Install ghostscript fonts (urw-base35) for OCR of PDFs with non-embedded fonts; fuller OCR error text

2026-10-18 01:53:13 -05:00
parent a8ea105b4c
commit 52104b30b9
3 changed files with 3 additions and 3 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 ocrmypdf ghostscript \
+ && apt-get install -y --no-install-recommends ffmpeg poppler-utils tesseract-ocr tesseract-ocr-eng ocrmypdf ghostscript fonts-urw-base35 \
 && rm -rf /var/lib/apt/lists/*

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