Issue 5325 - Add support for separator characters

lib/abp2blocklist.js

 /*
  * This file is part of Adblock Plus <https://adblockplus.org/>,
  * Copyright (C) 2006-2017 eyeo GmbH
  *
  * Adblock Plus is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 3 as
  * published by the Free Software Foundation.
  *
  * Adblock Plus is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
@@ skipping 130 matching lines @@
         break;
     }
 
     switch (c)
     {
       case "*":
         if (regexp.length > 0 && i < lastIndex && text[i + 1] != "*")
           regexp.push(".*");
         break;
       case "^":
-        if (i < lastIndex)
-          regexp.push(".");
+        let alphabet = "a-z";
+        // If justHostname is true and we've encountered a "^", it means we're
+        // still in the hostname part of the URL. Since hostnames are always
+        // lower case (Punycode), there's no need to include "A-Z" in the
+        // pattern. Further, subsequent code may lower-case the entire regular
+        // expression (if the URL contains only the hostname part), leaving us
+        // with "a-za-z", which would be redundant.
+        if (!justHostname)
+          alphabet = "A-Z" + alphabet;
+        let digits = "0-9";
+        // Note that the "-" must appear first here in order to retain its
+        // literal meaning within the brackets.
+        let specialCharacters = "-_.%";
+        let separator = "[^" + specialCharacters + alphabet + digits + "]";
+        if (i == 0)
+          regexp.push("^https?://(.*" + separator + ")?");
+        else if (i == lastIndex)
+          regexp.push("(" + separator + ".*)?$");
+        else
+          regexp.push(separator);
         break;
       case "|":
         if (i == 0)
         {
           regexp.push("^");
           break;
         }
         if (i == lastIndex)
         {
           regexp.push("$");
@@ skipping 376 matching lines @@
   {
     convertFilterAddRules(rules, filter, "block", true,
                           requestFilterExceptionDomains);
   }
 
   for (let filter of this.requestExceptions)
     convertFilterAddRules(rules, filter, "ignore-previous-rules", true);
 
   return rules.filter(rule => !hasNonASCI(rule));
 };