/**
* UTF-8 aware replacement for strpos().
*
* Returns the position of the first occurrence of $sub in the $str. If $sub is
* not found, it returns false.
*
* This will get alot slower if an negative $offset is used.
*
* This function may return boolean false, but may also return a non-boolean 0
* which evaluates to false. Use the === operator for testing the return value
* of this function.
*
* @param string $str The string to search in
* @param string $sub The string to search for
* @param int $offset If presented, it specifies the position in the string
* to begin the search
* @param bool $ci Should the function be case-insensitive?
* @return int The position or false on failure
*/
function utf8_search($str, $sub, $offset = 0, $ci = false)
{
$n = $r = 0;
// The position of matching UTF-8 character within the $sub
if ($offset < 0) {
$offset += utf8_length($str);
if ($offset < 0) {
$offset = 0;
}
}
while ($n < $offset) {
if (utf8_get_char($str, $j) === false) {
return false;
}
++$n;
}
while (true) {
if (!isset($sub_cp[$r])) {
if (utf8_get_char($sub, $i, $cp) !== false) {
$sub_cp[] = array($cp);
if ($ci && ($_ = unicode_swapcase($cp)) != $cp) {
$sub_cp[$r][] = $_;
}
} elseif (!$r) {
trigger_error('utf8_search: The string to search for is empty');
return false;
} else {
return $n;
}
}
$offset = $n + $r;
if (!isset($str_cp[$offset])) {
if (utf8_get_char($str, $j, $cp) !== false) {
$str_cp[$offset] = $cp;
} else {
return false;
}
}
if (in_array($str_cp[$offset], $sub_cp[$r])) {
$r++;
} else {
unset($str_cp[$n++]);
$r = 0;
}
}
}
/**
* UTF-8 aware replacement for strcmp().
*
* Comparison.
*
* Returns an integral value indicating the relationship between the strings.
*
* - A zero value indicates that both strings are equal.
* - A value greater than zero indicates that the first character that does not
* match has a greater value in $str than in $otherstr.
* - And a value less than zero indicates the opposite.
*
* @param string $str The UTF-8 encoded string
* @param string $otherstr Other UTF-8 encoded string
* @param bool $ci Should the function be case-insensitive?
* @return int
*/
function utf8_compare($str, $otherstr, $ci = false)
{
$diff = 0;
$char1 = $char2 = '';
do {
if ($char1 !== false) {
$char1 = utf8_get_char($str, $i, $cp1);
} else {
$diff--;
}
if ($char2 !== false) {
$char2 = utf8_get_char($otherstr, $j, $cp2);
} else {
$diff++;
}
if ($char1 === false) {
if ($char2 === false) {
return $diff;
}
} elseif ($char2 !== false) {
if ($cp1 != $cp2 && (!$ci || $cp1 != unicode_swapcase($cp2))) {
return $cp1 > $cp2 ? 1 : -1;
}
}
} while (true);
}
/**
* @dataProvider providerUnicodeSwapcase
*/
public function testUnicodeSwapcase($cp, $rv)
{
$this->assertEquals(unicode_swapcase($cp), $rv);
}
/**
* Returns a string with uppercase characters converted to lowercase and
* lowercase characters converted to uppercase.
*
* @param string $str The UTF-8 encoded string
* @return string The swapcased string
*/
function utf8_swapcase($str)
{
$rv = '';
while (($char = utf8_get_char($str, $i, $cp)) !== false) {
$_ = unicode_swapcase($cp);
if ($_ != $cp) {
$char = utf8_chr($_);
}
$rv .= $char;
}
return $rv;
}
