使用用戶端程式庫處理文件

<dependencyManagement>
  <dependencies>
    <dependency>
      <groupId>com.google.cloud</groupId>
      <artifactId>libraries-bom</artifactId>
      <version>26.65.0</version>
      <type>pom</type>
      <scope>import</scope>
    </dependency>
  </dependencies>
</dependencyManagement>

<dependencies>
  <dependency>
    <groupId>com.google.cloud</groupId>
    <artifactId>google-cloud-document-ai</artifactId>
  </dependency>
</dependencies>

implementation 'com.google.cloud:google-cloud-document-ai:2.74.0'

libraryDependencies += "com.google.cloud" % "google-cloud-document-ai" % "2.74.0"

using Google.Cloud.DocumentAI.V1;
using Google.Protobuf;
using System;
using System.IO;

public class QuickstartSample
{
    public Document Quickstart(
        string projectId = "your-project-id",
        string locationId = "your-processor-location",
        string processorId = "your-processor-id",
        string localPath = "my-local-path/my-file-name",
        string mimeType = "application/pdf"
    )
    {
        // Create client
        var client = new DocumentProcessorServiceClientBuilder
        {
            Endpoint = $"{locationId}-documentai.googleapis.com"
        }.Build();

        // Read in local file
        using var fileStream = File.OpenRead(localPath);
        var rawDocument = new RawDocument
        {
            Content = ByteString.FromStream(fileStream),
            MimeType = mimeType
        };

        // Initialize request argument(s)
        var request = new ProcessRequest
        {
            Name = ProcessorName.FromProjectLocationProcessor(projectId, locationId, processorId).ToString(),
            RawDocument = rawDocument
        };

        // Make the request
        var response = client.ProcessDocument(request);

        var document = response.Document;
        Console.WriteLine(document.Text);
        return document;
    }
}

#include "google/cloud/documentai/v1/document_processor_client.h"
#include "google/cloud/location.h"
#include <fstream>
#include <iostream>
#include <string>

int main(int argc, char* argv[]) try {
  if (argc != 5) {
    std::cerr << "Usage: " << argv[0]
              << " project-id location-id processor-id filename (PDF only)\n";
    return 1;
  }

  std::string const location_id = argv[2];
  if (location_id != "us" && location_id != "eu") {
    std::cerr << "location-id must be either 'us' or 'eu'\n";
    return 1;
  }
  auto const location = google::cloud::Location(argv[1], location_id);

  namespace documentai = ::google::cloud::documentai_v1;
  auto client = documentai::DocumentProcessorServiceClient(
      documentai::MakeDocumentProcessorServiceConnection(
          location.location_id()));

  google::cloud::documentai::v1::ProcessRequest req;
  req.set_name(location.FullName() + "/processors/" + argv[3]);
  req.set_skip_human_review(true);
  auto& doc = *req.mutable_raw_document();
  doc.set_mime_type("application/pdf");
  std::ifstream is(argv[4]);
  doc.set_content(std::string{std::istreambuf_iterator<char>(is), {}});

  auto resp = client.ProcessDocument(std::move(req));
  if (!resp) throw std::move(resp).status();
  std::cout << resp->document().text() << "\n";

  return 0;
} catch (google::cloud::Status const& status) {
  std::cerr << "google::cloud::Status thrown: " << status << "\n";
  return 1;
}

import (
	"context"
	"flag"
	"fmt"
	"os"

	documentai "cloud.google.com/go/documentai/apiv1"
	"cloud.google.com/go/documentai/apiv1/documentaipb"
	"google.golang.org/api/option"
)

func main() {
	projectID := flag.String("project_id", "PROJECT_ID", "Cloud Project ID")
	location := flag.String("location", "us", "The Processor location")
	// Create a Processor before running sample
	processorID := flag.String("processor_id", "aaaaaaaa", "The Processor ID")
	filePath := flag.String("file_path", "invoice.pdf", "The path to the file to parse")
	mimeType := flag.String("mime_type", "application/pdf", "The mimeType of the file")
	flag.Parse()

	ctx := context.Background()

	endpoint := fmt.Sprintf("%s-documentai.googleapis.com:443", *location)
	client, err := documentai.NewDocumentProcessorClient(ctx, option.WithEndpoint(endpoint))
	if err != nil {
		fmt.Println(fmt.Errorf("error creating Document AI client: %w", err))
	}
	defer client.Close()

