How to check substring in a string with fuzziness? - javascript

I have a string akstr = My name is khan and I want to know that does akstr contains My name which I can do easily but if I want to check does akstr contains My nama with little mistake in spelling and I want True as output. Could it be done using javascript?

Provided you use node.js, you can use the npm package natural.
It is used for natural language processing applications.
It has a set of methods for calculating String Distances. Meaning that My name is 94% equal to My nama. You can create your fuzzy algorithm based on that. An example:
const natural = require('natural');
let distance = natural.JaroWinklerDistance("My name", "My nama");
console.log(distance);
prints 0.9428571428571428
You may find other intersting stuff in it too, like spell checking and Approximate String Matching.
With just javascript I wrote a simple fuzzy contains method with three inputs. The first is the full string, the second, the substring and the third the allowed error. In this case with an error 2, you allow 2 characters to be different for the substring. With 0 you get the normal contains method. You can also change the way the error is calculated (maybe a percentage based on the substring length). I used the code for the levenstein method from here: https://gist.github.com/andrei-m/982927
function levenstein(a, b) {
var 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];
}
function fuzzyContains(a, b, error) {
var matchLength = a.length - b.length;
var distanceToMatch = levenstein(a, b) - matchLength;
if(distanceToMatch - error > 0) {
return false;
} else {
return true;
}
}
console.log(fuzzyContains("hello world entire", "worlf", 1))

You can compare the String, like
My Name
My Nama
is 90% matches so you can return true.
You will get more idea from the following link
Compare Strings Javascript Return %of Likely

Related

Find all possible function combinations

I have 3, js functions:
function f1(a,b){
return 0;//returns something
}
function f2(a,b){
return 0;//returns something
}
function f3(a){/*note that this has only 1 input: a*/
return 0;//returns something
}
I need to find all possible combinations of these functions up to two functions in a string that is, it need to return the below strings, in form of array
"f1(f1($,$),$)"//used functions:2:- f1,f1
"f1($,f1($,$))"//used functions:2:- f1,f1
"f1(f2($,$),$)"//used functions:2:- f1,f2
"f1($,f2($,$))"//used functions:2:- f1,f2
"f1(f3($),$)"//used functions:2:- f1,f3
"f1($,f3($))"//used functions:2:- f1,f3
"f1($,$)"//used functions:1:- f1
"f2(f1($,$),$)"//used functions:2:- f2,f1
"f2($,f1($,$))"//used functions:2:- f2,f1
"f2(f2($,$),$)"//used functions:2:- f2,f2
"f2($,f2($,$))"//used functions:2:- f2,f2
"f2(f3($),$)"//used functions:2:- f2,f3
"f2($,f3($))"//used functions:2:- f2,f3
"f2($,$)"//used functions:1:- f2
"f3(f1($,$))"//used functions:2:- f3,f1
"f3(f2($,$))"//used functions:2:- f3,f2
"f3(f3($))"//used functions:2:- f3,f3
"f3($)"//used functions:1:- f3
Notes:
$ represents some value that need not be interfered in this Q.s, so let $ ,be $ for this Q.s
the three js functions may vary to any extent, in my case 7 js functions, with six of them having two inputs ,and one function with one input
up to two functions in a string may vary to any extent, like up to 5 functions...
I have learnt to generate possible combinations ,as shown below
/*
* Generate all possible combinations from a list of characters for a given length
*/
function* charCombinations(chars, minLength, maxLength) {
chars = typeof chars === 'string' ? chars : '';
minLength = parseInt(minLength) || 0;
maxLength = Math.max(parseInt(maxLength) || 0, minLength);
//Generate for each word length
for (i = minLength; i <= maxLength; i++) {
//Generate the first word for the combination length by the repetition of first character.
word = (chars[0] || '').repeat(i);
yield word;
//Generate other possible combinations for the word
//Total combinations will be chars.length raised to power of word.length
//Make iteration for all possible combinations
for (j = 1; j < Math.pow(chars.length, i); j++) {
//Make iteration for all indices of the word
for (k = 0; k < i; k++) {
//check if the current index char need to be flipped to the next char.
if (!(j % Math.pow(chars.length, k))) {
// Flip the current index char to the next.
let charIndex = chars.indexOf(word[k]) + 1;
char = chars[charIndex < chars.length ? charIndex : 0];
word = word.substr(0, k) + char + word.substr(k + char.length);
}
}
//Re-oder not neccesary but it makes the words are yeilded alphabetically on ascending order.
yield word.split('').reverse().join('');
}
}
}
let combinations = charCombinations('abc', 1, 3);
let combination = 0;
var carray = [];
while (typeof combination != "undefined") {
combination = combinations.next().value
carray.push(combination);
}
carray.pop();
console.log(carray);
Its is a modification to this blog,
But I don't know how to implement it with a string that is in a form of function with brackets,
I guess using xml will help as shown in here
I have practice of using xml for data and algorithm handling in js,
But still I don't know how to implement it.,Please help
You can use a recursive generator that takes the following input:
An array of function-call strings with $ placeholders for arguments, so for example: ["f1($,$)", "f2($,$)", "f3($)"]. This means you can control how many arguments a function takes, and how many take just 1 (always 1 in your question), or 2, or even more.
A minimum number of function calls to generate per output (this seems to be always 1 in your question)
A maximum number of function calls to generate per output (like 7)
The algorithm passes the current string to the recursive call which can extend it further until the time comes to yield it. The idea is that every $ is found in the string and can be replaced with more nested function calls.
Snippet:
function* combinations(funcs, minCount, maxCount, result="$", start=0) {
if (maxCount <= 0) return yield result;
for (let f of funcs) {
for (let i = result.indexOf("$", start); i >= 0; i = result.indexOf("$", i + 1)) {
yield* combinations(funcs, minCount - 1, maxCount - 1, result.slice(0, i) + f + result.slice(i + 1), i);
}
}
if (minCount <= 0) yield result;
}
// Example run
for (let s of combinations(["f1($,$)", "f2($,$)", "f3($)"], 1, 2)) {
console.log(s);
}
In case your input is just the function objects (references), then you need some preprocessing so to get their names and the number of parameters they are defined with:
function describe(f) {
return `${f.name}(${Array(f.length).fill("$").join(",")})`;
}
function* combinations(funcs, minCount, maxCount, result="$", start=0) {
if (maxCount <= 0) return yield result;
for (let f of funcs) {
for (let i = result.indexOf("$", start); i >= 0; i = result.indexOf("$", i + 1)) {
yield* combinations(funcs, minCount - 1, maxCount - 1, result.slice(0, i) + f + result.slice(i + 1), i);
}
}
if (minCount <= 0) yield result;
}
// Example run
function f1(a,b){ return 0; }
function f2(a,b){ return 0; }
function f3(a){ return 0; }
for (let s of combinations([f1, f2, f3].map(describe), 1, 2)) {
console.log(s);
}

