/**
* 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++]);
$r = 0;
}
}
}
/**
* @dataProvider providerUtf8GetChar
*/
public function testUtf8GetChar($str, $rchars, $runicode)
{
$chars = $unicode = array();
while (($char = utf8_get_char($str, $i, $cp)) !== false) {
$chars[] = $char;
$unicode[] = $cp;
}
$this->assertEquals($chars, $rchars);
$this->assertEquals($unicode, $runicode);
}
/**
* UTF-8 aware replacement for substr().
*
* Returns the portion of the string specified by the start and end positions.
*
* @param string $str The UTF-8 encoded string
* @param int $start The start position
* @param int $end The end position
* @return string The portion of the string
*/
function utf8_slice($str, $start, $end = null)
{
$start = (int) $start;
if ($end !== null) {
$end = (int) $end;
}
if ($start < 0 || $end < 0) {
$len = utf8_length($str);
if ($start < 0) {
$start += $len;
if ($start < 0) {
$start = 0;
}
}
if ($end < 0) {
$end += $len;
if ($end < 0) {
$end = 0;
}
}
}
if ($end === null) {
$end = -1;
} elseif ($start > $end) {
return '';
}
$j = 0;
$chunk = '';
while (($char = utf8_get_char($str, $i)) !== false) {
if ($j >= $start) {
$chunk .= $char;
}
if ($j++ == $end) {
break;
}
}
return $chunk;
}
/**
* UTF-8 aware replacement for trim().
*
* Strip whitespace (or other characters) from the beginning and end of
* a string.
*
* @param string $str The UTF-8 encoded string
* @param mixed $stripchars The stripped characters
* @param int $striptype The optional argument $striptype can be
* UTF8_STRIP_BOTH, UTF8_STRIP_LEFT, or UTF8_STRIP_RIGHT.
* If $striptype is not specified it is assumed to be
* UTF8_STRIP_BOTH.
* @return string The stripped string
*/
function utf8_strip($str, $stripchars = null, $striptype = UTF8_STRIP_BOTH)
{
static $defaults;
global $unicode_separators_array;
if ($stripchars === null) {
if ($defaults === null) {
foreach ($unicode_separators_array as $cp) {
$defaults[] = utf8_chr($cp);
}
}
$stripchars = $defaults;
} elseif (is_array($stripchars)) {
$chars = array();
foreach ($stripchars as $char) {
if (($char = utf8_get_char($char)) !== false) {
$chars[] = $char;
}
}
$stripchars = $chars;
} else {
$stripchars = utf8_split($stripchars, 1);
}
$left = $striptype & UTF8_STRIP_LEFT;
$right = $striptype & UTF8_STRIP_RIGHT;
$rv = $buffer = '';
while ($char = utf8_get_char($str, $i)) {
$state = in_array($char, $stripchars);
if ($left) {
if ($state) {
continue;
} else {
$left = false;
}
}
if ($right) {
if ($state) {
$buffer .= $char;
continue;
} else {
$rv .= $buffer;
$buffer = '';
}
}
$rv .= $char;
}
return $rv;
}
/**
* Returns a string with the first character of each word converted to
* uppercase and the remainder to lowercase.
*
* @param string $str The UTF-8 encoded string
* @return string with the first character of each word converted to uppercase
* and the remainder to lowercase
*/
function utf8_capwords($str)
{
$rv = '';
$state = true;
while (($char = utf8_get_char($str, $i, $cp)) !== false) {
if (!($issep = unicode_is_separator($cp))) {
$_ = $state ? unicode_upcase($cp) : unicode_downcase($cp);
if ($_ != $cp) {
$char = utf8_chr($_);
}
}
$state = $issep;
$rv .= $char;
}
return $rv;
}
