I would like to randomize the email addresses that are being output and remove duplicates and have them retain the original order. This works perfectly fine when I do not randomize. I generate the emails, remove dups, and output and have no issues. I also have no issues randomizing. The issue I seem to have is combining the two. Being able to generate the array, randomize, remove dups AND retain the original order. Below is what I have tried already, this is the closest I have gotten. Thanks for any help.
function randomize(arr) {
var i, j, tmp;
for (i = arr.length - 1; i > 0; i--) {
j = Math.floor(Math.random() * (i + 1));
tmp = arr[i];
arr[i] = arr[j];
arr[j] = tmp;
}
return arr;
}
const sourceArray = [];
var arr = sourceArray;
// we start with an empty source array
// const sourceArray = [];
// the number of emails / 2
const numberOfEmails = 100000;
// first pass we add 100,000 emails
for (let index = 0; index < numberOfEmails; index++) {
sourceArray.push(`test${index}@google.com`);
}
// second pass we create dupes for all of them
for (let index = 0; index < numberOfEmails; index++) {
sourceArray.push(`test${index}@google.com`);
}
// throw in some extra dupes for fun
sourceArray.push(`test0@google.com`);
sourceArray.push(`test0@google.com`);
sourceArray.push(`test0@google.com`);
sourceArray.push(`test0@google.com`);
sourceArray.push(`test0@google.com`);
sourceArray.push(`test0@google.com`);
sourceArray.push(`test0@google.com`);
// this serves as a map of all email addresses that we want to keep
const map = {};
// an exact time before we run the algorithm
const before = Date.now();
// checks if the email is in the hash map
const isInHashmap = (email: string) => {
return map[email];
};
// iterate through all emails, check if they are in the hashmap already, if they are we ignore them, if not we add them.
sourceArray.forEach((email) => {
if (!isInHashmap(email)) {
map[email] = true;
}
});
// we fetch all keys from the hashmap
const result = Object.keys(map);
arr = randomize(arr);
console.log(`Randomized here: ${sourceArray}`);
console.log(`The count after deduplicating: ${result.length}`);
// gets the time expired between starting and completing deduping
const time = Date.now() - before;
console.log(`The time taken: ${time}ms`);
console.log(result);