有没有一种简单的方法可以将UTF-8字符串转换为其unicode?我基本上想做的是将"è"转换为"00E8"。
您可以使用json_encode
来执行此操作。。。
$str = "è";
$str = json_encode($str);
print $str;
这将打印''u00e8。如果需要,可以str_replace
删除''u。如果您想要E而不是E,则可以使用strtoupper
。
以下是我从的调试类中修改的一些内容
/**
* Display utf && non-printable characters as hex
*
* @param string $str string containing binary
* @param boolean $htmlout add html markup?
*
* @return string
*/
public function strInspect($str)
{
$this->htmlout = $htmlout;
$regex = <<<EOD
/
( ['x01-'x7F] ) # single-byte sequences 0xxxxxxx (ascii 0 - 127)
| (
(?: ['xC0-'xDF]['x80-'xBF] # double-byte sequences 110xxxxx 10xxxxxx
| ['xE0-'xEF]['x80-'xBF]{2} # triple-byte sequences 1110xxxx 10xxxxxx * 2
| ['xF0-'xF7]['x80-'xBF]{3} # quadruple-byte sequence 11110xxx 10xxxxxx * 3
){1,100} # ...one or more times
)
| ( ['x80-'xBF] ) # invalid byte in range 10000000 - 10111111 128 - 191
| ( ['xC0-'xFF] ) # invalid byte in range 11000000 - 11111111 192 - 255
| (.) # null (including x00 in the regex = fail)
/x
EOD;
$str_orig = $str;
$strlen = strlen($str);
$str = preg_replace_callback($regex, 'strInspectCallback', $str);
return $str;
}
/**
* Callback used by strInspect's preg_replace_callback
*
* @param array $matches matches
*
* @return string
*/
protected function strInspectCallback($matches)
{
$showHex = false;
if ($matches[1] !== '') {
// single byte sequence (may contain control char)
$str = $matches[1];
if (ord($str) < 32 || ord($str) == 127) {
$showHex = true;
if (in_array($str, array("'t","'n","'r"))) {
$showHex = false;
}
}
} elseif ($matches[2] !== '') {
// Valid byte sequence. return unmodified.
$str = $matches[2];
$sequences = array(
"'xef'xbb'xbf", // BOM
"'xc2'xa0", // no-break space
// "'xE2'x80'x89", // thin space
// "'xE2'x80'xAF", // narrow no-break space
"'xEF'xBF'xBD", // "Replacement Character"
);
foreach ($sequences as $seq) {
if ($str === $seq) {
$showHex = true;
break;
}
}
} elseif ($matches[3] !== '' || $matches[4] !== '') {
// Invalid byte
$str = $matches[3] != ''
? $matches[3]
: $matches[4];
$showHex = true;
} else {
// null char
$str = $matches[5];
$showHex = true;
}
if ($showHex) {
$chars = str_split($str);
foreach ($chars as $i => $c) {
$chars[$i] = ''x'.bin2hex($c);
}
$str = implode('', $chars);
}
return $str;
}