Support fetching a file from a git repo as an asset

spacy/cli/_util.py

@@ -1,3 +1,4 @@
+from tempfile import TemporaryDirectory
 from typing import Dict, Any, Union, List, Optional, Tuple, Iterable
 from typing import TYPE_CHECKING, overload
 import sys
@@ -405,16 +406,20 @@ def git_checkout(
             f"temporarily. To only download the files needed, make sure "
             f"you're using Git v2.22 or above."
         )
-    with make_tempdir() as tmp_dir:
-        cmd = f"git -C {tmp_dir} clone {repo} . -b {branch}"
+    with TemporaryDirectory() as tmp_dir:
+        tmp_path = Path(tmp_dir)
+        cmd = f"git -C {tmp_path} clone {repo} . -b {branch}"
         run_command(cmd, capture=True)
         # We need Path(name) to make sure we also support subdirectories
         try:
-            source_path = tmp_dir / Path(subpath)
-            if not is_subpath_of(tmp_dir, source_path):
+            source_path = tmp_path / Path(subpath)
+            if not is_subpath_of(tmp_path, source_path):
                 err = f"'{subpath}' is a path outside of the cloned repository."
                 msg.fail(err, repo, exits=1)
-            shutil.copytree(str(source_path), str(dest))
+            if os.path.isdir(source_path):
+                shutil.copytree(source_path, dest)
+            else:
+                shutil.copyfile(source_path, dest)
         except FileNotFoundError:
             err = f"Can't clone {subpath}. Make sure the directory exists in the repo (branch '{branch}')"
             msg.fail(err, repo, exits=1)

spacy/tests/test_cli.py

@@ -1,6 +1,7 @@
 import os
 import math
 from collections import Counter
+from tempfile import TemporaryDirectory
 from typing import Tuple, List, Dict, Any
 import pkg_resources
 import time
@@ -20,7 +21,7 @@
 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._util import upload_file, download_file, git_checkout
 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
@@ -145,6 +146,33 @@ def test_issue11235():
     assert cfg["commands"][0]["script"][0] == f"hello {lang_var}"
 
 
+def test_project_git_dir_asset():
+    with TemporaryDirectory() as d:
+        p = Path(d)
+        # Use a very small repo.
+        git_checkout(
+            "https://github.com/explosion/os-signpost.git",
+            "os_signpost",
+            p / "signpost",
+            branch="v0.0.3",
+        )
+        assert os.path.isdir(p / "signpost")
+
+
+@pytest.mark.issue(12168)
+def test_project_git_file_asset():
+    with TemporaryDirectory() as d:
+        p = Path(d)
+        # Use a very small repo.
+        git_checkout(
+            "https://github.com/explosion/os-signpost.git",
+            "README.md",
+            p / "readme.md",
+            branch="v0.0.3",
+        )
+        assert os.path.isfile(p / "readme.md")
+
+
 def test_cli_info():
     nlp = Dutch()
     nlp.add_pipe("textcat")