Posted By

Cory on 07/15/08

Tagged

Versions (?)

Last Edited at 07/15/08 10:38am

Statistics

Viewed 683 times

Favorited by 3 user(s)

Related snippets

Approximate / Fuzzy search base.

/ Published in: PHP

This is a simple base for an approximate search application. You can currently use this to do search's but it, is not very sophisticated, right now anything that is as difference in characters base on the threshold will show up in the result, so with a threshold of 1 "the" would return, "he", "she", "thee", etc. But this is more made for a base for extending with your own capabilities.

Highlighted TextExpand

<?php
	class FuzzySearch {
		public $string;
		public $search;
		
		public function __construct($string = null) {
			if(!empty($string)) {
				self::SetString($string);
			}
		}
		
		public function SetString($string) {
			if(is_string($string)) {
				$this->string = $string;
			}
		}
		
		public function SetSearch($search) {
			if(is_string($search)) {
				$this->search = $search;
			}
		}
		
		public function PreformSearch($search, $string = null, $threshold = 1, $caseSensitive = false) {
			if(empty($search) && !empty($this->search)) { $search = $this->search; }
			if(empty($string) && !empty($this->string)) { $string = $this->string; }
			$matches = array();
			
			if(isset($string) && strlen($string) > 0) {
				$words = explode(" ", $string);
				
				foreach($words as $word) {
					$stripedWord = self::StripFormatting($word);
					
					if(self::CompareStrings($search, $stripedWord, $caseSensitive) <= $threshold) {
						$matches[] = $stripedWord;
					}
				}
			}
			return $matches;
		}
		
		public function CompareStrings($str1, $str2, $caseInsensitive = false) {
			$threshold = 0;
			
			if($caseInsensitive) {
				$str1 = strtolower($str1);
				$str2 = strtolower($str2);
			}
			
			if(strlen($str1) != strlen($str2)) {
				if(strlen($str1) > strlen($str2)) {
					$threshold = strlen($str1) - strlen($str2);
				}
				else if(strlen($str2) > strlen($str1)) {
					$threshold = strlen($str2) - strlen($str1);
				}
			}
			
			for($i = 0; $i < strlen($str1); $i++) {
				if($i <= strlen($str2) - 1) {
					if($str1{$i} != $str2{$i}) {
						$threshold++;
					}
				}
			}
			return $threshold;
		}
		
		public function StripFormatting($str) {
			$formatting = array( ".", ",", ";", ":", "|", "[", "]", "{", "}", "(", ")", "=", "+",
								"!", "@", "#", "$", "%", "^", "&", "*", "/", "\\", "<", ">", "?");
			
			$str = str_replace($formatting, "", $str);
			$str = trim($str);
			return $str;
		}
	}
?>

Report this snippet Tweet