Issue 5141 - [emscripten] Convert filter matcher to C++

compiled/filter/RegExpFilter.h

 /*
  * 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
  * 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/>.
  */
 
 #pragma once
 
 #include "Filter.h"
 #include "ActiveFilter.h"
 #include "../bindings/runtime.h"
 
 enum class TrippleState {YES, NO, ANY};
 
 struct RegExpFilterData
 {
   mutable String::size_type mPatternStart;
-  union
-  {
-    mutable int mRegexpId;
-    mutable String::size_type mPatternEnd;
-  };

[Wladimir Palant, 2017/10/17 12:51:21]

The matcher might need to access the pattern part of the filter even after the
regexp has been generated, so this cannot be a union.

+  mutable String::size_type mPatternEnd;
+  mutable int mRegexpId;
   mutable String::size_type mDomainsStart;
   mutable String::size_type mDomainsEnd;
   mutable String::size_type mSitekeysStart;
   mutable String::size_type mSitekeysEnd;
   int mContentType;
   bool mMatchCase;
   TrippleState mThirdParty;
   TrippleState mCollapse;
 
   bool RegExpParsingDone() const
   {
-    return mPatternStart == String::npos;
-  }
-
-  void SetRegExp(int regexpId) const
-  {
-    mRegexpId = regexpId;
-    mPatternStart = String::npos;
+    return mRegexpId >= 0;
   }
 
   bool HasRegExp() const
   {
     return RegExpParsingDone() && mRegexpId;
   }
 
   const DependentString GetRegExpSource(const String& text) const
   {
     return DependentString(text, mPatternStart, mPatternEnd - mPatternStart);
@@ skipping 42 matching lines @@
   SitekeySet* GetSitekeys() const override;
 public:
   static constexpr Type classType = Type::REGEXP;
   explicit RegExpFilter(Type type, const String& text, const RegExpFilterData& data);
   ~RegExpFilter();
   static Type Parse(DependentString& text, DependentString& error,
       RegExpFilterData& data);
   static void GenerateCustomBindings();
   bool BINDINGS_EXPORTED Matches(const String& location, int typeMask,
       DependentString& docDomain, bool thirdParty, const String& sitekey) const;
+  const DependentString GetRegExpSource() const
+  {
+    return mData.GetRegExpSource(mText);
+  }
 };
 
 typedef intrusive_ptr<RegExpFilter> RegExpFilterPtr;