一个可以找出源代码中所有中文的工具_php实例

代码如下:

set_time_limit(0);
ob_implicit_flush();

//注释格式
$remark = array(
array('//debug', "\r\n")
, array('/**', '*/')
, array('/*debug', '*/')
, array('/*note', '*/')
, array('//note', "\r\n")
);

//以下目录和文件不被查询
$filter = 'forumdata|config\.inc\.php|debug|test|readme|utilities|upgrade|\.tpl.php|index\.htm|\.lang.php';

//项目目录
$sf = 'd:\\data\\labs\\develop\\dzhead\\';

//日志目录
$logname = 'cnlog.txt';
$langfile = 'lang.php';


$log = fopen($logname, 'w');
fclose($log);

$lf = fopen($langfile, 'wb');
fwrite($lf, "\r\n\r\n\t'spilt' => '----------------------------------------------------',");
fclose($lf);

$lf = fopen($langfile, 'ab');


$ptag = '\\';

findfile($sf);
fwrite($lf, "\r\n);\r\n\r\n?>");
fclose($lf);
function findfile($sf){
global $ptag, $logname, $filter, $lf;
$log = fopen($logname, 'ab');
global $remark;
if(is_dir($sf)) {
if($dh = opendir($sf)) {

while(($file = readdir($dh)) !== false) {
if($file == '.' || $file == '..') {
continue;
} elseif(filetype($sf.$file) == 'dir') {
findfile($sf.$file.$ptag);
} elseif((preg_match('/\.php$/', $file) || preg_match('/\.htm$/', $file)) && !preg_match('/('.$filter.')/', $sf.$file)) {

$sfp = fopen($sf.$file, 'rb');
$buf = fread($sfp, filesize($sf.$file));
fclose($sfp);
foreach($remark as $v) {
$data = '';
while(count($strcut = explode($v[0], $buf, 2)) > 1) {
$data .= $strcut[0];
if(($strcut = explode($v[1], $strcut[1], 2)) > 1){
$buf = $strcut[1];
} else {
$buf = $strcut[0];
break;
}

}
$data .= $strcut[0];
$buf = $data;
}
$data = $buf;
$lines = 0;
$cn = $str = '';
$cns = 0;
$ldata = "\r\n\t'".str_replace('.', '_', $file)."' => '";
for($i = 0; $i $c = ord($data{$i});
if($c == 0x0A || $data{$i+1} == ''){
$lines++;
if(!empty($cn)){
$ldata .= "',";
$ldata = str_replace("\r\n\t'".str_replace('.', '_', $file)."' => '',", '', $ldata);
fwrite($lf, $ldata);
$cn = "\r\n$lines:".$cn;
$str .= $cn;
$cn = '';
$ldata = "\r\n\t'".str_replace('.', '_', $file)."' => '";
}
} elseif($c >= 0x81 && $c <= 0xFE) {
$c = ord($data{++$i});
if($c >= 0x40 && $c <= 0xFE) {
$cn .= $data{$i-1}.$data{$i};
$ldata .= $data{$i-1}.$data{$i};
while(($c = ord($data{++$i})) != 0x3C && $c != 0x0A && $c != 0x0D && $c != 0x27 && $c != 0x3E && $c != 0x3B && $c != 0x22 && $c != 0x3D && $c <0x81) {
$space .= chr($c);
}
$i--;
if(ord($data{$i+1}) <0x81) {
$cns++;
$cn .= '$';
$ldata .= "',\r\n\t'".str_replace('.', '_', $file)."' => '";
} else {
$cn .= $space;
}
$space = '';
}
}
}
if($str != '') {
fwrite($log, "\n--".$sf.$file."----------------------- (共 $cns 处)");
echo "{$sf}$file (共 $cns 处)
";
ob_flush();flush();
$cns = 0;
}
fwrite($log, $str);
$str = '';
}
}
}
}
fclose($log);

}
?>