/* * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All Rights Reserved. * * Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance with * the License. A copy of the License is located at * * http://aws.amazon.com/apache2.0 * * or in the "license" file accompanying this file. This file 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. */ package com.amazonaws.services.comprehend.model; import java.io.Serializable; import javax.annotation.Generated; import com.amazonaws.protocol.StructuredPojo; import com.amazonaws.protocol.ProtocolMarshaller; /** *

* The input properties for training a document classifier. *

*

* For more information on how the input file is formatted, see Preparing training data in the * Comprehend Developer Guide. *

* * @see AWS API Documentation */ @Generated("com.amazonaws:aws-java-sdk-code-generator") public class DocumentClassifierInputDataConfig implements Serializable, Cloneable, StructuredPojo { /** *

* The format of your training data: *

* *

* If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default. *

*/ private String dataFormat; /** *

* The Amazon S3 URI for the input data. The S3 bucket must be in the same Region as the API endpoint that you are * calling. The URI can point to a single input file or it can provide the prefix for a collection of input files. *

*

* For example, if you use the URI S3://bucketName/prefix, if the prefix is a single file, Amazon * Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend uses all of * them as input. *

*

* This parameter is required if you set DataFormat to COMPREHEND_CSV. *

*/ private String s3Uri; /** *

* This specifies the Amazon S3 location where the test annotations for an entity recognizer are located. The URI * must be in the same Amazon Web Services Region as the API endpoint that you are calling. *

*/ private String testS3Uri; /** *

* Indicates the delimiter used to separate each label for training a multi-label classifier. The default delimiter * between labels is a pipe (|). You can use a different character as a delimiter (if it's an allowed character) by * specifying it under Delimiter for labels. If the training documents use a delimiter other than the default or the * delimiter you specify, the labels on that line will be combined to make a single unique label, such as * LABELLABELLABEL. *

*/ private String labelDelimiter; /** *

* A list of augmented manifest files that provide training data for your custom model. An augmented manifest file * is a labeled dataset that is produced by Amazon SageMaker Ground Truth. *

*

* This parameter is required if you set DataFormat to AUGMENTED_MANIFEST. *

*/ private java.util.List augmentedManifests; /** *

* The type of input documents for training the model. Provide plain-text documents to create a plain-text model, * and provide semi-structured documents to create a native model. *

*/ private String documentType; /** *

* The S3 location of the training documents. This parameter is required in a request to create a native classifier * model. *

*/ private DocumentClassifierDocuments documents; private DocumentReaderConfig documentReaderConfig; /** *

* The format of your training data: *

* *

* If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default. *

* * @param dataFormat * The format of your training data:

* *

* If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default. * @see DocumentClassifierDataFormat */ public void setDataFormat(String dataFormat) { this.dataFormat = dataFormat; } /** *

* The format of your training data: *

* *

* If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default. *

* * @return The format of your training data:

* *

* If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default. * @see DocumentClassifierDataFormat */ public String getDataFormat() { return this.dataFormat; } /** *

* The format of your training data: *

* *

* If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default. *

* * @param dataFormat * The format of your training data:

* *

* If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default. * @return Returns a reference to this object so that method calls can be chained together. * @see DocumentClassifierDataFormat */ public DocumentClassifierInputDataConfig withDataFormat(String dataFormat) { setDataFormat(dataFormat); return this; } /** *

* The format of your training data: *

* *

* If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default. *

* * @param dataFormat * The format of your training data:

* *

* If you don't specify a value, Amazon Comprehend uses COMPREHEND_CSV as the default. * @return Returns a reference to this object so that method calls can be chained together. * @see DocumentClassifierDataFormat */ public DocumentClassifierInputDataConfig withDataFormat(DocumentClassifierDataFormat dataFormat) { this.dataFormat = dataFormat.toString(); return this; } /** *

* The Amazon S3 URI for the input data. The S3 bucket must be in the same Region as the API endpoint that you are * calling. The URI can point to a single input file or it can provide the prefix for a collection of input files. *

*

* For example, if you use the URI S3://bucketName/prefix, if the prefix is a single file, Amazon * Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend uses all of * them as input. *

*

* This parameter is required if you set DataFormat to COMPREHEND_CSV. *

* * @param s3Uri * The Amazon S3 URI for the input data. The S3 bucket must be in the same Region as the API endpoint that * you are calling. The URI can point to a single input file or it can provide the prefix for a collection of * input files.

*

* For example, if you use the URI S3://bucketName/prefix, if the prefix is a single file, * Amazon Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend * uses all of them as input. *

*

* This parameter is required if you set DataFormat to COMPREHEND_CSV. */ public void setS3Uri(String s3Uri) { this.s3Uri = s3Uri; } /** *

* The Amazon S3 URI for the input data. The S3 bucket must be in the same Region as the API endpoint that you are * calling. The URI can point to a single input file or it can provide the prefix for a collection of input files. *

*

* For example, if you use the URI S3://bucketName/prefix, if the prefix is a single file, Amazon * Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend uses all of * them as input. *

*

* This parameter is required if you set DataFormat to COMPREHEND_CSV. *

* * @return The Amazon S3 URI for the input data. The S3 bucket must be in the same Region as the API endpoint that * you are calling. The URI can point to a single input file or it can provide the prefix for a collection * of input files.

*

* For example, if you use the URI S3://bucketName/prefix, if the prefix is a single file, * Amazon Comprehend uses that file as input. If more than one file begins with the prefix, Amazon * Comprehend uses all of them as input. *

*

* This parameter is required if you set DataFormat to COMPREHEND_CSV. */ public String getS3Uri() { return this.s3Uri; } /** *

* The Amazon S3 URI for the input data. The S3 bucket must be in the same Region as the API endpoint that you are * calling. The URI can point to a single input file or it can provide the prefix for a collection of input files. *

*

* For example, if you use the URI S3://bucketName/prefix, if the prefix is a single file, Amazon * Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend uses all of * them as input. *

*

* This parameter is required if you set DataFormat to COMPREHEND_CSV. *

* * @param s3Uri * The Amazon S3 URI for the input data. The S3 bucket must be in the same Region as the API endpoint that * you are calling. The URI can point to a single input file or it can provide the prefix for a collection of * input files.

*

* For example, if you use the URI S3://bucketName/prefix, if the prefix is a single file, * Amazon Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend * uses all of them as input. *

*

* This parameter is required if you set DataFormat to COMPREHEND_CSV. * @return Returns a reference to this object so that method calls can be chained together. */ public DocumentClassifierInputDataConfig withS3Uri(String s3Uri) { setS3Uri(s3Uri); return this; } /** *

* This specifies the Amazon S3 location where the test annotations for an entity recognizer are located. The URI * must be in the same Amazon Web Services Region as the API endpoint that you are calling. *

* * @param testS3Uri * This specifies the Amazon S3 location where the test annotations for an entity recognizer are located. The * URI must be in the same Amazon Web Services Region as the API endpoint that you are calling. */ public void setTestS3Uri(String testS3Uri) { this.testS3Uri = testS3Uri; } /** *

* This specifies the Amazon S3 location where the test annotations for an entity recognizer are located. The URI * must be in the same Amazon Web Services Region as the API endpoint that you are calling. *

* * @return This specifies the Amazon S3 location where the test annotations for an entity recognizer are located. * The URI must be in the same Amazon Web Services Region as the API endpoint that you are calling. */ public String getTestS3Uri() { return this.testS3Uri; } /** *

* This specifies the Amazon S3 location where the test annotations for an entity recognizer are located. The URI * must be in the same Amazon Web Services Region as the API endpoint that you are calling. *

* * @param testS3Uri * This specifies the Amazon S3 location where the test annotations for an entity recognizer are located. The * URI must be in the same Amazon Web Services Region as the API endpoint that you are calling. * @return Returns a reference to this object so that method calls can be chained together. */ public DocumentClassifierInputDataConfig withTestS3Uri(String testS3Uri) { setTestS3Uri(testS3Uri); return this; } /** *

* Indicates the delimiter used to separate each label for training a multi-label classifier. The default delimiter * between labels is a pipe (|). You can use a different character as a delimiter (if it's an allowed character) by * specifying it under Delimiter for labels. If the training documents use a delimiter other than the default or the * delimiter you specify, the labels on that line will be combined to make a single unique label, such as * LABELLABELLABEL. *

