Updated *.pak file format to support both UTF8 and UTF16

ui/base/resource/resource_bundle_posix.cc

Index: ui/base/resource/resource_bundle_posix.cc
diff --git a/ui/base/resource/resource_bundle_posix.cc b/ui/base/resource/resource_bundle_posix.cc
index d23a5b1da0986e82e09bd0cd52c68204084066a7..066053ec387a1a60206440c0e4c858645cd27112 100644
--- a/ui/base/resource/resource_bundle_posix.cc
+++ b/ui/base/resource/resource_bundle_posix.cc
@@ -11,6 +11,7 @@
 #include "base/string16.h"
 #include "base/string_piece.h"
 #include "base/synchronization/lock.h"
+#include "base/utf_string_conversions.h"
 #include "ui/base/l10n/l10n_util.h"
 #include "ui/base/resource/data_pack.h"
 #include "ui/base/ui_base_switches.h"
@@ -88,10 +89,19 @@ string16 ResourceBundle::GetLocalizedString(int message_id) {
     }
   }
 
-  // Data pack encodes strings as UTF16.
-  DCHECK_EQ(data.length() % 2, 0U);
-  string16 msg(reinterpret_cast<const char16*>(data.data()),
-               data.length() / 2);
+  // Strings should not be loaded from data back that contain binary data.
+  DCHECK(locale_resources_data_->GetTextEncodingType() == DataPack::UTF16 ||
+         locale_resources_data_->GetTextEncodingType() == DataPack::UTF8)
+      << "requested localized string from binary pack file";
+
+  // Data pack encodes strings as either UTF8 or UTF16.
+  string16 msg;
+  if (locale_resources_data_->GetTextEncodingType() == DataPack::UTF16) {
+    msg = string16(reinterpret_cast<const char16*>(data.data()),
+                   data.length() / 2);
+  } else if (locale_resources_data_->GetTextEncodingType() == DataPack::UTF8) {
+    msg = UTF8ToUTF16(data);

[tony, 2011/08/29 21:24:39]

This is fine for now.  We'll want to probably fix up l10n_util to get the raw
data and do the conversion in a follow up patch (to avoid unnecessary string
conversions).

[marcvs, 2011/08/30 07:58:55]

Yes, since GTK uses UTF8 I was saving this for later in an effort to replace
some of those calls, too so that they don't waste cycles doing UTF8->UTF16->UTF8
if the file already provides the adequate encoding.

+  }
   return msg;
 }