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

ui/base/resource/resource_bundle_posix.cc

 // Copyright (c) 2011 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #include "ui/base/resource/resource_bundle.h"
 
 #include "base/command_line.h"
 #include "base/file_path.h"
 #include "base/logging.h"
 #include "base/stl_util.h"
 #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"
 #include "ui/gfx/font.h"
 
 namespace ui {
 
 namespace {
 
 DataPack* LoadResourcesDataPak(FilePath resources_pak_path) {
@@ skipping 57 matching lines @@
   if (!locale_resources_data_->GetStringPiece(message_id, &data)) {
     // Fall back on the main data pack (shouldn't be any strings here except in
     // unittests).
     data = GetRawDataResource(message_id);
     if (data.empty()) {
       NOTREACHED() << "unable to find resource: " << message_id;
       return string16();
     }
   }
 
-  // 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;
 }
 
 void ResourceBundle::LoadCommonResources() {
   DCHECK(!resources_data_) << "chrome.pak already loaded";
   FilePath resources_file_path = GetResourcesFilePath();
   CHECK(!resources_file_path.empty()) << "chrome.pak not found";
   resources_data_ = LoadResourcesDataPak(resources_file_path);
   CHECK(resources_data_) << "failed to load chrome.pak";
 
@@ skipping 30 matching lines @@
 
 void ResourceBundle::LoadTestResources(const FilePath& path) {
   DCHECK(!resources_data_) << "resource already loaded";
 
   // Use the given resource pak for both common and localized resources.
   resources_data_ = LoadResourcesDataPak(path);
   locale_resources_data_ = LoadResourcesDataPak(path);
 }
 
 }  // namespace ui