>From d10bdeeb31225238f47a9002e891c62c06cd6a47 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Tim=20R=C3=BChsen?= <address@hidden>
Date: Tue, 30 Jun 2015 09:55:14 +0200
Subject: [PATCH] Work around a libidn <= 1.30 vulnerability

* src/iri.c: Add _utf8_is_valid() to check UTF-8 sequences before
  passing them to idna_to_ascii_8z().
---
 src/iri.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/src/iri.c b/src/iri.c
index 10ae994..faeca90 100644
--- a/src/iri.c
+++ b/src/iri.c
@@ -219,6 +219,51 @@ locale_to_utf8 (const char *str)
   return str;
 }
 
+/*
+ * Work around a libidn <= 1.30 vulnerability.
+ *
+ * The function checks for a valid UTF-8 character sequence before
+ * passing it to idna_to_ascii_8z().
+ *
+ * [1] http://lists.gnu.org/archive/html/help-libidn/2015-05/msg00002.html
+ * [2] https://lists.gnu.org/archive/html/bug-wget/2015-06/msg00002.html
+ * [3] http://curl.haxx.se/mail/lib-2015-06/0143.html
+ */
+static bool
+_utf8_is_valid(const char *utf8)
+{
+  int i, offset = 0;
+  const unsigned char *s = (const unsigned char *) utf8;
+
+  while (*s)
+    {
+      if ((*s & 0x80) == 0) /* 0xxxxxxx ASCII char */
+        offset = 1;
+      else if ((*s & 0xE0) == 0xC0) /* 110xxxxx 10xxxxxx */
+        offset = 2;
+      else if ((*s & 0xF0) == 0xE0) /* 1110xxxx 10xxxxxx 10xxxxxx */
+        offset = 3;
+      else if ((*s & 0xF8) == 0xF0) /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
+        offset = 4;
+      else if ((*s & 0xFC) == 0xF8)
+        offset = 5;
+      else if ((*s & 0xFE) == 0xFC)
+        offset = 6;
+      else
+        return false;
+
+      for (i = 1; i < offset; i++)
+        {
+          if ((s[i] & 0xC0) != 0x80)
+            return false;
+        }
+
+      s += offset;
+    }
+
+  return true;
+}
+
 /* Try to "ASCII encode" UTF-8 host. Return the new domain on success or NULL
    on error. */
 char *
@@ -235,6 +280,13 @@ idn_encode (struct iri *i, char *host)
           return NULL;  /* Nothing to encode or an error occured */
     }
 
+  if (!_utf8_is_valid(utf8_encoded ? utf8_encoded : host))
+    {
+      xfree (utf8_encoded);
+      logprintf (LOG_VERBOSE, _("Invalid UTF-8 sequence\n"));
+      return NULL;
+    }
+
   /* Store in ascii_encoded the ASCII UTF-8 NULL terminated string */
   ret = idna_to_ascii_8z (utf8_encoded ? utf8_encoded : host, &ascii_encoded, IDNA_FLAGS);
   xfree (utf8_encoded);
-- 
1.9.1