Javascript search string for numbers regex maybe? - javascript

I have a string like
:21::22::24::99:
And I want to find say if :22: is in said string. But is there a means of searching a string like above for one like I want to match it to with javascript, and if there is, does it involve regex magic or is there something else? Either way not sure how to do it, more so if regex is involved.

You can build the regular expression you need:
function findNumberInString(num, s) {
var re = new RegExp(':' + num + ':');
return re.test(s);
}
var s = ':21::22::24::99';
var n = '22';
findNumberInString(n, s); // true
or just use match (though test is cleaner to me)
!!s.match(':' + n + ':'); // true
Edit
Both the above use regular expressions, so a decimal ponit (.) will come to represent any character, so "4.1" will match "461" or even "4z1", so better to use a method based on String.prototype.indexOf just in case (unless you want "." to represent any character), so per Blender's comment:
function findNumberInString(num, s) {
return s.indexOf(':' + num + ':') != -1;
}

like this:
aStr = ':21::22::24::99:';
if(aStr.indexOf(':22:') != -1){
//':22:' exists in aStr
}
else{
//it doesn't
}

Related

Replace leading numbers with Javascript regex

As a follow up to this question (not by me), I need to replace leading numbers of an id with \\3n (where n is the number we're replacing).
Some examples:
"1foo" -> "\\31foo"
"1foo1" -> "\\31foo1"
"12foo" -> "\\31\\32foo"
"12fo3o4" -> "\\31\\32fo3o4"
"foo123" -> "foo123"
Below is a solution that replaces every instance of the number, but I don't know enough regex to make it stop once it hits a non-number.
function magic (str) {
return str.replace(/([0-9])/g, "\\3$1");
}
... Or is regex a bad way to go? I guess it would be easy enough to do it, just looping over each character of the string manually.
Here is a way to achieve what you need using a reverse string + look-ahead approach:
function revStr(str) {
return str.split('').reverse().join('');
}
var s = "12fo3o4";
document.write(revStr(revStr(s).replace(/\d(?=\d*$)/g, function (m) {
return m + "3\\\\";
}))
);
The regex is matching a number that can be followed by 0 or more numbers only until the end (which is actually start) of a reversed string (with \d(?=\d*$)). The callback allows to manipulate the match (we just add reversed \\ and 3. Then, we just reverse the result.
Just use two steps: first find the prefix, then operate on its characters:
s.replace(/^\d+/, function (m) {
return [].map.call(m, function (c) {
return '\\3' + c;
}).join('');
});
No need to emulate any features.
Here is how I would have done it:
function replace(str) {
var re = /^([\d]*)/;
var match = str.match(re)[0];
var replaced = match.replace(/([\d])/g, "\\3$1");
str = str.replace(match, replaced);
return str;
}
document.write(replace("12fo3o4"));
Don't get me wrong: the other answers are fine! My focus was more on readability.

