Search in sources :

Example 1 with Document

use of software.amazon.awssdk.services.textract.model.Document 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);
    }
}
Also used : FileInputStream(java.io.FileInputStream) InputStream(java.io.InputStream) TextractException(software.amazon.awssdk.services.textract.model.TextractException) FileNotFoundException(java.io.FileNotFoundException) Document(software.amazon.awssdk.services.textract.model.Document) DetectDocumentTextRequest(software.amazon.awssdk.services.textract.model.DetectDocumentTextRequest) FileInputStream(java.io.FileInputStream) DetectDocumentTextResponse(software.amazon.awssdk.services.textract.model.DetectDocumentTextResponse) SdkBytes(software.amazon.awssdk.core.SdkBytes) DocumentMetadata(software.amazon.awssdk.services.textract.model.DocumentMetadata) Block(software.amazon.awssdk.services.textract.model.Block) File(java.io.File)

Example 2 with Document

use of software.amazon.awssdk.services.textract.model.Document 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);
    }
}
Also used : DetectDocumentTextResponse(software.amazon.awssdk.services.textract.model.DetectDocumentTextResponse) DocumentMetadata(software.amazon.awssdk.services.textract.model.DocumentMetadata) TextractException(software.amazon.awssdk.services.textract.model.TextractException) Block(software.amazon.awssdk.services.textract.model.Block) S3Object(software.amazon.awssdk.services.textract.model.S3Object) Document(software.amazon.awssdk.services.textract.model.Document) DetectDocumentTextRequest(software.amazon.awssdk.services.textract.model.DetectDocumentTextRequest)

Example 3 with Document

use of software.amazon.awssdk.services.textract.model.Document in project aws-doc-sdk-examples by awsdocs.

the class AnalyzeDocument method analyzeDoc.

// snippet-start:[textract.java2._analyze_doc.main]
public static void analyzeDoc(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();
        List<FeatureType> featureTypes = new ArrayList<FeatureType>();
        featureTypes.add(FeatureType.FORMS);
        featureTypes.add(FeatureType.TABLES);
        AnalyzeDocumentRequest analyzeDocumentRequest = AnalyzeDocumentRequest.builder().featureTypes(featureTypes).document(myDoc).build();
        AnalyzeDocumentResponse analyzeDocument = textractClient.analyzeDocument(analyzeDocumentRequest);
        List<Block> docInfo = analyzeDocument.blocks();
        Iterator<Block> blockIterator = docInfo.iterator();
        while (blockIterator.hasNext()) {
            Block block = blockIterator.next();
            System.out.println("The block type is " + block.blockType().toString());
        }
    } catch (TextractException | FileNotFoundException e) {
        System.err.println(e.getMessage());
        System.exit(1);
    }
}
Also used : FeatureType(software.amazon.awssdk.services.textract.model.FeatureType) FileInputStream(java.io.FileInputStream) InputStream(java.io.InputStream) TextractException(software.amazon.awssdk.services.textract.model.TextractException) ArrayList(java.util.ArrayList) FileNotFoundException(java.io.FileNotFoundException) Document(software.amazon.awssdk.services.textract.model.Document) AnalyzeDocumentResponse(software.amazon.awssdk.services.textract.model.AnalyzeDocumentResponse) FileInputStream(java.io.FileInputStream) SdkBytes(software.amazon.awssdk.core.SdkBytes) Block(software.amazon.awssdk.services.textract.model.Block) File(java.io.File) AnalyzeDocumentRequest(software.amazon.awssdk.services.textract.model.AnalyzeDocumentRequest)

Example 4 with Document

use of software.amazon.awssdk.services.textract.model.Document in project aws-doc-sdk-examples by awsdocs.

the class TextractService method analyzeDoc.

public String analyzeDoc(byte[] bytes) {
    List myList = new ArrayList<String>();
    try {
        Region region = Region.US_EAST_2;
        TextractClient textractClient = TextractClient.builder().region(region).build();
        SdkBytes sourceBytes = SdkBytes.fromByteArray(bytes);
        // Get the input Document object as bytes
        Document myDoc = Document.builder().bytes(sourceBytes).build();
        List<FeatureType> featureTypes = new ArrayList<FeatureType>();
        featureTypes.add(FeatureType.FORMS);
        featureTypes.add(FeatureType.TABLES);
        AnalyzeDocumentRequest analyzeDocumentRequest = AnalyzeDocumentRequest.builder().featureTypes(featureTypes).document(myDoc).build();
        AnalyzeDocumentResponse analyzeDocument = textractClient.analyzeDocument(analyzeDocumentRequest);
        List<Block> docInfo = analyzeDocument.blocks();
        Iterator<Block> blockIterator = docInfo.iterator();
        while (blockIterator.hasNext()) {
            Block block = blockIterator.next();
            myList.add("The block type is " + block.blockType().toString());
        }
        return convertToString(toXml(myList));
    } catch (TextractException e) {
        System.err.println(e.getMessage());
        System.exit(1);
    }
    return "";
}
Also used : FeatureType(software.amazon.awssdk.services.textract.model.FeatureType) TextractClient(software.amazon.awssdk.services.textract.TextractClient) TextractException(software.amazon.awssdk.services.textract.model.TextractException) ArrayList(java.util.ArrayList) Document(software.amazon.awssdk.services.textract.model.Document) AnalyzeDocumentResponse(software.amazon.awssdk.services.textract.model.AnalyzeDocumentResponse) SdkBytes(software.amazon.awssdk.core.SdkBytes) Region(software.amazon.awssdk.regions.Region) Block(software.amazon.awssdk.services.textract.model.Block) ArrayList(java.util.ArrayList) List(java.util.List) AnalyzeDocumentRequest(software.amazon.awssdk.services.textract.model.AnalyzeDocumentRequest)

Aggregations

Block (software.amazon.awssdk.services.textract.model.Block)4 Document (software.amazon.awssdk.services.textract.model.Document)4 TextractException (software.amazon.awssdk.services.textract.model.TextractException)4 SdkBytes (software.amazon.awssdk.core.SdkBytes)3 File (java.io.File)2 FileInputStream (java.io.FileInputStream)2 FileNotFoundException (java.io.FileNotFoundException)2 InputStream (java.io.InputStream)2 ArrayList (java.util.ArrayList)2 AnalyzeDocumentRequest (software.amazon.awssdk.services.textract.model.AnalyzeDocumentRequest)2 AnalyzeDocumentResponse (software.amazon.awssdk.services.textract.model.AnalyzeDocumentResponse)2 DetectDocumentTextRequest (software.amazon.awssdk.services.textract.model.DetectDocumentTextRequest)2 DetectDocumentTextResponse (software.amazon.awssdk.services.textract.model.DetectDocumentTextResponse)2 DocumentMetadata (software.amazon.awssdk.services.textract.model.DocumentMetadata)2 FeatureType (software.amazon.awssdk.services.textract.model.FeatureType)2 List (java.util.List)1 Region (software.amazon.awssdk.regions.Region)1 TextractClient (software.amazon.awssdk.services.textract.TextractClient)1 S3Object (software.amazon.awssdk.services.textract.model.S3Object)1