use of com.google.cloud.vision.v1p3beta1.TextAnnotation in project java-vision by googleapis.
the class DetectBatchAnnotateFiles method detectBatchAnnotateFiles.
// Performs document feature detection on a local PDF/TIFF/GIF file.
public static void detectBatchAnnotateFiles(String filePath) {
try (ImageAnnotatorClient client = ImageAnnotatorClient.create()) {
// Annotate the first two pages and the last one (max 5 pages)
// First page starts at 1, and not 0. Last page is -1.
List<Integer> pages = Arrays.asList(1, 2, -1);
ByteString pdfBytes = ByteString.readFrom(new FileInputStream(filePath));
Feature feat = Feature.newBuilder().setType(Type.DOCUMENT_TEXT_DETECTION).build();
// Other supported mime types : 'image/tiff' or 'image/gif'
InputConfig inputConfig = InputConfig.newBuilder().setMimeType("application/pdf").setContent(pdfBytes).build();
AnnotateFileRequest request = AnnotateFileRequest.newBuilder().addFeatures(feat).setInputConfig(inputConfig).addAllPages(pages).build();
List<AnnotateFileRequest> requests = new ArrayList<>();
requests.add(request);
BatchAnnotateFilesRequest batchAnnotateFilesRequest = BatchAnnotateFilesRequest.newBuilder().addAllRequests(requests).build();
ApiFuture<BatchAnnotateFilesResponse> future = client.batchAnnotateFilesCallable().futureCall(batchAnnotateFilesRequest);
BatchAnnotateFilesResponse response = future.get();
// Getting the first response
AnnotateFileResponse annotateFileResponse = response.getResponses(0);
// For full list of available annotations, see http://g.co/cloud/vision/docs
TextAnnotation textAnnotation = annotateFileResponse.getResponses(0).getFullTextAnnotation();
for (Page page : textAnnotation.getPagesList()) {
String pageText = "";
for (Block block : page.getBlocksList()) {
String blockText = "";
for (Paragraph para : block.getParagraphsList()) {
String paraText = "";
for (Word word : para.getWordsList()) {
String wordText = "";
for (Symbol symbol : word.getSymbolsList()) {
wordText = wordText + symbol.getText();
System.out.format("Symbol text: %s (Confidence: %f)\n", symbol.getText(), symbol.getConfidence());
}
System.out.format("Word text: %s (Confidence: %f)\n\n", wordText, word.getConfidence());
paraText = String.format("%s %s", paraText, wordText);
}
// Output Example using Paragraph:
System.out.println("\nParagraph: \n" + paraText);
System.out.format("Paragraph Confidence: %f\n", para.getConfidence());
blockText = blockText + paraText;
}
pageText = pageText + blockText;
}
}
System.out.println("\nComplete annotation:");
System.out.println(textAnnotation.getText());
} catch (Exception e) {
System.out.println("Error during detectPdfText: \n" + e.toString());
}
}
use of com.google.cloud.vision.v1p3beta1.TextAnnotation in project java-vision by googleapis.
the class DetectBatchAnnotateFilesGcs method detectBatchAnnotateFilesGcs.
// Performs document feature detection on a remote PDF/TIFF/GIF file on Google Cloud Storage.
public static void detectBatchAnnotateFilesGcs(String gcsPath) {
try (ImageAnnotatorClient client = ImageAnnotatorClient.create()) {
// Annotate the first two pages and the last one (max 5 pages)
// First page starts at 1, and not 0. Last page is -1.
List<Integer> pages = Arrays.asList(1, 2, -1);
GcsSource gcsSource = GcsSource.newBuilder().setUri(gcsPath).build();
Feature feat = Feature.newBuilder().setType(Type.DOCUMENT_TEXT_DETECTION).build();
// Other supported mime types : 'image/tiff' or 'image/gif'
InputConfig inputConfig = InputConfig.newBuilder().setMimeType("application/pdf").setGcsSource(gcsSource).build();
AnnotateFileRequest request = AnnotateFileRequest.newBuilder().addFeatures(feat).setInputConfig(inputConfig).addAllPages(pages).build();
List<AnnotateFileRequest> requests = new ArrayList<>();
requests.add(request);
BatchAnnotateFilesRequest batchAnnotateFilesRequest = BatchAnnotateFilesRequest.newBuilder().addAllRequests(requests).build();
ApiFuture<BatchAnnotateFilesResponse> future = client.batchAnnotateFilesCallable().futureCall(batchAnnotateFilesRequest);
BatchAnnotateFilesResponse response = future.get();
// Getting the first response
AnnotateFileResponse annotateFileResponse = response.getResponses(0);
// For full list of available annotations, see http://g.co/cloud/vision/docs
TextAnnotation textAnnotation = annotateFileResponse.getResponses(0).getFullTextAnnotation();
for (Page page : textAnnotation.getPagesList()) {
String pageText = "";
for (Block block : page.getBlocksList()) {
String blockText = "";
for (Paragraph para : block.getParagraphsList()) {
String paraText = "";
for (Word word : para.getWordsList()) {
String wordText = "";
for (Symbol symbol : word.getSymbolsList()) {
wordText = wordText + symbol.getText();
System.out.format("Symbol text: %s (Confidence: %f)\n", symbol.getText(), symbol.getConfidence());
}
System.out.format("Word text: %s (Confidence: %f)\n\n", wordText, word.getConfidence());
paraText = String.format("%s %s", paraText, wordText);
}
// Output Example using Paragraph:
System.out.println("\nParagraph: \n" + paraText);
System.out.format("Paragraph Confidence: %f\n", para.getConfidence());
blockText = blockText + paraText;
}
pageText = pageText + blockText;
}
}
System.out.println("\nComplete annotation:");
System.out.println(textAnnotation.getText());
} catch (Exception e) {
System.out.println("Error during detectPdfText: \n" + e.toString());
}
}
use of com.google.cloud.vision.v1p3beta1.TextAnnotation in project java-vision by googleapis.
the class ITSystemTest method detectDocumentTextTest.
@Test
public void detectDocumentTextTest() throws IOException {
List<AnnotateImageResponse> responses = getResponsesList("text.jpg", Type.DOCUMENT_TEXT_DETECTION, false);
String actual = "";
for (AnnotateImageResponse imgResponse : responses) {
TextAnnotation annotation = imgResponse.getFullTextAnnotation();
actual = annotation.getText();
}
assertThat(actual).contains("After preparation is complete");
}
Aggregations