Amazon Textract を使用して、スキャンしたドキュメントから検索可能な PDF を自動的に生成する

...

//Amazon Textract を使用してテキストを抽出
List<TextLine> lines = extractText(imageBytes);

//画像とテキストを含む検索可能な PDF を生成
PDFDocument doc = new PDFDocument();
doc.addPage(image, imageType, lines);

//PDF をローカルディスクに保存
try(OutputStream outputStream = new FileOutputStream(outputDocumentName)) {
    doc.save(outputStream);
}

...

public class DemoPdfFromLocalImage {

    public static void run(String documentName, String outputDocumentName) throws IOException {

        System.out.println("Generating searchable pdf from: " + documentName);

        ImageType imageType = ImageType.JPEG;
        if(documentName.toLowerCase().endsWith(".png"))
            imageType = ImageType.PNG;

        //画像バイトを取得
        ByteBuffer imageBytes = null;
        try(InputStream in = new FileInputStream(documentName)) {
            imageBytes = ByteBuffer.wrap(IOUtils.toByteArray(in));
        }

        //テキストを抽出
        List<TextLine> lines = extractText(imageBytes);

        //画像を取得
        BufferedImage image = getImage(documentName);

        //新しい PDF ドキュメントを作成
        PDFDocument pdfDocument = new PDFDocument();

        //テキストレイヤーと画像を含むページを PDF 文書に追加
        pdfDocument.addPage(image, imageType, lines);

        //PDF をローカルディスクに保存
        try(OutputStream outputStream = new FileOutputStream(outputDocumentName)) {
            pdfDocument.save(outputStream);
            pdfDocument.close();
        }

        System.out.println("Generated searchable pdf: " + outputDocumentName);
    }
    
    private static BufferedImage getImage(String documentName) throws IOException {

        BufferedImage image = null;

        try(InputStream in = new FileInputStream(documentName)) {
            image = ImageIO.read(in);
        }

        return image;
    }

    private static List<TextLine> extractText(ByteBuffer imageBytes) {

        AmazonTextract client = AmazonTextractClientBuilder.defaultClient();

        DetectDocumentTextRequest request = new DetectDocumentTextRequest()
                .withDocument(new Document()
                        .withBytes(imageBytes));

        DetectDocumentTextResult result = client.detectDocumentText(request);

        List<TextLine> lines = new ArrayList<TextLine>();
        List<Block> blocks = result.getBlocks();
        BoundingBox boundingBox = null;
        for (Block block : blocks) {
            if ((block.getBlockType()).equals("LINE")) {
                boundingBox = block.getGeometry().getBoundingBox();
                lines.add(new TextLine(boundingBox.getLeft(),
                        boundingBox.getTop(),
                        boundingBox.getWidth(),
                        boundingBox.getHeight(),
                        block.getText()));
            }
        }

        return lines;
    }
}

public class DemoPdfFromS3Pdf {
    public static void run(String bucketName, String documentName, String outputDocumentName) throws IOException, InterruptedException {

        System.out.println("Generating searchable pdf from: " + bucketName + "/" + documentName);

        //Amazon Textract を使用してテキストを抽出
        List<ArrayList<TextLine>> linesInPages = extractText(bucketName, documentName);

        //Amazon S3 から入力 PDF ドキュメントを取得
        InputStream inputPdf = getPdfFromS3(bucketName, documentName);

        //新しい PDF ドキュメントを作成
        PDFDocument pdfDocument = new PDFDocument();

        //PDF ドキュメントの各ページにテキストレイヤーと画像を追加
        PDDocument inputDocument = PDDocument.load(inputPdf);
        PDFRenderer pdfRenderer = new PDFRenderer(inputDocument);
        BufferedImage image = null;
        for (int page = 0; page < inputDocument.getNumberOfPages(); ++page) {
            image = pdfRenderer.renderImageWithDPI(page, 300, org.apache.pdfbox.rendering.ImageType.RGB);

            pdfDocument.addPage(image, ImageType.JPEG, linesInPages.get(page));

