From ab0a210763118abe4c146faf1721e9a0d91c0ad7 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <jim@purplerock.ca>
Date: Tue, 14 Feb 2017 11:32:05 -0800
Subject: [PATCH] Update dockerfile.tess4 yet again

Installing Tess4 PPA over Tess3 proved too much pain, so sever the link
between this and the jbarlow83/ocrmypdf image, starting each from
scratch. Also the complete set of language packs proves too much - the
build seems likely to fail when trying to install so many.
---
 Dockerfile.tess4      | 53 +++++++++++++++++++++++++++++++++++++++----
 docs/installation.rst |  3 ++-
 2 files changed, 50 insertions(+), 6 deletions(-)

diff --git a/Dockerfile.tess4 b/Dockerfile.tess4
index d9bddf3c..68280554 100644
--- a/Dockerfile.tess4
+++ b/Dockerfile.tess4
@@ -1,20 +1,63 @@
 # OCRmyPDF
 #
 # VERSION               4.4.2
-FROM      jbarlow83/ocrmypdf:latest
+FROM 	ubuntu:16.10
 MAINTAINER James R. Barlow <jim@purplerock.ca>
 
-USER root
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  software-properties-common python-software-properties \
+  python3-wheel \
+  python3-reportlab \
+  python3-venv \
+  ghostscript \
+  qpdf \
+  poppler-utils \
+  unpaper \
+  libffi-dev
 
 RUN add-apt-repository ppa:alex-p/tesseract-ocr
 
 RUN apt-get update \
-	&& apt-get upgrade -y tesseract-ocr \
-	&& apt-get install -y --no-install-recommends tesseract-ocr-all
+	&& apt-get autoremove -y \
+	&& apt-get install -y --no-install-recommends \
+		tesseract-ocr \
+		tesseract-ocr-eng \
+		tesseract-ocr-fra \
+		tesseract-ocr-deu \
+		tesseract-ocr-spa \
+		tesseract-ocr-por \
+		tesseract-ocr-ara \
+		tesseract-ocr-rus \
+		tesseract-ocr-chi-sim 
 
-RUN apt-get autoremove -y && apt-get clean -y
+RUN python3 -m venv --system-site-packages /appenv
+
+# This installs the latest binary wheel instead of the code in the current
+# folder. Installing from source will fail, apparently because cffi needs
+# build-essentials (gcc) to do a source installation 
+# (i.e. "pip install ."). It's unclear to me why this is the case.
+RUN . /appenv/bin/activate; \
+  pip install --upgrade pip \
+  && pip install ocrmypdf
+
+# Now copy the application in, mainly to get the test suite.
+# Do this now to make the best use of Docker cache.
+COPY . /application
+RUN . /appenv/bin/activate; \
+  pip install -r /application/test_requirements.txt
+
+# Remove the junk, including the source version of application since it was
+# already installed
+RUN rm -rf /tmp/* /var/tmp/* /root/* /application/ocrmypdf \
+  && apt-get autoremove -y \
+  && apt-get autoclean -y
+
+RUN useradd docker \
+  && mkdir /home/docker \
+  && chown docker:docker /home/docker
 
 USER docker
+WORKDIR /home/docker
 
 # Must use array form of ENTRYPOINT
 # Non-array form does not append other arguments, because that is "intuitive"
diff --git a/docs/installation.rst b/docs/installation.rst
index 5f232895..1f04db1f 100644
--- a/docs/installation.rst
+++ b/docs/installation.rst
@@ -46,7 +46,8 @@ Assuming you have a Docker engine running, you can download one of the three ava
 +-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
 | ocrmypdf-polyglot           | ``docker pull jbarlow83/ocrmypdf-polyglot`` | As above, with all available language packs.                                    |
 +-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
-| ocrmypdf-tess4              | ``docker pull jbarlow83/ocrmypdf-tess4``    | Latest ocrmypdf with Tesseract 4.00.00alpha and all language packs.             |
+| ocrmypdf-tess4              | ``docker pull jbarlow83/ocrmypdf-tess4``    | Latest ocrmypdf with Tesseract 4.00.00alpha and English, French, German,        |
+|                             |                                             | Spanish, Portuguese, Chinese Simplified, Arabic and Russian (the top 8).        |
 +-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
 
 For example: