Name:		sentencepiece
Version:	0.1.92
Release:	3
Summary:	An unsupervised text tokenizer and detokenizer
License:	Apache-2.0
URL:		https://github.com/google/sentencepiece
Source0:	https://github.com/google/sentencepiece/archive/v%{version}.tar.gz
Patch0:         Removed-codes-where-Zero-Width-Joiner-replaced-with-.patch
BuildRequires:	gcc-c++ gcc autoconf pkgconfig protobuf-compiler protobuf
BuildRequires:  cmake >= 3.14.0
Requires:       protobuf protobuf-compiler

%description
SentencePiece is an unsupervised text tokenizer and detokenizer mainly for Neural Network-based text generation 
systems where the vocabulary size is predetermined prior to the neural model training.

%global debug_package %{nil}

%prep
%autosetup -p1 -n %{name}-%{version}

%build
mkdir -p cmake/build
cd cmake/build
cmake ../../ -DCMAKE_CXX_FLAGS="-D_FORTIFY_SOURCE=2 -O2 -Wno-unused-result -Wno-sign-compare"\
             -DCMAKE_C_FLAGS="-D_FORTIFY_SOURCE=2"\
             -DCMAKE_BUILD_TYPE=Release\
             -DSPM_USE_BUILTIN_PROTOBUF=ON\
             -DSPM_ENABLE_SHARED=OFF\
             -DSPM_BUILD_TEST=ON\
             -DCMAKE_INSTALL_LIBDIR=%{buildroot}%{_libdir}\
             -DCMAKE_INSTALL_BINDIR=%{buildroot}%{_bindir}\
             -DCMAKE_INSTALL_INCDIR=%{buildroot}%{_includedir}

make -j24 V=1
make CTEST_OUTPUT_ON_FAILURE=1 test
cd ../../

%install
cd cmake/build
make install

%files
%defattr(-,root,root)
%{_bindir}/spm_*
%{_libdir}/*.a
%{_libdir}/pkgconfig/*
%{_includedir}/sentencepiece_*.h

%changelog
* Tue Nov 2 2021 xiefangqi <xiefangqi2@huawei.com> - 0.1.92-3
- Prevent Zero Width Joiner replaced with whitespace
* Wed Sep 29 2021 xiefangqi <xiefangqi2@huawei.com> - 0.1.92-2
- add test cases
* Wed Sep 23 2021 xiefangqi <xiefangqi2@huawei.com> - 0.1.92-1
- package init