* * @param labelDelimiter * Indicates the delimiter used to separate each label for training a multi-label classifier. The default * delimiter between labels is a pipe (|). You can use a different character as a delimiter (if it's an * allowed character) by specifying it under Delimiter for labels. If the training documents use a delimiter * other than the default or the delimiter you specify, the labels on that line will be combined to make a * single unique label, such as LABELLABELLABEL. */ public void setLabelDelimiter(String labelDelimiter) { this.labelDelimiter = labelDelimiter; } /** *

* Indicates the delimiter used to separate each label for training a multi-label classifier. The default delimiter * between labels is a pipe (|). You can use a different character as a delimiter (if it's an allowed character) by * specifying it under Delimiter for labels. If the training documents use a delimiter other than the default or the * delimiter you specify, the labels on that line will be combined to make a single unique label, such as * LABELLABELLABEL. *

* * @return Indicates the delimiter used to separate each label for training a multi-label classifier. The default * delimiter between labels is a pipe (|). You can use a different character as a delimiter (if it's an * allowed character) by specifying it under Delimiter for labels. If the training documents use a delimiter * other than the default or the delimiter you specify, the labels on that line will be combined to make a * single unique label, such as LABELLABELLABEL. */ public String getLabelDelimiter() { return this.labelDelimiter; } /** *

* Indicates the delimiter used to separate each label for training a multi-label classifier. The default delimiter * between labels is a pipe (|). You can use a different character as a delimiter (if it's an allowed character) by * specifying it under Delimiter for labels. If the training documents use a delimiter other than the default or the * delimiter you specify, the labels on that line will be combined to make a single unique label, such as * LABELLABELLABEL. *

* * @param labelDelimiter * Indicates the delimiter used to separate each label for training a multi-label classifier. The default * delimiter between labels is a pipe (|). You can use a different character as a delimiter (if it's an * allowed character) by specifying it under Delimiter for labels. If the training documents use a delimiter * other than the default or the delimiter you specify, the labels on that line will be combined to make a * single unique label, such as LABELLABELLABEL. * @return Returns a reference to this object so that method calls can be chained together. */ public DocumentClassifierInputDataConfig withLabelDelimiter(String labelDelimiter) { setLabelDelimiter(labelDelimiter); return this; } /** *

* A list of augmented manifest files that provide training data for your custom model. An augmented manifest file * is a labeled dataset that is produced by Amazon SageMaker Ground Truth. *

*

* This parameter is required if you set DataFormat to AUGMENTED_MANIFEST. *

* * @return A list of augmented manifest files that provide training data for your custom model. An augmented * manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.

*

* This parameter is required if you set DataFormat to AUGMENTED_MANIFEST. */ public java.util.List getAugmentedManifests() { return augmentedManifests; } /** *

* A list of augmented manifest files that provide training data for your custom model. An augmented manifest file * is a labeled dataset that is produced by Amazon SageMaker Ground Truth. *

*

* This parameter is required if you set DataFormat to AUGMENTED_MANIFEST. *

* * @param augmentedManifests * A list of augmented manifest files that provide training data for your custom model. An augmented manifest * file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.

*

* This parameter is required if you set DataFormat to AUGMENTED_MANIFEST. */ public void setAugmentedManifests(java.util.Collection augmentedManifests) { if (augmentedManifests == null) { this.augmentedManifests = null; return; } this.augmentedManifests = new java.util.ArrayList(augmentedManifests); } /** *

* A list of augmented manifest files that provide training data for your custom model. An augmented manifest file * is a labeled dataset that is produced by Amazon SageMaker Ground Truth. *

*

* This parameter is required if you set DataFormat to AUGMENTED_MANIFEST. *

*

* NOTE: This method appends the values to the existing list (if any). Use * {@link #setAugmentedManifests(java.util.Collection)} or {@link #withAugmentedManifests(java.util.Collection)} if * you want to override the existing values. *

* * @param augmentedManifests * A list of augmented manifest files that provide training data for your custom model. An augmented manifest * file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.

*

* This parameter is required if you set DataFormat to AUGMENTED_MANIFEST. * @return Returns a reference to this object so that method calls can be chained together. */ public DocumentClassifierInputDataConfig withAugmentedManifests(AugmentedManifestsListItem... augmentedManifests) { if (this.augmentedManifests == null) { setAugmentedManifests(new java.util.ArrayList(augmentedManifests.length)); } for (AugmentedManifestsListItem ele : augmentedManifests) { this.augmentedManifests.add(ele); } return this; } /** *

* A list of augmented manifest files that provide training data for your custom model. An augmented manifest file * is a labeled dataset that is produced by Amazon SageMaker Ground Truth. *

*

* This parameter is required if you set DataFormat to AUGMENTED_MANIFEST. *

* * @param augmentedManifests * A list of augmented manifest files that provide training data for your custom model. An augmented manifest * file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.

*

* This parameter is required if you set DataFormat to AUGMENTED_MANIFEST. * @return Returns a reference to this object so that method calls can be chained together. */ public DocumentClassifierInputDataConfig withAugmentedManifests(java.util.Collection augmentedManifests) { setAugmentedManifests(augmentedManifests); return this; } /** *

* The type of input documents for training the model. Provide plain-text documents to create a plain-text model, * and provide semi-structured documents to create a native model. *

* * @param documentType * The type of input documents for training the model. Provide plain-text documents to create a plain-text * model, and provide semi-structured documents to create a native model. * @see DocumentClassifierDocumentTypeFormat */ public void setDocumentType(String documentType) { this.documentType = documentType; } /** *

* The type of input documents for training the model. Provide plain-text documents to create a plain-text model, * and provide semi-structured documents to create a native model. *

* * @return The type of input documents for training the model. Provide plain-text documents to create a plain-text * model, and provide semi-structured documents to create a native model. * @see DocumentClassifierDocumentTypeFormat */ public String getDocumentType() { return this.documentType; } /** *

* The type of input documents for training the model. Provide plain-text documents to create a plain-text model, * and provide semi-structured documents to create a native model. *

* * @param documentType * The type of input documents for training the model. Provide plain-text documents to create a plain-text * model, and provide semi-structured documents to create a native model. * @return Returns a reference to this object so that method calls can be chained together. * @see DocumentClassifierDocumentTypeFormat */ public DocumentClassifierInputDataConfig withDocumentType(String documentType) { setDocumentType(documentType); return this; } /** *

* The type of input documents for training the model. Provide plain-text documents to create a plain-text model, * and provide semi-structured documents to create a native model. *

* * @param documentType * The type of input documents for training the model. Provide plain-text documents to create a plain-text * model, and provide semi-structured documents to create a native model. * @return Returns a reference to this object so that method calls can be chained together. * @see DocumentClassifierDocumentTypeFormat */ public DocumentClassifierInputDataConfig withDocumentType(DocumentClassifierDocumentTypeFormat documentType) { this.documentType = documentType.toString(); return this; } /** *

* The S3 location of the training documents. This parameter is required in a request to create a native classifier * model. *

* * @param documents * The S3 location of the training documents. This parameter is required in a request to create a native * classifier model. */ public void setDocuments(DocumentClassifierDocuments documents) { this.documents = documents; } /** *

* The S3 location of the training documents. This parameter is required in a request to create a native classifier * model. *

* * @return The S3 location of the training documents. This parameter is required in a request to create a native * classifier model. */ public DocumentClassifierDocuments getDocuments() { return this.documents; } /** *

* The S3 location of the training documents. This parameter is required in a request to create a native classifier * model. *

* * @param documents * The S3 location of the training documents. This parameter is required in a request to create a native * classifier model. * @return Returns a reference to this object so that method calls can be chained together. */ public DocumentClassifierInputDataConfig withDocuments(DocumentClassifierDocuments documents) { setDocuments(documents); return this; } /** * @param documentReaderConfig */ public void setDocumentReaderConfig(DocumentReaderConfig documentReaderConfig) { this.documentReaderConfig = documentReaderConfig; } /** * @return */ public DocumentReaderConfig getDocumentReaderConfig() { return this.documentReaderConfig; } /** * @param documentReaderConfig * @return Returns a reference to this object so that method calls can be chained together. */ public DocumentClassifierInputDataConfig withDocumentReaderConfig(DocumentReaderConfig documentReaderConfig) { setDocumentReaderConfig(documentReaderConfig); return this; } /** * Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be * redacted from this string using a placeholder value. * * @return A string representation of this object. * * @see java.lang.Object#toString() */ @Override public String toString() { StringBuilder sb = new StringBuilder(); sb.append("{"); if (getDataFormat() != null) sb.append("DataFormat: ").append(getDataFormat()).append(","); if (getS3Uri() != null) sb.append("S3Uri: ").append(getS3Uri()).append(","); if (getTestS3Uri() != null) sb.append("TestS3Uri: ").append(getTestS3Uri()).append(","); if (getLabelDelimiter() != null) sb.append("LabelDelimiter: ").append(getLabelDelimiter()).append(","); if (getAugmentedManifests() != null) sb.append("AugmentedManifests: ").append(getAugmentedManifests()).append(","); if (getDocumentType() != null) sb.append("DocumentType: ").append(getDocumentType()).append(","); if (getDocuments() != null) sb.append("Documents: ").append(getDocuments()).append(","); if (getDocumentReaderConfig() != null) sb.append("DocumentReaderConfig: ").append(getDocumentReaderConfig()); sb.append("}"); return sb.toString(); } @Override public boolean equals(Object obj) { if (this == obj) return true; if (obj == null) return false; if (obj instanceof DocumentClassifierInputDataConfig == false) return false; DocumentClassifierInputDataConfig other = (DocumentClassifierInputDataConfig) obj; if (other.getDataFormat() == null ^ this.getDataFormat() == null) return false; if (other.getDataFormat() != null && other.getDataFormat().equals(this.getDataFormat()) == false) return false; if (other.getS3Uri() == null ^ this.getS3Uri() == null) return false; if (other.getS3Uri() != null && other.getS3Uri().equals(this.getS3Uri()) == false) return false; if (other.getTestS3Uri() == null ^ this.getTestS3Uri() == null) return false; if (other.getTestS3Uri() != null && other.getTestS3Uri().equals(this.getTestS3Uri()) == false) return false; if (other.getLabelDelimiter() == null ^ this.getLabelDelimiter() == null) return false; if (other.getLabelDelimiter() != null && other.getLabelDelimiter().equals(this.getLabelDelimiter()) == false) return false; if (other.getAugmentedManifests() == null ^ this.getAugmentedManifests() == null) return false; if (other.getAugmentedManifests() != null && other.getAugmentedManifests().equals(this.getAugmentedManifests()) == false) return false; if (other.getDocumentType() == null ^ this.getDocumentType() == null) return false; if (other.getDocumentType() != null && other.getDocumentType().equals(this.getDocumentType()) == false) return false; if (other.getDocuments() == null ^ this.getDocuments() == null) return false; if (other.getDocuments() != null && other.getDocuments().equals(this.getDocuments()) == false) return false; if (other.getDocumentReaderConfig() == null ^ this.getDocumentReaderConfig() == null) return false; if (other.getDocumentReaderConfig() != null && other.getDocumentReaderConfig().equals(this.getDocumentReaderConfig()) == false) return false; return true; } @Override public int hashCode() { final int prime = 31; int hashCode = 1; hashCode = prime * hashCode + ((getDataFormat() == null) ? 0 : getDataFormat().hashCode()); hashCode = prime * hashCode + ((getS3Uri() == null) ? 0 : getS3Uri().hashCode()); hashCode = prime * hashCode + ((getTestS3Uri() == null) ? 0 : getTestS3Uri().hashCode()); hashCode = prime * hashCode + ((getLabelDelimiter() == null) ? 0 : getLabelDelimiter().hashCode()); hashCode = prime * hashCode + ((getAugmentedManifests() == null) ? 0 : getAugmentedManifests().hashCode()); hashCode = prime * hashCode + ((getDocumentType() == null) ? 0 : getDocumentType().hashCode()); hashCode = prime * hashCode + ((getDocuments() == null) ? 0 : getDocuments().hashCode()); hashCode = prime * hashCode + ((getDocumentReaderConfig() == null) ? 0 : getDocumentReaderConfig().hashCode()); return hashCode; } @Override public DocumentClassifierInputDataConfig clone() { try { return (DocumentClassifierInputDataConfig) super.clone(); } catch (CloneNotSupportedException e) { throw new IllegalStateException("Got a CloneNotSupportedException from Object.clone() " + "even though we're Cloneable!", e); } } @com.amazonaws.annotation.SdkInternalApi @Override public void marshall(ProtocolMarshaller protocolMarshaller) { com.amazonaws.services.comprehend.model.transform.DocumentClassifierInputDataConfigMarshaller.getInstance().marshall(this, protocolMarshaller); } }