1 /* 2 * Copyright (C) 2018 The Android Open Source Project 3 * 4 * Licensed under the Apache License, Version 2.0 (the "License"); 5 * you may not use this file except in compliance with the License. 6 * You may obtain a copy of the License at 7 * 8 * http://www.apache.org/licenses/LICENSE-2.0 9 * 10 * Unless required by applicable law or agreed to in writing, software 11 * distributed under the License is distributed on an "AS IS" BASIS, 12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 * See the License for the specific language governing permissions and 14 * limitations under the License. 15 */ 16 17 #ifndef LIBTEXTCLASSIFIER_ANNOTATOR_GRAMMAR_DATES_PARSER_H_ 18 #define LIBTEXTCLASSIFIER_ANNOTATOR_GRAMMAR_DATES_PARSER_H_ 19 20 #include <vector> 21 22 #include "annotator/grammar/dates/annotations/annotation-options.h" 23 #include "annotator/grammar/dates/annotations/annotation.h" 24 #include "annotator/grammar/dates/dates_generated.h" 25 #include "annotator/grammar/dates/utils/date-match.h" 26 #include "utils/grammar/lexer.h" 27 #include "utils/grammar/rules-utils.h" 28 #include "utils/i18n/locale.h" 29 #include "utils/strings/stringpiece.h" 30 #include "utils/utf8/unilib.h" 31 32 namespace libtextclassifier3::dates { 33 34 // Parses datetime expressions in the input with the datetime grammar and 35 // constructs, validates, deduplicates and normalizes date time annotations. 36 class DateParser { 37 public: DateParser(const UniLib * unilib,const DatetimeRules * datetime_rules)38 explicit DateParser(const UniLib* unilib, const DatetimeRules* datetime_rules) 39 : unilib_(*unilib), 40 lexer_(unilib, datetime_rules->rules()), 41 datetime_rules_(datetime_rules), 42 rules_locales_(ParseRulesLocales(datetime_rules->rules())) {} 43 44 // Parses the dates in the input. Makes sure that the results do not 45 // overlap. 46 std::vector<DatetimeParseResultSpan> Parse( 47 StringPiece text, const std::vector<Token>& tokens, 48 const std::vector<Locale>& locales, 49 const DateAnnotationOptions& options) const; 50 51 private: 52 const UniLib& unilib_; 53 const grammar::Lexer lexer_; 54 55 // The datetime grammar. 56 const DatetimeRules* datetime_rules_; 57 58 // Pre-parsed locales of the rules. 59 const std::vector<std::vector<Locale>> rules_locales_; 60 }; 61 62 } // namespace libtextclassifier3::dates 63 64 #endif // LIBTEXTCLASSIFIER_ANNOTATOR_GRAMMAR_DATES_PARSER_H_ 65