Verhalten von Document-Splitter

import com.google.cloud.documentai.v1beta3.Document;
import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceClient;
import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceSettings;
import com.google.cloud.documentai.v1beta3.ProcessRequest;
import com.google.cloud.documentai.v1beta3.ProcessResponse;
import com.google.cloud.documentai.v1beta3.RawDocument;
import com.google.protobuf.ByteString;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeoutException;

public class ProcessSplitterDocument {
  public static void processSplitterDocument()
      throws IOException, InterruptedException, ExecutionException, TimeoutException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String location = "your-project-location"; // Format is "us" or "eu".
    String processerId = "your-processor-id";
    String filePath = "path/to/input/file.pdf";
    processSplitterDocument(projectId, location, processerId, filePath);
  }

  public static void processSplitterDocument(
      String projectId, String location, String processorId, String filePath)
      throws IOException, InterruptedException, ExecutionException, TimeoutException {
    // Initialize client that will be used to send requests. This client only needs
    // to be created
    // once, and can be reused for multiple requests. After completing all of your
    // requests, call
    // the "close" method on the client to safely clean up any remaining background
    // resources.
    String endpoint = String.format("%s-documentai.googleapis.com:443", location);
    DocumentProcessorServiceSettings settings =
        DocumentProcessorServiceSettings.newBuilder().setEndpoint(endpoint).build();
    try (DocumentProcessorServiceClient client = DocumentProcessorServiceClient.create(settings)) {
      // The full resource name of the processor, e.g.:
      // projects/project-id/locations/location/processor/processor-id
      // You must create new processors in the Cloud Console first
      String name =
          String.format("projects/%s/locations/%s/processors/%s", projectId, location, processorId);

      // Read the file.
      byte[] imageFileData = Files.readAllBytes(Paths.get(filePath));

      // Convert the image data to a Buffer and base64 encode it.
      ByteString content = ByteString.copyFrom(imageFileData);

      RawDocument document =
          RawDocument.newBuilder().setContent(content).setMimeType("application/pdf").build();

      // Configure the process request.
      ProcessRequest request =
          ProcessRequest.newBuilder().setName(name).setRawDocument(document).build();

      // Recognizes text entities in the PDF document
      ProcessResponse result = client.processDocument(request);
      Document documentResponse = result.getDocument();

      System.out.println("Document processing complete.");

      // Read the splitter output from the document splitter processor:
      // https://cloud.google.com/document-ai/docs/processors-list#processor_doc-splitter
      // This processor only provides text for the document and information on how
      // to split the document on logical boundaries. To identify and extract text,
      // form elements, and entities please see other processors like the OCR, form,
      // and specalized processors.
      List<Document.Entity> entities = documentResponse.getEntitiesList();
      System.out.printf("Found %d subdocuments:\n", entities.size());
      for (Document.Entity entity : entities) {
        float entityConfidence = entity.getConfidence();
        String pagesRangeText = pageRefsToString(entity.getPageAnchor().getPageRefsList());
        String subdocumentType = entity.getType();
        if (subdocumentType.isEmpty()) {
          System.out.printf(
              "%.2f%% confident that %s a subdocument.\n", entityConfidence * 100, pagesRangeText);
        } else {
          System.out.printf(
              "%.2f%% confident that %s a '%s' subdocument.\n",
              entityConfidence * 100, pagesRangeText, subdocumentType);
        }
      }
    }
  }

  // Converts page reference(s) to a string describing the page or page range.
  private static String pageRefsToString(List<Document.PageAnchor.PageRef> pageRefs) {
    if (pageRefs.size() == 1) {
      return String.format("page %d is", pageRefs.get(0).getPage() + 1);
    } else {
      long start = pageRefs.get(0).getPage() + 1;
      long end = pageRefs.get(1).getPage() + 1;
      return String.format("pages %d to %d are", start, end);
    }
  }
}

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'YOUR_PROJECT_LOCATION'; // Format is 'us' or 'eu'
// const processorId = 'YOUR_PROCESSOR_ID'; // Create processor in Cloud Console
// const filePath = '/path/to/local/pdf';

const {DocumentProcessorServiceClient} =
  require('@google-cloud/documentai').v1beta3;

// Instantiates a client
const client = new DocumentProcessorServiceClient();

async function processDocument() {
  // The full resource name of the processor, e.g.:
  // projects/project-id/locations/location/processor/processor-id
  // You must create new processors in the Cloud Console first
  const name = `projects/${projectId}/locations/${location}/processors/${processorId}`;

  // Read the file into memory.
  const fs = require('fs').promises;
  const imageFile = await fs.readFile(filePath);

  // Convert the image data to a Buffer and base64 encode it.
  const encodedImage = Buffer.from(imageFile).toString('base64');

  const request = {
    name,
    rawDocument: {
      content: encodedImage,
      mimeType: 'application/pdf',
    },
  };

  // Recognizes text entities in the PDF document
  const [result] = await client.processDocument(request);

  console.log('Document processing complete.');

