Javascript: Regular Expression to parse a formula - javascript

I have been working on a function to parse a formula for some time, but haven't been able to make it work properly. It seems to not always work - it filters some parts of the text but not all.
parseFormula(e) {
var formula = e.value, value = 0.00, tValue = 0.00, tFormula = '', dObj = {};
if(formula !== undefined && formula !== "") {
dObj._formulaIn = formula;
var f = formula.split(/\s/g);
for(var i = 0; i < f.length; i++) {
tFormula = f[i];
// Replacing PI
tFormula = tFormula.replace(/(pi)/gi,Math.PI);
dObj._1_pi_done = tFormula;
// Replacing Squareroot with placeholder
tFormula = tFormula.replace(/(sqrt)/gi,"__sqrt__");
tFormula = tFormula.replace(/(sqr)/gi,"__sqrt__");
tFormula = tFormula.replace(/(kvrt)/gi,"__sqrt__");
tFormula = tFormula.replace(/(kvr)/gi,"__sqrt__");
dObj._2_sqrt_done = tFormula;
// Removing units that may cause trouble
tFormula = tFormula.replace(/(m2||m3||t2||t3||c2||c3)/gi,"");
dObj._3_units_done = tFormula;
// Removing text
tFormula = tFormula.replace(/\D+[^\*\/\+\-]+[^\,\.]/gi,"");
dObj._4_text_done = tFormula;
// Removing language specific decimals
if(Language.defaultLang === "no_NB") {
tFormula = tFormula.replace(/(\.)/gi,"");
tFormula = tFormula.replace(/(\,)/gi,".");
} else {
tFormula = tFormula.replace(/(\,)/gi,"");
}
dObj._5_lang_done = tFormula;
// Re-applying Squareroot
tFormula = tFormula.replace(/(__sqrt__)/g,"Math.sqrt");
dObj._6_sqrt_done = tFormula;
if(tFormula === "") {
f.splice(i,1);
} else {
f[i] = tFormula;
}
dObj._7_splice_done = tFormula;
console.log(dObj);
}
formula = "";
for(var j = 0; j < f.length; j++) {
formula += f[j];
}
try {
value = eval(formula);
}
catch(err) {}
return value === 0 ? 0 : value.toFixed(4);
} else {
return 0;
}
}
I am not sure about any of the RegEx used in this function, hence why I am asking for help. For example, I am not sure if /(pi)/ is the right way to get the exact text "pi" and replace it with 3.141.
(I am using eval at the moment, but it's merely used for development)
Any help appreciated.
Edit:
The Formula I am trying to parse is a user input formula. Where he/she would type something like: 2/0.6 pcs of foo * pi bar + sqrt(4) foobar. Where I would want it to strip all the non-math letters and calculate the rest. Meaning the above formula would be interpreted as (2/0.6) * 3.141 + Math.sqrt(4) => 12.47
Edit 2:
e is a ExtJS object, passed through by a field in a grid, it contains the following variables:
colIdx (int)
column (Ext.grid.column.Column)
field (string)
grid (Ext.grid.Panel)
originalValue (string)
record (Ext.data.Model)
row (css selector)
rowIdx (int)
store (Ext.data.Store)
value (string)
view (Ext.grid.View)
Am currently unable to get the JSFiddle to work properly.