Compare two sentences word by word and return the number of word matches considering different word forms

Thanks to Nina I have a code to compare two sentences word by word and return the number of word matches like this:
function includeWords(wanted, seen) {
var wantedMap = wanted.split(/\s+/).reduce((m, s) => m.set(s, (m.get(s) || 0) + 1), new Map),
wantedArray = Array.from(wantedMap.keys()),
count = 0;
seen.split(/\s+/)
.forEach(s => {
var key = wantedArray.find(t => s === t || s.length > 3 && t.length > 3 && (s.startsWith(t) || t.startsWith(s)));
if (!wantedMap.get(key)) return;
console.log(s, key)
++count;
wantedMap.set(key, wantedMap.get(key) - 1);
});
return count;
}
let matches = includeWords('i was sent to earth to protect you introduced', 'they\'re were protecting him i knew that i was aware introducing');
console.log('Matched words: ' + matches);
The code works fine, but there is still one issue:
What if we want to return a match for introduced and introducing too?
If you want the program to consider the words 'introduce' and 'introducing' as a match, it would amount to a "fuzzy" match (non binary logic). One simple way of doing this would require more code, the algorithm of which would possibly resemble
Take 2 words that you wish to match, tokenize into ordered list
of letters
Compare positionally the respective letters, i.e
match a[0]==b[0]? a[1]==b[1] where a[0] represents the first letter
of the first word and b[0] represents the first tokenized
letter/character potential match candidate
KEep a rolling numeric count of such positional matches. In this case it is 8 (introduc).
divide by word length of a = 8/9 call this f
divide by word length of b = 8/11 call this g
Provide a threshold value beyond which the program will consider it a match. eg. if you say anything above 70% in BOTH f and g can be
considered a match - viola, you have your answer!
Please note that there is some normalization also needed to prevent low length words from becoming false positives. you can add a constraint that the aforementioned calculation applies to words with at least 5 letters(or something to that effect!
Hope this helps!!
Regards,
SR
You could calculate similarites for a word pair and get a relation how many characters are similar bei respecting the length of the given word and the wanted pattern.
function getSimilarity(a, b) {
var i = 0;
while (i < a.length) {
if (a[i] !== b[i]) break;
i++;
}
return i / Math.max(a.length, b.length);
}
console.log(getSimilarity('abcdefghij', 'abc')); // 0.3
console.log(getSimilarity('abcdefghij', 'abcdef')); // 0.6
console.log(getSimilarity('abcdefghij', 'abcdefghij')); // 1
console.log(getSimilarity('abcdef', 'abcdefghij')); // 0.6
console.log(getSimilarity('abcdefghij', 'abcdef')); // 0.6
console.log(getSimilarity('abcdefghij', 'xyz')); // 0
console.log(getSimilarity('introduced', 'introducing')); // 0.7272727272727273
Here's a quick fix solution.
It's not intended as a complete solution.
Since the English language has more than a few quirks that would almost require an AI to understand the language.
First add a function that can compare 2 words and returns a boolean.
It'll also make it easier to test for specific words, and adapt to what's really needed.
For example, here's a function that does the simple checks that were already used.
Plus an '...ed' versus '...ing' check.
function compareWords (word1, word2) {
if (word1 === word2)
return true;
if (word1.length > 3 && word2.length > 3) {
if (word1.startsWith(word2) || word2.startsWith(word1))
return true;
if (word1.length > 4 && word2.length > 4) {
if (/(ing|ed)$/.test(word1) && word1.replace(/(ing|ed)$/, 'inged') === word2.replace(/(ing|ed)$/, 'inged'))
return true;
}
}
return false;
}
//
// tests
//
let words = [
["same", "same"],
["different", "unsame"],
["priced", "pricing"],
["price", "priced"],
["producing", "produced"],
["produced", "producing"]
];
words.forEach( (arr, idx) => {
let word1= arr[0];
let word2= arr[1];
let isSame = compareWords(word1, word2);
console.log(`[${word1}] ≈ [${word2}] : ${isSame}`);
});
Then use it in the code you already have.
...
seen.split(/\s+/)
.forEach(s => {
var key = wantedArray.find(t => compareWords(t, s));
...
Regarding string similarity, here's f.e. an older SO post that has some methods to compare strings : Compare Strings Javascript Return %of Likely
I have implemented this, it seems to work fine. any suggestions would be appreciated..
let speechResult = "i was sent to earth to introducing protect yourself introduced seen";
let expectSt = ['they were protecting him knew introducing that you i seen was aware seen introducing'];
// Create arrays of words from above sentences
let speechResultWords = speechResult.split(/\s+/);
let expectStWords = expectSt[0].split(/\s+/);
function includeWords(){
// Declare a variable to hold the count number of matches
let arr = [];
for(let a = 0; a < speechResultWords.length; a++){
for(let b = 0; b < expectStWords.length; b++){
if(similarity(speechResultWords[a], expectStWords[b]) > 69){
arr.push(speechResultWords[a]);
console.log(speechResultWords[a] + ' includes in ' + expectStWords[b]);
}
} // End of first for loop
} // End of second for loop
let uniq = [...new Set(arr)];
return uniq.length;
};
let result = includeWords();
console.log(result)
// The algorithmn
function similarity(s1, s2) {
var longer = s1;
var shorter = s2;
if (s1.length < s2.length) {
longer = s2;
shorter = s1;
}
var longerLength = longer.length;
if (longerLength == 0) {
return 1.0;
}
return (longerLength - editDistance(longer, shorter)) / parseFloat(longerLength)*100;
}
function editDistance(s1, s2) {
s1 = s1.toLowerCase();
s2 = s2.toLowerCase();
var costs = new Array();
for (var i = 0; i <= s1.length; i++) {
var lastValue = i;
for (var j = 0; j <= s2.length; j++) {
if (i == 0)
costs[j] = j;
else {
if (j > 0) {
var newValue = costs[j - 1];
if (s1.charAt(i - 1) != s2.charAt(j - 1))
newValue = Math.min(Math.min(newValue, lastValue),
costs[j]) + 1;
costs[j - 1] = lastValue;
lastValue = newValue;
}
}
}
if (i > 0)
costs[s2.length] = lastValue;
}
return costs[s2.length];
}

