Correção nas funções de busca para corrigir problemas com acentuação e projeção

Edmar Moretti
1 parent 9c3ce7da
Showing 1 changed file with 156 additions and 57 deletions Show diff stats
classesphp/classe_atributos.php
@@ -705,28 +705,31 @@ class Atributos
 			if ($filtro != ""){
 				$l->setfilter("");
 			}
-			$b = "&Aacute;&Atilde;&Otilde;&Oacute;&Ocirc;&aacute;&atilde;&acirc;&agrave;&oacute;&otilde;&ocirc;&ograve;&uacute;&ucirc;&iacute;&ecirc;&eacute;&ccedil;";
-			$trocas = "AAOOOaaaaoooouuieecAAOOOaaaaoooouuieecAAOOOaaaaoooouuieec";
-			$buscas = b.(html_entity_decode($b,ENT_NOQUOTES,'UTF8')).(html_entity_decode($b,ENT_NOQUOTES,'ISO8859-1'));
 			$sopen = $l->open();
 			if($sopen == MS_FAILURE){
 				return "erro";
 			}
+			$ret = $this->mapa->extent;
+			/*
 			$prjMapa = $this->mapa->getProjection();
 			$prjTema = $l->getProjection();
-			$ret = $this->mapa->extent;
-			if (($prjTema != "") && ($prjMapa != $prjTema))	{
+			if ($prjTema != ""){
 				$projInObj = ms_newprojectionobj($prjTema);
 				$projOutObj = ms_newprojectionobj($prjMapa);
+			}
+			*/
+			/*
+			if (($prjTema != "") && ($prjMapa != $prjTema))	{
 				$status = $ret->project($projInObj, $projOutObj);
 				if($status !== MS_SUCCESS){
 					$ret = $this->mapa->extent;
 				}
 			}
-
+			*/
 			$fr = array();
 			if (@$l->queryByrect($ret) == MS_SUCCESS){
 				$res_count = $l->getNumresults();
+				$palavra = $this->remove_accents(strtolower($palavra));
 				for ($i = 0; $i < $res_count; ++$i)	{
 					$valitem = array();
 					if($this->v == 6){
@@ -742,8 +745,10 @@ class Atributos
 					$r = array();
 					foreach ($items as $item){
 						$v = trim($shape->values[$item]);
+						$nv = $this->remove_accents(strtolower($v));
+						//echo $v." - ".$nv."<br>";
 						if ($tipo == "exata"){
-							if ($v == $palavra || (strtr($v,$buscas,$trocas) == strtr($palavra,$buscas,$trocas)))
+							if ($nv == $palavra)
 							{
 								if($convC == true)
 								{
@@ -754,7 +759,7 @@ class Atributos
 							}
 						}
 						else{
-							if (strtolower($v) == strtolower($palavra) || (stristr(strtr(strtolower($v),$buscas,$trocas),strtr(strtolower($palavra),$buscas,$trocas)))){
+							if (stristr($nv,$palavra)){
 								if($convC == true){
 									$v = $this->converte($v);
 								}
@@ -765,9 +770,11 @@ class Atributos
 					}
 					if ($encontrado == "sim"){
 						$ret = $this->extensaoShape($shape,$l);
+						/*
 						if (($prjTema != "") && ($prjMapa != $prjTema)){
 							$ret->project($projInObj, $projOutObj);
 						}
+						*/
 						$novoreg["box"] = $ret;
 						$novoreg["valores"] = $r;
 						$encontrado = "nao";
@@ -776,55 +783,6 @@ class Atributos
 				}
 				$resultado[] = array("tema"=>$tema,"resultado"=>$fr);
 			}
-			/*
-			 $teste = $l->whichShapes($ret);
-			if($teste){
-			$fr = array();
-			while ($shape = $l->nextShape())
-			{
-			$novoreg = array();
-			$r = array();
-			foreach ($items as $item)
-			{
-			$v = trim($shape->values[$item]);
-			echo $v;
-			if ($tipo == "exata")
-			{
-			if (strtr($v,$buscas,$trocas) == strtr($palavra,$buscas,$trocas))
-			{
-			if($convC == true)
-			{$v = $this->converte($v);}
-			$r[] = array("item" => $item,"valor" => $v);
-			$encontrado = "sim";
-			}
-			}
-			else
-			{
-
-			if (stristr(strtr($v,$buscas,$trocas),strtr($palavra,$buscas,$trocas)))
-			{
-			if($convC == true)
-			{$v = $this->converte($v);}
-			$r[] = array("item" => $item,"valor" => $v);
-			$encontrado = "sim";
-			}
-			}
-			}
-			if ($encontrado == "sim")
-			{
-			$ret = $this->extensaoShape($shape,$l);
-			if (($prjTema != "") && ($prjMapa != $prjTema))
-			{$ret->project($projInObj, $projOutObj);}
-			$novoreg["box"] = $ret;
-			$novoreg["valores"] = $r;
-			$encontrado = "nao";
-			$fr[] = $novoreg;
-			}
-			}
-			$resultado[] = array("tema"=>$tema,"resultado"=>$fr);
-			$l->close();
-			}
-			*/
 		}
 		return($resultado);
 	}
@@ -2474,5 +2432,146 @@ class Atributos
 		}
 		return $texto;
 	}
+	function remove_accents($string) {
+		if (!preg_match('/[\x80-\xff]/', $string))
+			return $string;
+		if ($this->seems_utf8($string)) {
+			$chars = array(
+					// Decompositions for Latin-1 Supplement
+					chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
+					chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
+					chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
+					chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
+					chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
+					chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
+					chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
+					chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
+					chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
+					chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
+					chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
+					chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
+					chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
+					chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
+					chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
+					chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
+					chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
+					chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
+					chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
+					chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
+					chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
+					chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
+					chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
+					chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
+					chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
+					chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
+					chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
