Algorithm for counting occurrences of words in string - javascript

I am trying to build an algorithm to see, which words occurr the most in comments.
Therefore I came up with this (in Javascript):
var analyze = function(comments){
var detectedWords = [];
var result = {};
comments.forEach(function(comment){
var words = comment.message.split(" ");
words.forEach(function(word){
word = word.toLowerCase();
if(word !== ""){
if(detectedWords.indexOf(word) === -1){
detectedWords.push(word);
result[detectedWords.indexOf(word)] = {"name":word,"count":1};
}else{
result[detectedWords.indexOf(word)].count++;
}
}
});
});
return _.orderBy(result, ['count'], ['desc']);
}
Can the algorithm be optimized further? (toLowerCase() outside the inner loop?
In next step I would define a "blacklist" or words that are not interesting like "the, is, I, am, are,..."

You could use a hash table for reference to the array item for a faster access to the count object. result is now an array, which is now sortable.
var analyze = function (comments) {
var result = [],
hash = {};
comments.forEach(function (comment) {
var words = comment.message.split(" ");
words.forEach(function (word) {
word = word.toLowerCase();
if (word !== "") {
if (!hash[word]) {
hash[word] = { name: word, count: 0 };
result.push(hash[word]);
}
hash[word].count++;
}
});
});
return result.sort(function (a, b) { return b.count - a.count;});
//return _.orderBy(result, ['count'], ['desc']);
}
console.log(analyze([{ message: 'a b c d a v d e f g q' }]));

