Issue 1115 - Some yahoo page not correctly shown on IE8 when ABP enabled

src/shared/Utils.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 63 matching lines @@
   if (length == 0)
     return std::wstring();
 
   int utf16StringLength = MultiByteToWideChar(CP_UTF8, 0, str.c_str(), length, NULL, 0);
   if (utf16StringLength == 0)
     throw std::runtime_error("ToUTF16String failed. Can't determine the length of the buffer needed.");
 
   std::wstring utf16String(utf16StringLength, L'\0');
   MultiByteToWideChar(CP_UTF8, 0, str.c_str(), length, &utf16String[0], utf16StringLength);
   return utf16String;
+}
+
+std::vector<std::wstring> ToUtf16Strings(const std::vector<std::string>& values)
+{
+  std::vector<std::wstring> result;
+  result.reserve(values.size());
+  transform(values.begin(), values.end(), back_inserter(result), ToUtf16String);
+  return result;
 }
 
 std::wstring GetDllDir()
 {
   std::vector<WCHAR> path(MAX_PATH);
   int length = GetModuleFileNameW((HINSTANCE)&__ImageBase, &path[0], static_cast<DWORD>(path.size()));
 
   while (length == path.size())
   {
     // Buffer too small, double buffer size
@@ skipping 52 matching lines @@
   {
     input.replace(replaceStart, placeholder.length(), replacement);
   }
 }
 
 std::wstring GetSchemeAndHierarchicalPart(const std::wstring& url)
 {
   auto schemeAndHierarchicalPartEndsAt = url.find(L'?');
   if (schemeAndHierarchicalPartEndsAt == std::wstring::npos)
   {
     schemeAndHierarchicalPartEndsAt = url.find(L'#');

[Oleksandr, 2015/02/13 03:32:16]

So what if there's neither '?' nor '#' in the url?
Even more, why not just use CreateUri
(https://msdn.microsoft.com/en-us/library/ie/ms775098(v=vs.85).aspx) and then
just IUri::GetQuery? Or maybe WinHttpCrackUrl or InternetCrackUrl. For this and
GetQueryString below.
https://msdn.microsoft.com/en-us/library/windows/desktop/aa384092%28v=vs.85%2...
or
https://msdn.microsoft.com/en-us/library/windows/desktop/aa384376(v=vs.85).aspx

[sergei, 2015/02/13 15:21:56]

It means there is neither query nor fragment and we will return the original
URL. Actually, there is the test for that case.
I thought that it's an unnecessary overhead, especially I'm afraid that to parse
the URL they can instantiate a protocol handler (BTW, our implementation of
protocol handler) to use IInternetProtocolInfo::ParseUrl. At least I've seen
such behaviour but I don't remember whether it was for one of the mentioned
function or not.
CreateUri looks fine for me, should I investigate it and change?

[Oleksandr, 2015/02/16 06:59:28]

We are using WinHTTPCrackUrl in libadblockplus in DedfaultWebRequestWinInet.cpp,
FYI. I don't think that instantiates our APP. But at this stage, I guess there
is little point to look into CreateUrl and others since we already have a good
enough solution with tests.

   }
   return url.substr(0, schemeAndHierarchicalPartEndsAt);
 }
 
 std::wstring GetQueryString(const std::wstring& url)
 {
   auto questionSignPos = url.find(L'?');
   if (questionSignPos == std::wstring::npos)
   {
     return L"";
   }
   auto queryStringBeginsAt = questionSignPos + 1;
   auto endQueryStringPos = url.find(L'#', queryStringBeginsAt);
   if (endQueryStringPos == std::wstring::npos)
   {
     endQueryStringPos = url.length();
   }
   return url.substr(queryStringBeginsAt, endQueryStringPos - queryStringBeginsAt);
 }

[Eric, 2015/02/12 17:24:41]

This version much clearer and easier to verify correctness, including better
local variable names.

-
-void ForEachToken(const std::wstring& value, wchar_t delimiter,
-                 const std::function<bool(std::wstring::const_iterator begin, std::wstring::const_iterator end)>& tokenHandler)
-{
-  if (value.empty())
-  {
-    return;
-  }
-  std::wstring::size_type delimiterPos = value.find(delimiter);
-  std::wstring::size_type prevDelimiterPos = 0;
-  while(delimiterPos != std::wstring::npos)
-  {
-    if (!tokenHandler(value.begin() + prevDelimiterPos, value.begin() + delimiterPos))
-    {
-      return;
-    }
-    prevDelimiterPos = delimiterPos;
-    ++prevDelimiterPos; // skip the delimiter
-    delimiterPos = value.find(delimiter, prevDelimiterPos);
-  }
-  tokenHandler(value.begin() + prevDelimiterPos, value.end());
-}
-
-void ForEachQueryStringParameter(const std::wstring& queryString,
-                                 const std::function<bool(const std::wstring& name, const std::wstring& value)>& parameterHandler)
-{
-  if (queryString.empty())
-  {
-    return;
-  }
-  ForEachToken(queryString, L'&',
-    [&parameterHandler](std::wstring::const_iterator begin,
-                        std::wstring::const_iterator end)->bool
-    {
-      auto assignSignIt = std::find(begin, end, L'=');
-      auto valueBeginsAt = assignSignIt != end ? assignSignIt + 1 : assignSignIt;
-      return parameterHandler(std::wstring(begin, assignSignIt), std::wstring(valueBeginsAt, end));
-    });
-}