Node.js: Compare directory contents with file checksums asynchronously

Comparing the content of two directories binary-safe is a common used feature especially for data synchronization tasks. You can easily implement a simple compare algorithm by generating the sha256 checksums of each file – this is not a high-performance solution but even works on large files!

const _fs = require('fs-magic');

// compare directoy contents based on sha256 hash tables
async function compareDirectories(dir1, dir2){
    // fetch file lists
    const [files1, dirs1] = await _fs.scandir(dir1, true, true);
    const [files2, dirs2] = await _fs.scandir(dir2, true, true);

    // num files, directories equal ?
    if (files1.length != files2.length){
        throw new Error('The directories containing a different number of files ' + files1.length + '/' + files2.length);
    }
    if (dirs1.length != dirs2.length){
        throw new Error('The directories containing a different number of subdirectories ' + dirs1.length + '/' + dirs2.length);
    }

    // generate file checksums
    const hashes1 = await Promise.all(files1.map(f => _fs.sha256file(f)));
    const hashes2 = await Promise.all(files2.map(f => _fs.sha256file(f)));

    // convert arrays to objects filename=>hash
    const lookup = {};
    for (let i=0;i<hashes2.length;i++){
        // normalized filenames
        const f2 = files2[i].substr(dir2.length);
        
        // assign
        lookup[f2] = hashes2[i];
    }

    // compare dir1 to dir2
    for (let i=0;i<hashes1.length;i++){
        // normalized filenames
        const f1 = files1[i].substr(dir1.length);

        // exists ?
        if (!lookup[f1]){
            throw new Error('File <' + files1[i] + '> does not exist in <' + dir2 + '>');
        }

        // hash valid ?
        if (lookup[f1] !== hashes1[i]){
            throw new Error('File Checksum of <' + files1[i] + '> does not match <' + files2[i] + '>');
        }
    }

    return true;
}

await compareDirectories('/tmp/data0', '/tmp/data1');