use of com.google.cloud.vision.v1.AsyncBatchAnnotateFilesResponse in project spring-cloud-gcp by spring-cloud.
the class DocumentOcrTemplate method runOcrForDocument.
/**
* Runs OCR processing for a specified {@code document} and generates OCR output files
* under the path specified by {@code outputFilePathPrefix}.
*
* <p>
* For example, if you specify an {@code outputFilePathPrefix} of
* "gs://bucket_name/ocr_results/myDoc_", all the output files of OCR processing will be
* saved under prefix, such as:
*
* <ul>
* <li>gs://bucket_name/ocr_results/myDoc_output-1-to-5.json
* <li>gs://bucket_name/ocr_results/myDoc_output-6-to-10.json
* <li>gs://bucket_name/ocr_results/myDoc_output-11-to-15.json
* </ul>
*
* <p>
* Note: OCR processing operations may take several minutes to complete, so it may not be
* advisable to block on the completion of the operation. One may use the returned
* {@link ListenableFuture} to register callbacks or track the status of the operation.
*
* @param document The {@link GoogleStorageLocation} of the document to run OCR processing
* @param outputFilePathPrefix The {@link GoogleStorageLocation} of a file, folder, or a
* bucket describing the path for which all output files shall be saved under
*
* @return A {@link ListenableFuture} allowing you to register callbacks or wait for the
* completion of the operation.
*/
public ListenableFuture<DocumentOcrResultSet> runOcrForDocument(GoogleStorageLocation document, GoogleStorageLocation outputFilePathPrefix) {
Assert.isTrue(document.isFile(), "Provided document location is not a valid file location: " + document);
GcsSource gcsSource = GcsSource.newBuilder().setUri(document.uriString()).build();
String contentType = extractContentType(document);
InputConfig inputConfig = InputConfig.newBuilder().setMimeType(contentType).setGcsSource(gcsSource).build();
GcsDestination gcsDestination = GcsDestination.newBuilder().setUri(outputFilePathPrefix.uriString()).build();
OutputConfig outputConfig = OutputConfig.newBuilder().setGcsDestination(gcsDestination).setBatchSize(this.jsonOutputBatchSize).build();
AsyncAnnotateFileRequest request = AsyncAnnotateFileRequest.newBuilder().addFeatures(DOCUMENT_OCR_FEATURE).setInputConfig(inputConfig).setOutputConfig(outputConfig).build();
OperationFuture<AsyncBatchAnnotateFilesResponse, OperationMetadata> result = imageAnnotatorClient.asyncBatchAnnotateFilesAsync(Collections.singletonList(request));
return extractOcrResultFuture(result);
}
use of com.google.cloud.vision.v1.AsyncBatchAnnotateFilesResponse in project spring-cloud-gcp by spring-cloud.
the class DocumentOcrTemplate method extractOcrResultFuture.
private ListenableFuture<DocumentOcrResultSet> extractOcrResultFuture(OperationFuture<AsyncBatchAnnotateFilesResponse, OperationMetadata> grpcFuture) {
SettableListenableFuture<DocumentOcrResultSet> result = new SettableListenableFuture<>();
ApiFutures.addCallback(grpcFuture, new ApiFutureCallback<AsyncBatchAnnotateFilesResponse>() {
@Override
public void onFailure(Throwable throwable) {
result.setException(throwable);
}
@Override
public void onSuccess(AsyncBatchAnnotateFilesResponse asyncBatchAnnotateFilesResponse) {
String outputLocationUri = asyncBatchAnnotateFilesResponse.getResponsesList().get(0).getOutputConfig().getGcsDestination().getUri();
GoogleStorageLocation outputFolderLocation = new GoogleStorageLocation(outputLocationUri);
result.set(readOcrOutputFileSet(outputFolderLocation));
}
}, this.executor);
return result;
}
Aggregations