JavaScript - Binary search hangs every time

I have a 2D array, something like the following:
[1.11, 23]
[2.22, 52]
[3.33, 61]
...
Where the array is ordered by the first value in each row.
I am trying to find a value within the array that is close to the search value - within a certain sensitivity. The way this is set up, and the value of the sensitivity, ensure only one possible match within the array.
The search value is the current x-pos of the mouse. The search is called on mousemove, and so is being called often.
Originally I had the following (using a start-to-end for loop):
for(var i = 0; i < arr.length; i++){
if(Math.abs(arr[i][0] - x) <= sensitivity){
hit = true;
break;
}
}
And it works like a charm. So far, I've only been using small data sets, so there is no apparent lag using this method. But, eventually I will be using much larger data sets, and so want to switch this to a Binary Search:
var a = 0;
var b = arr.length - 1;
var c = 0;
while(a < b){
c = Math.floor((a + b) / 2);
if(Math.abs(arr[c][0] - x) <= sensitivity){
hit = true;
break;
}else if(arr[c][0] < x){
a = c;
}else{
b = c;
}
}
This works well, for all of 2 seconds, and then it hangs to the point where I need to restart my browser. I've used binary searches plenty in the past, and cannot for the life of me figure out why this one isn't working properly.
EDIT 1
var sensitivity = (width / arr.length) / 2.001
The points in the array are equidistant, and so this sensitivity ensures that there is no ambiguous 1/2-way point in between two arr values. You are either in one or the other.
Values are created dynamically at page load, but look exactly like what I've mentioned above. The x-values have more significant figures, and the y values are all over the place, but there is no significant difference between the small sample I provided and the generated one.
EDIT 2
Printed a list that was dynamically created:
[111.19999999999999, 358.8733333333333]
[131.4181818181818, 408.01333333333326]
[151.63636363636363, 249.25333333333327]
[171.85454545454544, 261.01333333333326]
[192.07272727272726, 298.39333333333326]
[212.29090909090908, 254.2933333333333]
[232.5090909090909, 308.47333333333324]
[252.72727272727272, 331.1533333333333]
[272.94545454545454, 386.1733333333333]
[293.16363636363633, 384.9133333333333]
[313.3818181818182, 224.05333333333328]
[333.6, 284.53333333333325]
[353.81818181818187, 278.2333333333333]
[374.0363636363637, 391.63333333333327]
[394.25454545454556, 322.33333333333326]
[414.4727272727274, 300.9133333333333]
[434.69090909090926, 452.95333333333326]
[454.9090909090911, 327.7933333333333]
[475.12727272727295, 394.9933333333332]
[495.3454545454548, 451.27333333333326]
[515.5636363636366, 350.89333333333326]
[535.7818181818185, 308.47333333333324]
[556.0000000000003, 395.83333333333326]
[576.2181818181822, 341.23333333333323]
[596.436363636364, 371.47333333333324]
[616.6545454545459, 436.9933333333333]
[636.8727272727277, 280.7533333333333]
[657.0909090909096, 395.4133333333333]
[677.3090909090914, 433.21333333333325]
[697.5272727272733, 355.09333333333325]
[717.7454545454551, 333.2533333333333]
[737.963636363637, 255.55333333333328]
[758.1818181818188, 204.7333333333333]
[778.4000000000007, 199.69333333333327]
[798.6181818181825, 202.63333333333327]
[818.8363636363644, 253.87333333333328]
[839.0545454545462, 410.5333333333333]
[859.272727272728, 345.85333333333324]
[879.4909090909099, 305.11333333333323]
[899.7090909090917, 337.8733333333333]
[919.9272727272736, 351.3133333333333]
[940.1454545454554, 324.01333333333326]
[960.3636363636373, 331.57333333333327]
[980.5818181818191, 447.4933333333333]
[1000.800000000001, 432.3733333333333]
As you can see, it is ordered by the first value in each row, ascending.
SOLUTION
Changing the condition to
while(a < b)
and
var b = positions.length;
and
else if(arr[c][0] < x){
a = c + 1;
}
did the trick.
Your binary search seems to be a bit off: try this.
var arr = [[1,0],[3,0],[5,0]];
var lo = 0;
var hi = arr.length;
var x = 5;
var sensitivity = 0.1;
while (lo < hi) {
var c = Math.floor((lo + hi) / 2);
if (Math.abs(arr[c][0] - x) <= sensitivity) {
hit = true;
console.log("FOUND " + c);
break;
} else if (x > arr[c][0]) {
lo = c + 1;
} else {
hi = c;
}
}
This is meant as a general reference to anyone implementing binary search.
Let:
lo be the smallest index that may possibly contain your value,
hi be one more than the largest index that may contain your value
If these conventions are followed, then binary search is simply:
while (lo < hi) {
var mid = (lo + hi) / 2;
if (query == ary[mid]) {
// do stuff
else if (query < ary[mid]) {
// query is smaller than mid
// so query can be anywhere between lo and (mid - 1)
// the upper bound should be adjusted
hi = mid;
else {
// query can be anywhere between (mid + 1) and hi.
// adjust the lower bound
lo = mid + 1;
}
I don't know your exact situation, but here's a way the code could crash:
1) Start with an array with two X values. This array will have a length of 2, so a = 0, b = 1, c = 0.
2) a < b, so the while loop executes.
3) c = floor((a + b) / 2) = floor(0.5) = 0.
4) Assume the mouse is not within sensitivity of the first X value, so the first if branch does not hit.
5) Assume our X values are to the right of our mouse, so the second if branch enters. This sets a = c, or 0, which it already is.
6) Thus, we get an endless loop.

