Package: file
Version: 4.15-2
Followup-For: Bug #345928
this is the patch:
it recognise the first three byte which indicate utf-8 encoding, even if
content is not utf-8.
--- file-4.15/src/ascmagic.c 2005-06-30 18:33:01.000000000 +0200
+++ file-4.15.modif_jmg/src/ascmagic.c 2006-01-11 17:48:39.000000000
+0100
@@ -59,6 +59,7 @@
|| (x) == 0x85 || (x) == '\f')
private int looks_ascii(const unsigned char *, size_t, unichar *,
size_t *);
+private int looks_utf8_header(const unsigned char *buf, size_t nbytes,
unichar *ubuf, size_t *ulen);
private int looks_utf8(const unsigned char *, size_t, unichar *, size_t
*);
private int looks_unicode(const unsigned char *, size_t, unichar *,
size_t *);
private int looks_latin1(const unsigned char *, size_t, unichar *,
size_t *);
@@ -121,6 +122,10 @@
code = "UTF-8 Unicode";
code_mime = "utf-8";
type = "text";
+ } else if (looks_utf8_header(buf, nbytes, ubuf, &ulen)) {
+ code = "UTF-8 broken";
+ code_mime = "utf-8 ???";
+ type = "text";
} else if ((i = looks_unicode(buf, nbytes, ubuf, &ulen)) != 0) {
if (i == 1)
code = "Little-endian UTF-16 Unicode";
@@ -512,6 +517,27 @@
}
private int
+looks_utf8_header(const unsigned char *buf, size_t nbytes, unichar
*ubuf, size_t *ulen)
+{
+ unsigned char utf8_header []= {0xef, 0xbb, 0xbf };
+ int got = 1;
+ int i;
+ *ulen = 0;
+ if (nbytes <3)
+ {
+ return 0;
+ }
+ for (i = 0; i < 3; i++) {
+ if ( buf[i] != utf8_header [i] )
+ {
+ got = 0;
+ }
+ //printf ("DEBUG: '%d' , '%d' : [%d] -> %d\n", buf[i],
utf8_header[i] , i, got);
+ }
+ return got;
+}
+
+private int
looks_utf8(const unsigned char *buf, size_t nbytes, unichar *ubuf,
size_t *ulen)
{
int i, n;
-- System Information:
Debian Release: testing/unstable
APT prefers testing
APT policy: (500, 'testing'), (500, 'stable')
Architecture: i386 (i686)
Shell: /bin/sh linked to /bin/bash
Kernel: Linux 2.6.12-1-686
Locale: [EMAIL PROTECTED], [EMAIL PROTECTED] (charmap=ISO-8859-15)
Versions of packages file depends on:
ii libc6 2.3.5-8 GNU C Library: Shared libraries an
ii libmagic1 4.15-2 File type determination library us
ii zlib1g 1:1.2.3-9 compression library - runtime
file recommends no packages.
-- no debconf information
--
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
