mindspore 2.7.0__cp311-none-any.whl → 2.7.1__cp311-none-any.whl

mindspore/include/mindspore/ccsrc/minddata/dataset/engine/datasetops/source/sst2_op.h

@@ -1,85 +0,0 @@
-/**
- * Copyright 2022 Huawei Technologies Co., Ltd
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-#ifndef MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_SST2_OP_H_
-#define MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_SST2_OP_H_
-
-#include <map>
-#include <memory>
-#include <string>
-#include <vector>
-
-#include "minddata/dataset/engine/datasetops/source/csv_op.h"
-
-namespace mindspore {
-namespace dataset {
-class SST2Op : public CsvOp {
- public:
-  /// \brief Constructor.
-  /// \param[in] dataset_files_list List of file paths for the dataset files.
-  /// \param[in] usage Usage of this dataset, can be 'train', 'test' or 'all'.
-  /// \param[in] field_delim A char that indicates the delimiter to separate fields.
-  /// \param[in] column_default List of default values for the CSV field (default={}). Each item in the list is
-  ///     either a valid type (float, int, or string).
-  /// \param[in] column_name List of column names of the dataset file.
-  /// \param[in] num_workers Num of workers reading files in parallel.
-  /// \param[in] num_samples The number of samples to be included in the dataset.
-  /// \param[in] worker_connector_size Size of each internal queue.
-  /// \param[in] op_connector_size Size of each queue in the connector that the child operator pulls from.
-  /// \param[in] shuffle_files Whether or not to shuffle the files before reading data.
-  /// \param[in] num_devices Number of devices that the dataset should be divided into.
-  /// \param[in] device_id The device ID within num_devices.
-  SST2Op(const std::vector<std::string> &dataset_files_list, const std::string &usage, char field_delim,
-         const std::vector<std::shared_ptr<BaseRecord>> &column_default, const std::vector<std::string> &column_name,
-         int32_t num_workers, int64_t num_samples, int32_t worker_connector_size, int32_t op_connector_size,
-         bool shuffle_files, int32_t num_devices, int32_t device_id);
-
-  /// \brief Destructor.
-  ~SST2Op() override = default;
-
-  /// \brief A print method typically used for debugging
-  /// \param[out] out The output stream to write output to
-  /// \param[in] show_all A bool to control if you want to show all info or just a summary
-  void Print(std::ostream &out, bool show_all) const override;
-
-  /// \brief DatasetName name getter.
-  /// \param[in] upper A bool to control if you want to return uppercase or lowercase Op name.
-  /// \return DatasetName of the current Op.
-  std::string DatasetName(bool upper = false) const { return upper ? "SST2" : "sst2"; }
-
-  /// \brief Op name getter
-  /// \return Name of the current Op.
-  std::string Name() const override { return "SST2Op"; }
-
-  /// \brief Split string based on a character delimiter
-  /// @param[in] s The input string
-  /// @param[in] delim The delimiter
-  /// @return The a string vector
-  std::vector<std::string> split(const std::string &s, char delim) override;
-
-  /// \brief Reads a csv file and loads the data into multiple tensors.
-  /// @param[in] file The file to read.
-  /// @param[in] start_offset The start offset of file.
-  /// @param[in] end_offset The end offset of file.
-  /// @param[in] worker_id The id of the worker that is executing this function.
-  /// @return Status The error code returned.
-  Status LoadFile(const std::string &file, int64_t start_offset, int64_t end_offset, int32_t worker_id) override;
-
-  std::string usage_;
-};
-}  // namespace dataset
-}  // namespace mindspore
-#endif  // MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_SST2_OP_H_

mindspore/include/mindspore/ccsrc/minddata/dataset/engine/datasetops/source/stl10_op.h

@@ -1,118 +0,0 @@
-/**
- * Copyright 2021 Huawei Technologies Co., Ltd
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-#ifndef MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_STL10_OP_H_
-#define MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_STL10_OP_H_
-
-#include <algorithm>
-#include <map>
-#include <memory>
-#include <string>
-#include <utility>
-#include <vector>
-
-#include "minddata/dataset/core/tensor.h"
-#include "minddata/dataset/engine/data_schema.h"
-#include "minddata/dataset/engine/datasetops/parallel_op.h"
-#include "minddata/dataset/engine/datasetops/source/mappable_leaf_op.h"
-#include "minddata/dataset/engine/datasetops/source/sampler/sampler.h"
-#include "minddata/dataset/util/path.h"
-#include "minddata/dataset/util/queue.h"
-#include "minddata/dataset/util/status.h"
-#include "minddata/dataset/util/wait_post.h"
-
-namespace mindspore {
-namespace dataset {
-class STL10Op : public MappableLeafOp {
- public:
-  // Constructor
-  // @param const std::string &usage - Usage of this dataset, can be 'train', 'test', 'unlabeled', "train+unlabeled" or
-  //     "all"
-  // @param int32_t num_workers - number of workers reading images in parallel.
-  // @param std::string folder_path - dir directory of stl10.
-  // @param int32_t queue_size - connector queue size.
-  // @param std::unique_ptr<DataSchema> data_schema - the schema of the stl10 dataset.
-  // @param td::unique_ptr<Sampler> sampler - sampler tells STL10Op what to read.
-  STL10Op(const std::string &usage, int32_t num_workers, const std::string &folder_path, int32_t queue_size,
-          std::unique_ptr<DataSchema> data_schema, std::shared_ptr<SamplerRT> sampler);
-
-  // Destructor
-  ~STL10Op() = default;
-
-  // Method derived from RandomAccess Op, enable Sampler to get all ids for each class
-  // @param (std::map<int32_t, std::vector<int64_t>> * cls_ids - key label, val all ids for this class
-  // @return Status The status code returned
-  Status GetClassIds(std::map<int32_t, std::vector<int64_t>> *cls_ids) const override;
-
-  // A print method typically used for debugging.
-  // @param out - The output stream to write output to.
-  // @param show_all - A bool to control if you want to show all info or just a summary.
-  void Print(std::ostream &out, bool show_all) const override;
-
-  // Function to count the number of samples in the STL10 dataset.
-  // @param dir path to the STL10 directory.
-  // @param const std::string &usage - Usage of this dataset, can be 'train', 'test', 'unlabeled', "train+unlabeled" or
-  //     "all"
-  // @param count output arg that will hold the minimum of the actual dataset size and numSamples.
-  // @return Status The status code returned.
-  static Status CountTotalRows(const std::string &dir, const std::string &usage, int64_t *count);
-
-  // Op name getter.
-  // @return Name of the current Op.
-  std::string Name() const override { return "STL10Op"; }
-
- private:
-  // Read the needed files in the directory, save the file in image_names_ and label_names_.
-  // @return Status The status code returned.
-  Status WalkAllFiles();
-
-  // Read the specified number of images and labels from the file stream.
-  // @param std::ifstream *image_reader - image file stream.
-  // @param std::ifstream *label_reader - label file stream.
-  // @param int64_t index - number of image to read.
-  // @return Status The status code returned.
-  Status ReadImageAndLabel(std::ifstream *image_reader, std::ifstream *label_reader, size_t index);
-
-  // Parse all stl10 dataset files
-  // @return Status The status code returned
-  Status ParseSTLData();
-
-  // Read all stl10 data files in the directory
-  // @return Status The status code returned.
-  Status PrepareData() override;
-
-  // Private function for computing the assignment of the column name map.
-  // @return - Status.
-  Status ComputeColMap() override;
-
-  // Load a tensor row according to a pair.
-  // @param uint64_t index - index need to load.
-  // @param TensorRow trow - image & label read into this tensor row.
-  // @return Status The status code returned.
-  Status LoadTensorRow(row_id_type index, TensorRow *trow) override;
-
-  std::string folder_path_;  // directory of image folder.
