pdf-decomposer/dist/checkFile.js

📚 Extract text and images (as buffers) from PDF files using native parsing and OCR with Tesseract.

"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.isFileValid = isFileValid;
/**
 * Check if file is valid throw error if not
 * @param buffer File buffer
 */
function isFileValid(buffer) {
    if (!isMimeValid(buffer)) {
        throw new Error('File is not a pdf');
    }
}
/**
 * Check if file is a pdf
 * @param buffer File buffer
 * @returns boolean true if pdf
 */
function isMimeValid(buffer) {
    if (!buffer || buffer.length < 4)
        return false;
    // PDF: always start with "%PDF"
    return buffer.subarray(0, 4).toString() === '%PDF';
}