Add Gitleaks Pre-Commit Automation

.github/workflows/pre-commit.yaml

@@ -0,0 +1,23 @@
+# .github/workflows/pre-commit.yml
+name: Pre-commit
+
+on:
+  pull_request:
+    branches: ['**']
+  push:
+    branches: ['**']
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+
+    steps:
+        - name: Checkout Repository
+          uses: actions/checkout@v4
+
+        - name: Set up Python
+          uses: actions/setup-python@v5
+          with:
+            python-version: '3.12'
+
+        - uses: pre-commit/action@v3.0.0

.github/workflows/python-app.yml → .github/workflows/python-app.yaml

@@ -21,12 +21,12 @@ jobs:
     steps:
     - name: Checkout Repository
       uses: actions/checkout@v4
-      
+
     - name: Install uv
       uses: astral-sh/setup-uv@v6
-   
+
     - name: Sync dependencies
       run: uv sync --all-extras
-   
+
     - name: Run tests
       run: uv run pytest

.gitignore

@@ -182,9 +182,9 @@ cython_debug/
 .abstra/
 
 # Visual Studio Code
-#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
 #  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
-#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  and can be added to the global gitignore or merged into this file. However, if you prefer,
 #  you could uncomment the following to ignore the entire vscode folder
 # .vscode/
 

.pre-commit-config.yaml

@@ -0,0 +1,24 @@
+repos:
+  # housekeeping 🧹
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+        args: ['--maxkb=500']
+
+  # make code pretty 💄
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.3.0
+    hooks:
+      - id: ruff
+        args: [ --fix ]
+      - id: ruff-format
+
+  # scanning for leaked secrets ㊙️
+  - repo: https://github.com/gitleaks/gitleaks
+    rev: v8.18.2
+    hooks:
+      - id: gitleaks

.vscode/extensions.json

@@ -0,0 +1,8 @@
+{
+  "recommendations": [
+    "ms-python.python",
+    "charliermarsh.ruff",
+    "ms-python.pylint"
+  ],
+  "unwantedRecommendations": []
+}

.vscode/settings.json

@@ -0,0 +1,20 @@
+{
+  "[python]": {
+    "editor.defaultFormatter": "charliermarsh.ruff",
+    "editor.formatOnSave": true,
+    "editor.codeActionsOnSave": {
+      "source.organizeImports": "explicit",
+      "source.fixAll.ruff": "explicit"
+    }
+  },
+  "python.testing.pytestArgs": [
+    "tests"
+  ],
+  "python.testing.unittestEnabled": false,
+  "python.testing.pytestEnabled": true,
+  "files.exclude": {
+    "**/.mypy_cache": true,
+    "**/.pytest_cache": true,
+    "**/.ruff_cache": true
+  }
+}

ruff.toml

@@ -45,7 +45,7 @@ select = [ # https://docs.astral.sh/ruff/rules/
     "W",   # PyCodeStyle Warnings
     "ANN", # flake8-annotations
     "B",   # flake8-bugbear
-    "TC",  # flake8-type-checking
+    "TCH",  # flake8-type-checking
     "PTH", # flake8-use-pathlib
     "NPY", # NumPy specific rules
     "TID", # flake8-tidy-imports

src/seaclips/collate.py

@@ -4,7 +4,7 @@
 # Licensed under the Apache License 2.0. See LICENSE file.
 
 from dataclasses import dataclass
-from typing import Any
+from typing import Any, Union
 
 import numpy as np
 import torch
@@ -39,7 +39,7 @@ class SeaClipsBatch:
         image_infos: List of image metadata dictionaries
         annotations: List of lists of annotation dictionaries
         video_infos: List of video metadata dictionaries
-        reference_frames: (optional) BatchedReferenceFrames instance for reference frames
+        reference_frames: (optional) BatchedReferenceFrames instance for ref frames
     """
 
     images: torch.Tensor
@@ -60,7 +60,7 @@ def seaclips_collate_fn(batch: list[SeaClipsSample]) -> SeaClipsBatch:
         batch: List of samples from SeaClipsDataset.__getitem__
 
     Returns:
-        SeaClipsBatch: Batched data structure containing images, annotations, and metadata.
+        SeaClipsBatch: Batched data structure containing images, annotations & metadata.
 
     Example:
         >>> from torch.utils.data import DataLoader
@@ -161,7 +161,7 @@ def _collate_reference_frames(
 
 
 def _get_image_tensor(
-    image: Any, target_size: tuple[int, int] | None = None
+    image: Union[Image.Image, torch.Tensor], target_size: tuple[int, int] | None = None
 ) -> torch.Tensor:
     if isinstance(image, Image.Image):
         image_array = np.array(image)
@@ -175,7 +175,7 @@ def _get_image_tensor(
         return image_tensor
 
     # --- 2. Pad to fixed size ---
-    C, H, W = image_tensor.shape
+    _, H, W = image_tensor.shape
     target_h, target_w = target_size
 
     if target_h < H or target_w < W:

src/seaclips/dataset.py

@@ -91,14 +91,14 @@ def _load_metadata(self) -> None:
             self.videos_idx = {}
             return
 
