使用 SDK for Java 2.x 的 Amazon Textract 示例 - Amazon SDK for Java 2.x
操作
Amazon Web Services 文档中描述的 Amazon Web Services 服务或功能可能因区域而异。要查看适用于中国区域的差异，请参阅 中国的 Amazon Web Services 服务入门 (PDF)。

本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。

使用 SDK for Java 2.x 的 Amazon Textract 示例

以下代码示例向您展示了如何在 Amazon Textract 中 Amazon SDK for Java 2.x 使用来执行操作和实现常见场景。

操作是大型程序的代码摘录，必须在上下文中运行。您可以通过操作了解如何调用单个服务函数，还可以通过函数相关场景和跨服务示例的上下文查看操作。

场景 是展示如何通过在同一服务中调用多个函数来完成特定任务的代码示例。

每个示例都包含一个指向的链接 GitHub，您可以在其中找到有关如何在上下文中设置和运行代码的说明。

主题

操作

以下代码示例演示了如何使用 AnalyzeDocument。

适用于 Java 2.x 的 SDK
注意

还有更多相关信息 GitHub。在 Amazon 代码示例存储库中查找完整示例，了解如何进行设置和运行。

import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.textract.TextractClient;
import software.amazon.awssdk.services.textract.model.AnalyzeDocumentRequest;
import software.amazon.awssdk.services.textract.model.Document;
import software.amazon.awssdk.services.textract.model.FeatureType;
import software.amazon.awssdk.services.textract.model.AnalyzeDocumentResponse;
import software.amazon.awssdk.services.textract.model.Block;
import software.amazon.awssdk.services.textract.model.TextractException;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;

/**
 * Before running this Java V2 code example, set up your development
 * environment, including your credentials.
 *
 * For more information, see the following documentation topic:
 *
 * https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
 */
public class AnalyzeDocument {
    public static void main(String[] args) {
        final String usage = """

                Usage:
                    <sourceDoc>\s

                Where:
                    sourceDoc - The path where the document is located (must be an image, for example, C:/AWS/book.png).\s
                """;

        if (args.length != 1) {
            System.out.println(usage);
            System.exit(1);
        }

        String sourceDoc = args[0];
        Region region = Region.US_EAST_2;
        TextractClient textractClient = TextractClient.builder()
                .region(region)
                .build();

        analyzeDoc(textractClient, sourceDoc);
        textractClient.close();
    }

    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);
        }
    }
}

  • 有关 API 的详细信息，请参阅 Amazon SDK for Java 2.x API 参考AnalyzeDocument中的。

以下代码示例演示了如何使用 DetectDocumentText。

适用于 Java 2.x 的 SDK
注意

还有更多相关信息 GitHub。在 Amazon 代码示例存储库中查找完整示例，了解如何进行设置和运行。

从输入文档检测文本。

import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.textract.TextractClient;
import software.amazon.awssdk.services.textract.model.Document;
import software.amazon.awssdk.services.textract.model.DetectDocumentTextRequest;
import software.amazon.awssdk.services.textract.model.DetectDocumentTextResponse;
import software.amazon.awssdk.services.textract.model.Block;
import software.amazon.awssdk.services.textract.model.DocumentMetadata;
import software.amazon.awssdk.services.textract.model.TextractException;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.InputStream;
import java.util.List;

/**
 * Before running this Java V2 code example, set up your development
 * environment, including your credentials.
 *
 * For more information, see the following documentation topic:
 *
 * https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
 */
public class DetectDocumentText {
    public static void main(String[] args) {
        final String usage = """

                Usage:
                    <sourceDoc>\s

                Where:
                    sourceDoc - The path where the document is located (must be an image, for example, C:/AWS/book.png).\s
                """;

        if (args.length != 1) {
            System.out.println(usage);
            System.exit(1);
        }

        String sourceDoc = args[0];
        Region region = Region.US_EAST_2;
        TextractClient textractClient = TextractClient.builder()
                .region(region)
                .build();

        detectDocText(textractClient, sourceDoc);
        textractClient.close();
    }

    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();
            for (Block block : docInfo) {
                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);
        }
    }
}

从位于 Amazon S3 桶中的文档检测文本。

import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.textract.model.S3Object;
import software.amazon.awssdk.services.textract.TextractClient;
import software.amazon.awssdk.services.textract.model.Document;
import software.amazon.awssdk.services.textract.model.DetectDocumentTextRequest;
import software.amazon.awssdk.services.textract.model.DetectDocumentTextResponse;
import software.amazon.awssdk.services.textract.model.Block;
import software.amazon.awssdk.services.textract.model.DocumentMetadata;
import software.amazon.awssdk.services.textract.model.TextractException;

/**
 * Before running this Java V2 code example, set up your development
 * environment, including your credentials.
 *
 * For more information, see the following documentation topic:
 *
 * https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
 */
public class DetectDocumentTextS3 {

    public static void main(String[] args) {
        final String usage = """

