Iterate two string arrays simultaneously using javascript - javascript

I am new to javascript. Now, I want to make comparison of two website pair by iterating two string array as a pair the same time. These two string array's length are the same. I have searched for sites but didn't find the way to do in javascript. For example, in python, people can do this by using zip(), referencing from
How to merge lists into a list of tuples?.
However, in javascript, I try to something similar to that, but it will iterate over the second list every time it iterate over the element of first list, which is not want I wanted.
codes not what I expected
var FistList=['https://test1-1/travel','https://test1-1/cook','https://test1-1/eat'];
var SecondList=['https://test1-2/travel','https://test1-2/cook','https://test1-2/eat'];
FirstList.forEach(firstListItem => {
SecondList.forEach(secondListItem => {
//do comparison for these two websites....
});
});
What I expect is to do comparison pair by pair, which is =>
first loop: do comparison of 'https://test1-1/travel' and 'https://test1-2/travel'
second loop: do comparison of 'https://test1-1/cook' and 'https://test1-2/cook'
third loop: do comparison of 'https://test1-1/eat' and 'https://test1-2/eat'
I searched for a whole day but cannot find the way to do in javascript. Please advise. Thanks in advance!

If all you want is to compare values in same position of each array just use the index argument of forEach to reference array element in other array
var FirstList=['https://test1-1/travel','https://test1-1/cook','https://test1-1/eat'];
var SecondList=['https://test1-2/travel','https://test1-1/cook','https://test1-1/eat'];
FirstList.forEach((str, i) => console.log(str === SecondList[i]))

I think a very similar question was already answered here: How to compare arrays in JavaScript?
Accepted answer (https://stackoverflow.com/a/14853974/1842205) describes in depth how you could achieve such a goal.
JavaScript lacks of such a feature like mentioned zip() method from Python. But we have something like prototyping in JS :). And you can create 2D array like below:
function createArray(length) {
var arr = new Array(length || 0),
i = length;
if (arguments.length > 1) {
var args = Array.prototype.slice.call(arguments, 1);
while(i--) arr[length-1 - i] = createArray.apply(this, args);
}
return arr;
}
Array.prototype.zip = function (secondArr) {
let result = createArray(secondArr.length, 2);
for (let i = 0; i < this.length; i++) {
result[i][0] = this[i];
result[i][1] = secondArr[i];
}
return result;
};
// usage
var FistList=['https://test1-1/travel','https://test1-1/cook','https://test1-1/eat'];
var SecondList=['https://test1-2/travel','https://test1-2/cook','https://test1-2/eat'];
console.log(JSON.stringify(FistList.zip(SecondList)));

I like the OP's idea of making a more functional solution using zip, which can be home-rolled or reused from loadash or underscore.
const firstArray=['https://test1-1/travel','https://test1-1/cook','https://test1-1/eat'];
const secondArray=['https://test1-2/travel','https://test1-2/cook','https://test1-2/eat'];
const zipped = _.zip(firstArray, secondArray)
const compared = zipped.map(([first, second]) => first === second)
console.log(compared)
// reduce the pairwise comparison to a single bool with every()
// depends on requirements, but probably true iff every comparison is true
const arraysMatch = compared.every(e => e)
console.log(arraysMatch)
<script src="https://cdnjs.cloudflare.com/ajax/libs/lodash.js/4.17.20/lodash.min.js"></script>
Note that more functional solutions often involve the creation of some intermediate arrays (aka garbage) which is fine for small inputs.

I think the purpose of a forEach loop is to iterate over 1 list only. I would consider using a generic for loop to serve this purpose.
EDIT: I edited the code, and added a string prototype function to calculate the Levenstein distance between 2 strings. It's not rigid to detect for an edit in the exact spot your strings are changed in the examples. But I expect the examples are probably not totally reflective of your real data anyway, so instead of giving you some questionable regex, I'm giving you Levenstein and hope you understand it doesn't care where the difference is, it just cares how much has changed. In the example I only allow 1 character or less of difference: if (diff <= 1) {
//Define a string function for Levenstein Edit Distance
//call it "distancefrom" for clarity
String.prototype.distancefrom = function(string) {
var a = this, b = string + "", m = [], i, j, min = Math.min;
if (!(a && b)) return (b || a).length;
for (i = 0; i <= b.length; m[i] = [i++]);
for (j = 0; j <= a.length; m[0][j] = j++);
for (i = 1; i <= b.length; i++) {
for (j = 1; j <= a.length; j++) {
m[i][j] = b.charAt(i - 1) == a.charAt(j - 1)
? m[i - 1][j - 1]
: m[i][j] = min(
m[i - 1][j - 1] + 1,
min(m[i][j - 1] + 1, m[i - 1 ][j] + 1))
}
}
return m[b.length][a.length];
}
//Your Code
var FirstList=['https://test1-1/travel','https://test1-1/cook','https://test1-1/eat', 'https://waffles.domain/syrup', 'http://pancakes.webpresence/butter'];
var SecondList=['https://test1-2/travel','https://test1-2/cook','https://test1-2/eat', 'https://waffles.domain/syrups', 'https://pancakes.webpresence/buttery'];
for (let i=0; i < FirstList.length; i++) {
let diff = FirstList[i].distancefrom(SecondList[i]);
console.log('"'+FirstList[i]+'" is different than "'+SecondList[i]+'" by '+diff+' characters');
if (diff <= 1) {
console.log('Since its less than 1 character of difference, it would technically Pass our test.');
} else {
console.log('Since its more than 1 character of difference, it would Fail our test!');
}
console.log('-----------------');
}
References:
Levenstin Gist by scottgelin on GitHub