Javascript convert PascalCase to underscore_case/snake_case

How can I convert PascalCase string into underscore_case/snake_case string? I need to convert dots into underscores as well.
eg. convert
TypeOfData.AlphaBeta
into
type_of_data_alpha_beta
You could try the below steps.
Capture all the uppercase letters and also match the preceding optional dot character.
Then convert the captured uppercase letters to lowercase and then return back to replace function with an _ as preceding character. This will be achieved by using anonymous function in the replacement part.
This would replace the starting uppercase letter to _ + lowercase_letter.
Finally removing the starting underscore will give you the desired output.
var s = 'TypeOfData.AlphaBeta';
console.log(s.replace(/(?:^|\.?)([A-Z])/g, function (x,y){return "_" + y.toLowerCase()}).replace(/^_/, ""));
OR
var s = 'TypeOfData.AlphaBeta';
alert(s.replace(/\.?([A-Z])/g, function (x,y){return "_" + y.toLowerCase()}).replace(/^_/, ""));
any way to stop it for when a whole word is in uppercase. eg. MotorRPM into motor_rpm instead of motor_r_p_m? or BatteryAAA into battery_aaa instead of battery_a_a_a?
var s = 'MotorRMP';
alert(s.replace(/\.?([A-Z]+)/g, function (x,y){return "_" + y.toLowerCase()}).replace(/^_/, ""));
str.split(/\.?(?=[A-Z])/).join('_').toLowerCase();
u're welcome
var s1 = 'someTextHere';
var s2 = 'SomeTextHere';
var s3 = 'TypeOfData.AlphaBeta';
var o1 = s1.split(/\.?(?=[A-Z])/).join('_').toLowerCase();
var o2 = s2.split(/\.?(?=[A-Z])/).join('_').toLowerCase();
var o3 = s3.split(/\.?(?=[A-Z])/).join('_').toLowerCase();
console.log(o1);
console.log(o2);
console.log(o3);
Alternatively using lodash:
lodash.snakeCase(str);
Example:
_.snakeCase('TypeOfData.AlphaBeta');
// ➜ 'type_of_data_alpha_beta'
Lodash is a fine library to give shortcut to many everyday js tasks.There are many other similar string manipulation functions such as camelCase, kebabCase etc.
This solution solves the non-trailing acronym issue with the solutions above
I ported the code in 1175208 from Python to JavaScript.
Javascript Code
function camelToSnakeCase(text) {
return text.replace(/(.)([A-Z][a-z]+)/, '$1_$2').replace(/([a-z0-9])([A-Z])/, '$1_$2').toLowerCase()
}
Working Examples:
camelToSnakeCase('thisISDifficult') -> this_is_difficult
camelToSnakeCase('thisISNT') -> this_isnt
camelToSnakeCase('somethingEasyLikeThis') -> something_easy_like_this
"alphaBetaGama".replace(/([A-Z])/g, "_$1").toLowerCase() // alpha_beta_gamma
Problem - Need to convert a camel-case string ( such as a property name ) into underscore style to meet interface requirements or for meta-programming.
Explanation
This line uses a feature of regular expressions where it can return a matched result ( first pair of () is $1, second is $2, etc ).
Each match in the string is converted to have an underscore ahead of it with _$1 string provided. At that point the string looks like alpha_Beta_Gamma.
To correct the capitalization, the entire string is converted toLowerCase().
Since toLowerCase is a fairly expensive operation, its best not to put it in the looping handler for each match-case, and run it once on the entire string.
After toLowerCase it the resulting string is alpha_beta_gamma ( in this example )
This will get you pretty far: https://github.com/domchristie/humps
You will probably have to use regex replace to replace the "." with an underscore.
I found this but I edited it so suit your question.
const camelToSnakeCase = str => str.replace(/[A-Z]/g, letter => `_${letter.toLowerCase()}`).replace(/^_/,'')
Good examples for js:
Snake Case
Kebab Case
Camel Case
Pascal Case
have here
function toCamelCase(s) {
// remove all characters that should not be in a variable name
// as well underscores an numbers from the beginning of the string
s = s.replace(/([^a-zA-Z0-9_\- ])|^[_0-9]+/g, "").trim().toLowerCase();
// uppercase letters preceeded by a hyphen or a space
s = s.replace(/([ -]+)([a-zA-Z0-9])/g, function(a,b,c) {
return c.toUpperCase();
});
// uppercase letters following numbers
s = s.replace(/([0-9]+)([a-zA-Z])/g, function(a,b,c) {
return b + c.toUpperCase();
});
return s;
}
Try this function, hope it helps.
"TestString".replace(/[A-Z]/g, val => "_" + val.toLowerCase()).replace(/^_/,"")
replaces all uppercase with an underscore and lowercase, then removes the leading underscore.
A Non-Regex Answer that converts PascalCase to snake_case
Note: I understand there are tons of good answers which solve this question elegantly. I was recently working on something similar to this where I chose not to use regex. So I felt to answer a non-regex solution to this.
const toSnakeCase = (str) => {
return str.slice(0,1).toLowerCase() + str.split('').slice(1).map((char) => {
if (char == char.toUpperCase()) return '_' + char.toLowerCase();
else return char;
}).join('');
}
Eg.
inputString = "ILoveJavascript" passed onto toSnakeCase()
would become "i_love_javascript"

