Ignore small words

Hello guys, is there any way of ignoring words with less than 4 characters in a string.?

Thanks

 

What do you mean ignore words that are less than 4 characters long? You want to remove them from the string? You could make a function that splits the string based on spaces, loops through the array and removes any that are less than 4. . .

A quick function I came up with:

<?
function removeSmallWords($baseString){
	$toReturn = "";
	$wordArray = spliti(" ", $baseString);
	foreach ($wordArray as $word) {
		if(strlen($word) >= 5){
			$toReturn .= $word . " ";
		}
	}
	return $toReturn;
}

$subjectString = "Hello There, this is a function test string";
echo removeSmallWords($subjectString);

// Outputs "Hello There, function string "

?>

PHP:

Hope that helps =]
~Todd

 

/**
get all thehtml tags regex
*/
function get_tags( $tag, $xml ) {
   $tag = preg_quote($tag);
   $matches[]="1";
   $matches[]="2";
   $regex = "/<\/?\w+((\s+(\w|\w[\w-]*\w)(\s*=\s*(?:\”.*?\”|’.*?’|[^'\">\s]+))?)+\s*|\s*)\/?>/i";
   $regex = "/<\/?\w+((\s+\w+(\s*=\s*(?:\".*?\"|'.*?'|[^'\">\s]+))?)+\s*|\s*)\/?>/i";
 	preg_match_all($regex,
                    $xml,
                    $matches
                    );

   return $matches;
 }


function splitHtmlTextOnlyProc($s, &$curr, &$nxt, $tag){
	$t=1;

	global $ll;
	$orig = $s;
	$str = $s;

	if(($curr - $nxt) == 0)return;

	$words = preg_split("/[\s,]+/", $str);
	$doneWords["aa"]=1;

	foreach($words as $k ){
		$kLower = strtolower($k);
		if(trim($k)=='')continue;
		if(isset($doneWords[$kLower ]))continue;
		$doneWords[$kLower ]=1;
		$k1 = getLink($k);
		$k1len = strlen($k1);
		$klen = strlen($k);
		if($k1len != $klen){

			$count = 0;
			$kq = preg_quote($k);
			$kt = "zT1TATAzy";
			$kt1 = preg_quote($kt);
			//$str =  preg_replace ( "/\b" . $kq . "\b/i", $k1 , $str, -1, $count);
			$s1 =  preg_replace ( "/\b" . $kq . "\b/i", $kt , $str, -1, $count);

			log2("splitadd1 tag $tag nxt $nxt count  $count len k " . $klen  . " len k1 "  . $k1len . " k $k kq $kq k1\n{$k1}\n---\norig \n{$orig}\n---\n s1\n{$s1}\n---\n\n str \n{$str}\n\n---\n ");

			//$count = 0;
			//$str =  preg_replace ( "/\b" . $kt . "\b/i", $k1 , $s1, -1, $count);
			$str = str_replace($kt, $k1, $s1);

			//$str = str_replace($k, $k1, $str, $count);
			//$str =  preg_replace ( "/" . $k . "/", $k1 , $str, -1, $count);


			$lNxt= $nxt ;
			$nxt += ($k1len  - $klen ) * $count;
			log2("splitadd tag $tag lNxt $lNxt nxt $nxt  count  $count len k " . $klen  . " len k1 "  . $k1len . " k $k kq $kq k1\n{$k1}\n---\ns1 \n{$s1} \n---\n str\n{$str}\n---\n\n ");
			//log2("splitadd lNxt $lNxt nxt $nxt count $count k \n$k\n k1 \n$k1\n\n");
		}

	}

	return $str;

}

/** user
*/

function hvisit( $html, $tags ) {

	 $ll="\n";
	 global $spl;
	 $nogos = array("<html", "<head", "<script", "<a", "<meta", "<style", "</head", "</style", "<title", "</title>", "<base", "<iframe");

	 //log2 ("Tags \n ");
	 //print_r($tags[0]);

	 $i = 0;
	 foreach($tags[0] as $tag){
		 $tags[0][$i] = strtolower($tags[0][$i]);
		 // "\n<!-- $i $tag \n" . $tags[0][$i] . "-->" ;
		 $i++;
	 }



	 $i = -1;
	 $loc1 = 0;
	 $loc2 = 0;
	 $oldLoc1= $loc1;
	 $ln1 = count($tags[0]);
	 $ln1_1 = $ln1 - 1;
	 $ahref = false;
	 foreach($tags[0] as $tag){
		$i++;

