Detect text in a PDF file in Cloud Storage

Perform optical character recognition (OCR) on a PDF file stored in Cloud Storage.

Explore further

For detailed documentation that includes this code sample, see the following:

• Batch file annotation offline
• Detect text in files (PDF/TIFF)

Code sample

Go

Before trying this sample, follow the Go setup instructions in the Vision quickstart using client libraries. For more information, see the Vision Go API reference documentation.

To authenticate to Vision, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

// detectAsyncDocumentURI performs Optical Character Recognition (OCR) on a
// PDF file stored in GCS.
func detectAsyncDocumentURI(w io.Writer, gcsSourceURI, gcsDestinationURI string) error {
	ctx := context.Background()

	client, err := vision.NewImageAnnotatorClient(ctx)
	if err != nil {
		return err
	}

	request := &visionpb.AsyncBatchAnnotateFilesRequest{
		Requests: []*visionpb.AsyncAnnotateFileRequest{
			{
				Features: []*visionpb.Feature{
					{
						Type: visionpb.Feature_DOCUMENT_TEXT_DETECTION,
					},
				},
				InputConfig: &visionpb.InputConfig{
					GcsSource: &visionpb.GcsSource{Uri: gcsSourceURI},
					// Supported MimeTypes are: "application/pdf" and "image/tiff".
					MimeType: "application/pdf",
				},
				OutputConfig: &visionpb.OutputConfig{
					GcsDestination: &visionpb.GcsDestination{Uri: gcsDestinationURI},
					// How many pages should be grouped into each json output file.
					BatchSize: 2,
				},
			},
		},
	}

	operation, err := client.AsyncBatchAnnotateFiles(ctx, request)
	if err != nil {
		return err
	}

	fmt.Fprintf(w, "Waiting for the operation to finish.")

	resp, err := operation.Wait(ctx)
	if err != nil {
		return err
	}

	fmt.Fprintf(w, "%v", resp)

	return nil
}

Java

Before trying this sample, follow the Java setup instructions in the Vision quickstart using client libraries. For more information, see the Vision Java API reference documentation.

To authenticate to Vision, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

/**
 * 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 {

  // Initialize client that will be used to send requests. This client only needs to be created
  // once, and can be reused for multiple requests. After completing all of your requests, call
  // 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(
                "application/pdf") // Supported MimeTypes: "application/pdf", "image/tiff"
            .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());

        // Process the first System.output file from GCS.
        // Since we specified batch size = 2, the first response contains
        // 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");
    }
  }
}

Node.js

Before trying this sample, follow the Node.js setup instructions in the Vision quickstart using client libraries. For more information, see the Vision Node.js API reference documentation.

To authenticate to Vision, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

// Imports the Google Cloud client libraries
const vision = require('@google-cloud/vision').v1;

// Creates a client
const client = new vision.ImageAnnotatorClient();

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// Bucket where the file resides
// const bucketName = 'my-bucket';
// Path to PDF file within bucket
// const fileName = 'path/to/document.pdf';
// The folder to store the results
// const outputPrefix = 'results'

const gcsSourceUri = `gs://${bucketName}/${fileName}`;
const gcsDestinationUri = `gs://${bucketName}/${outputPrefix}/`;

const inputConfig = {
  // Supported mime_types are: 'application/pdf' and 'image/tiff'
  mimeType: 'application/pdf',
  gcsSource: {
    uri: gcsSourceUri,
  },
};
const outputConfig = {
  gcsDestination: {
    uri: gcsDestinationUri,
  },
};
const features = [{type: 'DOCUMENT_TEXT_DETECTION'}];
const request = {
  requests: [
    {
      inputConfig: inputConfig,
      features: features,
      outputConfig: outputConfig,
    },
  ],
};

const [operation] = await client.asyncBatchAnnotateFiles(request);
const [filesResponse] = await operation.promise();
const destinationUri =
  filesResponse.responses[0].outputConfig.gcsDestination.uri;
console.log('Json saved to: ' + destinationUri);

PHP

Before trying this sample, follow the PHP setup instructions in the Vision quickstart using client libraries. For more information, see the Vision PHP API reference documentation.

To authenticate to Vision, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

namespace Google\Cloud\Samples\Vision;

use Google\Cloud\Storage\StorageClient;
use Google\Cloud\Vision\V1\AnnotateFileResponse;
use Google\Cloud\Vision\V1\AsyncAnnotateFileRequest;
use Google\Cloud\Vision\V1\Feature;
use Google\Cloud\Vision\V1\Feature\Type;
use Google\Cloud\Vision\V1\GcsDestination;
use Google\Cloud\Vision\V1\GcsSource;
use Google\Cloud\Vision\V1\ImageAnnotatorClient;
use Google\Cloud\Vision\V1\InputConfig;
use Google\Cloud\Vision\V1\OutputConfig;

/**
 * @param string $path    GCS path to the document, e.g. "gs://path/to/your/document.pdf"
 * @param string $output  GCS path to store the results, e.g. "gs://path/to/store/results/"
 */
function detect_pdf_gcs(string $path, string $output)
{
    # select ocr feature
    $feature = (new Feature())
        ->setType(Type::DOCUMENT_TEXT_DETECTION);

