%global srcname pdfminer

Name:           python-pdfminer
Version:        20110515
Release:        3%{?dist}
Summary:        Tool to extract information from a PDF

Group:          Development/Libraries

License:        MIT

URL:            http://www.unixuser.org/~euske/python/pdfminer/index.html
Source0:        http://pypi.python.org/packages/source/p/%{srcname}/%{srcname}-%{version}.tar.gz

BuildArch:      noarch
BuildRequires:  python2-devel, cmap

%description
PDFMiner is a tool for extracting information from PDF documents.
Unlike other PDF-related tools, it focuses entirely on getting and
analyzing text data. PDFMiner allows to obtain the exact location
of texts in a page, as well as other information such as fonts or
lines. It includes a PDF converter that can transform PDF files
into other text formats (such as HTML). It has an extensible PDF
parser that can be used for other purposes instead of text analysis.

%prep
%setup -q -n %{srcname}-%{version}
# Remove the bundled cmap data and replace it with that provided by the package
rm cmaprsrc/*
cp %{_datadir}/cmap/aj16/cid2code.txt cmaprsrc/cid2code_Adobe_Japan1.txt
cp %{_datadir}/cmap/ak12/cid2code.txt cmaprsrc/cid2code_Adobe_Korea1.txt
cp %{_datadir}/cmap/ag15/cid2code.txt cmaprsrc/cid2code_Adobe_GB1.txt
cp %{_datadir}/cmap/ac16/cid2code.txt cmaprsrc/cid2code_Adobe_CNS1.txt

%build
make cmap
%{__python} setup.py build

%install
chmod +x build/lib/pdfminer/*
# Rename the python scripts to get rid of the *.py suffix
mv build/scripts-2.7/dumppdf.py build/scripts-2.7/dumppdf
mv build/scripts-2.7/pdf2txt.py build/scripts-2.7/pdf2txt
mv build/scripts-2.7/latin2ascii.py build/scripts-2.7/latin2ascii
%{__python} setup.py install --skip-build --root %{buildroot}

%files
%{_bindir}/dumppdf
%{_bindir}/latin2ascii
%{_bindir}/pdf2txt
%{python_sitelib}/%{srcname}-20110515-py2.7.egg-info
%{python_sitelib}/%{srcname}/

%doc docs/*

%changelog
* Thu Sep 20 2012 'Ben Rosser' <rosser.bjr@gmail.com> 20110515-3
- Removed bundled cmap, changed to depend on cmap package instead

* Thu Jul 05 2012 'Ben Rosser' <rosser.bjr@gmail.com> 20110515-2
- Removed BuildRoot, clean, and first line of install
- Fixed issue with cmap data not being copied into package
- Fixed license (cmap is under BSD, not MIT)

* Tue May 22 2012 'Ben Rosser' <rosser.bjr@gmail.com> 20110515-1
- Fixed unowned directory issue and cleaned up the spec file

* Fri May 18 2012 'Ben Rosser' <rosser.bjr@gmail.com> 20110515-0
- Initial version of the package