php截取html字符串自动补全html标签,当数据量太大无法取出的问题的解决办法

首先,创建一个存储过程 get_clob:
t_name:要查询的表名;f_name:要查询的字段名;u_id:表的主键,查询条件;l_pos:截取的开始位置;
l_amount :截取长度; CREATE OR REPLACE PROCEDURE get_clob(t_name in
varchar2, f_name in varchar, u_id in integer, l_pos in integer,
l_amount in BINARY_INTEGER, ReturnValue out varchar2) is rule_xml
clob; l_buffer varchar2(3999); l_amount_ BINARY_INTEGER; begin
execute immediate ‘select ‘ ||f_name|| ‘ from ‘ ||t_name|| ‘ where
id=:1’ into rule_xml using u_id; l_amount_:=l_amount;
DBMS_LOB.read(rule_xml, l_amount_, l_pos, l_buffer); ReturnValue
:= l_buffer; end get_clob; 然后是php的处理程序: $content = “”; $num =
0;//clob字段长度 $stmt = $oracle-prepare(“select length(content) as num
from test where id = $id”); if ($stmt-execute()) { //zjh为查询的条件
$row = $stmt-fetch(); $num = $row[‘NUM’]; } $start =
1;//初始化开始位置 $len = 2500;//截取长度 $t_name = ‘test’;//操作表名
$f_name = ‘content’;//需要查询的clob字段名 while ($start = $num){
$ret=”; $sql = “begin get_clob(?,?,?,?,?,?); end;”; $stmt =
$oracle-prepare($sql); $stmt-bindParam(1, $t_name, PDO::PARAM_STR,
100); $stmt-bindParam(2, $f_name, PDO::PARAM_STR, 100);
$stmt-bindParam(3, $id, PDO::PARAM_STR, 100); $stmt-bindParam(4,
$start, PDO::PARAM_STR, 100); $stmt-bindParam(5, $len, PDO::PARAM_STR,
100); $stmt-bindParam(6, $ret, PDO::PARAM_STR, 5000); $stmt-execute();
$content .= $ret; $start=$start+$len; } $oracle = null;
以上就是完整的解决办法,这个方法不是俺的首创,做过pb项目的人大多数应该比较熟悉这种操作。
php操作Oracle的资料网上还是比较少的,能解决问题的就更不多了,发出来跟大家分享一下,肯定还有其他比较好的解决办法,欢迎跟大家一起探讨。

 代码如下

/**
 * 截取HTML,并自动补全闭合
 * @param $html
 * @param $length
 * @param $end
 */
function subHtml($html,$length) {
 $result = ”;
 $tagStack = array();
 $len = 0;

 $contents = preg_split(“~(<[^>]+?>)~si”,$html,
-1,PREG_SPLIT_NO_EMPTY| PREG_SPLIT_DELIM_CAPTURE);
 foreach($contents as $tag)
 {
 if (trim($tag)==””)  continue;
 if(preg_match(“~<([a-z0-9]+)[^/>]*?/>~si”,$tag)){
 $result .= $tag;
 }else
if(preg_match(“~</([a-z0-9]+)[^/>]*?>~si”,$tag,$match)){
 if($tagStack[count($tagStack)-1] == $match[1]){
 array_pop($tagStack);
 $result .= $tag;
 }
 }else
if(preg_match(“~<([a-z0-9]+)[^/>]*?>~si”,$tag,$match)){
 array_push($tagStack,$match[1]);
 $result .= $tag;
 }else if(preg_match(“~<!–.*?–>~si”,$tag)){
 $result .= $tag;
 }else{
 if($len + mstrlen($tag) < $length){
 $result .= $tag;
 $len += mstrlen($tag);
 }else {
 $str = msubstr($tag,0,$length-$len+1);
 $result .= $str;
 break;
 }

 }
 }
 while(!empty($tagStack)){
 $result .= ‘</’.array_pop($tagStack).’>’;
 }
 return  $result;
}

/**
 * 截取中文字符串
 * @param $string 字符串
 * @param $start 起始位
 * @param $length 长度
 * @param $charset  编码
 * @param $dot 附加字串
 */
function msubstr($string, $start, $length,$dot=”,$charset = ‘UTF-8’)
{
 $string = str_replace(array(‘&’, ‘"’, ‘<‘,
‘>’,’ ‘), array(‘&’, ‘”‘, ‘<‘, ‘>’,’ ‘), $string);
 if(strlen($string) <= $length) {
 return $string;
 }

 if(strtolower($charset) == ‘utf-8’) {
 $n = $tn = $noc = 0;
 while($n < strlen($string)) {
 $t = ord($string[$n]);
 if($t == 9 || $t == 10 || (32 <= $t && $t <= 126)) {
 $tn = 1; $n++;
 } elseif(194 <= $t && $t <= 223) {
 $tn = 2; $n += 2;
 } elseif(224 <= $t && $t <= 239) {
 $tn = 3; $n += 3;
 } elseif(240 <= $t && $t <= 247) {
 $tn = 4; $n += 4;
 } elseif(248 <= $t && $t <= 251) {
 $tn = 5; $n += 5;
 } elseif($t == 252 || $t == 253) {
 $tn = 6; $n += 6;
 } else {
 $n++;
 }
 $noc++;
 if($noc >= $length) {
 break;
 }
 }
 if($noc > $length) {
 $n -= $tn;
 }
 $strcut = substr($string, 0, $n);
 } else {
 for($i = 0; $i < $length; $i++) {
 $strcut .= ord($string[$i]) > 127 ? $string[$i].$string[++$i]
: $string[$i];
 }
 }

