Issue 3956 - Convert domain whitelisting filters

lib/abp2blocklist.js

 /*
  * This file is part of Adblock Plus <https://adblockplus.org/>,
  * Copyright (C) 2006-2016 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/>.
  */
 
 /** @module abp2blocklist */
 
 "use strict";
 
 let filterClasses = require("filterClasses");
 let tldjs = require("tldjs");
 let punycode = require("punycode");
 
 const selectorLimit = 5000;
 const typeMap = filterClasses.RegExpFilter.typeMap;
+const whitelistableRequestTypes = (typeMap.IMAGE
+                                   | typeMap.STYLESHEET
+                                   | typeMap.SCRIPT
+                                   | typeMap.FONT
+                                   | typeMap.MEDIA
+                                   | typeMap.POPUP
+                                   | typeMap.OBJECT
+                                   | typeMap.OBJECT_SUBREQUEST
+                                   | typeMap.XMLHTTPREQUEST
+                                   | typeMap.PING
+                                   | typeMap.SUBDOCUMENT
+                                   | typeMap.OTHER);
 
 function parseDomains(domains, included, excluded)
 {
   for (let domain in domains)
   {
     if (domain != "")
     {
       let enabled = domains[domain];
       domain = punycode.toASCII(domain.toLowerCase());
 
@@ skipping 190 matching lines @@
       filter.contentType & typeMap.DOCUMENT &&
       parsed.justHostname)
   {
     rules.push({
       trigger: {
         "url-filter": ".*",
         "if-domain": addDomainPrefix([parsed.hostname])
       },
       action: {type: "ignore-previous-rules"}
     });
-    // If the filter contains multiple options we'll need to generate further
-    // rules for it, but if not we can simply return now.
-    if (filter.contentType == typeMap.DOCUMENT)

[Sebastian Noack, 2016/05/17 10:55:24]

What if the filter is @@||example.com$document,elemhide?

Then we wouldn't bail out here, though we don't have to create another rule
either. I think we have to check for IMAGE, SUBDOCUMENT, SCRIPT, etc. explicitly
below. Perhaps move the respective mask to a const to avoid duplication.

[kzar, 2016/05/17 11:23:34]

Done.

-      return rules;
+    // If the filter contains other supported options we'll need to generate
+    // further rules for it, but if not we can simply return now.
+    if (!(filter.contentType | whitelistableRequestTypes))
+      return;
   }
 
   let trigger = {"url-filter": parsed.regexp};
 
   // Limit rules to HTTP(S) URLs
   if (!/^(\^|http)/i.test(trigger["url-filter"]))
     trigger["url-filter"] = "^https?://.*" + trigger["url-filter"];
 
   // For rules containing only a hostname we know that we're matching against
   // a lowercase string unless the matchCase option was passed.
@@ skipping 12 matching lines @@
     trigger["resource-type"] = getResourceTypes(filter);
   if (filter.thirdParty != null)
     trigger["load-type"] = [filter.thirdParty ? "third-party" : "first-party"];
 
   if (included.length > 0)
     trigger["if-domain"] = addDomainPrefix(included);
   else if (excluded.length > 0)
     trigger["unless-domain"] = addDomainPrefix(excluded);
 
   rules.push({trigger: trigger, action: {type: action}});
-
-  return rules;

[Sebastian Noack, 2016/05/17 10:55:24]

You don't have to return the rules here anymore.

[kzar, 2016/05/17 11:23:34]

Oops, Done.

 }
 
 function hasNonASCI(obj)
 {
   if (typeof obj == "string")
   {
     if (/[^\x00-\x7F]/.test(obj))
       return true;
   }
 
@@ skipping 90 matching lines @@
     return;
   if (filter instanceof filterClasses.RegExpFilter &&
       filter.regexpSource == null)
     return;
 
   if (filter instanceof filterClasses.BlockingFilter)
     this.requestFilters.push(filter);
 
   if (filter instanceof filterClasses.WhitelistFilter)
   {
-    if (filter.contentType & (typeMap.DOCUMENT
-                              | typeMap.IMAGE
-                              | typeMap.STYLESHEET
-                              | typeMap.SCRIPT
-                              | typeMap.FONT
-                              | typeMap.MEDIA
-                              | typeMap.POPUP
-                              | typeMap.OBJECT
-                              | typeMap.OBJECT_SUBREQUEST
-                              | typeMap.XMLHTTPREQUEST
-                              | typeMap.PING
-                              | typeMap.SUBDOCUMENT
-                              | typeMap.OTHER))
+    if (filter.contentType & (typeMap.DOCUMENT | whitelistableRequestTypes))
       this.requestExceptions.push(filter);
 
       if (filter.contentType & typeMap.ELEMHIDE)
         this.elemhideExceptions.push(filter);
   }
 
   if (filter instanceof filterClasses.ElemHideFilter)
     this.elemhideFilters.push(filter);
 
   if (filter instanceof filterClasses.ElemHideException)
@@ skipping 54 matching lines @@
 
   for (let filter of this.elemhideExceptions)
     convertFilterAddRules(rules, filter, "ignore-previous-rules", false);
   for (let filter of this.requestFilters)
     convertFilterAddRules(rules, filter, "block", true);
   for (let filter of this.requestExceptions)
     convertFilterAddRules(rules, filter, "ignore-previous-rules", true);
 
   return rules.filter(rule => !hasNonASCI(rule));
 };