/* strings -- print the strings of printable characters in files
- Copyright 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001
- Free Software Foundation, Inc.
+ Copyright (C) 1993-2015 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
+ the Free Software Foundation; either version 3, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
- Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
- 02111-1307, USA. */
+ Foundation, Inc., 51 Franklin Street - Fifth Floor, Boston, MA
+ 02110-1301, USA. */
\f
/* Usage: strings [options] file...
Options:
--all
-a
- - Do not scan only the initialized data section of object files.
+ - Scan each file in its entirety.
+
+ --data
+ -d Scan only the initialized data section(s) of object files.
--print-file-name
-f Print the name of the file before each string.
-t {o,x,d} Print the offset within the file before each string,
in octal/hex/decimal.
+ --include-all-whitespace
+ -w By default tab and space are the only whitepace included in graphic
+ char sequences. This option considers all of isspace() valid.
+
-o Like -to. (Some other implementations have -o like -to,
others like -td. We chose one arbitrarily.)
- --encoding={s,b,l,B,L}
- -e {s,b,l,B,L}
- Select character encoding: single-byte, bigendian 16-bit,
- littleendian 16-bit, bigendian 32-bit, littleendian 32-bit
+ --encoding={s,S,b,l,B,L}
+ -e {s,S,b,l,B,L}
+ Select character encoding: 7-bit-character, 8-bit-character,
+ bigendian 16-bit, littleendian 16-bit, bigendian 32-bit,
+ littleendian 32-bit.
--target=BFDNAME
+ -T {bfdname}
Specify a non-default object file format.
+ --output-separator=sep_string
+ -s sep_string String used to separate parsed strings in output.
+ Default is newline.
+
--help
-h Print the usage message on the standard output.
--version
+ -V
-v Print the program version number.
Written by Richard Stallman <rms@gnu.ai.mit.edu>
and David MacKenzie <djm@gnu.ai.mit.edu>. */
+#include "sysdep.h"
#include "bfd.h"
-#include <stdio.h>
-#include <getopt.h>
-#include <errno.h>
-#include "bucomm.h"
+#include "getopt.h"
#include "libiberty.h"
#include "safe-ctype.h"
+#include "bucomm.h"
-/* Some platforms need to put stdin into binary mode, to read
- binary files. */
-#ifdef HAVE_SETMODE
-#ifndef O_BINARY
-#ifdef _O_BINARY
-#define O_BINARY _O_BINARY
-#define setmode _setmode
-#else
-#define O_BINARY 0
-#endif
-#endif
-#if O_BINARY
-#include <io.h>
-#define SET_BINARY(f) do { if (!isatty(f)) setmode(f,O_BINARY); } while (0)
-#endif
-#endif
-
-#define isgraphic(c) (ISPRINT (c) || (c) == '\t')
+#define STRING_ISGRAPHIC(c) \
+ ( (c) >= 0 \
+ && (c) <= 255 \
+ && ((c) == '\t' || ISPRINT (c) || (encoding == 'S' && (c) > 127) \
+ || (include_all_whitespace == TRUE && ISSPACE (c))) \
+ )
#ifndef errno
extern int errno;
/* Minimum length of sequence of graphic chars to trigger output. */
static int string_min;
-/* true means print address within file for each string. */
-static boolean print_addresses;
+/* Whether or not we include all whitespace as a graphic char. */
+static bfd_boolean include_all_whitespace;
+
+/* TRUE means print address within file for each string. */
+static bfd_boolean print_addresses;
-/* true means print filename for each string. */
-static boolean print_filenames;
+/* TRUE means print filename for each string. */
+static bfd_boolean print_filenames;
-/* true means for object files scan only the data section. */
