* The input properties for an inference job. The document reader config field * applies only to non-text inputs for custom analysis. *
*/ public class InputDataConfig implements Serializable { /** ** The Amazon S3 URI for the input data. The URI must be in 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 data 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.
*
* Constraints:
* Length: - 1024
* Pattern: s3://[a-z0-9][\.\-a-z0-9]{1,61}[a-z0-9](/.*)?
*/
private String s3Uri;
/**
*
* Specifies how the text in an input file should be processed: *
*
* ONE_DOC_PER_FILE - Each file is considered a separate
* document. Use this option when you are processing large documents, such
* as newspaper articles or scientific papers.
*
* ONE_DOC_PER_LINE - Each line in a file is considered a
* separate document. Use this option when you are processing many short
* documents, such as text messages.
*
* Constraints:
* Allowed Values: ONE_DOC_PER_FILE, ONE_DOC_PER_LINE
*/
private String inputFormat;
/**
*
* Provides configuration parameters to override the default actions for * extracting text from PDF documents and image files. *
*/ private DocumentReaderConfig documentReaderConfig; /** ** The Amazon S3 URI for the input data. The URI must be in 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 data 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.
*
* Constraints:
* Length: - 1024
* Pattern: s3://[a-z0-9][\.\-a-z0-9]{1,61}[a-z0-9](/.*)?
*
* @return
* The Amazon S3 URI for the input data. The URI must be in 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 data 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.
*
* The Amazon S3 URI for the input data. The URI must be in 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 data 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.
*
* Constraints:
* Length: - 1024
* Pattern: s3://[a-z0-9][\.\-a-z0-9]{1,61}[a-z0-9](/.*)?
*
* @param s3Uri
* The Amazon S3 URI for the input data. The URI must be in 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 data 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.
*
* The Amazon S3 URI for the input data. The URI must be in 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 data 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.
*
* Returns a reference to this object so that method calls can be chained * together. *
* Constraints:
* Length: - 1024
* Pattern: s3://[a-z0-9][\.\-a-z0-9]{1,61}[a-z0-9](/.*)?
*
* @param s3Uri
* The Amazon S3 URI for the input data. The URI must be in 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 data 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.
*
* Specifies how the text in an input file should be processed: *
*
* ONE_DOC_PER_FILE - Each file is considered a separate
* document. Use this option when you are processing large documents, such
* as newspaper articles or scientific papers.
*
* ONE_DOC_PER_LINE - Each line in a file is considered a
* separate document. Use this option when you are processing many short
* documents, such as text messages.
*
* Constraints:
* Allowed Values: ONE_DOC_PER_FILE, ONE_DOC_PER_LINE
*
* @return
* Specifies how the text in an input file should be processed: *
*
* ONE_DOC_PER_FILE - Each file is considered a
* separate document. Use this option when you are processing large
* documents, such as newspaper articles or scientific papers.
*
* ONE_DOC_PER_LINE - Each line in a file is considered
* a separate document. Use this option when you are processing many
* short documents, such as text messages.
*
* Specifies how the text in an input file should be processed: *
*
* ONE_DOC_PER_FILE - Each file is considered a separate
* document. Use this option when you are processing large documents, such
* as newspaper articles or scientific papers.
*
* ONE_DOC_PER_LINE - Each line in a file is considered a
* separate document. Use this option when you are processing many short
* documents, such as text messages.
*
* Constraints:
* Allowed Values: ONE_DOC_PER_FILE, ONE_DOC_PER_LINE
*
* @param inputFormat
* Specifies how the text in an input file should be processed: *
*
* ONE_DOC_PER_FILE - Each file is considered a
* separate document. Use this option when you are processing
* large documents, such as newspaper articles or scientific
* papers.
*
* ONE_DOC_PER_LINE - Each line in a file is
* considered a separate document. Use this option when you are
* processing many short documents, such as text messages.
*
* Specifies how the text in an input file should be processed: *
*
* ONE_DOC_PER_FILE - Each file is considered a separate
* document. Use this option when you are processing large documents, such
* as newspaper articles or scientific papers.
*
* ONE_DOC_PER_LINE - Each line in a file is considered a
* separate document. Use this option when you are processing many short
* documents, such as text messages.
*
* Returns a reference to this object so that method calls can be chained * together. *
* Constraints:
* Allowed Values: ONE_DOC_PER_FILE, ONE_DOC_PER_LINE
*
* @param inputFormat
* Specifies how the text in an input file should be processed: *
*
* ONE_DOC_PER_FILE - Each file is considered a
* separate document. Use this option when you are processing
* large documents, such as newspaper articles or scientific
* papers.
