| Index: base/utf_string_conversions_unittest.cc
|
| ===================================================================
|
| --- base/utf_string_conversions_unittest.cc (revision 36459)
|
| +++ base/utf_string_conversions_unittest.cc (working copy)
|
| @@ -91,8 +91,8 @@
|
| } convert_cases[] = {
|
| // Regular UTF-8 input.
|
| {"\xe4\xbd\xa0\xe5\xa5\xbd", L"\x4f60\x597d", true},
|
| - // Non-character is rejected.
|
| - {"\xef\xbf\xbfHello", L"\xfffdHello", false},
|
| + // Non-character is passed through.
|
| + {"\xef\xbf\xbfHello", L"\xffffHello", true},
|
| // Truncated UTF-8 sequence.
|
| {"\xe4\xa0\xe5\xa5\xbd", L"\xfffd\x597d", false},
|
| // Truncated off the end.
|
| @@ -105,10 +105,10 @@
|
| // The result will either be in UTF-16 or UTF-32.
|
| #if defined(WCHAR_T_IS_UTF16)
|
| {"A\xF0\x90\x8C\x80z", L"A\xd800\xdf00z", true},
|
| - {"A\xF4\x8F\xBF\xBEz", L"A\xfffdz", false},
|
| + {"A\xF4\x8F\xBF\xBEz", L"A\xdbff\xdffez", true},
|
| #elif defined(WCHAR_T_IS_UTF32)
|
| {"A\xF0\x90\x8C\x80z", L"A\x10300z", true},
|
| - {"A\xF4\x8F\xBF\xBEz", L"A\xfffdz", false},
|
| + {"A\xF4\x8F\xBF\xBEz", L"A\x10fffez", true},
|
| #endif
|
| };
|
|
|
| @@ -148,9 +148,9 @@
|
| {L"\x4f60\x597d", "\xe4\xbd\xa0\xe5\xa5\xbd", true},
|
| // Test a non-BMP character.
|
| {L"\xd800\xdf00", "\xF0\x90\x8C\x80", true},
|
| - // Non-characters are rejected.
|
| - {L"\xffffHello", "\xef\xbf\xbdHello", false},
|
| - {L"\xdbff\xdffeHello", "\xef\xbf\xbdHello", false},
|
| + // Non-characters are passed through.
|
| + {L"\xffffHello", "\xEF\xBF\xBFHello", true},
|
| + {L"\xdbff\xdffeHello", "\xF4\x8F\xBF\xBEHello", true},
|
| // The first character is a truncated UTF-16 character.
|
| {L"\xd800\x597d", "\xef\xbf\xbd\xe5\xa5\xbd", false},
|
| // Truncated at the end.
|
| @@ -180,9 +180,9 @@
|
| {L"\x4f60\x597d", "\xe4\xbd\xa0\xe5\xa5\xbd", true},
|
| // Test a non-BMP character.
|
| {L"A\x10300z", "A\xF0\x90\x8C\x80z", true},
|
| - // Non-characters are rejected.
|
| - {L"\xffffHello", "\xEF\xBF\xBDHello", false},
|
| - {L"\x10fffeHello", "\xEF\xBF\xBDHello", false},
|
| + // Non-characters are passed through.
|
| + {L"\xffffHello", "\xEF\xBF\xBFHello", true},
|
| + {L"\x10fffeHello", "\xF4\x8F\xBF\xBEHello", true},
|
| // Invalid Unicode code points.
|
| {L"\xfffffffHello", "\xEF\xBF\xBDHello", false},
|
| // The first character is a truncated UTF-16 character.
|
|
|