SimpleIcuSortKey.php

<?php

/**
 * Simple emulation of ICU sortkeys for trivial strings (strings containing [A-Za-z0-9] only)
 *
 * See http://userguide.icu-project.org/collation/architecture#TOC-Sort-Keys
 */

function simple_sort_key($str)
{
	$part1 = '';
	$part2 = '';
	$part3 = '';
	$len = strlen($str);
	for ($i = 0; $i < $len; ++$i)
	{
		$c = $str[$i];
		if ($c >= '0' && $c <= '9')
		{
			$part1 .= chr(2 * (ord($c) - ord('0')) + 0x12);
		}
		else if ($c >= 'a' && $c <= 'z')
		{
			$part1 .= chr(2 * (ord($c) - ord('a')) + 0x27);
		}
		else if ($c >= 'A' && $c <= 'Z')
		{
			$part1 .= chr(2 * (ord($c) - ord('A')) + 0x27);
			$part3 .= chr(0x8F);
		}
		else
		{
			// ignore unsupported characters (?)
		}
	}
	$part2 .= chr(strlen($part1) + 4 - strlen($part2));
	$part3 .= chr(strlen($part1) + 4 - strlen($part3));

	return $part1 . chr(0x01) . $part2 . chr(0x01) . $part3 . chr(0x00);
}

function printable_sort_key($sk)
{
	$result = '';
	for ($i = 0; $i < strlen($sk); ++$i)
	{
		$c = ord($sk[$i]);

		if ($c === 1)
		{
			$result .= ' / ';
		}
		else if ($c === 0)
		{
			$result .= '.';
		}
		else
		{
			$h = dechex($c);
			while (strlen($h) < 2) $h = '0' . $h;
			$result .= $h;
		}
	}
	return $result;
}

echo 'a: ' .printable_sort_key(simple_sort_key('a')) . "<br />\n";
echo 'á: ' .printable_sort_key(simple_sort_key('á')) . "<br />\n";
echo 'č: ' .printable_sort_key(simple_sort_key('č')) . "<br />\n";
echo 'b: ' .printable_sort_key(simple_sort_key('b')) . "<br />\n";
echo '1: ' .printable_sort_key(simple_sort_key('1')) . "<br />\n";
echo 'b1: ' .printable_sort_key(simple_sort_key('b1')) . "<br />\n";
echo 'b11: ' .printable_sort_key(simple_sort_key('b11')) . "<br />\n";
echo 'ab12345: ' .printable_sort_key(simple_sort_key('ab12345')) . "<br />\n";