		$ln_tag = + strlen($tag);
		log2("iterate tag $tag loc1 $loc1 ln_tag  $ln_tag ");
		$loc1 = stripos($html, $tag, $loc1) + $ln_tag;
		log2("newLoc1 A loc1 $loc1 ");

		$aa1 = stripos($tag, "</a>");
		if($aa1 ===  false || $aa1 == NULL)$aa1 = stripos($tag, "</a ");
		$tag0 = str_replace(' ', '', $tag);
		//log2(" tag0 $tag0");
		if(($aa1 !== false && $aa1 != null) || $tag0 == '</a>'){
			//closing a tag
			$ahref = false;
			log2("closing a tag 3439");
		}
		else{
			if(!$ahref)$aa1 = stripos($tag, '<a');
		}
		if($ahref || ($aa1 !==  false && $aa1 !== NULL)){
			$ahref = true;

			log2("c1a href $tag nogo2 $nogo r $r loc1  $loc1 $ll");
			continue;
		}

		foreach($nogos as $nogo){
			$r = stripos($tag, $nogo);

			if($r !== false && $r !== NULL){
				log2("c1 $tag nogo $nogo r $r $ll");

				//$loc1 += $ln_tag;
				log2("newA loc1 $loc1 +ln ");
				$loc2 = $loc1;
				$oldLoc1= $loc1;
				break;

			}
		}
		if($r !== false && $r !== NULL){

			log2("c1a $tag nogo2 $nogo r $r loc1  $loc1 $ll");
			continue;
		}


		log2 (" proc3 c2 $tag \nloc1 $loc1 next |" . $tags[0][$i + 1] . "| i $i ln1 $ln1 \n");
		if($loc1===false){
			$loc1 = stripos($html, $tag, $oldLoc1) + $ln_tag;
			log2 ("<!-- unex err fileNoLog4 $fileNoLog4  -->\n");
			log2("newLoc1 B er loc1 $loc1 ");
		}
		if($loc1===false){
			log2 ("<!-- unex err 2 fileNoLog4 $fileNoLog4  -->\n");
			$loc1 =$oldLoc1;
			log2("newLoc1 C er loc1 $loc1 fileNoLog4 $fileNoLog4  ");
		}

		global $fileNoLog4;

		if($i < $ln1_1 && $tags[0][$i + 1] != ''){
			log2 ("<!-- search end " . $tags[0][$i + 1] . "\n");
			$loc2 = stripos($html, $tags[0][$i + 1], $loc1-1);
			if($loc2=== false){
				$loc2 = stripos($html, $tags[0][$i + 1], $oldLoc1);
				log2 ("<!-- unex err 3 fileNoLog4 $fileNoLog4 -->\n");
			}
			if($loc2=== false){
				$loc2 = strlen($html);
				log2 ("<!-- unex err 4 fileNoLog4 $fileNoLog4 -->\n");
			}
		}else{
			$loc2 = strlen($html);
		}
		log2 ("\n loc2 match $loc2 before loc1 $loc1 $ll");
		$ln2 = $loc2 - $loc1;

		$start= 0;
		$s3 = substr($html, $loc1, $ln2);
		$lns3 = strlen($s3);
		$ln3a = $lns3 ;
		log4("before loc1 $loc1 loc2 $loc2 ln2 $ln2 \n\n{$html}");
		log4("before sending loc1 $loc1 ln2 $ln2 \n{$tag}\n\n{$s3}");
		$s = splitHtmlTextOnlyProc($s3, $start , $lns3, $tag);
		if($lns3 != $ln3a ){
			$html = substr($html, 0, $loc1) . $s . substr($html, $loc2);

			//$loc1 = $loc1 + ln2 - $ln3a;
			//$loc1 += strlen($s) - $lns3;
			$loc1 = $loc1 +  $lns3;
			log2 ("split done with replce after loc1 $loc1 lns3 $lns3  $ll");
			log4("after loc $loc1 loc2 $loc2 ln2 $ln2 lns3 $lns3 html \n\n{$html}");
			log4("after loc $loc1 loc2 $loc2 ln2 $ln2 lns3 $lns3 s \n\n{$s}");
		}else{
			log2 ("split done no replces $ll");

		}
		$oldLoc1= $loc1;


	 }
	 return $html;

}

PHP:

 

Thank you all very mcuh guys!