Related

Alibaba interview: print a sentence with min spaces

I saw this interview question and gave a go. I got stuck. The interview question is:
Given a string
var s = "ilikealibaba";
and a dictionary
var d = ["i", "like", "ali", "liba", "baba", "alibaba"];
try to give the s with min space
The output may be
i like alibaba (2 spaces)
i like ali baba (3 spaces)
but pick no.1
I have some code, but got stuck in the printing.
If you have better way to do this question, let me know.
function isStartSub(part, s) {
var condi = s.startsWith(part);
return condi;
}
function getRestStr(part, s) {
var len = part.length;
var len1 = s.length;
var out = s.substring(len, len1);
return out;
}
function recPrint(arr) {
if(arr.length == 0) {
return '';
} else {
var str = arr.pop();
return str + recPrint(arr);
}
}
// NOTE: have trouble to print
// Or if you have better ways to do this interview question, please let me know
function myPrint(arr) {
return recPrint(arr);
}
function getMinArr(arr) {
var min = Number.MAX_SAFE_INTEGER;
var index = 0;
for(var i=0; i<arr.length; i++) {
var sub = arr[i];
if(sub.length < min) {
min = sub.length;
index = i;
} else {
}
}
return arr[index];
}
function rec(s, d, buf) {
// Base
if(s.length == 0) {
return;
} else {
}
for(var i=0; i<d.length; i++) {
var subBuf = [];
// baba
var part = d[i];
var condi = isStartSub(part, s);
if(condi) {
// rest string
var restStr = getRestStr(part, s);
rec(restStr, d, subBuf);
subBuf.unshift(part);
buf.unshift(subBuf);
} else {
}
} // end loop
}
function myfunc(s, d) {
var buf = [];
rec(s, d, buf);
console.log('-- test --');
console.dir(buf, {depth:null});
return myPrint(buf);
}
// Output will be
// 1. i like alibaba (with 2 spaces)
// 2. i like ali baba (with 3 spaces)
// we pick no.1, as it needs less spaces
var s = "ilikealibaba";
var d = ["i", "like", "ali", "liba", "baba", "alibaba"];
var out = myfunc(s, d);
console.log(out);
Basically, my output is, not sure how to print it....
[ [ 'i', [ 'like', [ 'alibaba' ], [ 'ali', [ 'baba' ] ] ] ] ]
This problem is best suited for a dynamic programming approach. The subproblem is, "what is the best way to create a prefix of s". Then, for a given prefix of s, we consider all words that match the end of the prefix, and choose the best one using the results from the earlier prefixes.
Here is an implementation:
var s = "ilikealibaba";
var arr = ["i", "like", "ali", "liba", "baba", "alibaba"];
var dp = []; // dp[i] is the optimal solution for s.substring(0, i)
dp.push("");
for (var i = 1; i <= s.length; i++) {
var best = null; // the best way so far for s.substring(0, i)
for (var j = 0; j < arr.length; j++) {
var word = arr[j];
// consider all words that appear at the end of the prefix
if (!s.substring(0, i).endsWith(word))
continue;
if (word.length == i) {
best = word; // using single word is optimal
break;
}
var prev = dp[i - word.length];
if (prev === null)
continue; // s.substring(i - word.length) can't be made at all
if (best === null || prev.length + word.length + 1 < best.length)
best = prev + " " + word;
}
dp.push(best);
}
console.log(dp[s.length]);
pkpnd's answer is along the right track. But word dictionaries tend to be quite large sets, and iterating over the entire dictionary at every character of the string is going to be inefficient. (Also, saving the entire sequence for each dp cell may consume a large amount of space.) Rather, we can frame the question, as we iterate over the string, as: given all the previous indexes of the string that had dictionary matches extending back (either to the start or to another match), which one is both a dictionary match when we include the current character, and has a smaller length in total. Generally:
f(i) = min(
f(j) + length(i - j) + (1 if j is after the start of the string)
)
for all j < i, where string[j] ended a dictionary match
and string[j+1..i] is in the dictionary
Since we only add another j when there is a match and a new match can only extend back to a previous match or to the start of the string, our data structure could be an array of tuples, (best index this match extends back to, total length up to here). We add another tuple if the current character can extend a dictionary match back to another record we already have. We can also optimize by exiting early from the backwards search once the matched substring would be greater than the longest word in the dictionary, and building the substring to compare against the dictionary as we iterate backwards.
JavaScript code:
function f(str, dict){
let m = [[-1, -1, -1]];
for (let i=0; i<str.length; i++){
let best = [null, null, Infinity];
let substr = '';
let _i = i;
for (let j=m.length-1; j>=0; j--){
let [idx, _j, _total] = m[j];
substr = str.substr(idx + 1, _i - idx) + substr;
_i = idx;
if (dict.has(substr)){
let total = _total + 1 + i - idx;
if (total < best[2])
best = [i, j, total];
}
}
if (best[0] !== null)
m.push(best);
}
return m;
}
var s = "ilikealibaba";
var d = new Set(["i", "like", "ali", "liba", "baba", "alibaba"]);
console.log(JSON.stringify(f(s,d)));
We can track back our result:
[[-1,-1,-1],[0,0,1],[4,1,6],[7,2,10],[11,2,14]]
[11, 2, 14] means a total length of 14,
where the previous index in m is 2 and the right index
of the substr is 11
=> follow it back to m[2] = [4, 1, 6]
this substr ended at index 4 (which means the
first was "alibaba"), and followed m[1]
