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_INDEX_ITERATOR_DOC_HIT_INFO_ITERATOR_SECTION_RESTRICT_H_ 16 #define ICING_INDEX_ITERATOR_DOC_HIT_INFO_ITERATOR_SECTION_RESTRICT_H_ 17 18 #include <cstdint> 19 #include <memory> 20 #include <set> 21 #include <string> 22 #include <vector> 23 24 #include "icing/text_classifier/lib3/utils/base/status.h" 25 #include "icing/text_classifier/lib3/utils/base/statusor.h" 26 #include "icing/index/iterator/doc-hit-info-iterator.h" 27 #include "icing/index/iterator/section-restrict-data.h" 28 #include "icing/proto/search.pb.h" 29 #include "icing/schema/schema-store.h" 30 #include "icing/schema/section.h" 31 #include "icing/store/document-id.h" 32 #include "icing/store/document-store.h" 33 34 namespace icing { 35 namespace lib { 36 37 // A iterator that helps filter for DocHitInfos whose term was in a section 38 // named target_section. 39 // 40 // NOTE: This is a little different from the DocHitInfoIteratorFilter class. 41 // That class is meant to be applied to the root of a query tree and filter over 42 // all results at the end. This class is more used in the limited scope of a 43 // term or a small group of terms. 44 class DocHitInfoIteratorSectionRestrict : public DocHitInfoLeafIterator { 45 public: 46 // Does not take any ownership, and all pointers must refer to valid objects 47 // that outlive the one constructed. 48 explicit DocHitInfoIteratorSectionRestrict( 49 std::unique_ptr<DocHitInfoIterator> delegate, SectionRestrictData* data); 50 51 // Methods that apply section restrictions to all DocHitInfoLeafIterator nodes 52 // inside the provided iterator tree, and return the root of the tree 53 // afterwards. These methods do not take any ownership for the raw pointer 54 // parameters, which must refer to valid objects that outlive the iterator 55 // returned. 56 static std::unique_ptr<DocHitInfoIterator> ApplyRestrictions( 57 std::unique_ptr<DocHitInfoIterator> iterator, 58 const DocumentStore* document_store, const SchemaStore* schema_store, 59 std::set<std::string> target_sections, int64_t current_time_ms); 60 static std::unique_ptr<DocHitInfoIterator> ApplyRestrictions( 61 std::unique_ptr<DocHitInfoIterator> iterator, 62 const DocumentStore* document_store, const SchemaStore* schema_store, 63 const SearchSpecProto& search_spec, int64_t current_time_ms); 64 static std::unique_ptr<DocHitInfoIterator> ApplyRestrictions( 65 std::unique_ptr<DocHitInfoIterator> iterator, SectionRestrictData* data); 66 67 libtextclassifier3::Status Advance() override; 68 69 libtextclassifier3::StatusOr<TrimmedNode> TrimRightMostNode() && override; 70 GetCallStats()71 CallStats GetCallStats() const override { return delegate_->GetCallStats(); } 72 73 std::string ToString() const override; 74 75 // Note that the DocHitInfoIteratorSectionRestrict can only be applied at 76 // DocHitInfoLeafIterator, which can be a term iterator or another 77 // DocHitInfoIteratorSectionRestrict. 78 // 79 // To filter the matching sections, filtering_section_mask should be set to 80 // doc_hit_info_.hit_section_ids_mask() held in the outermost 81 // DocHitInfoIteratorSectionRestrict, which is equal to the intersection of 82 // all hit_section_ids_mask in the DocHitInfoIteratorSectionRestrict chain, 83 // since for any two section restrict iterators chained together, the outer 84 // one's hit_section_ids_mask is always a subset of the inner one's 85 // hit_section_ids_mask. 86 void PopulateMatchedTermsStats( 87 std::vector<TermMatchInfo>* matched_terms_stats, 88 SectionIdMask filtering_section_mask = kSectionIdMaskAll) const override { 89 if (doc_hit_info_.document_id() == kInvalidDocumentId) { 90 // Current hit isn't valid, return. 91 return; 92 } 93 delegate_->PopulateMatchedTermsStats( 94 matched_terms_stats, 95 /*filtering_section_mask=*/filtering_section_mask & 96 doc_hit_info_.hit_section_ids_mask()); 97 } 98 99 private: 100 std::unique_ptr<DocHitInfoIterator> delegate_; 101 // Does not own. 102 SectionRestrictData* data_; 103 }; 104 105 } // namespace lib 106 } // namespace icing 107 108 #endif // ICING_INDEX_ITERATOR_DOC_HIT_INFO_ITERATOR_SECTION_RESTRICT_H_ 109