Update dart:io to convert strings between UTF8 and current code page

runtime/bin/utils_win.cc

 // Copyright (c) 2012, the Dart project authors.  Please see the AUTHORS file
 // for details. All rights reserved. Use of this source code is governed by a
 // BSD-style license that can be found in the LICENSE file.
 
 #include <errno.h>
 
 #include "bin/utils.h"
 
 static void FormatMessageIntoBuffer(DWORD code,
                                     char* buffer,
@@ skipping 27 matching lines @@
 
 void OSError::SetCodeAndMessage(SubSystem sub_system, int code) {
   set_sub_system(sub_system);
   set_code(code);
 
   static const int kMaxMessageLength = 256;
   char message[kMaxMessageLength];
   FormatMessageIntoBuffer(code_, message, kMaxMessageLength);
   SetMessage(message);
 }
+
+char* StringUtils::SystemStringToUtf8(char* str) {
+  int len = MultiByteToWideChar(CP_ACP, 0, str, -1, NULL, 0);
+  wchar_t* unicode = new wchar_t[len+1];
+  MultiByteToWideChar(CP_ACP, 0, str, -1, unicode, len);
+  unicode[len] = '\0';
+  len = WideCharToMultiByte(CP_UTF8, 0, unicode, -1, NULL, 0, NULL, NULL);

[Søren Gjesse, 2012/11/13 12:48:45]

If the len here and the len above are then same then it must be an ASCII string
and you should be able to just return str. That of cause means that you will
have to check whether to free or not every time this method is used.

Or maybe check for ASCII string up-front.

[Mads Ager (google), 2012/11/13 14:50:17]

Yeah, I think I'll save that for a separate change. Using the standard trick of
taking four bytes at a time and masking off an iteration up front for the common
ascii case is probably the cheapest.

+  char* utf8 = reinterpret_cast<char*>(malloc(len+1));
+  WideCharToMultiByte(CP_UTF8, 0, unicode, -1, utf8, len, NULL, NULL);
+  utf8[len] = '\0';
+  delete[] unicode;
+  return utf8;
+}
+
+char* StringUtils::Utf8ToSystemString(char* utf8) {
+  int len = MultiByteToWideChar(CP_UTF8, 0, utf8, -1, NULL, 0);
+  wchar_t* unicode = new wchar_t[len+1];
+  MultiByteToWideChar(CP_UTF8, 0, utf8, -1, unicode, len);
+  unicode[len] = '\0';
+  len = WideCharToMultiByte(CP_ACP, 0, unicode, -1, NULL, 0, NULL, NULL);
+  char* ansi = reinterpret_cast<char*>(malloc(len+1));
+  WideCharToMultiByte(CP_ACP, 0, unicode, -1, ansi, len, NULL, NULL);
+  ansi[len] = '\0';
+  delete[] unicode;
+  return ansi;
+}
+
+const char* StringUtils::Utf8ToSystemString(const char* utf8) {
+  return const_cast<const char*>(Utf8ToSystemString(const_cast<char*>(utf8)));
+}
+
+const char* StringUtils::SystemStringToUtf8(const char* str) {
+  return const_cast<const char*>(Utf8ToSystemString(const_cast<char*>(str)));
+}