[PATCH 1/5] string: add strtok/strtokv

[Ahmad Fatoum]

Hello Tobias,

On 8/28/25 5:05 PM, Tobias Waldekranz wrote:
> Add an implementation of libc's standard strtok(3), which is useful
> for tokenizing strings.

strtok was previously removed in favor of strsep as it doesn't suffer
from re-entrancy issues (poller and bthreads can run during delays). If
you want to allow escapes, there's also strsep_unescaped.

> Also, add a version that will collect all tokens from a string into an
> array, which is useful in situations where you need to know how many
> tokens there are, and when a token's relative position in the order is
> significant.

We have the inverse as strjoin, but not this. Maybe call it strsplit
instead?

Cheers,
Ahmad

> 
> Signed-off-by: Tobias Waldekranz <tobias at waldekranz.com>
> ---
>  include/string.h |  2 ++
>  lib/string.c     | 66 ++++++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 68 insertions(+)
> 
> diff --git a/include/string.h b/include/string.h
> index 71affe48b6..c8df8540d8 100644
> --- a/include/string.h
> +++ b/include/string.h
> @@ -8,6 +8,8 @@
>  void *mempcpy(void *dest, const void *src, size_t count);
>  int strtobool(const char *str, int *val);
>  char *strsep_unescaped(char **, const char *, char *);
> +char *strtok(char *str, const char *delim);
> +int strtokv(char *str, const char *delim, char ***vecp);
>  char *stpcpy(char *dest, const char *src);
>  bool strends(const char *str, const char *postfix);
>  
> diff --git a/lib/string.c b/lib/string.c
> index 73637cd971..be7e65eb45 100644
> --- a/lib/string.c
> +++ b/lib/string.c
> @@ -593,6 +593,72 @@ char *strsep_unescaped(char **s, const char *ct, char *delim)
>          return sbegin;
>  }
>  
> +/**
> + * strtok - extract tokens from string
> + * @str:	string to split
> + * @delim:	set of delimiter characters
> + *
> + * The strtok() function breaks up a string into zero or more nonempty
> + * tokens.  On the first call, the string to be parsed should be
> + * specified in @str.  In each subsequent call that should parse the
> + * same string, @str must be NULL.
> + *
> + * @delim specifies a set of bytes that delimit the tokens in the
> + * string.
> + *
> + * Each call to strtok() returns a pointer to a string containing the
> + * next token.  This is done by replacing the first delimiter with a
> + * NUL character, the operation is thus destructive to the string. If
> + * no more tokens are found, strtok() returns NULL.
> + */
> +char *strtok(char *str, const char *delim)
> +{
> +	static char *cursor;
> +
> +	if (str)
> +		cursor = str;
> +
> +	if (!cursor)
> +		return NULL;
> +
> +	cursor += strspn(cursor, delim);
> +	if (*cursor == '\0') {
> +		cursor = NULL;
> +		return NULL;
> +	}
> +
> +	return strsep(&cursor, delim);
> +}
> +EXPORT_SYMBOL(strtok);
> +
> +/**
> + * strtokv - split string into array of tokens based on a delimiter set
> + * @str:	string to split
> + * @delim:	set of delimiter characters
> + * @vecp:	array of tokens
> + *
> + * Split @str into tokens delimited by @delim, using strtok(), and
> + * store the allocated token array in @vecp, which the caller is
> + * responsible for freeing.
> + *
> + * Return: The number of tokens in the array.
> + */
> +int strtokv(char *str, const char *delim, char ***vecp)
> +{
> +	char *tok, **vec = NULL;
> +	int cnt = 0;
> +
> +
> +	for (tok = strtok(str, delim); tok; tok = strtok(NULL, delim)) {
> +		vec = xrealloc(vec, (cnt + 1) * sizeof(*vec));
> +		vec[cnt++] = tok;
> +	}
> +
> +	*vecp = vec;
> +	return cnt;
> +}
> +EXPORT_SYMBOL(strtokv);
> +
>  #ifndef __HAVE_ARCH_STRSWAB
>  /**
>   * strswab - swap adjacent even and odd bytes in %NUL-terminated string

-- 
Pengutronix e.K.                  |                             |
Steuerwalder Str. 21              | http://www.pengutronix.de/  |
31137 Hildesheim, Germany         | Phone: +49-5121-206917-0    |
Amtsgericht Hildesheim, HRA 2686  | Fax:   +49-5121-206917-5555 |