util: adds the utf8_count_chars function (4a4a46c2) · Commits · Wenxi XU / zephyr

include/zephyr/sys/util.h

+16 −0

Changes for include/zephyr/sys/util.h: 16 added lines, 0 removed lines.
Original line number	Diff line number	Diff line
		@@ -29,6 +29,8 @@
		#include <stddef.h>
		#include <stdint.h>
		#include <string.h>
		#include <sys/types.h>


		/** @brief Number of bits that make up a type */
		#define NUM_BITS(t) (sizeof(t) * BITS_PER_BYTE)
		@@ -688,6 +690,20 @@ char utf8_trunc(char utf8_str);
		*/
		char utf8_lcpy(char dst, const char *src, size_t n);

		/**
		* @brief Counts the characters in a UTF-8 encoded string @p s
		*
		* Counts the number of UTF-8 characters (code points) in a null-terminated string.
		* This function steps through each UTF-8 sequence by checking leading byte patterns.
		* It does not fully validate UTF-8 correctness, only counts characters.
		*
		* @param s The input string
		*
		* @return Number of UTF-8 characters in @p s on success or (negative) error code
		* otherwise.
		*/
		ssize_t utf8_count_chars(const char *s);

		#define __z_log2d(x) (32 - __builtin_clz(x) - 1)
		#define __z_log2q(x) (64 - __builtin_clzll(x) - 1)
		#define __z_log2(x) (sizeof(__typeof__(x)) > 4 ? __z_log2q(x) : __z_log2d(x))

+45 −0

Changes for lib/utils/utf8.c: 45 added lines, 0 removed lines.
Original line number	Diff line number	Diff line
		@@ -7,12 +7,15 @@
		#include <stdint.h>
		#include <string.h>
		#include <zephyr/sys/__assert.h>
		#include <errno.h>
		#include <sys/types.h>

		#define ASCII_CHAR 0x7F
		#define SEQUENCE_FIRST_MASK 0xC0
		#define SEQUENCE_LEN_2_BYTE 0xC0
		#define SEQUENCE_LEN_3_BYTE 0xE0
		#define SEQUENCE_LEN_4_BYTE 0xF0
		#define MSB_SET 0x80

		char utf8_trunc(char utf8_str)
		{
		@@ -79,3 +82,45 @@ char utf8_lcpy(char dst, const char *src, size_t n)

		return dst;
		}

		ssize_t utf8_count_chars(const char *s)
		{
		ssize_t count = 0;
		const char p = s; / getting a pointer to increment */

		while (*p != '\0') {
		if ((p & MSB_SET) == 0) { / 1-byte character: 0xxxxxxx */
		p += 1;
		} else if ((*p & SEQUENCE_LEN_3_BYTE) == SEQUENCE_FIRST_MASK) {
		/* 2-byte character: 110xxxxx */
		if ((p[1] & SEQUENCE_FIRST_MASK) != MSB_SET) {
		/* invalid continuation */
		return -EINVAL;
		}
		p += 2;
		} else if ((*p & SEQUENCE_LEN_4_BYTE) == SEQUENCE_LEN_3_BYTE) {
		/* 3-byte character: 1110xxxx */
		if ((p[1] & SEQUENCE_FIRST_MASK) != MSB_SET
		\|\| (p[2] & SEQUENCE_FIRST_MASK) != MSB_SET) {
		/* invalid continuation */
		return -EINVAL;
		}
		p += 3;
		} else if ((*p & 0xF8) == SEQUENCE_LEN_4_BYTE) {
		/* 4-byte character: 11110xxx */
		if ((p[1] & SEQUENCE_FIRST_MASK) != MSB_SET
		\|\| (p[2] & SEQUENCE_FIRST_MASK) != MSB_SET
		\|\| (p[3] & SEQUENCE_FIRST_MASK) != MSB_SET) {
		/* invalid continuation */
		return -EINVAL;
		}
		p += 4;
		} else {
		/* Invalid UTF-8 byte (return) */
		return -EINVAL;
		}
		count++;
		}

		return count;
		}