Dockerfile

FROM python:3.9

# Switch to root for system installations
USER root

# Install Tesseract and language data
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-eng \
    && rm -rf /var/lib/apt/lists/*

# Find tessdata directory and set permissions
RUN tessdata_dir=$(find /usr -name "tessdata" -type d | grep "tesseract") && \
    echo "Found tessdata at: $tessdata_dir" && \
    mkdir -p /usr/share/tesseract-ocr/4.00/tessdata && \
    cp -r $tessdata_dir/* /usr/share/tesseract-ocr/4.00/tessdata/ && \
    chmod -R 755 /usr/share/tesseract-ocr && \
    chown -R root:root /usr/share/tesseract-ocr

# Set environment variable for Tesseract
ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00/tessdata/

# Verify tessdata files are present
RUN ls -la $TESSDATA_PREFIX

# Create user and set up environment
RUN useradd -m -u 1000 user && \
    chown -R user:user /usr/share/tesseract-ocr/4.00/tessdata

RUN --mount=type=secret,id=Access_key,mode=0444,required=true \
 git clone $(cat /run/secrets/Access_key) /app
WORKDIR /app

# Switch to user for pip installations
USER user
ENV PATH="/home/user/.local/bin:$PATH"

# Install Python dependencies
RUN pip install --no-cache-dir --upgrade -r requirements.txt

# Copy application files
CMD ["gunicorn", "-b", "0.0.0.0:7860", "--timeout", "300", "--workers", "2", "--threads", "4", "app:app"]