Examples with GcsSource com.google.cloud.datalabeling.v1beta1.GcsSource used on opensource projects

Example 46 with GcsSource

use of com.google.cloud.datalabeling.v1beta1.GcsSource in project java-document-ai by googleapis.

the class SetEndPointBeta method setEndpoint.

public static void setEndpoint(String projectId, String location, String inputGcsUri) throws IOException {
    DocumentUnderstandingServiceSettings settings = DocumentUnderstandingServiceSettings.newBuilder().setEndpoint("eu-documentai.googleapis.com:443").build();
    // the "close" method on the client to safely clean up any remaining background resources.
    try (DocumentUnderstandingServiceClient client = DocumentUnderstandingServiceClient.create(settings)) {
        // Configure the request for processing the PDF
        String parent = String.format("projects/%s/locations/%s", projectId, location);
        GcsSource uri = GcsSource.newBuilder().setUri(inputGcsUri).build();
        // mime_type can be application/pdf, image/tiff,
        // and image/gif, or application/json
        InputConfig config = InputConfig.newBuilder().setGcsSource(uri).setMimeType("application/pdf").build();
        ProcessDocumentRequest request = ProcessDocumentRequest.newBuilder().setParent(parent).setInputConfig(config).build();
        // Recognizes text entities in the PDF document
        Document response = client.processDocument(request);
        // Get all of the document text as one big string
        String text = response.getText();
        // Process the output
        for (Document.Entity entity : response.getEntitiesList()) {
            System.out.printf("Entity text: %s\n", getText(entity, text));
            System.out.printf("Entity type: %s\n", entity.getType());
            System.out.printf("Entity mention text: %s\n", entity.getMentionText());
        }
    }
}

Example 47 with GcsSource

use of com.google.cloud.datalabeling.v1beta1.GcsSource in project java-document-ai by googleapis.

the class BatchParseTableBeta method batchParseTableGcs.

