Submitted By:            Douglas R. Reno <renodr at linuxfromscratch dot org>
Date:                    2021-09-07
Initial Package Version: 5.40
Origin:                  Upstream + Arch Linux
Upstream Status:         Applied
Description:             Fixes a problem with detection of XZ files as well as
                         several issues where a text file may be read as binary
                         instead of being judged by it's contents. This is to
                         fix Subversion and Mercurial.

diff -Naurp file-5.40.orig/magic/Magdir/compress file-5.40/magic/Magdir/compress
--- file-5.40.orig/magic/Magdir/compress	2021-09-07 12:06:42.208952362 -0500
+++ file-5.40/magic/Magdir/compress	2021-09-07 12:07:47.217366489 -0500
@@ -265,14 +265,13 @@
 
 # http://tukaani.org/xz/xz-file-format.txt
 0	ustring		\xFD7zXZ\x00		XZ compressed data, checksum
+!:strength * 2
+!:mime   application/x-xz
 >7	byte&0xf	0x0			NONE
 >7	byte&0xf	0x1			CRC32
 >7	byte&0xf	0x4			CRC64
 >7	byte&0xf	0xa			SHA-256
 
-!:strength * 2
-!:mime	application/x-xz
-
 # https://github.com/ckolivas/lrzip/blob/master/doc/magic.header.txt
 0	string		LRZI			LRZIP compressed data
 >4	byte		x			- version %d
diff -Naurp file-5.40.orig/src/encoding.c file-5.40/src/encoding.c
--- file-5.40.orig/src/encoding.c	2021-09-07 12:06:42.205952389 -0500
+++ file-5.40/src/encoding.c	2021-09-07 12:12:51.652664645 -0500
@@ -265,9 +265,7 @@ private int \
 looks_ ## NAME(const unsigned char *buf, size_t nbytes, file_unichar_t *ubuf, \
     size_t *ulen) \
 { \
-	size_t i, u; \
-	unsigned char dist[256]; \
-	memset(dist, 0, sizeof(dist)); \
+	size_t i; \
 \
 	*ulen = 0; \
 \
@@ -278,16 +276,7 @@ looks_ ## NAME(const unsigned char *buf,
 			return 0; \
 \
 		ubuf[(*ulen)++] = buf[i]; \
-		dist[buf[i]]++; \
-	} \
-	u = 0; \
-	for (i = 0; i < __arraycount(dist); i++) { \
-		if (dist[i]) \
-			u++; \
-	} \
-	if (u < 3) \
-		return 0; \
-\
+   } \
 	return 1; \
 }