*
* ONE_DOC_PER_LINE - Each line in a file is
* considered a separate document. Use this option when you are
* processing many short documents, such as text messages.
*
* Specifies how the text in an input file should be processed: *
*
* ONE_DOC_PER_FILE - Each file is considered a separate
* document. Use this option when you are processing large documents, such
* as newspaper articles or scientific papers.
*
* ONE_DOC_PER_LINE - Each line in a file is considered a
* separate document. Use this option when you are processing many short
* documents, such as text messages.
*
* Constraints:
* Allowed Values: ONE_DOC_PER_FILE, ONE_DOC_PER_LINE
*
* @param inputFormat
* Specifies how the text in an input file should be processed: *
*
* ONE_DOC_PER_FILE - Each file is considered a
* separate document. Use this option when you are processing
* large documents, such as newspaper articles or scientific
* papers.
*
* ONE_DOC_PER_LINE - Each line in a file is
* considered a separate document. Use this option when you are
* processing many short documents, such as text messages.
*
* Specifies how the text in an input file should be processed: *
*
* ONE_DOC_PER_FILE - Each file is considered a separate
* document. Use this option when you are processing large documents, such
* as newspaper articles or scientific papers.
*
* ONE_DOC_PER_LINE - Each line in a file is considered a
* separate document. Use this option when you are processing many short
* documents, such as text messages.
*
* Returns a reference to this object so that method calls can be chained * together. *
* Constraints:
* Allowed Values: ONE_DOC_PER_FILE, ONE_DOC_PER_LINE
*
* @param inputFormat
* Specifies how the text in an input file should be processed: *
*
* ONE_DOC_PER_FILE - Each file is considered a
* separate document. Use this option when you are processing
* large documents, such as newspaper articles or scientific
* papers.
*
* ONE_DOC_PER_LINE - Each line in a file is
* considered a separate document. Use this option when you are
* processing many short documents, such as text messages.
*
* Provides configuration parameters to override the default actions for * extracting text from PDF documents and image files. *
* * @return* Provides configuration parameters to override the default actions * for extracting text from PDF documents and image files. *
*/ public DocumentReaderConfig getDocumentReaderConfig() { return documentReaderConfig; } /** ** Provides configuration parameters to override the default actions for * extracting text from PDF documents and image files. *
* * @param documentReaderConfig* Provides configuration parameters to override the default * actions for extracting text from PDF documents and image * files. *
*/ public void setDocumentReaderConfig(DocumentReaderConfig documentReaderConfig) { this.documentReaderConfig = documentReaderConfig; } /** ** Provides configuration parameters to override the default actions for * extracting text from PDF documents and image files. *
** Returns a reference to this object so that method calls can be chained * together. * * @param documentReaderConfig
* Provides configuration parameters to override the default * actions for extracting text from PDF documents and image * files. *
* @return A reference to this updated object so that method calls can be * chained together. */ public InputDataConfig withDocumentReaderConfig(DocumentReaderConfig documentReaderConfig) { this.documentReaderConfig = documentReaderConfig; return this; } /** * Returns a string representation of this object; useful for testing and * debugging. * * @return A string representation of this object. * @see java.lang.Object#toString() */ @Override public String toString() { StringBuilder sb = new StringBuilder(); sb.append("{"); if (getS3Uri() != null) sb.append("S3Uri: " + getS3Uri() + ","); if (getInputFormat() != null) sb.append("InputFormat: " + getInputFormat() + ","); if (getDocumentReaderConfig() != null) sb.append("DocumentReaderConfig: " + getDocumentReaderConfig()); sb.append("}"); return sb.toString(); } @Override public int hashCode() { final int prime = 31; int hashCode = 1; hashCode = prime * hashCode + ((getS3Uri() == null) ? 0 : getS3Uri().hashCode()); hashCode = prime * hashCode + ((getInputFormat() == null) ? 0 : getInputFormat().hashCode()); hashCode = prime * hashCode + ((getDocumentReaderConfig() == null) ? 0 : getDocumentReaderConfig().hashCode()); return hashCode; } @Override public boolean equals(Object obj) { if (this == obj) return true; if (obj == null) return false; if (obj instanceof InputDataConfig == false) return false; InputDataConfig other = (InputDataConfig) obj; if (other.getS3Uri() == null ^ this.getS3Uri() == null) return false; if (other.getS3Uri() != null && other.getS3Uri().equals(this.getS3Uri()) == false) return false; if (other.getInputFormat() == null ^ this.getInputFormat() == null) return false; if (other.getInputFormat() != null && other.getInputFormat().equals(this.getInputFormat()) == 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; } }