Issue 6735 - Store domains in lower case

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 369 matching lines @@
   domainSource: null,
 
   /**
    * Separator character used in domainSource property, must be
    * overridden by subclasses
    * @type {string}
    */
   domainSeparator: null,
 
   /**
-   * Determines whether domainSource is already upper-case,
+   * Determines whether domainSource is already lower-case,
    * can be overridden by subclasses.
    * @type {boolean}
    */
-  domainSourceIsUpperCase: false,
+  domainSourceIsLowerCase: false,
 
   /**
    * Map containing domains that this filter should match on/not match
    * on or null if the filter should match on all domains
    * @type {?Map.<string,boolean>}
    */
   get domains()
   {
     let domains = null;
 
     if (this.domainSource)
     {
       let source = this.domainSource;
-      if (!this.domainSourceIsUpperCase)
+      if (!this.domainSourceIsLowerCase)
       {
-        // RegExpFilter already have uppercase domains
-        source = source.toUpperCase();
+        // RegExpFilter already have lowercase domains
+        source = source.toLowerCase();
       }
       let list = source.split(this.domainSeparator);
       if (list.length == 1 && list[0][0] != "~")
       {
         // Fast track for the common one-domain scenario
         domains = new Map([["", false], [list[0], true]]);
       }
       else
       {
         let hasIncludes = false;
@@ skipping 56 matching lines @@
 
     // If no domains are set the rule matches everywhere
     if (!this.domains)
       return true;
 
     // If the document has no host name, match only if the filter
     // isn't restricted to specific domains
     if (!docDomain)
       return this.domains.get("");
 
-    docDomain = docDomain.replace(/\.+$/, "").toUpperCase();
+    docDomain = docDomain.replace(/\.+$/, "").toLowerCase();
 
     while (true)
     {
       let isDomainIncluded = this.domains.get(docDomain);
       if (typeof isDomainIncluded != "undefined")
         return isDomainIncluded;
 
       let nextDot = docDomain.indexOf(".");
       if (nextDot < 0)
         break;
       docDomain = docDomain.substr(nextDot + 1);
     }
     return this.domains.get("");
   },
 
   /**
    * Checks whether this filter is active only on a domain and its subdomains.
    * @param {string} docDomain
    * @return {boolean}
    */
   isActiveOnlyOnDomain(docDomain)
   {
     if (!docDomain || !this.domains || this.domains.get(""))
       return false;
 
-    docDomain = docDomain.replace(/\.+$/, "").toUpperCase();
+    docDomain = docDomain.replace(/\.+$/, "").toLowerCase();
 
     for (let [domain, isIncluded] of this.domains)
     {
       if (isIncluded && domain != docDomain)
       {
         if (domain.length <= docDomain.length)
           return false;
 
         if (!domain.endsWith("." + docDomain))
           return false;
@@ skipping 80 matching lines @@
   else
   {
     // No need to convert this filter to regular expression yet, do it on demand
     this.regexpSource = regexpSource;
   }
 }
 exports.RegExpFilter = RegExpFilter;
 
 RegExpFilter.prototype = extend(ActiveFilter, {
   /**
-   * @see ActiveFilter.domainSourceIsUpperCase
+   * @see ActiveFilter.domainSourceIsLowerCase
    */
-  domainSourceIsUpperCase: true,
+  domainSourceIsLowerCase: true,
 
   /**
    * Number of filters contained, will always be 1 (required to
    * optimize Matcher).
    * @type {number}
    */
   length: 1,
 
