Further fixes for unicode handling in manifests

We were occasionally trying to compute schema 2 version 1 signatures on the *unicode* representation, which was failing the signature check. This PR adds a new wrapper type called `Bytes`, which all manifests must take in, and which handles the unicodes vs encoded utf-8 stuff in a central location. This PR also adds a test for the manifest that was breaking in production.

image/docker/schema2/manifest.py

@@ -16,7 +16,7 @@ from image.docker.schema2 import (DOCKER_SCHEMA2_MANIFEST_CONTENT_TYPE,
                                   EMPTY_LAYER_BLOB_DIGEST, EMPTY_LAYER_SIZE)
 from image.docker.schema1 import DockerSchema1ManifestBuilder
 from image.docker.schema2.config import DockerSchema2Config
-from image.docker.schemautil import ensure_utf8
+from util.bytes import Bytes
 
 # Keys.
 DOCKER_SCHEMA2_MANIFEST_VERSION_KEY = 'schemaVersion'
@@ -129,13 +129,15 @@ class DockerSchema2Manifest(ManifestInterface):
   }
 
   def __init__(self, manifest_bytes):
+    assert isinstance(manifest_bytes, Bytes)
+
     self._payload = manifest_bytes
 
     self._filesystem_layers = None
     self._cached_built_config = None
 
     try:
-      self._parsed = json.loads(ensure_utf8(self._payload))
+      self._parsed = json.loads(self._payload.as_unicode())
     except ValueError as ve:
       raise MalformedSchema2Manifest('malformed manifest data: %s' % ve)
 
@@ -166,7 +168,7 @@ class DockerSchema2Manifest(ManifestInterface):
 
   @property
   def digest(self):
-    return digest_tools.sha256_digest(ensure_utf8(self._payload))
+    return digest_tools.sha256_digest(self._payload.as_encoded_str())
 
   @property
   def config(self):
@@ -365,7 +367,7 @@ class DockerSchema2Manifest(ManifestInterface):
                                                                         self.config.size)
       raise MalformedSchema2Manifest(msg)
 
-    self._cached_built_config = DockerSchema2Config(config_bytes)
+    self._cached_built_config = DockerSchema2Config(Bytes.for_string_or_unicode(config_bytes))
     return self._cached_built_config
 
   def _generate_filesystem_layers(self):
@@ -446,4 +448,6 @@ class DockerSchema2ManifestBuilder(object):
         _build_layer(layer) for layer in self.filesystem_layers
       ],
     }
-    return DockerSchema2Manifest(json.dumps(manifest_dict, ensure_ascii=ensure_ascii, indent=3))
+
+    json_str = json.dumps(manifest_dict, ensure_ascii=ensure_ascii, indent=3)
+    return DockerSchema2Manifest(Bytes.for_string_or_unicode(json_str))