代码文件的编码不统一导致的坑

<?php

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

/*
 * +---------------------------------------------------
 *  遍历指定目录,形成一个目录句柄返回
 * +---------------------------------------------------
 *
 * +---------------------------------------------------
 */

function explorer_dir($sDir) {

    static $aTempArr = array();

    $dp = opendir($sDir);

    while ($sFileName = readdir($dp)) {
        if ($sFileName != ‘.‘ && $sFileName != ‘..‘) {
            $sPath = $sDir . "/" . $sFileName;
            if (is_dir($sPath)) {
                explorer_dir($sPath);
            } else {
//                $filetime=date("Y-m-d H:i:s",filectime("$path"));
//                $fp=$path.",".$filetime;
                $fp = $sPath;
                $aTempArr[] = $fp;
            }
        }
    }
    closedir($dp);
    return $aTempArr;
}
/*
 * +----------------------------------------------------------------------
 * //搜索指定目录下的gb2312编码文件,转换成utf-8编码文件
 * +----------------------------------------------------------------------
 */
function change_gb2312_to_utf8_dir($dir) {

    $all_dirs = explorer_dir($dir);
    $suffix_list = array(‘php‘, ‘htm‘, ‘html‘, ‘txt‘, ‘js‘);
    echo ‘get files count:‘;
    echo count($all_dirs) . ‘<br />‘;
    $i = 0;
    foreach ($all_dirs as $dir_key => $file_path) {

        $file_content = file_get_contents($file_path);
        $i++;
       echo $i . ‘、‘ . $file_path.‘<br />‘;
        var_dump($file_encode_type = mb_detect_encoding($file_content, array(‘UTF-8‘, ‘EUC-CN‘), true)); //EUC-CN是gb2312的另外称呼,php这个扩展返回的是值,不是gb2312
        echo ‘<br />‘;

        //获取文件的后缀,指定文件类型采取做操作，比如图片就不能去修改的
        $file_name = basename($file_path);
        $suffix = get_file_suffix($file_name);
        if (in_array($suffix, $suffix_list)) {
            if ($file_encode_type == ‘EUC-CN‘) {
                echo ‘<font color="red">had changed the file from ‘ . $file_encode_type . ‘(gb2312) to UTF-8:‘ . $file_path . ‘</font><br /><br />‘;
                //就是gb2312编码的
                $after_change_encode_content = iconv("gb2312", "UTF-8", $file_content);
                unlink($file_path);
                file_put_contents($file_path, $after_change_encode_content);
                unset($after_change_encode_content);
            }
        } else {

            echo ‘<font color="red">the file not in allow file type:‘ . $file_path . ‘</font><br /><br />‘;
        }
        unset($file_content);
        echo ‘--------------------------------------------------------------------<br /><br />‘;
    }
}



/*
 * +----------------------------------------------------------------------
 * //搜索指定目录下指定编码的文件,目的就是帮助我们看出自己的项目哪些是什么编码的文件
 * +----------------------------------------------------------------------
 */
function dir_file_encode_list($dir) {



    $all_dirs = explorer_dir($dir);

    echo ‘get files count:‘;
    echo count($all_dirs) . ‘<br />‘;
    $i = 0;
    foreach ($all_dirs as $dir_key => $file_path) {

        $file_content = file_get_contents($file_path);
        $i++;
        echo $i . ‘、‘ . $file_path.‘<br />‘;
        var_dump($file_encode_type = mb_detect_encoding($file_content, array(‘UTF-8‘, ‘EUC-CN‘), true)); //EUC-CN是gb2312的另外称呼,php这个扩展返回的是值,不是gb2312
        echo ‘<br />‘;
        unset($file_content);

        echo ‘--------------------------------------------------------------------<br /><br />‘;
    }
}
/*
 * +----------------------------------------------------------------------
 * 扫描指定目录下的指定目录下的html文件,批量将里面的
 * <meta http-equiv="Content-Type" content="text/html; charset=gbk" />
 * 指定的编码替换成另外一个编码
 * +----------------------------------------------------------------------
 */
function replace_html_charset($dir) {

    $all_dirs = explorer_dir($dir);
    $suffix_list = array(‘htm‘, ‘html‘,‘php‘);
    echo ‘get files count:‘;
    echo count($all_dirs) . ‘<br />‘;
    $i = 0;
    $charset = ‘<meta http-equiv="Content-Type" content="text/html; charset=gbk" />‘;
    $to_charset = ‘<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />‘;
    foreach ($all_dirs as $dir_key => $file_path) {

        $file_content = file_get_contents($file_path);
        $i++;
        echo $i . ‘、‘ . $file_path.‘<br />‘;
        //获取文件的后缀,指定文件类型采取做操作，比如图片就不能去修改的
        $file_name = basename($file_path);
        $suffix = get_file_suffix($file_name);
        if (in_array($suffix, $suffix_list)) {
            $patten = ‘%‘ . $charset . ‘%i‘;
       
            if (preg_match($patten, $file_content)) {
                $after_change_encode_content = str_ireplace($charset, $to_charset, $file_content);
                unlink($file_path);
                file_put_contents($file_path, $after_change_encode_content);
                unset($after_change_encode_content);
                echo ‘find limit :‘ . $file_path . ‘<br /><br />‘;
            }
        }else{
             echo ‘<font color="red">the file not in allow file type:‘ . $file_path . ‘</font><br /><br />‘;
        }
    }
}

//dir_file_encode_list("D:\\static\\develop\\mama\\test_change_encode");


//change_gb2312_to_utf8_dir("D:\\static\\develop\\mama\\test_change_encode");


//replace_html_charset("D:\\static\\develop\\mama\\test_change_encode");



function get_file_suffix($file_name){

    $file_name_arr = explode(".", $file_name);
        $suffix = array_pop($file_name_arr);

        return $suffix;
}