-  const std::string usage_;  // can only be either "train" or "test" or "unlabeled" or "train+unlabeled" or "all".
-  std::unique_ptr<DataSchema> data_schema_;
-
-  std::vector<std::pair<std::shared_ptr<Tensor>, int32_t>> stl10_image_label_pairs_;
-  std::vector<std::string> image_names_;
-  std::vector<std::string> label_names_;
-  std::vector<std::string> image_path_;
-  std::vector<std::string> label_path_;
-};
-}  // namespace dataset
-}  // namespace mindspore
-#endif  // MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_STL10_OP_H_

mindspore/include/mindspore/ccsrc/minddata/dataset/engine/datasetops/source/sun397_op.h

@@ -1,116 +0,0 @@
-/**
- * Copyright 2022 Huawei Technologies Co., Ltd
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-#ifndef MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_SUN397_OP_H_
-#define MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_SUN397_OP_H_
-
-#include <algorithm>
-#include <map>
-#include <memory>
-#include <string>
-#include <utility>
-#include <vector>
-
-#include "minddata/dataset/core/tensor.h"
-#include "minddata/dataset/engine/data_schema.h"
-#include "minddata/dataset/engine/datasetops/parallel_op.h"
-#include "minddata/dataset/engine/datasetops/source/mappable_leaf_op.h"
-#include "minddata/dataset/engine/datasetops/source/sampler/sampler.h"
-#include "minddata/dataset/util/path.h"
-#include "minddata/dataset/util/queue.h"
-#include "minddata/dataset/util/status.h"
-#include "minddata/dataset/util/wait_post.h"
-
-namespace mindspore {
-namespace dataset {
-/// \brief Forward declares.
-template <typename T>
-class Queue;
-
-using SUN397LabelPair = std::pair<std::shared_ptr<Tensor>, uint32_t>;
-
-class SUN397Op : public MappableLeafOp {
- public:
-  /// \brief Constructor.
-  /// \param[in] file_dir Dir directory of SUN397Dataset.
-  /// \param[in] decode Decode the images after reading.
-  /// \param[in] num_workers Num of workers reading images in parallel.
-  /// \param[in] queue_size Connector queue size.
-  /// \param[in] data_schema Schema of data.
-  /// \param[in] sampler Sampler tells SUN397Op what to read.
-  SUN397Op(const std::string &file_dir, bool decode, int32_t num_workers, int32_t queue_size,
-           std::unique_ptr<DataSchema> data_schema, std::shared_ptr<SamplerRT> sampler);
-
-  /// \brief Destructor.
-  ~SUN397Op() = default;
-
-  /// \brief Method derived from RandomAccess Op, enable Sampler to get all ids for each class.
-  /// \param[in] cls_ids Key label, val all ids for this class.
-  /// \return The status code returned.
-  Status GetClassIds(std::map<int32_t, std::vector<int64_t>> *cls_ids) const override;
-
-  /// \brief A print method typically used for debugging.
-  /// \param[out] out The output stream to write output to.
-  /// \param[in] show_all A bool to control if you want to show all info or just a summary.
-  void Print(std::ostream &out, bool show_all) const override;
-
-  /// \param[in] dir Path to the PhotoTour directory.
-  /// \param[in] decode Decode jpg format images.
-  /// \param[out] count Output arg that will hold the minimum of the actual dataset
-  ///     size and numSamples.
-  /// \return The status code returned.
-  static Status CountTotalRows(const std::string &dir, bool decode, int64_t *count);
-
-  /// \brief Op name getter.
-  /// \return Name of the current Op.
-  std::string Name() const override { return "SUN397Op"; }
-
- private:
-  /// \brief Load a tensor row according to a pair.
-  /// \param[in] row_id Id for this tensor row.
-  /// \param[out] row Image & label read into this tensor row.
-  /// \return Status The status code returned
-  Status LoadTensorRow(row_id_type row_id, TensorRow *row);
-
-  /// \brief The content in the given file path.