+					chr(195).chr(191) => 'y',
+					// Decompositions for Latin Extended-A
+					chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
+					chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
+					chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
+					chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
+					chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
+					chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
+					chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
+					chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
+					chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
+					chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
+					chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
+					chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
+					chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
+					chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
+					chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
+					chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
+					chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
+					chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
+					chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
+					chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
+					chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
+					chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
+					chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
+					chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
+					chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
+					chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
+					chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
+					chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
+					chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
+					chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
+					chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
+					chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
+					chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
+					chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
+					chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
+					chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
+					chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
+					chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
+					chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
+					chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
+					chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
+					chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
+					chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
+					chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
+					chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
+					chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
+					chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
+					chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
+					chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
+					chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
+					chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
+					chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
+					chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
+					chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
+					chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
+					chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
+					chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
+					chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
+					chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
+					chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
+					chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
+					chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
+					chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
+					chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
+					// Euro Sign
+					chr(226).chr(130).chr(172) => 'E',
+					// GBP (Pound) Sign
+					chr(194).chr(163) => '');
+			$string = strtr($string, $chars);
+		} else {
+			// Assume ISO-8859-1 if not UTF-8
+			$chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
+			.chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
+			.chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
+			.chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
+			.chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
+			.chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
+			.chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
+			.chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
+			.chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
+			.chr(252).chr(253).chr(255);
+			$chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
+			$string = strtr($string, $chars['in'], $chars['out']);
+			$double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
+			$double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
+			$string = str_replace($double_chars['in'], $double_chars['out'], $string);
+		}
+		return $string;
+	}
+	function seems_utf8($Str) { # by bmorel at ssi dot fr
+		$length = strlen($Str);
+		for ($i = 0; $i < $length; $i++) {
+			if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb
+			elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n = 1; # 110bbbbb
+			elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n = 2; # 1110bbbb
+			elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n = 3; # 11110bbb
+			elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n = 4; # 111110bb
+			elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n = 5; # 1111110b
+			else return false; # Does not match any model
+			for ($j = 0; $j < $n; $j++) { # n bytes matching 10bbbbbb follow ?