-static boolean datasection_only;
+/* TRUE means for object files scan only the data section. */
+static bfd_boolean datasection_only;
-/* true if we found an initialized data section in the current file. */
-static boolean got_a_section;
+/* TRUE if we found an initialized data section in the current file. */
+static bfd_boolean got_a_section;
/* The BFD object file format. */
static char *target;
static char encoding;
static int encoding_bytes;
+/* Output string used to separate parsed strings */
+static char *output_separator;
+
static struct option long_options[] =
{
{"all", no_argument, NULL, 'a'},
+ {"data", no_argument, NULL, 'd'},
{"print-file-name", no_argument, NULL, 'f'},
{"bytes", required_argument, NULL, 'n'},
{"radix", required_argument, NULL, 't'},
+ {"include-all-whitespace", required_argument, NULL, 'w'},
{"encoding", required_argument, NULL, 'e'},
{"target", required_argument, NULL, 'T'},
+ {"output-separator", required_argument, NULL, 's'},
{"help", no_argument, NULL, 'h'},
{"version", no_argument, NULL, 'v'},
{NULL, 0, NULL, 0}
};
-static void strings_a_section PARAMS ((bfd *, asection *, PTR));
-static boolean strings_object_file PARAMS ((const char *));
-static boolean strings_file PARAMS ((char *file));
-static int integer_arg PARAMS ((char *s));
-static void print_strings PARAMS ((const char *filename, FILE *stream,
- file_ptr address, int stop_point,
- int magiccount, char *magic));
-static void usage PARAMS ((FILE *stream, int status));
+/* Records the size of a named file so that we
+ do not repeatedly run bfd_stat() on it. */
+
+typedef struct
+{
+ const char * filename;
+ bfd_size_type filesize;
+} filename_and_size_t;
+
+static void strings_a_section (bfd *, asection *, void *);
+static bfd_boolean strings_object_file (const char *);
+static bfd_boolean strings_file (char *);
+static void print_strings (const char *, FILE *, file_ptr, int, int, char *);
+static void usage (FILE *, int);
+static long get_char (FILE *, file_ptr *, int *, char **);
\f
+int main (int, char **);
+
int
-main (argc, argv)
- int argc;
- char **argv;
+main (int argc, char **argv)
{
int optc;
int exit_status = 0;
- boolean files_given = false;
+ bfd_boolean files_given = FALSE;
+ char *s;
+ int numeric_opt = 0;
#if defined (HAVE_SETLOCALE)
setlocale (LC_ALL, "");
program_name = argv[0];
xmalloc_set_program_name (program_name);
- string_min = -1;
- print_addresses = false;
- print_filenames = false;
- datasection_only = true;
+ bfd_set_error_program_name (program_name);
+
+ expandargv (&argc, &argv);
+
+ string_min = 4;
+ include_all_whitespace = FALSE;
+ print_addresses = FALSE;
+ print_filenames = FALSE;
+ if (DEFAULT_STRINGS_ALL)
+ datasection_only = FALSE;
+ else
+ datasection_only = TRUE;
target = NULL;
encoding = 's';
+ output_separator = NULL;
- while ((optc = getopt_long (argc, argv, "afn:ot:e:v0123456789",
+ while ((optc = getopt_long (argc, argv, "adfhHn:wot:e:T:s:Vv0123456789",
long_options, (int *) 0)) != EOF)
{
switch (optc)
{
case 'a':
- datasection_only = false;
+ datasection_only = FALSE;
+ break;
+
+ case 'd':
+ datasection_only = TRUE;
break;
case 'f':
- print_filenames = true;
+ print_filenames = TRUE;
break;
+ case 'H':
case 'h':
usage (stdout, 0);
case 'n':
- string_min = integer_arg (optarg);
- if (string_min < 1)
- {
- fatal (_("invalid number %s"), optarg);
- }
