New blob_properties transport parameter for GCS (#632)

* Pass properties to set on GCS blob.

Example:
```
smart_open.open("gs://somewhere/somefile.json.gz", transport_params={
  "blob_properties": {
    "content_type": "application/json",
    "content_encoding": "gzip"
  }
}
```

* Update CHANGELOG.md

Co-authored-by: Michael Penkov <misha.penkov@gmail.com>
Co-authored-by: Michael Penkov <m@penkov.dev>

CHANGELOG.md

@@ -2,6 +2,7 @@
 
 - Work around changes to `urllib.parse.urlsplit` (PR [#633](https://github.com/RaRe-Technologies/smart_open/pull/633), [@judahrand](https://github.com/judahrand)
 - Change python_requires version to fix PEP 440 issue (PR [#639](https://github.com/RaRe-Technologies/smart_open/pull/639), [@lucasvieirasilva](https://github.com/lucasvieirasilva))
+- New blob_properties transport parameter for GCS (PR [#632](https://github.com/RaRe-Technologies/smart_open/pull/632), [@FHTheron](https://github.com/FHTheron))
 
 # 5.1.0, 25 May 2021
 

smart_open/gcs.py

@@ -112,6 +112,7 @@ def open(
         buffer_size=DEFAULT_BUFFER_SIZE,
         min_part_size=_MIN_MIN_PART_SIZE,
         client=None,  # type: google.cloud.storage.Client
+        blob_properties=None
         ):
     """Open an GCS blob for reading or writing.
 
@@ -129,6 +130,8 @@ def open(
         The minimum part size for multipart uploads.  For writing only.
     client: google.cloud.storage.Client, optional
         The GCS client to use when working with google-cloud-storage.
+    blob_properties: dict, optional
+        Set properties on blob before writing.  For writing only.
 
     """
     if mode == constants.READ_BINARY:
@@ -145,6 +148,7 @@ def open(
             blob_id,
             min_part_size=min_part_size,
             client=client,
+            blob_properties=blob_properties,
         )
     else:
         raise NotImplementedError('GCS support for mode %r not implemented' % mode)
@@ -396,6 +400,7 @@ def __init__(
             blob,
             min_part_size=_DEFAULT_MIN_PART_SIZE,
             client=None,  # type: google.cloud.storage.Client
+            blob_properties=None,
     ):
         if client is None:
             client = google.cloud.storage.Client()
@@ -412,6 +417,10 @@ def __init__(
 
         self._session = google.auth.transport.requests.AuthorizedSession(client._credentials)
 
+        if blob_properties:
+            for k, v in blob_properties.items():
+                setattr(self._blob, k, v)
+
         #
         # https://cloud.google.com/storage/docs/json_api/v1/how-tos/resumable-upload#start-resumable
         #

smart_open/tests/test_gcs.py

@@ -801,6 +801,18 @@ def test_write_04(self):
 
         self.assertEqual(output, [])
 
+    def test_write_05(self):
+        """Do blob_properties get applied?"""
+        smart_open_write = smart_open.gcs.Writer(BUCKET_NAME, WRITE_BLOB_NAME,
+            blob_properties={
+                "content_type": "random/x-test",
+                "content_encoding": "coded"
+            }
+        )
+        with smart_open_write as fout:  # noqa
+            assert fout._blob.content_type == "random/x-test"
+            assert fout._blob.content_encoding == "coded"
+
     def test_gzip(self):
         expected = u'а не спеть ли мне песню... о любви'.encode('utf-8')
         with smart_open.gcs.Writer(BUCKET_NAME, WRITE_BLOB_NAME) as fout: