automatic import of sentencepiece

3 files changed, 66 insertions, 121 deletions

diff --git a/.gitignore b/.gitignore
index b8681a5..f5b0f64 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,2 +1,3 @@
 /sentencepiece-0.1.99.tar.gz
 /v0.2.0.tar.gz
+/v0.1.98.tar.gz
diff --git a/sentencepiece.spec b/sentencepiece.spec
index 894787b..3aaa001 100644
--- a/sentencepiece.spec
+++ b/sentencepiece.spec
@@ -1,38 +1,22 @@
-%define __cmake_in_source_build 1
-%define _epel   %{?epel:%{epel}}%{!?epel:0}
-
 Name:		sentencepiece
-Version:	0.2.0
-Release:	5%{?dist}
-Summary:	An unsupervised text tokenizer for Neural Network-based text generation
-
-License:	ASL 2.0
+Version:	0.1.98
+Release:	1
+Summary:	An unsupervised text tokenizer and detokenizer
+License:	Apache-2.0
 URL:		https://github.com/google/sentencepiece
-Source0: https://github.com/google/sentencepiece/archive/refs/tags/v0.2.0.tar.gz
+Source0:	https://github.com/google/sentencepiece/archive/v%{version}.tar.gz
+BuildRequires:	gcc-c++ gcc autoconf pkgconfig protobuf-compiler protobuf
+BuildRequires:  cmake >= 3.14.0
+Requires:       protobuf protobuf-compiler
 
-BuildRequires: make
-%if 0%{_epel} >= 7
-BuildRequires:	cmake3
-%else
-BuildRequires:	cmake
-%endif
+%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.
 
-BuildRequires:	gcc-c++
-BuildRequires:	gperftools-devel
-BuildRequires:	pkgconfig
-BuildRequires:	python3-devel
-BuildRequires:	python3-setuptools
+%global debug_package %{nil}
 
-%description
-The SentencePiece is an unsupervised text tokenizer for Neural Network-based
-text generation.
-It 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.
-SentencePiece implements subword units and unigram language model with the 
-extension of direct training from raw sentences.
-SentencePiece allows us to make a purely end-to-end system that does not
-depend on language-specific pre/post-processing.
+%prep
+%autosetup -p1 -n %{name}-%{version}
 
 %package libs
 Summary:	Runtime libraries for SentencePiece
@@ -54,109 +38,69 @@ Requires:	%{name}-libs%{?_isa} = %{version}-%{release}
 %description devel
 This package contains header files to develop a software using SentencePiece.
 
-%package        -n python3-%{name}
-Summary:	Python module for SentencePiece
-Requires:	%{name}-libs%{?_isa} = %{version}-%{release}
-%{?python_provide:%python_provide python3-%{name}}
-
-%description -n python3-%{name}
-This package contains Python3 module file for SentencePiece.
-
-%prep
-%autosetup -n %{name}-%{version}-Source
-
 %build
-%if %{_epel} >= 7
-cmake3 . -DCMAKE_INSTALL_PREFIX=%{_prefix} -DCMAKE_INSTALL_LIBDIR=%{_libdir}
-%else
-%cmake . -DCMAKE_INSTALL_LIBDIR=%{_libdir}
-%endif
-%make_build
-pushd python
-CFLAGS="-I../src" LDFLAGS="-L../src -lsentencepiece" PKG_CONFIG_PATH=".." %{__python3} setup.py build
-popd
+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
-%make_install
-pushd python
-PKG_CONFIG_PATH=".." %py3_install
-popd
+cd cmake/build
+make install
 sed -i'' -e "s,%{buildroot},," %{buildroot}%{_libdir}/pkgconfig/sentencepiece.pc
 sed -i'' -e "s,${prefix}/lib,%{_libdir}," %{buildroot}%{_libdir}/pkgconfig/sentencepiece.pc
-find %{buildroot} -name '*.a' -delete
+
 
 %files libs
 %doc README.md
 %license LICENSE
 %{_libdir}/libsentencepiece*.so.0*
 
-%files devel
-%{_includedir}/sentencepiece*.h
-%{_libdir}/*.so
-%{_libdir}/pkgconfig/sentencepiece*.pc
-
 %files tools
 %{_bindir}/spm*
 
-%files -n python3-%{name}
-%{python3_sitearch}/%{name}.py
-%{python3_sitearch}/_%{name}*.so
-%{python3_sitearch}/__pycache__/*
-%{python3_sitearch}/%{name}-*.egg-info/
-
+%files
+%defattr(-,root,root)
+%{_bindir}/spm_*
+%{_libdir}/*.a
+%{_libdir}/pkgconfig/*
+%{_includedir}/sentencepiece*.h
 
