Restyle azure: support external dependencies and outputs

dvc/dependency/__init__.py

@@ -2,6 +2,7 @@
 from urllib.parse import urlparse
 
 import dvc.output as output
+from dvc.dependency.azure import AzureDependency
 from dvc.dependency.gs import GSDependency
 from dvc.dependency.hdfs import HDFSDependency
 from dvc.dependency.http import HTTPDependency
@@ -17,6 +18,7 @@
 from .repo import RepoDependency
 
 DEPS = [
+    AzureDependency,
     GSDependency,
     HDFSDependency,
     HTTPDependency,
@@ -30,6 +32,7 @@
     Schemes.LOCAL: LocalDependency,
     Schemes.SSH: SSHDependency,
     Schemes.S3: S3Dependency,
+    Schemes.AZURE: AzureDependency,
     Schemes.GS: GSDependency,
     Schemes.HDFS: HDFSDependency,
     Schemes.HTTP: HTTPDependency,

dvc/dependency/azure.py

@@ -0,0 +1,6 @@
+from dvc.dependency.base import BaseDependency
+from dvc.output.azure import AzureOutput
+
+
+class AzureDependency(BaseDependency, AzureOutput):
+    pass

dvc/output/__init__.py

@@ -2,19 +2,22 @@
 
 from voluptuous import And, Any, Coerce, Length, Lower, Required, SetTo
 
+from dvc.output.azure import AzureOutput
 from dvc.output.base import BaseOutput
 from dvc.output.gs import GSOutput
 from dvc.output.hdfs import HDFSOutput
 from dvc.output.local import LocalOutput
 from dvc.output.s3 import S3Output
 from dvc.output.ssh import SSHOutput
 from dvc.remote import Remote
+from dvc.remote.azure import AzureRemote
 from dvc.remote.hdfs import HDFSRemote
 from dvc.remote.local import LocalRemote
 from dvc.remote.s3 import S3Remote
 from dvc.scheme import Schemes
 
 OUTS = [
+    AzureOutput,
     HDFSOutput,
     S3Output,
     GSOutput,
@@ -23,6 +26,7 @@
 ]
 
 OUTS_MAP = {
+    Schemes.AZURE: AzureOutput,
     Schemes.HDFS: HDFSOutput,
     Schemes.S3: S3Output,
     Schemes.GS: GSOutput,
@@ -45,6 +49,7 @@
 # so when a few types of outputs share the same name, we only need
 # specify it once.
 CHECKSUMS_SCHEMA = {
+    AzureRemote.PARAM_CHECKSUM: CHECKSUM_SCHEMA,
     LocalRemote.PARAM_CHECKSUM: CHECKSUM_SCHEMA,
     S3Remote.PARAM_CHECKSUM: CHECKSUM_SCHEMA,
     HDFSRemote.PARAM_CHECKSUM: CHECKSUM_SCHEMA,

dvc/output/azure.py

@@ -0,0 +1,6 @@
+from dvc.output.base import BaseOutput
+from dvc.remote.azure import AzureRemote
+
+
+class AzureOutput(BaseOutput):
+    REMOTE = AzureRemote

dvc/remote/azure.py

@@ -81,6 +81,15 @@ def blob_service(self):
             blob_service.create_container(self.path_info.bucket)
         return blob_service
 
+    def get_etag(cls, path_info):
+        etag = self.blob_service.get_blob_properties(
+            path_info.bucket, path_info.path
+        ).properties.etag
+        return etag.strip('"')
+
+    def get_file_checksum(self, path_info):
+        return self.get_etag(path_info)
+
     def remove(self, path_info):
         if path_info.scheme != self.scheme:
             raise NotImplementedError

tests/unit/dependency/test_azure.py

@@ -0,0 +1,7 @@
+from dvc.dependency.azure import AzureDependency
+from tests.unit.dependency.test_local import TestLocalDependency
+
+
+class TestAzureDependency(TestLocalDependency):
+    def _get_cls(self):
+        return AzureDependency

tests/unit/output/test_azure.py

@@ -0,0 +1,7 @@
+from dvc.output.azure import AzureOutput
+from tests.unit.output.test_local import TestLocalOutput
+
+
+class TestAzureOutput(TestLocalOutput):
+    def _get_cls(self):
+        return AzureOutput