• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1 /**
2  * Copyright 2020 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_UNICODE_SCRIPT_TOKENIZER_OP_H_
17 #define MINDSPORE_CCSRC_MINDDATA_DATASET_TEXT_KERNELS_UNICODE_SCRIPT_TOKENIZER_OP_H_
18 #include <memory>
19 #include <vector>
20 #include <string>
21 
22 #include "minddata/dataset/core/tensor.h"
23 #include "minddata/dataset/kernels/tensor_op.h"
24 #include "minddata/dataset/text/kernels/tokenizer_op.h"
25 #include "minddata/dataset/util/status.h"
26 
27 namespace mindspore {
28 namespace dataset {
29 
30 class UnicodeScriptTokenizerOp : public TokenizerOp {
31  public:
32   static const bool kDefKeepWhitespace;
33 
34   explicit UnicodeScriptTokenizerOp(const bool &keep_whitespace = kDefKeepWhitespace,
35                                     const bool &with_offsets = kDefWithOffsets)
TokenizerOp(with_offsets)36       : TokenizerOp(with_offsets), keep_whitespace_(keep_whitespace) {}
37 
38   ~UnicodeScriptTokenizerOp() override = default;
39 
40   Status Tokenize(std::string_view str, std::vector<std::string> *splits, std::vector<uint32_t> *offsets_start,
41                   std::vector<uint32_t> *offsets_limit) override;
42 
Name()43   std::string Name() const override { return kUnicodeScriptTokenizerOp; }
44 
45  private:
46   bool keep_whitespace_;  // If or not keep whitespace tokens
47 };
48 }  // namespace dataset
49 }  // namespace mindspore
50 #endif  // MINDSPORE_CCSRC_MINDDATA_DATASET_TEXT_KERNELS_UNICODE_SCRIPT_TOKENIZER_OP_H_
51