/* strings -- print the strings of printable characters in files
- Copyright 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001,
- 2002, 2003, 2004, 2005, 2006, 2007, 2008 Free Software Foundation, Inc.
+ Copyright (C) 1993-2021 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
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.)
-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>
#include "getopt.h"
#include "libiberty.h"
#include "safe-ctype.h"
-#include <sys/stat.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 STRING_ISGRAPHIC(c) \
( (c) >= 0 \
&& (c) <= 255 \
- && ((c) == '\t' || ISPRINT (c) || (encoding == 'S' && (c) > 127)))
+ && ((c) == '\t' || ISPRINT (c) || (encoding == 'S' && (c) > 127) \
+ || (include_all_whitespace && ISSPACE (c))) \
+ )
#ifndef errno
extern int errno;
/* The BFD section flags that identify an initialized data section. */
#define DATA_FLAGS (SEC_ALLOC | SEC_LOAD | SEC_HAS_CONTENTS)
-#ifdef HAVE_FOPEN64
-typedef off64_t file_off;
-#define file_open(s,m) fopen64(s, m)
-#else
-typedef off_t file_off;
-#define file_open(s,m) fopen(s, m)
-#endif
-#ifdef HAVE_STAT64
-typedef struct stat64 statbuf;
-#define file_stat(f,s) stat64(f, s)
-#else
-typedef struct stat statbuf;
-#define file_stat(f,s) stat(f, s)
-#endif
-
/* Radix for printing addresses (must be 8, 10 or 16). */
static int address_radix;
/* Minimum length of sequence of graphic chars to trigger output. */
static int string_min;
+/* Whether or not we include all whitespace as a graphic char. */
+static bool include_all_whitespace;
+
/* TRUE means print address within file for each string. */
-static bfd_boolean print_addresses;
+static bool print_addresses;
/* TRUE means print filename for each string. */
-static bfd_boolean print_filenames;
+static bool print_filenames;
/* 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 bfd_boolean got_a_section;
+static bool datasection_only;
/* 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", no_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}
};
-/* 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 *file);
-static int integer_arg (char *s);
-static void print_strings (const char *, FILE *, file_off, int, int, char *);
-static void usage (FILE *, int);
-static long get_char (FILE *, file_off *, int *, char **);
+static bool strings_file (char *);
+static void print_strings (const char *, FILE *, file_ptr, int, int, char *);
+static void usage (FILE *, int) ATTRIBUTE_NORETURN;
\f
int main (int, char **);
{
int optc;
int exit_status = 0;
- bfd_boolean files_given = FALSE;
+ bool files_given = false;
+ char *s;
+ int numeric_opt = 0;
-#if defined (HAVE_SETLOCALE)
setlocale (LC_ALL, "");
-#endif
bindtextdomain (PACKAGE, LOCALEDIR);
textdomain (PACKAGE);
program_name = argv[0];
xmalloc_set_program_name (program_name);
+ bfd_set_error_program_name (program_name);
expandargv (&argc, &argv);
- string_min = -1;
- print_addresses = FALSE;
- print_filenames = FALSE;
- datasection_only = TRUE;
+ 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, "afhHn:ot:e:T:Vv0123456789",
+ 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':
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");
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)
{
usage (stderr, 1);
}
- bfd_init ();
+ if (bfd_init () != BFD_INIT_MAGIC)
+ fatal (_("fatal error: libbfd ABI mismatch"));
set_default_bfd_target ();
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]);
}
}
}
return (exit_status);
}
\f
-/* 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. */
+/* Scan section SECT of the file ABFD, whose printable name is
+ FILENAME. If it contains initialized data set GOT_A_SECTION and
+ print the strings in it. */
static void
-strings_a_section (bfd *abfd, asection *sect, void *arg)
+strings_a_section (bfd *abfd, asection *sect, const char *filename,
+ bool *got_a_section)
{
- 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;
+ bfd_byte *mem;
- sectsize = bfd_get_section_size (sect);
-
- if (sectsize <= 0)
+ if ((sect->flags & DATA_FLAGS) != DATA_FLAGS)
return;
- /* 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)
- {
- 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)
+ sectsize = bfd_section_size (sect);
+ if (sectsize == 0)
return;
- mem = xmalloc (sectsize);
-
- if (bfd_get_section_contents (abfd, sect, mem, (file_ptr) 0, sectsize))
+ if (!bfd_malloc_and_get_section (abfd, sect, &mem))
{
- got_a_section = TRUE;
-
- print_strings (filename_and_sizep->filename, NULL, sect->filepos,
- 0, sectsize, mem);
+ non_fatal (_("%s: Reading section %s failed: %s"),
+ filename, sect->name, bfd_errmsg (bfd_get_error ()));
+ return;
}
+ *got_a_section = true;
+ print_strings (filename, NULL, sect->filepos, 0, sectsize, (char *) mem);
free (mem);
}
Return TRUE if successful,
FALSE if not (such as if FILE is not an object file). */
-static bfd_boolean
+static bool
strings_object_file (const char *file)
{
- filename_and_size_t filename_and_size;
bfd *abfd;
+ asection *s;
+ bool got_a_section;
abfd = bfd_openr (file, target);
if (abfd == NULL)
/* Treat the file as a non-object file. */
- return FALSE;
+ 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
if (!bfd_check_format (abfd, bfd_object))
{
bfd_close (abfd);
- return FALSE;
+ return false;
}
- 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);
