From 6b2add5e70252c513f506f84cc386f47953df48d Mon Sep 17 00:00:00 2001 From: Simon McVittie Date: Mon, 22 Apr 2013 15:36:32 +0100 Subject: [PATCH] Accept non-characters when validating Unicode Unicode Corrigendum #9 clarifies that the non-characters U+nFFFE (for n in the range 0 to 0x10), U+nFFFF (for n in the same range), and U+FDD0..U+FDEF are valid for interchange, and their presence does not make a string ill-formed. GLib 2.36 made the corresponding change in its definition of UTF-8 as used by g_utf8_validate() and similar functions. Bug: https://bugs.freedesktop.org/show_bug.cgi?id=63072 Signed-off-by: Simon McVittie --- dbus/dbus-string.c | 10 +--------- test/syntax.c | 6 ++++-- 2 files changed, 5 insertions(+), 11 deletions(-) diff --git a/dbus/dbus-string.c b/dbus/dbus-string.c index 9accdb1..e3766aa 100644 --- a/dbus/dbus-string.c +++ b/dbus/dbus-string.c @@ -1577,19 +1577,11 @@ _dbus_string_split_on_byte (DBusString *source, * * The second check covers surrogate pairs (category Cs). * - * The last two checks cover "Noncharacter": defined as: - * "A code point that is permanently reserved for - * internal use, and that should never be interchanged. In - * Unicode 3.1, these consist of the values U+nFFFE and U+nFFFF - * (where n is from 0 to 10_16) and the values U+FDD0..U+FDEF." - * * @param Char the character */ #define UNICODE_VALID(Char) \ ((Char) < 0x110000 && \ - (((Char) & 0xFFFFF800) != 0xD800) && \ - ((Char) < 0xFDD0 || (Char) > 0xFDEF) && \ - ((Char) & 0xFFFE) != 0xFFFE) + (((Char) & 0xFFFFF800) != 0xD800)) /** * Finds the given substring in the string, diff --git a/test/syntax.c b/test/syntax.c index 88db963..e26b364 100644 --- a/test/syntax.c +++ b/test/syntax.c @@ -178,12 +178,14 @@ const char * const invalid_single_signatures[] = { const char * const valid_strings[] = { "", - "\xc2\xa9", + "\xc2\xa9", /* UTF-8 (c) symbol */ + "\xef\xbf\xbe", /* U+FFFE is reserved but Corrigendum 9 says it's OK */ NULL }; const char * const invalid_strings[] = { - "\xa9", + "\xa9", /* Latin-1 (c) symbol */ + "\xed\xa0\x80", /* UTF-16 surrogates are not valid in UTF-8 */ NULL }; -- 2.7.4