+ string_min = (int) strtoul (optarg, &s, 0);
+ if (s != NULL && *s != 0)
+ fatal (_("invalid integer argument %s"), optarg);
+ break;
+
+ case 'w':
+ include_all_whitespace = TRUE;
break;
case 'o':
- print_addresses = true;
+ print_addresses = TRUE;
address_radix = 8;
break;
case 't':
- print_addresses = true;
+ print_addresses = TRUE;
if (optarg[1] != '\0')
usage (stderr, 1);
switch (optarg[0])
encoding = optarg[0];
break;
+ case 's':
+ output_separator = optarg;
+ break;
+
+ case 'V':
case 'v':
print_version ("strings");
break;
usage (stderr, 1);
default:
- if (string_min < 0)
- string_min = optc - '0';
- else
- string_min = string_min * 10 + optc - '0';
+ numeric_opt = optind;
break;
}
}
- if (string_min < 0)
- string_min = 4;
+ if (numeric_opt != 0)
+ {
+ string_min = (int) strtoul (argv[numeric_opt - 1] + 1, &s, 0);
+ if (s != NULL && *s != 0)
+ fatal (_("invalid integer argument %s"), argv[numeric_opt - 1] + 1);
+ }
+ if (string_min < 1)
+ fatal (_("invalid minimum string length %d"), string_min);
switch (encoding)
{
+ case 'S':
case 's':
encoding_bytes = 1;
break;
if (optind >= argc)
{
- datasection_only = false;
-#ifdef SET_BINARY
+ datasection_only = FALSE;
SET_BINARY (fileno (stdin));
-#endif
print_strings ("{standard input}", stdin, 0, 0, 0, (char *) NULL);
- files_given = true;
+ files_given = TRUE;
}
else
{
for (; optind < argc; ++optind)
{
if (strcmp (argv[optind], "-") == 0)
- datasection_only = false;
+ datasection_only = FALSE;
else
{
- files_given = true;
- exit_status |= (strings_file (argv[optind]) == false);
+ files_given = TRUE;
+ exit_status |= strings_file (argv[optind]) == FALSE;
}
}
}
- if (files_given == false)
+ if (!files_given)
usage (stderr, 1);
return (exit_status);
}
\f
-/* Scan section SECT of the file ABFD, whose printable name is FILE.
- If it contains initialized data,
- set `got_a_section' and print the strings in it. */
+/* Scan section SECT of the file ABFD, whose printable name is in
+ ARG->filename and whose size might be in ARG->filesize. If it
+ contains initialized data set `got_a_section' and print the
+ strings in it.
+
+ FIXME: We ought to be able to return error codes/messages for
+ certain conditions. */
static void
-strings_a_section (abfd, sect, filearg)
- bfd *abfd;
- asection *sect;
- PTR filearg;
+strings_a_section (bfd *abfd, asection *sect, void *arg)
{
- const char *file = (const char *) filearg;
+ filename_and_size_t * filename_and_sizep;
+ bfd_size_type *filesizep;
+ bfd_size_type sectsize;
+ void *mem;
+
+ if ((sect->flags & DATA_FLAGS) != DATA_FLAGS)
+ return;
+
+ sectsize = bfd_get_section_size (sect);
+
+ if (sectsize <= 0)
+ return;
- if ((sect->flags & DATA_FLAGS) == DATA_FLAGS)
+ /* Get the size of the file. This might have been cached for us. */
+ filename_and_sizep = (filename_and_size_t *) arg;
+ filesizep = & filename_and_sizep->filesize;
+
+ if (*filesizep == 0)
{
- bfd_size_type sz = bfd_get_section_size_before_reloc (sect);
- PTR mem = xmalloc (sz);
- if (bfd_get_section_contents (abfd, sect, mem, (file_ptr) 0, sz))
- {
- got_a_section = true;
- print_strings (file, (FILE *) NULL, sect->filepos, 0, sz, mem);
- }
- free (mem);
+ struct stat st;
+
+ if (bfd_stat (abfd, &st))
+ return;
+
+ /* Cache the result so that we do not repeatedly stat this file. */
+ *filesizep = st.st_size;
+ }
+
+ /* Compare the size of the section against the size of the file.
