Issue 3670 - Make rules case sensitive where possible

lib/contentBlockerList.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 32 matching lines @@
   }
 }
 
 function escapeRegExp(s)
 {
   return s.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
 }
 
 function matchDomain(domain)
 {
-  return "^https?://([^/:]*\\.)?" + escapeRegExp(domain) + "[/:]";
+  return "^https?://([^/:]*\\.)?" + escapeRegExp(domain).toLowerCase() + "[/:]";
 }
 
 function convertElemHideFilter(filter, elemhideSelectorExceptions)
 {
   let included = [];
   let excluded = [];
   let rules = [];
 
   parseDomains(filter.domains, included, excluded);
 
   if (excluded.length == 0 && !(filter.selector in elemhideSelectorExceptions))
     return {matchDomains: included.map(matchDomain), selector: filter.selector};
 }
 
+// Convert the "regexpSource" part of a filter's text to a regular expression,
+// also deciding if the expression can safely be converted to and matched as
+// lowercase.
 function toRegExp(text)
 {
   let result = [];
   let lastIndex = text.length - 1;
+  let containsHostname = false;
+  let caseSensitive = false;
 
   for (let i = 0; i < text.length; i++)
   {
     let c = text[i];
 
     switch (c)
     {
       case "*":
         if (result.length > 0 && i < lastIndex && text[i + 1] != "*")
           result.push(".*");
         break;
       case "^":
         if (i < lastIndex)
           result.push(".");
         break;
       case "|":
         if (i == 0)
         {
           result.push("^");
           break;
         }
         if (i == lastIndex)
         {
           result.push("$");
           break;
         }
         if (i == 1 && text[0] == "|")
         {
           result.push("https?://");
+          containsHostname = caseSensitive = true;
           break;
         }
-      case ".": case "+": case "?": case "$":
-      case "{": case "}": case "(": case ")":
-      case "[": case "]": case "\\":
+        result.push("\\", c);
+        break;
+      case "/": case "?": case "*": case "^":
+        if (containsHostname && i < lastIndex)

[Sebastian Noack, 2016/02/24 20:31:05]

I think caseSensitive shouldn't be reset to false on any of these charecters,
but on any alpha character that follows. For example ||example.com/42 can be
case sensitive as well.

[kzar, 2016/02/24 21:20:47]

Done.

+          caseSensitive = false;
+        else if (!containsHostname &&
+                 i >= 2 && text[i-2] == ":" && text[i-1] == "/" && c == "/")

[Sebastian Noack, 2016/02/24 20:31:05]

I think it would make more sense to handle "/" separately and the fall through
to the code here:

case "/":
  if (!containsHostname && text.charAt(i-2) == ":"
                        && text.charAt(i-1) == "/")
    containsHostname = caseSensitive = true;

case "?":
case "*":
case "^":
  ...

[kzar, 2016/02/24 21:20:47]

Done.

+          containsHostname = caseSensitive = true;
+        if (c != "?")
+        {
+          result.push(c);
+          break;
+        }
+      case ".": case "+": case "$": case "{":
+      case "}": case "(": case ")": case "[":
+      case "]": case "\\":
         result.push("\\", c);
         break;
       default:
         result.push(c);
     }
   }
 
-  return result.join("");
+  return {regexp: result.join(""), caseSensitive: caseSensitive};
 }
 
-function getRegExpSource(filter)
+function getRegExpTrigger(filter)
 {
-  let source = toRegExp(filter.regexpSource.replace(
+  let result = toRegExp(filter.regexpSource.replace(
     // Safari expects punycode, filter lists use unicode
     /^(\|\||\|?https?:\/\/)([\w\-.*\u0080-\uFFFF]+)/i,
     function (match, prefix, domain)
     {
       return prefix + punycode.toASCII(domain);
     }
   ));
 
+  let trigger = {"url-filter": result.regexp};
+
   // Limit rules to to HTTP(S) URLs
-  if (!/^(\^|http)/i.test(source))
-    source = "^https?://.*" + source;
+  if (!/^(\^|http)/i.test(trigger["url-filter"]))
+    trigger["url-filter"] = "^https?://.*" + trigger["url-filter"];
 
-  return source;
+  // For rules containing only a hostname we know that we're matching against
+  // a lowercase string and can therefore enable case sensitive matching.
+  if (result.caseSensitive)
+  {
+    trigger["url-filter"] = trigger["url-filter"].toLowerCase();
+    trigger["url-filter-is-case-sensitive"] = true;
+  }
+
+  return trigger;
 }
 
 function getResourceTypes(filter)
 {
   let types = [];
 
   if (filter.contentType & typeMap.IMAGE)
     types.push("image");
   if (filter.contentType & typeMap.STYLESHEET)
     types.push("style-sheet");
@@ skipping 26 matching lines @@
 
     if (tldjs.getDomain(domain) == domain)
       result.push("www." + domain);
   }
 
   return result;
 }
 
 function convertFilter(filter, action, withResourceTypes)
 {
-  let trigger = {"url-filter": getRegExpSource(filter)};
+  let trigger = getRegExpTrigger(filter);
   let included = [];
   let excluded = [];
 
-  parseDomains(filter.domains, included, excluded);
+  if (filter.matchCase)
+    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)
     trigger["unless-domain"] = addDomainPrefix(excluded);
@@ skipping 177 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,
+                  "url-filter-is-case-sensitive": true},
         action: {type: "css-display-none",
                  selector: selector}
       });
     }
   });
 
   for (let filter of this.elemhideExceptions)
     addRule(convertFilter(filter, "ignore-previous-rules", false));
   for (let filter of this.requestFilters)
     addRule(convertFilter(filter, "block", true));
   for (let filter of this.requestExceptions)
     addRule(convertFilter(filter, "ignore-previous-rules", true));
 
   return rules;
 };