1 /** 2 * Copyright 2022 Huawei Technologies Co., Ltd 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 #ifndef MINDSPORE_CCSRC_MINDDATA_DATASET_TEXT_KERNELS_FILTER_WIKIPEDIA_XML_OP_H_ 17 #define MINDSPORE_CCSRC_MINDDATA_DATASET_TEXT_KERNELS_FILTER_WIKIPEDIA_XML_OP_H_ 18 19 #include <map> 20 #include <memory> 21 #include <string> 22 23 #include "unicode/errorcode.h" 24 #include "unicode/regex.h" 25 #include "unicode/utypes.h" 26 27 #include "minddata/dataset/core/tensor.h" 28 #include "minddata/dataset/kernels/tensor_op.h" 29 #include "minddata/dataset/text/kernels/whitespace_tokenizer_op.h" 30 #include "minddata/dataset/util/status.h" 31 32 namespace mindspore { 33 namespace dataset { 34 class FilterWikipediaXMLOp : public TensorOp { 35 public: FilterWikipediaXMLOp()36 FilterWikipediaXMLOp() {} 37 38 ~FilterWikipediaXMLOp() override = default; 39 40 Status Compute(const std::shared_ptr<Tensor> &input, std::shared_ptr<Tensor> *output) override; 41 Name()42 std::string Name() const override { return kFilterWikipediaXMLOp; } 43 44 private: 45 Status FilterWikipediaXML(const std::string_view &text, std::string *out) const; 46 }; 47 } // namespace dataset 48 } // namespace mindspore 49 #endif // MINDSPORE_CCSRC_MINDDATA_DATASET_TEXT_KERNELS_FILTER_WIKIPEDIA_XML_OP_H_ 50