added __all__ declarations

Author: sidmohan0

.github/workflows/dev-cicd.yml

@@ -15,13 +15,14 @@ jobs:
       - name: Check out repo
         uses: actions/checkout@v4
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: "3.10"
+          cache: "pip"
       - name: Install pre-commit
         run: pip install pre-commit
       - name: Run pre-commit
-        run: pre-commit run --all-files
+        run: pre-commit run --all-files --show-diff-on-failure
 
   build:
     runs-on: ubuntu-latest
@@ -46,9 +47,10 @@ jobs:
           docker-images: true
           swap-storage: true
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: "pip"
       - name: Install Tesseract OCR
         run: |
           sudo apt-get update

datafog/exceptions.py

@@ -6,6 +6,7 @@
 
 from typing import Optional
 
+
 class DataFogException(Exception):
     """
     Base exception for DataFog SDK.

datafog/processing/text_processing/__init__.py

@@ -1 +1,3 @@
 from .spacy_pii_annotator import SpacyPIIAnnotator
+
+__all__ = ["SpacyPIIAnnotator"]

datafog/processing/text_processing/spacy_pii_annotator.py

@@ -63,7 +63,9 @@ def annotate(self, text: str) -> Dict[str, List[str]]:
             if len(text) > MAXIMAL_STRING_SIZE:
                 text = text[:MAXIMAL_STRING_SIZE]
             doc = self.nlp(text)
-            classified_entities: Dict[str, List[str]] = {label: [] for label in PII_ANNOTATION_LABELS}
+            classified_entities: Dict[str, List[str]] = {
+                label: [] for label in PII_ANNOTATION_LABELS
+            }
             for ent in doc.ents:
                 if ent.label_ in classified_entities:
                     classified_entities[ent.label_].append(ent.text)

datafog/services/__init__.py

@@ -1,3 +1,5 @@
 from .image_service import ImageService
 from .spark_service import SparkService
 from .text_service import TextService
+
+__all__ = ["ImageService", "SparkService", "TextService"]

datafog/services/image_service.py

@@ -95,7 +95,9 @@ def __init__(self, use_donut: bool = False, use_tesseract: bool = True):
             PytesseractProcessor() if self.use_tesseract else None
         )
 
-    async def download_images(self, urls: List[str]) -> List[Union[Image.Image, BaseException]]:
+    async def download_images(
+        self, urls: List[str]
+    ) -> List[Union[Image.Image, BaseException]]:
         tasks = [
             asyncio.create_task(self.downloader.download_image(url)) for url in urls
         ]

notes/story-1.8-tkt.md

@@ -1,4 +1,4 @@
 – Delete committed artifacts, extend .gitignore.
 – Add CI jobs for lint (ruff/flake8), mypy, tests, bench.
-– Pin exact versions in requirements*.txt; keep full dependency set.
-– Update docs / README badges.
+– Pin exact versions in requirements\*.txt; keep full dependency set.
+– Update docs / README badges.

run_tests.py

@@ -1,6 +1,5 @@
 #!/usr/bin/env python
 
-import os
 import subprocess
 import sys
 

scripts/compare_benchmarks.py

@@ -1,7 +1,6 @@
 #!/usr/bin/env python3
 
 import json
-import os
 import sys
 
 

scripts/fixed_text_service.py

@@ -4,10 +4,9 @@
 """
 
 import asyncio
-from typing import Dict, List, Optional, Union
+from typing import Dict, List, Union
 
 from datafog.processing.text_processing.regex_annotator.regex_annotator import (
-    AnnotationResult,
     RegexAnnotator,
     Span,
 )

tests/benchmark_text_service.py

@@ -1,12 +1,9 @@
 """Benchmark tests for comparing regex vs spaCy performance in TextService."""
 
 import time
-from typing import Dict, List
 
 import pytest
 
-from datafog.processing.text_processing.regex_annotator import RegexAnnotator
-from datafog.processing.text_processing.spacy_pii_annotator import SpacyPIIAnnotator
 from datafog.services.text_service import TextService
 
 

tests/test_cli_smoke.py

@@ -5,15 +5,11 @@
 
 import os
 import tempfile
-from pathlib import Path
-from unittest.mock import patch
 
 import pytest
 from typer.testing import CliRunner
 
 from datafog.client import app
-from datafog.models.anonymizer import Anonymizer, AnonymizerType
-from datafog.models.spacy_nlp import SpacyAnnotator
 
 
 @pytest.fixture

tests/test_client.py

@@ -1,16 +1,11 @@
-from unittest.mock import MagicMock, patch
+from unittest.mock import patch
 
 import pytest
 from typer.testing import CliRunner
 
 from datafog.client import app
 from datafog.models.annotator import AnnotationResult, AnnotatorMetadata
-from datafog.models.anonymizer import (
-    AnonymizationResult,
-    Anonymizer,
-    AnonymizerType,
-    HashType,
-)
+from datafog.models.anonymizer import AnonymizationResult, AnonymizerType, HashType
 from datafog.models.common import EntityTypes
 
 runner = CliRunner()

tests/test_donut_lazy_import.py

@@ -1,10 +1,6 @@
-import asyncio
-import importlib
 import sys
 from unittest.mock import patch
 
-import pytest
-
 from datafog.services.image_service import ImageService
 
 

tests/test_main.py

@@ -1,4 +1,3 @@
-import asyncio
 import json
 import logging
 import re

tests/test_ocr_integration.py

@@ -6,8 +6,6 @@
 """
 
 import io
-import json
-import os
 from unittest.mock import patch
 
 import pytest

tests/test_regex_annotator.py

@@ -1,12 +1,9 @@
-from typing import Dict, List, Tuple
-
 import pytest
 
 # Import the regex annotator module
 from datafog.processing.text_processing.regex_annotator import (
     AnnotationResult,
     RegexAnnotator,
-    Span,
 )
 
 

tests/test_text_service_integration.py

@@ -1,13 +1,7 @@
 """Integration tests for TextService engine selection functionality."""
 
-from unittest.mock import MagicMock, patch
-
 import pytest
 
-from datafog.processing.text_processing.regex_annotator.regex_annotator import (
-    RegexAnnotator,
-)
-from datafog.processing.text_processing.spacy_pii_annotator import SpacyPIIAnnotator
 from datafog.services.text_service import TextService