Function main

document-ai/process-document.js:18–101

(projectId, location, processorId, filePath)

'use strict';

async function main(projectId, location, processorId, filePath) {
  // [START documentai_process_document]
  /**
   * 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
  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);
    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