# This version is forked from the original PDFExtract by Øyvind Berg
# (see http://elacin.github.com/PDFExtract/). It is distributed under
# the same Apache License version 2.0.

# distribute patched pdfbox or just patches?
# The version of pdfbox distributed here is r1157684, with certain
# patches applied (see PDFExtract/parent/patch)

# NOTE: These installation steps have been tested on a standard
# xubuntu distribution, with Subversion and Maven also installed.

# How to build PDFExtract from source:

# install TEI P5 model
cd TEI-P5-Java-model
mvn install
cd ..

# install and patch PDFBox
svn co -r 1157684 http://svn.apache.org/repos/asf/pdfbox/trunk/ pdfbox
cd pdfbox
patch -p0 < ../PDFExtract/parent/patch/pdfbox_poms.patch
patch -p0 < ../PDFExtract/parent/patch/pdfbox-font-bounding-boxes.patch 
patch -p0 < ../PDFExtract/parent/patch/pdfbox-drawer-visibility.patch
mvn -DskipTests=true install
cd ..

# package PDFExtract
cd PDFExtract/parent
mvn -DskipTests=true package

# the binary distribution will have been created in  PDFExtract/pdfextract-cli/target/pdfextract-cli-${VERSION}-bin.tar.bz2