Class UriHelper

app/src/main/java/eu/faircode/email/UriHelper.java:52–663

import java.util.regex.Pattern;

public class UriHelper {
    // https://publicsuffix.org/
    private static final HashSet<String> suffixList = new HashSet<>();

    // https://raw.githubusercontent.com/publicsuffix/list/master/public_suffix_list.dat
    private static final String SUFFIX_LIST_NAME = "public_suffix_list.dat";

    // https://github.com/svenjacobs/leon
    // https://github.com/newhouse/url-tracking-stripper
    // https://maxchadwick.xyz/tracking-query-params-registry/
    private static final List<String> PARANOID_QUERY = Collections.unmodifiableList(Arrays.asList(
            // https://en.wikipedia.org/wiki/UTM_parameters
            "awt_a", // AWeber
            "awt_l", // AWeber
            "awt_m", // AWeber

            "icid", // Adobe
            "ef_id", // https://experienceleague.adobe.com/docs/advertising-cloud/integrations/analytics/mc/mc-ids.html
            "_ga", // Google Analytics
            "gclid", // Google
            "gclsrc", // Google ads
            "dclid", // DoubleClick (Google)
            "fbclid", // Facebook
            "igshid", // Instagram
            "msclkid", // https://help.ads.microsoft.com/apex/index/3/en/60000

            "mc_cid", // MailChimp
            "mc_eid", // MailChimp

            "zanpid", // Zanox (Awin)

            "kclickid", // https://support.freespee.com/hc/en-us/articles/202577831-Kenshoo-integration

            "oly_anon_id", "oly_enc_id", // https://training.omeda.com/knowledge-base/olytics-product-outline/
            "_openstat", // https://yandex.com/support/direct/statistics/url-tags.html
            "vero_conv", "vero_id", // https://help.getvero.com/cloud/articles/what-is-vero_id/
            "wickedid", // https://help.wickedreports.com/how-to-manually-tag-a-facebook-ad-with-wickedid
            "yclid", // https://ads-help.yahoo.co.jp/yahooads/ss/articledetail?lan=en&aid=20442
            "__s", // https://ads-help.yahoo.co.jp/yahooads/ss/articledetail?lan=en&aid=20442
            "guccounter", "guce_referrer", "guce_referrer_sig", // Yahoo
            "rb_clickid", // Russian
            "s_cid", // https://help.goacoustic.com/hc/en-us/articles/360043311613-Track-lead-sources
            "ml_subscriber", "ml_subscriber_hash", // https://www.mailerlite.com/help/how-to-integrate-your-forms-to-a-wix-website
            "twclid", // https://business.twitter.com/en/blog/performance-advertising-on-twitter.html
            "gbraid", "wbraid", // https://support.google.com/google-ads/answer/10417364
            "_hsenc", "__hssc", "__hstc", "__hsfp", "hsCtaTracking" // https://knowledge.hubspot.com/reports/what-cookies-does-hubspot-set-in-a-visitor-s-browser
    ));

    // https://github.com/snarfed/granary/blob/master/granary/facebook.py#L1789

    private static final List<String> FACEBOOK_WHITELIST_PATH = Collections.unmodifiableList(Arrays.asList(
            "/nd/", "/n/", "/story.php"
    ));

    private static final List<String> FACEBOOK_WHITELIST_QUERY = Collections.unmodifiableList(Arrays.asList(
            "story_fbid", "fbid", "id", "comment_id"
    ));