It's probably easier to tokenize the expression you want to parse. When tokenized it's way easier to read that stream of tokens and build your own expressions.
I've put up a demo on jsFiddle which can parse your given formula
In the demo I used this Tokenizer class and tokens to build a TokenStream from the formula.
function Tokenizer() {
this.tokens = {};
// The regular expression which matches a token per group.
this.regex = null;
// Holds the names of the tokens. Index matches group. See buildExpression()
this.tokenNames = [];
}
Tokenizer.prototype = {
addToken: function(name, expression) {
this.tokens[name] = expression;
},
tokenize: function(data) {
this.buildExpression(data);
var tokens = this.findTokens(data);
return new TokenStream(tokens);
},
buildExpression: function (data) {
var tokenRegex = [];
for (var tokenName in this.tokens) {
this.tokenNames.push(tokenName);
tokenRegex.push('('+this.tokens[tokenName]+')');
}
this.regex = new RegExp(tokenRegex.join('|'), 'g');
},
findTokens: function(data) {
var tokens = [];
var match;
while ((match = this.regex.exec(data)) !== null) {
if (match == undefined) {
continue;
}
for (var group = 1; group < match.length; group++) {
if (!match[group]) continue;
tokens.push({
name: this.tokenNames[group - 1],
data: match[group]
});
}
}
return tokens;
}
}
TokenStream = function (tokens) {
this.cursor = 0;
this.tokens = tokens;
}
TokenStream.prototype = {
next: function () {
return this.tokens[this.cursor++];
},
peek: function (direction) {
if (direction === undefined) {
direction = 0;
}
return this.tokens[this.cursor + direction];
}
}
Defined tokens
tokenizer.addToken('whitespace', '\\s+');
tokenizer.addToken('l_paren', '\\(');
tokenizer.addToken('r_paren', '\\)');
tokenizer.addToken('float', '[0-9]+\\.[0-9]+');
tokenizer.addToken('int', '[0-9]+');
tokenizer.addToken('div', '\\/');
tokenizer.addToken('mul', '\\*');
tokenizer.addToken('add', '\\+');
tokenizer.addToken('constant', 'pi|PI');
tokenizer.addToken('id', '[a-zA-Z_][a-zA-Z0-9_]*');
With the above tokens defined the tokenizer can recognize everything in your formula. When the formula
2/0.6 pcs of foo * pi bar + sqrt(4) foobar
is tokenized the result would be a token stream similar to
int(2), div(/), float(0.6), whitespace( ), id(pcs), whitespace( ), id(of), whitespace( ), id(foo), whitespace( ), mul(*), whitespace( ), constant(pi), whitespace( ), id(bar), whitespace( ), add(+), whitespace( ), id(sqrt), l_paren((), int(4), r_paren()), whitespace( ), id(foobar)

You cannot really use a regular expression to match a formula. Formulae are a context-free language and regular expressions are limited to regular languages, the latter being a subset of the former. There are a number of algorithms for recognizing context-free languages such as CYK and LL parsers. I don't recommend studying those if you already haven't since the topic is quite large.
What you can do quickly, efficiently and easy though, is to attempt to calculate the formula using Reverse Polish Notation (RPN) (use the Shunting Yard algorithm to convert your formula to RPN). If the attempt fails (due to parenthesis not maching, invalid functions / constants, w/e), clearly the text is not a formula, otherwise all is good. Shunting yard is not a particularly difficult algorithm and you should have no trouble implementing it. Even if you do, the wikipedia page I linked above has pseudo code and there a good number of questions in SO as well to help you.

Related

Recursive parser using split in javascript

I have an algorithm where the user will enter a string and I will parse it into an array of 2+ dimensions. So, for example, the user can enter 1,2,3;4,5,6 and set the text to be parsed by the semicolon and the comma. The first pass through will create an array with 2 entries. The second pass through will create a 3 entry array in both prior spots.
The user can add or remove the number of text items to be used to parse the original string such as the semicolon or comma, meaning the resulting array can have as many dimensions as parsing items.
This doesn't seem like a difficult problem, but I have run into some snags.
Here is my code so far.
vm.parsers = [';', ','];
vm.inputString = "1,2,3,4,5;6,7,8,9,10";
function parseDatasetText( )
{
vm.real = vm.parseMe( vm.inputString, 0);
};
function parseMe( itemToParse, indexToParse )
{
if ( indexToParse < vm.parsers.length )
{
console.log('Parsing *'+itemToParse+'* with '+vm.parsers[indexToParse]);
var tempResults = itemToParse.split( vm.parsers[indexToParse] );
for (var a=0; a<tempResults.length; a++)
{
console.log('Pushing '+tempResults[a]);
tempResults[a] = vm.parseMe( tempResults[a], parseInt( indexToParse ) + 1 )
console.log('This value is '+tempResults[a]);
}
}else
{
console.log('Returning '+itemToParse);
return itemToParse
}
};
As you can see from the console logs, the algorithm spits out an undefined after the last parse, and the final answer is undefined.
Maybe I just haven't slept enough, but I was thinking that the array would recursively populate via the splits?
Thanks
function parseDatasetText(){
//composing parser from right to left into a single function
//that applies them from left to right on the data
var fn = vm.parsers.reduceRight(
(nextFn, delimiter) => v => String(v).split(delimiter).map(nextFn),
v => v
);
return fn( vm.inputString );
}
Don't know what else to add.
You can use a simple recursive function like the following (here an example with 3 different delimiters):
function multiSplit(xs, delimiters) {
if (!delimiters.length) return xs;
return xs.split(delimiters[0]).map(x => multiSplit(x, delimiters.slice(1)));
}
data = '1:10,2:20,3:30;4:40,5:50,6:60';
res = multiSplit(data, [';', ',', ':']);
console.log(res)
The following function should suit your requirements, please let me know if not
var parsers = [';', ',', ':'],
inputString = "1:a,2:b,3:c,4:d,5:e;6:f,7:g,8:h,9:i,10:j",
Result = [];
function Split(incoming) {
var temp = null;
for (var i = 0; i < parsers.length; i++)
if (incoming.indexOf(parsers[i]) >= 0) {
temp = incoming.split(parsers[i]);
break;
}
if (temp == null) return incoming;
var outgoing = [];
for (var i = 0; i < temp.length; i++)
outgoing[outgoing.length] = Split(temp[i])
return outgoing;
}
Result = Split(inputString);
try it on https://jsfiddle.net/cgy7nre1/
Edit 1 -
Added another inputString and another set of parsers: https://jsfiddle.net/cgy7nre1/1/
Did you mean this?
var inputString = "1,2,3,4,5;6,7,8,9,10";
var array=inputString.split(';');
for (var i=0;i<array.length;i++){
array[i]=array[i].split(',');
}
console.log(array);

