Issue 7296 - Implement lightweight URL parsing

lib/url.js

 /*
  * This file is part of Adblock Plus <https://adblockplus.org/>,
  * Copyright (C) 2006-present 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 22 matching lines @@
 {
   let map = new Map();
 
   for (let key in publicSuffixes)
     map.set(key, publicSuffixes[key]);
 
   return map;
 }
 
 /**
+ * A <code>URLInfo</code> object represents information about a URL. It is
+ * returned by <code>{@link parseURL}</code>.
+ */
+class URLInfo
+{
+  /**
+   * Creates a <code>URLInfo</code> object.
+   *
+   * @param {string} href The entire URL.
+   * @param {string} [protocol] The protocol scheme of the URL, including the
+   *   final <code>:</code>.
+   * @param {string} [hostname] The hostname of the URL.
+   *
+   * @private
+   */
+  constructor(href, protocol = "", hostname = "")
+  {
+    this._href = href;
+    this._protocol = protocol;
+    this._hostname = hostname;
+  }
+
+  /**
+   * The entire URL.
+   * @type {string}
+   */
+  get href()
+  {
+    return this._href;
+  }
+
+  /**
+   * The protocol scheme of the URL, including the final <code>:</code>.
+   * @type {string}
+   */
+  get protocol()
+  {
+    return this._protocol;
+  }
+
+  /**
+   * The hostname of the URL.
+   * @type {string}
+   */
+  get hostname()
+  {
+    return this._hostname;
+  }
+
+  /**
+   * Returns the entire URL.
+   * @returns {string} The entire URL.
+   */
+  toString()
+  {
+    return this._href;
+  }
+}
+
+/**
+ * Parses a URL to extract the protocol and the hostname. This is a lightweight
+ * alternative to the native <code>URL</code> object. Unlike the
+ * <code>URL</code> object, this function is not robust and will give incorrect
+ * results for invalid URLs. <em>Use this function with valid, normalized,
+ * properly encoded (IDNA and percent-encoding) URLs only.</em>
+ *
+ * @param {string} url The URL to parse.
+ * @returns {URLInfo} Information about the URL.
+ */
+function parseURL(url)
+{
+  let match = /^([^:]+:)(?:\/\/(?:[^/]*@)?(\[[^\]]*\]|[^:/]+))?/.exec(url);
+  return match ? new URLInfo(url, match[1], match[2]) : new URLInfo(url);

[hub, 2019/02/21 16:24:08]

if the parsing fails, then we only have a valid `_href` in URLInfo. I'm
wondering if instead we shouldn't just return null instead.

[Manish Jethani, 2019/02/23 07:32:05]

Actually since the function assumes that the URL will always be valid and
normalized, `match` should never be null (and if it is then an error should be
thrown).

I have updated the patch so it works this way now.

+}
+
+exports.parseURL = parseURL;
+
+/**
  * Normalizes a hostname.
  * @param {string} hostname
  * @returns {string}
  */
 function normalizeHostname(hostname)
 {
   return (hostname[hostname.length - 1] == "." ?
             hostname.replace(/\.+$/, "") : hostname).toLowerCase();
 }
 
@@ skipping 100 matching lines @@
   if (requestHostname == documentHostname)
     return false;
 
   if (!isDomain(requestHostname) || !isDomain(documentHostname))
     return true;
 
   return getBaseDomain(requestHostname) != getBaseDomain(documentHostname);
 }
 
 exports.isThirdParty = isThirdParty;