Yiddish letter frequency calculation

result.csv

yiddish-frequency.js

# Source text: Tevye the Milkman, https://www.cs.uky.edu/~raphael/yiddish/tevye.html;

// Take the text, normalize it and remove characters other than Yiddish letters and digraphs:
const yiText = document.body.innerText.normalize('NFD').replace(/[^ײױא-תװ]/g, '')

// Frequency list function (source link: https://stackoverflow.com/a/5668246)
function freqs(arr) {
    var a = [], b = [], prev;
    arr.sort();
    for (var i = 0; i < arr.length; i++) {
        if (arr[i] !== prev) {
            a.push(arr[i]);
            b.push(1);
        } else {
            b[b.length-1]++;
        }
        prev = arr[i];
    }
    return [a, b];
}

// Now, calculate the frequencies:
const [letters, freqs] = freqs(Array.from(yiText));
const freqsList = freqs.map((x, i) => [letters[i], x]).sort((x, y) => y[1] - x[1]);
const csv = freqsList.map(([letter, freq]) => `"${letter}",${freq/yiText.length}`).join('\n')