=> [0, 0, 1], means this substr ended at index 1
so the previous one was "like"
And there you have it: "i like alibaba"
As you're asked to find a shortest answer probably Breadth-First Search would be a possible solution. Or you could look into A* Search.
Here is working example with A* (cause it's less bring to do than BFS :)), basically just copied from Wikipedia article. All the "turning string into a graph" magick happens in the getNeighbors function
https://jsfiddle.net/yLeps4v5/4/
var str = 'ilikealibaba'
var dictionary = ['i', 'like', 'ali', 'baba', 'alibaba']
var START = -1
var FINISH = str.length - 1
// Returns all the positions in the string that we can "jump" to from position i
function getNeighbors(i) {
const matchingWords = dictionary.filter(word => str.slice(i + 1, i + 1 + word.length) == word)
return matchingWords.map(word => i + word.length)
}
function aStar(start, goal) {
// The set of nodes already evaluated
const closedSet = {};
// The set of currently discovered nodes that are not evaluated yet.
// Initially, only the start node is known.
const openSet = [start];
// For each node, which node it can most efficiently be reached from.
// If a node can be reached from many nodes, cameFrom will eventually contain the
// most efficient previous step.
var cameFrom = {};
// For each node, the cost of getting from the start node to that node.
const gScore = dictionary.reduce((acc, word) => { acc[word] = Infinity; return acc }, {})
// The cost of going from start to start is zero.
gScore[start] = 0
while (openSet.length > 0) {
var current = openSet.shift()
if (current == goal) {
return reconstruct_path(cameFrom, current)
}
closedSet[current] = true;
getNeighbors(current).forEach(neighbor => {
if (closedSet[neighbor]) {
return // Ignore the neighbor which is already evaluated.
}
if (openSet.indexOf(neighbor) == -1) { // Discover a new node
openSet.push(neighbor)
}
// The distance from start to a neighbor
var tentative_gScore = gScore[current] + 1
if (tentative_gScore >= gScore[neighbor]) {
return // This is not a better path.
}
// This path is the best until now. Record it!
cameFrom[neighbor] = current
gScore[neighbor] = tentative_gScore
})
}
throw new Error('path not found')
}
function reconstruct_path(cameFrom, current) {
var answer = [];
while (cameFrom[current] || cameFrom[current] == 0) {
answer.push(str.slice(cameFrom[current] + 1, current + 1))
current = cameFrom[current];
}
return answer.reverse()
}
console.log(aStar(START, FINISH));
You could collect all possible combinations of the string by checking the starting string and render then the result.
If more than one result has the minimum length, all results are taken.
It might not work for extrema with string who just contains the same base string, like 'abcabc' and 'abc'. In this case I suggest to use the shortest string and update any part result by iterating for finding longer strings and replace if possible.
function getWords(string, array = []) {
words
.filter(w => string.startsWith(w))
.forEach(s => {
var rest = string.slice(s.length),
temp = array.concat(s);
if (rest) {
getWords(rest, temp);
} else {
result.push(temp);
}
});
}
var string = "ilikealibaba",
words = ["i", "like", "ali", "liba", "baba", "alibaba"],
result = [];
getWords(string);
console.log('all possible combinations:', result);
console.log('result:', result.reduce((r, a) => {
if (!r || r[0].length > a.length) {
return [a];
}
if (r[0].length === a.length) {
r.push(a);
}
return r;
}, undefined))
Use trie data structure
Construct a trie data structure based on the dictionary data
Search the sentence for all possible slices and build a solution tree
Deep traverse the solution tree and sort the final combinations
const sentence = 'ilikealibaba';
const words = ['i', 'like', 'ali', 'liba', 'baba', 'alibaba',];
class TrieNode {
constructor() { }
set(a) {
this[a] = this[a] || new TrieNode();
return this[a];
}
search(word, marks, depth = 1) {
word = Array.isArray(word) ? word : word.split('');
const a = word.shift();
if (this[a]) {
if (this[a]._) {
marks.push(depth);
}
this[a].search(word, marks, depth + 1);
} else {
return 0;
}
}
}
TrieNode.createTree = words => {
const root = new TrieNode();
words.forEach(word => {
let currentNode = root;
for (let i = 0; i < word.length; i++) {
currentNode = currentNode.set(word[i]);
}
currentNode.set('_');
});
return root;
};
const t = TrieNode.createTree(words);
function searchSentence(sentence) {
const marks = [];
t.search(sentence, marks);
const ret = {};
marks.map(mark => {
ret[mark] = searchSentence(sentence.slice(mark));
});
return ret;
}
const solutionTree = searchSentence(sentence);
function deepTraverse(tree, sentence, targetLen = sentence.length) {
const stack = [];
const sum = () => stack.reduce((acc, mark) => acc + mark, 0);
const ret = [];
(function traverse(tree) {
const keys = Object.keys(tree);
keys.forEach(key => {
stack.push(+key);
if (sum() === targetLen) {
const result = [];
let tempStr = sentence;
stack.forEach(mark => {
result.push(tempStr.slice(0, mark));
tempStr = tempStr.slice(mark);
});
ret.push(result);
}
if(tree[key]) {
traverse(tree[key]);
}
stack.pop();
});
})(tree);
return ret;
}
const solutions = deepTraverse(solutionTree, sentence);
solutions.sort((s1, s2) => s1.length - s2.length).forEach((s, i) => {
console.log(`${i + 1}. ${s.join(' ')} (${s.length - 1} spaces)`);
});
console.log('pick no.1');