 %changelog
-* Sat Jul 22 2023 Fedora Release Engineering <releng@fedoraproject.org> - 0.1.92-11
-- Rebuilt for https://fedoraproject.org/wiki/Fedora_39_Mass_Rebuild
- 
-* Tue Jun 13 2023 Python Maint <python-maint@redhat.com> - 0.1.92-10
-- Rebuilt for Python 3.12
- 
-* Sat Jan 21 2023 Fedora Release Engineering <releng@fedoraproject.org> - 0.1.92-9
-- Rebuilt for https://fedoraproject.org/wiki/Fedora_38_Mass_Rebuild
- 
-* Sat Jul 23 2022 Fedora Release Engineering <releng@fedoraproject.org> - 0.1.92-8
-- Rebuilt for https://fedoraproject.org/wiki/Fedora_37_Mass_Rebuild
- 
-* Mon Jun 13 2022 Python Maint <python-maint@redhat.com> - 0.1.92-7
-- Rebuilt for Python 3.11
- 
-* Sat Jan 22 2022 Fedora Release Engineering <releng@fedoraproject.org> - 0.1.92-6
-- Rebuilt for https://fedoraproject.org/wiki/Fedora_36_Mass_Rebuild
-
-* Fri Jul 23 2021 Fedora Release Engineering <releng@fedoraproject.org> - 0.1.92-5
-- Rebuilt for https://fedoraproject.org/wiki/Fedora_35_Mass_Rebuild
-
-* Fri Jun 04 2021 Python Maint <python-maint@redhat.com> - 0.1.92-4
-- Rebuilt for Python 3.10
-
-* Wed Jan 27 2021 Fedora Release Engineering <releng@fedoraproject.org> - 0.1.92-3
-- Rebuilt for https://fedoraproject.org/wiki/Fedora_34_Mass_Rebuild
-
-* Wed Oct 07 2020 Kentaro Hayashi <kenhys@gmail.com> - 0.1.92-2
-- Add missing BuildRequires: python3-setuptools
-
-* Thu Oct 01 2020 Kentaro Hayashi <kenhys@gmail.com> - 0.1.92-1
-- New upstream release
-
-* Tue Sep 22 2020 Jeff Law <law@redhat.com> - 0.1.84-6
-- Use cmake_in_source_build to fix FTBFS due to recent cmake macro changes
-
-* Sat Aug 01 2020 Fedora Release Engineering <releng@fedoraproject.org> - 0.1.84-5
-- Second attempt - Rebuilt for
-  https://fedoraproject.org/wiki/Fedora_33_Mass_Rebuild
-
-* Wed Jul 29 2020 Fedora Release Engineering <releng@fedoraproject.org> - 0.1.84-4
-- Rebuilt for https://fedoraproject.org/wiki/Fedora_33_Mass_Rebuild
-
-* Tue May 26 2020 Miro Hrončok <mhroncok@redhat.com> - 0.1.84-3
-- Rebuilt for Python 3.9
-
-* Thu Jan 30 2020 Fedora Release Engineering <releng@fedoraproject.org> - 0.1.84-2
-- Rebuilt for https://fedoraproject.org/wiki/Fedora_32_Mass_Rebuild
-
-* Thu Nov 14 2019 Kentaro Hayashi <hayashi@clear-code.com> - 0.1.84-1
-- New upstream release
-
-* Mon Oct 07 2019 Kentaro Hayashi <hayashi@clear-code.com> - 0.1.83-1
-- initial packaging
+* Fri May 12 2023 liuyongqi <liuyongqi5@huawei.com> - 0.1.98-1
+- Sentencepiece version updata: Upgraded from 0.1.92 to 0.1.98
+
+* Fri Nov 27 2021 xiefangqi <xiefangqi2@huawei.com> - 0.1.92.6
+- Fix split_digits support to SentencepieceTrainer spec parser
+- Add sentencepiece.pc install
+- Add spm_train --help option
+- Fix FTBFS problem on armel/mips/powerpc/m68k/sh4
+- Fix endian problem on android plarform
+- Fix pb protobuf header file can't find problem
+- Restore the sentence boundary
+
+* Tue Nov 16 2021 xiefangqi <xiefangqi2@huawei.com> - 0.1.92.5
+- add README.md/README.en.md
+
+* Tue Nov 2 2021 xiefangqi <xiefangqi2@huawei.com> - 0.1.92-4
+- fix of an unattainable condition
+
+* 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
diff --git a/sources b/sources
index fecd2a5..2edc851 100644
--- a/sources
+++ b/sources
@@ -1 +1 @@
-6ee244227f5ee8123de05980920e2936  v0.2.0.tar.gz
+2bba6f65825ef0b17a8bed1630f8e709  v0.1.98.tar.gz