Issue 6735 - Store domains in lower case

lib/filterClasses.js

Index: lib/filterClasses.js
===================================================================
--- a/lib/filterClasses.js
+++ b/lib/filterClasses.js
@@ -382,38 +382,38 @@
   /**
    * 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
@@ -480,17 +480,17 @@
     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(".");
@@ -506,17 +506,17 @@
    * @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;
 
@@ -607,19 +607,19 @@
     // 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,
 
@@ -750,50 +750,70 @@
     {
       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)
-      {
-        contentType |= RegExpFilter.typeMap[option];
+
+      let inverse = option[0] == "~";
+      if (inverse)
+        option = option.substr(1);
 
-        if (option == "CSP" && value)
-          csp = value;
-      }
-      else if (option[0] == "~" && option.substr(1) in RegExpFilter.typeMap)
+      let type = RegExpFilter.typeMap[option.replace(/-/, "_").toUpperCase()];
+      if (type)
       {
-        if (contentType == null)
-          ({contentType} = RegExpFilter.prototype);
-        contentType &= ~RegExpFilter.typeMap[option.substr(1)];
+        if (inverse)
+        {
+          if (contentType == null)
+            ({contentType} = RegExpFilter.prototype);
+          contentType &= ~type;
+        }
+        else
+        {
+          contentType |= type;
+
+          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 == "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");
+      {
+        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");
+        }
+      }
     }
   }
 
   // For security reasons, never match $rewrite filters
   // against requests that might load any code to be executed.
   if (rewrite != null)
   {
     if (contentType == null)