public static void batchParseTableGcs(String projectId, String location, String outputGcsBucketName, String outputGcsPrefix, String inputGcsUri) throws IOException, InterruptedException, ExecutionException, TimeoutException {
    // the "close" method on the client to safely clean up any remaining background resources.
    try (DocumentUnderstandingServiceClient client = DocumentUnderstandingServiceClient.create()) {
        // Configure the request for processing the PDF
        String parent = String.format("projects/%s/locations/%s", projectId, location);
        TableBoundHint tableBoundHints = TableBoundHint.newBuilder().setBoundingBox(// Each vertice coordinate must be a number between 0 and 1
        BoundingPoly.newBuilder().addNormalizedVertices(NormalizedVertex.newBuilder().setX(0).setX(0).build()).addNormalizedVertices(NormalizedVertex.newBuilder().setX(1).setX(0).build()).addNormalizedVertices(NormalizedVertex.newBuilder().setX(1).setX(1).build()).addNormalizedVertices(NormalizedVertex.newBuilder().setX(0).setX(1).build()).build()).setPageNumber(1).build();
        TableExtractionParams params = TableExtractionParams.newBuilder().setEnabled(true).addTableBoundHints(tableBoundHints).build();
        GcsSource inputUri = GcsSource.newBuilder().setUri(inputGcsUri).build();
        // mime_type can be application/pdf, image/tiff,
        // and image/gif, or application/json
        InputConfig config = InputConfig.newBuilder().setGcsSource(inputUri).setMimeType("application/pdf").build();
        GcsDestination gcsDestination = GcsDestination.newBuilder().setUri(String.format("gs://%s/%s", outputGcsBucketName, outputGcsPrefix)).build();
        OutputConfig outputConfig = OutputConfig.newBuilder().setGcsDestination(gcsDestination).setPagesPerShard(1).build();
        ProcessDocumentRequest request = ProcessDocumentRequest.newBuilder().setTableExtractionParams(params).setInputConfig(config).setOutputConfig(outputConfig).build();
        BatchProcessDocumentsRequest requests = BatchProcessDocumentsRequest.newBuilder().addRequests(request).setParent(parent).build();
        // Batch process document using a long-running operation.
        OperationFuture<BatchProcessDocumentsResponse, OperationMetadata> future = client.batchProcessDocumentsAsync(requests);
        // Wait for operation to complete.
        System.out.println("Waiting for operation to complete...");
        future.get(360, TimeUnit.SECONDS);
        System.out.println("Document processing complete.");
        Storage storage = StorageOptions.newBuilder().setProjectId(projectId).build().getService();
        Bucket bucket = storage.get(outputGcsBucketName);
        // List all of the files in the Storage bucket.
        Page<Blob> blobs = bucket.list(Storage.BlobListOption.currentDirectory(), Storage.BlobListOption.prefix(outputGcsPrefix));
        int idx = 0;
        for (Blob blob : blobs.iterateAll()) {
            if (!blob.isDirectory()) {
                System.out.printf("Fetched file #%d\n", ++idx);
                // Read the results
                // Download and store json data in a temp file.
                File tempFile = File.createTempFile("file", ".json");
                Blob fileInfo = storage.get(BlobId.of(outputGcsBucketName, blob.getName()));
                fileInfo.downloadTo(tempFile.toPath());
                // Parse json file into Document.
                FileReader reader = new FileReader(tempFile);
                Document.Builder builder = Document.newBuilder();
                JsonFormat.parser().merge(reader, builder);
                Document document = builder.build();
                // Get all of the document text as one big string.
                String text = document.getText();
                // Process the output.
                if (document.getPagesCount() > 0) {
                    Document.Page page1 = document.getPages(0);
                    if (page1.getTablesCount() > 0) {
                        Document.Page.Table table = page1.getTables(0);
                        System.out.println("Results from first table processed:");
                        System.out.println("Header row:");
                        if (table.getHeaderRowsCount() > 0) {
                            Document.Page.Table.TableRow headerRow = table.getHeaderRows(0);
                            for (Document.Page.Table.TableCell tableCell : headerRow.getCellsList()) {
                                if (!tableCell.getLayout().getTextAnchor().getTextSegmentsList().isEmpty()) {
                                    // Extract shards from the text field
                                    // First shard in document doesn't have startIndex property
                                    List<Document.TextAnchor.TextSegment> textSegments = tableCell.getLayout().getTextAnchor().getTextSegmentsList();
                                    int startIdx = textSegments.size() > 0 ? (int) textSegments.get(0).getStartIndex() : 0;
                                    int endIdx = (int) textSegments.get(0).getEndIndex();
                                    System.out.printf("\t%s", text.substring(startIdx, endIdx));
                                }
                            }
                        }
                    }
                }
                // Clean up temp file.
                tempFile.deleteOnExit();
            }
        }
    }
}

Example 48 with GcsSource

use of com.google.cloud.datalabeling.v1beta1.GcsSource in project java-document-ai by googleapis.

the class ParseTableBeta method parseTable.

