Issue 7052 - Use string-based matching for literal patterns

lib/common.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
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
  * along with Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 "use strict";
 
 /**
+ * Regular expression used to match the <code>||</code> prefix in an otherwise
+ * literal pattern.
+ * @type {RegExp}
+ */
+let doubleAnchorRegExp = new RegExp(filterToRegExp("||") + "$");
+
+/**
+ * Checks whether the given pattern is a string of literal characters with no
+ * wildcards or any other special characters. If the pattern is prefixed with a
+ * <code>||</code> but otherwise contains no special characters, it is still
+ * considered to be a literal pattern.
+ * @param {string} pattern
+ * @returns {boolean}
+ */
+function isLiteralPattern(pattern)
+{
+  return !/[*^|]/.test(pattern.replace(/^\|{2}/, ""));
+}
+
+exports.isLiteralPattern = isLiteralPattern;
+
+/**
+ * Checks whether the given URL matches the given pattern.
+ * @param {string} location The URL to check.
+ * @param {string} pattern The pattern to match. This may be prefixed with a
+ *   <code>||</code> to match the beginning of the URL. Any other characters
+ *   are treated literally.
+ * @returns {boolean}
+ */
+function locationMatchesPattern(location, pattern)
+{
+  if (pattern[0] == "|" && pattern[1] == "|")
+  {
+    let index = location.indexOf(pattern.substring(2));
+
+    // The "||" prefix requires that the text that follows does not start with
+    // a forward slash. Normally this is part of the generated regular
+    // expression, but since we're faking it here with string-based matching we

[Manish Jethani, 2018/10/19 21:59:13]

Since it's all in the same file now I don't think this comment adds much value
(it's potentially misleading actually because "normally" implies this is not
normal, but half the filters are actually going to go through this path).

+    // need to do the check ourselves.
+    return index != -1 && location[index] != "/" &&
+           doubleAnchorRegExp.test(location.substring(0, index));
+  }
+
+  return location.includes(pattern);
+}
+
+exports.locationMatchesPattern = locationMatchesPattern;
+
+/**
  * Converts raw text into a regular expression string
  * @param {string} text the string to convert
  * @return {string} regular expression representation of the text
  */
 function textToRegExp(text)
 {
   return text.replace(/[-/\\^$*+?.()|[\]{}]/g, "\\$&");
 }
 
 exports.textToRegExp = textToRegExp;
@@ skipping 176 matching lines @@
     // Note that the first group in the regular expression is optional. If it
     // doesn't match (e.g. "#foo::nth-child(1)"), type will be an empty string.
     qualifiedSelector += sub.substr(0, index) + type + qualifier + rest;
   }
 
   // Remove the initial comma and space.
   return qualifiedSelector.substr(2);
 }
 
 exports.qualifySelector = qualifySelector;