Add md5 hash property to GSPath (#483)

HISTORY.md

@@ -3,6 +3,7 @@
 ## Unreleased
 
 - Fixed `CloudPath(...) / other` to correctly attempt to fall back on `other`'s `__rtruediv__` implementation, in order to support classes that explicitly support the `/` with a `CloudPath` instance. Previously, this would always raise a `TypeError` if `other` were not a `str` or `PurePosixPath`. (PR [#479](https://github.com/drivendataorg/cloudpathlib/pull/479))
+- Add `md5` property to `GSPath`, updated LocalGSPath to include `md5` property, updated mock_gs.MockBlob to include `md5_hash` property.
 - Fixed an uncaught exception on Azure Gen2 storage accounts with HNS enabled when used with `DefaultAzureCredential`. (Issue [#486](https://github.com/drivendataorg/cloudpathlib/issues/486))
 
 ## v0.20.0 (2024-10-18)

README.md

@@ -205,7 +205,7 @@ Most methods and properties from `pathlib.Path` are supported except for the one
 | `bucket`               | ❌                | ✅         | ✅         |
 | `container`            | ✅                | ❌         | ❌         |
 | `key`                  | ❌                | ✅         | ❌         |
-| `md5`                  | ✅                | ❌         | ❌         |
+| `md5`                  | ✅                | ❌         | ✅         |
 
 ----
 

cloudpathlib/gs/gsclient.py

@@ -121,6 +121,7 @@ def _get_metadata(self, cloud_path: GSPath) -> Optional[Dict[str, Any]]:
                 "size": blob.size,
                 "updated": blob.updated,
                 "content_type": blob.content_type,
+                "md5_hash": blob.md5_hash,
             }
 
     def _download_file(self, cloud_path: GSPath, local_path: Union[str, os.PathLike]) -> Path:

cloudpathlib/gs/gspath.py

@@ -1,7 +1,7 @@
 import os
 from pathlib import Path
 from tempfile import TemporaryDirectory
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Optional
 
 from ..cloudpath import CloudPath, NoStatError, register_path_class
 
@@ -95,3 +95,10 @@
     @property
     def etag(self):
         return self.client._get_metadata(self).get("etag")
+
+    @property
+    def md5(self) -> Optional[str]:
+        meta = self.client._get_metadata(self)
+        if not meta:
+            return None
+        return meta.get("md5_hash", None)

cloudpathlib/local/implementations/gs.py

@@ -53,6 +53,10 @@
     def etag(self):
         return self.client._md5(self)
 
+    @property
+    def md5(self) -> str:
+        return self.client._md5(self)
+
 
 LocalGSPath.__name__ = "GSPath"
 

tests/mock_clients/mock_gs.py

@@ -1,4 +1,5 @@
 from datetime import datetime, timedelta
+import os
 from pathlib import Path, PurePosixPath
 import shutil
 from tempfile import TemporaryDirectory
@@ -95,6 +96,10 @@ def upload_from_filename(self, filename, content_type=None):
     def etag(self):
         return "etag"
 
+    @property
+    def md5_hash(self):
+        return os.environ.get("MOCK_EXPECTED_MD5_HASH", "md5_hash")
+
     @property
     def size(self):
         path = self.bucket / self.name

tests/test_gs_specific.py

@@ -49,3 +49,29 @@ def test_as_url(gs_rig):
     assert "X-Goog-Date" in query_params
     assert "X-Goog-SignedHeaders" in query_params
     assert "X-Goog-Signature" in query_params
+
+
+@pytest.mark.parametrize(
+    "contents",
+    [
+        "hello world",
+        "another test case",
+    ],
+)
+def test_md5_property(contents, gs_rig, monkeypatch):
+    def _calculate_b64_wrapped_md5_hash(contents: str) -> str:
+        # https://cloud.google.com/storage/docs/json_api/v1/objects
+        from base64 import b64encode
+        from hashlib import md5
+
+        contents_md5_bytes = md5(contents.encode()).digest()
+        b64string = b64encode(contents_md5_bytes).decode()
+        return b64string
+
+    # if USE_LIVE_CLOUD this doesnt have any effect
+    expected_hash = _calculate_b64_wrapped_md5_hash(contents)
+    monkeypatch.setenv("MOCK_EXPECTED_MD5_HASH", expected_hash)
+
+    p: GSPath = gs_rig.create_cloud_path("dir_0/file0_0.txt")
+    p.write_text(contents)
+    assert p.md5 == expected_hash