public static void parseTable(String projectId, String location, String inputGcsUri) throws IOException {
    // the "close" method on the client to safely clean up any remaining background resources.
    try (DocumentUnderstandingServiceClient client = DocumentUnderstandingServiceClient.create()) {
        // Configure the request for processing the PDF
        String parent = String.format("projects/%s/locations/%s", projectId, location);
        TableBoundHint tableBoundHints = TableBoundHint.newBuilder().setBoundingBox(// Each vertice coordinate must be a number between 0 and 1
        BoundingPoly.newBuilder().addNormalizedVertices(NormalizedVertex.newBuilder().setX(0).setX(0).build()).addNormalizedVertices(NormalizedVertex.newBuilder().setX(1).setX(0).build()).addNormalizedVertices(NormalizedVertex.newBuilder().setX(1).setX(1).build()).addNormalizedVertices(NormalizedVertex.newBuilder().setX(0).setX(1).build()).build()).setPageNumber(1).build();
        TableExtractionParams params = TableExtractionParams.newBuilder().setEnabled(true).addTableBoundHints(tableBoundHints).build();
        GcsSource uri = GcsSource.newBuilder().setUri(inputGcsUri).build();
        // mime_type can be application/pdf, image/tiff,
        // and image/gif, or application/json
        InputConfig config = InputConfig.newBuilder().setGcsSource(uri).setMimeType("application/pdf").build();
        ProcessDocumentRequest request = ProcessDocumentRequest.newBuilder().setParent(parent).setTableExtractionParams(params).setInputConfig(config).build();
        // Recognizes text entities in the PDF document
        Document response = client.processDocument(request);
        // Get all of the document text as one big string
        String text = response.getText();
        // Get the first table in the document
        if (response.getPagesCount() > 0) {
            Document.Page page1 = response.getPages(0);
            if (page1.getTablesCount() > 0) {
                Document.Page.Table table = page1.getTables(0);
                System.out.println("Results from first table processed:");
                List<Document.Page.DetectedLanguage> detectedLangs = page1.getDetectedLanguagesList();
                String langCode = detectedLangs.size() > 0 ? detectedLangs.get(0).getLanguageCode() : "NOT_FOUND";
                System.out.printf("First detected language: : %s", langCode);
                Document.Page.Table.TableRow headerRow = table.getHeaderRows(0);
                System.out.println("Header row:");
                for (Document.Page.Table.TableCell tableCell : headerRow.getCellsList()) {
                    if (tableCell.getLayout().getTextAnchor().getTextSegmentsList() != null) {
                        // Extract shards from the text field
                        // First shard in document doesn't have startIndex property
                        System.out.printf("\t%s", getText(tableCell.getLayout(), text));
                    }
                }
            }
        }
    }
}

Example 49 with GcsSource

use of com.google.cloud.datalabeling.v1beta1.GcsSource in project java-document-ai by googleapis.

the class QuickStart method quickStart.

public static void quickStart(String projectId, String location, String inputGcsUri) throws IOException {
    // the "close" method on the client to safely clean up any remaining background resources.
    try (DocumentUnderstandingServiceClient client = DocumentUnderstandingServiceClient.create()) {
        // Configure the request for processing a single document
        String parent = String.format("projects/%s/locations/%s", projectId, location);
        GcsSource uri = GcsSource.newBuilder().setUri(inputGcsUri).build();
        // mime_type can be application/pdf, image/tiff,
        // and image/gif, or application/json
        InputConfig config = InputConfig.newBuilder().setGcsSource(uri).setMimeType("application/pdf").build();
        ProcessDocumentRequest request = ProcessDocumentRequest.newBuilder().setParent(parent).setInputConfig(config).build();
        // Recognizes text entities in the PDF document
        Document response = client.processDocument(request);
        // Get all of the document text as one big string
        String text = response.getText();
        // Process the output
        for (Document.Entity entity : response.getEntitiesList()) {
            System.out.printf("Entity text: %s\n", getText(entity, text));
            System.out.printf("Entity type: %s\n", entity.getType());
            System.out.printf("Entity mention text: %s\n", entity.getMentionText());
        }
    }
}

Example 50 with GcsSource

use of com.google.cloud.datalabeling.v1beta1.GcsSource in project java-vision by googleapis.

the class Detect method detectDocumentsGcs.

