tesseract.js-core

import { readFileSync } from 'fs'; import TesseractCoreInit from 'tesseract.js-core/tesseract-core'; const runOcr = async (imagePath) => { console.log('Loading TesseractCore module...'); // The factory function returns a Promise that resolves to the Emscripten module const TesseractCore = await TesseractCoreInit(); console.log('TesseractCore module loaded. Initializing...'); // This is a minimal example showing low-level API interaction. // In a real application, consider using tesseract.js for a higher-level API. const core = new TesseractCore.TesseractApi(); core.Init(process.env.LANG_PATH || '/usr/share/tessdata', 'eng'); // Initialize with language data const imageBuffer = readFileSync(imagePath); // Assuming imageBuffer is a PNG or JPG and Tesseract can handle its format directly // In a browser, you might pass a Canvas/ImageData object core.SetImage(imageBuffer, imageBuffer.width, imageBuffer.height, 4, imageBuffer.width * 4); core.Recognize(); const text = core.GetUTF8Text(); console.log('Recognized Text:', text); core.End(); TesseractCore.destroy(core); // Clean up Emscripten instance }; // Example usage: Assumes 'image.png' exists in the same directory // For a real scenario, replace 'image.png' with your actual image path. // process.env.LANG_PATH should point to directory containing .traineddata files. runOcr('image.png').catch(console.error);