hashtags_extract_regex.js

// Problem: Given a instagram post, we need to identify "all" the hashtags in the post
// Assumption: Hashtags will only have alphanumeric characters
// alphanumeric: [a-zA-Z0-9]

function extractHashTag(post) {
    let pattern = /#[a-zA-Z0-9]+/g
    // [a-zA-Z0-9] means any character from a to z, A to Z, 0 to 9
    // + means one or more
    const matchResult = post.match(pattern); // ["#beachday", "#day1"]
    return matchResult;
}

let string = "Enjoying my day at the beach! #beachday #day1";
extractHashTag(string); // Output: ["beachday", "day1"]

// Problem: Identify all the spaces in the instagram post and replace them with underscores
let string = "Enjoying my day at the beach! #beachday #day1 #metime";
let pattern = /\s/g;
// \s means any whitespace character (space, tab, newline, and similar)
const newString = string.replace(pattern, "_");
console.log(newString)

let string = "apple";
let pattern = /ap{2}le/g
// p{2} means match the character p exactly 2 times.
console.log(string.match(pattern)); // Output: ["pp"]

let pattern2 = /ap{2,4}le/g
// p{2,4} means match the character p at least 2 times and at most 4 times.
console.log(string.match(pattern2))

let pattern3 = /ap*le/g
// p* means match the character p "0 or more times".
console.log(string.match(pattern3))

let pattern4 = /ap+le/g
// p+ means match the character p "1 or more times".
console.log(string.match(pattern4))

let pattern5 = /ap?le/g
// p? means match the character p "0 or 1 times".
console.log(string.match(pattern5))

/*?= is a part of regular expression syntax in JavaScript. It is used to create a positive lookahead.
A lookahead is a type of zero-width assertion that allows you to match a pattern only if it is followed by another pattern, without including the second pattern in the match.
Here's an example:*/

let string = "apple banana mango";
let regex = /apple(?=\sbanana)/;
console.log(string.match(regex)); // Output: [ 'apple', index: 0, input: 'apple banana mango', groups: undefined ]

/*
In this case, the regex /apple(?=\sbanana)/ matches "apple" only if it is followed by " banana". The space before "banana" in (?=\sbanana) is necessary to match the space in the original string.
It's important to note that the lookahead pattern \sbanana (meaning "a space followed by 'banana'") is not included in the match result. The match only includes "apple". This is what's meant by "zero-width": the lookahead doesn't consume characters in the string, but only asserts whether a match is possible.
*/