(size_t)-1 is also undefined behaviour.
On Sat, 18 Dec 2021 20:21:42 +0100
<g...@suckless.org> wrote:
> commit cb7e9c00899ae0ed57a84991308b7f880f4ddef6
> Author: Laslo Hunhold <d...@frign.de>
> AuthorDate: Sat Dec 18 20:21:04 2021 +0100
> Commit: Laslo Hunhold <d...@frign.de>
> CommitDate: Sat Dec 18 20:21:04 2021 +0100
>
> Use SIZE_MAX instead of (size_t)-1
>
> This makes a bit clearer what we mean, and given the library is C99
> we can rely on this constant to exist.
>
> Signed-off-by: Laslo Hunhold <d...@frign.de>
>
> diff --git a/man/grapheme_decode_utf8.3 b/man/grapheme_decode_utf8.3
> index 26e3afb..d5c7c9d 100644
> --- a/man/grapheme_decode_utf8.3
> +++ b/man/grapheme_decode_utf8.3
> @@ -31,8 +31,8 @@ Given NUL has a unique 1 byte representation, it is safe to
> operate on
> NUL-terminated strings by setting
> .Va len
> to
> -.Dv (size_t)-1
> -and terminating when
> +.Dv SIZE_MAX
> +(stdint.h is already included by grapheme.h) and terminating when
> .Va cp
> is 0 (see
> .Sx EXAMPLES
> @@ -87,7 +87,7 @@ print_cps_nul_terminated(const char *str)
> uint_least32_t cp;
>
> for (off = 0; (ret = grapheme_decode_utf8(str + off,
> - (size_t)-1, &cp)) > 0 &&
> + SIZE_MAX, &cp)) > 0 &&
> cp != 0; off += ret) {
> printf("%"PRIxLEAST32"\\n", cp);
> }
> diff --git a/src/character.c b/src/character.c
> index 015b4e0..8f1143f 100644
> --- a/src/character.c
> +++ b/src/character.c
> @@ -197,19 +197,19 @@ grapheme_next_character_break(const char *str)
> * miss it, even if the previous UTF-8 sequence terminates
> * unexpectedly, as it would either act as an unexpected byte,
> * saved for later, or as a null byte itself, that we can catch.
> - * We pass (size_t)-1 to the length, as we will never read beyond
> + * We pass SIZE_MAX to the length, as we will never read beyond
> * the null byte for the reasons given above.
> */
>
> /* get first codepoint */
> - len += grapheme_decode_utf8(str, (size_t)-1, &cp0);
> + len += grapheme_decode_utf8(str, SIZE_MAX, &cp0);
> if (cp0 == GRAPHEME_INVALID_CODEPOINT) {
> return len;
> }
>
> while (cp0 != 0) {
> /* get next codepoint */
> - ret = grapheme_decode_utf8(str + len, (size_t)-1, &cp1);
> + ret = grapheme_decode_utf8(str + len, SIZE_MAX, &cp1);
>
> if (cp1 == GRAPHEME_INVALID_CODEPOINT ||
> grapheme_is_character_break(cp0, cp1, &state)) {
>
