I have a string like so:
var str = "FacebookExternalHit and some other gibberish";
Now I have a list of strings to test if they exist in str. Here they are in array format:
var bots = ["FacebookExternalHit", "LinkedInBot", "TwitterBot", "Baiduspider"];
What is the fastest and/or shortest method to search str and see if any of the bots values are present? Regex is fine if that's the best method.
Using join you can do:
var m = str.match( new RegExp("\\b(" + bots.join('|') + ")\\b", "ig") );
//=> ["FacebookExternalHit"]
I don't know that regex is necessarily the way to go here. Check out Array.prototype.some()
var str = "FacebookExternalHit and some other gibberish";
var bots = ["FacebookExternalHit", "LinkedInBot", "TwitterBot", "Baiduspider"];
var isBot = bots.some(function(botName) {
return str.indexOf(botName) !== -1;
});
console.log("isBot: %o", isBot);
A regular for loop is even faster:
var str = "FacebookExternalHit and some other gibberish";
var bots = ["FacebookExternalHit", "LinkedInBot", "TwitterBot", "Baiduspider"];
var isBot = false;
for (var i = 0, ln = bots.length; i < ln; i++) {
if (str.indexOf(bots[i]) !== -1) {
isBot = true;
break;
}
}
console.log("isBot: %o", isBot);
Related
Edit
sorry if the question wasn't clear
here is the question..
create your version of javascript split function,
you may use indexOf and substring to help.
so if i give you a string "heellloolllloolllo" and i want to remove "llll" the function should return "heellloooolllo"
This what I did so far:
function split() {
var entered_string = document.forms["form1"]["str"].value;
var deleted_char = document.forms["form1"]["char"].value;
var index = entered_string.indexOf(deleted_char);
var i = deleted_char.length;
var result;
var x ;
for (x = 0; x< entered_string.length; x++ )
{
if (index < 0) {
result = entered_string;
} else {
result = entered_string.substring(0, index) +entered_string.substring(index+i);
}
}
alert(result)
}
Use the replace() function with the g at the end of your regular expression. It's called a "global modifier".
var string = 'heellloolllloolllo';
var res = string.replace(/llll/g, '');
console.log(res)
If your substring is a variable then you need to construct a new Regex object and set the g as the second parameter.
var string = 'heellloolllloolllo';
var find = 'llll';
var regex = new RegExp(find,'g');
var res = string.replace(regex, '');
console.log(res)
There are other useful modifiers you can use:
g - Global replace. Replace all instances of the matched string in the provided text.
i - Case insensitive replace. Replace all instances of the matched string, ignoring differences in case.
m - Multi-line replace. The regular expression should be tested for matches over multiple lines.
See this post for more information, credit to #codejoe.
Using String#replace and RegExp (the clean way)
var str = 'llllheellloolllloolllollll';
var matchStr = 'llll';
function removeSubString(str, matchStr) {
var re = new RegExp(matchStr, 'g');
return str.replace(re,"");
}
console.log(removeSubString(str, matchStr));
Using String#indexOf and String#substring
var str = 'llllheellloolllloolllollll';
var matchStr = 'llll';
function removeSubString(str, matchStr) {
var index = str.indexOf(matchStr);
while(index != -1) {
var firstSubStr = str.substring(0, index);
var lastSubStr = str.substring(index + matchStr.length);
str = firstSubStr + lastSubStr;
index = str.indexOf(matchStr);
}
return str;
}
console.log(removeSubString(str,matchStr))
Is there a javascript string function that search a regex and it will start the search at the end?
If not, what is the fastest and/or cleanest way to search the index of a regex starting from the end?
example of regex:
/<\/?([a-z][a-z0-9]*)\b[^>]*>?/gi
Maybe this can be useful and easier:
str.lastIndexOf(str.match(<your_regex_here>).pop());
Perhaps something like this is suitable for you?
