I want to reject user input if it contains 2 sequential numbers or characters ,for example 1234,jkl, zyxw and if it contains more than 1 same numbers or characters like aaer,0000,aabb,pp22. Thank you for insights. I have regex for the second one but dont know how to combine the two expressions:
"([a-zA-Z0-9])\\1{1,}"
Doing this in regex is neither sound nor practical. However, you can easily check if your input contains a sequential (abc.. or cba) pattern using code like that:
function isSequencial(input) {
var numpattern = '0123456789012345789'; // match ascending/descending sequence of numbers.
var charpattern = 'ABCDEFGHIJKLMNOPQRSTUVWXYZYXWVUTSRQPONMLKJIHGFEDCBA'; // match ascending/descending sequence of letters.
for (var i = 0; i < input.length-1; i++) {
var shard = input.substring(i,i+2);
if(numpattern.indexOf(shard) != -1) {
console.log('sequential number pattern detected: ' + shard);
return true;
}
if (charpattern.indexOf(shard.toUpperCase()) != -1) {
console.log('sequential letter pattern detected: ' +shard);
return true;
}
}
return false;
}
console.log("isSequencial(a234):" + isSequencial("a234"));
console.log("isSequencial(azyx):" + isSequencial("azyx"));
console.log("isSequencial(xbc):" + isSequencial("xbc"));
console.log("isSequencial(2435):" + isSequencial("2435"));
This code can be optimized but is easy to understand and maintain since it does not try to do multiple things at once. You should be able to combine this with your existing approach.
The simplest solution for your first requirement would be to parse it, as with a regex it will be not that easy to set up, if at all possible.
Here I used charCodeAt (and check for both sequence/equal and duplicates characters)
var input1 = "1543abc3";
var input2 = "cba23DEf";
var input3 = "ba2354cd";
console.log('test 1');
testit(input1.split(''));
console.log('test 2');
testit(input2.split(''));
console.log('test 3');
testit(input3.split(''));
function testit (arr) {
var prev = arr[0].charCodeAt(0) + 1, prev2 = -1;
for (var i = 1; i < arr.length; i++) {
var arritem = arr[i].charCodeAt(0);
if ( (arritem == prev && arritem == (prev2+1)) || // abc
(arritem == (prev-2) && arritem == (prev2-3)) // cba
) {
console.log(' - sequence, more than 2: ', arr[i-2], arr[i-1], arr[i] );
//return false;
}
if (arr.indexOf(arr[i-1],i) > -1) {
console.log(' - duplicate, more than 1: ', arr[i-1] );
//return false;
}
prev2 = prev;
prev = arr[i].charCodeAt(0) + 1;
}
//return true;
}
Given string in the form:
'"abc",ab(),c(d(),e()),f(g(),zyx),h(123)'
How can I split it to get the below array format:
abc
ab()
c(d(),e())
f(g(),zyx)
h(123)
I have tried normal javascript split, however it doesn't work as desired. Trying Regular Expression but not yet successful.
You can keep track of the parentheses, and add those expressions when the left and right parens equalize.
For example-
function splitNoParen(s){
var left= 0, right= 0, A= [],
M= s.match(/([^()]+)|([()])/g), L= M.length, next, str= '';
for(var i= 0; i<L; i++){
next= M[i];
if(next=== '(')++left;
else if(next=== ')')++right;
if(left!== 0){
str+= next;
if(left=== right){
A[A.length-1]+=str;
left= right= 0;
str= '';
}
}
else A=A.concat(next.match(/([^,]+)/g));
}
return A;
}
var s1= '"abc",ab(),c(d(),e()),f(g(),zyx),h(123)';
splitNoParen(s1).join('\n');
/* returned value: (String)
"abc"
ab()
c(d(),e())
f(g(),zyx)
h(123)
*/
This might be not the best or more refined solution, and also maybe won't fit every single possibility, but based on your example it works:
var data = '"abc",ab(),c(d(),e()),f(g(),zyx),h(123)';
// Create a preResult splitting the commas.
var preResult = data.replace(/"/g, '').split(',');
// Create an empty result.
var result = [];
for (var i = 0; i < preResult.length; i++) {
// Check on every preResult if the number of parentheses match.
// Opening ones...
var opening = preResult[i].match(/\(/g) || 0;
// Closing ones...
var closing = preResult[i].match(/\)/g) || 0;
if (opening != 0 &&
closing != 0 &&
opening.length != closing.length) {
// If the current item contains a different number of opening
// and closing parentheses, merge it with the next adding a
// comma in between.
result.push(preResult[i] + ',' + preResult[i + 1]);
i++;
} else {
// Leave it as it is.
result.push(preResult[i]);
}
}
Demo
For future reference, here's another approach to top-level splitting, using string.replace as a control flow operator:
function psplit(s) {
var depth = 0, seg = 0, rv = [];
s.replace(/[^(),]*([)]*)([(]*)(,)?/g,
function (m, cls, opn, com, off, s) {
depth += opn.length - cls.length;
var newseg = off + m.length;
if (!depth && com) {
rv.push(s.substring(seg, newseg - 1));
seg = newseg;
}
return m;
});
rv.push(s.substring(seg));
return rv;
}
console.log(psplit('abc,ab(),c(d(),e()),f(g(),zyx),h(123)'))
["abc", "ab()", "c(d(),e())", "f(g(),zyx)", "h(123)"]
Getting it to handle quotes as well would not be too complicated, but at some point you need to decide to use a real parser such as jison, and I suspect that would be the point. In any event, there's not enough detail in the question to know what the desired handling of double quotes is.
You can't use .split for this, but instead you'll have to write a small parser like this:
function splitNoParen(s){
let results = [];
let next;
let str = '';
let left = 0, right = 0;
function keepResult() {
results.push(str);
str = '';
}
for(var i = 0; i<s.length; i++) {
switch(s[i]) {
case ',':
if((left === right)) {
keepResult();
left = right = 0;
} else {
str += s[i];
}
break;
case '(':
left++;
str += s[i];
break;
case ')':
right++;
str += s[i];
break;
default:
str += s[i];
}
}
keepResult();
return results;
}
var s1= '"abc",ab(),c(d(),e()),f(g(),zyx),h(123)';
console.log(splitNoParen(s1).join('\n'));
var s2='cats,(my-foo)-bar,baz';
console.log(splitNoParen(s2).join('\n'));
Had a similar issue and existing solutions were hard to generalize. So here's another parser that's a bit more readable and easier to extend to your personal needs. It'll also work with curly braces, brackets, normal braces, and strings of any type. License is MIT.
/**
* This function takes an input string and splits it by the given token, but only if the token is not inside
* braces of any kind, or a string.
* #param {string} input The string to split.
* #param {string} split_by Must be a single character.
* #returns {string[]} An array of split parts without the split_by character.
*/
export function parse_split(input:string, split_by:string = ",") : string[]
{
// Javascript has 3 types of strings
const STRING_TYPES = ["'","`","\""] as const;
// Some symbols can be nested, like braces, and must be counted
const state = {"{":0,"[":0,"(":0};
// Some cannot be nested, like a string, and just flip a flag.
// Additionally, once the string flag has been flipped, it can only be unflipped
// by the same token.
let string_state : (typeof STRING_TYPES)[number] | undefined = undefined
// Nestable symbols come in sets, usually in pairs.
// These sets increase or decrease the state, depending on the symbol.
const pairs : Record<string,[keyof typeof state,number]> = {
"{":["{",1],
"}":["{",-1],
"[":["[",1],
"]":["[",-1],
"(":["(",1],
")":["(",-1]
}
let start = 0;
let results = [];
let length = input.length;
for(let i = 0; i < length; ++i)
{
let char = input[i];
// Backslash escapes the next character. We directly skip 2 characters by incrementing i one extra time.
if(char === "\\")
{
i++;
continue;
}
// If the symbol exists in the single/not nested state object, flip the corresponding state flag.
if(char == string_state)
{
string_state = undefined;
console.log("Closed string ", string_state);
}
// if it's not in a string, but it's a string opener, remember the string type in string_state.
else if(string_state === undefined && STRING_TYPES.includes(char as typeof STRING_TYPES[number]))
{
string_state = char as typeof STRING_TYPES[number];
}
// If it's not in a string, and if it's a paired symbol, increase or decrease the state based on our "pairs" constant.
else if(string_state === undefined && (char in pairs) )
{
let [key,value] = pairs[char];
state[key] += value;
}
// If it's our split symbol...
else if(char === split_by)
{
// ... check whether any flags are active ...
if(Object.entries(state).every(([k,v])=>v == 0) && (string_state === undefined))
{
// ... if not, then this is a valid split.
results.push(input.substring(start,i))
start = i+1;
}
}
}
// Add the last segment if the string didn't end in the split_by symbol, otherwise add an empty string
if(start < input.length)
{
results.push(input.substring(start,input.length))
}
else
results.push("");
return results;
}
With this regex, it makes the job:
const regex = /,(?![^(]*\))/g;
const str = '"abc",ab(),c(d(),e()),f(g(),zyx),h(123)';
const result = str.split(regex);
console.log(result);
Javascript
var str='"abc",ab(),c(d(),e()),f(g(),zyx),h(123)'
str.split('"').toString().split(',').filter(Boolean);
this should work
I have an expression say
log(1,3)+4,5+max(7,8,9)
where comma is being used two ways.
1- In "log(1,3)+4,5" comma is being used in place of dot(.) or decimal sign.i.e. "log(1,3)+4,5" is equivalent to "log(1.3)+4.5".
2- In max(7,8,9) it is being used as number separator. i.e. this outcome of this is 9 ; the maximum number.
My problem is to substitute comma; which is being used as decimal separator; with decimal but this should not affect max(7,8,9). i.e. I need to convert above expression to
log(1.3)+4.5+max(7,8,9)
What I tried-
function substitute(expr) {
expr.replace(/,/g, function ($`) {
/*some processing here to decide whether comma to be substituted with dot or not.On that basis I will return either dot or comma.*/
}
But how can I pass $` value to associated function
or
Is it possible to do this in javascript.
expr.replace(/,/g,function ($`) {
if yes then how?
Your language is ambiguous.
max(8,1,8,2)
Does this return 8, 8,1 or 8,2?
Your language also doesn't look regular, so you can't parse it with a regular expression, you need the context. If something like this is allowed:
max(1,max(2,3)) // 3?
Assuming you can get rid of the ambiguity, you could write a parser to do the context detection.
This could be a solution :
function myFilter(string) {
// save all functions and signs
var functions = [];
var regExp = /[+,-]max\(([^\)]+)\)/;
matches = true;
while (matches !== null) {
var matches = regExp.exec(string);
if (matches !== null) {
functions.push(matches[0]);
string = string.replace(matches[0], '');
}
}
// replace all remaining commas with dots
string = string.replace(/,/g , ".");
for (i in functions) {
string += functions[i];
}
return string;
}
var s = '1,3+4,5+max(7,8,9)-max(2,3,5)';
var filteredString = myFilter(s);
jsFiddle Demo
This currently works with multiple max functions but only + and - signs. It could be improved with *, / and more... You will have to find the good regex.
Try the below using Javascript. Hope this helps you in logic.
DEMO HERE
var value = "log(1,3)-4,5+max(7,8,9)";
var val = '';
var splitValue, appendSym;
if (value.indexOf("+") != -1)
{
splitValue = value.split("+");
appendSym = "+";
}
else if(value.indexOf("-") != -1)
{
splitValue = value.split("-");
appendSym = "-";
}
else if(value.indexOf("*") != -1)
{
splitValue = value.split("*");
appendSym = "*";
}
else
{
splitValue = value.split("/");
appendSym = "/";
}
var length = splitValue.length;
for (var i = 0; i < length; i++) {
if (val) val += appendSym;
var strrep = splitValue[i].replace(/,/g,".");
if (splitValue[i].indexOf("max") != -1 || splitValue[i].indexOf("min") != -1)
{
val+=splitValue[i];
}
else
{
val+=strrep;
}
}
alert(val);
The output for the above code is log(1.3)-4.5+max(7,8,9)
I have a string that looks something like the following 'test:1;hello:five;just:23'. With this string I need to be able to do the following.
....
var test = MergeTokens('test:1;hello:five;just:23', 'yes:23;test:567');
...
The end result should be 'test:567;hello:five;just:23;yes:23' (note the exact order of the tokens is not that important).
Just wondering if anyone has any smart ideas of how to go about this. I was thinking a regex replace on each of the tokens on right and if a replace didn't occur because there was not match just append it. But maybe there is better way.
Cheers
Anthony
Edit: The right side should override the left. The left being what was originally there and the right side being the new content. Another way of looking at it, is that you only keep the tokens on the left if they don't exist on the right and you keep all the tokens on the right.
#Ferdinand
Thanks for the reply. The problem is the efficiency with which the solution you proposed. I was initially thinking down similar lines but discounted it due to the O(n*z) complexity of the merge (where n and z is the number tokens on the left and right respectively) let alone the splitting and joining.
Hence why I was trying to look down the path of a regex. Maybe behind the scenes, regex is just as bad or worse, but having a regex which removes any token from the left string that exists on the right (O(n) for the total amount of token on the right) and then just add the 2 string together (i.e. vat test = test1 + test2) seems more efficient. thanks
I would use join() and split() to create some utility functions to pack and unpack your token data to an object:
// Unpacks a token string into an object.
function splitTokens(str) {
var data = {}, pairs = str.split(';');
for (var i = 0; i < pairs.length; ++i) {
var pair = pairs[i].split(':');
data[pair[0]] = pair[1];
}
return data;
}
// Packs an object into a token string.
function joinTokens(data) {
var pairs = [];
for (var key in data) {
pairs.push(key + ":" + data[key]);
}
return pairs.join(';');
}
Using these, merging is easy:
// Merges all token strings (supports a variable number of arguments).
function mergeTokens() {
var data = {};
for (var i = 0; i < arguments.length; ++i) {
var d = splitTokens(arguments[i]);
for (var key in d) {
data[key] = d[key];
}
}
return joinTokens(data);
}
The utility functions are also useful if you want to extract some keys (say,"test") and/or check for existence:
var data = splitTokens(str);
if (data["test"] === undefined) {
// Does not exist
} else {
alert("Value of 'test': " + data["test"]);
}
The following is what I ended thiking about. What do you guys recon?
Thanks
Anthony
function Tokenizer(input, tokenSpacer, tokenValueSpacer) {
this.Tokenizer = {};
this.TokenSpacer = tokenSpacer;
this.TokenValueSpacer = tokenValueSpacer;
if (input) {
var TokenizerParts = input.split(this.TokenSpacer);
var i, nv;
for (i = 0; i < TokenizerParts.length; i++) {
nv = TokenizerParts[i].split(this.TokenValueSpacer);
this.Tokenizer[nv[0]] = nv[1];
}
}
}
Tokenizer.prototype.add = function(name, value) {
if (arguments.length == 1 && arguments[0].constructor == Object) {
this.addMany(arguments[0]);
return;
}
this.Tokenizer[name] = value;
}
Tokenizer.prototype.addMany = function(newValues) {
for (nv in newValues) {
this.Tokenizer[nv] = newValues[nv];
}
}
Tokenizer.prototype.remove = function(name) {
if (arguments.length == 1 && arguments[0].constructor == Array) {
this.removeMany(arguments[0]);
return;
}
delete this.Tokenizer[name];
}
Tokenizer.prototype.removeMany = function(deleteNames) {
var i;
for (i = 0; i < deleteNames.length; i++) {
delete this.Tokenizer[deleteNames[i]];
}
}
Tokenizer.prototype.MergeTokenizers = function(newTokenizer) {
this.addMany(newTokenizer.Tokenizer);
}
Tokenizer.prototype.getTokenString = function() {
var nv, q = [];
for (nv in this.Tokenizer) {
q[q.length] = nv + this.TokenValueSpacer + this.Tokenizer[nv];
}
return q.join(this.TokenSpacer);
}
Tokenizer.prototype.toString = Tokenizer.prototype.getTokenString;
i am a few years late, but i think this is what you are looking for:
function MergeTokens(input, replace){
var replaceTokens = replace.split(";");
for(i=0; i<replaceTokens.length; i++){
var pair = replaceTokens[i].split(":");
var result = input;
regString = "\\b" + pair[0] + ":[\\w]*\\b";
var reg = new RegExp(regString);
if(reg.test(result)){
result = result.replace(reg, replaceTokens[i]);
}
else{
result = result + replaceTokens[i];
}
}
return result;
}