libgrapheme

grapheme cluster utility library
git clone git://git.suckless.org/libgrapheme
Log | Files | Refs | LICENSE

commit 97b556d67245215e201fef717082b0156f161eed
parent 78da47437d40097f29bcbbf6e6c394175dee1944
Author: Laslo Hunhold <dev@frign.de>
Date:   Mon, 12 Oct 2020 13:56:52 +0200

Make example in grapheme_bytelen.3 more portable and mention UTF-8

Signed-off-by: Laslo Hunhold <dev@frign.de>

Diffstat:
Mman/grapheme_bytelen.3 | 34+++++++++++++++++++++++++++++++---
1 file changed, 31 insertions(+), 3 deletions(-)

diff --git a/man/grapheme_bytelen.3 b/man/grapheme_bytelen.3 @@ -14,7 +14,7 @@ The function computes the length (in bytes) of the grapheme cluster (see .Xr libgrapheme 7 ) -beginning at the NUL-terminated string +beginning at the UTF-8-encoded NUL-terminated string .Va str . .Sh RETURN VALUES The @@ -35,13 +35,41 @@ is int main(void) { - char *s = "Tëst 👨\\u200d👩\\u200d👦 🇺🇸 नी நி!"; + /* UTF-8 encoded input */ + char *s = + "T" + "\\xC3\\xAB" /* U+000EB LATIN SMALL LETTER E + WITH DIAERESIS */ + "s" + "t" + " " + "\\xF0\\x9F\\x91\\xA8" /* U+1F468 MAN */ + "\\xE2\\x80\\x8D" /* U+0200D ZERO WIDTH JOINER */ + "\\xF0\\x9F\\x91\\xA9" /* U+1F469 WOMAN */ + "\\xE2\\x80\\x8D" /* U+0200D ZERO WIDTH JOINER */ + "\\xF0\\x9F\\x91\\xA6" /* U+1F466 BOY */ + " " + "\\xF0\\x9F\\x87\\xBA" /* U+1F1FA REGIONAL INDICATOR + SYMBOL LETTER U */ + "\\xF0\\x9F\\x87\\xB8" /* U+1F1F8 REGIONAL INDICATOR + SYMBOL LETTER S */ + " " + "\\xE0\\xA4\\xA8" /* U+00928 DEVANAGARI LETTER NA */ + "\\xE0\\xA5\\x80" /* U+00940 DEVANAGARI VOWEL + SIGN II */ + " " + "\\xE0\\xAE\\xA8" /* U+00BA8 TAMIL LETTER NA */ + "\\xE0\\xAE\\xBF" /* U+00BBF TAMIL VOWEL SIGN I */ + "!"; size_t len; + /* print input string */ + printf("Input: %s\\n", s); + /* print each grapheme cluster with accompanying byte-length */ while (*s != '\\0') { len = grapheme_bytelen(s); - printf("%2zu bytes | %.*s\\n", len, (int)len, s, len); + printf("%2zu byte(s) | %.*s\\n", len, (int)len, s, len); s += len; }