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_UTILS_GRAMMAR_TEXT_CONTEXT_H_ 18 #define LIBTEXTCLASSIFIER_UTILS_GRAMMAR_TEXT_CONTEXT_H_ 19 20 #include <vector> 21 22 #include "annotator/types.h" 23 #include "utils/i18n/locale.h" 24 #include "utils/utf8/unicodetext.h" 25 26 namespace libtextclassifier3::grammar { 27 28 // Input to the parser. 29 struct TextContext { 30 // Returns a view on a span of the text. SpanTextContext31 const UnicodeText Span(const CodepointSpan& span) const { 32 return text.Substring(codepoints[span.first], codepoints[span.second], 33 /*do_copy=*/false); 34 } 35 36 // The input text. 37 UnicodeText text; 38 39 // Pre-enumerated codepoints for fast substring extraction. 40 std::vector<UnicodeText::const_iterator> codepoints; 41 42 // The tokenized input text. 43 std::vector<Token> tokens; 44 45 // Locales of the input text. 46 std::vector<Locale> locales; 47 48 // Text annotations. 49 std::vector<AnnotatedSpan> annotations; 50 51 // The span of tokens to consider. 52 TokenSpan context_span; 53 }; 54 55 }; // namespace libtextclassifier3::grammar 56 57 #endif // LIBTEXTCLASSIFIER_UTILS_GRAMMAR_TEXT_CONTEXT_H_ 58