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 // Methods for string normalization. 18 19 #ifndef LIBTEXTCLASSIFIER_UTILS_NORMALIZATION_H_ 20 #define LIBTEXTCLASSIFIER_UTILS_NORMALIZATION_H_ 21 22 #include "utils/base/integral_types.h" 23 #include "utils/normalization_generated.h" 24 #include "utils/utf8/unicodetext.h" 25 #include "utils/utf8/unilib.h" 26 27 namespace libtextclassifier3 { 28 29 // Normalizes a text according to the options. 30 UnicodeText NormalizeText(const UniLib& unilib, 31 const NormalizationOptions* normalization_options, 32 const UnicodeText& text); 33 34 // Normalizes a text codepoint wise by applying each codepoint wise op in 35 // `codepointwise_ops` that is interpreted as a set of 36 // `CodepointwiseNormalizationOp`. 37 UnicodeText NormalizeTextCodepointWise(const UniLib& unilib, 38 const uint32 codepointwise_ops, 39 const UnicodeText& text); 40 41 } // namespace libtextclassifier3 42 43 #endif // LIBTEXTCLASSIFIER_UTILS_NORMALIZATION_H_ 44