How can I match multiple occurrences with a regex

Question

I am trying to parse url-encoded strings that are made up of key=value pairs separated by either & or &.

The following will only match the first occurrence, breaking apart the keys and values into separate result elements:

var result = mystring.match(/(?:&|&)?([^=]+)=([^&]+)/)

The results for the string '1111342=Adam%20Franco&348572=Bob%20Jones' would be:

['1111342', 'Adam%20Franco']

Using the global flag, 'g', will match all occurrences, but only return the fully matched sub-strings, not the separated keys and values:

var result = mystring.match(/(?:&|&)?([^=]+)=([^&]+)/g)

The results for the string '1111342=Adam%20Franco&348572=Bob%20Jones' would be:

['1111342=Adam%20Franco', '&348572=Bob%20Jones']

While I could split the string on & and break apart each key/value pair individually, is there any way using JavaScript's regular expression support to match multiple occurrences of the pattern /(?:&|&)?([^=]+)=([^&]+)/ similar to PHP's preg_match_all() function?

I'm aiming for some way to get results with the sub-matches separated like:

[['1111342', '348572'], ['Adam%20Franco', 'Bob%20Jones']]

or

[['1111342', 'Adam%20Franco'], ['348572', 'Bob%20Jones']]

Answer 1

If you can get away with using map this is a four-line-solution:

var mystring = '1111342=Adam%20Franco&348572=Bob%20Jones';

var result = mystring.match(/(&|&)?([^=]+)=([^&]+)/g) || [];
result = result.map(function(i) {
  return i.match(/(&|&)?([^=]+)=([^&]+)/);
});

console.log(result);

Ain't pretty, ain't efficient, but at least it is compact. ;)

Answer 2

Well... I had a similar problem... I want an incremental / step search with RegExp (eg: start search... do some processing... continue search until last match)

After lots of internet search... like always (this is turning an habit now) I end up in StackOverflow and found the answer...

Whats is not referred and matters to mention is "lastIndex" I now understand why the RegExp object implements the "lastIndex" property

Answer 3

Splitting it looks like the best option in to me:

'1111342=Adam%20Franco&348572=Bob%20Jones'.split('&').map(x => x.match(/(?:&|&)?([^=]+)=([^&]+)/))

Answer 4

I would suggest an alternative regex, using sub-groups to capture name and value of the parameters individually:

function getUrlParams(url) {
  var re = /(?:\?|&(?:amp;)?)([^=&#]+)(?:=?([^&#]*))/g,
      match, params = {},
      decode = function (s) {return decodeURIComponent(s.replace(/\+/g, " "));};

  if (typeof url == "undefined") url = document.location.href;

  while (match = re.exec(url)) {
    params[decode(match[1])] = decode(match[2]);
  }
  return params;
}

var result = getUrlParams("http://maps.google.de/maps?f=q&source=s_q&hl=de&geocode=&q=Frankfurt+am+Main&sll=50.106047,8.679886&sspn=0.370369,0.833588&ie=UTF8&ll=50.116616,8.680573&spn=0.35972,0.833588&z=11&iwloc=addr");

result is an object:

{
  f: "q"
  geocode: ""
  hl: "de"
  ie: "UTF8"
  iwloc: "addr"
  ll: "50.116616,8.680573"
  q: "Frankfurt am Main"
  sll: "50.106047,8.679886"
  source: "s_q"
  spn: "0.35972,0.833588"
  sspn: "0.370369,0.833588"
  z: "11"
}

The regex breaks down as follows:

(?:            # non-capturing group
  \?|&         #   "?" or "&"
  (?:amp;)?    #   (allow "&", for wrongly HTML-encoded URLs)
)              # end non-capturing group
(              # group 1
  [^=&#]+      #   any character except "=", "&" or "#"; at least once
)              # end group 1 - this will be the parameter's name
(?:            # non-capturing group
  =?           #   an "=", optional
  (            #   group 2
    [^&#]*     #     any character except "&" or "#"; any number of times
  )            #   end group 2 - this will be the parameter's value
)              # end non-capturing group

Answer 5

If someone (like me) needs Tomalak's method with array support (ie. multiple select), here it is:

function getUrlParams(url) {
  var re = /(?:\?|&(?:amp;)?)([^=&#]+)(?:=?([^&#]*))/g,
      match, params = {},
      decode = function (s) {return decodeURIComponent(s.replace(/\+/g, " "));};

  if (typeof url == "undefined") url = document.location.href;

  while (match = re.exec(url)) {
    if( params[decode(match[1])] ) {
        if( typeof params[decode(match[1])] != 'object' ) {
            params[decode(match[1])] = new Array( params[decode(match[1])], decode(match[2]) );
        } else {
            params[decode(match[1])].push(decode(match[2]));
        }
    }
    else
        params[decode(match[1])] = decode(match[2]);
  }
  return params;
}
var urlParams = getUrlParams(location.search);

input ?my=1&my=2&my=things

result 1,2,things (earlier returned only: things)

Answer 6

Use window.URL:

> s = 'http://www.example.com/index.html?1111342=Adam%20Franco&348572=Bob%20Jones'
> u = new URL(s)
> Array.from(u.searchParams.entries())
[["1111342", "Adam Franco"], ["348572", "Bob Jones"]]