+				if ((++$i == $length) || ((ord($Str[$i]) & 0xC0) != 0x80))
+				return false;
+			}
+		}
+		return true;
+	}
 }
 ?>
 \ No newline at end of file
	@@ -705,28 +705,31 @@ class Atributos		@@ -705,28 +705,31 @@ class Atributos
705	if ($filtro != ""){	705	if ($filtro != ""){
706	$l->setfilter("");	706	$l->setfilter("");
707	}	707	}
708	- $b = "ÁÃÕÓÔáãâàóõôòúûíêéç";
709	- $trocas = "AAOOOaaaaoooouuieecAAOOOaaaaoooouuieecAAOOOaaaaoooouuieec";
710	- $buscas = b.(html_entity_decode($b,ENT_NOQUOTES,'UTF8')).(html_entity_decode($b,ENT_NOQUOTES,'ISO8859-1'));
711	$sopen = $l->open();	708	$sopen = $l->open();
712	if($sopen == MS_FAILURE){	709	if($sopen == MS_FAILURE){
713	return "erro";	710	return "erro";
714	}	711	}
		712	+ $ret = $this->mapa->extent;
		713	+ /*
715	$prjMapa = $this->mapa->getProjection();	714	$prjMapa = $this->mapa->getProjection();
716	$prjTema = $l->getProjection();	715	$prjTema = $l->getProjection();
717	- $ret = $this->mapa->extent;
718	- if (($prjTema != "") && ($prjMapa != $prjTema)) {	716	+ if ($prjTema != ""){
719	$projInObj = ms_newprojectionobj($prjTema);	717	$projInObj = ms_newprojectionobj($prjTema);
720	$projOutObj = ms_newprojectionobj($prjMapa);	718	$projOutObj = ms_newprojectionobj($prjMapa);
		719	+ }
		720	+ */
		721	+ /*
		722	+ if (($prjTema != "") && ($prjMapa != $prjTema)) {
721	$status = $ret->project($projInObj, $projOutObj);	723	$status = $ret->project($projInObj, $projOutObj);
722	if($status !== MS_SUCCESS){	724	if($status !== MS_SUCCESS){
723	$ret = $this->mapa->extent;	725	$ret = $this->mapa->extent;
724	}	726	}
725	}	727	}
726	-	728	+ */
727	$fr = array();	729	$fr = array();
728	if (@$l->queryByrect($ret) == MS_SUCCESS){	730	if (@$l->queryByrect($ret) == MS_SUCCESS){
729	$res_count = $l->getNumresults();	731	$res_count = $l->getNumresults();
		732	+ $palavra = $this->remove_accents(strtolower($palavra));
730	for ($i = 0; $i < $res_count; ++$i) {	733	for ($i = 0; $i < $res_count; ++$i) {
731	$valitem = array();	734	$valitem = array();
732	if($this->v == 6){	735	if($this->v == 6){
	@@ -742,8 +745,10 @@ class Atributos		@@ -742,8 +745,10 @@ class Atributos
742	$r = array();	745	$r = array();
743	foreach ($items as $item){	746	foreach ($items as $item){
744	$v = trim($shape->values[$item]);	747	$v = trim($shape->values[$item]);
		748	+ $nv = $this->remove_accents(strtolower($v));
		749	+ //echo $v." - ".$nv."<br>";
745	if ($tipo == "exata"){	750	if ($tipo == "exata"){
746	- if ($v == $palavra \|\| (strtr($v,$buscas,$trocas) == strtr($palavra,$buscas,$trocas)))	751	+ if ($nv == $palavra)
747	{	752	{
748	if($convC == true)	753	if($convC == true)
749	{	754	{
	@@ -754,7 +759,7 @@ class Atributos		@@ -754,7 +759,7 @@ class Atributos
754	}	759	}
755	}	760	}
756	else{	761	else{
757	- if (strtolower($v) == strtolower($palavra) \|\| (stristr(strtr(strtolower($v),$buscas,$trocas),strtr(strtolower($palavra),$buscas,$trocas)))){	762	+ if (stristr($nv,$palavra)){
758	if($convC == true){	763	if($convC == true){
759	$v = $this->converte($v);	764	$v = $this->converte($v);
760	}	765	}
	@@ -765,9 +770,11 @@ class Atributos		@@ -765,9 +770,11 @@ class Atributos
765	}	770	}
766	if ($encontrado == "sim"){	771	if ($encontrado == "sim"){
767	$ret = $this->extensaoShape($shape,$l);	772	$ret = $this->extensaoShape($shape,$l);
		773	+ /*
768	if (($prjTema != "") && ($prjMapa != $prjTema)){	774	if (($prjTema != "") && ($prjMapa != $prjTema)){
769	$ret->project($projInObj, $projOutObj);	775	$ret->project($projInObj, $projOutObj);
770	}	776	}
		777	+ */
771	$novoreg["box"] = $ret;	778	$novoreg["box"] = $ret;
772	$novoreg["valores"] = $r;	779	$novoreg["valores"] = $r;
773	$encontrado = "nao";	780	$encontrado = "nao";
	@@ -776,55 +783,6 @@ class Atributos		@@ -776,55 +783,6 @@ class Atributos
776	}	783	}
777	$resultado[] = array("tema"=>$tema,"resultado"=>$fr);	784	$resultado[] = array("tema"=>$tema,"resultado"=>$fr);
778	}	785	}
779	- /*
780	- $teste = $l->whichShapes($ret);
781	- if($teste){
782	- $fr = array();
783	- while ($shape = $l->nextShape())
784	- {
785	- $novoreg = array();
786	- $r = array();
787	- foreach ($items as $item)
788	- {
789	- $v = trim($shape->values[$item]);
790	- echo $v;
791	- if ($tipo == "exata")
792	- {
793	- if (strtr($v,$buscas,$trocas) == strtr($palavra,$buscas,$trocas))
794	- {
795	- if($convC == true)
796	- {$v = $this->converte($v);}
797	- $r[] = array("item" => $item,"valor" => $v);
798	- $encontrado = "sim";
799	- }
800	- }
801	- else
802	- {
803	-
804	- if (stristr(strtr($v,$buscas,$trocas),strtr($palavra,$buscas,$trocas)))
805	- {
806	- if($convC == true)
807	- {$v = $this->converte($v);}
