#
# spec file for package python-pytesseract
#
# Copyright (c) 2020 SUSE LLC
#
# 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 https://bugs.opensuse.org/
#


%{?!python_module:%define python_module() python-%{**} python3-%{**}}
Name:           python-pytesseract
Version:        0.3.4
Release:        1.1
Summary:        Python wrapper for Google's Tesseract-OCR
License:        GPL-3.0-only
Group:          Development/Languages/Python
URL:            https://github.com/madmaze/python-tesseract
# https://github.com/madmaze/pytesseract/issues/262
Source:         https://github.com/madmaze/pytesseract/archive/v%{version}.tar.gz
BuildRequires:  %{python_module setuptools}
BuildRequires:  fdupes
BuildRequires:  python-rpm-macros
Requires:       python-Pillow
Requires:       python-setuptools
Requires:       tesseract-traineddata-deu
Requires:       tesseract-traineddata-eng
Requires:       pkgconfig(tesseract)
BuildArch:      noarch
# SECTION test requirements
BuildRequires:  %{python_module Pillow}
BuildRequires:  %{python_module pytest}
BuildRequires:  tesseract-ocr-traineddata-orientation_and_script_detection
BuildRequires:  tesseract-traineddata-deu
BuildRequires:  tesseract-traineddata-eng
BuildRequires:  tesseract-traineddata-fra
BuildRequires:  pkgconfig(tesseract)
# /SECTION
Requires(post):   update-alternatives
Requires(postun):  update-alternatives
%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 can be used
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 instead of writing it to a file. There is no 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

# by eisfair
sed -i 's/--strict-markers//' tox.ini

%build
%python_build

%install
%python_install
%python_clone -a %{buildroot}%{_bindir}/pytesseract
%python_expand %fdupes %{buildroot}%{$python_sitelib}

%check
%pytest

%post
%python_install_alternative pytesseract

%postun
%python_uninstall_alternative pytesseract

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

%changelog
* Tue May  5 2020 Matej Cepl <mcepl@suse.com>
- Update to 0.3.4:
  - Support for WebP images
  - Support for python 3.8 (CI testing)
  - Improved cli error reporting
- Don't use %%python3_only command, but properly use alternatives.
* Mon Mar 23 2020 pgajdos@suse.com
- version update to 0.3.3
  * no upstream changelog
* Tue Sep 10 2019 Tomáš Chvátal <tchvatal@suse.com>
- Update to 0.3.0:
  * no upstream changelog
* Mon Jul 22 2019 Tomáš Chvátal <tchvatal@suse.com>
- Update to 0.2.7:
  * no upstream changelog
* Tue May 14 2019 John Jolly <jjolly@suse.com>
- Update to 0.2.6
  + No upstream changelog
* Tue Dec  4 2018 Matej Cepl <mcepl@suse.com>
- Remove superfluous devel dependency for noarch package
* Sun Jul 29 2018 jengelh@inai.de
- Fix some grammar issues and replace future plans by current state.
* Thu May 24 2018 toddrme2178@gmail.com
- Update to 0.2.0
  * Convert image to RGB mode in order to save as PNG
- Update to 0.1.9
  * Preserve source image extension and metadata info
  * Don't delete every file in current directory if the temp_name is not populated
  * Remove enum dependency, fix bug with missing text in last line
  * Support for different output types
  * Added verbose option that returns detailed output from tesseract run
- Update to 0.1.8
  * Add initial support for numpy arrays/opencv images
  * Improved method to discard alpha channel
  * Add optional nice agrument for runing tesseract with different priority
  * fix python 3 byte string bug
- spec file cleanups
* Wed Oct 18 2017 toddrme2178@gmail.com
- Implement single-spec version
- Update to version 0.1.7
  * No changelog
* Tue Jun 10 2014 jnweiger@gmail.com
- pull from pypi. needed by testipy