Javascript RegEx match URLs for tokens extraction

Question

Given a URL like this:

localhost:3000/sell-residential/house-apartment-penthouse-size-30-any-for-0-100000-in-miami%3b+orlando%3b/list-1?numRooms=2&numBaths=2&numParkingSpaces=1&misc=photo-only&interiorFeatures=heating%2Clift&exteriorFeatures=garden%2Cbalcony

I would like to extract some values using RegEx. What I have done is the following fully-commented function:

function listingTokens(reqUrl){

    let retValue = {page: LISTING_PAGE_URI};

    const path_parameters_matcher = /(?:([^?]+))/g;
    // Group1 = url before query string
    // Group2 = url after query string
    let match = reqUrl.match(path_parameters_matcher);

    let path = match[0];
    let params = match[1];

    const path_matcher = /(?:([^\/\/]+))/g;
    // get the path tokens separed by /
    let path_tokens = path.match(path_matcher);

    let filter_values = [];
    // first path token --> Mandatory gives the channel and the category
    let channel_category = path_tokens[0];
    // second path token --> Mandatory gives main filter values
    let filters = path_tokens[1];
    // third path token --> Mandatory page requested
    let list_page = reqUrl.match(page_matcher)[1];

    // exctract channel and category splitting the previous extracted token
    let channel = channel_category.split('-')[0];
    let category = channel_category.split('-').length > 1 ? channel_category.split('-')[1] : '';

    // default filters object
    let filtersObj = {
        "channel": channel || null,
        "category_type": category || null,
        "property_type": [],
        "localities": [],
        "min_price": "any",
        "max_price": "any",
        "min_meter": "any",
        "max_meter": "any",
        "bedroom_number": "any"
    };

    // Regular expressions for match the filter values considering random order and possible missing path values
    let property_filters_matcher = /(?=house-).*(?=-size-)|(?=house-).*(?=-for-)|(?=house-).*(?=-in-)|(?=house-).*/;
    let size_filters_matcher = /(?=size-).*(?=-house-)|(?=size-).*(?=-for-)|(?=size-).*(?=-in-)|(?=size-).*/;
    let price_filters_matcher = /(?=for-).*(?=-size-)|(?=for-).*(?=-house-)|(?=for-).*(?=-in-)|(?=for-).*/;
    let locality_filters_matcher = /(?=in-).*(?=-size-)|(?=in-).*(?=-for-)|(?=in-).*(?=-house-)|(?=in-).*/;
    // Regular expressions for match tokens separed by -
    const tokens_matcher = /(?:([^-]+))/g;

    // Should match for ex. house-apartment-penthouse
    match = property_filters_matcher.exec(filters);
    if(match){
        // the first token would be the filter name and the spread result would be the values
        let [filter, ...values] = match[0].match(tokens_matcher);
        filtersObj.property_type = values;
    }
    // Should match for ex. size-30-any
    match = size_filters_matcher.exec(filters);
    if(match){
        // the first token would be the filter name the second the from size and the third to size
        let [filter, from, to] = match[0].match(tokens_matcher);
        filtersObj.min_meter = from;
        filtersObj.max_meter = to;
    }
    // Should match for ex. for-0-100000
    match = price_filters_matcher.exec(filters);
    if(match){
        // the first token would be the filter name the second the from price and the third to price
        let [filter, from, to] = match[0].match(tokens_matcher);
        filtersObj.min_price = from;
        filtersObj.max_price = to;
    }
    // Should match for ex. in-miami%3b+orlando%3b
    match = locality_filters_matcher.exec(filters);
    if(match){
        // the first token would be the filter name the second the locality or localities
        let [filter, value] = match[0].match(tokens_matcher);
        // clean the values and split by separator ; (%3b)
        let local = value.replace("+", "").split(';');
        let localities = [];
        for(let i = 0; i < local.length; i++){
            // if not empty add to the result
            if(local[i]){
                localities.push({"key": local[i], "displayValue": local[i].replace(",", " "), "withZones": false});
            }
        }

        filtersObj.localities = localities;
    }

    // Merge the objects in the final result
    Object.assign(retValue, {pageNumber: list_page, selected_filters: filtersObj});
    return retValue;
}

I'm not handling the possible query string values by now, but I think it would be something similar to the filters matching.

What I am asking is if there is a better way to extract those values -- I'm confident there is, because I'm pretty new in ES2015 and advanced RegExes are not my strongest field of knowledge.

Answer 1

I can give you some feedback on your regexes.

First of all, you don't need the parenthesis in some of these. These two:

/(?:([^?]+))/g
/(?:([^-]+))/g

would become:

/[^?]+/g
/[^-]+/g

The first capture group was equal to the entire matched group, so you just use [0] (which you appear to be doing already, except for the one line).

Now the same thing applies to this regex too, but you can also remove one set of \/s:

/(?:([^\/\/]+))/g

becomes:

/[^\/]+/g

Next, there's this regex, and two others like it. I have added spaces so you can see the repetition:

/(?=house-).*(?=-size-)|
 (?=house-).*(?=-for-) |
 (?=house-).*(?=-in-)  |
 (?=house-).*/

As it is written, the regex takes 427 steps to find a match in your example string (according to regex101.com). There's no compelling reason to be using look aheads for "house-" here, either. It will just be eaten by by the .*, so you might as well just extract it:

/house-(?:.*(?=-size-)|.*(?=-for-)|.*(?=-in-)|.*)/

This cuts it down to 391 steps, but it is still getting hung up in the .* portion.

Looking further into your code, it seems that you just want to get the two values after it: house-???????-???????-. Your other regex already does that, so you can just use it here, instead. The other thing I would suggest is using \b, which ensures that there's a word boundary (so the following will not match something starting with "penthouse"):

/\bhouse-([^-]+)-([^-]+)/

This cuts it down to 18 steps. That's a HUGE improvement from the original 427. It's also shorter and more readable than your original.

You can get the matches by using:

match = property_filters_matcher.exec(filters);
if(match){
    filtersObj.min_meter = match[1];
    filtersObj.max_meter = match[2];
}

This will allow the regex to be more robust, and also improve some of the other parts of your code.