808	- $r[] = array("item" => $item,"valor" => $v);
809	- $encontrado = "sim";
810	- }
811	- }
812	- }
813	- if ($encontrado == "sim")
814	- {
815	- $ret = $this->extensaoShape($shape,$l);
816	- if (($prjTema != "") && ($prjMapa != $prjTema))
817	- {$ret->project($projInObj, $projOutObj);}
818	- $novoreg["box"] = $ret;
819	- $novoreg["valores"] = $r;
820	- $encontrado = "nao";
821	- $fr[] = $novoreg;
822	- }
823	- }
824	- $resultado[] = array("tema"=>$tema,"resultado"=>$fr);
825	- $l->close();
826	- }
827	- */
828	}	786	}
829	return($resultado);	787	return($resultado);
830	}	788	}
	@@ -2474,5 +2432,146 @@ class Atributos		@@ -2474,5 +2432,146 @@ class Atributos
2474	}	2432	}
2475	return $texto;	2433	return $texto;
2476	}	2434	}
		2435	+ function remove_accents($string) {
		2436	+ if (!preg_match('/[\x80-\xff]/', $string))
		2437	+ return $string;
		2438	+ if ($this->seems_utf8($string)) {
		2439	+ $chars = array(
		2440	+ // Decompositions for Latin-1 Supplement
		2441	+ chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
		2442	+ chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
		2443	+ chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
		2444	+ chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
		2445	+ chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
		2446	+ chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
		2447	+ chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
		2448	+ chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
		2449	+ chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
		2450	+ chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
		2451	+ chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
		2452	+ chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
		2453	+ chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
		2454	+ chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
		2455	+ chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
		2456	+ chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
		2457	+ chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
		2458	+ chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
		2459	+ chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
		2460	+ chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
		2461	+ chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
		2462	+ chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
		2463	+ chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
		2464	+ chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
		2465	+ chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
		2466	+ chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
		2467	+ chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
		2468	+ chr(195).chr(191) => 'y',
		2469	+ // Decompositions for Latin Extended-A
		2470	+ chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
		2471	+ chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
		2472	+ chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
		2473	+ chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
		2474	+ chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
		2475	+ chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
		2476	+ chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
		2477	+ chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
		2478	+ chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
		2479	+ chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
		2480	+ chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
		2481	+ chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
		2482	+ chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
		2483	+ chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
		2484	+ chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
		2485	+ chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
		2486	+ chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
		2487	+ chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
		2488	+ chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
		2489	+ chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
		2490	+ chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
		2491	+ chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
		2492	+ chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
		2493	+ chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
		2494	+ chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
		2495	+ chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
		2496	+ chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
