Recovered 3.2.2

.flake8

@@ -1,5 +1,5 @@
 [flake8]
-ignore = E203, E266, E501, W503
-max-line-length = 80
+ignore = E203, E266, E501, W503, B006, B007, B008, F401, C416, B950, B904
+max-line-length = 88
 max-complexity = 18
-select = B,C,E,F,W,T4,B9
+select = B,C,E,F,W,T4,B9

.github/workflows/dev-cicd-tests.yml → .github/workflows/dev-cicd.yml

@@ -1,4 +1,4 @@
-name: dev-cicd-tests
+name: dev-cicd-setup-and-test
 
 on:
   push:
@@ -17,23 +17,44 @@ jobs:
       - name: Run pre-commit
         uses: pre-commit/action@v3.0.1
 
-  build:
+  build-and-test:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10", "3.11"]
+        python-version: ["3.10"]
     steps:
       - uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
       - uses: actions/checkout@v3
-      - name: Test with tox
+
+      - name: Install Tesseract OCR
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y software-properties-common
+          sudo add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
+          sudo apt-get update
+          sudo apt-get install -y tesseract-ocr
+          sudo apt-get install -y libtesseract-dev
+          tesseract --version
+          dpkg -l | grep tesseract
+
+      - name: Verify Tesseract Installation
+        run: |
+          which tesseract
+          tesseract --list-langs
+
+      - name: Update PATH
+        run: echo "export PATH=$PATH:/usr/bin" >> $GITHUB_ENV
+
+      - name: Install dependencies and run tests
         run: |
           pip install tox
           tox -- --cov datafog --cov-report xml --cov-report term
+
       - name: Submit to codecov
         uses: codecov/codecov-action@v3
-        if: ${{ matrix.python-version == '3.11' }}
+        if: ${{ matrix.python-version == '3.10' }}
 
       - name: Upload coverage reports to Codecov
         uses: codecov/codecov-action@v4.0.1

.github/workflows/feature-cicd.yml

@@ -0,0 +1,64 @@
+name: feature-cicd-setup-and-test
+
+on:
+  push:
+    branches:
+      - feature/*
+  pull_request:
+    branches:
+      - feature/*
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repo
+        uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      - name: Install pre-commit
+        run: pip install pre-commit
+      - name: Run pre-commit
+        run: pre-commit run --all-files
+
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10"]
+    steps:
+      - name: Check out repo
+        uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install Tesseract OCR
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y software-properties-common
+          sudo add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
+          sudo apt-get update
+          sudo apt-get install -y tesseract-ocr libtesseract-dev
+          tesseract --version
+          dpkg -l | grep tesseract
+      - name: Verify Tesseract Installation
+        run: |
+          which tesseract
+          tesseract --list-langs
+      - name: Install Dependencies
+        run: |
+          pip install -U pip
+          pip install -e .
+          pip install tox just pre-commit
+      - name: Run Tests with tox
+        run: tox -- --cov datafog --cov-report xml --cov-report term --codeblocks
+      - name: Submit to Codecov
+        uses: codecov/codecov-action@v3
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          files: ./coverage.xml
+          flags: unittests
+          name: codecov-umbrella

.github/workflows/main-cicd-tests.yml → .github/workflows/main-cicd.yml

@@ -21,19 +21,40 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10", "3.11"]
+        python-version: ["3.10"]
     steps:
       - uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
+
       - uses: actions/checkout@v3
-      - name: Test with tox
+      - name: Install Tesseract OCR
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y software-properties-common
+          sudo add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
+          sudo apt-get update
+          sudo apt-get install -y tesseract-ocr
+          sudo apt-get install -y libtesseract-dev
+          tesseract --version
+          dpkg -l | grep tesseract
+
+      - name: Verify Tesseract Installation
+        run: |
+          which tesseract
+          tesseract --list-langs
+
+      - name: Update PATH
+        run: echo "export PATH=$PATH:/usr/bin" >> $GITHUB_ENV
+
+      - name: Install dependencies and run tests
         run: |
           pip install tox
           tox -- --cov datafog --cov-report xml --cov-report term
+
       - name: Submit to codecov
         uses: codecov/codecov-action@v3
-        if: ${{ matrix.python-version == '3.11' }}
+        if: ${{ matrix.python-version == '3.10' }}
 
       - name: Upload coverage reports to Codecov
         uses: codecov/codecov-action@v4.0.1

.gitignore

@@ -9,18 +9,24 @@ build/
 *.egg-info/
 .pytest_cache/
 .tox/
-/src/datafog/__pycache__/
-/src/datafog/pii_tools/__pycache__/
-/tests/__pycache__/
-/tests/scratch.py
+src/datafog/__pycache__/
+src/datafog/pii_tools/__pycache__/
+tests/__pycache__/
+tests/scratch.py
+tests/.datafog_env/
 node_modules/
 datafog_debug.log
 sotu_2023.txt
 .DS_Store
-/venv/
+venv/
 datafog-python/datafog/processing/image_processing/__pycache__/
 datafog-python/datafog/processing/text_processing/__pycache__/
 datafog-python/datafog/services/__pycache__/
 datafog-python/datafog/processing/__pycache__/
 datafog-python/datafog/__pycache__/
-
+.env
+coverage.xml
+htmlcov/
+.venv/
+node_modules/
+.DS_Store

.pre-commit-config.yaml

@@ -4,19 +4,25 @@ repos:
     hooks:
       - id: isort
         args: [--profile=black]
+        exclude: .venv
 
   - repo: https://github.com/psf/black
     rev: 24.2.0
     hooks:
       - id: black
         language_version: python3
+        exclude: .venv
 
   - repo: https://github.com/pycqa/flake8
     rev: 7.0.0
     hooks:
       - id: flake8
+        args: [--max-line-length=88] # Match Black's line length
+        additional_dependencies: [flake8-bugbear, flake8-comprehensions]
+        exclude: .venv
 
   - repo: https://github.com/pre-commit/mirrors-prettier
     rev: v4.0.0-alpha.8
     hooks:
       - id: prettier
+        exclude: .venv