Javascript
function lastIndexOfRx(string, regex) {
var match = string.match(regex);
return match ? string.lastIndexOf(match.slice(-1)) : -1;
}
var rx = /<\/?([a-z][a-z0-9]*)\b[^>]*>?/gi;
console.log(lastIndexOfRx("", rx));
console.log(lastIndexOfRx("<i>it</i><b>bo</b>", rx));
jsFiddle
And just for interest, this function vs the function that you choose to go with. jsperf
This requires that you format your regex correctly for matching exactly the pattern you want and globally (like given in your question), for example /.*(<\/?([a-z][a-z0-9]*)\b[^>]*>?)/i will not work with this function. But what you do get is a function that is clean and fast.
You may create a reverse function like:
function reverse (s) {
var o = '';
for (var i = s.length - 1; i >= 0; i--)
o += s[i];
return o;
}
and then use
var yourString = reverse("Your string goes here");
var regex = new Regex(your_expression);
var result = yourString.match(regex);
Another idea: if you want to search by word in reverse order then
function reverseWord(s) {
var o = '';
var split = s.split(' ');
for (var i = split.length - 1; i >= 0; i--)
o += split[i] + ' ';
return o;
}
var yourString = reverseWord("Your string goes here");
var regex = new Regex(your_expression);
var result = yourString.match(regex);
Andreas gave this from the comment:
https://stackoverflow.com/a/274094/402037
String.prototype.regexLastIndexOf = function(regex, startpos) {
regex = (regex.global) ? regex : new RegExp(regex.source, "g" + (regex.ignoreCase ? "i" : "") + (regex.multiLine ? "m" : ""));
if(typeof (startpos) == "undefined") {
startpos = this.length;
} else if(startpos < 0) {
startpos = 0;
}
var stringToWorkWith = this.substring(0, startpos + 1);
var lastIndexOf = -1;
var nextStop = 0;
while((result = regex.exec(stringToWorkWith)) != null) {
lastIndexOf = result.index;
regex.lastIndex = ++nextStop;
}
return lastIndexOf;
}
Which gives the functionality that I need, I tested my regex, and it is successful. So I'll use this
It depends what you exactly want to search for. You can use string.lastIndexOf or inside the regexp to use $ (end of the string).
Update:
try the regexp
/<\/?([a-z][a-z0-9]*)\b[^>]*>?[\w\W]*$/gi
var m = text.match(/.*(<\/?([a-z][a-z0-9]*)\b[^>]*>?)/i);
if (m) {
textFound = m[1];
position = text.lastIndexOf(textFound);
}
Use .* to skip as much text as posible, capture the text found and search it with lastIndexOf
EDIT:
Well, if text is found, no need to search with lastIndexOf. m[0] contains the full coincidence (including all the initial padding), and m[1] the searched text. So position of found text is m[0].length - m[1].length
var m = text.match(/.*(<\/?([a-z][a-z0-9]*)\b[^>]*>?)/i);
if (m) {
textFound = m[1];
position = m[0].length - m[1].length;
}
Assuming you're looking for a string 'token', then you need the position of 'token' that has no other 'token' following until the end of the string.
So you should compose your regex something like that:
$token = 'token';
$re = "/(?:$token)[^(?:$token)]*$/";
This will find your 'token' where no further 'token' can be found until string end. The "(?:" grouping simply makes the group non-storing, slightly speeding up performance and saving memory.
Here's a thing i've been trying to resolve...
We've got some data from an ajax call and the result data is between other stuff a huge string with key:value data. For example:
"2R=OK|2M=2 row(s) found|V1=1,2|"
Is it posible for js to do something like:
var value = someFunction(str, param);
so if i search for "V1" parameter it will return "1,2"
I got this running on Sql server no sweat, but i'm struggling with js to parse the string.
So far i'm able to do this by a VERY rudimentary for loop like this:
var str = "2R=OK|2M=2 row(s) found|V1=1,2|";
var param = "V1";
var arr = str.split("|");
var i = 0;
var value = "";
for(i = 0; i<arr.length; ++i){
if( arr[i].indexOf(param)>-1 ){
value = arr[i].split("=")[1];
}
}
console.log(value);
if i put that into a function it works, but i wonder if there's a more efficient way to do it, maybe some regex? but i suck at it. Hopefully somebody may shine a light on this for me?
