From 817db7592af8f6d48b6066dbdf6d83ea8e9909fa Mon Sep 17 00:00:00 2001
From: Stephen Gaito <stephen@perceptisys.co.uk>
Date: Mon, 25 Nov 2019 11:19:44 +0000
Subject: [PATCH] initial working draft of building docker image

---
 buildScripts/createDockerImage | 31 +++++++++++++++---
 buildScripts/dockerFunctions   | 59 ++++++++++++++++++++++++++++++++++
 buildScripts/versionEnvs       |  2 ++
 3 files changed, 87 insertions(+), 5 deletions(-)
 create mode 100644 buildScripts/dockerFunctions

diff --git a/buildScripts/createDockerImage b/buildScripts/createDockerImage
index bc11110..f9f2cda 100755
--- a/buildScripts/createDockerImage
+++ b/buildScripts/createDockerImage
@@ -1,13 +1,34 @@
 #!/bin/bash 
 
-# This bash script creates an Docker Image for pdf2htmlEX
+# This bash script creates a docker image from an existing pdf2htmlEX
 
 source buildScripts/versionEnvs
 
-cd imageBuild
+source buildScripts/dockerFunctions
 
-pip install git+https://github.com/larsks/dockerize
+mkdir -p imageBuild/dockerDir
+
+cd pdf2htmlEX/build
+
+sudo rm -rf install_manifest.txt
+
+make install DESTDIR=../../imageBuild/dockerDir
+
+cd ../../imageBuild/dockerDir
+
+copy_deps
+
+delete_blacklisted
+
+cat >> Dockerfile <<DOCKERFILE_HERE_DOC
+FROM $DOCKER_FROM
+COPY ./ /
+RUN ldconfig
+ENTRYPOINT ["/usr/bin/pdf2htmlEX"]
+DOCKERFILE_HERE_DOC
+
+cd ..
+
+docker build -t stephengaito/pdf2htmlex:test-`date +%Y%m%d-%H.%M.%S` dockerDir
 
-dockerize		\
-  /usr/bin/pdf2htmlEX	\
 
diff --git a/buildScripts/dockerFunctions b/buildScripts/dockerFunctions
new file mode 100644
index 0000000..f9fb372
--- /dev/null
+++ b/buildScripts/dockerFunctions
@@ -0,0 +1,59 @@
+# The following has been extracted and modified for our use under an MIT 
+# license by Stephen Gaito on 2019/NOV/25
+#
+# The original was taken from:
+# https://raw.githubusercontent.com/AppImage/pkg2appimage/master/functions.sh
+# (commit ID ed1d385282a6aa6c9a93b52296f20555adf9bae7 commited 2019/Apr/9)
+# 
+# The original copyright was: Copyright (c) 2004-16 Simon Peter
+#
+
+# Copy the library dependencies of all exectuable files in the current 
+# directory (it can be beneficial to run this multiple times)
+#
+copy_deps()
+{
+  PWD=$(readlink -f .)
+  FILES=$(find . -type f -executable -or -name *.so.* -or -name *.so	\
+          | sort | uniq )
+
+  for FILE in $FILES ; do
+    ldd "${FILE}" | grep "=>" | awk '{print $3}'	\
+    | xargs -I '{}' echo '{}' >> DEPSFILE
+  done
+ 
+ DEPS=$(cat DEPSFILE | sort | uniq)
+
+  for FILE in $DEPS ; do
+    if [ -e $FILE ] && [[ $(readlink -f $FILE)/ != $PWD/* ]] ; then
+      cp -v --parents -rfL $FILE ./ || true
+    fi
+  done
+  rm -f DEPSFILE
+}
+
+# Delete blacklisted files. Our blacklisted files are the shared libraries 
+# extracted from the "base" docker image
+# 
+delete_blacklisted()
+{
+  docker run --rm -it --entrypoint=find $DOCKER_FROM -iname "*.so.*"		\
+    | xargs -i basename {} | sed 's/\r//g' | sed 's/\(so\.[0-9]\+\).*$/\1/'	\
+    | sort | uniq > BLACKLISTED_FILES
+
+  for FILE in $(cat BLACKLISTED_FILES | tr "\r\n" "  ") ; do
+    FILES="$(find . -name "${FILE}*" -not -path "./usr/optional/*")"
+    for FOUND in $FILES ; do
+      rm -vf "$FOUND" "$(readlink -f "$FOUND")"
+    done
+  done
+
+  rm BLACKLISTED_FILES
+
+  # Do not bundle developer stuff
+  rm -rf usr/include || true
+  rm -rf usr/lib/cmake || true
+  rm -rf usr/lib/pkgconfig || true
+  find . -name '*.la' | xargs -i rm {}
+}
+
diff --git a/buildScripts/versionEnvs b/buildScripts/versionEnvs
index e7bf2c2..3cea7c5 100644
--- a/buildScripts/versionEnvs
+++ b/buildScripts/versionEnvs
@@ -9,3 +9,5 @@ export POPPLER_VERSION=poppler-0.81.0
 export FONTFORGE_VERSION=20170731
 export PDF2HTMLEX_VERSION=newBuildSystem
 export MACHINE_ARCH=`uname -m`
+export DOCKER_FROM=ubuntu:16.04
+