Permutations without recursive function call

Requirement: Algorithm to generate all possible combinations of a set , without duplicates , or recursively calling function to return results.
The majority , if not all of the Answers provided at Permutations in JavaScript? recursively call a function from within a loop or other function to return results.
Example of recursive function call within loop
function p(a, b, res) {
var b = b || [], res = res || [], len = a.length;
if (!len)
res.push(b)
else
for (var i = 0; i < len
// recursive call to `p` here
; p(a.slice(0, i).concat(a.slice(i + 1, len)), b.concat(a[i]), res)
, i++
);
return res
}
p(["a", "b", "c"]);
The current Question attempts to create the given permutation in a linear process , relying on the previous permutation.
For example , given an array
var arr = ["a", "b", "c"];
to determine the total number of possible permutations
for (var len = 1, i = k = arr.length; len < i ; k *= len++);
k should return 6 , or total number of possible permutations of arr ["a", "b", "c"]
With the total number of individual permutations determined for a set , the resulting array which would contain all six permutations could be created and filled using Array.prototype.slice() , Array.prototype.concat() and Array.prototype.reverse()
var res = new Array(new Array(k));
res[0] = arr;
res[1] = res[0].slice(0,1).concat(res[0].slice(-2).reverse());
res[2] = res[1].slice(-1).concat(res[1].slice(0,2));
res[3] = res[2].slice(0,1).concat(res[2].slice(-2).reverse());
res[4] = res[3].slice(-2).concat(res[3].slice(0,1));
res[5] = res[4].slice(0,1).concat(res[4].slice(-2).reverse());
Attempted to reproduce results based on the pattern displayed at the graph for An Ordered Lexicographic Permutation Algorithm based on one published in Practical Algorithms in C++ at Calculating Permutations and Job Interview Questions .
There appears to be a pattern that could be extended if the input set was , for example
["a", "b", "c", "d", "e"]
where 120 permutations would be expected.
An example of an attempt at filling array relying only on previous permutation
// returns duplicate entries at `j`
var arr = ["a", "b", "c", "d", "e"], j = [];
var i = k = arr.length;
arr.forEach(function(a, b, array) {
if (b > 1) {
k *= b;
if (b === i -1) {
for (var q = 0;j.length < k;q++) {
if (q === 0) {
j[q] = array;
} else {
j[q] = !(q % i)
? array.slice(q % i).reverse().concat(array.slice(0, q % i))
: array.slice(q % i).concat(array.slice(0, q % i));
}
}
}
}
})
however have not yet been able to make the necessary adjustments at parameters for .slice() , .concat() , .reverse() at above js to step from one permutation to the next ; while only using the previous array entry within res to determine current permutation , without using recursive.
Noticed even , odd balance of calls and tried to use modulus % operator and input array .length to either call .reverse() or not at ["a", "b", "c", "d", "e"] array , though did not produce results without duplicate entries.
The expected result is that the above pattern could be reduced to two lines called in succession for the duration of the process until all permutations completed, res filled ; one each for call to .reverse() , call without .reverse() ; e.g., after res[0] filled
// odd , how to adjust `.slice()` , `.concat()` parameters
// for array of unknown `n` `.length` ?
res[i] = res[i - 1].slice(0,1).concat(res[i - 1].slice(-2).reverse());
// even
res[i] = res[1 - 1].slice(-1).concat(res[i - 1].slice(0,2));
Question: What adjustments to above pattern are necessary , in particular parameters , or index , passed .slice() , .concat() to produce all possible permutations of a given set without using a recursive call to the currently processing function ?
var arr = ["a", "b", "c"];
for (var len = 1, i = k = arr.length; len < i; k *= len++);
var res = new Array(new Array(k));
res[0] = arr;
res[1] = res[0].slice(0, 1).concat(res[0].slice(-2).reverse());
res[2] = res[1].slice(-1).concat(res[1].slice(0, 2));
res[3] = res[2].slice(0, 1).concat(res[2].slice(-2).reverse());
res[4] = res[3].slice(-2).concat(res[3].slice(0, 1));
res[5] = res[4].slice(0, 1).concat(res[4].slice(-2).reverse());
console.log(res);
Edit, Update
Have found a process to utilize pattern described above to return permutations in lexicographic order for an input up to .length 4 , using a single for loop. Expected results are not returned for array with .length of 5.
The pattern is based on the second chart at "Calculating Permutations and Job Interview Questions"[0].
Would prefer not to use .splice() or .sort() to return results, though used here while attempting to adhere to last "rotate" requirement at each column. The variable r should reference the index of the first element of the next permutation, which it does.
The use of .splice() , .sort() could be included if their usage followed the pattern at the chart ; though at js below, they actually do not.
Not entirely certain that the issue with js below is only the statement following if (i % (total / len) === reset) , though that portion required the most investment of time; yet still does not return expected results.
Specifically, now referring to the chart, at rotating , for example 2 to index 0, 1 to index 2. Attempted to achieve this by using r , which is a negative index, to traverses from right to left to retrieve next item that should be positioned at index 0 of adjacent "column".
At next column, 2 would be placed at index 2 , 3 would be placed at index 0. This is portion, as far as have been able to grasp or debug, so far, is the area where error is occurring.
Again, returns expected results for [1,2,3,4], though not for [1,2,3,4,5]
var arr = [1, 2, 3, 4];
for (var l = 1, j = total = arr.length; l < j ; total *= l++);
for (var i = 1
, reset = 0
, idx = 0
, r = 0
, len = arr.length
, res = [arr]
; i < total; i++) {
// previous permutation
var prev = res[i - 1];
// if we are at permutation `6` here, or, completion of all
// permutations beginning with `1`;
// setting next "column", place `2` at `index` 0;
// following all permutations beginning with `2`, place `3` at
// `index` `0`; with same process for `3` to `4`
if (i % (total / len) === reset) {
r = --r % -(len);
var next = prev.slice(r);
if (r === -1) {
// first implementation used for setting item at index `-1`
// to `index` 0
// would prefer to use single process for all "rotations",
// instead of splitting into `if` , `else`, though not there, yet
res[i] = [next[0]].concat(prev.slice(0, 1), prev.slice(1, len - 1)
.reverse());
} else {
// workaround for "rotation" at from `index` `r` to `index` `0`
// the chart does not actually use the previous permutation here,
// but rather, the first permutation of that particular "column";
// here, using `r` `,i`, `len`, would be
// `res[i - (i - 1) % (total / len)]`
var curr = prev.slice();
// this may be useful, to retrieve `r`,
// `prev` without item at `r` `index`
curr.splice(prev.indexOf(next[0]), 1);
// this is not optiomal
curr.sort(function(a, b) {
return arr.indexOf(a) > arr.indexOf(b)
});
// place `next[0]` at `index` `0`
// place remainder of sorted array at `index` `1` - n
curr.splice(0, 0, next[0])
res[i] = curr
}
idx = reset;
} else {
if (i % 2) {
// odd
res[i] = prev.slice(0, len - 2).concat(prev.slice(-2)
.reverse())
} else {
// even
--idx
res[i] = prev.slice(0, len - (len - 1))
.concat(prev.slice(idx), prev.slice(1, len + (idx)))
}
}
}
// try with `arr` : `[1,2,3,4,5]` to return `res` that is not correct;
// how can above `js` be adjusted to return correct results for `[1,2,3,4,5]` ?
console.log(res, res.length)
Resources:
Generating Permutation with Javascript
(Countdown) QuickPerm Head Lexicography:
(Formally Example_03 ~ Palindromes)
Generating all Permutations [non-recursive]
(Attempt to port to from C++ to javascript jsfiddle http://jsfiddle.net/tvvvjf3p/)
Calculating Permutation without Recursion - Part 2
permutations of a string using iteration
iterative-permutation
Permutations by swapping
Evaluation of permutation algorithms
Permutation algorithm without recursion? Java
Non-recursive algorithm for full permutation with repetitive elements?
String permutations in Java (non-recursive)
Generating permutations lazily
How to generate all permutations of a list in Python
Can all permutations of a set or string be generated in O(n log n) time?
Finding the nth lexicographic permutation of ‘0123456789’
Combinations and Permutations
Here is a simple solution to compute the nth permutation of a string:
function string_nth_permutation(str, n) {
var len = str.length, i, f, res;
for (f = i = 1; i <= len; i++)
f *= i;
if (n >= 0 && n < f) {
for (res = ""; len > 0; len--) {
f /= len;
i = Math.floor(n / f);
n %= f;
res += str.charAt(i);
str = str.substring(0, i) + str.substring(i + 1);
}
}
return res;
}
The algorithm follows these simple steps:
first compute f = len!, there are factorial(len) total permutations of a set of len different elements.
as the first element, divide the permutation number by (len-1)! and chose the element at the resulting offset. There are (len-1)! different permutations that have any given element as their first element.
remove the chosen element from the set and use the remainder of the division as the permutation number to keep going.
perform these steps with the rest of the set, whose length is reduced by one.
This algorithm is very simple and has interesting properties:
It computes the n-th permutation directly.
If the set is ordered, the permutations are generated in lexicographical order.
It works even if set elements cannot be compared to one another, such as objects, arrays, functions...
Permutation number 0 is the set in the order given.
Permutation number factorial(a.length)-1 is the last one: the set a in reverse order.
Permutations outside this range are returned as undefined.
It can easily be converted to handle a set stored as an array:
function array_nth_permutation(a, n) {
var b = a.slice(); // copy of the set
var len = a.length; // length of the set
var res; // return value, undefined
var i, f;
// compute f = factorial(len)
for (f = i = 1; i <= len; i++)
f *= i;
// if the permutation number is within range
if (n >= 0 && n < f) {
// start with the empty set, loop for len elements