Thanks!
This seems to work for your specific use-case:
function getValueByKey(haystack, needle) {
if (!haystack || !needle) {
return false;
}
else {
var re = new RegExp(needle + '=(.+)');
return haystack.match(re)[1];
}
}
var str = "2R=OK|2M=2 row(s) found|V1=1,2|",
test = getValueByKey(str, 'V1');
console.log(test);
JS Fiddle demo.
And, to include the separator in your search (in order to prevent somethingElseV1 matching for V1):
function getValueByKey(haystack, needle, separator) {
if (!haystack || !needle) {
return false;
}
else {
var re = new RegExp('\\' + separator + needle + '=(.+)\\' + separator);
return haystack.match(re)[1];
}
}
var str = "2R=OK|2M=2 row(s) found|V1=1,2|",
test = getValueByKey(str, 'V1', '|');
console.log(test);
JS Fiddle demo.
Note that this approach does require the use of the new RegExp() constructor (rather than creating a regex-literal using /.../) in order to pass variables into the regular expression.
Similarly, because we're using a string to create the regular expression within the constructor, we need to double-escape characters that require escaping (escaping first within the string and then escaping within in the created RegExp).
References:
RegExp.
String.match().
This should work for you and it's delimiters are configurable (if you wish to parse a similar string with different delimiters, you can just pass in the delimiters as arguments):
var parseKeyValue = (function(){
return function(str, search, keyDelim, valueDelim){
keyDelim = quote(keyDelim || '|');
valueDelim = quote(valueDelim || '=');
var regexp = new RegExp('(?:^|' + keyDelim + ')' + quote(search) + valueDelim + '(.*?)(?:' + keyDelim + '|$)');
var result = regexp.exec(str);
if(result && result.length > 1)
return result[1];
};
function quote(str){
return (str+'').replace(/([.?*+^$[\]\\(){}|-])/g, "\\$1");
}
})();
Quote function borrowed form this answer
Usage examples:
var str = "2R=OK|2M=2 row(s) found|V1=1,2|";
var param = "V1";
parseKeyValue(str, param); // "1,2"
var str = "2R=OK&2M=2 row(s) found&V1=1,2";
var param = "2R";
parseKeyValue(str, param, '&'); // "OK"
var str =
"2R=>OK\n\
2M->2 row(s) found\n\
V1->1,2";
var param = "2M";
parseKeyValue(str, param, '\n', '->'); // "2 row(s) found"
Here is another approach:
HTML:
<div id="2R"></div>
<div id="2M"></div>
<div id="V1"></div>
Javascript:
function createDictionary(input) {
var splittedInput = input.split(/[=|]/),
kvpCount = Math.floor(splittedInput.length / 2),
i, key, value,
dictionary = {};
for (i = 0; i < kvpCount; i += 1) {
key = splittedInput[i * 2];
value = splittedInput[i * 2 + 1];
dictionary[key] = value;
}
return dictionary;
}
var input = "2R=OK|2M=2 row(s) found|V1=1,2|",
dictionary = createDictionary(input),
div2R = document.getElementById("2R"),
div2M = document.getElementById("2M"),
divV1 = document.getElementById("V1");
div2R.innerHTML = dictionary["2R"];
div2M.innerHTML = dictionary["2M"];
divV1.innerHTML = dictionary["V1"];
Result:
OK
2 row(s) found
1,2
the list looks like:
3434,346,1,6,46
How can I append a number to it with javascript, but only if it doesn't already exist in it?
Assuming your initial value is a string (you didn't say).
var listOfNumbers = '3434,346,1,6,46', add = 34332;
var numbers = listOfNumbers.split(',');
if(numbers.indexOf(add)!=-1) {
numbers.push(add);
}
listOfNumbers = numbers.join(',');
Basically i convert the string into an array, check the existence of the value using indexOf(), adding only if it doesn't exist.
I then convert the value back to a string using join.
