ctype_lower misditect non-lower characters on Mac OSX 10.8.

01_ctype_lower misditect_non-lower_characters.php

<?php

$expected = [];
$result = [];

for ($i = 0; $i <= 0xFF; ++$i) {

    setlocale(LC_ALL, 'C');
    if (ctype_lower(chr($i))) {
        $expected[] = $i;
    }

    setlocale(LC_ALL, 'en_US.UTF-8');
    if (ctype_lower(chr($i))) {
        $result[] = $i;
    }

}

var_dump(
    [] === array_diff($result, $expected)
);

02_ctype_lower misditect_non-lower_characters.c

#include <stdio.h>
#include <locale.h>
#include <ctype.h>

int main() {

    int i;
    int c;

    for (i = 0; i <= 0xFF; ++i) {
 
        setlocale(LC_ALL, "C");

        if (islower(i)) {

            c = i;

        }

        setlocale(LC_ALL, "en_US.UTF-8");

        if (islower(i) && c != i) {

            printf("0x%X, ", i);

        }


    }

    printf("\n");

    return 0;
}

03_show_misdetected_characters.php

<?php

for ($i = 0; $i < 0x10FFFF; $i += 1) {

    $char = utf8_chr($i);

    if (ctype_lower($char)) {
        echo "{$char}, ";
    }

}

function utf8_chr($code_point)
{
    if ($code_point < 0 || (0xD800 <= $code_point && $code_point <= 0xDFFF) || 0x10FFFF < $code_point) {
        return false;
    }

    $ret = str_repeat('0', 8 - strlen(dechex($code_point))).dechex($code_point);
    $ret = hex2bin($ret);
    
    return mb_convert_encoding($ret, 'UTF-8', 'UTF-32BE');
}