Related

Bug in leetcode, javascript 219. Contains Duplicate II

This is the question: https://leetcode.com/problems/contains-duplicate-ii/
Given an integer array nums and an integer k, return true if there are two distinct indices i and j in the array such that nums[i] == nums[j] and abs(i - j) <= k.
My code:
var containsNearbyDuplicate = function(nums, k) {
for(let i = 0; i < nums.length; i++) {
for(let j = i+1; j < nums.length; j++) {
console.log([i, j])
if(nums[i] == nums[j] && Math.abs(i-j) <= k){
return true;
}
}
}
return false;
};
On submission, I can pass 20/51 cases with status being 'Time Limit Exceeded'.
I can pass the following example inputs:
Example 1:
Input: nums = [1,2,3,1], k = 3
Output: true
Example 2:
Input: nums = [1,0,1,1], k = 1
Output: true
Example 3:
Input: nums = [1,2,3,1,2,3], k = 2
Output: false
I can't think of any fringe cases which is causing the submission to exceed time limit. I'm aware that there are other ways to solve this problem, but I would like to know what's wrong with my code.
EDIT:
I realised the problem is with this line: console.log([i, j]). If I comment it out, there is no problem with submission. But I'm not quite sure why that line is causing the time limit exceeded error.
Leetcode and similar sites often provide huge data sets as input. In such cases, an unnecessarily computationally complex algorithm can take too much processing time to complete. That may be what's happening here.
You have a nested loop - if the input array contains 1000 items, that's on the order of 1000 * 1000 iterations. Use a different, less expensive algorithm - such as by iterating over the input only once. One possible approach is
var containsNearbyDuplicate = function(nums, k) {
const numsByLastIndex = {};
for(let i = 0; i < nums.length; i++) {
const num = nums[i];
if (numsByLastIndex[num] !== undefined && i - numsByLastIndex[num] <= k) {
return true;
}
numsByLastIndex[num] = i;
}
return false;
};
When I try the above code, the time required has changed from on the order of 9 seconds (which may be close to the limit) down to 1/4 of a second.
Another issue is that logging in the Node CLI, if you do a ton of logging, can slow things down. Sometimes, logging can even take up most of the processing time of your script. It's not needed to perform the task, so feel free to remove it.

Word Break algorithm

I'm trying to implement the "Word Break" algorithm.
Problem:
Given a non-empty string s and a dictionary wordDict containing a list of non-empty words, determine if s can be segmented into a space-separated sequence of one or more dictionary words.
Note:
The same word in the dictionary may be reused multiple times in the segmentation.
You may assume the dictionary does not contain duplicate words.
Example:
Input: s = "leetcode", wordDict = ["leet", "code"]
Output: true
Explanation: Return true because "leetcode" can be segmented as "leet code".
My solution:
var wordBreak = function(s, wordDict) {
if(!wordDict || wordDict.length === 0)
return false;
while(wordDict.length > 0 || s.length > 0) {
const word = wordDict.shift();
const index = s.indexOf(word);
if(index === -1) {
return false;
}
s = s.substring(0, index) + s.substring(index+word.length, s.length);
}
return s.length === 0 && wordDict.length === 0 ? true : false;
};
It works for the example (input) above. However it fails for the input below.
Input: s = "applepenapple", wordDict = ["apple", "pen"]
Output: true
Explanation: Return true because "applepenapple" can be segmented as "apple pen apple".
Note that you are allowed to reuse a dictionary word.
How can I keep track of words that I already eliminate and check it at the end. This input above, the remaining s string contains "apple" which is in the word dictionary, so the output should be true.
Thanks
A simple Javascript solution.
This loops through the wordDict array and checks if each word exist in the str. If it doesn't that is when the indexOf the word return -1, the function returns false. However, if the words in the wordDict array are in the string, it returns true at the end of the for loop.
const wordBreak =(str, wordDict)=>{
if (!wordDict || wordDict.length === 0) return false
for(let i=0; I<wordDict.length; i++){
const dictIndex = str.indexOf(wordDict[i])
if(dictIndex === -1){
return false
}
}
return true
}
This is an interesting problem I met two years ago in a different context, i.e., query tokenization. In my case, the number of words in the dictionary was in the order of several million, therefore a recursive approach looking each time for a different word of the dictionary was not practicable. Furthermore, I needed to apply dynamic programming to solve the task for strict efficiency reasons.
First of all, I suggest you to use the AhoCorasick algorithm to find the words within your search string. The algorithm looks for an arbitrary number of patterns in a string in linear time in the length of the string regardless of the number of patterns to find (no more number of words times length of the string operation, indeed each find of a word in a string needs to scan the entire string..).
Luckily, I found a javascript implementation of the algorithm here.
Using the code linked above and dynamic programming to track the words appearing in your string, I wrote the following javascript solution:
function wordBreak(s, wordDict) {
const len = s.length;
const memoization_array_words = new Array(len).fill(null);
const memoization_array_scores = new Array(len).fill(0);
const wordScores = {};
wordDict.forEach(function(word) {
wordScores[word] = 1
});
automata = new AhoCorasick(wordDict);
results = automata.search(s);
results.forEach(function(result) {
// result[0] contains the end position
// result[1] contains the list of words ending in that position
const end_pos = result[0];
result[1].forEach(function(word) {
const prev_end_pos = end_pos - word.length;
const prev_score = (prev_end_pos == -1) ? 0 : memoization_array_scores[prev_end_pos];
const score = prev_score + wordScores[word];
if (score > memoization_array_scores[end_pos]) {
memoization_array_words[end_pos] = word;
memoization_array_scores[end_pos] = score;
}
});
});
if (memoization_array_words[len-1] == null) {
return false;
}
solution = []
var pos_to_keep = len - 1;
while (pos_to_keep >= 0) {
const word = memoization_array_words[pos_to_keep];
solution.push(word);
pos_to_keep -= word.length;
}
return solution.reverse()
}
where memoization_array_words and memoization_array_scores are filled left to right when we meet a word occurring after a previous one or at the beginning of the string s. The code should be autoesplicative, but if you need any explanation write me a comment, please.
As a plus, I associated a score to each word (here is 1 for simplicity) that allows you to distinguish between the different solutions. For instance, if you associate to each word an importance score, you will end up with the tokenization with the greatest score. In the code above, the tokenization with the highest number of words.
Extended version: I testing over the wordDict with some if there is one of the worde that beginns at the test-string (indexOf==0). If so I shorten the string about the length of the word and call the function recursivly with the shortened string. Otherwise the string is not splitable and I return false. I go this way on till an error occurs or the length of the string is 0 and I win because everything goes allright.
Remark: The error when the WordBreak is not clearly like with s= "cars" wordDict = ["car","ca","rs"] is now fixed. For this I calling in the some-methode the algorithm recursivly. So if one way stops before ending I go backwards and search for alternatives till I found one or there is no possibility left.
Remarks to; array.some
In an array.forEach there can't used a break without using some ugly tricks (like try...catch and throwing an error), so I could use the classic variant of the for-loop. But there exists the array.some method this loops like a forEach-loop but there had only one of the elements to be return true so the result is true.
Example:
const array = [1, 2, 3, 4, 5];
// checks whether an element is even
const even = (element) => element % 2 === 0;
console.log(array.some(even));
Here is the code of the working algorithm.
var wordBreak = function(s, wordDict) {
if (!wordDict || wordDict.length === 0) return false;
while (s.length > 0) {
let test = wordDict.some( (word,index) => {
if (s.indexOf(word)===0) {
s_new = s.substr(word.length);
return wordBreak(s_new, wordDict);
}
});
if (!test ) return false;
s=s_new;
}
if (s.length === 0) return true;
}
s = "leetcode"; wordDict = ["leet", "code"];
console.log(wordBreak(s, wordDict));
s = "applepenapple"; wordDict = ["apple", "pen"];
console.log(wordBreak(s, wordDict));
s= "cars"; wordDict = ["car","ca","rs"];
console.log(wordBreak(s, wordDict));
function wordBreak(dict, str){
if (!str){
return true;
}
for (const word of dict){
if (str.startsWith(word)){
return wordBreak(dict, str.substring(word.length, str.length))
}
}
return false;
}
You could also probably optimize the loop over dict by pre-sorting the array and using binary search, but hopefully this gets the point across.
If you'd be looking for a Dynamic Programming solution, we'd use an array for recording, and then we'd loop through and keep track of the word.
This'll pass through in JavaScript:
const wordBreak = function(s, wordDict) {
const len = s.length
const dp = new Array(len + 1).fill(false)
dp[0] = true
for (let i = 1; i < len + 1; i++) {
for (let j = 0; j < i; j++) {
if (dp[j] === true && wordDict.includes(s.slice(j, i))) {
dp[i] = true
break
}
}
}
return dp[s.length]
}
In Python, we would have used a list (which is similar to an array of JavaScript) with the same size as our string:
class Solution:
def wordBreak(self, s, words):
dp = [False] * len(s)
for i in range(len(s)):
for word in words:
k = i - len(word)
if word == s[k + 1:i + 1] and (dp[k] or k == -1):
dp[i] = True
return dp[-1]
Similarly in Java, we'd have used a boolean[]:
public final class Solution {
public static final boolean wordBreak(
String s,
List<String> words
) {
if (s == null || s.length() == 0) {
return false;
}
final int len = s.length();
boolean[] dp = new boolean[len];
for (int i = 0; i < len; i++) {
for (int j = 0; j <= i; j++) {
final String sub = s.substring(j, i + 1);
if (words.contains(sub) && (j == 0 || dp[j - 1])) {
dp[i] = true;
break;
}
}
}
return dp[len - 1];
}
}
Here is LeetCode's DP solution:
public class Solution {
public boolean wordBreak(String s, List<String> wordDict) {
Set<String> wordDictSet=new HashSet(wordDict);
boolean[] dp = new boolean[s.length() + 1];
dp[0] = true;
for (int i = 1; i <= s.length(); i++) {
for (int j = 0; j < i; j++) {
if (dp[j] && wordDictSet.contains(s.substring(j, i))) {
dp[i] = true;
break;
}
}
}
return dp[s.length()];
}
}
References
For additional details, please see the Discussion Board which you can find plenty of well-explained accepted solutions in there, with a variety of languages including efficient algorithms and asymptotic time/space complexity analysis1, 2.