  // Read fields specificly from the specalized US drivers license processor:
  // https://cloud.google.com/document-ai/docs/processors-list#processor_us-driver-license-parser
  // retriving data from other specalized processors follow a similar pattern.
  // For a complete list of processors see:
  // https://cloud.google.com/document-ai/docs/processors-list
  //
  // OCR and other data is also present in the quality processor's response.
  // Please see the OCR and other samples for how to parse other data in the
  // response.
  const {document} = result;
  console.log(`Found ${document.entities.length} subdocuments:`);
  for (const entity of document.entities) {
    const conf = entity.confidence * 100;
    const pagesRange = pageRefsToRange(entity.pageAnchor.pageRefs);
    if (entity.type !== '') {
      console.log(
        `${conf.toFixed(2)}% confident that ${pagesRange} a "${
          entity.type
        }" subdocument.`
      );
    } else {
      console.log(
        `${conf.toFixed(2)}% confident that ${pagesRange} a subdocument.`
      );
    }
  }
}

// Converts a page ref to a string describing the page or page range.
const pageRefsToRange = pageRefs => {
  if (pageRefs.length === 1) {
    const num = parseInt(pageRefs[0].page) + 1 || 1;
    return `page ${num} is`;
  } else {
    const start = parseInt(pageRefs[0].page) + 1 || 1;
    const end = parseInt(pageRefs[1].page) + 1;
    return `pages ${start} to ${end} are`;
  }
};

from typing import Optional, Sequence

from google.api_core.client_options import ClientOptions
from google.cloud import documentai

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_PROCESSOR_LOCATION" # Format is "us" or "eu"
# processor_id = "YOUR_PROCESSOR_ID" # Create processor before running sample
# processor_version = "rc" # Refer to https://cloud.google.com/document-ai/docs/manage-processor-versions for more information
# file_path = "/path/to/local/pdf"
# mime_type = "application/pdf" # Refer to https://cloud.google.com/document-ai/docs/file-types for supported file types


def process_document_splitter_sample(
    project_id: str,
    location: str,
    processor_id: str,
    processor_version: str,
    file_path: str,
    mime_type: str,
) -> None:
    # Online processing request to Document AI
    document = process_document(
        project_id, location, processor_id, processor_version, file_path, mime_type
    )

    # Read the splitter output from a document splitter/classifier processor:
    # e.g. https://cloud.google.com/document-ai/docs/processors-list#processor_procurement-document-splitter
    # This processor only provides text for the document and information on how
    # to split the document on logical boundaries. To identify and extract text,
    # form elements, and entities please see other processors like the OCR, form,
    # and specalized processors.

    print(f"Found {len(document.entities)} subdocuments:")
    for entity in document.entities:
        conf_percent = f"{entity.confidence:.1%}"
        pages_range = page_refs_to_string(entity.page_anchor.page_refs)

        # Print subdocument type information, if available
        if entity.type_:
            print(
                f"{conf_percent} confident that {pages_range} a '{entity.type_}' subdocument."
            )
        else:
            print(f"{conf_percent} confident that {pages_range} a subdocument.")


def page_refs_to_string(
    page_refs: Sequence[documentai.Document.PageAnchor.PageRef],
) -> str:
    """Converts a page ref to a string describing the page or page range."""
    pages = [str(int(page_ref.page) + 1) for page_ref in page_refs]
    if len(pages) == 1:
        return f"page {pages[0]} is"
    else:
        return f"pages {', '.join(pages)} are"




def process_document(
    project_id: str,
    location: str,
    processor_id: str,
    processor_version: str,
    file_path: str,
    mime_type: str,
    process_options: Optional[documentai.ProcessOptions] = None,
) -> documentai.Document:
    # You must set the `api_endpoint` if you use a location other than "us".
    client = documentai.DocumentProcessorServiceClient(
        client_options=ClientOptions(
            api_endpoint=f"{location}-documentai.googleapis.com"
        )
    )

    # The full resource name of the processor version, e.g.:
    # `projects/{project_id}/locations/{location}/processors/{processor_id}/processorVersions/{processor_version_id}`
    # You must create a processor before running this sample.
    name = client.processor_version_path(
        project_id, location, processor_id, processor_version
    )

    # Read the file into memory
    with open(file_path, "rb") as image:
        image_content = image.read()

    # Configure the process request
    request = documentai.ProcessRequest(
        name=name,
        raw_document=documentai.RawDocument(content=image_content, mime_type=mime_type),
        # Only supported for Document OCR processor
        process_options=process_options,
    )

    result = client.process_document(request=request)

    # For a full list of `Document` object attributes, reference this page:
    # https://cloud.google.com/document-ai/docs/reference/rest/v1/Document
    return result.document

from google.cloud.documentai_toolbox import document

# TODO(developer): Uncomment these variables before running the sample.
# Given a local document.proto or sharded document.proto from a splitter/classifier in path
# document_path = "path/to/local/document.json"
# pdf_path = "path/to/local/document.pdf"
# output_path = "resources/output/"


def split_pdf_sample(document_path: str, pdf_path: str, output_path: str) -> None:
    wrapped_document = document.Document.from_document_path(document_path=document_path)

    output_files = wrapped_document.split_pdf(
        pdf_path=pdf_path, output_path=output_path
    )

    print("Document Successfully Split")
    for output_file in output_files:
        print(output_file)