Created
October 1, 2012 15:54
-
-
Save julp/3812648 to your computer and use it in GitHub Desktop.
Couper le texte sur le mot le plus proche pour un extrait (début) de texte limité à X graphèmes
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <?php | |
| function cut_on_nearest_word_at($string, $length = 150) { | |
| $start = grapheme_substr($string, 0, $length); | |
| $byte_offset = strlen($start); | |
| $ubrk = IntlBreakIterator::createWordInstance(ini_get('intl.default_locale')); | |
| $ubrk->setText($string); | |
| $byte_offset = $ubrk->preceding($byte_offset); | |
| return substr($string, 0, $byte_offset); | |
| } | |
| $N0="\xF0\x9D\x9F\x8E"; # 1D7CE, Nd | |
| $N1="\xF0\x9D\x9F\x8F"; | |
| $N2="\xF0\x9D\x9F\x90"; | |
| $N3="\xF0\x9D\x9F\x91"; | |
| $N4="\xF0\x9D\x9F\x92"; | |
| $N5="\xF0\x9D\x9F\x93"; | |
| $N6="\xF0\x9D\x9F\x94"; | |
| $N7="\xF0\x9D\x9F\x95"; | |
| $N8="\xF0\x9D\x9F\x96"; | |
| $N9="\xF0\x9D\x9F\x97"; | |
| var_dump( | |
| cut_on_nearest_word_at( | |
| str_repeat("$N1$N2$N3$N4$N5$N6$N7$N8$N9 ", 10), | |
| 33 | |
| ) | |
| ); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment