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 #include "utils/test-utils.h" 18 19 #include <iterator> 20 21 #include "utils/strings/split.h" 22 #include "utils/strings/stringpiece.h" 23 24 namespace libtextclassifier3 { 25 26 using libtextclassifier3::Token; 27 28 // Returns a list of Tokens for given input string. Can't handle non-ASCII 29 // input. TokenizeAsciiOnSpace(const std::string & text)30std::vector<Token> TokenizeAsciiOnSpace(const std::string& text) { 31 std::vector<Token> result; 32 for (const StringPiece token : strings::Split(text, ' ')) { 33 const int start_offset = std::distance(text.data(), token.data()); 34 const int token_length = token.length(); 35 result.push_back( 36 Token{token.ToString(), start_offset, start_offset + token_length}); 37 } 38 return result; 39 } 40 41 } // namespace libtextclassifier3 42