	// Open local file.
	data, err := os.ReadFile(*filePath)
	if err != nil {
		fmt.Println(fmt.Errorf("os.ReadFile: %w", err))
	}

	req := &documentaipb.ProcessRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/processors/%s", *projectID, *location, *processorID),
		Source: &documentaipb.ProcessRequest_RawDocument{
			RawDocument: &documentaipb.RawDocument{
				Content:  data,
				MimeType: *mimeType,
			},
		},
	}
	resp, err := client.ProcessDocument(ctx, req)
	if err != nil {
		fmt.Println(fmt.Errorf("processDocument: %w", err))
	}

	// Handle the results.
	document := resp.GetDocument()
	fmt.Printf("Document Text: %s", document.GetText())
}

import com.google.cloud.documentai.v1.Document;
import com.google.cloud.documentai.v1.DocumentProcessorServiceClient;
import com.google.cloud.documentai.v1.DocumentProcessorServiceSettings;
import com.google.cloud.documentai.v1.ProcessRequest;
import com.google.cloud.documentai.v1.ProcessResponse;
import com.google.cloud.documentai.v1.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 QuickStart {
  public static void main(String[] args)
      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 processorId = "your-processor-id";
    String filePath = "path/to/input/file.pdf";
    quickStart(projectId, location, processorId, filePath);
  }

  public static void quickStart(
      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();

      // Get all of the document text as one big string
      String text = documentResponse.getText();

      // Read the text recognition output from the processor
      System.out.println("The document contains the following paragraphs:");
      Document.Page firstPage = documentResponse.getPages(0);
      List<Document.Page.Paragraph> paragraphs = firstPage.getParagraphsList();

      for (Document.Page.Paragraph paragraph : paragraphs) {
        String paragraphText = getText(paragraph.getLayout().getTextAnchor(), text);
        System.out.printf("Paragraph text:\n%s\n", paragraphText);
      }
    }
  }

  // Extract shards from the text field
  private static String getText(Document.TextAnchor textAnchor, String text) {
    if (textAnchor.getTextSegmentsList().size() > 0) {
      int startIdx = (int) textAnchor.getTextSegments(0).getStartIndex();
      int endIdx = (int) textAnchor.getTextSegments(0).getEndIndex();
      return text.substring(startIdx, endIdx);
    }
    return "[NO TEXT]";
  }
}

/**
 * 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').v1;

// Instantiates a client
// apiEndpoint regions available: eu-documentai.googleapis.com, us-documentai.googleapis.com (Required if using eu based processor)
// const client = new DocumentProcessorServiceClient({apiEndpoint: 'eu-documentai.googleapis.com'});
const client = new DocumentProcessorServiceClient();

async function quickstart() {
  // 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);
  const {document} = result;

  // Get all of the document text as one big string
  const {text} = document;

  // Extract shards from the text field
  const getText = textAnchor => {
    if (!textAnchor.textSegments || textAnchor.textSegments.length === 0) {
      return '';
    }

    // First shard in document doesn't have startIndex property
    const startIndex = textAnchor.textSegments[0].startIndex || 0;
    const endIndex = textAnchor.textSegments[0].endIndex;

    return text.substring(startIndex, endIndex);
  };

  // Read the text recognition output from the processor
  console.log('The document contains the following paragraphs:');
  const [page1] = document.pages;
  const {paragraphs} = page1;

  for (const paragraph of paragraphs) {
    const paragraphText = getText(paragraph.layout.textAnchor);
    console.log(`Paragraph text:\n${paragraphText}`);
  }
}

# Include the autoloader for libraries installed with Composer.
require __DIR__ . '/vendor/autoload.php';

# Import the Google Cloud client library.
use Google\Cloud\DocumentAI\V1\Client\DocumentProcessorServiceClient;
use Google\Cloud\DocumentAI\V1\RawDocument;
use Google\Cloud\DocumentAI\V1\ProcessRequest;

