Add smart_open requirement, update deprecated options (#11864)

* Switch from deprecated `ignore_ext` to `compression`
* Add upload/download test for local files

requirements.txt

@@ -11,6 +11,7 @@ srsly>=2.4.3,<3.0.0
 catalogue>=2.0.6,<2.1.0
 typer>=0.3.0,<0.8.0
 pathy>=0.3.5
+smart-open>=5.2.1,<7.0.0
 # Third party dependencies
 numpy>=1.15.0
 requests>=2.13.0,<3.0.0

setup.cfg

@@ -53,6 +53,7 @@ install_requires =
     # Third-party dependencies
     typer>=0.3.0,<0.8.0
     pathy>=0.3.5
+    smart-open>=5.2.1,<7.0.0
     tqdm>=4.38.0,<5.0.0
     numpy>=1.15.0
     requests>=2.13.0,<3.0.0

spacy/cli/_util.py

@@ -358,7 +358,7 @@ def download_file(src: Union[str, "Pathy"], dest: Path, *, force: bool = False)
     if dest.exists() and not force:
         return None
     src = str(src)
-    with smart_open.open(src, mode="rb", ignore_ext=True) as input_file:
+    with smart_open.open(src, mode="rb", compression="disable") as input_file:
         with dest.open(mode="wb") as output_file:
             shutil.copyfileobj(input_file, output_file)
 

spacy/tests/test_cli.py

@@ -17,6 +17,7 @@ from spacy.cli._util import is_subpath_of, load_project_config
 from spacy.cli._util import parse_config_overrides, string_to_list
 from spacy.cli._util import substitute_project_variables
 from spacy.cli._util import validate_project_commands
+from spacy.cli._util import upload_file, download_file
 from spacy.cli.debug_data import _compile_gold, _get_labels_from_model
 from spacy.cli.debug_data import _get_labels_from_spancat
 from spacy.cli.debug_data import _get_distribution, _get_kl_divergence
@@ -1014,3 +1015,18 @@ def test_project_check_requirements(reqs, output):
         pkg_resources.require("spacyunknowndoesnotexist12345")
     except pkg_resources.DistributionNotFound:
         assert output == _check_requirements([req.strip() for req in reqs.split("\n")])
+
+
+def test_upload_download_local_file():
+    with make_tempdir() as d1, make_tempdir() as d2:
+        filename = "f.txt"
+        content = "content"
+        local_file = d1 / filename
+        remote_file = d2 / filename
+        with local_file.open(mode="w") as file_:
+            file_.write(content)
+        upload_file(local_file, remote_file)
+        local_file.unlink()
+        download_file(remote_file, local_file)
+        with local_file.open(mode="r") as file_:
+            assert file_.read() == content