Add UTF-8-support to strings(1), add t-flag and refactor code

Previously, the string-length was limited to BUFSIZ, which is an
obvious deficiency.
Now the buffer only needs to be as long as the user specifies the
minimal string length.
I added UTF-8-support, because that's how POSIX wants it and there
are cases where you need this. It doesn't add ELF-barf compared to
the previous implementation.
The t-flag is also pretty important for POSIX-compliance, so I added
it.
The only trouble previously was the a-flag, but given that POSIX
leaves undefined what the a-flag actually does, we set it as default
and don't care about parsing ELF-headers, which has already
turned out to be a security issue in GNU coreutils[0].

[0]: http://lcamtuf.blogspot.ro/2014/10/psa-dont-run-strings-on-untrusted-files.html
This commit is contained in:
FRIGN 2015-02-17 17:04:36 +01:00
parent 949dafc171
commit e5b5497773
3 changed files with 80 additions and 35 deletions

2
README
View File

@ -67,7 +67,7 @@ The following tools are implemented ('*' == finished, '#' == UTF-8 support,
sort no -m, -o, -d, -f, -i
=* split yes none
=* sponge non-posix none
strings no -t
#* strings yes none
=* sync non-posix none
=* tail yes none
=* tar non-posix none

View File

@ -1,32 +1,52 @@
.Dd November 23, 2014
.Dd Februrary 17, 2015
.Dt STRINGS 1
.Os sbase
.Sh NAME
.Nm strings
.Nd print the strings of printable characters in files
.Nd print strings of printable characters in files
.Sh SYNOPSIS
.Nm
.Op Fl a
.Op Fl n Ar len
.Op Fl n Ar num
.Op Fl t Ar format
.Op Ar file ...
.Sh DESCRIPTION
.Nm
prints the printable character sequences that are at least 4 characters
long. If no
.Ar files
are given,
writes sequences of at least 4 printable characters in each
.Ar file
to stdout.
If no
.Ar file
is given,
.Nm
reads from stdin.
.Sh OPTIONS
.Bl -tag -width Ds
.It Fl a
Scan files in their entirety. This is the default.
.It Fl n Ar len
Only print sequences that are at least
.Ar len
characters. The default is 4 characters.
Scan each
.Ar file
entirely. This is the default.
.It Fl n Ar num
Print sequences of at least
.Ar num
characters. The default is 4.
.It Fl t Ar format
Prepend each string with its byte offset, with
.Ar format
being one of
.Sy d , o , x
for decimal, octal or hexadecimal numbers.
.El
.Sh STANDARDS
The
.Nm
mirrors the semantics of Plan9
.Xr strings 1 .
utility is compliant with the
.St -p1003.1-2008
specification.
.Pp
The
.Op Fl t
output format has been changed from "%F %s" to "%8lF: %s", with
.Sy F
being one of
.Sy d , o , x .

View File

@ -1,50 +1,75 @@
/* See LICENSE file for copyright and license details. */
#include <ctype.h>
#include <limits.h>
#include <stdio.h>
#include <stdlib.h>
#include "utf.h"
#include "util.h"
static void
strings(FILE *fp, const char *fname, int len)
{
unsigned char buf[BUFSIZ];
int c, i = 0;
off_t offset = 0;
static char *format = "";
do {
offset++;
if (isprint(c = getc(fp)))
buf[i++] = c;
if ((!isprint(c) && i >= len) || i == sizeof(buf) - 1) {
buf[i] = '\0';
printf("%8ld: %s\n", (long)offset - i - 1, buf);
static void
strings(FILE *fp, const char *fname, size_t len)
{
Rune r, *rbuf;
size_t i, bread;
off_t off;
rbuf = emalloc(len * sizeof(*rbuf));
for (off = 0, i = 0; (bread = efgetrune(&r, fp, fname)); ) {
off += bread;
if (r == Runeerror)
continue;
else if (!isprintrune(r)) {
if (i > len)
putchar('\n');
i = 0;
continue;
}
} while (c != EOF);
if (ferror(fp))
eprintf("%s: read error:", fname);
if (i < len) {
rbuf[i++] = r;
continue;
} else if (i > len) {
efputrune(&r, stdout, "<stdout>");
continue;
}
printf(format, (long)off - i);
for (i = 0; i < len; i++) {
efputrune(rbuf + i, stdout, "<stdout>");
}
i++;
}
free(rbuf);
}
static void
usage(void)
{
eprintf("usage: %s [-a] [-n len] [file ...]\n", argv0);
eprintf("usage: %s [-a] [-n num] [-t format] [file ...]\n", argv0);
}
int
main(int argc, char *argv[])
{
FILE *fp;
size_t len = 4;
int ret = 0;
int len = 4;
char f;
ARGBEGIN {
case 'a':
break;
case 'n':
len = estrtonum(EARGF(usage()), 1, INT_MAX);
len = estrtonum(EARGF(usage()), 1, LLONG_MAX);
break;
case 't':
format = estrdup("%8l#: ");
f = *EARGF(usage());
if (f == 'd' || f == 'o' || f == 'x')
format[3] = f;
else
usage();
break;
default:
usage();