From 34965b4e77b3091dd0d959873b21239f3da02ac4 Mon Sep 17 00:00:00 2001
From: Matthias Vallentin <vallentin@icir.org>
Date: Thu, 1 Aug 2013 19:15:28 +0200
Subject: [PATCH] Support UHF hashing for >= UHASH_KEY_SIZE bytes.

---
 src/probabilistic/Hasher.cc | 23 +++++++++++++++++++----
 src/probabilistic/Hasher.h  |  5 +++--
 2 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/src/probabilistic/Hasher.cc b/src/probabilistic/Hasher.cc
index b59274df7d..fe8eb66ad9 100644
--- a/src/probabilistic/Hasher.cc
+++ b/src/probabilistic/Hasher.cc
@@ -1,6 +1,7 @@
 // See the file "COPYING" in the main distribution directory for copyright.
 
 #include <typeinfo>
+#include <openssl/md5.h>
 
 #include "Hasher.h"
 #include "NetVar.h"
@@ -82,15 +83,29 @@ Hasher::Hasher(size_t arg_k, size_t arg_seed)
 	seed = arg_seed;
 	}
 
-UHF::UHF(size_t seed)
-	: h(seed)
+UHF::UHF(size_t arg_seed)
+	: h(arg_seed)
 	{
+  seed = arg_seed;
 	}
 
+// This function is almost equivalent to HashKey::HashBytes except that it does
+// not depend on global state and that we mix in the seed multiple times.
 Hasher::digest UHF::hash(const void* x, size_t n) const
 	{
-	assert(n <= UHASH_KEY_SIZE);
-	return n == 0 ? 0 : h(x, n);
+	if ( n <= UHASH_KEY_SIZE )
+		return n == 0 ? 0 : h(x, n);
+
+	unsigned char d[16];
+	MD5(reinterpret_cast<const unsigned char*>(x), n, d);
+
+	const unsigned char* s = reinterpret_cast<const unsigned char*>(&seed);
+	for ( size_t i = 0; i < 16; ++i )
+		d[i] ^= s[i % sizeof(seed)];
+
+	MD5(d, 16, d);
+
+	return d[0];
 	}
 
 DefaultHasher::DefaultHasher(size_t k, size_t seed)
diff --git a/src/probabilistic/Hasher.h b/src/probabilistic/Hasher.h
index 6b75fa1bea..a3322f5e37 100644
--- a/src/probabilistic/Hasher.h
+++ b/src/probabilistic/Hasher.h
@@ -123,9 +123,9 @@ public:
 	 * Constructs an H3 hash function seeded with a given seed and an
 	 * optional extra seed to replace the initial Bro seed.
 	 *
-	 * @param seed The seed to use for this instance.
+	 * @param arg_seed The seed to use for this instance.
 	 */
-	UHF(size_t seed = 0);
+	UHF(size_t arg_seed = 0);
 
 	template <typename T>
 	Hasher::digest operator()(const T& x) const
@@ -171,6 +171,7 @@ private:
 	static size_t compute_seed(size_t seed);
 
 	H3<Hasher::digest, UHASH_KEY_SIZE> h;
+	size_t seed;
 };