Find smallest substring containing a given set of letters in a larger string

Say you have the following string:
FJKAUNOJDCUTCRHBYDLXKEODVBWTYPTSHASQQFCPRMLDXIJMYPVOHBDUGSMBLMVUMMZYHULSUIZIMZTICQORLNTOVKVAMQTKHVRIFMNTSLYGHEHFAHWWATLYAPEXTHEPKJUGDVWUDDPRQLUZMSZOJPSIKAIHLTONYXAULECXXKWFQOIKELWOHRVRUCXIAASKHMWTMAJEWGEESLWRTQKVHRRCDYXNT
LDSUPXMQTQDFAQAPYBGXPOLOCLFQNGNKPKOBHZWHRXAWAWJKMTJSLDLNHMUGVVOPSAMRUJEYUOBPFNEHPZZCLPNZKWMTCXERPZRFKSXVEZTYCXFRHRGEITWHRRYPWSVAYBUHCERJXDCYAVICPTNBGIODLYLMEYLISEYNXNMCDPJJRCTLYNFMJZQNCLAGHUDVLYIGASGXSZYPZKLAWQUDVNTWGFFY
FFSMQWUNUPZRJMTHACFELGHDZEJWFDWVPYOZEVEJKQWHQAHOCIYWGVLPSHFESCGEUCJGYLGDWPIWIDWZZXRUFXERABQJOXZALQOCSAYBRHXQQGUDADYSORTYZQPWGMBLNAQOFODSNXSZFURUNPMZGHTAJUJROIGMRKIZHSFUSKIZJJTLGOEEPBMIXISDHOAIFNFEKKSLEXSJLSGLCYYFEQBKIZZTQQ
XBQZAPXAAIFQEIXELQEZGFEPCKFPGXULLAHXTSRXDEMKFKABUTAABSLNQBNMXNEPODPGAORYJXCHCGKECLJVRBPRLHORREEIZOBSHDSCETTTNFTSMQPQIJBLKNZDMXOTRBNMTKHHCZQQMSLOAXJQKRHDGZVGITHYGVDXRTVBJEAHYBYRYKJAVXPOKHFFMEPHAGFOOPFNKQAUGYLVPWUJUPCUGGIXGR
AMELUTEPYILBIUOCKKUUBJROQFTXMZRLXBAMHSDTEKRRIKZUFNLGTQAEUINMBPYTWXULQNIIRXHHGQDPENXAJNWXULFBNKBRINUMTRBFWBYVNKNKDFR
I'm trying to find the smallest substring containing the letters ABCDA.
I tried a regex approach.
console.log(str.match(/[A].*?[B].*?[C].*?[D].*?[A]/gm).sort((a, b) => a.length - b.length)[0]);
This works, but it only find strings where ABCDA appear (in that order). Meaning it won't find substring where the letters appear in a order like this: BCDAA
I'm trying to change my regex to account for this. How would I do that without using | and type out all the different cases?
You can't.
Let's consider a special case: Assume the letters you are looking for are A, A, and B. At some point in your regexp there will certainly be a B. However, the parts to the left and to the right of the B are independent of each other, so you cannot refer from one to the other. How many As are matched in the subexpression to the right of the B depends on the number of As being already matched in the left part. This is not possible with regular expressions, so you will have to unfold all the different orders, which can be many!
Another popular example that illustrates the problem is to match opening brackets with closing brackets. It's not possible to write a regular expression asserting that in a given string a sequence of opening brackets is followed by a sequence of closing brackets of the same length. The reason for this is that to count the brackets you would need a stack machine in contrast to a finite state machine but regular expressions are limited to patterns that can be matched using FSMs.
This algorithm doesn't use a regex, but found both solutions as well.