Simplest way of finding mode in Javascript [duplicate]

This question already has answers here:
Get the element with the highest occurrence in an array
(42 answers)
Closed 4 years ago.
I am a beginner in JavaScript and I was trying to write code for finding the mode. My code is running but it can find the mode only when it is written consecutively. But when there is an array like this a = [1,2,3,4,5,2], it can not find the mode.
As I am a beginner I do not want to write anything complex but want to learn it in the simplest way. Can anyone please help me in this purpose?
list = [1,2,3,4,5,6,7,7]
var empty = []
i = 0
max = 0
while (i<list.length){
if (list[i]==list[i+1]){
empty = list[i]
i += 1
}else{
i +=1
}
}
document.write(empty)
Your code assumes that the parameter array is pre-sorted which is a risky and limiting assumption, and only appears to work on sorted arrays (counterexample: [1,1,1,7,7] incorrectly reports 7 as the mode).
If you wish you persist with this approach, you're on the right track, but you'll need to keep track of the current/best streaks, current/best elements and perform a final check for longest streak before returning the result:
var mode = a => {
a = a.slice().sort((x, y) => x - y);
var bestStreak = 1;
var bestElem = a[0];
var currentStreak = 1;
var currentElem = a[0];
for (let i = 1; i < a.length; i++) {
if (a[i-1] !== a[i]) {
if (currentStreak > bestStreak) {
bestStreak = currentStreak;
bestElem = currentElem;
}
currentStreak = 0;
currentElem = a[i];
}
currentStreak++;
}
return currentStreak > bestStreak ? currentElem : bestElem;
};
console.log(mode([1,2,3,4,5,6,7,7]));
console.log(mode([1,1,1,4,5,6,7,7]));
console.log(mode([1,2,3,3,3,6,3,7]));
console.log(mode([1,3,3,4,5,2,2,1]));
console.log(mode([]));
Having said that, sorting is a non-linear operation, so I recommend trying another approach.
The idea is to keep a count of occurrences for each item in the array using an object, then take the element with the highest count. I used reduce to perform these two operations:
const mode = a =>
Object.values(
a.reduce((count, e) => {
if (!(e in count)) {
count[e] = [0, e];
}
count[e][0]++;
return count;
}, {})
).reduce((a, v) => v[0] < a[0] ? a : v, [0, null])[1];
;
console.log(mode([1,2,3,4,5,6,7,7]));
console.log(mode([1,1,1,4,5,6,7,7]));
console.log(mode([1,2,3,3,3,6,3,7]));
console.log(mode([1,3,3,4,5,2,2,1]));
console.log(mode([]));
Or, the same thing, written without reduce for readability:
const mode = a => {
const count = {};
a.forEach(e => {
if (!(e in count)) {
count[e] = 0;
}
count[e]++;
});
let bestElement;
let bestCount = 0;
Object.entries(count).forEach(([k, v]) => {
if (v > bestCount) {
bestElement = k;
bestCount = v;
}
});
return bestElement;
};
console.log(mode([1,2,3,4,5,6,7,7]));
console.log(mode([1,1,1,4,5,6,7,7]));
console.log(mode([1,2,3,3,3,6,3,7]));
console.log(mode([1,3,3,4,5,2,2,1]));
console.log(mode([]));
Note that these approaches don't choose the same mode in case of ties. You may wish to add an array to keep track of all modes, or change your algorithm to pick the first or last occurring mode to suit your needs.
use a hash
list = [1,2,3,4,5,6,7,7]
counts = {}
list.forEach(function(e) {
if(counts[e] === undefined) {
counts[e] = 0
}
counts[e] += 1
})
which results in this:
{1:1,2:1,3:1,4:1,5:1,6:1,7:2}
This related question deals with finding the max and min in a hash, which is essentially what you do at the end of this.
Fast way to get the min/max values among properties of object