for (res = []; len > 0; len--) {
// determine the next element:
// there are f/len subsets for each possible element,
f /= len;
// a simple division gives the leading element index
i = Math.floor(n / f);
// alternately: i = (n - n % f) / f;
res.push(b.splice(i, 1)[0]);
// reduce n for the remaining subset:
// compute the remainder of the above division
n %= f;
// extract the i-th element from b and push it at the end of res
}
}
// return the permutated set or undefined if n is out of range
return res;
}
clarification:
f is first computed as factorial(len).
For each step, f is divided by len, giving exacty the previous factorial.
n divided by this new value of f gives the slot number among the len slots that have the same initial element. Javascript does not have integral division, we could use (n / f) ... 0) to convert the result of the division to its integral part but it introduces a limitation to sets of 12 elements. Math.floor(n / f) allows for sets of up to 18 elements. We could also use (n - n % f) / f, probably more efficient too.
n must be reduced to the permutation number within this slot, that is the remainder of the division n / f.
We could use i differently in the second loop, storing the division remainder, avoiding Math.floor() and the extra % operator. Here is an alternative for this loop that may be even less readable:
// start with the empty set, loop for len elements
for (res = []; len > 0; len--) {
i = n % (f /= len);
res.push(b.splice((n - i) / f, 1)[0]);
n = i;
}
I think this post should help you. The algorithm should be easily translatable to JavaScript (I think it is more than 70% already JavaScript-compatible).
slice and reverse are bad calls to use if you are after efficiency. The algorithm described in the post is following the most efficient implementation of the next_permutation function, that is even integrated in some programming languages (like C++ e.g.)
EDIT
As I iterated over the algorithm once again I think you can just remove the types of the variables and you should be good to go in JavaScript.
EDIT
JavaScript version:
function nextPermutation(array) {
// Find non-increasing suffix
var i = array.length - 1;
while (i > 0 && array[i - 1] >= array[i])
i--;
if (i <= 0)
return false;
// Find successor to pivot
var j = array.length - 1;
while (array[j] <= array[i - 1])
j--;
var temp = array[i - 1];
array[i - 1] = array[j];
array[j] = temp;
// Reverse suffix
j = array.length - 1;
while (i < j) {
temp = array[i];
array[i] = array[j];
array[j] = temp;
i++;
j--;
}
return true;
}
One method to create permutations is by adding each element in all of the spaces between elements in all of the results so far. This can be done without recursion using loops and a queue.
JavaScript code:
function ps(a){
var res = [[]];
for (var i=0; i<a.length; i++){
while(res[res.length-1].length == i){
var l = res.pop();
for (var j=0; j<=l.length; j++){
var copy = l.slice();
copy.splice(j,0,a[i]);
res.unshift(copy);
}
}
}
return res;
}
console.log(JSON.stringify(ps(['a','b','c','d'])));
Here could be another solution, inspired from the Steinhaus-Johnson-Trotter algorithm:
function p(input) {
var i, j, k, temp, base, current, outputs = [[input[0]]];
for (i = 1; i < input.length; i++) {
current = [];
for (j = 0; j < outputs.length; j++) {
base = outputs[j];
for (k = 0; k <= base.length; k++) {
temp = base.slice();
temp.splice(k, 0, input[i]);
current.push(temp);
}
}
outputs = current;
}
return outputs;
}
// call
var outputs = p(["a", "b", "c", "d"]);
for (var i = 0; i < outputs.length; i++) {
document.write(JSON.stringify(outputs[i]) + "<br />");
}
Here's a snippet for an approach that I came up with on my own, but naturally was also able to find it described elsewhere:
generatePermutations = function(arr) {
if (arr.length < 2) {
return arr.slice();
}
var factorial = [1];
for (var i = 1; i <= arr.length; i++) {
factorial.push(factorial[factorial.length - 1] * i);
}
var allPerms = [];
for (var permNumber = 0; permNumber < factorial[factorial.length - 1]; permNumber++) {
var unused = arr.slice();
var nextPerm = [];
while (unused.length) {
var nextIndex = Math.floor((permNumber % factorial[unused.length]) / factorial[unused.length - 1]);
nextPerm.push(unused[nextIndex]);
unused.splice(nextIndex, 1);
}
allPerms.push(nextPerm);
}
return allPerms;
};
Enter comma-separated string (e.g. a,b,c):
<br/>
<input id="arrInput" type="text" />
<br/>
<button onclick="perms.innerHTML = generatePermutations(arrInput.value.split(',')).join('<br/>')">
Generate permutations
</button>
<br/>
<div id="perms"></div>
Explanation
Since there are factorial(arr.length) permutations for a given array arr, each number between 0 and factorial(arr.length)-1 encodes a particular permutation. To unencode a permutation number, repeatedly remove elements from arr until there are no elements left. The exact index of which element to remove is given by the formula (permNumber % factorial(arr.length)) / factorial(arr.length-1). Other formulas could be used to determine the index to remove, as long as it preserves the one-to-one mapping between number and permutation.
Example
The following is how all permutations would be generated for the array (a,b,c,d):
# Perm 1st El 2nd El 3rd El 4th El
0 abcd (a,b,c,d)[0] (b,c,d)[0] (c,d)[0] (d)[0]
1 abdc (a,b,c,d)[0] (b,c,d)[0] (c,d)[1] (c)[0]
2 acbd (a,b,c,d)[0] (b,c,d)[1] (b,d)[0] (d)[0]
3 acdb (a,b,c,d)[0] (b,c,d)[1] (b,d)[1] (b)[0]
4 adbc (a,b,c,d)[0] (b,c,d)[2] (b,c)[0] (c)[0]
5 adcb (a,b,c,d)[0] (b,c,d)[2] (b,c)[1] (b)[0]
6 bacd (a,b,c,d)[1] (a,c,d)[0] (c,d)[0] (d)[0]
7 badc (a,b,c,d)[1] (a,c,d)[0] (c,d)[1] (c)[0]
8 bcad (a,b,c,d)[1] (a,c,d)[1] (a,d)[0] (d)[0]
9 bcda (a,b,c,d)[1] (a,c,d)[1] (a,d)[1] (a)[0]
10 bdac (a,b,c,d)[1] (a,c,d)[2] (a,c)[0] (c)[0]
11 bdca (a,b,c,d)[1] (a,c,d)[2] (a,c)[1] (a)[0]
12 cabd (a,b,c,d)[2] (a,b,d)[0] (b,d)[0] (d)[0]
13 cadb (a,b,c,d)[2] (a,b,d)[0] (b,d)[1] (b)[0]
14 cbad (a,b,c,d)[2] (a,b,d)[1] (a,d)[0] (d)[0]
15 cbda (a,b,c,d)[2] (a,b,d)[1] (a,d)[1] (a)[0]
16 cdab (a,b,c,d)[2] (a,b,d)[2] (a,b)[0] (b)[0]
17 cdba (a,b,c,d)[2] (a,b,d)[2] (a,b)[1] (a)[0]
18 dabc (a,b,c,d)[3] (a,b,c)[0] (b,c)[0] (c)[0]
19 dacb (a,b,c,d)[3] (a,b,c)[0] (b,c)[1] (b)[0]
20 dbac (a,b,c,d)[3] (a,b,c)[1] (a,c)[0] (c)[0]
21 dbca (a,b,c,d)[3] (a,b,c)[1] (a,c)[1] (a)[0]
22 dcab (a,b,c,d)[3] (a,b,c)[2] (a,b)[0] (b)[0]
23 dcba (a,b,c,d)[3] (a,b,c)[2] (a,b)[1] (a)[0]
Note that each permutation # is of the form:
(firstElIndex * 3!) + (secondElIndex * 2!) + (thirdElIndex * 1!) + (fourthElIndex * 0!)
which is basically the reverse process of the formula given in the explanation.
I dare to add another answer, aiming at answering you question regarding slice, concat, reverse.
The answer is it is possible (almost), but it would not be quite effective. What you are doing in your algorithm is the following:
Find the first inversion in the permutation array, right-to-left (inversion in this case defined as i and j where i < j and perm[i] > perm[j], indices given left-to-right)
place the bigger number of the inversion
concatenate the processed numbers in reversed order, which will be the same as sorted order, as no inversions were observed.
concatenate the second number of the inversion (still sorted in accordsnce with the previos number, as no inversions were observed)
This is mainly, what my first answer does, but in a bit more optimal manner.
Example
Consider the permutation 9,10, 11, 8, 7, 6, 5, 4 ,3,2,1
The first inversion right-to-left is 10, 11.
And really the next permutation is:
9,11,1,2,3,4,5,6,7,8,9,10=9concat(11)concat(rev(8,7,6,5,4,3,2,1))concat(10)
Source code
Here I include the source code as I envision it:
var nextPermutation = function(arr) {
for (var i = arr.length - 2; i >= 0; i--) {
if (arr[i] < arr[i + 1]) {
return arr.slice(0, i).concat([arr[i + 1]]).concat(arr.slice(i + 2).reverse()).concat([arr[i]]);
}
}
// return again the first permutation if calling next permutation on last.
return arr.reverse();
}
console.log(nextPermutation([9, 10, 11, 8, 7, 6, 5, 4, 3, 2, 1]));
console.log(nextPermutation([6, 5, 4, 3, 2, 1]));
console.log(nextPermutation([1, 2, 3, 4, 5, 6]));
The code is avaiable for jsfiddle here.
A fairly simple C++ code without recursion.
#include <vector>
#include <algorithm>
#include <iterator>
#include <iostream>
#include <string>
// Integer data
void print_all_permutations(std::vector<int> &data) {
std::stable_sort(std::begin(data), std::end(data));
do {
std::copy(data.begin(), data.end(), std::ostream_iterator<int>(std::cout, " ")), std::cout << '\n';
} while (std::next_permutation(std::begin(data), std::end(data)));
}
// Character data (string)
void print_all_permutations(std::string &data) {
std::stable_sort(std::begin(data), std::end(data));
do {
std::copy(data.begin(), data.end(), std::ostream_iterator<char>(std::cout, " ")), std::cout << '\n';
} while (std::next_permutation(std::begin(data), std::end(data)));
}
int main()
{
std::vector<int> v({1,2,3,4});
print_all_permutations(v);
std::string s("abcd");
print_all_permutations(s);
return 0;
}
We can find next permutation of a sequence in linear time.
Here is an answer from #le_m. It might be of help.
The following very efficient algorithm uses Heap's method to generate all permutations of N elements with runtime complexity in O(N!):
function permute(permutation) {
var length = permutation.length,
result = [permutation.slice()],
c = new Array(length).fill(0),
i = 1, k, p;
while (i < length) {
if (c[i] < i) {
k = i % 2 && c[i];
p = permutation[i];
permutation[i] = permutation[k];
permutation[k] = p;
++c[i];
i = 1;
result.push(permutation.slice());
} else {
c[i] = 0;
++i;
}
}
return result;
}
console.log(JSON.stringify(permute([1, 2, 3, 4])));
You can use a stack to go through permutations.
This approach is ideal when dealing with trees or other problems while not leaning on recursion.
You will need to make adjustments to not have any duplicate values.
type permutation = [string, string[]]
function p(str: string): string[]{
const res: string[] = []
const stack: permutation[] = [["", str.split('')]]
while(stack.length){
const [head, tail] = stack.pop()
if(!tail.length){
res.push(head)
continue
}
for(let i = 0; i < tail.length; i++){
let newTail = tail.slice()
newTail.splice(i, 1)
stack.push([head + tail[i], newTail])
}
}
return res
}

