Add support for the extended header parameter syntax in Content-Disposition header (RFC 5987).

It's not generic, but is only used for 'filename' param. 

The CL is originally by James Simonsen I reviewed at http://codereview.chromium.org/4254001/show

I added a check for ASCIIness for RFC 5987 extended header and a few tests to NetUti*.GetFileNameFromCD
(net_unittests) and I*.ConvertCo*Norma* (base_unittests).  I also replaced '\uxxxx' notation with
the corresponding UTF-8 byte sequence because Visual Studio does not understand it yet.

BUG=57830
TEST="net_unittests --gtest_filter=NetU*.GetFil*", "base_unittests --gtest_filter=I*.Conver*Norm*" and tests
at http://greenbytes.de/tech/tc2231/

Original CL / Review: By James Simonsen; at http://codereview.chromium.org/4254001/show

Review URL: http://codereview.chromium.org/4435001

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@64987 0039d316-1c4b-4281-b951-d872f2087c98

1 files changed, 26 insertions, 0 deletions

diff --git a/base/i18n/icu_string_conversions.cc b/base/i18n/icu_string_conversions.cc
index 9014a7b..c353feb 100644
--- a/base/i18n/icu_string_conversions.cc
+++ b/base/i18n/icu_string_conversions.cc
@@ -9,9 +9,11 @@
 #include "base/basictypes.h"
 #include "base/logging.h"
 #include "base/string_util.h"
+#include "base/utf_string_conversions.h"
 #include "unicode/ucnv.h"
 #include "unicode/ucnv_cb.h"
 #include "unicode/ucnv_err.h"
+#include "unicode/unorm.h"
 #include "unicode/ustring.h"
 
 namespace base {
@@ -264,4 +266,28 @@ bool CodepageToWide(const std::string& encoded,
 #endif  // defined(WCHAR_T_IS_UTF32)
 }
 
+bool ConvertToUtf8AndNormalize(const std::string& text,
+                               const std::string& charset,
+                               std::string* result) {
+  result->clear();
+  string16 utf16;
+  if (!CodepageToUTF16(
+      text, charset.c_str(), OnStringConversionError::FAIL, &utf16))
+    return false;
+
+  UErrorCode status = U_ZERO_ERROR;
+  size_t max_length = utf16.length() + 1;
+  string16 normalized_utf16;
+  int actual_length = unorm_normalize(
+      utf16.c_str(), utf16.length(), UNORM_NFC, 0,
+      WriteInto(&normalized_utf16, max_length),
+      static_cast<int>(max_length), &status);
+  if (!U_SUCCESS(status))
+    return false;
+  normalized_utf16.resize(actual_length);
+
+  return UTF16ToUTF8(normalized_utf16.data(),
+                     normalized_utf16.length(), result);
+}
+
 }  // namespace base