    # set $path (file to OCR) as source
    $gcsSource = (new GcsSource())
        ->setUri($path);
    # supported mime_types are: 'application/pdf' and 'image/tiff'
    $mimeType = 'application/pdf';
    $inputConfig = (new InputConfig())
        ->setGcsSource($gcsSource)
        ->setMimeType($mimeType);

    # set $output as destination
    $gcsDestination = (new GcsDestination())
        ->setUri($output);
    # how many pages should be grouped into each json output file.
    $batchSize = 2;
    $outputConfig = (new OutputConfig())
        ->setGcsDestination($gcsDestination)
        ->setBatchSize($batchSize);

    # prepare request using configs set above
    $request = (new AsyncAnnotateFileRequest())
        ->setFeatures([$feature])
        ->setInputConfig($inputConfig)
        ->setOutputConfig($outputConfig);
    $requests = [$request];

    # make request
    $imageAnnotator = new ImageAnnotatorClient();
    $operation = $imageAnnotator->asyncBatchAnnotateFiles($requests);
    print('Waiting for operation to finish.' . PHP_EOL);
    $operation->pollUntilComplete();

    # once the request has completed and the output has been
    # written to GCS, we can list all the output files.
    preg_match('/^gs:\/\/([a-zA-Z0-9\._\-]+)\/?(\S+)?$/', $output, $match);
    $bucketName = $match[1];
    $prefix = isset($match[2]) ? $match[2] : '';

    $storage = new StorageClient();
    $bucket = $storage->bucket($bucketName);
    $options = ['prefix' => $prefix];
    $objects = $bucket->objects($options);

    # save first object for sample below
    $objects->next();
    $firstObject = $objects->current();

    # list objects with the given prefix.
    print('Output files:' . PHP_EOL);
    foreach ($objects as $object) {
        print($object->name() . PHP_EOL);
    }

    # process the first output file from GCS.
    # since we specified batch_size=2, the first response contains
    # the first two pages of the input file.
    $jsonString = $firstObject->downloadAsString();
    $firstBatch = new AnnotateFileResponse();
    $firstBatch->mergeFromJsonString($jsonString);

    # get annotation and print text
    foreach ($firstBatch->getResponses() as $response) {
        $annotation = $response->getFullTextAnnotation();
        print($annotation->getText());
    }

    $imageAnnotator->close();
}

Python

Before trying this sample, follow the Python setup instructions in the Vision quickstart using client libraries. For more information, see the Vision Python API reference documentation.

To authenticate to Vision, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

def async_detect_document(gcs_source_uri, gcs_destination_uri):
    """OCR with PDF/TIFF as source files on GCS"""
    import json
    import re
    from google.cloud import vision
    from google.cloud import storage

    # Supported mime_types are: 'application/pdf' and 'image/tiff'
    mime_type = "application/pdf"

    # How many pages should be grouped into each json output file.
    batch_size = 2

    client = vision.ImageAnnotatorClient()

    feature = vision.Feature(type_=vision.Feature.Type.DOCUMENT_TEXT_DETECTION)

    gcs_source = vision.GcsSource(uri=gcs_source_uri)
    input_config = vision.InputConfig(gcs_source=gcs_source, mime_type=mime_type)

    gcs_destination = vision.GcsDestination(uri=gcs_destination_uri)
    output_config = vision.OutputConfig(
        gcs_destination=gcs_destination, batch_size=batch_size
    )

    async_request = vision.AsyncAnnotateFileRequest(
        features=[feature], input_config=input_config, output_config=output_config
    )

    operation = client.async_batch_annotate_files(requests=[async_request])

    print("Waiting for the operation to finish.")
    operation.result(timeout=420)

    # Once the request has completed and the output has been
    # written to GCS, we can list all the output files.
    storage_client = storage.Client()

    match = re.match(r"gs://([^/]+)/(.+)", gcs_destination_uri)
    bucket_name = match.group(1)
    prefix = match.group(2)

    bucket = storage_client.get_bucket(bucket_name)

    # List objects with the given prefix, filtering out folders.
    blob_list = [
        blob
        for blob in list(bucket.list_blobs(prefix=prefix))
        if not blob.name.endswith("/")
    ]
    print("Output files:")
    for blob in blob_list:
        print(blob.name)

    # Process the first output file from GCS.
    # Since we specified batch_size=2, the first response contains
    # the first two pages of the input file.
    output = blob_list[0]

    json_string = output.download_as_bytes().decode("utf-8")
    response = json.loads(json_string)

    # The actual response for the first page of the input file.
    first_page_response = response["responses"][0]
    annotation = first_page_response["fullTextAnnotation"]

    # Here we print the full text from the first page.
    # The response contains more information:
    # annotation/pages/blocks/paragraphs/words/symbols
    # including confidence scores and bounding boxes
    print("Full text:\n")
    print(annotation["text"])

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.