 return $strcut.$dot;
}

/**
 * 取得字符串的长度,包括中英文。
 */
function mstrlen($str,$charset = ‘UTF-8’){
 if (function_exists(‘mb_substr’)) {
 $length=mb_strlen($str,$charset);
 } elseif (function_exists(‘iconv_substr’)) {
 $length=iconv_strlen($str,$charset);
 } else {
 preg_match_all(“/[x01-x7f]|[xc2-xdf][x80-xbf]|xe0[xa0-xbf][x80-xbf]|[xe1-xef][x80-xbf][x80-xbf]|xf0[x90-xbf][x80-xbf][x80-xbf]|[xf1-xf7][x80-xbf][x80-xbf][x80-xbf]/”,
$text, $ar); 
 $length=count($ar[0]);
 }
 return $length;
}

实例

 代码如下

* @param 要截取的HTML $str
* @param 截取的数量 $num
* @param 是否需要加上更多 $more
* @return 截取串
*/
function phpos_chsubstr_ahtml($str,$num,$more=false)
{
    $leng=strlen($str);
      if($num>=$leng)      return $str;
    $word=0;
    $i=0;                        /** 字符串指针 **/
    $stag=array(array());        /** 存放开始HTML的标志 **/
    $etag=array(array());        /** 存放结束HTML的标志 **/
    $sp = 0;
    $ep = 0;
      while($word!=$num)
      {

          if(ord($str[$i])>128)
          {
            //$re.=substr($str,$i,3);
            $i+=3;
            $word++;
          }
          else if ($str[$i]=='<‘)
          {
              if ($str[$i+1] == ‘!’)
              {
                $i++;
                  continue;
              }

              if ($str[$i+1]==’/’)   
              {
                $ptag=&$etag ;
                $k=&$ep;
                $i+=2;
              }
              else                   
              {
                $ptag=&$stag;
                $i+=1;
                $k=&$sp;
              }

              for(;$i<$leng;$i++)       
              {
                  if ($str[$i] == ‘ ‘)
                  {
                    $ptag[$k] = implode(”,$ptag[$k]);
                    $k++;
                      break;
                  }
                  if ($str[$i] != ‘>’)
                  {
                    $ptag[$k][]=$str[$i];
                      continue;
                  }
                  else               
                  {
                    $ptag[$k] = implode(”,$ptag[$k]);
                    $k++;
                      break;
                  }
              }
            $i++;
              continue;
          }
          else
          {
            //$re.=substr($str,$i,1);
            $word++;
            $i++;
          }
      }
      foreach ($etag as $val)
      {
        $key1=array_search($val,$stag);
          if ($key1 !== false)          unset($stag[$key]);
      }
      foreach ($stag as $key => $val)
      {
          if (in_array($val,array(‘br’,’img’)))
unset($stag[$key1]);
      }
    array_reverse($stag);
    $ends = ‘</’.implode(‘></’,$stag).’>’;
    $re = substr($str,0,$i).$ends;
      if($more)    $re.=’…’;
      return $re;
}

PHP截取字符串,生成文章摘要
我们在写BLOG时经常需要显示文章前一部分,但是又怕不恰当截断破坏封闭标签以造成整个文档结构破坏

  

 代码如下

  function text_zhaiyao($text,$length){ //文章摘要生成函数  $test:内容
$length:摘要长度
    global $Briefing_Length;
    mb_regex_encoding(“UTF-8”);
    if(mb_strlen($text) <= $length ) return $text;
    $Foremost = mb_substr($text, 0, $length);
    $re = “<(/?)
   
(P|DIV|H1|H2|H3|H4|H5|H6|ADDRESS|PRE|TABLE|TR|TD|TH|INPUT|SELECT|TEXTAREA|OBJECT|A|UL|OL|LI|
   
BASE|META|LINK|HR|BR|PARAM|IMG|AREA|INPUT|SPAN)[^>]*(>?)”;
    $Single = “/BASE|META|LINK|HR|BR|PARAM|IMG|AREA|INPUT|BR/i”;
    
    $Stack = array(); $posStack = array();
    
    mb_ereg_search_init($Foremost, $re, ‘i’);
    
    while($pos = mb_ereg_search_pos()){
    $match = mb_ereg_search_getregs();
    /* [Child-matching Formulation]:
    
    $matche[1] : A “/” charactor indicating whether current
“<…>” Friction is
    Closing Part
    $matche[2] : Element Name.
    $matche[3] : Right > of a “<…>” Friction
    */
    if($match[1]==””){
    $Elem = $match[2];
    if(mb_eregi($Single, $Elem) && $match[3] !=””){
    continue;
    }