Find the replaced part in a string using Javascript

function str_replace(str , part_to_replace , replace_with) {
var res = str.replace(part_to_replace , replace_with);
return res;
}
console.log(str_replace("amir" , "ir" , "er")) //returns "amer"
I want the function to return "e" which is the only part that changed aka replaced part so how i am supposed to do that ?
thanks in advance.
You could iterate all characters and take only the changed ones.
function check(a, b) {
if (a.length !== b.length) { return; }
return b
.split('') // take an array
.filter(function (c, i) { // filter
return a[i] !== c; // check characters
})
.join(''); // return string
}
function str_replace(str, part_to_replace, replace_with) {
return str.replace(part_to_replace, replace_with);
}
console.log(str_replace("amir", "ir", "er"));
console.log(check("amir", str_replace("amir", "ir", "er")));
It looks like you want an array of characters in the new string that were not present in the old one. This will do the trick:
function getDifference(oldStr, newStr) {
// .split('') turns your string into an array of characters
var oldSplit = oldStr.split('');
var newSplit = newStr.split('');
// then compare the arrays and get the difference
var diff = [];
for (var i = 0; i < newSplit.length; i++) {
if (newSplit[i] !== oldSplit[i]) {
diff.push(newSplit[i]);
}
}
return diff;
}
var diff = getDifference('amir', str_replace('amir', 'ir', 'er'));
console.log(diff); // e

splitting a string into a multidimensional array

I have a list of strings, I want to check if the string contains a specific word, and if it does split all the words in the string and add it to an associative array.
myString = ['RT #Arsenal: Waiting for the international', 'We’re hungry for revenge #_nachomonreal on Saturday\'s match and aiming for a strong finish']
wordtoFind = ['#Arsenal']
I want to loop through the wordtoFind and if it is in myString, split up myString into individual words and create an object like
newWord = {#Arsenal:[{RT:1},{Waiting:1},{for:1},{the:1},{international:1}]}
for(z=0; z <wordtoFind.length; z++){
for ( i = 0 ; i < myString.length; i++) {
if (myString[i].indexOf(wordtoFind[z].key) > -1){
myString[i].split(" ")
}
}
}
I would say something likes would work, this also counts the amount of occurrences of a word in a sentence. JavaScript does not have associative arrays like PHP for instance. They just have objects or numbered arrays:
var myString = ['RT #Arsenal: Waiting for the international', 'We’re hungry for revenge #_nachomonreal on Saturday\'s match and aiming for a strong finish'];
var wordtoFind = ['#Arsenal'];
var result = {};
for(var i = 0, l = wordtoFind.length; i < l; i++) {
for(var ii = 0, ll = myString.length; ii < ll; ii++) {
if(myString[ii].indexOf(wordtoFind[i]) !== -1) {
var split = myString[ii].split(' ');
var resultpart = {};
for(var iii = 0, lll = split.length; iii < lll; iii++) {
if(split[iii] !== wordtoFind[i]) {
if(!resultpart.hasOwnProperty(split[iii])) {
resultpart[split[iii]] = 0;
}
resultpart[split[iii]]++;
}
}
result[wordtoFind[i]] = resultpart;
}
}
}
console.log(result);
//{"#Arsenal":{"RT":1,"Waiting":1,"for":1,"the":1,"international":1}}
This method makes use of the forEach-function and callbacks.
The containsWord-function was left with a for-loop for now to reduce some callbacks, this can obviously be changed.
var myString = [
'RT #Arsenal: Waiting for the international',
'We’re hungry for revenge #_nachomonreal on Saturday\'s match and aiming for a strong finish',
'#Arsenal: one two three four two four three four three four'
];
var wordtoFind = ['#Arsenal'];
// define the preprocessor that is used before the equality check
function preprocessor(word) {
return word.replace(':', '');
}
function findOccurences(array, search, callback, preprocessor) {
var result = {};
var count = 0;
// calculate the maximum iterations
var max = search.length * array.length;
// iterate the search strings that should be matched
search.forEach(function(needle) {
// iterate the array of strings that should be searched in
array.forEach(function(haystack) {
if (containsWord(haystack, needle, preprocessor)) {
var words = haystack.split(' ');
// iterate every word to count the occurences and write them to the result
words.forEach(function(word) {
countOccurence(result, needle, word);
})
}
count++;
// once every iteration finished, call the callback
if (count == max) {
callback && callback(result);
}
});
});
}
function containsWord(haystack, needle, preprocessor) {
var words = haystack.split(' ');
for (var i = 0; i < words.length; i++) {
var word = words[i];
// preprocess a word before it's compared
if (preprocessor) {
word = preprocessor(word);
}
// if it matches return true
if (word === needle) {
return true;
}
}
return false;
}
function countOccurence(result, key, word) {
// add array to object if it doesn't exist yet
if (!result.hasOwnProperty(key)) {
result[key] = [];
}
var entry = result[key];
// set the count to 0 if it doesn't exist yet
if (!entry.hasOwnProperty(word)) {
entry[word] = 0;
}
entry[word]++;
}
// call our function to find the occurences
findOccurences(myString, wordtoFind, function(result) {
// do something with the result
console.log(result);
}, preprocessor);
// output:
/*
{ '#Arsenal':
[ RT: 1,
'#Arsenal:': 2,
Waiting: 1,
for: 1,
the: 1,
international: 1,
one: 1,
two: 2,
three: 3,
four: 4 ] }
*/
Feel free to ask any questions, if the answer needs clarification.
I hope this fits your needs.
You're on the right track. You just need to store the split string into the associative array variable.
var assocArr = [];
for(z=0; z <wordtoFind.length; z++){
for ( i = 0 ; i < myString.length; i++) {
if (myString[i].indexOf(wordtoFind[z]) > -1){
myString[i].split(" ").forEach(function(word){
assocArr.push(word);
});
}
}
}
I think the key problem that stuck you is the data structure. The optimal structure should be something like this:
{
#Arsenal:[
{RT:1, Waiting:1, for:1, the:1, international:1},
{xxx:1, yyy:1, zzz:3}, //for there are multiple ones in 'myString' that contain the same '#Arsenal'
{slkj:1, sldjfl:2, lsdkjf:1} //maybe more
]
someOtherWord:[
{},
{},
....
]
}
And the code:
var result = {};
//This function will return an object like {RT:1, Waiting:1, for:1, the:1, international:1}.
function calculateCount(string, key) {
var wordCounts = {};
string.split(" ").forEach(function (word) {
if (word !== key) {
if (wordCounts[word] === undefined) wordCounts[word] = 1;
else wordCounts[word]++;
}
});
return wordCounts;
}
//For each 'word to find' and each string that contain the 'word to find', push in that returned object {RT:1, Waiting:1, for:1, the:1, international:1}.
wordToFind.forEach(function (word) {
var current = result[word] = [];
myString.forEach(function (str) {
if (str.indexOf(word) > -1) {
current.push(
calculateCount(str, word)
);
}
}); //Missed the right parenthesis here
});

How do I make Array.indexOf() case insensitive?

I am making a piece of code for a website that will have a list of names in an array and pick a random name, I want to add a feature that will let the user add or delete a name from the array. I have all of these features but when deleting a name, the user has to type the name to match the Case in the array. I tried to make the so it would be Case-Insensitive, what am I doing wrong?
<html>
<!--Other code uneeded for this question-->
<p id="canidates"></p>
<body>
<input type="text" id="delname" /><button onclick="delName()">Remove Name from List</button>
<script>
//Array of names
var names = [];
//Other code uneeded for this question
//List of Canidates
document.getElementById('canidates').innerHTML =
"<strong>List of Canidates:</strong> " + names.join(" | ");
//Other code uneeded for this question
//Remove name from Array
function delName() {
var dnameVal = document.getElementById('delname').value;
var pos = names.indexOf(dnameVal);
var namepos = names[pos]
var posstr = namepos.toUpperCase();
var dup = dnameVal.toUpperCase();
if(dup != posstr) {
alert("Not a valid name");
}
else {
names.splice(pos, 1);
document.getElementById('canidates').innerHTML =
"<strong>List of Canidates:</strong> " + names.join(" | ");
}
}
</script>
</body>
</html>
ES2015 findIndex:
var array = ['I', 'hAve', 'theSe', 'ITEMs'],
indexOf = (arr, q) => arr.findIndex(item => q.toLowerCase() === item.toLowerCase());
console.log( indexOf(array, 'i') ) // 0
console.log( indexOf(array, 'these') ) // 2
console.log( indexOf(array, 'items') ) // 3
In ECMA-262, 5th edition, you could use Array.prototype.some for this.
var array = [ 'I', 'hAve', 'theSe', 'ITEMs' ];
var query = 'these'.toLowerCase();
var index = -1;
array.some(function(element, i) {
if (query === element.toLowerCase()) {
index = i;
return true;
}
});
// Result: index = 2
Easy way would be to have a temporary array that contains all the names in uppercase. Then you can compare the user input. So your code could become somthing like this:
function delName() {
var dnameVal = document.getElementById('delname').value;
var upperCaseNames = names.map(function(value) {
return value.toUpperCase();
});
var pos = upperCaseNames.indexOf(dnameVal.toUpperCase());
if(pos === -1) {
alert("Not a valid name");
}
else {
names.splice(pos, 1);
document.getElementById('canidates').innerHTML =
"<strong>List of Canidates:</strong> " + names.join(" | ");
}
}
Hope this helps solve your problem.
The most elegant solution would be to convert the array into a string first, then do a case insensitive comparison. For example:
var needle = "PearS"
var haystack = ["Apple", "banNnas", "pEArs"];
var stricmp = haystack.toString().toLowerCase(); // returns
// "apple,bananas,pears"
if (stricmp.indexOf(needle.toLowerCase()) > -1) {
// the search term was found in the array
} else {
// the search term was not found in the array
}
Probably best to create your own custom indexOf method, something like this.
'use strict';
var customIndexOf = function(arrayLike, searchElement) {
var object = Object(arrayLike);
var length = object.length >>> 0;
var fromIndex = arguments.length > 2 ? arguments[2] >> 0 : 0;
if (length < 1 || typeof searchElement !== 'string' || fromIndex >= length) {
return -1;
}
if (fromIndex < 0) {
fromIndex = Math.max(length - Math.abs(fromIndex), 0);
}
var search = searchElement.toLowerCase();
for (var index = fromIndex; index < length; index += 1) {
if (index in object) {
var item = object[index];
if (typeof item === 'string' && search === item.toLowerCase()) {
return index;
}
}
}
return -1;
};
var names = [
'John',
'Anne',
'Brian'
];
console.log(customIndexOf(names, 'aNnE'));
Or even
'use strict';
var customIndexOf = function(array, searchElement, fromIndex) {
return array.map(function(value) {
return value.toLowerCase();
}).indexOf(searchElement.toLowerCase(), fromIndex);
};
var names = [
'John',
'Anne',
'Brian'
];
console.log(customIndexOf(names, 'aNnE'));
You may also want to add more checks to be sure that each element in the array is actually a String and that the searchElement is also actually a String too. If pre-ES5 then load appropriate shims
You can use Array.prototype.find()
found = myArray.find(key => key.toUpperCase() === searchString.toUpperCase()) != undefined;
Example:
myArray = ['An', 'aRRay', 'oF', 'StringS'];
searchString = 'array';
found = myArray.find(key => key.toUpperCase() === searchString.toUpperCase()) != undefined;
if (found ) {
// The array contains the search string
}
else {
// Search string not found
}
Note: Array cannot contain undefined as a value.
It is possible using by map method. For example see below code
var _name = ['prasho','abraham','sam','anna']
var _list = [{name:'prasho'},{name:'Gorge'}];
for(var i=0;i<_list.length;i++)
{
if(_name.map(function (c) {
return c.toLowerCase();
}).indexOf(_list[i].name.toLowerCase()) != -1) {
//do what ever
}else{
//do what ever
}
}
More info
I needed something similar to this where I needed compare two strings using includes and needed to be able to support both case and case insensitive searches so I wrote the following small function
function compare(l1: string, l2: string, ignoreCase = true): boolean {
return (ignoreCase ? l1.toLowerCase() : l1).includes((ignoreCase ? l2.toLowerCase() : l2));
}
Same principle could apply to indexOf as below
function indexOf(l1: string, l2: string, ignoreCase = true): number {
return (ignoreCase ? l1.toLowerCase() : l1).indexOf((ignoreCase ? l2.toLowerCase() : l2));
}
I know this is not specifically Array.indexOf but hope this helps someone out if the come across this post on their travels.
To answer the ops question though, you can apply this similarly to an array combined with this answer from #ULIT JAIDEE (the slight change to this was using the tilda character as a separator in case any of the array values contained spaces)
function compare(l1: any[], l2: any[], ignoreCase = true): boolean {
return (ignoreCase ? l1.join('~').toLowerCase().split('~') : l1).indexOf((ignoreCase ? l2.join('~').toLowerCase().split('~') : l2));
}
Again hope this helps.
Turn the array into a string separated by a delimiter, turn that string lowercase, and then split the string back into an array by the same delimiter:
function findIt(arr, find, del) {
if (!del) { del = '_//_'; }
arr = arr.join(del).toLowerCase().split(del);
return arr.indexOf(find.toLowerCase());
}
var arr = ['Tom Riddle', 'Ron Weasley', 'Harry Potter', 'Hermione Granger'];
var find = 'HaRrY PoTtEr';
var index = findIt(arr, find);
if (~index) {
alert('Found ' + arr[index] + '! :D');
} else {
alert('Did not find it. D:');
}
This is the shortest one.
haystack.join(' ').toLowerCase().split(' ').indexOf(needle.toLowerCase())
// unique only, removes latter occurrences
array.filter((v, i, a) => a.findIndex(j => v.toLowerCase() === j.toLowerCase()) === i);
To improve on #vsync answer and handle mixed content in the array here is my take. (I understand the OP is about case-sensitive thus it implies strings, maybe :)
var array = ['I', 'hAve', 7, {}, 'theSe', 'ITEMs'],
Contains = (arr, q) =>
arr.findIndex((item) => q.toString().toLowerCase() === item.toString().toLowerCase());
console.log(Contains(array, 'i'));
console.log(Contains(array, 'x'));
console.log(Contains(array, {} ));
console.log(Contains(array, 7 ));
You can't make it case-insensitive. I'd use an object instead to hold a set of names:
function Names() {
this.names = {};
this.getKey = function(name) {
return name.toLowerCase();
}
this.add = function(name) {
this.names[this.getKey(name)] = name;
}
this.remove = function(name) {
var key = this.getKey(name);
if (key in this.names) {
delete this.names[key];
} else {
throw Error('Name does not exist');
}
}
this.toString = function() {
var names = [];
for (var key in this.names) {
names.push(this.names[key]);
}
return names.join(' | ');
}
}
var names = new Names();
function update() {
document.getElementById('canidates').innerHTML = '<strong>List of Canidates:</strong> ' + names;
}
function deleteName() {
var name = document.getElementById('delname').value;
try {
names.remove(name);
update();
} catch {
alert('Not a valid name');
}
}
update();

Javascript sort alphabetically matching the beginning of string then alphabetically for contained text

I need help sorting through some data.
Say I type "piz" in a searchfield. I get in return and array with all the entries that contain "piz".
I now want to display them in the following order:
pizza
pizzeria
apizzetto
berpizzo
First the items that start with what I typed in alphabetical order then the ones that contain what I typed in alphabetical order.
Instead if I sort them alphabetically I get the following
apizzetto
berpizzo
pizza
pizzeria
Does anyone know how to do this?
Thanks for your help.
You can split the data into two arrays, one that starts with your input and one that doesn't. Sort each separately, then combine the two results:
var data = [
'pizzeria',
'berpizzo',
'apizzetto',
'pizza'
];
function sortInputFirst(input, data) {
var first = [];
var others = [];
for (var i = 0; i < data.length; i++) {
if (data[i].indexOf(input) == 0) {
first.push(data[i]);
} else {
others.push(data[i]);
}
}
first.sort();
others.sort();
return(first.concat(others));
}
var results = sortInputFirst('piz', data);
You can see it work here: http://jsfiddle.net/jfriend00/nH2Ff/
The right full solution is:
var data = [
'pizzeria',
'berpizzo',
'apizzetto',
'pizza'
];
var _sortByTerm = function (data, term) {
return data.sort(function (a, b) {
return a.indexOf(term) < b.indexOf(term) ? -1 : 1;
});
};
var result = _sortByTerm(data, 'piz');
If you want object sort, use this function:
var _sortByTerm = function (data, key, term) {
return data.sort(function (a, b) {
return a[key].indexOf(term) < b[key].indexOf(term) ? -1 : 1;
});
};
Using reduce:
const data = ['pizzeria', 'berpizzo', 'pizza', 'apizzetto'];
function sortInputFirst(input, data) {
data.sort();
const [first, others] = data.reduce(([a, b], c) => (c.indexOf(input) == 0 ? [[...a, c], b] : [a, [...b, c]]), [[], []]);
return(first.concat(others));
}
const output = sortInputFirst('piz', data);
console.log(output)
Here's another one:
var str = 'piz';
var arr = ['apizzetto','pizzeria','berpizzo','pizza'];
arr.sort(function(a,b) {
var bgnA = a.substr(0,str.length).toLowerCase();
var bgnB = b.substr(0,str.length).toLowerCase();
if (bgnA == str.toLowerCase()) {
if (bgnB != str.toLowerCase()) return -1;
} else if (bgnB == str.toLowerCase()) return 1;
return a < b ? -1 : (a > b ? 1 : 0);
});
console.log(arr);
Here's how I used the top voted answer to make my search function use a normalized set of data. It removes accents before comparing strings and is also case insensitive.
function getAutocompleteNormalizedMatches(userInput, array) {
const normalizedInput = getNormalizedString(userInput);
let normalizedListItem;
let startsWith = [];
let anywhere = [];
for (let i = 0; i < array.length; i++) {
normalizedListItem = getNormalizedString(array[i]);
if (normalizedListItem.indexOf(normalizedInput) === 0) {
startsWith.push(array[i])
} else if (normalizedListItem.includes(normalizedInput)) {
anywhere.push(array[i])
}
}
startsWith.sort();
anywhere.sort();
return startsWith.concat(anywhere);
}
const getNormalizedString = function (str) {
str = str.replace(/\s+/g, " ").trim();
return (str ? removeDiacritics(str.toLowerCase()) : "");
};
To get the removeDiacritics() function, please refer to this link because it takes quite a bit of useless space if you guys don't need it: Remove accents diacritics in a string with JavaScript

Categories

Resources