Issue 3670 - Make rules case sensitive where possible

lib/contentBlockerLists.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
@@ skipping 154 matching lines @@
   {
     result.push(domain);
 
     if (getBaseDomain(domain) == domain)
       result.push("www." + domain);
   }
 
   return result;
 }
 
+function caseSensitive(filter)

[Sebastian Noack, 2016/02/21 21:42:30]

It probably makes sense to integrate the logic here into the state machine that
converts the filter to a regular expression.

Also note that we have to convert filters that doesn't explicitly use the
$match_case option to lowercase. Otherwise, filters like ||EXAMPLE.COM would
never match, while they previously did match requests like
"https://example.com".

[kzar, 2016/02/24 15:43:29]

Done.

+{
+  if (filter.matchCase)
+    return true;
+
+  if (!(filter.text.startsWith("||") || filter.text.startsWith("://")))

[Sebastian Noack, 2016/02/21 21:42:30]

Filters usually don't start with "://". But filters like http://adserver.com are
supposed to be marked case sensitive.

[kzar, 2016/02/24 15:43:29]

Done.

+    return false;
+
+  let offset = filter.text.startsWith("||") ? 2 : 3;
+  let boundary = filter.text.substr(offset).search(/\/\?\*\^/);

[Sebastian Noack, 2016/02/21 21:42:30]

This regular expression would only match a seqeunce of "/?*^". However, we are
looking for any of these charecters. It seems you forgot the brackets. But as I
said in the comment above, this logic should be rather integrated in the state
machine that we have in place, anyway.

[kzar, 2016/02/24 15:43:29]

(Yep, forgot the brackets.)

+
+  if (boundary == -1)
+    return true;
+
+  return filter.text.substr(offset + boundary + 1).search(/[a-zA-Z]/) == -1;
+}
+
 function convertFilter(filter, action, withResourceTypes)
 {
   let trigger = {"url-filter": getRegExpSource(filter)};
   let included = [];
   let excluded = [];
 
+  if (caseSensitive(filter))
+    trigger["url-filter-is-case-sensitive"] = true;
+
   parseDomains(filter.domains, included, excluded);
 
   if (withResourceTypes)
     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)
@@ skipping 164 matching lines @@
   {
     while (selectors.length)
     {
       let selector = selectors.splice(0, selectorLimit).join(", ");
 
       // As of Safari 9.0 element IDs are matched as lowercase. We work around
       // this by converting to the attribute format [id="elementID"]
       selector = convertIDSelectorsToAttributeSelectors(selector);
 
       addRule({
-        trigger: {"url-filter": matchDomain},
+        trigger: {"url-filter": matchDomain,

[Sebastian Noack, 2016/02/21 21:42:30]

Same for element hiding filters; we have to make sure to convert the host to
lowercase.

[kzar, 2016/02/24 15:43:29]

Done.

+                  "url-filter-is-case-sensitive": true},
         action: {type: "css-display-none",
                  selector: selector}
       });
     }
   });
 
   for (let filter of elemhideExceptions)
     addRule(convertFilter(filter, "ignore-previous-rules", false));
   for (let filter of requestFilters)
     addRule(convertFilter(filter, "block", true));
   for (let filter of requestExceptions)
     addRule(convertFilter(filter, "ignore-previous-rules", true));
 
   return rules;
 };