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 #include "icing/tokenization/tokenizer-factory.h" 16 17 #include <memory> 18 19 #include "icing/text_classifier/lib3/utils/base/statusor.h" 20 #include "icing/absl_ports/canonical_errors.h" 21 #include "icing/proto/schema.pb.h" 22 #include "icing/tokenization/language-segmenter.h" 23 #include "icing/tokenization/plain-tokenizer.h" 24 #include "icing/tokenization/rfc822-tokenizer.h" 25 #include "icing/tokenization/tokenizer.h" 26 27 #ifdef ENABLE_URL_TOKENIZER 28 #include "icing/tokenization/url-tokenizer.h" 29 #endif // ENABLE_URL_TOKENIZER 30 31 #include "icing/tokenization/verbatim-tokenizer.h" 32 #include "icing/util/status-macros.h" 33 34 namespace icing { 35 namespace lib { 36 37 namespace tokenizer_factory { 38 39 libtextclassifier3::StatusOr<std::unique_ptr<Tokenizer>> CreateIndexingTokenizer(StringIndexingConfig::TokenizerType::Code type,const LanguageSegmenter * lang_segmenter)40CreateIndexingTokenizer(StringIndexingConfig::TokenizerType::Code type, 41 const LanguageSegmenter* lang_segmenter) { 42 ICING_RETURN_ERROR_IF_NULL(lang_segmenter); 43 44 switch (type) { 45 case StringIndexingConfig::TokenizerType::PLAIN: 46 return std::make_unique<PlainTokenizer>(lang_segmenter); 47 case StringIndexingConfig::TokenizerType::VERBATIM: 48 return std::make_unique<VerbatimTokenizer>(); 49 case StringIndexingConfig::TokenizerType::RFC822: 50 return std::make_unique<Rfc822Tokenizer>(); 51 // TODO (b/246964044): remove ifdef guard when url-tokenizer is ready for export 52 // to Android. 53 #ifdef ENABLE_URL_TOKENIZER 54 case StringIndexingConfig::TokenizerType::URL: 55 return std::make_unique<UrlTokenizer>(); 56 #endif // ENABLE_URL_TOKENIZER 57 case StringIndexingConfig::TokenizerType::NONE: 58 [[fallthrough]]; 59 default: 60 // This should never happen. 61 return absl_ports::InvalidArgumentError( 62 "Invalid tokenizer type for an indexed section"); 63 } 64 } 65 66 } // namespace tokenizer_factory 67 68 } // namespace lib 69 } // namespace icing 70