Regular Expressions required format

I want to validate following text using regular expressions
integer(1..any)/'fs' or 'sf'/ + or - /integer(1..any)/(h) or (m) or (d)
samples :
1) 8fs+60h
2) 10sf-30m
3) 2fs+3h
3) 15sf-20m
i tried with this
function checkRegx(str,id){
var arr = strSplit(str);
var regx_FS =/\wFS\w|\d{0,9}\d[hmd]/gi;
for (var i in arr){
var str_ = arr[i];
console.log(str_);
var is_ok = str_.match(regx_FS);
var err_pos = str_.search(regx_FS);
if(is_ok){
console.log(' ID from ok ' + id);
$('#'+id).text('Format Error');
break;
}else{
console.log(' ID from fail ' + id);
$('#'+id).text('');
}
}
}
but it is not working
please can any one help me to make this correct
This should do it:
/^[1-9]\d*(?:fs|sf)[-+][1-9]\d*[hmd]$/i
You were close, but you seem to be missing some basic regex comprehension.
First of all, the ^ and $ just make sure you're matching the entire string. Otherwise any junk before or after will count as valid.
The formation [1-9]\d* allows for any integer from 1 upwards (and any number of digits long).
(?:fs|sf) is an alternation (the ?: is to make the group non-capturing) to allow for both options.
[-+] and [hmd] are character classes allowing to match any one of the characters in there.
That final i allows the letters to be lowercase or uppercase.
I don't see how the expression you tried relates anyhow to the description you gave us. What you want is
/\d+(fs|sf)[+-]\d+[hmd]/
Since you seem to know a bit about regular expressions I won't give a step-by-step explanation :-)
If you need exclude zero from the "integer" matches, use [1-9]\d* instead. Not sure whether by "(1..any)" you meant the number of digits or the number itself.
Looking on the code, you
should not use for in enumerations on arrays
will need string start and end anchors to check whether _str exactly matches the regex (instead of only some part)
don't need the global flag on the regex
rather might use the RegExp test method than match - you don't need a result string but only whether it did match or not
are not using the err_pos variable anywhere, and it hardly will work with search
function checkRegx(str, id) {
var arr = strSplit(str);
var regx_FS = /^\d+(fs|sf)[+-]\d+[hmd]$/i;
for (var i=0; i<arr.length; i++) {
var str = arr[i];
console.log(str);
if (regx_FS.test(str) {
console.log(' ID from ok ' + id);
$('#'+id).text('Format Error');
break;
} else {
console.log(' ID from fail ' + id);
$('#'+id).text('');
}
}
}
Btw, it would be better to separate the validation (regex, array split, iteration) from the output (id, jQuery, logs) into two functions.
Try something like this:
/^\d+(?:fs|sf)[-+]\d+[hmd]$/i

Regex, grab only one instance of each letter

I have a paragraph that's broken up into an array, split at the periods. I'd like to perform a regex on index[i], replacing it's contents with one instance of each letter that index[i]'s string value has.
So; index[i]:"This is a sentence" would return --> index[i]:"thisaenc"
I read this thread. But i'm not sure if that's what i'm looking for.
Not sure how to do this in regex, but here's a very simple function to do it without using regex:
function charsInString(input) {
var output='';
for(var pos=0; pos<input.length; pos++) {
char=input.charAt(pos).toLowerCase();
if(output.indexOf(char) == -1 && char != ' ') {output+=char;}
}
return output;
}
alert(charsInString('This is a sentence'));
As I'm pretty sure what you need cannot be achieved using a single regular expression, I offer a more general solution:
// collapseSentences(ary) will collapse each sentence in ary
// into a string containing its constituent chars
// #param {Array} the array of strings to collapse
// #return {Array} the collapsed sentences
function collapseSentences(ary){
var result=[];
ary.forEach(function(line){
var tmp={};
line.toLowerCase().split('').forEach(function(c){
if(c >= 'a' && c <= 'z') {
tmp[c]++;
}
});
result.push(Object.keys(tmp).join(''));
});
return result;
}
which should do what you want except that the order of characters in each sentence cannot be guaranteed to be preserved, though in most cases it is.
Given:
var index=['This is a sentence','This is a test','this is another test'],
result=collapseSentences(index);
result contains:
["thisaenc","thisae", "thisanoer"]
(\w)(?<!.*?\1)
This yields a match for each of the right characters, but as if you were reading right-to-left instead.
This finds a word character, then looks ahead for the character just matched.
Nevermind, i managed:
justC = "";
if (color[i+1].match(/A/g)) {justC += " L_A";}
if (color[i+1].match(/B/g)) {justC += " L_B";}
if (color[i+1].match(/C/g)) {justC += " L_C";}
if (color[i+1].match(/D/g)) {justC += " L_D";}
if (color[i+1].match(/E/g)) {justC += " L_E";}
else {color[i+1] = "L_F";}
It's not exactly what my question may have lead to belive is what i wanted, but the printout for this is what i was after, for use in a class: <span class="L_A L_C L_E"></span>
How about:
var re = /(.)((.*?)\1)/g;
var str = 'This is a sentence';
x = str.toLowerCase();
x = x.replace(/ /g, '');
while(x.match(re)) {
x=x.replace(re, '$1$3');
}
I don't think this can be done in one fell regex swoop. You are going to need to use a loop.
While my example was not written in your language of choice, it doesn't seem to use any regex features not present in javascript.
perl -e '$foo="This is a sentence"; while ($foo =~ s/((.).*?)\2/$1/ig) { print "<$1><$2><$foo>\n"; } print "$foo\n";'
Producing:
This aenc

How can I concatenate regex literals in JavaScript?

Is it possible to do something like this?
var pattern = /some regex segment/ + /* comment here */
/another segment/;
Or do I have to use new RegExp() syntax and concatenate a string? I'd prefer to use the literal as the code is both more self-evident and concise.
Here is how to create a regular expression without using the regular expression literal syntax. This lets you do arbitary string manipulation before it becomes a regular expression object:
var segment_part = "some bit of the regexp";
var pattern = new RegExp("some regex segment" + /*comment here */
segment_part + /* that was defined just now */
"another segment");
If you have two regular expression literals, you can in fact concatenate them using this technique:
var regex1 = /foo/g;
var regex2 = /bar/y;
var flags = (regex1.flags + regex2.flags).split("").sort().join("").replace(/(.)(?=.*\1)/g, "");
var regex3 = new RegExp(expression_one.source + expression_two.source, flags);
// regex3 is now /foobar/gy
It's just more wordy than just having expression one and two being literal strings instead of literal regular expressions.
Just randomly concatenating regular expressions objects can have some adverse side effects. Use the RegExp.source instead:
var r1 = /abc/g;
var r2 = /def/;
var r3 = new RegExp(r1.source + r2.source,
(r1.global ? 'g' : '')
+ (r1.ignoreCase ? 'i' : '') +
(r1.multiline ? 'm' : ''));
console.log(r3);
var m = 'test that abcdef and abcdef has a match?'.match(r3);
console.log(m);
// m should contain 2 matches
This will also give you the ability to retain the regular expression flags from a previous RegExp using the standard RegExp flags.
jsFiddle
I don't quite agree with the "eval" option.
var xxx = /abcd/;
var yyy = /efgh/;
var zzz = new RegExp(eval(xxx)+eval(yyy));
will give "//abcd//efgh//" which is not the intended result.
Using source like
var zzz = new RegExp(xxx.source+yyy.source);
will give "/abcdefgh/" and that is correct.
Logicaly there is no need to EVALUATE, you know your EXPRESSION. You just need its SOURCE or how it is written not necessarely its value. As for the flags, you just need to use the optional argument of RegExp.
In my situation, I do run in the issue of ^ and $ being used in several expression I am trying to concatenate together! Those expressions are grammar filters used accross the program. Now I wan't to use some of them together to handle the case of PREPOSITIONS.
I may have to "slice" the sources to remove the starting and ending ^( and/or )$ :)
Cheers, Alex.
Problem If the regexp contains back-matching groups like \1.
var r = /(a|b)\1/ // Matches aa, bb but nothing else.
var p = /(c|d)\1/ // Matches cc, dd but nothing else.
Then just contatenating the sources will not work. Indeed, the combination of the two is:
var rp = /(a|b)\1(c|d)\1/
rp.test("aadd") // Returns false
The solution:
First we count the number of matching groups in the first regex, Then for each back-matching token in the second, we increment it by the number of matching groups.
function concatenate(r1, r2) {
var count = function(r, str) {
return str.match(r).length;
}
var numberGroups = /([^\\]|^)(?=\((?!\?:))/g; // Home-made regexp to count groups.
var offset = count(numberGroups, r1.source);
var escapedMatch = /[\\](?:(\d+)|.)/g; // Home-made regexp for escaped literals, greedy on numbers.
var r2newSource = r2.source.replace(escapedMatch, function(match, number) { return number?"\\"+(number-0+offset):match; });
return new RegExp(r1.source+r2newSource,
(r1.global ? 'g' : '')
+ (r1.ignoreCase ? 'i' : '')
+ (r1.multiline ? 'm' : ''));
}
Test:
var rp = concatenate(r, p) // returns /(a|b)\1(c|d)\2/
rp.test("aadd") // Returns true
Providing that:
you know what you do in your regexp;