-  /// \param[in] info_file Info file name.
-  /// \param[out] ans Store the content of the info file.
-  /// \return Status The status code returned
-  Status GetFileContent(const std::string &info_file, std::string *ans);
-
-  /// \brief Load the meta information of categories.
-  /// \param[in] category_meta_name Category file name.
-  /// \return Status The status code returned.
-  Status LoadCategories(const std::string &category_meta_name);
-
-  /// \brief Initialize SUN397Op related var, calls the function to walk all files.
-  /// \return Status The status code returned.
-  Status PrepareData() override;
-
-  /// \brief Private function for computing the assignment of the column name map.
-  /// \return Status The status code returned.
-  Status ComputeColMap() override;
-
-  int64_t buf_cnt_;
-  std::unique_ptr<DataSchema> data_schema_;
-
-  std::string folder_path_;  // directory of image folder
-  const bool decode_;
-  std::map<std::string, uint32_t> categorie2id_;
-  std::vector<std::pair<std::string, uint32_t>> image_path_label_pairs_;
-};
-}  // namespace dataset
-}  // namespace mindspore
-#endif  // MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_SUN397_OP_H_

mindspore/include/mindspore/ccsrc/minddata/dataset/engine/datasetops/source/tedlium_op.h

@@ -1,126 +0,0 @@
-/**
- * Copyright 2021 Huawei Technologies Co., Ltd
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-#ifndef MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_TEDLIUM_OP_H_
-#define MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_TEDLIUM_OP_H_
-
-#include <map>
-#include <memory>
-#include <string>
-#include <vector>
-
-#include "minddata/dataset/core/tensor.h"
-#include "minddata/dataset/engine/datasetops/parallel_op.h"
-#include "minddata/dataset/engine/datasetops/source/mappable_leaf_op.h"
-#include "minddata/dataset/engine/datasetops/source/sampler/sampler.h"
-#include "minddata/dataset/engine/ir/cache/dataset_cache.h"
-
-#include "minddata/dataset/util/status.h"
-#include "minddata/dataset/util/path.h"
-
-namespace mindspore {
-namespace dataset {
-class TedliumOp : public MappableLeafOp {
- public:
-  /// \brief Constructor.
-  /// \param[in] dataset_dir Directory of tedlium dataset.
-  /// \param[in] release Release of tedlium dataset, can be 'release1', 'release2' or 'release3'.
-  /// \param[in] usage Usage of this dataset, if release is release3, can be '', else 'train', 'dev', 'test' or 'all'.
-  /// \param[in] extensions Extensions of the sph file, only '.sph' is valid.
-  /// \param[in] num_parallel_workers Number of workers in parallel.
-  /// \param[in] data_schema Schema of dataset.
-  /// \param[in] sampler Sampler tells TedliumOp what to read.
-  /// \param[in] queue_size Connector queue size.
-  TedliumOp(const std::string &dataset_dir, const std::string &release, const std::string &usage,
-            const std::string &extensions, int32_t num_parallel_workers, std::unique_ptr<DataSchema> data_schema,
-            std::shared_ptr<SamplerRT> sampler, int32_t queue_size);
-
-  /// \brief Destructor.
-  ~TedliumOp() = default;
-
-  /// \brief A print method typically used for debugging.
-  /// \param[in] out Out stream.
-  /// \param[in] show_all Whether to show all information.
-  void Print(std::ostream &out, bool show_all) const override;
-
-  /// \brief Op name getter.
-  std::string Name() const override { return "TedliumOp"; }
-
-  /// \brief Initialize TedliumOp related var, calls the function to walk all files.
-  /// \return Status The status code returned.
-  Status PrepareData() override;
-
-  /// \brief Function to count the number of samples in the TEDLIUM dataset.
-  /// \param[in] dataset_dir Directory of tedlium dataset.
-  /// \param[in] release Release of tedlium dataset.
