FROM ubuntu:bionic RUN apt-get update && \ apt-get install -y --no-install-recommends \ build-essential \ ca-certificates \ cmake \ curl \ gcc \ git \ libtesseract-dev \ poppler-utils \ tesseract-ocr ARG xpdf_version RUN curl -O https://dl.xpdfreader.com/xpdf-${xpdf_version}.tar.gz && \ tar -xvf xpdf-${xpdf_version}.tar.gz && \ cd xpdf-${xpdf_version} && \ cmake . && \ make && \ cp xpdf/pdftotext /opt && \ cd .. \ rm -rf xpdf-${xpdf_version}