If that is a string, you can use the .split() and .join() functions, as well as .push():
var data = '3434,346,1,6,46';
var arr = data.split(',');
var add = newInt;
arr.push(newInt);
data = arr.join(',');
If that is already an array, you can just use .push():
var data = [3434,346,1,6,46];
var add = newInt;
data.push(add);
UPDATE: Didn't read the last line to check for duplicates, the best approach I can think of is a loop:
var data = [3434,346,1,6,46];
var add = newInt;
var exists = false;
for (var i = 0; i < input.length; i++) {
if (data[i] == add) {
exists = true;
break;
}
}
if (!exists) {
data.push(add);
// then you would join if you wanted a string
}
You can also use a regular expression:
function appendConditional(s, n) {
var re = new RegExp('(^|\\b)' + n + '(\\b|$)');
if (!re.test(s)) {
return s + (s.length? ',' : '') + n;
}
return s;
}
var nums = '3434,346,1,6,46'
alert( appendConditional(nums, '12') ); // '3434,346,1,6,46,12'
alert( appendConditional(nums, '6') ); // '3434,346,1,6,46'
Oh, since some really like ternary operators and obfustically short code:
function appendConditional(s, n) {
var re = new RegExp('(^|\\b)' + n + '(\\b|$)');
return s + (re.test(s)? '' : (''+s? ',':'') + n );
}
No jQuery, "shims" or cross-browser issues. :-)
Given an input like:
<input type="test" value="3,4,9" />
What's the best way to remove a value like 9, 4 or 3, without having issues with the commas, I don't want this ending up:
value="3,4,"
value="3,,9"
value=",4,9"
Is there a clean way to get this done in JavaScript/jQuery?
You could split your value into an array, then filter out values you do not want.
$("input[type='test']").val().split(",") // ["3","4","9"]
.filter(function(v){return !isNaN(parseInt(v))}) // filter out anything which is not 0 or more
Here is a less terse version which filters out anything which is not numeric
var array = $("input[type='test']").val().split(",");
// If you are dealing with numeric values then you will want
// to cast the string as a number
var numbers = array.map(function(v){ return parseInt(v)});
// Remove anything which is not a number
var filtered = numbers.filter(function(v){ return !isNaN(v)});
// If you want to rejoin your values
var joined = filtered.join(",");
Finally change the value on the input
$("input[type='test']").val(joined);
Similar to PHP implode/explode functions
Array.prototype.remove = function(from, to) {
var rest = this.slice((to || from) + 1 || this.length);
this.length = from < 0 ? this.length + from : from;
return this.push.apply(this, rest);
};
var explode = value.split(',');
explode.remove(1);
var implode = explode.join(',');
Documentation:
fce: Split
fce: Join
fce: Array.remove
No jQuery required :P
<script type="text/javascript">
//var subject = '3,4,9';
//var subject = '3,,9';
var subject = ',,4,9';
var clean = Array();
var i = 0;
subject = subject.split(',');
for (var a in subject)
{
if(subject[a].length)
{
clean[i] = subject[a];
i++;
}
}
document.write(clean.join(','));
</script>
You may also use pure javascript. Let say you want to take off only "4":
value = value.replace(/4,?/, '')
or "3" and "9":
value = value.replace(/([39],?)+/, '')
I think this function will work for what you are trying to do: http://www.w3schools.com/jsref/jsref_split.asp
string.split(separator, limit)
use
array = string.split(separator);
to break a string into an array. then use this to join after manipulations.
string = array.join(separator);
var ary = value.split(',');
ary.splice(indexOfItemToRemove,1)
var result = ary.join(',');
This is discussed in another post:
remove value from comma separated values string
var removeValue = function(list, value, separator) {
separator = separator || ",";
var values = list.split(",");
for(var i = 0 ; i < values.length ; i++) {
if(values[i] == value) {
values.splice(i, 1);
return values.join(",");
}
}
return list;
}
You can use this function:
function removeComma(x) {
var str = '';
var subs = '';
for(i=1; i<=x.length; i++) {
subs = x.substring(i-1, i).trim();
if(subs !== ',') {
str = str+subs;
}
}
return str;
}