                Usage:
                    <bucketName> <docName>\s

                Where:
                    bucketName - The name of the Amazon S3 bucket that contains the document.\s

                    docName - The document name (must be an image, i.e., book.png).\s
                """;

        if (args.length != 2) {
            System.out.println(usage);
            System.exit(1);
        }

        String bucketName = args[0];
        String docName = args[1];
        Region region = Region.US_WEST_2;
        TextractClient textractClient = TextractClient.builder()
                .region(region)
                .build();

        detectDocTextS3(textractClient, bucketName, docName);
        textractClient.close();
    }

    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();

            DetectDocumentTextRequest detectDocumentTextRequest = DetectDocumentTextRequest.builder()
                    .document(myDoc)
                    .build();

            DetectDocumentTextResponse textResponse = textractClient.detectDocumentText(detectDocumentTextRequest);
            for (Block block : textResponse.blocks()) {
                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);
        }
    }
}

  • 有关 API 的详细信息，请参阅 Amazon SDK for Java 2.x API 参考DetectDocumentText中的。

以下代码示例演示了如何使用 StartDocumentAnalysis。

适用于 Java 2.x 的 SDK
注意

还有更多相关信息 GitHub。在 Amazon 代码示例存储库中查找完整示例，了解如何进行设置和运行。

import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.textract.model.S3Object;
import software.amazon.awssdk.services.textract.TextractClient;
import software.amazon.awssdk.services.textract.model.StartDocumentAnalysisRequest;
import software.amazon.awssdk.services.textract.model.DocumentLocation;
import software.amazon.awssdk.services.textract.model.TextractException;
import software.amazon.awssdk.services.textract.model.StartDocumentAnalysisResponse;
import software.amazon.awssdk.services.textract.model.GetDocumentAnalysisRequest;
import software.amazon.awssdk.services.textract.model.GetDocumentAnalysisResponse;
import software.amazon.awssdk.services.textract.model.FeatureType;
import java.util.ArrayList;
import java.util.List;

/**
 * Before running this Java V2 code example, set up your development
 * environment, including your credentials.
 *
 * For more information, see the following documentation topic:
 *
 * https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
 */
public class StartDocumentAnalysis {
    public static void main(String[] args) {
        final String usage = """

                Usage:
                    <bucketName> <docName>\s

                Where:
                    bucketName - The name of the Amazon S3 bucket that contains the document.\s
                    docName - The document name (must be an image, for example, book.png).\s
                """;

        if (args.length != 2) {
            System.out.println(usage);
            System.exit(1);
        }

        String bucketName = args[0];
        String docName = args[1];
        Region region = Region.US_WEST_2;
        TextractClient textractClient = TextractClient.builder()
                .region(region)
                .build();

        String jobId = startDocAnalysisS3(textractClient, bucketName, docName);
        System.out.println("Getting results for job " + jobId);
        String status = getJobResults(textractClient, jobId);
        System.out.println("The job status is " + status);
        textractClient.close();
    }

    public static String startDocAnalysisS3(TextractClient textractClient, String bucketName, String docName) {
        try {
            List<FeatureType> myList = new ArrayList<>();
            myList.add(FeatureType.TABLES);
            myList.add(FeatureType.FORMS);

            S3Object s3Object = S3Object.builder()
                    .bucket(bucketName)
                    .name(docName)
                    .build();

            DocumentLocation location = DocumentLocation.builder()
                    .s3Object(s3Object)
                    .build();

            StartDocumentAnalysisRequest documentAnalysisRequest = StartDocumentAnalysisRequest.builder()
                    .documentLocation(location)
                    .featureTypes(myList)
                    .build();

            StartDocumentAnalysisResponse response = textractClient.startDocumentAnalysis(documentAnalysisRequest);

            // Get the job ID
            String jobId = response.jobId();
            return jobId;

        } catch (TextractException e) {
            System.err.println(e.getMessage());
            System.exit(1);
        }
        return "";
    }

    private static String getJobResults(TextractClient textractClient, String jobId) {
        boolean finished = false;
        int index = 0;
        String status = "";

        try {
            while (!finished) {
                GetDocumentAnalysisRequest analysisRequest = GetDocumentAnalysisRequest.builder()
                        .jobId(jobId)
                        .maxResults(1000)
                        .build();

                GetDocumentAnalysisResponse response = textractClient.getDocumentAnalysis(analysisRequest);
                status = response.jobStatus().toString();

                if (status.compareTo("SUCCEEDED") == 0)
                    finished = true;
                else {
                    System.out.println(index + " status is: " + status);
                    Thread.sleep(1000);
                }
                index++;
            }

            return status;

        } catch (InterruptedException e) {
            System.out.println(e.getMessage());
            System.exit(1);
        }
        return "";
    }
}

  • 有关 API 的详细信息，请参阅 Amazon SDK for Java 2.x API 参考StartDocumentAnalysis中的。