Generate unique number based on string input in Javascript

In the past I have made a function that generates an unique id (number) from a string. Today I discover that it is not as unique as should be. Never saw a problem before with it. Today two different inputs generates the same id (number).
I use the same technique in Delphi, C++, PHP and Javascript to generate the same id's so there is no difference when different languages are involved to a project. For example this can be handy to communicate, for HTML id's, tempfiles etc.
In general, what I do is calculate a CRC16 of a string, add the sum and return it.
For example, these two strings generate the same id (number):
o.uniqueId( 'M:/Mijn Muziek/Various Artists/Revs & ElBee - Tell It To My Heart.mp3' );
o.uniqueId( 'M:/Mijn Muziek/Various Artists/Dwight Yoakam - The Back Of Your Hand.Mp3');
They both generates an id of 224904.
The following example is a javascript example. My question is, how can i avoid (with a little change) that it generates a duplicate? (In case you might wonder what 'o.' means, it is the object where these functions belongs to):
o.getCrc16 = function(s, bSumPos) {
if(typeof s !== 'string' || s.length === 0) {
return 0;
}
var crc = 0xFFFF,
L = s.length,
sum = 0,
x = 0,
j = 0;
for(var i = 0; i < L; i++) {
j = s.charCodeAt(i);
sum += ((i + 1) * j);
x = ((crc >> 8) ^ j) & 0xFF;
x ^= x >> 4;
crc = ((crc << 8) ^ (x << 12) ^ (x << 5) ^ x) & 0xFFFF;
}
return crc + ((bSumPos ? 1 : 0) * sum);
}
o.uniqueId = function(s, bres) {
if(s == undefined || typeof s != 'string') {
if(!o.___uqidc) {
o.___uqidc = 0;
} else {
++o.___uqidc;
}
var od = new Date(),
i = s = od.getTime() + '' + o.___uqidc;
} else {
var i = o.getCrc16(s, true);
}
return((bres) ? 'res:' : '') + (i + (i ? s.length : 0));
};
How can I avoid duplicates with use of a little change to the code?
All right, did allot of testing and come to this. A relative short unique id generated by the following:
o.lz = function(i,c)
{
if( typeof c != 'number' || c <= 0 || (typeof i != 'number' && typeof i != 'string') )
{ return i; }
i+='';
while( i.length < c )
{ i='0'+i; }
return i;
}
o.getHashCode = function(s)
{
var hash=0,c=(typeof s == 'string')?s.length:0,i=0;
while(i<c)
{
hash = ((hash<<5)-hash)+s.charCodeAt(i++);
//hash = hash & hash; // Convert to 32bit integer
}
return ( hash < 0 )?((hash*-1)+0xFFFFFFFF):hash; // convert to unsigned
};
o.uniqueId = function( s, bres )
{
if( s == undefined || typeof s != 'string' )
{
if( !o.___uqidc )
{ o.___uqidc=0; }
else { ++o.___uqidc; }
var od = new Date(),
i = s = od.getTime()+''+o.___uqidc;
}
else { var i = o.getHashCode( s ); }
return ((bres)?'res:':'')+i.toString(32)+'-'+o.lz((s.length*4).toString(16),3);
};
Examples:
o.uniqueId( 'M:/Mijn Muziek/Various Artists/Revs & ElBee - Tell It To My Heart.mp3' );
o.uniqueId( 'M:/Mijn Muziek/Various Artists/Dwight Yoakam - The Back Of Your Hand.Mp3');
Will produce the following id's:
dh8qi9t-114
je38ugg-120
For my purpose it seems to be unique enough, also the extra length adds some more uniqueness. Test it on filesystem with approx 40.000 mp3 files and did not found any collision.
If you think this is not the way to go, please let me know.
You should increase the number of bits created by your hash function. Assuming that your hash function approximately uniform over the space, you can mathematically derive the probability of observing a collision.
This is strongly related to the birthday paradox. In the case of CRC16, where the hash value is 17 bits (though your implementation may have a mistake; I don't see how you obtained 224094 as that is greater than 2^17), you will have a collision probability above 50% when you store more than approximately 2^8 items. In addition, CRC is not really a great hashing function because it's meant for error detection, not uniform hashing.
This table shows mathematical probabilities of collision based on hash length. For example, if you have a 128-bit hash key, you can store up to 10^31 elements before the collision probability increases beyond 10^-15. As a comparison, this probability is lower than that of your hard drive failing, or maybe your computer being zapped by lightning, so a safe number to use.
Just increase your hash length based on the number of strings you are planning to identify, and a pick a collision probability that is acceptable to you.

Categories