php实现中文分词的例子

<?php
function get_keywords_str($content='')
{
require('./phpanalysis.class.php');
$pa = new PhpAnalysis('utf-8', 'utf-8', false);
$pa->LoadDict();//载入
$pa->SetSource($content);//将要分开的内容传入
$pa->StartAnalysis(false);
$tags = $pa->GetFinallyResult(',',6);//分词样式是以逗号分开/分词长度
return $tags; www.111cn.net
}
$str="李世民是唐朝的第二任皇帝";
echo "分词前:".$str."<br/>";
echo "分词后:".get_keywords_str($str);
?>

//判断moblie
function is_mobile()
{
    $_SERVER['ALL_HTTP'] = isset($_SERVER['ALL_HTTP']) ? $_SERVER['ALL_HTTP'] : '';
 
    $mobile_browser = '0';
 
    if(preg_match('/(up.browser|up.link|mmp|symbian|smartphone|midp|wap|phone|iphone|ipad|ipod|android|xoom|ios)/i', strtolower($_SERVER['HTTP_USER_AGENT'])))
        $mobile_browser++;
 
    if((isset($_SERVER['HTTP_ACCEPT'])) and (strpos(strtolower($_SERVER['HTTP_ACCEPT']),'application/vnd.wap.xhtml+xml') !== false))
        $mobile_browser++;
 
    if(isset($_SERVER['HTTP_X_WAP_PROFILE']))
        $mobile_browser++;
 
    if(isset($_SERVER['HTTP_PROFILE']))
        $mobile_browser++;
 
    $mobile_ua = strtolower(substr($_SERVER['HTTP_USER_AGENT'],0,4));
    $mobile_agents = array(
                        'w3c ','acs-','alav','alca','amoi','audi','avan','benq','bird','blac',
                        'blaz','brew','cell','cldc','cmd-','dang','doco','eric','hipt','inno',
                        'ipaq','java','jigs','kddi','keji','leno','lg-c','lg-d','lg-g','lge-',
                        'maui','maxo','midp','mits','mmef','mobi','mot-','moto','mwbp','nec-',
                        'newt','noki','oper','palm','pana','pant','phil','play','port','prox',
                        'qwap','sage','sams','sany','sch-','sec-','send','seri','sgh-','shar',
                        'sie-','siem','smal','smar','sony','sph-','symb','t-mo','teli','tim-',
                        'tosh','tsm-','upg1','upsi','vk-v','voda','wap-','wapa','wapi','wapp',
                        'wapr','webc','winw','winw','xda','xda-'
                        );
 
    if(in_array($mobile_ua, $mobile_agents))
        $mobile_browser++;
 
    if(strpos(strtolower($_SERVER['ALL_HTTP']), 'operamini') !== false)
        $mobile_browser++;
       www.111cn.net
    // Pre-final check to reset everything if the user is on Windows
    if(strpos(strtolower($_SERVER['HTTP_USER_AGENT']), 'windows') !== false)
        $mobile_browser=0;
 
    // But WP7 is also Windows, with a slightly different characteristic
    if(strpos(strtolower($_SERVER['HTTP_USER_AGENT']), 'windows phone') !== false)
        $mobile_browser++;
 
    if($mobile_browser>0)
        return true;
    else
        return false;
}

<?php

$string = "hello world";

echo urlencode($string) . '<br/>'; //输出：hello+world
echo rawurldecode($string) . '<br/>';//输出：hello%20world

?>

<?php
for ($i = 0x20; $i < 0x7f; $i++) {
$str .= dechex($i);
}

$asscii = pack("H*",$str);
echo "所有的可打印的asscii字符：（从空格到~）n". $asscii."\n";
echo "urlencode 的结果：\n".urlencode($asscii);
echo "\n";
echo "urlencode 不做编码的字符：\n".preg_replace("/%.{2}/","",urlencode($asscii));
echo "\n";
echo "rawurlencode 的结果：\n".rawurlencode($asscii);
echo "\n";
echo "rawurlencode 不做编码的字符：\n".preg_replace("/%.{2}/","",rawurlencode($asscii));
echo  "\n";

exit;
?>

输出结果：
———————————————————————————
所有的可打印的asscii字符：（从空格到~）
!"#$%&’()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_abcdefghijklmnopqrstuvwxyz{|}~
urlencode 的结果：
+%21%22%23%24%25%26%27%28%29%2A%2B%2C-.%2F0123456789%3A%3B%3C%3D%3E%3F%40ABCDEFGHIJKLMNOPQRSTUVWXYZ%5B%5C%5D%5E_%60abcdefghijklmnopqrstuvwxyz%7B%7C%7D%7E
urlencode 不做编码的字符：
+-.0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz
rawurlencode 的结果：
%20%21%22%23%24%25%26%27%28%29%2A%2B%2C-.%2F0123456789%3A%3B%3C%3D%3E%3F%40ABCDEFGHIJKLMNOPQRSTUVWXYZ%5B%5C%5D%5E_%60abcdefghijklmnopqrstuvwxyz%7B%7C%7D%7E
rawurlencode 不做编码的字符：
-.0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz

>>>  console.log(encodeURIComponent("统一注册1"));

%E7%BB%9F%E4%B8%80%E6%B3%A8%E5%86%8C1
>>> console.log(escape("统一注册1"));
%u7EDF%u4E00%u6CE8%u518C1

<?php
echo iconv("utf-8","gbk",urldecode("%E7%BB%9F%E4%B8%80%E6%B3%A8%E5%86%8C1"));
echo "\n";
echo urldecode("%u7EDF%u4E00%u6CE8%u518C1");
// 使用下面的unescape可以
//echo iconv("utf-8","gbk",unescape("%u7EDF%u4E00%u6CE8%u518C1");
exit;
?>

输出结果：
======================================
统一注册1
%u7EDF%u4E00%u6CE8%u518C1
======================================

function unescape($str) {
    $str = rawurldecode($str);
    preg_match_all("/(?:%u.{4})|&#x.{4};|&#d+;|.+/U",$str,$r);
    $ar = $r[0];
    foreach($ar as $k=>$v) {
        if(substr($v,0,2) == "%u")
            $ar[$k] = iconv("UCS-2","UTF-8",pack("H4",substr($v,-4)));
        elseif(substr($v,0,3) == "&#x")
            $ar[$k] = iconv("UCS-2","UTF-8",pack("H4",substr($v,3,-1)));
        elseif(substr($v,0,2) == "&#") {
            $ar[$k] = iconv("UCS-2","UTF-8",pack("n",substr($v,2,-1)));
        }
    }
    return join("",$ar);
}

?>

>>> console.log(escape(" !\"#$%&'()*+,-./0123456789:;=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_abcdefghijklmnopqrstuvwxyz{|}~"));
%20%21%22%23%24%25%26%27%28%29*+%2C-./0123456789%3A%3B%3C%3D%3E%3F@ABCDEFGHIJKLMNOPQRSTUVWXYZ%5B%5D%5E_%60abcdefghijklmnopqrstuvwxyz%7B%7C%7D%7E
>>> console.log(encodeURIComponent("!\"#$%&’()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_abcdefghijklmnopqrstuvwxyz{|}~"));
%20!%22%23%24%25%26'()*%2B%2C-.%2F0123456789%3A%3B%3C%3D%3E%3F%40ABCDEFGHIJKLMNOPQRSTUVWXYZ%5B%5D%5E_%60abcdefghijklmnopqrstuvwxyz%7B%7C%7D~
>>> console.log(escape("!\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_abcdefghijklmnopqrstuvwxyz{|}~").replace(/%.{2}/g,""));

*+-./0123456789@ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz
>>> console.log(encodeURIComponent("!\"#$%&’()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~").replace(/%.{2}/g,""));
!’()*-.0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz~

数组->字符
$txt=implode("?",arr[]);

字符->数组
$arr[]=explode("?",txt);

$data = array('上海', '北京', '武汉');
$data = serialize($data);
echo $data;

<?php
$file="./data/file.cache";
$array = array("count" => "3000",
              "num"  =>"300");
 //缓存
file_put_contents($file,serialize($array));//写入缓存
$cacheArray = unserialize(file_get_contents($file));
print_r($cacheArray);
?>

/**
* 将字符串转换为数组
*
* @param    string  $data   字符串
* @return   array   返回数组格式，如果，data为空，则返回空数组
*/ 
 function string2array($data) {  
    if($data == '') return array();  
    @eval("$array = $data;");  
    return $array;  
}  
 /**
* 将数组转换为字符串
*
* @param    array   $data       数组
* @param    bool    $isformdata 如果为0，则不使用new_stripslashes处理，可选参数，默认为1
* @return   string  返回字符串，如果，data为空，则返回空
*/ 
function array2string($data, $isformdata = 1) {  
    if($data == '') return '';  
    if($isformdata) $data = new_stripslashes($data);  
    return addslashes(var_export($data, TRUE));  
}