로컬 파일 배치에 주석 추가(베타)

온라인 상태일 때 로컬 파일 배치에 주석을 추가합니다.

코드 샘플

Java

이 샘플을 사용해 보기 전에 Vision 빠른 시작: 클라이언트 라이브러리 사용의 Java 설정 안내를 따르세요. 자세한 내용은 Vision Java API 참고 문서를 참조하세요.

Vision에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

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.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 com.google.protobuf.ByteString;
import java.io.FileInputStream;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;

public class DetectBatchAnnotateFiles {

  // Performs document feature detection on a local PDF/TIFF/GIF file.
  public static void detectBatchAnnotateFiles(String filePath) {
    // String filePath = "path/to/your_file";

    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());
    }
  }
}

Python

이 샘플을 사용해 보기 전에 Vision 빠른 시작: 클라이언트 라이브러리 사용의 Python 설정 안내를 따르세요. 자세한 내용은 Vision Python API 참고 문서를 참조하세요.

Vision에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

def detect_batch_annotate_files(path):
    """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:
    path: The path to the local file.
    """
    from google.cloud import vision_v1p4beta1 as vision

    client = vision.ImageAnnotatorClient()

    with open(path, "rb") as pdf_file:
        content = pdf_file.read()

    # Other supported mime_types: image/tiff' or 'image/gif'
    mime_type = "application/pdf"
    input_config = vision.InputConfig(content=content, 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(f"\nBlock confidence: {block.confidence}\n")
                for par in block.paragraphs:
                    print(f"\tParagraph confidence: {par.confidence}")
                    for word in par.words:
                        symbol_texts = [symbol.text for symbol in word.symbols]
                        word_text = "".join(symbol_texts)
                        print(
                            "\t\tWord text: {} (confidence: {})".format(
                                word_text, word.confidence
                            )
                        )
                        for symbol in word.symbols:
                            print(
                                "\t\t\tSymbol: {} (confidence: {})".format(
                                    symbol.text, symbol.confidence
                                )
                            )

다음 단계

다른 Google Cloud 제품의 코드 샘플을 검색하고 필터링하려면 Google Cloud 샘플 브라우저를 참조하세요.