function print_utf8($ascii)
{
$char = utf8_chr($ascii);
if (preg_match("#[\\x00-\\x1F]|\\x7F|(?:\\xC2[\\x80-\\xA0])#", $char)) {
return htmlentities("<control>");
}
return $char;
}
/**
* Takes an array of ints representing the Unicode characters and returns
* a UTF-8 string.
*
* @param array $array array of unicode code points representing a string
* @return string UTF-8 character string
*/
function utf8_from_unicode($array)
{
$str = '';
foreach ($array as $value) {
$str .= utf8_chr($value);
}
return $str;
}
function filter_named_entities(&$content)
{
global $html_named_entities_mapping_mine;
foreach ($html_named_entities_mapping_mine as $name => $value) {
$content = str_replace('&' . $name . ';', utf8_chr($value), $content);
}
$content = str_replace('í', 'i', $content);
# Ugly hack
}
/**
* @dataProvider providerFailingUtf8Chr
*/
public function testFailingUtf8ChrReturnValue($cp)
{
$this->assertFalse(@utf8_chr($cp, true));
}
/**
* decode_ncr() 回调函数
* 函数会忽略大部分 (不是全部) 错误的 NCR
*/
function utf8_from_ncr_callback($m)
{
$cp = strncasecmp($m[1], 'x', 1) ? $m[1] : hexdec(substr($m[1], 1));
return utf8_chr($cp);
}
/**
* 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 $rv;
}
}
}
// do some tests for things that transform into something with the number one
if (strpos($temp_hold, utf8_chr(0x31)) !== false) {
// any kind of letter L?
if (strpos($value[0], 'LETTER L') !== false || strpos($value[0], 'IOTA') !== false || strpos($value[0], 'SMALL L ') !== false || preg_match('/SMALL LIGATURE [^L]*L /', $value[0])) {
// replace all of the mappings that transform some sort of letter l to number one instead to some sort of letter l to latin small letter l
$temp_hold = str_replace(utf8_chr(0x31), utf8_chr(0x6c), $temp_hold);
}
}
// uppercased chars that were folded do not exist in this universe,
// no amount of normalization could ever "trick" this into not working
if (in_array($value[1], $casefold_array[1])) {
continue;
}
$uniarray[utf8_chr(hexdec((string) $value[1]))] = $temp_hold;
}
echo "Writing to confusables.{$phpEx}\n";
$fp = fopen($phpbb_root_path . 'includes/utf/data/confusables.' . $phpEx, 'wb');
fwrite($fp, '<?php return ' . my_var_export($uniarray) . ';');
fclose($fp);
/**
* Return a parsable string representation of a variable
*
* This is function is limited to array/strings/integers
*
* @param mixed $var Variable
* @return string PHP code representing the variable
*/
function my_var_export($var)
{
} else {
if ($cp > 0x7ff) {
return chr(0xe0 | $cp >> 12) . chr(0x80 | $cp >> 6 & 0x3f) . chr(0x80 | $cp & 0x3f);
} else {
if ($cp > 0x7f) {
return chr(0xc0 | $cp >> 6) . chr(0x80 | $cp & 0x3f);
} else {
return chr($cp);
}
}
}
}
preg_match_all('/^([0-9A-F]+); ([CFS]); ([0-9A-F]+(?: [0-9A-F]+)*);/im', $unidata, $array, PREG_SET_ORDER);
$uniarray = array();
foreach ($array as $value) {
$uniarray[$value[2]][utf8_chr(hexdec((string) $value[1]))] = implode(array_map('utf8_chr', array_map('hexdec', explode(' ', $value[3]))));
}
foreach ($uniarray as $idx => $contents) {
echo "Writing to case_fold_{$idx}.{$phpEx}\n";
$fp = fopen($phpbb_root_path . 'includes/utf/data/case_fold_' . strtolower($idx) . '.' . $phpEx, 'wb');
fwrite($fp, '<?php return ' . my_var_export($contents) . ';');
fclose($fp);
}
/**
* Return a parsable string representation of a variable
*
* This is function is limited to array/strings/integers
*
* @param mixed $var Variable
* @return string PHP code representing the variable
*/
/**
* Callback function for utf8_decode_entities
* @param array
* @return string
*/
function utf8_hexchr_callback($matches)
{
return utf8_chr(hexdec($matches[1]));
}
/**
* utf8_strrpos( )
*
* Find position of last occurrence of a char in a UTF-8 string
* @since 1.3
*
* @param string $haystack The string to search in
* @param string $needle The string to search for
* @param int $offset Number of char to ignore from start or end
* @return int THe position of last occurrance of needle
*/
function utf8_strrpos($haystack, $needle, $offset = 0)
{
if ((int) $needle === $needle && $needle >= 0) {
$needle = utf8_chr($needle);
}
$needle = utf8_clean((string) $needle);
$offset = (int) $offset;
$haystack = utf8_clean($haystack);
if (mbstring_loaded()) {
//mb_strrpos returns wrong position if invalid characters are found in $haystack before $needle
return mb_strrpos($haystack, $needle, $offset, 'UTF-8');
}
if (iconv_loaded() && $offset === 0) {
//iconv_strrpos is not tolerant to invalid characters
//iconv_strrpos does not accept $offset
return iconv_strrpos($haystack, $needle, 'UTF-8');
}
if ($offset > 0) {
$haystack = utf8_substr($haystack, $offset);
} else {
if ($offset < 0) {
$haystack = utf8_substr($haystack, 0, $offset);
}
}
if (($pos = strrpos($haystack, $needle)) !== false) {
$left = substr($haystack, 0, $pos);
return ($offset > 0 ? $offset : 0) + utf8_strlen($left);
}
return false;
}
/**
* 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;
}