-  /// \param[in] usage Usage of this dataset, if release is release3, can be '', else 'train', 'dev', 'test' or 'all'.
-  /// \param[in] extensions Extensions of the sph file, only '.sph' is valid.
-  /// \param[in] count Output arg that will hold the actual dataset size.
-  /// \return Status The status code returned.
-  static Status CountTotalRows(const std::string &dataset_dir, const std::string &release, const std::string &usage,
-                               const std::string &extensions, int64_t *count);
-
- private:
-  /// \brief Read stm file.
-  /// \param[in] file_stm_path The path of stm file.
-  /// \param[in] row_line Which line of the file we need to read.
-  /// \param[out] talk_id Talk identifier of the row_line in the file.
-  /// \param[out] speaker_id Speaker identifier of the row_line in the file.
-  /// \param[out] start_time Start time of the row_line in the file.
-  /// \param[out] end_time End time of the row_line in the file.
-  /// \param[out] identifier Identifier of the row_line in the file.
-  /// \param[out] transcript Transcript of the row_line in the file.
-  /// \return Status The status code returned.
-  Status ReadStm(const Path &file_stm_path, int32_t row_line, std::string *talk_id, std::string *speaker_id,
-                 std::string *start_time, std::string *end_time, std::string *identifier, std::string *transcript);
-
-  /// \brief Read sph file.
-  /// \param[in] file_sph_path The path of sph file.
-  /// \param[in] start_time The start_time of row we need to use.
-  /// \param[in] end_time The end_time of row we need to use.
-  /// \param[out] sample_rate Sample rate of the row.
-  /// \param[out] result Waveform result vector of the row.
-  /// \return Status The status code returned.
-  Status ReadSph(const Path &file_sph_path, double start_time, double end_time, int32_t *sample_rate,
-                 std::vector<float> *result);
-
-  /// \brief Read stm files according current release`s usage.
-  /// \param[in] stm_folder The folder of stm files.
-  /// \param[in] release_usage For release1 or release2, use usage_, for release3, "data".
-  /// \return Status The status code returned.
-  Status ReadStmFolderRows(const Path &stm_folder, const std::string &release_usage);
-
-  /// \brief Load a tensor row according to a pair.
-  /// \param[in] row_id Id of row need to load.
-  /// \param[in] row Audio & label read into this tensor row.
-  /// \return Status The status code returned.
-  Status LoadTensorRow(row_id_type row_id, TensorRow *row) override;
-
-  /// \brief Private function for computing the assignment of the column name map.
-  /// \return Status The status code returned.
-  Status ComputeColMap() override;
-
-  const std::string release_;
-  const std::string dataset_dir_;
-  const std::string usage_;
-  const std::string extensions_;
-  std::unique_ptr<DataSchema> data_schema_;
-
-  std::vector<std::vector<std::string> > audio_files_;
-  std::vector<std::string> usage_list_;
-};
-}  // namespace dataset
-}  // namespace mindspore
-#endif  // MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_TEDLIUM_OP_H_

mindspore/include/mindspore/ccsrc/minddata/dataset/engine/datasetops/source/text_file_op.h

@@ -1,124 +0,0 @@
-/**
- * Copyright 2020-2022 Huawei Technologies Co., Ltd
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-#ifndef MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_TEXT_FILE_OP_H_
-#define MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_TEXT_FILE_OP_H_
-
-#include <memory>
-#include <map>
-#include <mutex>
-#include <string>
-#include <utility>
-#include <vector>
-
-#include "minddata/dataset/util/status.h"
-#include "minddata/dataset/util/auto_index.h"
-#include "minddata/dataset/engine/data_schema.h"
-#include "minddata/dataset/engine/datasetops/parallel_op.h"
-#include "minddata/dataset/engine/datasetops/source/nonmappable_leaf_op.h"
-#include "minddata/dataset/util/queue.h"
-#include "minddata/dataset/util/wait_post.h"
-#include "minddata/dataset/engine/jagged_connector.h"
-
-namespace mindspore {
-namespace dataset {
-using StringIndex = AutoIndexObj<std::string>;
-
-class TextFileOp : public NonMappableLeafOp {
- public:
-  // Constructor of TextFileOp
-  // @note The builder class should be used to call this constructor.
