Ignore parsing hidden files on kedro viz --lite

RELEASE.md

@@ -16,6 +16,7 @@ Please follow the established format:
 
 - Add ESM bundle for Kedro-Viz. (#2268)
 - Fix `%run_viz` using old process in jupyter notebook. (#2267)
+- Ignore parsing hidden files on `kedro viz --lite`. (#2271)
 - Make Kedro-Viz compatible with the new `KedroDataCatalog`. (#2274)
 
 ## Community contributions

package/kedro_viz/autoreload_file_filter.py

@@ -10,6 +10,8 @@
 from pathspec import GitIgnoreSpec
 from watchfiles import Change, DefaultFilter
 
+from kedro_viz.utils import load_gitignore_patterns
+
 logger = logging.getLogger(__name__)
 
 
@@ -35,15 +37,7 @@ def __init__(self, base_path: Optional[Path] = None):
         super().__init__()
 
         # Load .gitignore patterns
-        gitignore_path = self.cwd / ".gitignore"
-        try:
-            with open(gitignore_path, "r", encoding="utf-8") as gitignore_file:
-                ignore_patterns = gitignore_file.read().splitlines()
-            self.gitignore_spec: Optional[GitIgnoreSpec] = GitIgnoreSpec.from_lines(
-                "gitwildmatch", ignore_patterns
-            )
-        except FileNotFoundError:
-            self.gitignore_spec = None
+        self.gitignore_spec = load_gitignore_patterns(self.cwd)
 
     def __call__(self, change: Change, path: str) -> bool:
         """

package/kedro_viz/integrations/kedro/lite_parser.py

@@ -7,6 +7,8 @@
 from typing import Dict, List, Set, Union
 from unittest.mock import MagicMock
 
+from kedro_viz.utils import Spinner, is_file_ignored, load_gitignore_patterns
+
 logger = logging.getLogger(__name__)
 
 
@@ -232,14 +234,22 @@ def parse(self, target_path: Path) -> Union[Dict[str, Set[str]], None]:
         Returns:
             A dictionary of file(s) in the target path and a set of module names
         """
+        spinner = Spinner("Processing your project files...")
+        spinner.start()
 
         if not target_path.exists():
             logger.warning("Path `%s` does not exist", str(target_path))
             return None
 
         unresolved_imports: Dict[str, Set[str]] = {}
 
+        # Load .gitignore patterns
+        gitignore_spec = load_gitignore_patterns(target_path)
+
         if target_path.is_file():
+            if is_file_ignored(target_path):
+                return unresolved_imports
+
             try:
                 missing_dependencies = self._get_unresolved_imports(target_path)
                 if len(missing_dependencies) > 0:
@@ -254,7 +264,11 @@ def parse(self, target_path: Path) -> Union[Dict[str, Set[str]], None]:
             return unresolved_imports
 
         # handling directories
-        _project_file_paths = set(target_path.rglob("*.py"))
+        _project_file_paths = set(
+            file_path
+            for file_path in target_path.rglob("*.py")
+            if not is_file_ignored(file_path, target_path, gitignore_spec)
+        )
 
         for file_path in _project_file_paths:
             try:
@@ -270,11 +284,12 @@ def parse(self, target_path: Path) -> Union[Dict[str, Set[str]], None]:
                 if len(missing_dependencies) > 0:
                     unresolved_imports[str(file_path)] = missing_dependencies
             except Exception as exc:  # noqa: BLE001 # pragma: no cover
-                logger.error(
-                    "An error occurred in LiteParser while mocking dependencies in %s : %s",
+                logger.warning(
+                    "An issue occurred in LiteParser while mocking dependencies in %s : %s",
                     file_path,
                     exc,
                 )
                 continue
 
+        spinner.stop()
         return unresolved_imports

package/kedro_viz/utils.py

@@ -5,7 +5,10 @@
 import threading
 import time
 from itertools import cycle
-from typing import Any, Tuple
+from pathlib import Path
+from typing import Any, Optional, Tuple
+
+from pathspec import GitIgnoreSpec
 