		2497	+ chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
		2498	+ chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
		2499	+ chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
		2500	+ chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
		2501	+ chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
		2502	+ chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
		2503	+ chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
		2504	+ chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
		2505	+ chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
		2506	+ chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
		2507	+ chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
		2508	+ chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
		2509	+ chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
		2510	+ chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
		2511	+ chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
		2512	+ chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
		2513	+ chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
		2514	+ chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
		2515	+ chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
		2516	+ chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
		2517	+ chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
		2518	+ chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
		2519	+ chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
		2520	+ chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
		2521	+ chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
		2522	+ chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
		2523	+ chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
		2524	+ chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
		2525	+ chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
		2526	+ chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
		2527	+ chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
		2528	+ chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
		2529	+ chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
		2530	+ chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
		2531	+ chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
		2532	+ chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
		2533	+ chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
		2534	+ // Euro Sign
		2535	+ chr(226).chr(130).chr(172) => 'E',
		2536	+ // GBP (Pound) Sign
		2537	+ chr(194).chr(163) => '');
		2538	+ $string = strtr($string, $chars);
		2539	+ } else {
		2540	+ // Assume ISO-8859-1 if not UTF-8
		2541	+ $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
		2542	+ .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
		2543	+ .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
		2544	+ .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
		2545	+ .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
		2546	+ .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
		2547	+ .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
		2548	+ .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
		2549	+ .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
		2550	+ .chr(252).chr(253).chr(255);
		2551	+ $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
		2552	+ $string = strtr($string, $chars['in'], $chars['out']);
		2553	+ $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
		2554	+ $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
		2555	+ $string = str_replace($double_chars['in'], $double_chars['out'], $string);
		2556	+ }
		2557	+ return $string;
		2558	+ }
		2559	+ function seems_utf8($Str) { # by bmorel at ssi dot fr
		2560	+ $length = strlen($Str);
		2561	+ for ($i = 0; $i < $length; $i++) {
		2562	+ if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb
		2563	+ elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n = 1; # 110bbbbb
		2564	+ elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n = 2; # 1110bbbb
		2565	+ elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n = 3; # 11110bbb
		2566	+ elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n = 4; # 111110bb
		2567	+ elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n = 5; # 1111110b
		2568	+ else return false; # Does not match any model
		2569	+ for ($j = 0; $j < $n; $j++) { # n bytes matching 10bbbbbb follow ?
		2570	+ if ((++$i == $length) \|\| ((ord($Str[$i]) & 0xC0) != 0x80))
		2571	+ return false;
		2572	+ }
		2573	+ }
		2574	+ return true;
		2575	+ }
2477	}	2576	}
2478	?>	2577	?>
2479	\ No newline at end of file	2578	\ No newline at end of file