Ty_Tech/old-books
6
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Audiobook Producer
2026-10-18 01:53:13 -05:00
parent a8ea105b4c
commit 52104b30b9
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
_pipeline/Dockerfile
+1 -1
View File
@@ -4,7 +4,7 @@
FROM python:3.13-slim FROM python:3.13-slim
RUN apt-get update \ 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/* && rm -rf /var/lib/apt/lists/*
COPY _pipeline/requirements.txt /tmp/requirements.txt COPY _pipeline/requirements.txt /tmp/requirements.txt
_pipeline/ci/install.sh
+1 -1
View File
@@ -3,7 +3,7 @@
set -euo pipefail set -euo pipefail
export DEBIAN_FRONTEND=noninteractive export DEBIAN_FRONTEND=noninteractive
apt-get update -qq apt-get update -qq
apt-get install -y -qq --no-install-recommends ffmpeg poppler-utils tesseract-ocr tesseract-ocr-eng ocrmypdf ghostscript \ apt-get install -y -qq --no-install-recommends ffmpeg poppler-utils tesseract-ocr tesseract-ocr-eng ocrmypdf ghostscript fonts-urw-base35 \
python3 python3-venv python3-pip git curl ca-certificates python3 python3-venv python3-pip git curl ca-certificates
python3 -m venv .venv python3 -m venv .venv
.venv/bin/pip install -q --disable-pip-version-check -r _pipeline/requirements.txt .venv/bin/pip install -q --disable-pip-version-check -r _pipeline/requirements.txt
_pipeline/ingest.py
+1 -1
View File
@@ -108,5 +108,5 @@ def ocr_if_needed(cfg, book_dir, book):
src = os.path.join(book_dir, book["source_pdf"]) src = os.path.join(book_dir, book["source_pdf"])
r = subprocess.run(["ocrmypdf", "--skip-text", "-l", cfg["ocr"]["language"], src, out], capture_output=True, text=True) r = subprocess.run(["ocrmypdf", "--skip-text", "-l", cfg["ocr"]["language"], src, out], capture_output=True, text=True)
if r.returncode != 0: if r.returncode != 0:
return [("ocr-failed", where, "ocrmypdf exit %d: %s" % (r.returncode, r.stderr.strip()[-300:]))] return [("ocr-failed", where, "ocrmypdf exit %d: %s" % (r.returncode, (r.stderr.strip()[:300] + " ... " + r.stderr.strip()[-300:]) if len(r.stderr) > 650 else r.stderr.strip()))]
return [("ocr", where, "OCR applied to a scratch copy; original untouched")] return [("ocr", where, "OCR applied to a scratch copy; original untouched")]