Help parsing string (City, State Zip) with JavaScript

Question

I've got a string with the following format:

City, State ZIP

I'd like to get City and State from this string.

How can I do that with JavaScript? edit: note that he doesn't mention he already has the zip code when he gets here, if that helps you in your solution ~~ drachenstern

Answer 1

var address = "San Francisco, CA 94129";

function parseAddress(address) {
    // Make sure the address is a string.
    if (typeof address !== "string") throw "Address is not a string.";

    // Trim the address.
    address = address.trim();

    // Make an object to contain the data.
    var returned = {};

    // Find the comma.
    var comma = address.indexOf(',');

    // Pull out the city.
    returned.city = address.slice(0, comma);

    // Get everything after the city.
    var after = address.substring(comma + 2); // The string after the comma, +2 so that we skip the comma and the space.

    // Find the space.
    var space = after.lastIndexOf(' ');

    // Pull out the state.
    returned.state = after.slice(0, space);

    // Pull out the zip code.
    returned.zip = after.substring(space + 1);

    // Return the data.
    return returned;
}

address = parseAddress(address);

This is probably better then using regular expressions and String.split(), as it takes into account that the state and city may have spaces.

EDIT: Bug fix: It only included the first word of multi-word state names.

And here's a minified version. :D

function parseAddress(a) {if(typeof a!=="string") throw "Address is not a string.";a=a.trim();var r={},c=a.indexOf(',');r.city=a.slice(0,c);var f=a.substring(c+2),s=f.lastIndexOf(' ');r.state=f.slice(0,s);r.zip=f.substring(s+1);return r;}

Answer 2

There are many ways to do this. Here's a very naive one:

var parts = "City, State ZIP".split(/\s+/); // split on whitespace
var city = parts[0].slice(0, parts[0].length - 1); // remove trailing comma
var state = parts[1];
var zip = parts[2];

Here's one that accounts for the presence of spaces in either the city or state or both:

var parts = "san fran bay, new mex state 666666".split(/\s+|,/),
    partition = parts.indexOf(""),
    city = parts.slice(0, partition).join(" "),
    state = parts.slice(partition + 1, -1).join(" "),
    zip = parts.pop();

This last one only works if you're lucky enough to be in an environment that supports destructuring assignment:

var city, statezip, state, zip, parts;
[city, statezip] = "Spaced City, New Mexico ZIP".split(/,\s*/);
parts = statezip.split(/\s+/);
zip = parts.pop();
state = parts.join(" ");

None of these perform any validation, of course.

Answer 3

Ok, since advising regex isn't good, here's my solution. It takes into account cities that have spaces in them, which the other responses here don't seem to do:

    var str = "New York, NY 20101";
    var cityAndRest = str.split(',');
    var city = cityAndRest[0];
    var stateAndZip = cityAndRest[1].trim().split(' ');
    var state = stateAndZip[0];
    var zip = stateAndZip[1];

Answer 4

First assumption: American addresses only.

First find out if the last 5 or the last 10 characters are numeric. A simpler test is to see if the last character is numeric. If so, it's probably got the zip code included. Then a simple test to see if the last 10 contains a space (city #####) or if the last ten include a dash (12345-6789) to figure out if it's a 5 or 5+4 zip. We'll test for a hyphen and no space. (city-du-lac 12345 captures -lac 12345)

Next, all addresses split the city and state by a comma, so we want the last comma. Find the index of the last comma, and split there. I don't know of a city that uses commas in it's name, and I'm sure not gonna let my parser burst on an unknown if I can help it. I do ignore the fact that Washington DC could also be Washington, DC. I figure edge cases are for libraries, not one off scripts.

Lastly, trim everything that remains to remove trailing or leading spaces.

function IsNumeric(n) {
  return !isNaN(parseFloat(n)) && isFinite(n);
}

var addr = 'New York City, New York 10101';
//var addr = 'San Bernadino, CA 11111';
function getCityStateZip(addr){
  var city; var state;var zip;
  city = ''; state = ''; zip = '';
  var addrLen = addr.length;
  if ( IsNumeric( addr.substring(addrLen - 1) ) ) {
    //contains a zipcode - just a sanity check
    //get last 10 characters for testing easily
    var lastTen = addr.substring( addrLen - 10 );
    if ( lastTen.indexOf('-') > 0 && ( lastTen.indexOf(' ') == -1 ) ) {
      //found a hyphen and no space (matches our complex rule for zipcodes)
      zip = lastTen;
    } else {
      zip = addr.substring( addrLen - 5 ); //assume a basic 5 zip code
    }
  }
  var zipLen = zip.length;
  addrLen = addrLen - zipLen - 1;
  addr = addr.substring(0, addrLen ); //remove the chars we just moved into zip

  var lastComma = addr.lastIndexOf(',');
  if ( lastComma == -1 ) {
    //you have a problem, how do you want to handle it?
  }
  city = addr.substring(0,lastComma); //skip the comma itself, yes?
  state = addr.substring(lastComma + 2);
  return { 'city':city,'state': state,'zip': zip};
}

getCityStateZip(addr)

IsNumeric js function can be found here Validate decimal numbers in JavaScript - IsNumeric()