Using insertion sort method to order numbers from largest to smallest

I'm trying to sort numbers from user input (.prompt) from largest to smallest using the insertion sort method. I'm having difficulty understanding how to apply this method in my html code. Any advice is greatly appreciated!
The only difference according to me might be with interface part as
prompt take input as a string where you can take input as csv then split on commas and get an array of substrings, then parseInt and use in sorting as usual.
Note that this assumes the user is only going to input numbers. You will want to modify this code to account for users entering all kinds of data.
Updated Answer
This is self-explanatory if you're familiar with map and parseFloat. parseFloat just converts a string to a floating point number (1.5, 6.004, etc). map calls a callback function on each element of an array, and returns an array that contains the results. In this code, map is doing parseFloat on each element of the array and returning the result.
Oh, and one more thing that isn't obvious; sort sorts according to string Unicode code points (see here for more info). Therefore, 10 comes before 2 because 1 comes before 2. That's why we need .sort((a,b) => (a-b)), which I got from a comment on this answer.
const numberArray = prompt('Enter several numbers with a space between each').split(' ');
numberArray.map(element => parseFloat(element)).sort((a,b) => (a-b)).reverse();
First answer, but sorts 6 as greater than 10 because 6 comes before 1 in ASCII I think.
const numberArray = prompt('Enter several numbers with a space between each').split(' ');
numberArray.map(element => parseFloat(element));
function insertionSort(array) {
for (let i = 0; i < array.length; i += 1) {
const temp = array[i];
let j = i - 1;
while (j >= 0 && array[j] > temp) {
array[j + 1] = array[j];
j -= 1;
}
array[j + 1] = temp;
}
return array.reverse();
}
insertionSort(numberArray);
I got the insertion sort algorithm from Benoit Vallon's blog
As mentioned in the previous answer.. It is the same as you would do with any other language.
You need however to update your question to reflect exactly what have you tried and ask something more acurate.
Nevertheless, here is a simple sample of how you can achieve this. Take note that I did not do any type validation or or conversion. So it's on you to make sure the user inputs a number
var toSort=[];
$('#sort').on('click',function(){
var result= insertionSort(toSort);
$('p').html(result.toString());
});
$('#prompt').on('click',function(){
toSort.push(prompt("Enter a number",0));
});
/* from http://blog.benoitvallon.com/sorting-algorithms-in-javascript/the-insertion-sort-algorithm/ */
function insertionSort(array) {
for(var i = 0; i < array.length; i++) {
var temp = array[i];
var j = i - 1;
while (j >= 0 && array[j] > temp) {
array[j + 1] = array[j];
j--;
}
array[j + 1] = temp;
}
return array;
}
<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
<button id="prompt">Prompt</button>
<button id="sort">Sort</button>
<h1>End result:</h1>
<p></p>