// [END vision_fulltext_detection_gcs]
// [START vision_text_detection_pdf_gcs]
/**
 * Performs document text OCR with PDF/TIFF as source files on Google Cloud Storage.
 *
 * @param gcsSourcePath The path to the remote file on Google Cloud Storage to detect document
 *     text on.
 * @param gcsDestinationPath The path to the remote file on Google Cloud Storage to store the
 *     results on.
 * @throws Exception on errors while closing the client.
 */
public static void detectDocumentsGcs(String gcsSourcePath, String gcsDestinationPath) throws Exception {
    // the "close" method on the client to safely clean up any remaining background resources.
    try (ImageAnnotatorClient client = ImageAnnotatorClient.create()) {
        List<AsyncAnnotateFileRequest> requests = new ArrayList<>();
        // Set the GCS source path for the remote file.
        GcsSource gcsSource = GcsSource.newBuilder().setUri(gcsSourcePath).build();
        // Create the configuration with the specified MIME (Multipurpose Internet Mail Extensions)
        // types
        InputConfig inputConfig = InputConfig.newBuilder().setMimeType(// Supported MimeTypes: "application/pdf", "image/tiff"
        "application/pdf").setGcsSource(gcsSource).build();
        // Set the GCS destination path for where to save the results.
        GcsDestination gcsDestination = GcsDestination.newBuilder().setUri(gcsDestinationPath).build();
        // Create the configuration for the System.output with the batch size.
        // The batch size sets how many pages should be grouped into each json System.output file.
        OutputConfig outputConfig = OutputConfig.newBuilder().setBatchSize(2).setGcsDestination(gcsDestination).build();
        // Select the Feature required by the vision API
        Feature feature = Feature.newBuilder().setType(Feature.Type.DOCUMENT_TEXT_DETECTION).build();
        // Build the OCR request
        AsyncAnnotateFileRequest request = AsyncAnnotateFileRequest.newBuilder().addFeatures(feature).setInputConfig(inputConfig).setOutputConfig(outputConfig).build();
        requests.add(request);
        // Perform the OCR request
        OperationFuture<AsyncBatchAnnotateFilesResponse, OperationMetadata> response = client.asyncBatchAnnotateFilesAsync(requests);
        System.out.println("Waiting for the operation to finish.");
        // Wait for the request to finish. (The result is not used, since the API saves the result to
        // the specified location on GCS.)
        List<AsyncAnnotateFileResponse> result = response.get(180, TimeUnit.SECONDS).getResponsesList();
        // Once the request has completed and the System.output has been
        // written to GCS, we can list all the System.output files.
        Storage storage = StorageOptions.getDefaultInstance().getService();
        // Get the destination location from the gcsDestinationPath
        Pattern pattern = Pattern.compile("gs://([^/]+)/(.+)");
        Matcher matcher = pattern.matcher(gcsDestinationPath);
        if (matcher.find()) {
            String bucketName = matcher.group(1);
            String prefix = matcher.group(2);
            // Get the list of objects with the given prefix from the GCS bucket
            Bucket bucket = storage.get(bucketName);
            com.google.api.gax.paging.Page<Blob> pageList = bucket.list(BlobListOption.prefix(prefix));
            Blob firstOutputFile = null;
            // List objects with the given prefix.
            System.out.println("Output files:");
            for (Blob blob : pageList.iterateAll()) {
                System.out.println(blob.getName());
                // the first two pages of the input file.
                if (firstOutputFile == null) {
                    firstOutputFile = blob;
                }
            }
            // Get the contents of the file and convert the JSON contents to an AnnotateFileResponse
            // object. If the Blob is small read all its content in one request
            // (Note: the file is a .json file)
            // Storage guide: https://cloud.google.com/storage/docs/downloading-objects
            String jsonContents = new String(firstOutputFile.getContent());
            Builder builder = AnnotateFileResponse.newBuilder();
            JsonFormat.parser().merge(jsonContents, builder);
            // Build the AnnotateFileResponse object
            AnnotateFileResponse annotateFileResponse = builder.build();
            // Parse through the object to get the actual response for the first page of the input file.
            AnnotateImageResponse annotateImageResponse = annotateFileResponse.getResponses(0);
            // Here we print the full text from the first page.
            // The response contains more information:
            // annotation/pages/blocks/paragraphs/words/symbols
            // including confidence score and bounding boxes
            System.out.format("%nText: %s%n", annotateImageResponse.getFullTextAnnotation().getText());
        } else {
            System.out.println("No MATCH");
        }
    }
}