);
+ if (!isspace((unsigned char)*p) && *p != '/')
+ badfmt(fmt);
+ /* may overwrite either white space or slash */
+ tfu->reps = atoi(savep);
+ tfu->flags = F_SETREP;
+ /* skip trailing white space */
+ for (++p; isspace((unsigned char)*p); ++p);
+ }
+
+ /* skip slash and trailing white space */
+ if (*p == '/')
+ while (isspace((unsigned char)*++p));
+
+ /* byte count */
+ if (isdigit((unsigned char)*p)) {
+ for (savep = p; isdigit((unsigned char)*p); ++p);
+ if (!isspace((unsigned char)*p))
+ badfmt(fmt);
+ tfu->bcnt = atoi(savep);
+ /* skip trailing white space */
+ for (++p; isspace((unsigned char)*p); ++p);
+ }
+
+ /* format */
+ if (*p != '"')
+ badfmt(fmt);
+ for (savep = ++p; *p != '"';)
+ if (*p++ == 0)
+ badfmt(fmt);
+ if (!(tfu->fmt = malloc(p - savep + 1)))
+ nomem();
+ (void) strncpy(tfu->fmt, 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;
+ 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 = fu->fmt; *fmt; ++fmt) {
+ if (*fmt != '%')
+ continue;
+ /*
+ * skip any special chars -- save precision in
+ * case it's a %s format.
+ */
+ while (*++fmt && strchr(spec + 1, *fmt));
+ if (*fmt == '.' && isdigit((unsigned char)*++fmt)) {
+ prec = atoi(fmt);
+ while (isdigit((unsigned char)*++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;
+ FU *fu;
+ char *p1, *p2;
+ char savech, *fmtp, cs[3];
+ int nconv, prec;
+ size_t len;
+
+ nextpr = NULL;
+ 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 = fu->fmt; *fmtp; nextpr = &pr->nextpr) {
+ pr = emalloc(sizeof(PR));
+ 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 = 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; *p1 && strchr(spec, *p1); ++p1);
+ } else {
+ /* Skip any special chars, field width. */
+ while (*++p1 && strchr(spec + 1, *p1));
+ if (*p1 == '.' &&
+ isdigit((unsigned char)*++p1)) {
+ sokay = USEPREC;
+ prec = atoi(p1);
+ while (isdigit((unsigned char)*++p1))
+ continue;
+ } else
+ sokay = NOTOKAY;
+ }
+
+ p2 = *p1 ? p1 + 1 : p1; /* 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(p1);
+ }
+ break;
+ case 'd': case 'i':
+ case 'o': case 'u': case 'x': case 'X':
+ if (cs[0] == 'd' || cs[0] == 'i')
+ pr->flags = F_INT;
+ else
+ pr->flags = F_UINT;
+
+ 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;
+ case 8:
+ pr->bcnt = 8;
+ break;
+ default:
+ p1[1] = '\0';
+ badcnt(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:
+ p1[1] = '\0';
+ badcnt(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:
+ if (p1[2])
+ p1[3] = '\0';
+ badconv(p1);
+ }
+ break;
+ case 'c':
+ case 'p':
+ case 'u':
+ if (p1[1] == 'c') {
+ pr->flags = F_C;
+ /* cs[0] = 'c'; set in conv_c */
+ } else if (p1[1] == 'p') {
+ pr->flags = F_P;
+ cs[0] = 'c';
+ } else {
+ pr->flags = F_U;
+ /* cs[0] = 'c'; set in conv_u */
+ }
+
+ switch(fu->bcnt) {
+ case 0: case 1:
+ pr->bcnt = 1;
+ break;
+ default:
+ p1[2] = '\0';
+ badcnt(p1);
+ }
+ break;
+ default:
+ if (p1[1])
+ p1[2] = '\0';
+ badconv(p1);
+ }
+ break;
+ default:
+ if (cs[0])
+ p1[1] = '\0';
+ badconv(p1);
+ }
+
+ /*
+ * Copy to PR format string, set conversion character
+ * pointer, update original.
+ */
+ savech = *p2;
+ p1[0] = '\0';
+ len = strlen(fmtp) + strlen(cs) + 1;
+ pr->fmt = emalloc(len);
+ snprintf(pr->fmt, len, "%s%s", fmtp, 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) {
+ if (!fu->nextpr)
+ break;
+ for (pr = fu->nextpr;; pr = pr->nextpr)
+ if (!pr->nextpr)
+ break;
+ for (p1 = pr->fmt, p2 = NULL; *p1; ++p1)
+ p2 = isspace((unsigned char)*p1) ? p1 : NULL;
+ if (p2)
+ pr->nospace = 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 '\0':
+ *p2++ = '\\';
+ *p2 = '\0';
+ return; /* incomplete escape sequence */
+ 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;
+ }
+ } else
+ *p2 = *p1;
+ }
+}
+
+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);
+}
diff --git a/hexdump/util.h b/hexdump/util.h
@@ -0,0 +1,4 @@
+#include <stdio.h>
+#include <stddef.h>
+
+char *fgetln(FILE *, size_t *);
