#
# spec file for package python-pytesseract
#
# Copyright (c) 2018 SUSE LINUX GmbH, Nuernberg, Germany.
#
# All modifications and additions to the file contributed by third parties
# remain the property of their copyright owners, unless otherwise agreed
# upon. The license for this file, and modifications and additions to the
# file, is the same license as for the pristine package itself (unless the
# license for the pristine package is not an Open Source License, in which
# case the license is the MIT License). An "Open Source License" is a
# license that conforms to the Open Source Definition (Version 1.9)
# published by the Open Source Initiative.

# Please submit bugfixes or comments via http://bugs.opensuse.org/
#


%{?!python_module:%define python_module() python-%{**} python3-%{**}}
Name:           python-pytesseract
Version:        0.2.0
Release:        0
Summary:        Python wrapper for google's Tesseract-OCR
License:        GPL-3.0
Group:          Development/Languages/Python
Url:            https://github.com/madmaze/python-tesseract
Source:         https://files.pythonhosted.org/packages/source/p/pytesseract/pytesseract-%{version}.tar.gz
Source10:       https://raw.githubusercontent.com/madmaze/pytesseract/v%{version}/LICENSE
BuildRequires:  %{python_module devel}
BuildRequires:  %{python_module setuptools}
BuildRequires:  fdupes
BuildRequires:  python-rpm-macros
# SECTION test requirements
BuildRequires:  %{python_module Pillow}
BuildRequires:  pkgconfig(tesseract)
BuildRequires:  tesseract-traineddata-eng
BuildRequires:  tesseract-traineddata-deu
# /SECTION
Requires:       python-Pillow
Requires:       pkgconfig(tesseract)
Requires:       tesseract-traineddata-eng
Requires:       tesseract-traineddata-deu
BuildArch:      noarch

%python_subpackages

%description
Python-tesseract is an optical character recognition (OCR) tool for python.
That is, it will recognize and "read" the text embedded in images.

Python-tesseract is a wrapper for `Google's Tesseract-OCR Engine`_. It is also useful as a
stand-alone invocation script to tesseract, as it can read all image types
supported by the Python Imaging Library, including jpeg, png, gif, bmp, tiff,
and others, whereas tesseract-ocr by default only supports tiff and bmp.
Additionally, if used as a script, Python-tesseract will print the recognized
text in stead of writing it to a file. Support for confidence estimates and
bounding box data is planned for future releases.

%prep
%setup -q -n pytesseract-%{version}
sed -i -e '/^#!\//, 1d' src/pytesseract.py
cp %{SOURCE10} .

%build
%python_build

%install
%python_install
%python_expand %fdupes %{buildroot}%{$python_sitelib}

%files %{python_files}
%doc README.rst
%license LICENSE
%python3_only %{_bindir}/pytesseract
%{python_sitelib}/*

%changelog