Annotazione di un batch di file in Cloud Storage (beta)

Annota un gruppo di file in Cloud Storage quando sei online.

Esempio di codice

Java

Prima di provare questo esempio, segui le istruzioni per la configurazione di Java nella guida rapida di Vision che utilizza le librerie client. Per ulteriori informazioni, consulta la documentazione di riferimento dell'API Vision Java.

import com.google.api.core.ApiFuture;
import com.google.cloud.vision.v1p4beta1.AnnotateFileRequest;
import com.google.cloud.vision.v1p4beta1.AnnotateFileResponse;
import com.google.cloud.vision.v1p4beta1.BatchAnnotateFilesRequest;
import com.google.cloud.vision.v1p4beta1.BatchAnnotateFilesResponse;
import com.google.cloud.vision.v1p4beta1.Block;
import com.google.cloud.vision.v1p4beta1.Feature;
import com.google.cloud.vision.v1p4beta1.Feature.Type;
import com.google.cloud.vision.v1p4beta1.GcsSource;
import com.google.cloud.vision.v1p4beta1.ImageAnnotatorClient;
import com.google.cloud.vision.v1p4beta1.InputConfig;
import com.google.cloud.vision.v1p4beta1.Page;
import com.google.cloud.vision.v1p4beta1.Paragraph;
import com.google.cloud.vision.v1p4beta1.Symbol;
import com.google.cloud.vision.v1p4beta1.TextAnnotation;
import com.google.cloud.vision.v1p4beta1.Word;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;

public class DetectBatchAnnotateFilesGcs {

  // Performs document feature detection on a remote PDF/TIFF/GIF file on Google Cloud Storage.
  public static void detectBatchAnnotateFilesGcs(String gcsPath) {
    // String gcsPath = "gs://Your_BUCKET_ID/path_to_your_data";

    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());
    }
  }
}

Python

Prima di provare questo esempio, segui le istruzioni di configurazione di Python nella guida rapida di Vision che utilizza le librerie client. Per ulteriori informazioni, consulta la documentazione di riferimento dell'API Vision Python.

def detect_batch_annotate_files_uri(gcs_uri):
    """Detects document features in a PDF/TIFF/GIF file.

    While your PDF file may have several pages,
    this API can process up to 5 pages only.

    Args:
    uri: The path to the file in Google Cloud Storage (gs://...)
    """
    from google.cloud import vision_v1p4beta1 as vision
    client = vision.ImageAnnotatorClient()

    # Other supported mime_types: image/tiff' or 'image/gif'
    mime_type = 'application/pdf'
    input_config = vision.InputConfig(
        gcs_source=vision.GcsSource(uri=gcs_uri), mime_type=mime_type)

    feature = vision.Feature(
        type_=vision.Feature.Type.DOCUMENT_TEXT_DETECTION)
    # Annotate the first two pages and the last one (max 5 pages)
    # First page starts at 1, and not 0. Last page is -1.
    pages = [1, 2, -1]

    request = vision.AnnotateFileRequest(
        input_config=input_config,
        features=[feature],
        pages=pages)

    response = client.batch_annotate_files(requests=[request])

    for image_response in response.responses[0].responses:
        for page in image_response.full_text_annotation.pages:
            for block in page.blocks:
                print(u'\nBlock confidence: {}\n'.format(block.confidence))
                for par in block.paragraphs:
                    print(u'\tParagraph confidence: {}'.format(par.confidence))
                    for word in par.words:
                        symbol_texts = [symbol.text for symbol in word.symbols]
                        word_text = ''.join(symbol_texts)
                        print(u'\t\tWord text: {} (confidence: {})'.format(
                            word_text, word.confidence))
                        for symbol in word.symbols:
                            print(u'\t\t\tSymbol: {} (confidence: {})'.format(
                                symbol.text, symbol.confidence))

Passaggi successivi

Per cercare e filtrare esempi di codice per altri prodotti Google Cloud, vedi il browser di esempio Google Cloud.