+ If the section is bigger then the file must be corrupt and
+ we should not try dumping it. */
+ if (sectsize >= *filesizep)
+ return;
+
+ mem = xmalloc (sectsize);
+
+ if (bfd_get_section_contents (abfd, sect, mem, (file_ptr) 0, sectsize))
+ {
+ got_a_section = TRUE;
+
+ print_strings (filename_and_sizep->filename, NULL, sect->filepos,
+ 0, sectsize, (char *) mem);
}
+
+ free (mem);
}
/* Scan all of the sections in FILE, and print the strings
in the initialized data section(s).
- Return true if successful,
- false if not (such as if FILE is not an object file). */
+ Return TRUE if successful,
+ FALSE if not (such as if FILE is not an object file). */
-static boolean
-strings_object_file (file)
- const char *file;
+static bfd_boolean
+strings_object_file (const char *file)
{
- bfd *abfd = bfd_openr (file, target);
+ filename_and_size_t filename_and_size;
+ bfd *abfd;
+
+ abfd = bfd_openr (file, target);
if (abfd == NULL)
- {
- /* Treat the file as a non-object file. */
- return false;
- }
+ /* Treat the file as a non-object file. */
+ return FALSE;
/* This call is mainly for its side effect of reading in the sections.
We follow the traditional behavior of `strings' in that we don't
complain if we don't recognize a file to be an object file. */
- if (bfd_check_format (abfd, bfd_object) == false)
+ if (!bfd_check_format (abfd, bfd_object))
{
bfd_close (abfd);
- return false;
+ return FALSE;
}
- got_a_section = false;
- bfd_map_over_sections (abfd, strings_a_section, (PTR) file);
+ got_a_section = FALSE;
+ filename_and_size.filename = file;
+ filename_and_size.filesize = 0;
+ bfd_map_over_sections (abfd, strings_a_section, & filename_and_size);
if (!bfd_close (abfd))
{
bfd_nonfatal (file);
- return false;
+ return FALSE;
}
return got_a_section;
}
-/* Print the strings in FILE. Return true if ok, false if an error occurs. */
+/* Print the strings in FILE. Return TRUE if ok, FALSE if an error occurs. */
-static boolean
-strings_file (file)
- char *file;
+static bfd_boolean
+strings_file (char *file)
{
+ struct stat st;
+
+ /* get_file_size does not support non-S_ISREG files. */
+
+ if (stat (file, &st) < 0)
+ {
+ if (errno == ENOENT)
+ non_fatal (_("'%s': No such file"), file);
+ else
+ non_fatal (_("Warning: could not locate '%s'. reason: %s"),
+ file, strerror (errno));
+ return FALSE;
+ }
+
/* If we weren't told to scan the whole file,
try to open it as an object file and only look at
initialized data sections. If that fails, fall back to the
{
FILE *stream;
- stream = fopen (file, "rb");
- /* Not all systems permit "rb", so try "r" if it failed. */
- if (stream == NULL)
- stream = fopen (file, "r");
+ stream = fopen (file, FOPEN_RB);
if (stream == NULL)
{
fprintf (stderr, "%s: ", program_name);
perror (file);
- return false;
+ return FALSE;
}
print_strings (file, stream, (file_ptr) 0, 0, 0, (char *) 0);
{
fprintf (stderr, "%s: ", program_name);
perror (file);
- return false;
+ return FALSE;
}
}
- return true;
+ return TRUE;
}
\f
/* Read the next character, return EOF if none available.
MAGICCOUNT is how many characters are in it. */
static long
-get_char (stream, address, magiccount, magic)
- FILE *stream;
- file_ptr *address;
- int *magiccount;
- char **magic;
+get_char (FILE *stream, file_ptr *address, int *magiccount, char **magic)
{
int c, i;
- long r;
- unsigned char buf[4];
+ long r = 0;
for (i = 0; i < encoding_bytes; i++)
{
{
if (stream == NULL)
return EOF;
+
+ /* Only use getc_unlocked if we found a declaration for it.
