Add tests for projects to master (#12303)

* Add tests for projects to master

* Fix git clone related issues on Windows

* Add stat import

spacy/tests/test_cli_app.py

@@ -1,5 +1,7 @@
 import os
 from pathlib import Path
+import pytest
+import srsly
 from typer.testing import CliRunner
 from spacy.tokens import DocBin, Doc
 
@@ -89,3 +91,138 @@ def test_debug_data_trainable_lemmatizer_cli(en_vocab):
         # Instead of checking specific wording of the output, which may change,
         # we'll check that this section of the debug output is present.
         assert "= Trainable Lemmatizer =" in result_debug_data.stdout
+
+
+# project tests
+
+SAMPLE_PROJECT = {
+    "title": "Sample project",
+    "description": "This is a project for testing",
+    "assets": [
+        {
+            "dest": "assets/spacy-readme.md",
+            "url": "https://github.com/explosion/spaCy/raw/dec81508d28b47f09a06203c472b37f00db6c869/README.md",
+            "checksum": "411b2c89ccf34288fae8ed126bf652f7",
+        },
+        {
+            "dest": "assets/citation.cff",
+            "url": "https://github.com/explosion/spaCy/raw/master/CITATION.cff",
+            "checksum": "c996bfd80202d480eb2e592369714e5e",
+            "extra": True,
+        },
+    ],
+    "commands": [
+        {
+            "name": "ok",
+            "help": "print ok",
+            "script": ["python -c \"print('okokok')\""],
+        },
+        {
+            "name": "create",
+            "help": "make a file",
+            "script": ["touch abc.txt"],
+            "outputs": ["abc.txt"],
+        },
+        {
+            "name": "clean",
+            "help": "remove test file",
+            "script": ["rm abc.txt"],
+        },
+    ],
+}
+
+SAMPLE_PROJECT_TEXT = srsly.yaml_dumps(SAMPLE_PROJECT)
+
+
+@pytest.fixture
+def project_dir():
+    with make_tempdir() as pdir:
+        (pdir / "project.yml").write_text(SAMPLE_PROJECT_TEXT)
+        yield pdir
+
+
+def test_project_document(project_dir):
+    readme_path = project_dir / "README.md"
+    assert not readme_path.exists(), "README already exists"
+    result = CliRunner().invoke(
+        app, ["project", "document", str(project_dir), "-o", str(readme_path)]
+    )
+    assert result.exit_code == 0
+    assert readme_path.is_file()
+    text = readme_path.read_text("utf-8")
+    assert SAMPLE_PROJECT["description"] in text
+
+
+def test_project_assets(project_dir):
+    asset_dir = project_dir / "assets"
+    assert not asset_dir.exists(), "Assets dir is already present"
+    result = CliRunner().invoke(app, ["project", "assets", str(project_dir)])
+    assert result.exit_code == 0
+    assert (asset_dir / "spacy-readme.md").is_file(), "Assets not downloaded"
+    # check that extras work
+    result = CliRunner().invoke(app, ["project", "assets", "--extra", str(project_dir)])
+    assert result.exit_code == 0
+    assert (asset_dir / "citation.cff").is_file(), "Extras not downloaded"
+
+
+def test_project_run(project_dir):
+    # make sure dry run works
+    test_file = project_dir / "abc.txt"
+    result = CliRunner().invoke(
+        app, ["project", "run", "--dry", "create", str(project_dir)]
+    )
+    assert result.exit_code == 0
+    assert not test_file.is_file()
+    result = CliRunner().invoke(app, ["project", "run", "create", str(project_dir)])
+    assert result.exit_code == 0
+    assert test_file.is_file()
+    result = CliRunner().invoke(app, ["project", "run", "ok", str(project_dir)])
+    assert result.exit_code == 0
+    assert "okokok" in result.stdout
+
+
+@pytest.mark.parametrize(
+    "options",
+    [
+        "",
+        # "--sparse",
+        "--branch v3",
+        "--repo https://github.com/explosion/projects --branch v3",
+    ],
+)
+def test_project_clone(options):
+    with make_tempdir() as workspace:
+        out = workspace / "project"
+        target = "benchmarks/ner_conll03"
+        if not options:
+            options = []
+        else:
+            options = options.split()
+        result = CliRunner().invoke(
+            app, ["project", "clone", target, *options, str(out)]
+        )
+        assert result.exit_code == 0
+        assert (out / "README.md").is_file()
+
+
+def test_project_push_pull(project_dir):
+    proj = dict(SAMPLE_PROJECT)
+    remote = "xyz"
+
+    with make_tempdir() as remote_dir:
+        proj["remotes"] = {remote: str(remote_dir)}
+        proj_text = srsly.yaml_dumps(proj)
+        (project_dir / "project.yml").write_text(proj_text)
+
+        test_file = project_dir / "abc.txt"
+        result = CliRunner().invoke(app, ["project", "run", "create", str(project_dir)])
+        assert result.exit_code == 0
+        assert test_file.is_file()
+        result = CliRunner().invoke(app, ["project", "push", remote, str(project_dir)])
+        assert result.exit_code == 0
+        result = CliRunner().invoke(app, ["project", "run", "clean", str(project_dir)])
+        assert result.exit_code == 0
+        assert not test_file.exists()
+        result = CliRunner().invoke(app, ["project", "pull", remote, str(project_dir)])
+        assert result.exit_code == 0
+        assert test_file.is_file()

spacy/util.py

@@ -32,6 +32,7 @@ import inspect
 import pkgutil
 import logging
 import socket
+import stat
 
 try:
     import cupy.random
@@ -1050,8 +1051,15 @@ def make_tempdir() -> Generator[Path, None, None]:
     """
     d = Path(tempfile.mkdtemp())
     yield d
+
+    # On Windows, git clones use read-only files, which cause permission errors
+    # when being deleted. This forcibly fixes permissions.
+    def force_remove(rmfunc, path, ex):
+        os.chmod(path, stat.S_IWRITE)
+        rmfunc(path)
+
     try:
-        shutil.rmtree(str(d))
+        shutil.rmtree(str(d), onerror=force_remove)
     except PermissionError as e:
         warnings.warn(Warnings.W091.format(dir=d, msg=e))