-  // @param num_workers - number of worker threads reading data from tf_file files.
-  // @param total_num_rows - number of rows to read
-  // @param dataset_files_list - list of filepaths for the dataset files.
-  // @param data_schema - the data schema object.
-  // @param op_connector_size - size of each queue in the connector that the child operator pulls from.
-  // @param columns_to_load - the names of the columns to load data from.
-  // @param shuffle_files - whether or not to shuffle the files before reading data.
-  // @param equal_rows_per_shard - whether or not to get equal rows for each process.
-  TextFileOp(int32_t num_workers, int64_t total_rows, int32_t worker_connector_size, std::unique_ptr<DataSchema>,
-             std::vector<std::string> text_files_list, int32_t op_connector_size, bool shuffle_files,
-             int32_t num_devices, int32_t device_id);
-
-  // Default destructor
-  ~TextFileOp() = default;
-
-  // A print method typically used for debugging
-  // @param out - The output stream to write output to
-  // @param show_all - A bool to control if you want to show all info or just a summary
-  void Print(std::ostream &out, bool show_all) const override;
-
-  // Instantiates the internal queues and connectors
-  // @return Status - the error code returned
-  Status Init() override;
-
-  // Get total rows in files.
-  // @param files - all text files.
-  // @param count - number of rows.
-  // @return Status - the error coed returned.
-  static Status CountAllFileRows(const std::vector<std::string> &files, int64_t *count);
-
-  // Op name getter
-  // @return Name of the current Op
-  std::string Name() const override { return "TextFileOp"; }
-
-  // DatasetName name getter
-  // \return DatasetName of the current Op
-  virtual std::string DatasetName(bool upper = false) const { return upper ? "TextFile" : "text file"; }
-
-  // File names getter
-  // @return Vector of the input file names
-  std::vector<std::string> FileNames() { return text_files_list_; }
-
- protected:
-  // Parses a single row and puts the data into a tensor table.
-  // @param line - the content of the row.
-  // @param tensor_table - the tensor table to put the parsed data in.
-  // @param row - the id of the row filled in the tensor table.
-  // @return Status - the error code returned.
-  Status LoadTensor(const std::string &line, TensorRow *out_row) const;
-
-  // Reads a text file and loads the data into multiple TensorRows.
-  // @param file - the file to read.
-  // @param start_offset - the start offset of file.
-  // @param end_offset - the end offset of file.
-  // @param worker_id - the id of the worker that is executing this function.
-  // @return Status - the error code returned.
-  Status LoadFile(const std::string &file, int64_t start_offset, int64_t end_offset, int32_t worker_id) override;
-
-  // Calculate number of rows in each shard.
-  // @return Status - the error code returned.
-  Status CalculateNumRowsPerShard() override;
-
-  // Fill the IOBlockQueue.
-  // @para i_keys - keys of file to fill to the IOBlockQueue
-  // @return Status - the error code returned.
-  Status FillIOBlockQueue(const std::vector<int64_t> &i_keys) override;
-
-  // Private function for computing the assignment of the column name map.
-  // @return - Status
-  Status ComputeColMap() override;
-
-  // Count number of rows in each file.
-  // @param file - txt file name.
-  // @return int64_t - the total number of rows in file.
-  virtual int64_t CountTotalRows(const std::string &file);
-
-  std::vector<std::string> text_files_list_;
-  std::unique_ptr<DataSchema> data_schema_;
-};
-}  // namespace dataset
-}  // namespace mindspore
-#endif  // MINDSPORE_CCSRC_MINDDATA_DATASET_ENGINE_DATASETOPS_SOURCE_TEXT_FILE_OP_H_