            System.out.println("Processed page index: " + page);
        }

        //PDF をストリームに保存
        ByteArrayOutputStream os = new ByteArrayOutputStream();
        pdfDocument.save(os);
        pdfDocument.close();
        inputDocument.close();

        //PDF を S3 にアップロード
        UploadToS3(bucketName, outputDocumentName, "application/pdf", os.toByteArray());

        System.out.println("Generated searchable pdf: " + bucketName + "/" + outputDocumentName);
    }

    private static List<ArrayList<TextLine>> extractText(String bucketName, String documentName) throws InterruptedException {

        AmazonTextract client = AmazonTextractClientBuilder.defaultClient();

        StartDocumentTextDetectionRequest req = new StartDocumentTextDetectionRequest()
                .withDocumentLocation(new DocumentLocation()
                        .withS3Object(new S3Object()
                                .withBucket(bucketName)
                                .withName(documentName)))
                .withJobTag("DetectingText");

        StartDocumentTextDetectionResult startDocumentTextDetectionResult = client.startDocumentTextDetection(req);
        String startJobId = startDocumentTextDetectionResult.getJobId();

        System.out.println("Text detection job started with Id: " + startJobId);

        GetDocumentTextDetectionRequest documentTextDetectionRequest = null;
        GetDocumentTextDetectionResult response = null;

        String jobStatus = "IN_PROGRESS";

        while (jobStatus.equals("IN_PROGRESS")) {
            System.out.println("Waiting for job to complete...");
            TimeUnit.SECONDS.sleep(10);
            documentTextDetectionRequest = new GetDocumentTextDetectionRequest()
                    .withJobId(startJobId)
                    .withMaxResults(1);

            response = client.getDocumentTextDetection(documentTextDetectionRequest);
            jobStatus = response.getJobStatus();
        }

        int maxResults = 1000;
        String paginationToken = null;
        Boolean finished = false;

        List<ArrayList<TextLine>> pages = new ArrayList<ArrayList<TextLine>>();
        ArrayList<TextLine> page = null;
        BoundingBox boundingBox = null;

        while (finished == false) {
            documentTextDetectionRequest = new GetDocumentTextDetectionRequest()
                    .withJobId(startJobId)
                    .withMaxResults(maxResults)
                    .withNextToken(paginationToken);
            response = client.getDocumentTextDetection(documentTextDetectionRequest);

            //ブロック情報を表示
            List<Block> blocks = response.getBlocks();
            for (Block block : blocks) {
                if (block.getBlockType().equals("PAGE")) {
                    page = new ArrayList<TextLine>();
                    pages.add(page);
                } else if (block.getBlockType().equals("LINE")) {
                    boundingBox = block.getGeometry().getBoundingBox();
                    page.add(new TextLine(boundingBox.getLeft(),
                            boundingBox.getTop(),
                            boundingBox.getWidth(),
                            boundingBox.getHeight(),
                            block.getText()));
                }
            }
            paginationToken = response.getNextToken();
            if (paginationToken == null)
                finished = true;
        }

        return pages;
    }

    private static InputStream getPdfFromS3(String bucketName, String documentName) throws IOException {

        AmazonS3 s3client = AmazonS3ClientBuilder.defaultClient();
        com.amazonaws.services.s3.model.S3Object fullObject = s3client.getObject(new GetObjectRequest(bucketName, documentName));
        InputStream in = fullObject.getObjectContent();
        return in;
    }

    private static void UploadToS3(String bucketName, String objectName, String contentType, byte[] bytes) {
        AmazonS3 s3client = AmazonS3ClientBuilder.defaultClient();
        ByteArrayInputStream baInputStream = new ByteArrayInputStream(bytes);
        ObjectMetadata metadata = new ObjectMetadata();
        metadata.setContentLength(bytes.length);
        metadata.setContentType(contentType);
        PutObjectRequest putRequest = new PutObjectRequest(bucketName, objectName, baInputStream, metadata);
        s3client.putObject(putRequest);
    }
}