$str = 'hello word2 haha word1 word4 word2';
$arrRet = trie_filter_search_all($resTrie, $str);
print_all($str, $arrRet);
echo "\ntest2///////////////////\n";
$str = 'hello word';
$arrRet = trie_filter_search($resTrie, $str);
print_all($str, array($arrRet));
//Array()
$arrRet = trie_filter_search_all($resTrie, 'hello word');
print_all($str, $arrRet);
echo "\ntest3///////////////////\n";
echo "start memory=" . memory_get_usage(true) . "\n";
date_default_timezone_set('Asia/Chongqing');
$test = array('a', 'abd', 'dad', 'pab', 'dda', 'word1f', 'cword1', 'cword1t');
foreach ($test as $v) {
// echo "per start memory=".memory_get_usage(true)."\n";
$arrRet = trie_filter_search_all($resTrie, $v);
// echo "per end memory=".memory_get_usage(true)."\n";
//print_all($v, $arrRet);
}
echo "end memory=" . memory_get_usage(true) . "\n";
echo date('Y-m-d H:i:s');
trie_filter_free($resTrie);
function print_all($str, $res)
{
//print_r($res);
echo "{$str}\n";
foreach ($res as $k => $v) {
echo $k . "=>{$v[0]}-{$v[1]}-" . substr($str, $v[0], $v[1]) . "\n";
}
}
ini_set('display_errors', 1);
error_reporting(E_ALL ^ E_NOTICE);
$arrWord = array('Key', 'w ord', '12345678');
$resTrie = trie_filter_new();
echo "\nsave key\n";
foreach ($arrWord as $k => $v) {
echo "id:", $k, ' -> ', $v, "\n";
trie_filter_store($resTrie, $k, $v, TRIE_FILTER_UP | TRIE_FILTER_SP | TRIE_FILTER_NUM);
}
//去掉关键字中的空格 小写转为大写 数字转为0
//实际相当于 array('WORD', 'KEY', '00000000');
trie_filter_save($resTrie, __DIR__ . '/blackword.tree');
$resTrie = trie_filter_load(__DIR__ . '/blackword.tree');
$strContent = 'hello wo rd WORD kEy 0123456789';
$arrRet = trie_filter_search_all($resTrie, $strContent, TRIE_FILTER_UP | TRIE_FILTER_SP | TRIE_FILTER_NUM);
//小写转为大写 数字转为0 忽略文本中的空格
//实际相当于 'HELLOWORDWORDKEY0000000000'
print_all($strContent, $arrRet);
function print_all($str, $res)
{
echo "\ntext:{$str}\n", "\nmatch ", count($res) / 3, "\n";
for ($i = 0, $c = count($res); $i < $c; $i += 3) {
echo 'id:', $res[$i + 2], ' -> ', substr($str, $res[$i], $res[$i + 1]), "\n";
}
}
trie_filter_free($resTrie);
/*输出为
save key
id:0 -> Key
/**
* 替换字符串中首次匹配到的敏感词
*
* @param $str
* @return string
* @throws Exception
*/
protected function oneReplace($str)
{
if (empty($str) || !is_string($str)) {
return '';
}
if (!$this->isEnable) {
return $str;
}
if (!is_resource($this->trie)) {
throw new Exception('Trie Error');
}
// 搜索敏感词
$arrRet = trie_filter_search_all($this->trie, $str);
// 没有敏感词，直接返回原句
if (empty($arrRet)) {
return $str;
}
// 用于存储替换后的字符串
$newStr = '';
// 记录上一个敏感词结尾的位置，初始为0
$end = 0;
foreach ($arrRet as $key => $value) {
$start = $value[0];
$length = $value[1];
$word = substr($str, $start, $length);
if (self::isSubstitute($word)) {
continue;
}
/**
* 如果敏感词是英文，就需要特殊判断
* 因为匹配出来的英文敏感词可能只是某个单词的一部分
* 例如：假设 ab 是敏感词，可能 ab 只是在单词 abstract 中的一部分内容，这种情况 ab 应该不算作敏感词，不应该被替换
*/
if (self::isAlpha($word)) {
$beforeChr = mb_substr(substr($str, 0, $start), -1, 1, 'UTF-8');
$afterChr = mb_substr(substr($str, $start + $length), 0, 1, 'UTF-8');
// 如果英文敏感词的前一个字符或后一个字符也是英文的话，就不替换
if (self::isAlpha($beforeChr) || self::isAlpha($afterChr)) {
continue;
}
}
// 拼接敏感词前面的内容
$newStr .= substr($str, $end, $start - $end);
// 记录敏感词结尾的位置
$end = $start + $length;
// 拼接*号（敏感词替换为了*）
$newStr .= str_repeat('*', mb_strlen($word, 'UTF-8'));
// 匹配一次即可，跳出循环
break;
}
$newStr .= substr($str, $end);
return $newStr;
}
