From: Joey Hess <joey@gnu.kitenet.net>
Date: Tue, 5 May 2009 19:06:34 +0000 (-0400)
Subject: isutf8: Reject UTF-8-encoded UTF-16 surrogates. Closes: #525301 (Thanks, Jakub Wilk... 
X-Git-Tag: 0.35~2
X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=a250ae89f37849be1caf204a07d2e4e563503390;p=moreutils

isutf8: Reject UTF-8-encoded UTF-16 surrogates. Closes: #525301 (Thanks, Jakub Wilk and liw)
---

diff --git a/check-isutf8 b/check-isutf8
index 3abb315..83a4eed 100755
--- a/check-isutf8
+++ b/check-isutf8
@@ -39,5 +39,8 @@ check 1 '\xc2'
 check 1 '\xc2\x20'
 check 1 '\x20\xc2'
 check 1 '\300\200'
+check 1 '\xed\xa0\x88\xed\xbd\x85' # UTF-16 surrogates
+check 1 '\xef\xbf\xbe' # 0xFFFE
+check 1 '\xef\xbf\xbf' # 0xFFFF
 
 exit $failed
diff --git a/debian/changelog b/debian/changelog
index aac1f3f..7b638cb 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -3,6 +3,8 @@ moreutils (0.35) UNRELEASED; urgency=low
   * ifdata: Don't assume that all interface names are 6 characters or less,
     for instance "wmaster0" is longer. Increase the limit to 20 characters.
     Closes: #526654 (Thanks, Alan Pope)
+  * isutf8: Reject UTF-8-encoded UTF-16 surrogates. Closes: #525301
+    (Thanks, Jakub Wilk and liw)
 
  -- Joey Hess <joeyh@debian.org>  Sat, 02 May 2009 20:40:23 -0400
 
diff --git a/isutf8.c b/isutf8.c
index 4306c7d..c5f5eeb 100644
--- a/isutf8.c
+++ b/isutf8.c
@@ -127,6 +127,14 @@ static unsigned long decodeutf8(unsigned char *buf, int nbytes)
                             return INVALID_CHAR;
                 u = (u << 6) | (buf[j] & 0x3f);
         }
+
+        /* Conforming UTF-8 cannot contain codes 0xd800–0xdfff (UTF-16 
+           surrogates) as well as 0xfffe and 0xffff. */
+        if (u >= 0xD800 && u <= 0xDFFF)
+            return INVALID_CHAR;
+        if (u == 0xFFFE || u == 0xFFFF)
+            return INVALID_CHAR;
+
         return u;
 }
 
@@ -145,7 +153,7 @@ static int is_utf8_byte_stream(FILE *file, char *filename, int quiet) {
         int nbytes, nbytes2;
         int c;
         unsigned long code;
-	unsigned long line, col, byteoff;
+        unsigned long line, col, byteoff;
 
         nbytes = 0;
         line = 1;