PHP之 敏感词过滤

方式一

<?php
 
    /**
     * 敏感词过滤
     *
     * @param string
     * @return string
     */
    function sensitive_words_filter($str)
    {
        if (!$str) return '';
        $file = 'public/system/plug/censorwords/CensorWords'; //文件路径及内容自定义
        $words = file($file);
        foreach ($words as $word) {
            $word = str_replace(array("\r\n", "\r", "\n", "/", "<", ">", "=", " "), '', $word);
            if (!$word) continue;
 
            $ret = preg_match("/$word/", $str, $match);
            if ($ret) {
                return $match[0];
            }
        }
        return '';
    }

二 同思路
创建 敏感词.csv

// 敏感词过滤
    $result = $this->get_Sensitive_Words_csv($params['post_content']);
    if($result == true){
        return reply("包含敏感字",1,$validator->errors());
    }

function get_Sensitive_Words_csv($content=''){

    // $csv_file='精确敏感词.csv';
    $csv_file='/www/wwwroot/mg.csv';  // 不能中文文件名

    // 防止乱码
    $content = '';
    $text = file_get_contents($csv_file);

    //$encodType = mb_detect_encoding($text);
    define('UTF32_BIG_ENDIAN_BOM', chr(0x00) . chr(0x00) . chr(0xFE) . chr(0xFF));
    define('UTF32_LITTLE_ENDIAN_BOM', chr(0xFF) . chr(0xFE) . chr(0x00) . chr(0x00));
    define('UTF16_BIG_ENDIAN_BOM', chr(0xFE) . chr(0xFF));
    define('UTF16_LITTLE_ENDIAN_BOM', chr(0xFF) . chr(0xFE));
    define('UTF8_BOM', chr(0xEF) . chr(0xBB) . chr(0xBF));
    $first2 = substr($text, 0, 2);
    $first3 = substr($text, 0, 3);
    $first4 = substr($text, 0, 3);
    $encodType = "";
    if (UTF8_BOM == $first3) {
        $encodType = 'UTF-8 BOM';
    } else if (UTF32_BIG_ENDIAN_BOM == $first4) {
        $encodType = 'UTF-32BE';
    } else if (UTF32_LITTLE_ENDIAN_BOM == $first4) {
        $encodType = 'UTF-32LE';
    } else if (UTF16_BIG_ENDIAN_BOM == $first2) {
        $encodType = 'UTF-16BE';
    } else if (UTF16_LITTLE_ENDIAN_BOM == $first2) {
        $encodType = 'UTF-16LE';
    }

    //下面的判断主要还是判断ANSI编码的·
    if ('' == $encodType) {
        //即默认创建的txt文本-ANSI编码的
        $content = iconv("GBK", "UTF-8", $text);
    } else if ('UTF-8 BOM' == $encodType) {
        //本来就是UTF-8不用转换
        $content = $text;
    } else {
        //其他的格式都转化为UTF-8就可以了
        $content = iconv($encodType, "UTF-8", $text);
    }
    $arr = explode("\r\n",$content);


    //读取文件
    // $file=file_get_contents($csv_file);
    // $arr = explode("\r\n",$file);

    foreach($arr as $k=>$v){
        if($v){
            if(strpos($content,trim($v))!==false){  // 有敏感字
                return true;
            }
        }
    }

    return false;
}