use of com.google.cloud.vision.v1p4beta1.GcsSource in project java-retail by googleapis.
the class CreateTestResources method getImportProductsGcsRequest.
public static ImportProductsRequest getImportProductsGcsRequest(String gcsObjectName) {
GcsSource gcsSource = GcsSource.newBuilder().addAllInputUris(Collections.singleton(String.format("gs://%s/%s", BUCKET_NAME, gcsObjectName))).build();
ProductInputConfig inputConfig = ProductInputConfig.newBuilder().setGcsSource(gcsSource).build();
System.out.println("GRS source: " + gcsSource.getInputUrisList());
ImportErrorsConfig errorsConfig = ImportErrorsConfig.newBuilder().setGcsPrefix(GCS_ERROR_BUCKET).build();
ImportProductsRequest importRequest = ImportProductsRequest.newBuilder().setParent(DEFAULT_CATALOG).setReconciliationMode(ReconciliationMode.INCREMENTAL).setInputConfig(inputConfig).setErrorsConfig(errorsConfig).build();
System.out.println("Import products from google cloud source request: " + importRequest);
return importRequest;
}
use of com.google.cloud.vision.v1p4beta1.GcsSource in project java-document-ai by googleapis.
the class BatchParseFormBeta method batchParseFormGcs.
public static void batchParseFormGcs(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);
// Improve form parsing results by providing key-value pair hints.
// For each key hint, key is text that is likely to appear in the
// document as a form field name (i.e. "DOB").
// Value types are optional, but can be one or more of:
// ADDRESS, LOCATION, ORGANIZATION, PERSON, PHONE_NUMBER, ID,
// NUMBER, EMAIL, PRICE, TERMS, DATE, NAME
KeyValuePairHint keyValuePairHint = KeyValuePairHint.newBuilder().setKey("Phone").addValueTypes("PHONE_NUMBER").build();
KeyValuePairHint keyValuePairHint2 = KeyValuePairHint.newBuilder().setKey("Contact").addValueTypes("EMAIL").addValueTypes("NAME").build();
// Setting enabled=True enables form extraction
FormExtractionParams params = FormExtractionParams.newBuilder().setEnabled(true).addKeyValuePairHints(keyValuePairHint).addKeyValuePairHints(keyValuePairHint2).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().setFormExtractionParams(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);
for (Document.Page.FormField field : page1.getFormFieldsList()) {
String fieldName = getText(field.getFieldName(), text);
String fieldValue = getText(field.getFieldValue(), text);
System.out.println("Extracted form fields pair:");
System.out.printf("\t(%s, %s))", fieldName, fieldValue);
}
}
// Clean up temp file.
tempFile.deleteOnExit();
}
}
}
}
use of com.google.cloud.vision.v1p4beta1.GcsSource in project java-document-ai by googleapis.
the class ParseFormBeta method parseForm.
public static void parseForm(String projectId, String location, String inputGcsUri) throws IOException, ExecutionException, InterruptedException {
// 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);
// Improve form parsing results by providing key-value pair hints.
// For each key hint, key is text that is likely to appear in the
// document as a form field name (i.e. "DOB").
// Value types are optional, but can be one or more of:
// ADDRESS, LOCATION, ORGANIZATION, PERSON, PHONE_NUMBER, ID,
// NUMBER, EMAIL, PRICE, TERMS, DATE, NAME
KeyValuePairHint keyValuePairHint = KeyValuePairHint.newBuilder().setKey("Phone").addValueTypes("PHONE_NUMBER").build();
KeyValuePairHint keyValuePairHint2 = KeyValuePairHint.newBuilder().setKey("Contact").addValueTypes("EMAIL").addValueTypes("NAME").build();
// Setting enabled=True enables form extraction
FormExtractionParams params = FormExtractionParams.newBuilder().setEnabled(true).addKeyValuePairHints(keyValuePairHint).addKeyValuePairHints(keyValuePairHint2).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).setFormExtractionParams(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();
// Process the output
if (response.getPagesCount() > 0) {
Document.Page page1 = response.getPages(0);
for (Document.Page.FormField field : page1.getFormFieldsList()) {
String fieldName = getText(field.getFieldName(), text);
String fieldValue = getText(field.getFieldValue(), text);
System.out.println("Extracted form fields pair:");
System.out.printf("\t(%s, %s))", fieldName, fieldValue);
}
}
}
}
use of com.google.cloud.vision.v1p4beta1.GcsSource in project google-cloud-java by GoogleCloudPlatform.
the class TranslateSnippetsBeta method createGlossary.
// [END translate_batch_translate_text_beta]
/**
* Creates a glossary.
*
* @param projectId - Id of the project.
* @param location - location name.
* @param name - Glossary name.
* @param gcsUri - Google Cloud Storage URI where glossary is stored in csv format.
*/
// [START translate_create_glossary_beta]
static Glossary createGlossary(String projectId, String location, String name, String gcsUri) {
try (TranslationServiceClient translationServiceClient = TranslationServiceClient.create()) {
LocationName locationName = LocationName.newBuilder().setProject(projectId).setLocation(location).build();
LanguageCodesSet languageCodesSet = LanguageCodesSet.newBuilder().addLanguageCodes("en").addLanguageCodes("es").build();
GcsSource gcsSource = GcsSource.newBuilder().setInputUri(gcsUri).build();
GlossaryInputConfig glossaryInputConfig = GlossaryInputConfig.newBuilder().setGcsSource(gcsSource).build();
GlossaryName glossaryName = GlossaryName.newBuilder().setProject(projectId).setLocation(location).setGlossary(name).build();
Glossary glossary = Glossary.newBuilder().setLanguageCodesSet(languageCodesSet).setInputConfig(glossaryInputConfig).setName(glossaryName.toString()).build();
CreateGlossaryRequest request = CreateGlossaryRequest.newBuilder().setParent(locationName.toString()).setGlossary(glossary).build();
// Call the API
Glossary response = translationServiceClient.createGlossaryAsync(request).get(300, TimeUnit.SECONDS);
System.out.format("Created: %s\n", response.getName());
System.out.format("Input Uri: %s\n", response.getInputConfig().getGcsSource());
return response;
} catch (Exception e) {
throw new RuntimeException("Couldn't create client.", e);
}
}
use of com.google.cloud.vision.v1p4beta1.GcsSource in project java-document-ai by googleapis.
the class ParseWithModelBeta method parseWithModel.
public static void parseWithModel(String projectId, String location, String autoMlModel, String gcsUri) 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);
AutoMlParams params = AutoMlParams.newBuilder().setModel(autoMlModel).build();
GcsSource uri = GcsSource.newBuilder().setUri(gcsUri).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).setAutomlParams(params).setInputConfig(config).build();
// Recognizes text entities in the PDF document
Document response = client.processDocument(request);
// Process the output
for (Document.Label label : response.getLabelsList()) {
System.out.printf("Label detected: %s\n", label.getName());
System.out.printf("Confidence: %s\n", label.getConfidence());
}
}
}
Aggregations