use of software.amazon.awssdk.services.textract.model.DetectDocumentTextRequest in project aws-doc-sdk-examples by awsdocs.
the class DetectDocumentText method detectDocText.
// snippet-start:[textract.java2._detect_doc_text.main]
public static void detectDocText(TextractClient textractClient, String sourceDoc) {
try {
InputStream sourceStream = new FileInputStream(new File(sourceDoc));
SdkBytes sourceBytes = SdkBytes.fromInputStream(sourceStream);
// Get the input Document object as bytes
Document myDoc = Document.builder().bytes(sourceBytes).build();
DetectDocumentTextRequest detectDocumentTextRequest = DetectDocumentTextRequest.builder().document(myDoc).build();
// Invoke the Detect operation
DetectDocumentTextResponse textResponse = textractClient.detectDocumentText(detectDocumentTextRequest);
List<Block> docInfo = textResponse.blocks();
Iterator<Block> blockIterator = docInfo.iterator();
while (blockIterator.hasNext()) {
Block block = blockIterator.next();
System.out.println("The block type is " + block.blockType().toString());
}
DocumentMetadata documentMetadata = textResponse.documentMetadata();
System.out.println("The number of pages in the document is " + documentMetadata.pages());
} catch (TextractException | FileNotFoundException e) {
System.err.println(e.getMessage());
System.exit(1);
}
}
use of software.amazon.awssdk.services.textract.model.DetectDocumentTextRequest in project aws-doc-sdk-examples by awsdocs.
the class DetectDocumentTextS3 method detectDocTextS3.
// snippet-start:[textract.java2._detect_s3_text.main]
public static void detectDocTextS3(TextractClient textractClient, String bucketName, String docName) {
try {
S3Object s3Object = S3Object.builder().bucket(bucketName).name(docName).build();
// Create a Document object and reference the s3Object instance
Document myDoc = Document.builder().s3Object(s3Object).build();
// Create a DetectDocumentTextRequest object
DetectDocumentTextRequest detectDocumentTextRequest = DetectDocumentTextRequest.builder().document(myDoc).build();
// Invoke the detectDocumentText method
DetectDocumentTextResponse textResponse = textractClient.detectDocumentText(detectDocumentTextRequest);
List<Block> docInfo = textResponse.blocks();
Iterator<Block> blockIterator = docInfo.iterator();
while (blockIterator.hasNext()) {
Block block = blockIterator.next();
System.out.println("The block type is " + block.blockType().toString());
}
DocumentMetadata documentMetadata = textResponse.documentMetadata();
System.out.println("The number of pages in the document is " + documentMetadata.pages());
} catch (TextractException e) {
System.err.println(e.getMessage());
System.exit(1);
}
}
Aggregations