var haystack = 'FJKAUNOJDCUTCRHBYDLXKEODVBWTYPTSHASQQFCPRMLDXIJMYPVOHBDUGSMBLMVUMMZYHULSUIZIMZTICQORLNTOVKVAMQTKHVRIFMNTSLYGHEHFAHWWATLYAPEXTHEPKJUGDVWUDDPRQLUZMSZOJPSIKAIHLTONYXAULECXXKWFQOIKELWOHRVRUCXIAASKHMWTMAJEWGEESLWRTQKVHRRCDYXNTLDSUPXMQTQDFAQAPYBGXPOLOCLFQNGNKPKOBHZWHRXAWAWJKMTJSLDLNHMUGVVOPSAMRUJEYUOBPFNEHPZZCLPNZKWMTCXERPZRFKSXVEZTYCXFRHRGEITWHRRYPWSVAYBUHCERJXDCYAVICPTNBGIODLYLMEYLISEYNXNMCDPJJRCTLYNFMJZQNCLAGHUDVLYIGASGXSZYPZKLAWQUDVNTWGFFYFFSMQWUNUPZRJMTHACFELGHDZEJWFDWVPYOZEVEJKQWHQAHOCIYWGVLPSHFESCGEUCJGYLGDWPIWIDWZZXRUFXERABQJOXZALQOCSAYBRHXQQGUDADYSORTYZQPWGMBLNAQOFODSNXSZFURUNPMZGHTAJUJROIGMRKIZHSFUSKIZJJTLGOEEPBMIXISDHOAIFNFEKKSLEXSJLSGLCYYFEQBKIZZTQQXBQZAPXAAIFQEIXELQEZGFEPCKFPGXULLAHXTSRXDEMKFKABUTAABSLNQBNMXNEPODPGAORYJXCHCGKECLJVRBPRLHORREEIZOBSHDSCETTTNFTSMQPQIJBLKNZDMXOTRBNMTKHHCZQQMSLOAXJQKRHDGZVGITHYGVDXRTVBJEAHYBYRYKJAVXPOKHFFMEPHAGFOOPFNKQAUGYLVPWUJUPCUGGIXGRAMELUTEPYILBIUOCKKUUBJROQFTXMZRLXBAMHSDTEKRRIKZUFNLGTQAEUINMBPYTWXULQNIIRXHHGQDPENXAJNWXULFBNKBRINUMTRBFWBYVNKNKDFR';
var needle = 'ABCDA'; // the order of letters doesn't matter
var letters = {};
needle.split('').forEach(function(ch) {
letters[ch] = letters[ch] || 0;
letters[ch]++;
});
var shortestSubstringLength = haystack.length;
var shortestSubstrings = []; // storage for found substrings
var startingPos = 0;
var length;
var currentPos;
var notFound;
var letterKeys = Object.keys(letters); // unique leters
do {
lettersLeft = JSON.parse(JSON.stringify(letters)); // copy letters count object
notFound = false;
posStart = haystack.length;
posEnd = 0;
letterKeys.forEach(function(ch) {
currentPos = startingPos;
while (!notFound && lettersLeft[ch] > 0) {
currentPos = haystack.indexOf(ch, currentPos);
if (currentPos >= 0) {
lettersLeft[ch]--;
posStart = Math.min(currentPos, posStart);
posEnd = Math.max(currentPos, posEnd);
currentPos++;
} else {
notFound = true;
}
}
});
if (!notFound) {
length = posEnd - posStart + 1;
startingPos = posStart + 1; // starting position for next iteration
}
if (!notFound && length === shortestSubstringLength) {
shortestSubstrings.push(haystack.substr(posStart, length));
}
if (!notFound && length < shortestSubstringLength) {
shortestSubstrings = [haystack.substr(posStart, length)];
shortestSubstringLength = length;
}
} while (!notFound);
console.log(shortestSubstrings);
Maybe not as clear as using regex could be (well, for me regex are never really clear :D ) you can use brute force (not so brute)
Create an index of "valid" points of your string (those with the letters you want) and iterate with a double loop over it getting substrings containing at least 5 of those points, checking that they are valid solutions. Maybe not the most efficient way, but easy to implement, to understand, and probably to optimize.
var haystack="UGDVWUDDPRQLUZMSZOJPSIKAIHLTONYXAULECXXKWFQOIKELWOHRVRUCXIAASKHMWTMAJEWGEESLWRTQKVHRRCDYXNTLDSUPXMQTQDFAQAPYBGXPOLOCLFQNGNKPKOBHZWHRXAWAWJKMTJSLDLNHMUGVVOPSAMRUJEYUOBPFNEHPZZCLPNZKWMTCXERPZRFKSXVEZTYCXFRHRGEITWHRRYPWSVAYBUHCERJXDCYAVICPTNBGIODLYLMEYLISEYNXNMCDPJJRCTLYNFMJZQNCLAGHUDVLYIGASGXSZYPZKLAWQUDVNTWGFFYFFSMQWUNUPZRJMTHACFELGHDZEJWFDWVPYOZEVEJKQWHQAHOCIYWGVLPSHFESCGEUCJGYLGDWPIWIDWZZXRUFXERABQJOXZALQOCSAYBRHXQQGUDADYSORTYZQPWGMBLNAQOFODSNXSZFURUNPMZGHTAJUJROIGMRKIZHSFUSKIZJJTLGOEEPBMIXISDHOAIFNFEKKSLEXSJLSGLCYYFEQBKIZZTQQXBQZAPXAAIFQEIXELQEZGFEPCKFPGXULLAHXTSRXDEMKFKABUTAABSLNQBNMXNEPODPGAORYJXCHCGKECLJVRBPRLHORREEIZOBSHDSCETTTNFTSMQPQIJBLKNZDMXOTRBNMTKHHCZQQMSLOAXJQKRHDGZVGITHYGVDXRTVBJEAHYBYRYKJAVXPOKHFFMEPHAGFOOPFNKQAUGYLVPWUJUPCUGGIXGR";
var needle="ABCD";
var size=haystack.length;
var candidate_substring="";
var minimal_length=size;
var solutions=new Array();
var points=Array();
for(var i=0;i<size;i++){
if(needle.indexOf(haystack[i])>-1) points.push(i);
}
var limit_i= points.length-4;
var limit_k= points.length;
for (var i=0;i<limit_i;i++){
for(var k=i;k<limit_k;k++){
if(points[k]-points[i]+1<=minimal_length){
candidate_substring=haystack.substr(points[i],points[k]-points[i]+1);
if(is_valid(candidate_substring)){
solutions.push(candidate_substring);
if(candidate_substring.length < minimal_length) minimal_length=candidate_substring.length;
}
}
}
}
document.write('<p>Solution length:'+minimal_length+'<p>');
for(var i=0;i<solutions.length;i++){
if(solutions[i].length<=minimal_length) document.write('<p>Solution:'+solutions[i]+'<p>');
}
function is_valid(candidate_substring){
//verify we've got all characters
for(var j=0;j<candidate_substring.length;j++){
if(candidate_substring.indexOf(needle.charAt(j))<0) return false;
}
//...and verify we have two "A"
if(candidate_substring.indexOf("A")==candidate_substring.lastIndexOf("A")) return false;
return true;
}
Just had this problem in an interview as a coding assignment and came up with another solution, (it's not as optimal as the one above but maybe it's easier to understand).
function MinWindowSubstring(strArr) {
const N = strArr[0];
const K = strArr[1];
const letters = {};
K.split('').forEach( (character) => {
letters[character] = letters[character] ? letters[character] + 1 : 1;
});
let possibleSequencesList = [];
const letterKeys = Object.keys(letters);
for(let i=0; i< N.length; i++) {
const char = N[i];
if (new String(letterKeys).indexOf(char) !== -1) {
// found a character in the string
// update all previus sequences
possibleSequencesList.forEach((seq) => {
if(!seq.sequenceComplete) {
seq[char] = seq[char]-1;
seq.lastIndex = i;
// check if sequence is complete
var sequenceComplete = true;
letterKeys.forEach( (letter) => {
if(seq[letter] > 0) {
sequenceComplete = false;
}
});
seq.sequenceComplete = sequenceComplete
}
})
// create a new sequence starting from it
const newSeq = {
startPoint: i,
lastIndex: i,
sequenceComplete: false,
...letters
}
newSeq[char] = newSeq[char]-1;
possibleSequencesList.push(newSeq);
}
}
// cleanup sequences
let sequencesList = possibleSequencesList.filter(sequence => sequence.sequenceComplete);
let output = [];
let minLength = N.length;
// find the smalles one
sequencesList.forEach( seq => {
if( (seq.lastIndex - seq.startPoint) < minLength) {
minLength = seq.lastIndex - seq.startPoint;
output = N.substring(seq.startPoint, seq.lastIndex + 1);
}
})
return output;
}

Javascript: Split a string by comma, except inside parentheses

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

Writing a function that "solves" an equation

I want to write a function which will allow me to "solve" an equation in js.
what I want (not in a programming language):
function f(x) { 1 + x * x }
var z = 2
var y = f(z) //y will be 5 as a number
what I have written in JS:
function P(cfg) { ....
this.equation = "1 + x";
....};
P.prototype.eqn = function(x) {
var tmp = eval(this.equation);
return tmp;
};
....
P.prototype.draw = function() {....
for(var i = 0; i < z; i++)
ctx.lineTo(i, this.eqn(i));
....};
also I've read that using eval in a loop is probably not a good idea, but I have not figured out another way (yet) (JS beginner)...
The problem with this code is, that at least in FF the var tmp will STILL contain the string from this.equation instead of the calculated value.
I would appreciate any further insight very much!
Thank you for your time :)
EDIT: because my question was not formulated very well:
after the execution of line
var tmp = eval(this.equation);
the var tmp will hold a STRING which equals the string this.equation, instead of the desired solution y value.
Also I do not mean solve but evaluate, thanks for that tip :)
Based on your example, I'd say that you want to "evaluate an expression", rather than "solve an equation". For evaluating an expression, you can probably find many tutorials. I'll break it down in brief though. You need to do a few steps.
Starting with your string "1 + x * x", you need to break it into tokens. Specifically, break it down into: "1", "+", "x", "*", "x". At this point, you can substitute your variables ("x") for their literal values ("2"), giving you "1", "+", "2", "*", "2"
Now you need to parse the expression. Based on order of operations PEMDAS you need to create a tree data structure, where parenthetical clauses (stuff surrounded by parenthesis) are executed first, multiplication and division next, and then additions and subtraction last. Parsing is often not an easy task, and you may want to put together a simpler BNF grammar (though you can probably find a grammar for simple math expressions with some googling).
Next, walk the tree, depth first, evaluating the operations as you go up the tree. Once you get to the top of the tree, you have your solution.
If instead you want to "solve an equation", you're going to need something much more sophisticated, like Sage
I have used this expression evaluator before. It seemed to work very well. It allows you to pass expressions into a Parser that returns a function object that can then evaluate inputs.
var expr = Parser.parse("2 ^ x");
expr.evaluate({ x: 3 }); // 8
It supports trig functions (sin, cos, ect...) and other handy built in functions such as abs & ciel.
var expr = Parser.parse("sin(x/2) + cos(x/2)")
expr.evaluate({x: Math.PI / 2}); // 1
Examples: http://silentmatt.com/javascript-expression-evaluator/
Code: https://github.com/silentmatt/js-expression-eval
Note that this lib does not use eval().
Not sure I entirely understand your question but how about:
var makeFunctionOfX = function(src) {
return Function('x', 'return ' + src);
};
Then you can say things like:
var g = makeFunctionOfX('2 * x')
var y = g(3); // y contains 6
The great advantage of this over eval is that the Function we create has no magic ability to see variables in the scope (hence the need to explicitly pass it x as a parameter name).
