Add 'process': one command for a whole book (all chapters), idempotent, loud failures, OCR required; synthetic test-PDF tool

2026-10-18 01:34:58 -05:00
parent 460d4648cb
commit 8c9ea14568
6 changed files with 656 additions and 2 deletions
@@ -4,7 +4,7 @@
 FROM python:3.13-slim

 RUN apt-get update \
- && apt-get install -y --no-install-recommends ffmpeg poppler-utils tesseract-ocr tesseract-ocr-eng ghostscript \
+ && apt-get install -y --no-install-recommends ffmpeg poppler-utils tesseract-ocr tesseract-ocr-eng ocrmypdf ghostscript \
 && rm -rf /var/lib/apt/lists/*

 COPY _pipeline/requirements.txt /tmp/requirements.txt