-        with open(self.config.annotation_path, encoding="utf-8") as f:
+        with open(self.config.annotation_path, encoding="utf-8") as f:  # noqa: PTH123
             data = json.load(f)
 
         self.videos_data = data["videos"]
         self.videos_idx = {vid["id"]: vid for vid in self.videos_data}
 
     def _build_video_frame_index(self) -> None:
-        """Build index mapping video_id to sorted list of (frame_id, image_id, idx) tuples."""
+        """Build index mapping video_id -> sorted list w (frame_id,image_id,idx)."""
         self.video_frames_idx = {}
 
         for idx, img_id in enumerate(self.image_ids):
@@ -138,7 +138,8 @@ def __getitem__(self, idx: int) -> SeaClipsSample:
                 - image_info: Image metadata (id, video_id, frame_id, etc.)
                 - annotations: List of annotation dictionaries with parsed fields
                 - video_info: Video metadata for this frame
-                - reference_frames: List of ReferenceFrame if load_reference_frames=True else None.
+                - reference_frames: List of ReferenceFrame if load_reference_frames=True
+                    else None.
         """
         if idx >= len(self):
             raise IndexError(
@@ -198,7 +199,8 @@ def _get_reference_frames(
 
         if current_pos is None:
             raise ValueError(
-                f"Current index {current_idx} not found in video frames for video_id {video_id}"
+                f"Current index {current_idx} not found in video \
+                frames for video_id {video_id}"
             )
 
         for offset in self.config.ref_frame_range:
@@ -207,7 +209,7 @@ def _get_reference_frames(
             # Check if reference frame exists
             if not (0 <= ref_pos < len(video_frames)):
                 ref_pos = current_pos  # Use current frame if out of bounds
-                offset = 0
+                offset = 0  # noqa: PLW2901
 
             _, ref_img_id, _ = video_frames[ref_pos]
 
@@ -300,7 +302,7 @@ def filter_by_metadata(
         """Filter images by metadata attributes.
 
         Args:
-            weather: Filter by weather condition ("sunny", "overcast", "cloudy", "rainy")
+            weather: Filter by weather ("sunny", "overcast", "cloudy", "rainy")
             sea_state: Filter by sea state ("smooth", "wavy")
             camera_sensor: Filter by camera sensor type ("e-CAM", "Axis", "FLIR")
             water_reflections: Filter by water reflections presence ("yes", "no")

src/seaclips/visualization.py

@@ -5,9 +5,9 @@
 
 import random
 
-import matplotlib.patches as patches
 import matplotlib.pyplot as plt
 import numpy as np
+from matplotlib import patches
 from matplotlib.figure import Figure
 from PIL import Image
 
@@ -145,7 +145,7 @@ def show_sample(
 
         return fig
 
-    def show_sample_with_references(
+    def show_sample_with_references(  # noqa: PLR0914
         self,
         idx: int,
         show_labels: bool = True,
@@ -218,7 +218,7 @@ def show_sample_with_references(
                     spine.set_linewidth(3)
                     spine.set_visible(True)
 
-        for idx in range(n_frames, len(axes)):
+        for idx in range(n_frames, len(axes)):  # noqa: PLR1704
             axes[idx].axis("off")
 
         video_info = self.dataset.videos_idx[sample.video_info["id"]]
@@ -266,7 +266,7 @@ def show_video_sequence(
             axes = np.array([axes])
         axes = axes.flatten()
 
-        for idx, (frame, ax) in enumerate(zip(frames_to_show, axes)):
+        for _, (frame, ax) in enumerate(zip(frames_to_show, axes)):
             image = frame.image
             annotations = frame.annotations
             img_info = frame.image_info
@@ -330,7 +330,7 @@ def show_grid(
         return fig
 
 
-def show_sample(dataset: SeaClipsDataset, idx: int, **kwargs) -> Figure:
+def show_sample(dataset: SeaClipsDataset, idx: int, **kwargs) -> Figure:  # noqa: ANN003
     """Convenience function to visualize a sample.
 
     Args:

tests/conftest.py

@@ -5,7 +5,6 @@
 
 import pytest
 from PIL import Image
-
 from seaclips.dataset import ReferenceFrame, SeaClipsSample
 
 
@@ -107,7 +106,7 @@ def dataset_root(tmp_path, sample_coco_data):
             img.save(split_dir / f"{i:06d}.png")
 
         annotation_file = tmp_path / f"seaclips-{split}.json"
-        with open(annotation_file, "w", encoding="utf-8") as f:
+        with open(annotation_file, "w", encoding="utf-8") as f:  # noqa: PTH123
             json.dump(sample_coco_data, f)
 
     return tmp_path

tests/test_collate.py

@@ -1,8 +1,6 @@
 """Tests for collate functions."""
 
-import pytest
 import torch
-
 from seaclips.collate import seaclips_collate_fn
 
 

tests/test_config.py

@@ -4,7 +4,6 @@
 from pathlib import Path
 
 import pytest
-
 from seaclips.config import SeaClipsConfig
 
 

tests/test_dataset.py

@@ -3,7 +3,6 @@
 
 import pytest
 from PIL import Image
-
 from seaclips.config import SeaClipsConfig
 from seaclips.dataset import SeaClipsDataset