Re: What have you done to strings!

[Nicholas Clifton <nickc at redhat dot com>]

Hi Guys.

 OK - what do you think of the attached patch ?  It does the following:

  * Makes -a be strings default behaviour.

  * Adds a new option to strings -d which restores the old
    behaviour of only scanning data sections.

  * Provides a configure time option --disable-default-strings-all
    which restores the old behaviour of strings scanning data
    sections be default.

  * Updates the documentation to describe -d, plus why -a might be
    preferred and how the - option works as well.

  * Adds a NEWS entry about all of the above.

Cheers
  Nick

diff --git a/binutils/NEWS b/binutils/NEWS
index 126219b..e7af3c7 100644
--- a/binutils/NEWS
+++ b/binutils/NEWS
@@ -1,5 +1,10 @@
 -*- text -*-
 
+* Add --data option to strings to only print strings in loadable, initialized
+  data sections.  Change the default behaviour to be --all, but add a new
+  configure time option of --disable-default-strings-all to restore the old
+  default behaviour.
+
 Changes in 2.25:
 
 * Add --include-all-whitespace to strings.
diff --git a/binutils/configure.ac b/binutils/configure.ac
index c5da20d..c5aadd8 100644
--- a/binutils/configure.ac
+++ b/binutils/configure.ac
@@ -55,6 +55,18 @@ fi], [default_ar_deterministic=0])
 AC_DEFINE_UNQUOTED(DEFAULT_AR_DETERMINISTIC, $default_ar_deterministic,
 		   [Should ar and ranlib use -D behavior by default?])
 
+AC_ARG_ENABLE(default-strings-all,
+[AS_HELP_STRING([--disable-default-strings-all],
+		[strings defaults to --data behavior])], [
+if test "${enableval}" = no; then
+  default_strings_all=0
+else
+  default_strings_all=1
+fi], [default_strings_all=1])
+
+AC_DEFINE_UNQUOTED(DEFAULT_STRINGS_ALL, $default_strings_all,
+		   [Should strings use -a behavior by default?])
+
 AM_BINUTILS_WARNINGS
 
 AC_CONFIG_HEADERS(config.h:config.in)
diff --git a/binutils/doc/binutils.texi b/binutils/doc/binutils.texi
index 3874f25..eee77b1 100644
--- a/binutils/doc/binutils.texi
+++ b/binutils/doc/binutils.texi
@@ -2672,15 +2672,24 @@ strings [@option{-afovV}] [@option{-}@var{min-len}]
 
 @c man begin DESCRIPTION strings
 
-For each @var{file} given, @sc{gnu} @command{strings} prints the printable
-character sequences that are at least 4 characters long (or the number
-given with the options below) and are followed by an unprintable
-character.  By default, it only prints the strings from the initialized
-and loaded sections of object files; for other types of files, it prints
-the strings from the whole file.
+For each @var{file} given, @sc{gnu} @command{strings} prints the
+printable character sequences that are at least 4 characters long (or
+the number given with the options below) and are followed by an
+unprintable character.
 
-@command{strings} is mainly useful for determining the contents of non-text
-files.
+Depending upon how the strings program was configured it will default
+to either displaying all the printable sequences that it can find in
+each file, or only those sequences that are in loadable, initialized
+data sections.  If the file type in unrecognizable, or if strings is
+reading from stdin then it will always display all of the printable
+sequences that it can find.
+
+For backwards compatibility any file that occurs after a command line
+option of just @option{-} will also be scanned in full, regardless of
+the presence of any @option{-d} option. 
+
+@command{strings} is mainly useful for determining the contents of
+non-text files.
 
 @c man end
 
@@ -2690,8 +2699,25 @@ files.
 @item -a
 @itemx --all
 @itemx -
-Do not scan only the initialized and loaded sections of object files;
-scan the whole files.
+Scan the whole file, regardless of what sections it contains or
+whether those sections are loaded or initialized.  Normally this is
+the default behaviour, but strings can be configured so that the
+@option{-d} is the default instead.
+
+The @option{-} option is position dependent and forces strings to
+perform full scans of any file that is mentioned after the @option{-}
+on the command line, even if the @option{-d} option has been
+specified.
+
+@item -d
+@itemx --data
+Only print strings from initialized, loaded data sections in the
+file.  This may reduce the amount of garbage in the output, but it
+also exposes the strings program to any security flaws that may be
+present in the BFD library used to scan and load sections.  Strings
+can be configured so that this option is the default behaviour.  In
+such cases the @option{-a} option can be used to avoid using the BFD
+library and instead just print all of the strings found in the file.
 
 @item -f
 @itemx --print-file-name
diff --git a/binutils/strings.c b/binutils/strings.c
index f92132b..72085ac 100644
--- a/binutils/strings.c
+++ b/binutils/strings.c
@@ -23,6 +23,9 @@
    -a
    -		Do not scan only the initialized data section of object files.
 
+   --data
+   -d		Scan each file in its entirety.
+
    --print-file-name
    -f		Print the name of the file before each string.
 
@@ -114,6 +117,7 @@ static int encoding_bytes;
 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'},
@@ -136,7 +140,7 @@ typedef struct
 
 static void strings_a_section (bfd *, asection *, void *);
 static bfd_boolean strings_object_file (const char *);
-static bfd_boolean strings_file (char *file);
+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 **);
@@ -167,11 +171,14 @@ main (int argc, char **argv)
   include_all_whitespace = FALSE;
   print_addresses = FALSE;
   print_filenames = FALSE;
-  datasection_only = TRUE;
+  if (DEFAULT_STRINGS_ALL)
+    datasection_only = FALSE;
+  else
+    datasection_only = TRUE;
   target = NULL;
   encoding = 's';
 
-  while ((optc = getopt_long (argc, argv, "afhHn:wot:e:T:Vv0123456789",
+  while ((optc = getopt_long (argc, argv, "adfhHn:wot:e:T:Vv0123456789",
 			      long_options, (int *) 0)) != EOF)
     {
       switch (optc)
@@ -180,6 +187,10 @@ main (int argc, char **argv)
 	  datasection_only = FALSE;
 	  break;
 
+	case 'd':
+	  datasection_only = TRUE;
+	  break;
+
 	case 'f':
 	  print_filenames = TRUE;
 	  break;
@@ -648,8 +659,18 @@ 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\