+ got_a_section = false;
+ for (s = abfd->sections; s != NULL; s = s->next)
+ strings_a_section (abfd, s, file, &got_a_section);
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. */
-static bfd_boolean
+static bool
strings_file (char *file)
{
- statbuf st;
+ struct stat st;
- if (file_stat (file, &st) < 0)
+ /* 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;
+ return false;
+ }
+ else if (S_ISDIR (st.st_mode))
+ {
+ non_fatal (_("Warning: '%s' is a directory"), file);
+ return false;
}
/* If we weren't told to scan the whole file,
{
FILE *stream;
- stream = file_open (file, FOPEN_RB);
+ stream = fopen (file, FOPEN_RB);
if (stream == NULL)
{
fprintf (stderr, "%s: ", program_name);
perror (file);
- return FALSE;
+ return false;
}
- print_strings (file, stream, (file_off) 0, 0, 0, (char *) 0);
+ print_strings (file, stream, (file_ptr) 0, 0, 0, (char *) 0);
if (fclose (stream) == EOF)
{
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 (FILE *stream, file_off *address, int *magiccount, char **magic)
+get_char (FILE *stream, file_ptr *address, int *magiccount, char **magic)
{
int c, i;
- long r = EOF;
- unsigned char buf[4];
+ long r = 0;
for (i = 0; i < encoding_bytes; i++)
{
}
(*address)++;
- buf[i] = c;
+ r = (r << 8) | (c & 0xff);
}
switch (encoding)
{
- case 'S':
- 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;
}
+
+/* Throw away one byte of a (possibly) multi-byte char C, updating
+ address and buffer to suit. */
+
+static void
+unget_part_char (long c, file_ptr *address, int *magiccount, char **magic)
+{
+ static char tmp[4];
+
+ if (encoding_bytes > 1)
+ {
+ *address -= encoding_bytes - 1;
+
+ if (*magiccount == 0)
+ {
+ /* If no magic buffer exists, use temp buffer. */
+ switch (encoding)
+ {
+ default:
+ break;
+ case 'b':
+ tmp[0] = c & 0xff;
+ *magiccount = 1;
+ break;
+ case 'l':
+ tmp[0] = (c >> 8) & 0xff;
+ *magiccount = 1;
+ break;
+ case 'B':
+ tmp[0] = (c >> 16) & 0xff;
+ tmp[1] = (c >> 8) & 0xff;
+ tmp[2] = c & 0xff;
+ *magiccount = 3;
+ break;
+ case 'L':
+ tmp[0] = (c >> 8) & 0xff;
+ tmp[1] = (c >> 16) & 0xff;
+ tmp[2] = (c >> 24) & 0xff;
+ *magiccount = 3;
+ break;
+ }
+ *magic = tmp;
+ }
+ else
+ {
+ /* If magic buffer exists, rewind. */
+ *magic -= encoding_bytes - 1;
+ *magiccount += encoding_bytes - 1;
+ }
+ }
+}
\f
/* Find the strings in file FILENAME, read from STREAM.
Assume that STREAM is positioned so that the next byte read
Those characters come at address ADDRESS and the data in STREAM follow. */
static void
-print_strings (const char *filename, FILE *stream, file_off address,
+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));
while (1)
{
- file_off start;
+ file_ptr start;
int i;
long c;
{
c = get_char (stream, &address, &magiccount, &magic);
if (c == EOF)
- return;
+ {
+ free (buf);
+ return;
+ }
+
if (! STRING_ISGRAPHIC (c))
- /* Found a non-graphic. Try again starting with next char. */
- goto tryline;
+ {
+ /* Found a non-graphic. Try again starting with next byte. */
+ unget_part_char (c, &address, &magiccount, &magic);
+ goto tryline;
+ }
buf[i] = c;
}
switch (address_radix)
{
case 8:
-#if __STDC_VERSION__ >= 199901L || (defined(__GNUC__) && __GNUC__ >= 2)
if (sizeof (start) > sizeof (long))
{
#ifndef __MSVCRT__
- printf ("%7llo ", (unsigned long long) start);
+ printf ("%7llo ", (unsigned long long) start);
#else
- printf ("%7I64o ", (unsigned long long) start);
+ 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:
-#if __STDC_VERSION__ >= 199901L || (defined(__GNUC__) && __GNUC__ >= 2)
if (sizeof (start) > sizeof (long))
{
#ifndef __MSVCRT__
- printf ("%7lld ", (unsigned long long) start);
+ printf ("%7llu ", (unsigned long long) start);
#else
- printf ("%7I64d ", (unsigned long long) start);
+ 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:
-#if __STDC_VERSION__ >= 199901L || (defined(__GNUC__) && __GNUC__ >= 2)
if (sizeof (start) > sizeof (long))
{
#ifndef __MSVCRT__
- printf ("%7llx ", (unsigned long long) start);
+ printf ("%7llx ", (unsigned long long) start);
#else
- printf ("%7I64x ", (unsigned long long) start);
+ 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;
}
if (c == EOF)
break;
if (! STRING_ISGRAPHIC (c))
- break;
+ {
+ unget_part_char (c, &address, &magiccount, &magic);
+ break;
+ }
putchar (c);
}
- putchar ('\n');
- }
-}
-\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 (char *s)
-{
- 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';
+ if (output_separator)
+ fputs (output_separator, stdout);
else
- value += (c & ~40) - 'A';
+ putchar ('\n');
}
-
- if (c == 'b')
- value *= 512;
- else if (c == 'B')
- value *= 1024;
- else
- p--;
-
- if (*p)
- fatal (_("invalid integer argument %s"), s);
-
- return value;
+ free (buf);
}
-
+\f
static void
usage (FILE *stream, int status)
{
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\
+ 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
+ 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"));
+
+ fprintf (stream, _("\
-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\
+ -<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 --version Print the program's version number\n"));
+ -v -V --version Print the program's version number\n"));
list_supported_targets (program_name, stream);
if (REPORT_BUGS_TO[0] && status == 0)
fprintf (stream, _("Report bugs to %s\n"), REPORT_BUGS_TO);