01c4fe80b5
Save all currently accumulated repository changes as a backup snapshot for Gitea so no local work is lost.
60 lines
1.4 KiB
Docker
60 lines
1.4 KiB
Docker
# PDF Processor Microservice
|
|
FROM python:3.11-slim
|
|
|
|
# Install system dependencies
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
# For bash script
|
|
bash \
|
|
jq \
|
|
wget \
|
|
curl \
|
|
# ImageMagick for image conversion
|
|
imagemagick \
|
|
# Ghostscript for PDF operations
|
|
ghostscript \
|
|
# LibreOffice for document conversion
|
|
libreoffice-core \
|
|
libreoffice-writer \
|
|
libreoffice-calc \
|
|
libreoffice-impress \
|
|
# Fonts for proper rendering
|
|
fonts-liberation \
|
|
fonts-dejavu \
|
|
# Clean up
|
|
&& apt-get clean \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Fix ImageMagick policy to allow PDF operations
|
|
RUN sed -i 's/rights="none" pattern="PDF"/rights="read|write" pattern="PDF"/g' /etc/ImageMagick-6/policy.xml || true
|
|
|
|
# Set working directory
|
|
WORKDIR /app
|
|
|
|
# Copy requirements and install Python dependencies
|
|
COPY requirements.txt .
|
|
RUN pip install --no-cache-dir -r requirements.txt
|
|
|
|
# Copy application code
|
|
COPY app/ ./app/
|
|
COPY scripts/ ./scripts/
|
|
|
|
# Make script executable
|
|
RUN chmod +x ./scripts/process_pdfs.sh
|
|
|
|
# Create temp directories
|
|
RUN mkdir -p /tmp/pdf_work /tmp/pdf_output
|
|
|
|
# Expose port
|
|
EXPOSE 8300
|
|
|
|
# Health check
|
|
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
|
|
CMD curl -f http://localhost:8300/health || exit 1
|
|
|
|
# Run the application
|
|
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8300"]
|
|
|
|
|
|
|
|
|