[$csp2 adblockpluscore] Issue 6329 - Add the CSP filter type

lib/filterClasses.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 80 matching lines @@
 /**
  * Regular expression that RegExp filters specified as RegExps should match
  * @type {RegExp}
  */
 Filter.regexpRegExp = /^(@@)?\/.*\/(?:\$~?[\w-]+(?:=[^,\s]+)?(?:,~?[\w-]+(?:=[^,\s]+)?)*)?$/;
 /**
  * Regular expression that options on a RegExp filter should match
  * @type {RegExp}
  */
 Filter.optionsRegExp = /\$(~?[\w-]+(?:=[^,]+)?(?:,~?[\w-]+(?:=[^,]+)?)*)$/;
+/**
+ * Regular expression that matches an invalid Content Security Policy
+ * @type {RegExp}
+ */
+Filter.invalidCSPRegExp = /(;|^) ?(base-uri|referrer|report-to|report-uri|upgrade-insecure-requests)\b/i;
 
 /**
  * Creates a filter of correct type from its text representation - does the
  * basic parsing and calls the right constructor then.
  *
  * @param {string} text   as in Filter()
  * @return {Filter}
  */
 Filter.fromText = function(text)
 {
@@ skipping 54 matching lines @@
  * Removes unnecessary whitespaces from filter text, will only return null if
  * the input parameter is null.
  * @param {string} text
  * @return {string}
  */
 Filter.normalize = function(text)
 {
   if (!text)
     return text;
 
-  // Remove line breaks and such
+  // Remove line breaks, tabs etc
   text = text.replace(/[^\S ]+/g, "");
 
   // Don't remove spaces inside comments
   if (/^ *!/.test(text))
     return text.trim();
 
   // Special treatment for element hiding filters, right side is allowed to
   // contain spaces
   if (Filter.elemhideRegExp.test(text))
   {
     let [, domain, separator, selector] = /^(.*?)(#@?#?)(.*)$/.exec(text);
     return domain.replace(/ +/g, "") + separator + selector.trim();
   }
 
-  // For most regexp filters we strip all whitespace.
+  // For most regexp filters we strip all spaces, but $csp filter options
+  // are allowed to contain single (non trailing) spaces.
   let strippedText = text.replace(/ +/g, "");
-  if (!/csp=/i.test(strippedText))
+  if (!strippedText.includes("$") || !/\bcsp=/i.test(strippedText))
     return strippedText;
 
   let optionsMatch = Filter.optionsRegExp.exec(strippedText);
   if (!optionsMatch)
     return strippedText;
 
-  // But since the values of $csp filter options are allowed to contain single
-  // (non trailing) spaces we have to be more careful if they might be present.
+  // For $csp filters we must first separate out the options part of the
+  // text, being careful to preserve its spaces.
   let beforeOptions = strippedText.substring(0, optionsMatch.index);
-  let optionsText = text;
-  for (let i = beforeOptions.split("$").length; i > 0; i--)
-    optionsText = optionsText.substr(optionsText.indexOf("$") + 1);
-
-  let options = [];
-  for (let option of optionsText.split(","))
-  {
-    let cspMatch = /^( *c *s *p *=)([^,]+)/i.exec(option);
+  let strippedDollarIndex = -1;
+  let dollarIndex = -1;
+  do
+  {
+    strippedDollarIndex = beforeOptions.indexOf("$", strippedDollarIndex + 1);
+    dollarIndex = text.indexOf("$", dollarIndex + 1);
+  }
+  while (strippedDollarIndex != -1);
+  let optionsText = text.substr(dollarIndex + 1);
+
+  // Then we can normalize spaces in the options part safely
+  let options = optionsText.split(",");
+  for (let i = 0; i < options.length; i++)
+  {
+    let option = options[i];
+    let cspMatch = /^ *c *s *p *=/i.exec(option);
     if (cspMatch)
     {
-      options.push(
-        cspMatch[1].replace(/ +/g, "") + cspMatch[2].trim().replace(/ +/g, " ")
-      );
+      options[i] = cspMatch[0].replace(/ +/g, "") +
+                   option.substr(cspMatch[0].length).trim().replace(/ +/g, " ");
     }
     else
-      options.push(option.replace(/ +/g, ""));
+      options[i] = option.replace(/ +/g, "");
   }
 
   return beforeOptions + "$" + options.join();
 };
 
 /**
  * @see filterToRegExp
  */
 Filter.toRegExp = filterToRegExp;
 
@@ skipping 546 matching lines @@
         option = option.substr(0, separatorIndex);
       }
       option = option.replace(/-/, "_").toUpperCase();
       if (option in RegExpFilter.typeMap)
       {
         if (contentType == null)
           contentType = 0;
         contentType |= RegExpFilter.typeMap[option];
 
         if (option == "CSP" && typeof value != "undefined")
-        {
-          if (csp)
-            csp.push(value);
-          else
-            csp = [value];
-        }
+          csp = value;
       }
       else if (option[0] == "~" && option.substr(1) in RegExpFilter.typeMap)
       {
         if (contentType == null)
           ({contentType} = RegExpFilter.prototype);
         contentType &= ~RegExpFilter.typeMap[option.substr(1)];
       }
       else if (option == "MATCH_CASE")
         matchCase = true;
       else if (option == "~MATCH_CASE")
@@ skipping 12 matching lines @@
         sitekeys = value.toUpperCase();
       else
         return new InvalidFilter(origText, "filter_unknown_option");
     }
   }
 
   try
   {
     if (blocking)
     {
-      if (csp)
-      {
-        csp = csp.join("; ").toLowerCase();
-
-        // Prevent filters from injecting report-uri or report-to directives
-        // since they are a privacy concern. Regexp based upon reBadCSP[1].
-        // [1] - https://github.com/gorhill/uBlock/blob/67e06f53b4d73df6179f6d320553a55da4ead40e/src/js/static-net-filtering.js#L1362
-        if (/(;|^)\s*report-(to|uri)\b/.test(csp))
-          return new InvalidFilter(origText, "filter_invalid_csp");
-      }
+      if (csp && Filter.invalidCSPRegExp.test(csp))
+        return new InvalidFilter(origText, "filter_invalid_csp");
 
       return new BlockingFilter(origText, text, contentType, matchCase, domains,
                                 thirdParty, sitekeys, collapse, csp);
     }
     return new WhitelistFilter(origText, text, contentType, matchCase, domains,
                                thirdParty, sitekeys);
   }
   catch (e)
   {
     return new InvalidFilter(origText, "filter_invalid_regexp");
@@ skipping 238 matching lines @@
  */
 function ElemHideEmulationFilter(text, domains, selector)
 {
   ElemHideBase.call(this, text, domains, selector);
 }
 exports.ElemHideEmulationFilter = ElemHideEmulationFilter;
 
 ElemHideEmulationFilter.prototype = extend(ElemHideBase, {
   type: "elemhideemulation"
 });