use of com.google.cloud.vision.v1p4beta1.AnnotateFileResponse in project spring-cloud-gcp by GoogleCloudPlatform.
the class CloudVisionTemplate method extractTextFromFile.
/**
* Extract the text out of a file and return the result as a String.
*
* @param fileResource the file one wishes to analyze
* @param mimeType the mime type of the fileResource. Currently, only "application/pdf",
* "image/tiff" and "image/gif" are supported.
* @return the text extracted from the pdf as a string per page
* @throws CloudVisionException if the image could not be read or if text extraction failed
*/
public List<String> extractTextFromFile(Resource fileResource, String mimeType) {
AnnotateFileResponse response = analyzeFile(fileResource, mimeType, Type.DOCUMENT_TEXT_DETECTION);
List<AnnotateImageResponse> annotateImageResponses = response.getResponsesList();
if (annotateImageResponses.isEmpty()) {
throw new CloudVisionException(EMPTY_RESPONSE_ERROR_MESSAGE);
}
List<String> result = annotateImageResponses.stream().map(annotateImageResponse -> annotateImageResponse.getFullTextAnnotation().getText()).collect(Collectors.toList());
if (result.isEmpty() && response.getError().getCode() != Code.OK.getNumber()) {
throw new CloudVisionException(response.getError().getMessage());
}
return result;
}
use of com.google.cloud.vision.v1p4beta1.AnnotateFileResponse in project spring-cloud-gcp by GoogleCloudPlatform.
the class CloudVisionTemplate method analyzeFile.
/**
* Analyze a file and extract the features of the image specified by {@code featureTypes}.
*
* <p>A feature describes the kind of Cloud Vision analysis one wishes to perform on a file, such
* as text detection, image labelling, facial detection, etc. A full list of feature types can be
* found in {@link Feature.Type}.
*
* @param fileResource the file one wishes to analyze. The Cloud Vision APIs support image formats
* described here: https://cloud.google.com/vision/docs/supported-files. Documents with more
* than 5 pages are not supported.
* @param mimeType the mime type of the fileResource. Currently, only "application/pdf",
* "image/tiff" and "image/gif" are supported.
* @param featureTypes the types of image analysis to perform on the image
* @return the results of file analyse
* @throws CloudVisionException if the file could not be read or if a malformed response is
* received from the Cloud Vision APIs
*/
public AnnotateFileResponse analyzeFile(Resource fileResource, String mimeType, Feature.Type... featureTypes) {
ByteString imgBytes;
try {
imgBytes = ByteString.readFrom(fileResource.getInputStream());
} catch (IOException ex) {
throw new CloudVisionException(READ_BYTES_ERROR_MESSAGE, ex);
}
InputConfig inputConfig = InputConfig.newBuilder().setMimeType(mimeType).setContent(imgBytes).build();
List<Feature> featureList = Arrays.stream(featureTypes).map(featureType -> Feature.newBuilder().setType(featureType).build()).collect(Collectors.toList());
BatchAnnotateFilesRequest request = BatchAnnotateFilesRequest.newBuilder().addRequests(AnnotateFileRequest.newBuilder().addAllFeatures(featureList).setInputConfig(inputConfig).build()).build();
BatchAnnotateFilesResponse response = this.imageAnnotatorClient.batchAnnotateFiles(request);
List<AnnotateFileResponse> annotateFileResponses = response.getResponsesList();
if (!annotateFileResponses.isEmpty()) {
return annotateFileResponses.get(0);
} else {
throw new CloudVisionException(EMPTY_RESPONSE_ERROR_MESSAGE);
}
}
use of com.google.cloud.vision.v1p4beta1.AnnotateFileResponse in project spring-cloud-gcp by GoogleCloudPlatform.
the class OcrPageRange method parseJsonBlob.
private static List<TextAnnotation> parseJsonBlob(Blob blob) throws InvalidProtocolBufferException {
AnnotateFileResponse.Builder annotateFileResponseBuilder = AnnotateFileResponse.newBuilder();
String jsonContent = new String(blob.getContent(), StandardCharsets.UTF_8);
JsonFormat.parser().ignoringUnknownFields().merge(jsonContent, annotateFileResponseBuilder);
AnnotateFileResponse annotateFileResponse = annotateFileResponseBuilder.build();
return annotateFileResponse.getResponsesList().stream().map(AnnotateImageResponse::getFullTextAnnotation).collect(Collectors.toList());
}
Aggregations