Issue #3343 - Eliminate unescaping of URL

src/plugin/PluginWbPassThrough.cpp

 /*
  * This file is part of Adblock Plus <https://adblockplus.org/>,
  * Copyright (C) 2006-2015 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 22 matching lines @@
           "<!-- blocked by AdblockPlus -->"
         "</body>"
     "</html>";
 
   template <typename T>
   T ASCIIStringToLower(const T& text)
   {
     T textlower;
     std::transform(text.begin(), text.end(), std::back_inserter(textlower), 
       [](T::value_type ch)
-          { 
-            return std::tolower(ch, std::locale());
-          }
-        );
+      {
+        return std::tolower(ch, std::locale());
+      }
+    );
     return textlower;
   }
 
   typedef AdblockPlus::FilterEngine::ContentType ContentType;
 
   template <class T>
   T ExtractHttpHeader(const T& allHeaders, const T& targetHeaderNameWithColon, const T& delimiter)
   {
     const T allHeadersLower = ASCIIStringToLower(allHeaders);
     auto targetHeaderBeginsAt = allHeadersLower.find(ASCIIStringToLower(targetHeaderNameWithColon));
@@ skipping 78 matching lines @@
   }
 }
 
 WBPassthruSink::WBPassthruSink()
   : m_currentPositionOfSentPage(0)
   , m_contentType(ContentType::CONTENT_TYPE_OTHER)
   , m_isCustomResponse(false)
 {
 }
 
-ContentType WBPassthruSink::GetContentTypeFromMimeType(const CString& mimeType)
-{
-  if (mimeType.Find(L"image/") >= 0)
+ContentType WBPassthruSink::GetContentTypeFromMimeType(const std::wstring& mimeType)
+{
+  if (mimeType.find(L"image/") != std::wstring::npos)
   {
     return ContentType::CONTENT_TYPE_IMAGE;
   }
-  if (mimeType.Find(L"text/css") >= 0)
+  if (mimeType.find(L"text/css") != std::wstring::npos)
   {
     return ContentType::CONTENT_TYPE_STYLESHEET;
   }
-  if ((mimeType.Find(L"application/javascript") >= 0) || (mimeType.Find(L"application/json") >= 0))
+  if ((mimeType.find(L"application/javascript") != std::wstring::npos) || (mimeType.find(L"application/json") != std::wstring::npos))
   {
     return ContentType::CONTENT_TYPE_SCRIPT;
   }
-  if (mimeType.Find(L"application/x-shockwave-flash") >= 0)
+  if (mimeType.find(L"application/x-shockwave-flash") != std::wstring::npos)
   {
     return ContentType::CONTENT_TYPE_OBJECT;
   }
-  if (mimeType.Find(L"text/html") >= 0)
+  if (mimeType.find(L"text/html") != std::wstring::npos)
   {
     return ContentType::CONTENT_TYPE_SUBDOCUMENT;
   }
   // It is important to have this check last, since it is rather generic, and might overlay text/html, for example
-  if (mimeType.Find(L"xml") >= 0)
+  if (mimeType.find(L"xml") != std::wstring::npos)
   {
     return ContentType::CONTENT_TYPE_XMLHTTPREQUEST;
   }
 
   return ContentType::CONTENT_TYPE_OTHER;
 }
 
 ContentType WBPassthruSink::GetContentTypeFromURL(const std::wstring& src)
 {
   std::wstring schemeAndHierarchicalPart = GetSchemeAndHierarchicalPart(src);
@@ skipping 10 matching lines @@
       if (contentType != ContentType::CONTENT_TYPE_OTHER)
       {
          return contentType;
       }
       token = wcstok_s(nullptr, L"&=", &nextToken);
     }
   }
   return contentType;
 }
 
-ContentType WBPassthruSink::GetContentType(const CString& mimeType, const std::wstring& domain, const std::wstring& src)
+ContentType WBPassthruSink::GetContentType(const std::wstring& mimeType, const std::wstring& domain, const std::wstring& src)
 {
   // No referer or mime type
   // BINDSTRING_XDR_ORIGIN works only for IE v8+
-  if (mimeType.IsEmpty() && domain.empty() && AdblockPlus::IE::InstalledMajorVersion() >= 8)
+  if (mimeType.empty() && domain.empty() && AdblockPlus::IE::InstalledMajorVersion() >= 8)
   {
     return ContentType::CONTENT_TYPE_XMLHTTPREQUEST;
   }
   ContentType contentType = GetContentTypeFromMimeType(mimeType);
   if (contentType == ContentType::CONTENT_TYPE_OTHER)
   {
     contentType = GetContentTypeFromURL(src);
   }
   return contentType;
 }
@@ skipping 106 matching lines @@
 
 STDMETHODIMP WBPassthruSink::BeginningTransaction(LPCWSTR szURL, LPCWSTR szHeaders, DWORD dwReserved, LPWSTR* pszAdditionalHeaders)
 {
   if (!szURL)
   {
     return E_POINTER;
   }
   std::wstring src = szURL;
   DEBUG_GENERAL(src);
 
-  std::string acceptHeader = ExtractHttpAcceptHeader(m_spTargetProtocol);
-
   if (pszAdditionalHeaders)
   {
     *pszAdditionalHeaders = nullptr;
   }
 
   CComPtr<IHttpNegotiate> httpNegotiate;
   QueryServiceFromClient(&httpNegotiate);
   // This fills the pszAdditionalHeaders with more headers. One of which is the Referer header, which we need.
   // There doesn't seem to be any other way to get this header before the request has been made.
   HRESULT nativeHr = httpNegotiate ? httpNegotiate->BeginningTransaction(szURL, szHeaders, dwReserved, pszAdditionalHeaders) : S_OK;
 
   if (pszAdditionalHeaders && *pszAdditionalHeaders)
   {
     m_boundDomain = ExtractHttpHeader<std::wstring>(*pszAdditionalHeaders, L"Referer:", L"\n");
   }
   m_boundDomain = TrimString(m_boundDomain);
-  m_contentType = GetContentType(ATL::CString(acceptHeader.c_str()), m_boundDomain, src);
+  m_contentType = GetContentType(ToUtf16String(ExtractHttpAcceptHeader(m_spTargetProtocol)), m_boundDomain, src);
 
   CPluginTab* tab = CPluginClass::GetTab(::GetCurrentThreadId());
   CPluginClient* client = CPluginClient::GetInstance();
 
   if (tab && client)
   {
     std::wstring documentUrl = tab->GetDocumentUrl();
     // Page is identical to document => don't block
     if (documentUrl == src)
     {
@@ skipping 76 matching lines @@
   }
 
   return OnStart(szUrl, pOIProtSink, pOIBindInfo, grfPI, dwReserved, m_spInternetProtocol);
 }
 
 STDMETHODIMP WBPassthru::Read(/* [in, out] */ void *pv,/* [in] */ ULONG cb,/* [out] */ ULONG *pcbRead)
 {
   WBPassthruSink* pSink = GetSink();
   return pSink->OnRead(pv, cb, pcbRead);
 }