+ Otherwise, libc is not thread safe by default, and we
+ should not use it. */
+
+#if defined(HAVE_GETC_UNLOCKED) && HAVE_DECL_GETC_UNLOCKED
+ c = getc_unlocked (stream);
+#else
c = getc (stream);
+#endif
if (c == EOF)
return EOF;
}
(*address)++;
- buf[i] = c;
+ r = (r << 8) | (c & 0xff);
}
switch (encoding)
{
- case 's':
- r = buf[0];
- break;
- case 'b':
- r = (buf[0] << 8) | buf[1];
+ default:
break;
case 'l':
- r = buf[0] | (buf[1] << 8);
- break;
- case 'B':
- r = ((long) buf[0] << 24) | ((long) buf[1] << 16) |
- ((long) buf[2] << 8) | buf[3];
+ r = ((r & 0xff) << 8) | ((r & 0xff00) >> 8);
break;
case 'L':
- r = buf[0] | ((long) buf[1] << 8) | ((long) buf[2] << 16) |
- ((long) buf[3] << 24);
+ r = (((r & 0xff) << 24) | ((r & 0xff00) << 8)
+ | ((r & 0xff0000) >> 8) | ((r & 0xff000000) >> 24));
break;
}
- if (r == EOF)
- return 0;
-
return r;
}
\f
Those characters come at address ADDRESS and the data in STREAM follow. */
static void
-print_strings (filename, stream, address, stop_point, magiccount, magic)
- const char *filename;
- FILE *stream;
- file_ptr address;
- int stop_point;
- int magiccount;
- char *magic;
+print_strings (const char *filename, FILE *stream, file_ptr address,
+ int stop_point, int magiccount, char *magic)
{
char *buf = (char *) xmalloc (sizeof (char) * (string_min + 1));
{
c = get_char (stream, &address, &magiccount, &magic);
if (c == EOF)
- return;
- if (c > 255 || c < 0 || !isgraphic (c))
+ {
+ free (buf);
+ return;
+ }
+ if (! STRING_ISGRAPHIC (c))
/* Found a non-graphic. Try again starting with next char. */
goto tryline;
buf[i] = c;
}
/* We found a run of `string_min' graphic characters. Print up
- to the next non-graphic character. */
+ to the next non-graphic character. */
if (print_filenames)
printf ("%s: ", filename);
switch (address_radix)
{
case 8:
- printf ("%7lo ", (unsigned long) start);
+#ifdef HAVE_LONG_LONG
+ if (sizeof (start) > sizeof (long))
+ {
+# ifndef __MSVCRT__
+ printf ("%7llo ", (unsigned long long) start);
+# else
+ printf ("%7I64o ", (unsigned long long) start);
+# endif
+ }
+ else
+#elif !BFD_HOST_64BIT_LONG
+ if (start != (unsigned long) start)
+ printf ("++%7lo ", (unsigned long) start);
+ else
+#endif
+ printf ("%7lo ", (unsigned long) start);
break;
case 10:
- printf ("%7ld ", (long) start);
+#ifdef HAVE_LONG_LONG
+ if (sizeof (start) > sizeof (long))
+ {
+# ifndef __MSVCRT__
+ printf ("%7lld ", (unsigned long long) start);
+# else
+ printf ("%7I64d ", (unsigned long long) start);
+# endif
+ }
+ else
+#elif !BFD_HOST_64BIT_LONG
+ if (start != (unsigned long) start)
+ printf ("++%7ld ", (unsigned long) start);
+ else
+#endif
+ printf ("%7ld ", (long) start);
break;
case 16:
- printf ("%7lx ", (unsigned long) start);
+#ifdef HAVE_LONG_LONG
+ if (sizeof (start) > sizeof (long))
+ {
+# ifndef __MSVCRT__
+ printf ("%7llx ", (unsigned long long) start);
+# else
+ printf ("%7I64x ", (unsigned long long) start);
+# endif
+ }
+ else
+#elif !BFD_HOST_64BIT_LONG
+ if (start != (unsigned long) start)
+ printf ("%lx%8.8lx ", (unsigned long) (start >> 32),
