Fix translation of Java murmur2 code, fix byte encoding for Python 3.

Avoid further type changes when Murmur2Partitioner is passed a byte
array.  Change leftover-bytes logic to match the Java switch statement,
and add tests to verify that partition selection matches Java implementation.

1 files changed, 23 insertions, 0 deletions

diff --git a/test/test_partitioner.py b/test/test_partitioner.py
new file mode 100644
index 0000000..67cd83b
--- /dev/null
+++ b/test/test_partitioner.py
@@ -0,0 +1,23 @@
+import six
+from . import unittest
+
+from kafka.partitioner import (Murmur2Partitioner)
+
+class TestMurmurPartitioner(unittest.TestCase):
+    def test_hash_bytes(self):
+        p = Murmur2Partitioner(range(1000))
+        self.assertEqual(p.partition(bytearray(b'test')), p.partition(b'test'))
+
+    def test_hash_encoding(self):
+        p = Murmur2Partitioner(range(1000))
+        self.assertEqual(p.partition('test'), p.partition(u'test'))
+
+    def test_murmur2_java_compatibility(self):
+        p = Murmur2Partitioner(range(1000))
+        # compare with output from Kafka's org.apache.kafka.clients.producer.Partitioner
+        self.assertEqual(681, p.partition(b''))
+        self.assertEqual(524, p.partition(b'a'))
+        self.assertEqual(434, p.partition(b'ab'))
+        self.assertEqual(107, p.partition(b'abc'))
+        self.assertEqual(566, p.partition(b'123456789'))
+        self.assertEqual(742, p.partition(b'\x00 '))