Re: [PATCH] change utf8_strwidth() return type to size_t

On 7/26/26 2:34 PM, Hardik Kumar wrote:
> The patch changes the return types of `utf8_strwidth()` and
> `utf8_strnwidth()` to `size_t` (implementing a //TODO). Both functions
> have been updated in the header file also.
> 
> Signed-off-by: Hardik Kumar <[email protected]>
> ---
>  utf8.c | 13 ++++---------
>  utf8.h |  4 ++--
>  2 files changed, 6 insertions(+), 11 deletions(-)

What about callers that still expect int?  Are they all safe without
cast_size_t_to_int()?

> 
> diff --git a/utf8.c b/utf8.c
> index 96460cc..1081573 100644
> --- a/utf8.c
> +++ b/utf8.c
> @@ -208,7 +208,7 @@ int utf8_width(const char **start, size_t *remainder_p)
>   * string, assuming that the string is utf8.  Returns strlen() instead
>   * if the string does not look like a valid utf8 string.
>   */
> -int utf8_strnwidth(const char *string, size_t len, int skip_ansi)
> +size_t utf8_strnwidth(const char *string, size_t len, int skip_ansi)
>  {
>  	const char *orig = string;
>  	size_t width = 0;
> @@ -225,15 +225,10 @@ int utf8_strnwidth(const char *string, size_t len, int skip_ansi)
>  		if (glyph_width > 0)
>  			width += glyph_width;
>  	}
> -
> -	/*
> -	 * TODO: fix the interface of this function and `utf8_strwidth()` to
> -	 * return `size_t` instead of `int`.
> -	 */
> -	return cast_size_t_to_int(string ? width : len);
> +	return (string) ? width : len;

Nit: Why the parentheses around "string"?

>  }
>  
> -int utf8_strwidth(const char *string)
> +size_t utf8_strwidth(const char *string)
>  {
>  	return utf8_strnwidth(string, strlen(string), 0);
>  }
> @@ -821,7 +816,7 @@ void strbuf_utf8_align(struct strbuf *buf, align_type position, unsigned int wid
>  		       const char *s)
>  {
>  	size_t slen = strlen(s);
> -	int display_len = utf8_strnwidth(s, slen, 0);
> +	size_t display_len = utf8_strnwidth(s, slen, 0);
>  	int utf8_compensation = slen - display_len;
>  
>  	if (display_len >= width) {
> diff --git a/utf8.h b/utf8.h
> index cf8ecb0..531e968 100644
> --- a/utf8.h
> +++ b/utf8.h
> @@ -7,8 +7,8 @@ typedef unsigned int ucs_char_t;  /* assuming 32bit int */
>  
>  size_t display_mode_esc_sequence_len(const char *s);
>  int utf8_width(const char **start, size_t *remainder_p);
> -int utf8_strnwidth(const char *string, size_t len, int skip_ansi);
> -int utf8_strwidth(const char *string);
> +size_t utf8_strnwidth(const char *string, size_t len, int skip_ansi);
> +size_t utf8_strwidth(const char *string);
>  int is_utf8(const char *text);
>  int is_encoding_utf8(const char *name);
>  int same_encoding(const char *, const char *);
> 
> base-commit: 9a0c4701dcd5725c4184599322b52933ff5005ca