 TRANSCODING_SEPARATOR = "@"
 
@@ -63,6 +66,36 @@ def is_dataset_param(dataset_name: str) -> bool:
     return dataset_name.lower().startswith("params:") or dataset_name == "parameters"
 
 
+def load_gitignore_patterns(project_path: Path) -> Optional[GitIgnoreSpec]:
+    """Loads gitignore spec to detect ignored files"""
+    gitignore_path = project_path / ".gitignore"
+
+    if not gitignore_path.exists():
+        return None
+
+    with open(gitignore_path, "r", encoding="utf-8") as gitignore_file:
+        ignore_patterns = gitignore_file.read().splitlines()
+        gitignore_spec = GitIgnoreSpec.from_lines("gitwildmatch", ignore_patterns)
+        return gitignore_spec
+
+
+def is_file_ignored(
+    file_path: Path,
+    project_path: Optional[Path] = None,
+    gitignore_spec: Optional[GitIgnoreSpec] = None,
+) -> bool:
+    """Returns True if the file should be ignored."""
+    if file_path.name.startswith("."):  # Ignore hidden files/folders
+        return True
+    if (
+        gitignore_spec
+        and project_path
+        and gitignore_spec.match_file(str(file_path.relative_to(project_path)))
+    ):
+        return True
+    return False
+
+
 def merge_dicts(dict_one: dict[str, Any], dict_two: dict[str, Any]) -> dict[str, Any]:
     """Utility to merge two dictionaries"""
     import copy

package/tests/test_integrations/test_lite_parser.py

@@ -11,17 +11,34 @@ def sample_project_path(tmp_path):
     # Create a sample directory structure
     package_dir = tmp_path / "mock_spaceflights"
     package_dir.mkdir()
+
+    venv_dir = package_dir / ".venv"
+    venv_dir.mkdir()
+
     (package_dir / "__init__.py").touch()
     (package_dir / "__init__.py").write_text(
         "from mock_spaceflights import data_processing\n"
         "from mock_spaceflights.data_processing import create_metrics"
     )
+    (package_dir / ".test_hidden.py").write_text(
+        "import os\n"
+        "import nonexistentmodule\n"
+        "from . import test\n"
+        "from typing import Dict"
+    )
+    (venv_dir / "test_venv.py").write_text(
+        "import os\n"
+        "import nonexistentmodule\n"
+        "from . import test\n"
+        "from typing import Dict"
+    )
     (package_dir / "data_processing.py").write_text(
         "import os\n"
         "import nonexistentmodule\n"
         "from . import test\n"
         "from typing import Dict"
     )
+    (package_dir / ".gitignore").write_text("venv\n" ".venv")
     return tmp_path
 
 
@@ -173,6 +190,12 @@ def test_parse_non_existent_path(self, lite_parser):
         assert not lite_parser.parse(Path("non/existent/path"))
         assert not lite_parser.parse(Path("non/existent/path/file.py"))
 
+    def test_parse_hidden_file_path(self, lite_parser, sample_project_path):
+        file_path = Path(sample_project_path / "mock_spaceflights/.test_hidden.py")
+
+        unresolved_imports = lite_parser.parse(file_path)
+        assert unresolved_imports == {}
+
     def test_file_parse(self, lite_parser, sample_project_path):
         file_path = Path(sample_project_path / "mock_spaceflights/data_processing.py")
         unresolved_imports = lite_parser.parse(file_path)
@@ -199,7 +222,9 @@ def test_parse_logs_error_on_exception(self, lite_parser, tmp_path, caplog):
         )
 
     def test_directory_parse(self, lite_parser, sample_project_path):
-        unresolved_imports = lite_parser.parse(sample_project_path)
+        unresolved_imports = lite_parser.parse(
+            sample_project_path / "mock_spaceflights"
+        )
         expected_file_path = Path(
             sample_project_path / "mock_spaceflights/data_processing.py"
         )