1 // Copyright (C) 2019 Google LLC 2 // 3 // Licensed under the Apache License, Version 2.0 (the "License"); 4 // you may not use this file except in compliance with the License. 5 // You may obtain a copy of the License at 6 // 7 // http://www.apache.org/licenses/LICENSE-2.0 8 // 9 // Unless required by applicable law or agreed to in writing, software 10 // distributed under the License is distributed on an "AS IS" BASIS, 11 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 // See the License for the specific language governing permissions and 13 // limitations under the License. 14 15 #ifndef ICING_TOKENIZATION_LANGUAGE_SEGMENTER_FACTORY_H_ 16 #define ICING_TOKENIZATION_LANGUAGE_SEGMENTER_FACTORY_H_ 17 18 #include <memory> 19 #include <string_view> 20 #include <utility> 21 22 #include "icing/text_classifier/lib3/utils/base/statusor.h" 23 #include "icing/jni/jni-cache.h" 24 #include "icing/tokenization/language-segmenter.h" 25 26 namespace icing { 27 namespace lib { 28 29 namespace language_segmenter_factory { 30 31 struct SegmenterOptions { 32 explicit SegmenterOptions(std::string locale, 33 const JniCache* jni_cache = nullptr, 34 bool enable_icu_segmenter = false) localeSegmenterOptions35 : locale(std::move(locale)), 36 jni_cache(jni_cache), 37 enable_icu_segmenter(enable_icu_segmenter) {} 38 39 std::string locale; 40 41 // Does not hold ownership. 42 const JniCache* jni_cache; 43 44 // Determines whether to use an ICU based language segmenter 45 // in icu-with-reverse-jni-language-segmenter-factory or not. 46 // The default value is false, which means that the fallback option of a 47 // Reverse JNI based language segmenter will be used. 48 // 49 // This variable is a no-op for all other segmenter factories because they 50 // only support one segmenter type. 51 bool enable_icu_segmenter; 52 }; 53 54 // Creates a language segmenter with the given locale. 55 // 56 // Returns: 57 // A LanguageSegmenter on success 58 // INVALID_ARGUMENT_ERROR if locale string is invalid 59 libtextclassifier3::StatusOr<std::unique_ptr<LanguageSegmenter>> Create( 60 SegmenterOptions options); 61 62 } // namespace language_segmenter_factory 63 64 } // namespace lib 65 } // namespace icing 66 67 #endif // ICING_TOKENIZATION_LANGUAGE_SEGMENTER_FACTORY_H_ 68