you have many regex pieces to form a pattern and they will use same flag;
you find it more readable to separate your small pattern chunks into an array;
you also want to be able to comment each part for next dev or yourself later;
you prefer to visually simplify your regex like /this/g rather than new RegExp('this', 'g');
it's ok for you to assemble the regex in an extra step rather than having it in one piece from the start;
Then you may like to write this way:
var regexParts =
[
/\b(\d+|null)\b/,// Some comments.
/\b(true|false)\b/,
/\b(new|getElementsBy(?:Tag|Class|)Name|arguments|getElementById|if|else|do|null|return|case|default|function|typeof|undefined|instanceof|this|document|window|while|for|switch|in|break|continue|length|var|(?:clear|set)(?:Timeout|Interval))(?=\W)/,
/(\$|jQuery)/,
/many more patterns/
],
regexString = regexParts.map(function(x){return x.source}).join('|'),
regexPattern = new RegExp(regexString, 'g');
you can then do something like:
string.replace(regexPattern, function()
{
var m = arguments,
Class = '';
switch(true)
{
// Numbers and 'null'.
case (Boolean)(m[1]):
m = m[1];
Class = 'number';
break;
// True or False.
case (Boolean)(m[2]):
m = m[2];
Class = 'bool';
break;
// True or False.
case (Boolean)(m[3]):
m = m[3];
Class = 'keyword';
break;
// $ or 'jQuery'.
case (Boolean)(m[4]):
m = m[4];
Class = 'dollar';
break;
// More cases...
}
return '<span class="' + Class + '">' + m + '</span>';
})
In my particular case (a code-mirror-like editor), it is much easier to perform one big regex, rather than a lot of replaces like following as each time I replace with a html tag to wrap an expression, the next pattern will be harder to target without affecting the html tag itself (and without the good lookbehind that is unfortunately not supported in javascript):
.replace(/(\b\d+|null\b)/g, '<span class="number">$1</span>')
.replace(/(\btrue|false\b)/g, '<span class="bool">$1</span>')
.replace(/\b(new|getElementsBy(?:Tag|Class|)Name|arguments|getElementById|if|else|do|null|return|case|default|function|typeof|undefined|instanceof|this|document|window|while|for|switch|in|break|continue|var|(?:clear|set)(?:Timeout|Interval))(?=\W)/g, '<span class="keyword">$1</span>')
.replace(/\$/g, '<span class="dollar">$</span>')
.replace(/([\[\](){}.:;,+\-?=])/g, '<span class="ponctuation">$1</span>')
It would be preferable to use the literal syntax as often as possible. It's shorter, more legible, and you do not need escape quotes or double-escape backlashes. From "Javascript Patterns", Stoyan Stefanov 2010.
But using New may be the only way to concatenate.
I would avoid eval. Its not safe.
You could do something like:
function concatRegex(...segments) {
return new RegExp(segments.join(''));
}
The segments would be strings (rather than regex literals) passed in as separate arguments.
You can concat regex source from both the literal and RegExp class:
var xxx = new RegExp(/abcd/);
var zzz = new RegExp(xxx.source + /efgh/.source);
Use the constructor with 2 params and avoid the problem with trailing '/':
var re_final = new RegExp("\\" + ".", "g"); // constructor can have 2 params!
console.log("...finally".replace(re_final, "!") + "\n" + re_final +
" works as expected..."); // !!!finally works as expected
// meanwhile
re_final = new RegExp("\\" + "." + "g"); // appends final '/'
console.log("... finally".replace(re_final, "!")); // ...finally
console.log(re_final, "does not work!"); // does not work
No, the literal way is not supported. You'll have to use RegExp.
the easier way to me would be concatenate the sources, ex.:
a = /\d+/
b = /\w+/
c = new RegExp(a.source + b.source)
the c value will result in:
/\d+\w+/
I prefer to use eval('your expression') because it does not add the /on each end/ that ='new RegExp' does.

Categories