Add Gitea Actions workflow: _incoming/*.pdf drop-folder pipeline, with dry-run dispatch

2026-10-18 01:34:58 -05:00
parent 8c9ea14568
commit 53d21ea2e5
3 changed files with 159 additions and 0 deletions
@@ -0,0 +1,11 @@
+#!/usr/bin/env bash
+# Installs everything the job needs in a FRESH container (node:20-bookworm). Safe to run twice.
+set -euo pipefail
+export DEBIAN_FRONTEND=noninteractive
+apt-get update -qq
+apt-get install -y -qq --no-install-recommends ffmpeg poppler-utils tesseract-ocr tesseract-ocr-eng ocrmypdf ghostscript \
+  python3 python3-venv python3-pip git curl ca-certificates
+python3 -m venv .venv
+.venv/bin/pip install -q --disable-pip-version-check -r _pipeline/requirements.txt
+echo "--- tool versions"
+python3 --version; ffmpeg -version | head -1; tesseract --version 2>&1 | head -1; ocrmypdf --version; pdftotext -v 2>&1 | head -1