Using eval is safe if you trust the input from the user, and works just fine. (I have no idea what you mean by "the var tmp will still have the string this.equation".)
function FuncCreator(eqn){ this.eqn = eqn }
FuncCreator.prototype.run = function(x,y,z){ return eval(this.eqn) }
var add1 = new FuncCreator('1+x');
var result = add1.run(41); // 42
var complex = new FuncCreator('Math.sin(x*y) / Math.cos(z)');
var result = complex.run(3,4,5); // -1.891591285331882
If you don't trust the user input, you'll need to actually parse the input and process it yourself. This is non-trivial.
You can use the expression parser from the math.js library and do something like this:
var parser = math.parser();
var f = parser.eval('function f(x) = 1 + x * x');
// use the created function f in expressions:
parser.eval('z = 2'); // 2
parser.eval('y = f(z)'); // 5
// or use the created function f in JavaScript:
var z = 2; // 2
var y = f(z); // 5
Creating functions in math.js is quite currently limited, loops and blocks needed to define more extensive functions are not yet supported.
This is an old thread, but I wrote this equation calculator, this doesn't solve algebraic equations though. There is however a function that will allow you to provide an array containing assigned variables. But this doesn't solve for variables that don't have an assigned value.
I probably haven't permuted every test case scenario, but it seems to work pretty decent.
Edit: This would have to be modified to handle negative numbers. Other than that... works fine.
Here is a fiddle
<!doctype html>
<html>
<head>
<title>Javascript Equation Calculator</title>
</head>
<body>
<input type="button" onclick="main()" value="calculate"><br>
<input type="text" id="userinput"><br>
<span id="result">Ready.</span><br>
<script>
function Calculator(){}
String.prototype.replaceLast = function (what, replacement)
{
var pcs = this.split(what);
var lastPc = pcs.pop();
return pcs.join(what) + replacement + lastPc;
};
function inS(substr, str){return (str.indexOf(substr) > -1);}
function arrayValueOrToken(arr, key, token)
{
if(key in arr)
{
return arr[key];
}
return token;
}
function reduceEquation(inputStr)
{
console.log("reduceEquation Executed-----");
while(hasNest(inputStr))
{
if(hasNest(inputStr))
{
inputStr = inputStr.replace(")(",')*(');
for(var i=0;i<=9;i++)
{
inputStr = inputStr.replace(i+"(",i+'*(');
inputStr = inputStr.replace(")"+i,')*'+i);
}
var s = inputStr.lastIndexOf("(");
var e = 0;
for(i=s;i,inputStr.length;i++){if(inputStr[i]==")"){e=i+1;break;}}
var eq = inputStr.substring(s,e);
var replace = eq;
eq = eq.replace(/[()]/g, '');
var substitution = solveEquation(eq);
inputStr = inputStr.replaceLast(replace,substitution);
}
}
return inputStr;
}
function solveEquation(eq)
{
console.log("solveEquation Executed-----");
eq = doFirstOrder(eq);
eq = doLastOrder(eq);
return eq;
}
function doFirstOrder(eq)
{
console.log("doFirstOrder Executed-----");
for(var i=0;i<eq.length;i++)
{
if(eq[i]=="*"){eq = solve(eq,"*");return doFirstOrder(eq);}
if(eq[i]=='/'){eq = solve(eq,'/');return doFirstOrder(eq);}
}
return eq;
}
function doLastOrder(eq)
{
console.log("doLastOrder Executed-----");
for(var i=0;i<eq.length;i++)
{
if(eq[i]=="+"){eq = solve(eq,"+");return doLastOrder(eq);}
if(eq[i]=="-"){eq = solve(eq,"-");return doLastOrder(eq);}
}
return eq;
}
function solve(eq, operator)
{
var setOp = operator;
console.log("solve Executed-----");
var buildEq = "",var1 = true,done = false,char="";
var operators = "+-/*";
var ops = operators.replace(operator, '').split('');
var a=ops[0];
var b=ops[1];
var c=ops[2];
