Fix handling of four byte utf8 manifests

- Adds the charset: utf-8 to all the manifest responses
- Makes sure we connect to MySQL in utf8mb4 mode, to ensure we can properly read and write 4-byte utf8 strings
- Adds tests for all of the above

image/docker/test/test_schema1.py

@@ -178,3 +178,22 @@ def test_validate_manifest_known_issue():
 
   layers = list(manifest.get_layers(None))
   assert layers[-1].author is None
+
+
+@pytest.mark.parametrize('with_key', [
+  None,
+  docker_v2_signing_key,
+])
+def test_validate_manifest_with_emoji(with_key):
+  builder = DockerSchema1ManifestBuilder('somenamespace', 'somerepo', 'sometag')
+  builder.add_layer('sha256:abcde', json.dumps({
+    'id': 'someid',
+    'author': u'😱',
+  }, ensure_ascii=False))
+
+  built = builder.build(with_key, ensure_ascii=False)
+  built._validate()
+
+  # Ensure the manifest can be reloaded.
+  built_bytes = built.bytes.as_encoded_str()
+  DockerSchema1Manifest(Bytes.for_string_or_unicode(built_bytes))