OcrTesseractService.ts

import Tesseract from "tesseract.js";
import PdfService from "./PdfService";

export const OcrTesseractLanguages = [
  { name: "English", value: "eng" },
  { name: "Spanish", value: "spa" },
];

async function scan(file: string, lang: string): Promise<string> {
  return await new Promise(async (resolve, reject) => {
    try {
      if (file.endsWith(".pdf") || file.startsWith("data:application/pdf")) {
        const images = await PdfService.convertToImages({ file });
        console.log({ images });
        let text = "";
        for (const image of images) {
          text += await scanImage(image.base64, lang);
        }

        // const text = await PdfService.convertToText(file);
        resolve(text);
      } else {
        // OCR
        const text = await scanImage(file, lang);
        resolve(text);
      }
    } catch (e) {
      // eslint-disable-next-line no-console
      console.log(e);
      reject(e);
    }
  });
}

async function scanImage(file: string, lang: string): Promise<string> {
  // eslint-disable-next-line no-console
  console.log("[OCR] Scanning image: ", file, lang);
  return await new Promise(async (resolve, reject) => {
    let image = file;
    await Tesseract.recognize(image, lang, {
      logger: (m) => {
        // eslint-disable-next-line no-console
        console.log("[OCR] Logger: ", JSON.stringify(m));
      },
    })
      .then(({ data: { text } }) => {
        // eslint-disable-next-line no-console
        console.log("[OCR] Result: ", text);
        resolve(text);
      })
      .catch((e) => {
        // eslint-disable-next-line no-console
        console.log("[OCR] Error: ", e);
        reject(e);
      });
  });
}

export default {
  scan,
};