1 // Copyright (C) 2023 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_INDEX_TERM_INDEXING_HANDLER_H_ 16 #define ICING_INDEX_TERM_INDEXING_HANDLER_H_ 17 18 #include <memory> 19 #include <utility> 20 21 #include "icing/text_classifier/lib3/utils/base/status.h" 22 #include "icing/text_classifier/lib3/utils/base/statusor.h" 23 #include "icing/index/data-indexing-handler.h" 24 #include "icing/index/index.h" 25 #include "icing/index/property-existence-indexing-handler.h" 26 #include "icing/index/string-section-indexing-handler.h" 27 #include "icing/proto/logging.pb.h" 28 #include "icing/store/document-id.h" 29 #include "icing/transform/normalizer.h" 30 #include "icing/util/clock.h" 31 #include "icing/util/tokenized-document.h" 32 33 namespace icing { 34 namespace lib { 35 36 class TermIndexingHandler : public DataIndexingHandler { 37 public: 38 // Creates a TermIndexingHandler instance which does not take 39 // ownership of any input components. All pointers must refer to valid objects 40 // that outlive the created TermIndexingHandler instance. 41 // 42 // Returns: 43 // - A TermIndexingHandler instance on success 44 // - FAILED_PRECONDITION_ERROR if any of the input pointer is null 45 static libtextclassifier3::StatusOr<std::unique_ptr<TermIndexingHandler>> 46 Create(const Clock* clock, const Normalizer* normalizer, Index* index, 47 bool build_property_existence_metadata_hits); 48 49 ~TermIndexingHandler() override = default; 50 51 // Handles term indexing process: 52 // - Checks if document_id > last_added_document_id. 53 // - Updates last_added_document_id to document_id. 54 // - Handles PropertyExistenceIndexingHandler. 55 // - Handles StringSectionIndexingHandler. 56 // - Sorts the lite index if necessary. 57 // - Merges the lite index into the main index if necessary. 58 // 59 /// Returns: 60 // - OK on success 61 // - INVALID_ARGUMENT_ERROR if document_id is less than or equal to the 62 // document_id of a previously indexed document in non recovery mode. 63 // - RESOURCE_EXHAUSTED_ERROR if the index is full and can't add anymore 64 // content. 65 // - DATA_LOSS_ERROR if an attempt to merge the index fails and both indices 66 // are cleared as a result. 67 // - INTERNAL_ERROR if any other errors occur. 68 // - Any main/lite index errors. 69 libtextclassifier3::Status Handle( 70 const TokenizedDocument& tokenized_document, DocumentId document_id, 71 bool recovery_mode, PutDocumentStatsProto* put_document_stats) override; 72 73 private: TermIndexingHandler(const Clock * clock,Index * index,std::unique_ptr<PropertyExistenceIndexingHandler> property_existence_indexing_handler,std::unique_ptr<StringSectionIndexingHandler> string_section_indexing_handler)74 explicit TermIndexingHandler(const Clock* clock, Index* index, 75 std::unique_ptr<PropertyExistenceIndexingHandler> 76 property_existence_indexing_handler, 77 std::unique_ptr<StringSectionIndexingHandler> 78 string_section_indexing_handler) 79 : DataIndexingHandler(clock), 80 index_(*index), 81 property_existence_indexing_handler_( 82 std::move(property_existence_indexing_handler)), 83 string_section_indexing_handler_( 84 std::move(string_section_indexing_handler)) {} 85 86 Index& index_; // Does not own. 87 88 std::unique_ptr<PropertyExistenceIndexingHandler> 89 property_existence_indexing_handler_; // Nullable 90 std::unique_ptr<StringSectionIndexingHandler> 91 string_section_indexing_handler_; 92 }; 93 94 } // namespace lib 95 } // namespace icing 96 97 #endif // ICING_INDEX_TERM_INDEXING_HANDLER_H_ 98