Count the number of occurrences of a character in a string in Javascript

I need to count the number of occurrences of a character in a string.
For example, suppose my string contains:
var mainStr = "str1,str2,str3,str4";
I want to find the count of comma , character, which is 3. And the count of individual strings after the split along comma, which is 4.
I also need to validate that each of the strings i.e str1 or str2 or str3 or str4 should not exceed, say, 15 characters.
I have updated this answer. I like the idea of using a match better, but it is slower:
console.log(("str1,str2,str3,str4".match(/,/g) || []).length); //logs 3
console.log(("str1,str2,str3,str4".match(new RegExp("str", "g")) || []).length); //logs 4
Use a regular expression literal if you know what you are searching for beforehand, if not you can use the RegExp constructor, and pass in the g flag as an argument.
match returns null with no results thus the || []
The original answer I made in 2009 is below. It creates an array unnecessarily, but using a split is faster (as of September 2014). I'm ambivalent, if I really needed the speed there would be no question that I would use a split, but I would prefer to use match.
Old answer (from 2009):
If you're looking for the commas:
(mainStr.split(",").length - 1) //3
If you're looking for the str
(mainStr.split("str").length - 1) //4
Both in #Lo's answer and in my own silly performance test split comes ahead in speed, at least in Chrome, but again creating the extra array just doesn't seem sane.
There are at least five ways. The best option, which should also be the fastest (owing to the native RegEx engine) is placed at the top.
Method 1
("this is foo bar".match(/o/g)||[]).length;
// returns 2
Method 2
"this is foo bar".split("o").length - 1;
// returns 2
Split not recommended as it is resource hungry. It allocates new instances of 'Array' for each match. Don't try it for a >100MB file via FileReader. You can observe the exact resource usage using Chrome's profiler option.
Method 3
var stringsearch = "o"
,str = "this is foo bar";
for(var count=-1,index=-2; index != -1; count++,index=str.indexOf(stringsearch,index+1) );
// returns 2
Method 4
Searching for a single character
var stringsearch = "o"
,str = "this is foo bar";
for(var i=count=0; i<str.length; count+=+(stringsearch===str[i++]));
// returns 2
Method 5
Element mapping and filtering. This is not recommended due to its overall resource preallocation rather than using Pythonian 'generators':
var str = "this is foo bar"
str.split('').map( function(e,i){ if(e === 'o') return i;} )
.filter(Boolean)
//>[9, 10]
[9, 10].length
// returns 2
Share:
I made this gist, with currently 8 methods of character-counting, so we can directly pool and share our ideas - just for fun, and perhaps some interesting benchmarks :)
Add this function to sting prototype :
String.prototype.count=function(c) {
var result = 0, i = 0;
for(i;i<this.length;i++)if(this[i]==c)result++;
return result;
};
usage:
console.log("strings".count("s")); //2
Simply, use the split to find out the number of occurrences of a character in a string.
mainStr.split(',').length // gives 4 which is the number of strings after splitting using delimiter comma
mainStr.split(',').length - 1 // gives 3 which is the count of comma
A quick Google search got this (from http://www.codecodex.com/wiki/index.php?title=Count_the_number_of_occurrences_of_a_specific_character_in_a_string#JavaScript)
String.prototype.count=function(s1) {
return (this.length - this.replace(new RegExp(s1,"g"), '').length) / s1.length;
}
Use it like this:
test = 'one,two,three,four'
commas = test.count(',') // returns 3
You can also rest your string and work with it like an array of elements using
Array.prototype.filter()
const mainStr = 'str1,str2,str3,str4';
const commas = [...mainStr].filter(l => l === ',').length;
console.log(commas);
Or
Array.prototype.reduce()
const mainStr = 'str1,str2,str3,str4';
const commas = [...mainStr].reduce((a, c) => c === ',' ? ++a : a, 0);
console.log(commas);
UPDATE: This might be simple, but it is not the fastest. See benchmarks below.
It's amazing that in 13 years, this answer hasn't shown up. Intuitively, it seems like it should be fastest:
const s = "The quick brown fox jumps over the lazy dog.";
const oCount = s.length - s.replaceAll('o', '').length;
If there are only two kinds of character in the string, then this is faster still:
const s = "001101001";
const oneCount = s.replaceAll('0', '').length;
BENCHMARKS
const { performance } = require('node:perf_hooks');
const ITERATIONS = 10000000;
const TEST_STRING = "The quick brown fox jumps over the lazy dog.";
console.log(ITERATIONS, "iterations");
let sum = 0; // make sure compiler doesn't optimize code out
let start = performance.now();
for (let i = 0; i < ITERATIONS; ++i) {
sum += TEST_STRING.length - TEST_STRING.replaceAll('o', '').length;
}
let end = performance.now();
console.log(" replaceAll duration", end - start, `(sum ${sum})`);
sum = 0;
start = performance.now();
for (let i = 0; i < ITERATIONS; ++i) {
sum += TEST_STRING.split('o').length - 1
}
end = performance.now();
console.log(" split duration", end - start, `(sum ${sum})`);
10000 iterations
replaceAll duration 2.6167500019073486 (sum 40000)
split duration 2.0777920186519623 (sum 40000)
100000 iterations
replaceAll duration 17.563208997249603 (sum 400000)
split duration 8.087624996900558 (sum 400000)
1000000 iterations
replaceAll duration 128.71587499976158 (sum 4000000)
split duration 64.15841698646545 (sum 4000000)
10000000 iterations
replaceAll duration 1223.3415840268135 (sum 40000000)
split duration 629.1629169881344 (sum 40000000)
Here is a similar solution, but it uses Array.prototype.reduce
function countCharacters(char, string) {
return string.split('').reduce((acc, ch) => ch === char ? acc + 1: acc, 0)
}
As was mentioned, String.prototype.split works much faster than String.prototype.replace.
