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_TOKENFREE_BYTE_ENCODER_H_ 18 #define LIBTEXTCLASSIFIER_UTILS_TOKENFREE_BYTE_ENCODER_H_ 19 20 #include <vector> 21 22 #include "utils/base/logging.h" 23 #include "utils/container/string-set.h" 24 #include "utils/strings/stringpiece.h" 25 26 namespace libtextclassifier3 { 27 28 // Encoder to segment/tokenize strings into bytes 29 class ByteEncoder { 30 public: 31 bool Encode(StringPiece input_text, std::vector<int64_t>* encoded_text) const; ByteEncoder()32 ByteEncoder() {} 33 }; 34 35 } // namespace libtextclassifier3 36 37 #endif // LIBTEXTCLASSIFIER_UTILS_TOKENFREE_BYTE_ENCODER_H_ 38