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 NLP_SAFT_COMPONENTS_COMMON_MOBILE_LITE_STRINGS_STR_SPLIT_H_ 18 #define NLP_SAFT_COMPONENTS_COMMON_MOBILE_LITE_STRINGS_STR_SPLIT_H_ 19 20 #include <vector> 21 22 #include "lang_id/common/lite_strings/stringpiece.h" 23 24 namespace libtextclassifier3 { 25 namespace mobile { 26 27 // Splits |text| on |delim|; similar to absl::StrSplit. 28 // 29 // Returns a list of tokens. Each token is represented by a StringPiece that 30 // indicates a range of chars from |text|. 31 // 32 // Example: StrSplit("apple,orange", ',') returns two tokens: a StringPiece that 33 // points to "apple", and another one for "orange". 34 // 35 // If one concatenates all returned tokens with |delim| in between, one gets the 36 // original |text|. E.g., If we split "apple,orange," on ',', we get three 37 // tokens: "apple", "orange" and "" (an empty token). We do not filter out 38 // empty tokens. If necessary, the caller can do that. 39 // 40 // Note: if the input text is empty, we return an empty list of tokens. In 41 // general, the number of returned tokens is 1 + the number of occurences of 42 // |delim| inside |text|. 43 std::vector<StringPiece> LiteStrSplit(StringPiece text, char delim); 44 45 } // namespace mobile 46 } // namespace nlp_saft 47 48 #endif // NLP_SAFT_COMPONENTS_COMMON_MOBILE_LITE_STRINGS_STR_SPLIT_H_ 49