If you are using lodash, the _.countBy method will do this:
_.countBy("abcda")['a'] //2
This method also work with array:
_.countBy(['ab', 'cd', 'ab'])['ab'] //2
ok, an other one with regexp - probably not fast, but short and better readable then others, in my case just '_' to count
key.replace(/[^_]/g,'').length
just remove everything that does not look like your char
but it does not look nice with a string as input
I have found that the best approach to search for a character in a very large string (that is 1 000 000 characters long, for example) is to use the replace() method.
window.count_replace = function (str, schar) {
return str.length - str.replace(RegExp(schar), '').length;
};
You can see yet another JSPerf suite to test this method along with other methods of finding a character in a string.
Performance of Split vs RegExp
var i = 0;
var split_start = new Date().getTime();
while (i < 30000) {
"1234,453,123,324".split(",").length -1;
i++;
}
var split_end = new Date().getTime();
var split_time = split_end - split_start;
i= 0;
var reg_start = new Date().getTime();
while (i < 30000) {
("1234,453,123,324".match(/,/g) || []).length;
i++;
}
var reg_end = new Date().getTime();
var reg_time = reg_end - reg_start;
alert ('Split Execution time: ' + split_time + "\n" + 'RegExp Execution time: ' + reg_time + "\n");
I made a slight improvement on the accepted answer, it allows to check with case-sensitive/case-insensitive matching, and is a method attached to the string object:
String.prototype.count = function(lit, cis) {
var m = this.toString().match(new RegExp(lit, ((cis) ? "gi" : "g")));
return (m != null) ? m.length : 0;
}
lit is the string to search for ( such as 'ex' ), and cis is case-insensitivity, defaulted to false, it will allow for choice of case insensitive matches.
To search the string 'I love StackOverflow.com' for the lower-case letter 'o', you would use:
var amount_of_os = 'I love StackOverflow.com'.count('o');
amount_of_os would be equal to 2.
If we were to search the same string again using case-insensitive matching, you would use:
var amount_of_os = 'I love StackOverflow.com'.count('o', true);
This time, amount_of_os would be equal to 3, since the capital O from the string gets included in the search.
Easiest way i found out...
Example-
str = 'mississippi';
function find_occurences(str, char_to_count){
return str.split(char_to_count).length - 1;
}
find_occurences(str, 'i') //outputs 4
Here is my solution. Lots of solution already posted before me. But I love to share my view here.
const mainStr = 'str1,str2,str3,str4';
const commaAndStringCounter = (str) => {
const commas = [...str].filter(letter => letter === ',').length;
const numOfStr = str.split(',').length;
return `Commas: ${commas}, String: ${numOfStr}`;
}
// Run the code
console.log(commaAndStringCounter(mainStr)); // Output: Commas: 3, String: 4
Here you find my REPL
I just did a very quick and dirty test on repl.it using Node v7.4. For a single character, the standard for loop is quickest:
Some code:
// winner!
function charCount1(s, c) {
let count = 0;
c = c.charAt(0); // we save some time here
for(let i = 0; i < s.length; ++i) {
if(c === s.charAt(i)) {
++count;
}
}
return count;
}
function charCount2(s, c) {
return (s.match(new RegExp(c[0], 'g')) || []).length;
}
function charCount3(s, c) {
let count = 0;
for(ch of s) {
if(c === ch) {
++count;
}
}
return count;
}
function perfIt() {
const s = 'Hello, World!';
const c = 'o';
console.time('charCount1');
for(let i = 0; i < 10000; i++) {
charCount1(s, c);
}
console.timeEnd('charCount1');
console.time('charCount2');
for(let i = 0; i < 10000; i++) {
charCount2(s, c);
}
console.timeEnd('charCount2');
console.time('charCount3');
for(let i = 0; i < 10000; i++) {
charCount2(s, c);
}
console.timeEnd('charCount3');
}
Results from a few runs:
perfIt()
charCount1: 3.301ms
charCount2: 11.652ms
charCount3: 174.043ms
undefined
perfIt()
charCount1: 2.110ms
charCount2: 11.931ms
charCount3: 177.743ms
undefined
perfIt()
charCount1: 2.074ms
charCount2: 11.738ms
charCount3: 152.611ms
undefined
perfIt()
charCount1: 2.076ms
charCount2: 11.685ms
charCount3: 154.757ms
undefined
Update 2021-Feb-10: Fixed typo in repl.it demo
Update 2020-Oct-24: Still the case with Node.js 12 (play with it yourself here)
UPDATE 06/10/2022
So I ran various perf tests and if your use case allows it, it seems that using split is going to perform the best overall.
function countChar(char: string, string: string): number {
return string.split(char).length - 1
}
countChar('x', 'foo x bar x baz x')
I know I am late to the party here but I was rather baffled no one answered this with the most basic of approaches. A large portion of the answers provided by the community for this question are iteration based but all are moving over strings on a per-character basis which is not really efficient.
When dealing with a large string that contains thousands of characters walking over each character to get the occurance count can become rather extraneous not to mention a code-smell. The below solutions take advantage of slice, indexOf and the trusted traditional while loop. These approaches prevent us having to walk over each character and will greatly speed up the time it takes to count occurances. These follow similar logic to that you'd find in parsers and lexical analyzers that require string walks.
Using with Slice
In this approach we are leveraging slice and with every indexOf match we will move our way through the string and eliminate the previous searched potions. Each time we call indexOf the size of the string it searches will be smaller.
function countChar (char: string, search: string): number {
let num: number = 0;
let str: string = search;
let pos: number = str.indexOf(char);
while(pos > -1) {
str = str.slice(pos + 1);
pos = str.indexOf(char);
num++;
}
return num;
}
