From 3a5ffc79e0d66332fe93aad3c619f5ebcefa1c94 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <jim@purplerock.ca>
Date: Sat, 22 Aug 2015 00:30:39 -0700
Subject: [PATCH] Stock debian unpaper is no good; replace with 6.1 built from
 source

debian and ubuntu both install unpaper 0.4.2 or so. No .deb packages
available at higher version numbers although ArchLinux had something.
Considered making a separate image to handle building and install but
decided that was a premature optimization at this point, so just build
the unpaper that works. All tests pass.
---
 Dockerfile | 32 +++++++++++++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

diff --git a/Dockerfile b/Dockerfile
index 5fb64ac2..27cefca5 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -16,7 +16,6 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
   tesseract-ocr \
   tesseract-ocr-deu tesseract-ocr-spa tesseract-ocr-eng tesseract-ocr-fra \
   qpdf \
-  unpaper \
   poppler-utils \
   python3 \
   python3-pip \
@@ -31,6 +30,37 @@ RUN dpkg-reconfigure locales && \
   /usr/sbin/update-locale LANG=C.UTF-8
 ENV LC_ALL C.UTF-8
 
+# Build unpaper 6.1
+RUN apt-get install -y \
+  wget \
+  gcc \
+  libavformat-dev \
+  libavcodec-dev \
+  libavutil-dev \
+  autoconf \
+  automake \
+  make \
+  pkg-config \
+  xsltproc
+
+WORKDIR /root
+RUN wget https://github.com/Flameeyes/unpaper/archive/unpaper-6.1.tar.gz
+RUN tar xf unpaper-6.1.tar.gz
+WORKDIR /root/unpaper-unpaper-6.1
+RUN autoreconf -i
+RUN ./configure CFLAGS="-O2 -march=native -pipe -flto"
+RUN make -j install
+
+RUN apt-get remove -y \
+  gcc \
+  autoconf \
+  automake \
+  pkg-config \
+  xsltproc \
+  make
+RUN apt-get autoremove -y && apt-get clean -y
+RUN rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
 # Set up a Python virtualenv and take all of the system packages, so we can
 # rely on the platform packages rather than importing GCC and compiling them
 RUN pyvenv /appenv \