Cleanup/fix benchmark and ci issues

.github/workflows/benchmark.yml

@@ -26,7 +26,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install -e .
+          pip install -e ".[nlp]"
           pip install -r requirements-dev.txt
 
       - name: Restore benchmark data

.github/workflows/ci.yml

@@ -0,0 +1,75 @@
+name: CI
+
+on:
+  push:
+    branches: [main, dev, "feature/*", "fix/*", "chore/*", "cleanup/*"]
+  pull_request:
+    branches: [main, dev]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@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 --show-diff-on-failure
+
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "pip"
+
+      - name: Install Tesseract OCR
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y tesseract-ocr libtesseract-dev
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e ".[nlp,ocr]"
+          pip install -r requirements-dev.txt
+
+      - name: Run tests
+        run: |
+          python -m pytest tests/ --cov=datafog --cov-report=xml --cov-report=term
+
+      - name: Upload coverage
+        uses: codecov/codecov-action@v4
+        with:
+          file: ./coverage.xml
+          token: ${{ secrets.CODECOV_TOKEN }}
+
+  wheel-size:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+          cache: "pip"
+
+      - name: Install build dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install build wheel
+
+      - name: Build wheel
+        run: python -m build --wheel
+
+      - name: Check wheel size
+        run: python scripts/check_wheel_size.py