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_UTIL_DOCUMENT_VALIDATOR_H_ 16 #define ICING_UTIL_DOCUMENT_VALIDATOR_H_ 17 18 #include "icing/text_classifier/lib3/utils/base/status.h" 19 #include "icing/proto/document.pb.h" 20 #include "icing/schema/schema-store.h" 21 22 namespace icing { 23 namespace lib { 24 25 // This class validates DocumentProto based on the corresponding 26 // SchemaTypeConfigProto in the given type config map. 27 class DocumentValidator { 28 public: 29 explicit DocumentValidator(const SchemaStore* schema_store); 30 DocumentValidator() = delete; 31 32 // This function validates: 33 // 1. DocumentProto.namespace is not empty 34 // 2. DocumentProto.uri is not empty in top-level documents. Nested documents 35 // may have empty uris. 36 // 3. DocumentProto.schema is not empty 37 // 4. DocumentProto.schema matches one of SchemaTypeConfigProto.schema_type 38 // in the given SchemaProto in constructor 39 // 5. Each PropertyProto.name in DocumentProto.properties is not empty 40 // 6. Each PropertyProto.name is unique 41 // 7. Each PropertyProto.name matches one of 42 // PropertyConfigProto.property_name in the given SchemaProto in 43 // constructor 44 // 8. For each PropertyProto, the size of repeated value field matches 45 // PropertyConfigProto.cardinality defined in the given SchemaProto in 46 // constructor (e.g. OPTIONAL means 0 or 1, REQUIRED means 1) 47 // 9. For each PropertyProto with nested DocumentProto, 48 // DocumentProto.schema (nested) matches the current 49 // PropertyConfigProto.schema_type 50 // 10. All PropertyProto with REQUIRED cardinality in the corresponding 51 // PropertyConfigProto present in the DocumentProto 52 // 11. DocumentProto.score is not negative 53 // 12. DocumentProto.creation_timestamp_ms is not negative 54 // 13. DocumentProto.ttl_ms is not negative 55 // 56 // In addition, all nested DocumentProto will also be validated towards the 57 // requirements above. 58 // 59 // 'depth' indicates what nesting level the document may be at. A top-level 60 // document has a nesting depth of 0. 61 // 62 // Returns: 63 // OK on success 64 // FAILED_PRECONDITION if no schema is set yet 65 // INVALID_ARGUMENT if any of case 1, 2, 3, 5, 8, 9, 10, 11, 12, 13 fails 66 // NOT_FOUND if case 4 or 7 fails 67 // ALREADY_EXISTS if case 6 fails 68 // INTERNAL on any I/O error 69 libtextclassifier3::Status Validate(const DocumentProto& document, 70 int depth = 0); 71 UpdateSchemaStore(const SchemaStore * schema_store)72 void UpdateSchemaStore(const SchemaStore* schema_store) { 73 schema_store_ = schema_store; 74 } 75 76 private: 77 const SchemaStore* schema_store_; 78 }; 79 80 } // namespace lib 81 } // namespace icing 82 83 #endif // ICING_UTIL_DOCUMENT_VALIDATOR_H_ 84