Azure: Ensure platform random_seed is always serializable as JSON.

The Azure platform surfaces random bytes into /sys via Hyper-V.
Python 2.7 json.dump() raises an exception if asked to convert
a str with non-character content, and python 3.0 json.dump()
won't serialize a "bytes" value. As a result, c-i instance
data is often not written by Azure, making reboots slower (c-i
has to repeat work).

The random data is base64-encoded and then decoded into a string
(str or unicode depending on the version of Python in use). The
base64 string has just as many bits of entropy, so we're not
throwing away useful "information", but we can be certain
json.dump() will correctly serialize the bits.

2 files changed, 23 insertions, 2 deletions

diff --git a/tests/data/azure/non_unicode_random_string b/tests/data/azure/non_unicode_random_string
new file mode 100644
index 00000000..b9ecefb9
--- /dev/null
+++ b/tests/data/azure/non_unicode_random_string
@@ -0,0 +1 @@
+OEM0d\x00\x00\x00\x01\x80VRTUALMICROSFT\x02\x17\x00\x06MSFT\x97\x00\x00\x00C\xb4{V\xf4X%\x061x\x90\x1c\xfen\x86\xbf~\xf5\x8c\x94&\x88\xed\x84\xf9B\xbd\xd3\xf1\xdb\xee:\xd9\x0fc\x0e\x83(\xbd\xe3'\xfc\x85,\xdf\xf4\x13\x99N\xc5\xf3Y\x1e\xe3\x0b\xa4H\x08J\xb9\xdcdb$
\ No newline at end of file
diff --git a/tests/unittests/test_datasource/test_azure.py b/tests/unittests/test_datasource/test_azure.py
index 6b05b8f1..53c56cd0 100644
--- a/tests/unittests/test_datasource/test_azure.py
+++ b/tests/unittests/test_datasource/test_azure.py
@@ -7,11 +7,11 @@ from cloudinit.sources import (
     UNSET, DataSourceAzure as dsaz, InvalidMetaDataException)
 from cloudinit.util import (b64e, decode_binary, load_file, write_file,
                             find_freebsd_part, get_path_dev_freebsd,
-                            MountFailedError)
+                            MountFailedError, json_dumps, load_json)
 from cloudinit.version import version_string as vs
 from cloudinit.tests.helpers import (
     HttprettyTestCase, CiTestCase, populate_dir, mock, wrap_and_call,
-    ExitStack)
+    ExitStack, resourceLocation)
 
 import crypt
 import httpretty
@@ -1923,4 +1923,24 @@ class TestWBIsPlatformViable(CiTestCase):
             self.logs.getvalue())
 
 
+class TestRandomSeed(CiTestCase):
+    """Test proper handling of random_seed"""
+
+    def test_non_ascii_seed_is_serializable(self):
+        """Pass if a random string from the Azure infrastructure which
+        contains at least one non-Unicode character can be converted to/from
+        JSON without alteration and without throwing an exception.
+        """
+        path = resourceLocation("azure/non_unicode_random_string")
+        result = dsaz._get_random_seed(path)
+
+        obj = {'seed': result}
+        try:
+            serialized = json_dumps(obj)
+            deserialized = load_json(serialized)
+        except UnicodeDecodeError:
+            self.fail("Non-serializable random seed returned")
+
+        self.assertEqual(deserialized['seed'], result)
+
 # vi: ts=4 expandtab