> What about just filtering two u16 (one surrogate pair)? Existing NLS
> modules do not support code points above U+FFFF so two u16 (one
> surrogate pair) just needs to be converted to one replacement character.
Hi Pali,
You're right.
>
> diff --git a/fs/exfat/nls.c b/fs/exfat/nls.c
> index 81d75aed9..f626a0a89 100644
> --- a/fs/exfat/nls.c
> +++ b/fs/exfat/nls.c
> @@ -545,7 +545,10 @@ static int __exfat_nls_vfsname_to_utf16s(struct
> super_block *sb,
> return unilen;
> }
>
> -static int __exfat_nls_uni16s_to_vfsname(struct super_block *sb,
> +#define SURROGATE_PAIR 0x0000d800
> +#define SURROGATE_LOW 0x00000400
> +
> +static int __exfat_nls_utf16s_to_vfsname(struct super_block *sb,
> struct exfat_uni_name *p_uniname, unsigned char *p_cstring,
> int buflen)
> {
> @@ -559,7 +562,23 @@ static int __exfat_nls_uni16s_to_vfsname(struct
> super_block *sb,
> if (*uniname == '\0')
> break;
>
> - len = exfat_convert_uni_to_ch(nls, *uniname, buf, NULL);
> + if ((*uniname & SURROGATE_MASK) != SURROGATE_PAIR) {
> + len = exfat_convert_uni_to_ch(nls, *uniname, buf,
> NULL);
> + } else {
> + /* Process UTF-16 surrogate pair as one character */
> + if (!(*uniname & SURROGATE_LOW) && i+1 <
> MAX_NAME_LENGTH &&
> + (*(uniname+1) & SURROGATE_MASK) == SURROGATE_PAIR
> &&
> + (*(uniname+1) & SURROGATE_LOW)) {
> + uniname++;
> + i++;
> + }
> + /* UTF-16 surrogate pair encodes code points above
> Ux+FFFF.
> + * Code points above U+FFFF are not supported by
> kernel NLS
> + * framework therefore use replacement character */
> + len = 1;
> + buf[0] = '_';
> + }
> +
> if (out_len + len >= buflen)
> len = buflen - 1 - out_len;
> out_len += len;
> @@ -623,7 +642,7 @@ int exfat_nls_uni16s_to_vfsname(struct super_block *sb,
> if (EXFAT_SB(sb)->options.utf8)
> return __exfat_nls_utf16s_to_vfsname(sb, uniname, p_cstring,
> buflen);
> - return __exfat_nls_uni16s_to_vfsname(sb, uniname, p_cstring,
> buflen);
> + return __exfat_nls_utf16s_to_vfsname(sb, uniname, p_cstring,
> buflen);
> }
>
> int exfat_nls_vfsname_to_uni16s(struct super_block *sb,
>
> I have not tested this code, it is just an idea how to quick & dirty
> solve this problem that NLS framework works with UCS-2 encoding and
> UCS-4/UTF-32 or UTF-16.
I will check and test this code.
Thanks for your suggestion.
