Git ingestion part of Milestone 2

tests/test_git_ingestion.py

@@ -0,0 +1,47 @@
+import subprocess
+
+from repo_registry.repo_ingestion.git import GitIngestionService
+
+
+def run(command, cwd):
+    subprocess.run(command, cwd=cwd, check=True, capture_output=True, text=True)
+
+
+def make_git_repo(path):
+    path.mkdir()
+    run(["git", "init", "-b", "main"], path)
+    run(["git", "config", "user.email", "tests@example.com"], path)
+    run(["git", "config", "user.name", "Tests"], path)
+    (path / "README.md").write_text("# Clone Me\n", encoding="utf-8")
+    (path / "app.py").write_text("print('ok')\n", encoding="utf-8")
+    run(["git", "add", "."], path)
+    run(["git", "commit", "-m", "initial"], path)
+
+
+def test_ingestion_keeps_local_paths_local(tmp_path):
+    source = tmp_path / "source"
+    source.mkdir()
+
+    checkout = GitIngestionService(tmp_path / "checkouts").resolve(str(source))
+
+    assert checkout.source_path == source.resolve()
+    assert checkout.was_cloned is False
+
+
+def test_ingestion_clones_file_url(tmp_path):
+    source = tmp_path / "source"
+    make_git_repo(source)
+
+    checkout = GitIngestionService(tmp_path / "checkouts").resolve(source.as_uri())
+
+    assert checkout.was_cloned is True
+    assert checkout.source_path != source.resolve()
+    assert (checkout.source_path / "README.md").exists()
+    branch = subprocess.run(
+        ["git", "branch", "--show-current"],
+        cwd=checkout.source_path,
+        check=True,
+        capture_output=True,
+        text=True,
+    ).stdout.strip()
+    assert branch == "main"

tests/test_registry_service.py

@@ -1,11 +1,14 @@
+import subprocess
+
 from repo_registry.core.service import RegistryService
+from repo_registry.repo_ingestion.git import GitIngestionService
 from repo_registry.storage.sqlite import NotFoundError, RegistryStore
 
 
 def make_service(tmp_path):
     store = RegistryStore(tmp_path / "registry.sqlite3")
     store.initialize()
-    return RegistryService(store)
+    return RegistryService(store, ingestion=GitIngestionService(tmp_path / "checkouts"))
 
 
 def test_manual_registry_builds_ability_map(tmp_path):
@@ -144,3 +147,35 @@ def test_analyze_repository_failure_is_recorded(tmp_path):
     assert summary.snapshot is None
     assert "does not exist" in (summary.analysis_run.error_message or "")
     assert service.get_repository(repository.id).status == "analysis_failed"
+
+
+def test_analyze_repository_clones_git_url_before_scanning(tmp_path):
+    source = tmp_path / "git-source"
+    source.mkdir()
+    subprocess.run(["git", "init", "-b", "main"], cwd=source, check=True)
+    subprocess.run(
+        ["git", "config", "user.email", "tests@example.com"],
+        cwd=source,
+        check=True,
+    )
+    subprocess.run(
+        ["git", "config", "user.name", "Tests"],
+        cwd=source,
+        check=True,
+    )
+    (source / "README.md").write_text("# Git Source\n", encoding="utf-8")
+    (source / "requirements.txt").write_text("pytest\n", encoding="utf-8")
+    subprocess.run(["git", "add", "."], cwd=source, check=True)
+    subprocess.run(["git", "commit", "-m", "initial"], cwd=source, check=True)
+
+    service = make_service(tmp_path)
+    repository = service.register_repository(name="Git Source", url=source.as_uri())
+
+    summary = service.analyze_repository(repository.id)
+
+    assert summary.analysis_run.status == "completed"
+    assert summary.snapshot is not None
+    assert str(tmp_path / "checkouts") in summary.snapshot.source_path
+    fact_names = {(fact.kind, fact.name, fact.path) for fact in summary.facts}
+    assert ("documentation", "README", "README.md") in fact_names
+    assert ("framework", "pytest", "requirements.txt") in fact_names

tests/test_web_api.py

@@ -5,7 +5,10 @@ from repo_registry.web_api.app import Settings, app, get_settings
 
 def test_api_manual_registry_loop(tmp_path):
     def override_settings():
-        return Settings(database_path=str(tmp_path / "api.sqlite3"))
+        return Settings(
+            database_path=str(tmp_path / "api.sqlite3"),
+            checkout_root=str(tmp_path / "checkouts"),
+        )
 
     app.dependency_overrides[get_settings] = override_settings
     client = TestClient(app)
@@ -79,7 +82,10 @@ def test_api_analysis_run_loop(tmp_path):
     )
 
     def override_settings():
-        return Settings(database_path=str(tmp_path / "api-analysis.sqlite3"))
+        return Settings(
+            database_path=str(tmp_path / "api-analysis.sqlite3"),
+            checkout_root=str(tmp_path / "api-checkouts"),
+        )
 
     app.dependency_overrides[get_settings] = override_settings
     client = TestClient(app)