// Call the function
countChar('x', 'foo x bar x baz x') // 3
Using with IndexOf from position
Similar to the first approach using slice but instead of augmenting the string we are searching it will leverage the from parameter in indexOf method.
function countChar (char: string, str: string): number {
let num: number = 0;
let pos: number = str.indexOf(char);
while(pos > -1) {
pos = str.indexOf(char, pos + 1);
num++;
}
return num;
}
// Call the function
countChar('x', 'foo x bar x baz x') // 3
Personally, I go for the second approach over the first, but both are fine and performant when dealing with large strings but also smaller sized ones too.
s = 'dir/dir/dir/dir/'
for(i=l=0;i<s.length;i++)
if(s[i] == '/')
l++
I was working on a small project that required a sub-string counter. Searching for the wrong phrases provided me with no results, however after writing my own implementation I have stumbled upon this question. Anyway, here is my way, it is probably slower than most here but might be helpful to someone:
function count_letters() {
var counter = 0;
for (var i = 0; i < input.length; i++) {
var index_of_sub = input.indexOf(input_letter, i);
if (index_of_sub > -1) {
counter++;
i = index_of_sub;
}
}
http://jsfiddle.net/5ZzHt/1/
Please let me know if you find this implementation to fail or do not follow some standards! :)
UPDATE
You may want to substitute:
for (var i = 0; i < input.length; i++) {
With:
for (var i = 0, input_length = input.length; i < input_length; i++) {
Interesting read discussing the above:
http://www.erichynds.com/blog/javascript-length-property-is-a-stored-value
What about string.split(desiredCharecter).length-1
Example:
var str = "hellow how is life";
var len = str.split("h").length-1; will give count 2 for character "h" in the above string;
The fastest method seems to be via the index operator:
function charOccurances (str, char)
{
for (var c = 0, i = 0, len = str.length; i < len; ++i)
{
if (str[i] == char)
{
++c;
}
}
return c;
}
console.log( charOccurances('example/path/script.js', '/') ); // 2
Or as a prototype function:
String.prototype.charOccurances = function (char)
{
for (var c = 0, i = 0, len = this.length; i < len; ++i)
{
if (this[i] == char)
{
++c;
}
}
return c;
}
console.log( 'example/path/script.js'.charOccurances('/') ); // 2
function len(text,char){
return text.innerText.split(string).length
}
console.log(len("str1,str2,str3,str4",","))
This is a very short function.
The following uses a regular expression to test the length. testex ensures you don't have 16 or greater consecutive non-comma characters. If it passes the test, then it proceeds to split the string. counting the commas is as simple as counting the tokens minus one.
var mainStr = "str1,str2,str3,str4";
var testregex = /([^,]{16,})/g;
if (testregex.test(mainStr)) {
alert("values must be separated by commas and each may not exceed 15 characters");
} else {
var strs = mainStr.split(',');
alert("mainStr contains " + strs.length + " substrings separated by commas.");
alert("mainStr contains " + (strs.length-1) + " commas.");
}
I'm using Node.js v.6.0.0 and the fastest is the one with index (the 3rd method in Lo Sauer's answer).
The second is:
function count(s, c) {
var n = 0;
for (let x of s) {
if (x == c)
n++;
}
return n;
}
And there is:
function character_count(string, char, ptr = 0, count = 0) {
while (ptr = string.indexOf(char, ptr) + 1) {count ++}
return count
}
Works with integers too!
Here's one just as fast as the split() and the replace methods, which are a tiny bit faster than the regex method (in Chrome and Firefox both).
let num = 0;
let str = "str1,str2,str3,str4";
//Note: Pre-calculating `.length` is an optimization;
//otherwise, it recalculates it every loop iteration.
let len = str.length;
//Note: Don't use a `for (... of ...)` loop, it's slow!
for (let charIndex = 0; charIndex < len; ++charIndex) {
if (str[charIndex] === ',') {
++num;
}
}
var mainStr = "str1,str2,str3,str4";
var splitStr = mainStr.split(",").length - 1; // subtracting 1 is important!
alert(splitStr);
Splitting into an array gives us a number of elements, which will always be 1 more than the number of instances of the character. This may not be the most memory efficient, but if your input is always going to be small, this is a straight-forward and easy to understand way to do it.
If you need to parse very large strings (greater than a few hundred characters), or if this is in a core loop that processes large volumes of data, I would recommend a different strategy.
String.prototype.reduce = Array.prototype.reduce;
String.prototype.count = function(c) {
return this.reduce(((n, x) => n + (x === c ? 1 : 0)), 0)
};
const n = "bugs bunny was here".count("b")
console.log(n)
Similar to the prototype based above, but does not allocate an array for the string. Allocation is the problem of nearly every version above, except the loop variants. This avoids loop code, reusing the browser implemented Array.reduce function.
My solution:
function countOcurrences(str, value){
var regExp = new RegExp(value, "gi");
return str.match(regExp) ? str.match(regExp).length : 0;
}
I know this might be an old question but I have a simple solution for low-level beginners in JavaScript.
As a beginner, I could only understand some of the solutions to this question so I used two nested FOR loops to check each character against every other character in the string, incrementing a count variable for each character found that equals that character.
I created a new blank object where each property key is a character and the value is how many times each character appeared in the string(count).
Example function:-
function countAllCharacters(str) {
var obj = {};
if(str.length!==0){
for(i=0;i<str.length;i++){
var count = 0;
for(j=0;j<str.length;j++){
if(str[i] === str[j]){
count++;
}
}
if(!obj.hasOwnProperty(str[i])){
obj[str[i]] = count;
}
}
}
return obj;
}

Categories