Page-marker grouping, OCR improvements, homelab CI #3

Merged
ilia merged 6 commits from feature/grouping-ocr-ci into master 2026-07-26 14:48:54 -05:00
4 changed files with 48 additions and 3 deletions
Showing only changes of commit 17be9cef33 - Show all commits
+44
View File
@@ -0,0 +1,44 @@
---
# Homelab CI — Python lane + secret scan. Lint and tests are HARD gates.
name: CI
on:
push:
branches: [master]
pull_request:
types: [opened, synchronize, reopened]
jobs:
python-ci:
runs-on: [homelab, self-hosted, linux, python]
container:
image: node:20-bookworm
steps:
- uses: actions/checkout@v4
- name: Install Python tooling
run: |
apt-get update -qq
DEBIAN_FRONTEND=noninteractive apt-get install -y -qq \
python3 python3-pip python3-venv \
tesseract-ocr libgl1 libglib2.0-0
python3 -m pip install --upgrade pip --break-system-packages
pip install -r requirements.txt --break-system-packages
pip install pytest ruff --break-system-packages
- name: Ruff lint (hard gate)
run: ruff check .
- name: Pytest (hard gate)
run: pytest -q
secret-scan:
runs-on: [homelab, self-hosted, linux, heavy]
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Gitleaks
run: |
docker run --rm -v "$PWD:/repo" ghcr.io/gitleaks/gitleaks:latest \
detect --source /repo --no-banner --redact
-1
View File
@@ -130,7 +130,6 @@ def detect_document(
resolution for a full-quality perspective warp.
"""
h, w = image_bgr.shape[:2]
frame_area = float(h * w)
scale = detect_width / w if w > detect_width else 1.0
small = (
+4
View File
@@ -0,0 +1,4 @@
line-length = 120
[lint]
select = ["E4", "E7", "E9", "F", "I"]
-2
View File
@@ -1,4 +1,3 @@
import numpy as np
import pytest
from PIL import Image
@@ -32,7 +31,6 @@ def test_images_to_pdf_multi_page(tmp_path):
images_to_pdf(paths, out)
data = out.read_bytes()
# img2pdf writes one xobject image per page; a 3-page PDF should be
# meaningfully larger than a 1-page PDF of the same-size images.
single = tmp_path / "single.pdf"