libgrapheme

unicode string library
git clone git://git.suckless.org/libgrapheme
Log | Files | Refs | README | LICENSE

grapheme_is_character_break.3 (1882B)


      1 .Dd 2021-12-22
      2 .Dt GRAPHEME_IS_CHARACTER_BREAK 3
      3 .Os suckless.org
      4 .Sh NAME
      5 .Nm grapheme_is_character_break
      6 .Nd test for a grapheme cluster break between two codepoints
      7 .Sh SYNOPSIS
      8 .In grapheme.h
      9 .Ft size_t
     10 .Fn grapheme_is_character_break "uint_least32_t cp1" "uint_least32_t cp2" "GRAPHEME_STATE *state"
     11 .Sh DESCRIPTION
     12 The
     13 .Fn grapheme_is_character_break
     14 function determines if there is a grapheme cluster break (see
     15 .Xr libgrapheme 7 )
     16 between the two codepoints
     17 .Va cp1
     18 and
     19 .Va cp2 .
     20 By specification this decision depends on a
     21 .Va state
     22 that can at most be completely reset after detecting a break and must
     23 be reset every time one deviates from sequential processing.
     24 .Pp
     25 If
     26 .Va state
     27 is
     28 .Dv NULL
     29 .Fn grapheme_is_character_break
     30 behaves as if it was called with a fully reset state.
     31 .Sh RETURN VALUES
     32 The
     33 .Fn grapheme_is_character_break
     34 function returns
     35 .Va true
     36 if there is a grapheme cluster break between the codepoints
     37 .Va cp1
     38 and
     39 .Va cp2
     40 and
     41 .Va false
     42 if there is not.
     43 .Sh EXAMPLES
     44 .Bd -literal
     45 /* cc (-static) -o example example.c -lgrapheme */
     46 #include <grapheme.h>
     47 #include <stdint.h>
     48 #include <stdio.h>
     49 #include <stdlib.h>
     50 
     51 int
     52 main(void)
     53 {
     54 	GRAPHEME_STATE state = { 0 };
     55 	uint_least32_t s1[] = ..., s2[] = ...; /* two input arrays */
     56 	size_t i;
     57 
     58 	for (i = 0; i + 1 < sizeof(s1) / sizeof(*s1); i++) {
     59 		if (grapheme_is_character_break(s[i], s[i + 1], &state)) {
     60 			printf("break in s1 at offset %zu\n", i);
     61 		}
     62 	}
     63 	memset(&state, 0, sizeof(state)); /* reset state */
     64 	for (i = 0; i + 1 < sizeof(s2) / sizeof(*s2); i++) {
     65 		if (grapheme_is_character_break(s[i], s[i + 1], &state)) {
     66 			printf("break in s2 at offset %zu\n", i);
     67 		}
     68 	}
     69 
     70 	return 0;
     71 }
     72 .Ed
     73 .Sh SEE ALSO
     74 .Xr grapheme_next_character_break 3 ,
     75 .Xr libgrapheme 7
     76 .Sh STANDARDS
     77 .Fn grapheme_is_character_break
     78 is compliant with the Unicode 14.0.0 specification.
     79 .Sh AUTHORS
     80 .An Laslo Hunhold Aq Mt dev@frign.de