for(var i=0;i<eq.length;i++)
{
char = eq[i];
switch(true)
{
case(char==operator):if(var1===true){var1 = false;}else{done = true;}break;
case(char==a):
case(char==b):
case(char==c):if(var1){char = ""; buildEq = "";}else{done = true;}
}
if(done){break;}
buildEq = buildEq + char;
}
var parts = parts = buildEq.split(operator);
var solution = null;
if(operator=="+"){solution = parseFloat(parts[0]) + parseFloat(parts[1]);}
if(operator=="-"){solution = parseFloat(parts[0]) - parseFloat(parts[1]);}
if(operator=="*"){solution = parseFloat(parts[0]) * parseFloat(parts[1]);}
if(operator=="/"){solution = parseFloat(parts[0]) / parseFloat(parts[1]);}
return eq.replace(buildEq, solution);
}
function hasNest(inputStr){return inS("(",inputStr);}
function allNestsComplete(inputStr)
{
var oC = 0, cC = 0,char="";
for(var i=0;i<inputStr.length;i++){char = inputStr[i];if(char=="("){oC+=1;}if(char==")"){cC+=1;}}
return (oC==cC);
}
Calculator.prototype.calc = function(inputStr)
{
console.log("Calc Executed-----");
inputStr = inputStr.replace(/ /g, "");
inputStr = inputStr.replace(/\\/g, '/');
inputStr = inputStr.replace(/x/g, "*")
inputStr = inputStr.replace(/X/g, "*")
if(!allNestsComplete(inputStr)){return "Nested operations not opened/closed properly.";}
inputStr=reduceEquation(inputStr);
inputStr = solveEquation(inputStr);
return inputStr;
};
Calculator.prototype.calcWithVars = function(inputList)
{
if(inputList.length < 2){return "One or more missing arguments!";}
var vars = [];
var assocVars = [];
var lastVarIndex = inputList.length - 2;
var i = 0;
var inputStr = inputList[inputList.length-1];
for(i=0;i<=lastVarIndex;i++)
{
vars.push(inputList[i].replace(/ /g, ""));
}
for(i=0;i<=vars.length-1;i++)
{
var vParts = vars[i].split("=");
var vName = vParts[0];
var vValue = vParts[1];
assocVars[vName] = vValue;
}
inputStr = inputStr.replace(/ /g, "");
var eqVars = inputStr.replace(/\s+/g, ' ').replace(/[^a-zA-Z-]/g, ' ').replace(/\s\s+/g, ' ');
if(inS(" ", eqVars))
{
eqVars = eqVars.split(" ");
}
else{eqVars = [eqVars];}
eqVars.sort(function(a, b){return a.length - a.length;});
var tempTokens = [];
var tempCount = 1;
for(i=0;i<eqVars.length;i++)
{
var eqVname = eqVars[i];
var substitution = arrayValueOrToken(assocVars, eqVname, "<unknown>");
if(substitution != "<unknown>")
{
inputStr = inputStr.replace(eqVname,substitution);
}
else
{
var tempToken = "#______#"+tempCount+"#______#";
tempCount++;
tempTokens.push(tempToken + "?" + eqVname);
inputStr = inputStr.replace(eqVname,tempToken);
}
}
for(i=0;i<tempTokens.length;i++)
{
var tokenSet = tempTokens[i];
var tokenParts = tokenSet.split("?");
var token = tokenParts[0];
var variableName = tokenParts[1];
inputStr = inputStr.replace(token,variableName);
}
var answerName = "<unknown>";
var eq = inputStr;
if(inS("=", inputStr))
{
var eqParts = inputStr.split("=");
answerName = eqParts[0];
eq = eqParts[1];
}
eq = this.calc(eq);
var result = [];
for(i=0;i<eqVars.length;i++)
{
var v = arrayValueOrToken(assocVars, eqVars[i], "<unknown>");
if(v != "<unknown>")
{
result.push(assocVars[eqVars[i]]);
}
}
result.push(eq);
return result;
};
function main()
{
var calculator = new Calculator();
elUserInput = document.getElementById('userinput');
console.log("input: "+ elUserInput.value);
elResult = document.getElementById('result');
equation = elUserInput.value;
result = calculator.calc(equation);
console.log("result: "+ result);
elResult.innerHTML = result;
}
</script>
</body>
</html>

Javascript token replace/append

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;
}

Categories