正则表达式从字符串中提取重复序列

Question

I am trying to extract the function arguments from my string s

var s = "function (a, b,   c) { return \'hello\'; }";
var re = /^function[^\(]*\(\W*(?:(\w+)[,\s)]*)+\)/g;

console.log( re.exec(s) );

/*
[ 'function (a, b,   c)',
  'c',
  index: 0,
  input: 'function (a, b,   c) { return \'hello\'; }' ]
*/

The problem

It is only capturing c .

Desired output

/*
[ 'function (a, b,   c)',
  'a',
  'b',
  'c',
  index: 0,
  input: 'function (a, b,   c) { return \'hello\'; }' ]
*/

Disclaimer

This code is used in a module and must be accomplished with a single regular expression . Other techniques I've seen on StackOverflow will not work.

Answer 1

You can't have a variable number of capturing groups within a regular expression. The best you can probably do is:

var s = "function (a, b,   c) { return \'hello\'; }";
s.match(/.*?\((.*)\)/)[1].split(/[,\s]+/);

// returns ["a", "b", "c"]

Answer 2

I would suggest to divide the task to sub-tasks:

• Retrieve list of arguments
• Split retrieved list
• Compose the result

Like this:

var reFuncDecl = /^function\s*\(([^)]+)\)/g,
    reSplitArg = /[,\s]+/;

function funcInfo(s) {
    var matches = reFuncDecl.exec(s),
    args = matches[1].split(reSplitArg);
    reFuncDecl.lastIndex = 0;
    return {
        declaration: matches[0],
        args: args,
        input: s
    };
}


var s = "function (a, b,   c,d,e,\nf) { return \'hello\'; }",
    info = funcInfo(s);
for(var prop in info) {
    document.write(prop + ': ' + info[prop] + '<br />');
}
console.log(funcInfo(s));​

DEMO