php检测文件内容编码的方法

核心用到的是mb_convert_encoding函数，示例代码如下：

 

<?php
header("Content-type: text/html; charset=utf-8");

/**
 * 获取内容的编码
 * @param string $str
 */
function get_encoding($str = "") {
    $encodings = array (
        'ASCII', 
        'UTF-8', 
        'GBK' 
    );
    foreach ( $encodings as $encoding ) {
        if ($str === mb_convert_encoding ( mb_convert_encoding ( $str, "UTF-32", $encoding ), $encoding, "UTF-32" )) {
            return $encoding;
        }
    }
    return false;
}
/**
 * 
 * 检测utf-8内容是否含有BOM头信息
 * @param string $str
 */
function utf8_has_bom($str) {
    $chars = substr ( $str, 0, 3 );
    $bom = chr ( 0xEF ) . chr ( 0xBB ) . chr ( 0xBF );
    return $chars === $bom;
}


// $filename = 'C:\Users\Administrator\Desktop\test.txt';
// $filename = 'C:\Users\Administrator\Desktop\ansi.txt';
// $filename = 'C:\Users\Administrator\Desktop\Unicode.txt';
$filename = 'C:\Users\Administrator\Desktop\my.txt';

// 检测编码
$str = file_get_contents($filename);
$encode = get_encoding($str);
var_dump($encode);


// 转换成"UTF-8"编码
if($encode != 'UTF-8'){
    $str = mb_convert_encoding($str, "UTF-8", $encode);
}

var_dump($str);

 

参考文档：https://gist.github.com/welefen/7746175