Add stricter filtering and tests for cli data directory discovery (#910)

* Add stricter filtering and tests for cli data directory discovery

* Semver

* Ignore ruff on error type

* Format

* Fix for windows paths

* Fix for windows paths

* Uncomment blob tests

* Sort by timestamp name instead of modified date

* Format

* Add additional folder name test

.semversioner/next-release/patch-20240812232353903544.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "Improves filtering for data dir inferring"
+}

graphrag/query/cli.py

@@ -4,7 +4,7 @@
 """Command line interface for the query module."""
 
 import asyncio
-import os
+import re
 from pathlib import Path
 from typing import cast
 
@@ -129,7 +129,9 @@ def _infer_data_dir(root: str) -> str:
     output = Path(root) / "output"
     # use the latest data-run folder
     if output.exists():
-        folders = sorted(output.iterdir(), key=os.path.getmtime, reverse=True)
+        expr = re.compile(r"\d{8}-\d{6}")
+        filtered = [f for f in output.iterdir() if f.is_dir() and expr.match(f.name)]
+        folders = sorted(filtered, key=lambda f: f.name, reverse=True)
         if len(folders) > 0:
             folder = folders[0]
             return str((folder / "artifacts").absolute())

tests/unit/query/__init__.py

@@ -0,0 +1,2 @@
+# Copyright (c) 2024 Microsoft Corporation.
+# Licensed under the MIT License

tests/unit/query/test_infer_data_dir.py

@@ -0,0 +1,32 @@
+# Copyright (c) 2024 Microsoft Corporation.
+# Licensed under the MIT License
+from pathlib import Path
+
+import pytest
+
+from graphrag.query.cli import _infer_data_dir
+
+
+def test_infer_data_dir():
+    root = "./tests/unit/query/data/defaults"
+    result = Path(_infer_data_dir(root))
+    assert result.parts[-2] == "20240812-121000"
+
+
+def test_infer_data_dir_ignores_hidden_files():
+    """A hidden file, starting with '.', will naturally be selected as latest data directory."""
+    root = "./tests/unit/query/data/hidden"
+    result = Path(_infer_data_dir(root))
+    assert result.parts[-2] == "20240812-121000"
+
+
+def test_infer_data_dir_ignores_non_numeric():
+    root = "./tests/unit/query/data/non-numeric"
+    result = Path(_infer_data_dir(root))
+    assert result.parts[-2] == "20240812-121000"
+
+
+def test_infer_data_dir_throws_on_no_match():
+    root = "./tests/unit/query/data/empty"
+    with pytest.raises(ValueError):  # noqa PT011 (this is what is actually thrown...)
+        _infer_data_dir(root)