+ (unsigned long) (start & 0xffffffff));
+ else
+#endif
+ printf ("%7lx ", (unsigned long) start);
break;
}
c = get_char (stream, &address, &magiccount, &magic);
if (c == EOF)
break;
- if (c > 255 || c < 0 || !isgraphic (c))
+ if (! STRING_ISGRAPHIC (c))
break;
putchar (c);
}
- putchar ('\n');
+ if (output_separator)
+ fputs (output_separator, stdout);
+ else
+ putchar ('\n');
}
+ free (buf);
}
\f
-/* Parse string S as an integer, using decimal radix by default,
- but allowing octal and hex numbers as in C. */
-
-static int
-integer_arg (s)
- char *s;
+static void
+usage (FILE *stream, int status)
{
- int value;
- int radix = 10;
- char *p = s;
- int c;
-
- if (*p != '0')
- radix = 10;
- else if (*++p == 'x')
- {
- radix = 16;
- p++;
- }
- else
- radix = 8;
-
- value = 0;
- while (((c = *p++) >= '0' && c <= '9')
- || (radix == 16 && (c & ~40) >= 'A' && (c & ~40) <= 'Z'))
- {
- value *= radix;
- if (c >= '0' && c <= '9')
- value += c - '0';
- else
- value += (c & ~40) - 'A';
- }
-
- if (c == 'b')
- value *= 512;
- else if (c == 'B')
- value *= 1024;
+ fprintf (stream, _("Usage: %s [option(s)] [file(s)]\n"), program_name);
+ fprintf (stream, _(" Display printable strings in [file(s)] (stdin by default)\n"));
+ fprintf (stream, _(" The options are:\n"));
+
+ if (DEFAULT_STRINGS_ALL)
+ fprintf (stream, _("\
+ -a - --all Scan the entire file, not just the data section [default]\n\
+ -d --data Only scan the data sections in the file\n"));
else
- p--;
+ fprintf (stream, _("\
+ -a - --all Scan the entire file, not just the data section\n\
+ -d --data Only scan the data sections in the file [default]\n"));
- if (*p)
- {
- fatal (_("invalid integer argument %s"), s);
- }
- return value;
-}
-
-static void
-usage (stream, status)
- FILE *stream;
- int status;
-{
fprintf (stream, _("\
-Usage: %s [-afov] [-n min-len] [-min-len] [-t {o,x,d}] [-e {s,b,l,B,L}]\n\
- [-] [--all] [--print-file-name] [--bytes=min-len] [--radix={o,x,d}]\n\
- [--target=bfdname] [--encoding {s,b,l,B,L}] [--help] [--version] file...\n"),
- program_name);
+ -f --print-file-name Print the name of the file before each string\n\
+ -n --bytes=[number] Locate & print any NUL-terminated sequence of at\n\
+ -<number> least [number] characters (default 4).\n\
+ -t --radix={o,d,x} Print the location of the string in base 8, 10 or 16\n\
+ -w --include-all-whitespace Include all whitespace as valid string characters\n\
+ -o An alias for --radix=o\n\
+ -T --target=<BFDNAME> Specify the binary file format\n\
+ -e --encoding={s,S,b,l,B,L} Select character size and endianness:\n\
+ s = 7-bit, S = 8-bit, {b,l} = 16-bit, {B,L} = 32-bit\n\
+ -s --output-separator=<string> String used to separate strings in output.\n\
+ @<file> Read options from <file>\n\
+ -h --help Display this information\n\
+ -v -V --version Print the program's version number\n"));
list_supported_targets (program_name, stream);
- if (status == 0)
+ if (REPORT_BUGS_TO[0] && status == 0)
fprintf (stream, _("Report bugs to %s\n"), REPORT_BUGS_TO);
exit (status);
}