   /**
    * @see ActiveFilter.domainSeparator
@@ skipping 120 matching lines @@
     text = match.input.substr(0, match.index);
     for (let option of options)
     {
       let value = null;
       let separatorIndex = option.indexOf("=");
       if (separatorIndex >= 0)
       {
         value = option.substr(separatorIndex + 1);
         option = option.substr(0, separatorIndex);
       }
-      option = option.replace(/-/, "_").toUpperCase();
-      if (option in RegExpFilter.typeMap)
+
+      let inverse = option[0] == "~";
+      if (inverse)
+        option = option.substr(1);
+
+      let type = RegExpFilter.typeMap[option.replace(/-/, "_").toUpperCase()];
+      if (type)
       {
-        contentType |= RegExpFilter.typeMap[option];
+        if (inverse)
+        {
+          if (contentType == null)
+            ({contentType} = RegExpFilter.prototype);
+          contentType &= ~type;
+        }
+        else
+        {
+          contentType |= type;
 
-        if (option == "CSP" && value)
-          csp = value;
+          if (type == RegExpFilter.typeMap.CSP && value)

[Manish Jethani, 2018/06/08 14:21:14]

By the way in the case of csp we quietly ignore the option if it has no value,
so we are not being consistent. Anyway we should address these things
separately, not as part of this patch.

[kzar, 2018/06/15 10:44:03]

Yea, agreed. By the way Rosie is reimplementing this stuff in Python ATM, so if
you change the behaviour ping her in IRC.

+            csp = value;
+        }
       }
-      else if (option[0] == "~" && option.substr(1) in RegExpFilter.typeMap)
+      else
       {
-        if (contentType == null)
-          ({contentType} = RegExpFilter.prototype);
-        contentType &= ~RegExpFilter.typeMap[option.substr(1)];
+        switch (option.toLowerCase())
+        {
+          case "match-case":
+            matchCase = !inverse;
+            break;
+          case "domain":
+            if (!value)
+              return new InvalidFilter(origText, "filter_unknown_option");
+            domains = value.toLowerCase();
+            break;
+          case "third-party":
+            thirdParty = !inverse;
+            break;
+          case "collapse":
+            collapse = !inverse;
+            break;
+          case "sitekey":
+            if (!value)

[Manish Jethani, 2018/06/08 14:19:42]

There's a bit of code repetition here but I'm OK with it.

[kzar, 2018/06/15 10:44:03]

Yea, I think it's fine.

+              return new InvalidFilter(origText, "filter_unknown_option");
+            sitekeys = value.toUpperCase();
+            break;
+          case "rewrite":
+            if (!value)

[Manish Jethani, 2018/06/08 14:19:42]

Note that this will get updated for the rewrite option in the other patch.

+              return new InvalidFilter(origText, "filter_unknown_option");
+            rewrite = value;
+            break;
+          default:
+            return new InvalidFilter(origText, "filter_unknown_option");
+        }
       }
-      else if (option == "MATCH_CASE")
-        matchCase = true;
-      else if (option == "~MATCH_CASE")
-        matchCase = false;
-      else if (option == "DOMAIN" && value)
-        domains = value.toUpperCase();
-      else if (option == "THIRD_PARTY")
-        thirdParty = true;
-      else if (option == "~THIRD_PARTY")
-        thirdParty = false;
-      else if (option == "COLLAPSE")
-        collapse = true;
-      else if (option == "~COLLAPSE")
-        collapse = false;
-      else if (option == "SITEKEY" && value)
-        sitekeys = value.toUpperCase();
-      else if (option == "REWRITE" && value)
-        rewrite = value;
-      else
-        return new InvalidFilter(origText, "filter_unknown_option");
     }
   }
 
   // For security reasons, never match $rewrite filters
   // against requests that might load any code to be executed.
   if (rewrite != null)
   {
     if (contentType == null)
       ({contentType} = RegExpFilter.prototype);
     contentType &= ~(RegExpFilter.typeMap.SCRIPT |
@@ skipping 278 matching lines @@
  */
 function ElemHideEmulationFilter(text, domains, selector)
 {
   ElemHideBase.call(this, text, domains, selector);
 }
 exports.ElemHideEmulationFilter = ElemHideEmulationFilter;
 
 ElemHideEmulationFilter.prototype = extend(ElemHideBase, {
   type: "elemhideemulation"
 });