# TODO(developer): Update the following lines before running the sample.
# Your Google Cloud Platform project ID.
$projectId = 'YOUR_PROJECT_ID';

# Your Processor Location.
$location = 'us';

# Your Processor ID as hexadecimal characters.
# Not to be confused with the Processor Display Name.
$processorId = 'YOUR_PROCESSOR_ID';

# Path for the file to read.
$documentPath = 'resources/invoice.pdf';

# Create Client.
$client = new DocumentProcessorServiceClient();

# Read in file.
$handle = fopen($documentPath, 'rb');
$contents = fread($handle, filesize($documentPath));
fclose($handle);

# Load file contents into a RawDocument.
$rawDocument = (new RawDocument())
    ->setContent($contents)
    ->SetMimeType('application/pdf');

# Get the Fully-qualified Processor Name.
$fullProcessorName = $client->processorName($projectId, $location, $processorId);

# Send a ProcessRequest and get a ProcessResponse.
$request = (new ProcessRequest())
    ->setName($fullProcessorName)
    ->setRawDocument($rawDocument);

$response = $client->processDocument($request);

# Show the text found in the document.
printf('Document Text: %s', $response->getDocument()->getText());

from google.api_core.client_options import ClientOptions
from google.cloud import documentai_v1

# TODO(developer): Create a processor of type "OCR_PROCESSOR".

# TODO(developer): Update and uncomment these variables before running the sample.
# project_id = "MY_PROJECT_ID"

# Processor ID as hexadecimal characters.
# Not to be confused with the Processor Display Name.
# processor_id = "MY_PROCESSOR_ID"

# Processor location. For example: "us" or "eu".
# location = "MY_PROCESSOR_LOCATION"

# Path for file to process.
# file_path = "/path/to/local/pdf"

# Set `api_endpoint` if you use a location other than "us".
opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")

# Initialize Document AI client.
client = documentai_v1.DocumentProcessorServiceClient(client_options=opts)

# Get the Fully-qualified Processor path.
full_processor_name = client.processor_path(project_id, location, processor_id)

# Get a Processor reference.
request = documentai_v1.GetProcessorRequest(name=full_processor_name)
processor = client.get_processor(request=request)

# `processor.name` is the full resource name of the processor.
# For example: `projects/{project_id}/locations/{location}/processors/{processor_id}`
print(f"Processor Name: {processor.name}")

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

# Load binary data.
# For supported MIME types, refer to https://cloud.google.com/document-ai/docs/file-types
raw_document = documentai_v1.RawDocument(
    content=image_content,
    mime_type="application/pdf",
)

# Send a request and get the processed document.
request = documentai_v1.ProcessRequest(name=processor.name, raw_document=raw_document)
result = client.process_document(request=request)
document = result.document

# Read the text recognition output from the processor.
# For a full list of `Document` object attributes, reference this page:
# https://cloud.google.com/document-ai/docs/reference/rest/v1/Document
print("The document contains the following text:")
print(document.text)

require "google/cloud/document_ai/v1"

##
# Document AI quickstart
#
# @param project_id [String] Your Google Cloud project (e.g. "my-project")
# @param location_id [String] Your Processor Location (e.g. "us")
# @param processor_id [String] Your Processor ID (e.g. "a14dae8f043b60bd")
# @param file_path [String] Path to Local File (e.g. "invoice.pdf")
# @param mime_type [String] Refer to https://cloud.google.com/document-ai/docs/file-types (e.g. "application/pdf")
#
def quickstart project_id:, location_id:, processor_id:, file_path:, mime_type:
  # Create the Document AI client.
  client = ::Google::Cloud::DocumentAI::V1::DocumentProcessorService::Client.new do |config|
    config.endpoint = "#{location_id}-documentai.googleapis.com"
  end

  # Build the resource name from the project.
  name = client.processor_path(
    project: project_id,
    location: location_id,
    processor: processor_id
  )

  # Read the bytes into memory
  content = File.binread file_path

  # Create request
  request = Google::Cloud::DocumentAI::V1::ProcessRequest.new(
    skip_human_review: true,
    name: name,
    raw_document: {
      content: content,
      mime_type: mime_type
    }
  )

  # Process document
  response = client.process_document request

  # Handle response
  puts response.document.text
end