WebSVN – eFlore/Applications.cel – Diff – /trunk/jrest/bibliotheque/NameParser.php

 <?php
+// declare(encoding='UTF-8');
 /**
+ * Classe permettant de convertir une chaine d'un nom scientifique en un format standard.
+ *
+ * Source orignale :
  * Taxamatch-Webservice PHP v1.0.0
  * @author Michael Giddens
  * @link http://www.silverbiology.com
- */
+ *
+ *
- /* Adapation par David Delon Decembre 2010 : gestion sous espece
+ * @internal   Mininum PHP version : 5.2
- */
+ * @category   CEL
-/**
+ * @package    Services
+ * @subpackage Bibliothèques
- * Class NameParser
+ * @version    0.1
- * Used to convert a string to a standarized format.
+ * @author     Mathias CHOUET <mathias@tela-botanica.org>
+ * @author     David DELON <david@clapas.net>
+ * @author     Jean-Pascal MILCENT <jpm@tela-botanica.org>
+ * @author     Aurelien PERONNET <aurelien@tela-botanica.org>
+ * @license    GPL v3 <http://www.gnu.org/licenses/gpl.txt>
+ * @license    CECILL v2 <http://www.cecill.info/licences/Licence_CeCILL_V2-en.txt>
+ * @copyright  1999-2014 Tela Botanica <accueil@tela-botanica.org>
  */
 class NameParser {
 	/**
 	 * Whether to debug or nor
 	 * @var bool|integer
 	 */
-	public $debug_flag;
-	/**
-	 * Constructor
-	 */
-	public function __construct( ) {
 	public $debug_flag;
 	/**
 	 * Sets value to the method property
 	 * @param mixed $name class property name
 	 * This will reduce the string to only allow once space between characters
 	 * @param string $str : string to reduce space
 	 * @return string : string with only once space between characters
 	 */
-	private function reduce_spaces( $str ) {
+	private function reduce_spaces($str) {
-		$str = preg_replace("/ {2,}/", ' ', $str );
+		$str = preg_replace('/ {2,}/', ' ', $str );
 		$str = trim( $str );
 		return( $str );
+	}
 	/**
 	 * @param string $str : authority string
 	 * @param integer $upcase : convert to uppercase if $upcase = 1
 	 * @return string : parsed author string
 	 */
-	public function parse_auth( $str, $upcase=1 ) {
+	public function parse_auth($str, $upcase = 1) {
 		$this->debug['parse_auth'][] = "1";
 		$temp = $str = trim($str);
   		if ( ($str == NULL) || ($str == '') ) {
 			$temp = str_replace(' -', '-', $temp);
 			$this->debug['parse_auth'][] = "6 (temp:$temp)";
 			foreach( explode(' ', $temp) as $this_word ) {
 			foreach (explode(' ', $temp) as $this_word) {
 				//$this->debug['parse_auth'][] = "7 (this_word:$this_word)";
 				$elapsed_chars = '';
 				//	like '(%'
 				// Add back the word to the final translation
 				$elapsed_chars .= $this_word . ' ';
 				//$this->debug['parse_auth'][] = "7c (this_word:$this_word) (elapsed_chars:$elapsed_chars)";
-			}
+			}
-			$elapsed_chars = $this->reduce_spaces( str_replace(' )', ')', $elapsed_chars) );
 			$elapsed_chars = $this->reduce_spaces( str_replace(' )', ')', $elapsed_chars) );
 			return trim( $elapsed_chars ) ;
-		}
+		}
+	}
 	/**
+	 *
 	 * @param string $str : input string ( genus, genus+species, or genus+species+authority )
 	 * @return string : parsed string
 	 */
 	public function parse( $str = NULL ) {
 		unset($this->debug['parse']);
 		$temp = '';
 		$first_str_part = NULL;
 		$second_str_part = NULL;
 		$temp_genus = '';
 		$temp_species = '';
 			$temp = str_replace( $set, '&', $temp );
 			//$this->debug['parse'][] = "2b1 (temp:$temp)";
 			// remove any content in angle brackets (e.g. html tags - <i>, </i>, etc.)
-			$html_pattern = "(\<(/?[^\>]+)\>)";
+			$html_pattern = '(\<(/?[^\>]+)\>)';
 			//? This should not just handle html tags but all <*>
 			$temp = preg_replace( $html_pattern, '', $temp);
 			//$this->debug['parse'][] = "2b2 (temp:$temp)";
 			// if second term (only) is in round brackets, presume it is a subgenus or a comment and remove it
 			// examples: Barbatia (Mesocibota) bistrigata (Dunker, 1866) => Barbatia bistrigata (Dunker, 1866)
 			// Barbatia (?) bistrigata (Dunker, 1866) => Barbatia bistrigata (Dunker, 1866)
 			// (obviously this will not suit genus + author alone, where first part of authorname is in brackets,
 			// however this is very rare?? and in any case we are not supporting genus+authority in this version)
 			//if ( $temp like '% (%)%'
-			$temp = preg_replace( "/ \(\w*\W*\)/", '', $temp, 1 );
+			$temp = preg_replace( '/ \(\w*\W*\)/', '', $temp, 1 );
 			//? Not sure if this will catch if
 			//$this->debug['parse'][] = "2b3 (temp:$temp)";
 			// if second term (only) is in square brackets, presume it is a comment and remove it
 			// example: Aphis [?] ficus Theobald, [1918] => Aphis ficus Theobald, [1918]
 			//if ( $temp like '% [%]%'
-			$temp = preg_replace( "/ \[\w*\W*\]/", '', $temp, 1 );
+			$temp = preg_replace( '/ \[\w*\W*\]/', '', $temp, 1 );
 			//? Not sure if this will catch if
 			//$this->debug['parse'][] = "2b4 (temp:$temp)";
 			// drop indicators of questionable id's - presume all are lowercase for now (could extend as needed)
-			$temp = preg_replace( "/ cf /", " ", $temp );
+			$temp = preg_replace('/ cf /', ' ', $temp );
-			$temp = preg_replace( "/ cf\. /", " ", $temp );
+			$temp = preg_replace('/ cf\. /', ' ', $temp );
-			$temp = preg_replace( "/ near /", " ", $temp );
+			$temp = preg_replace('/ near /', ' ', $temp );
-			$temp = preg_replace( "/ aff\. /", " ", $temp );
+			$temp = preg_replace('/ aff\. /', ' ', $temp );
-			$temp = preg_replace( "/ sp\. /", " ", $temp );
+			$temp = preg_replace('/ sp\. /', ' ', $temp );
 			//$this->debug['parse'][] = "2b6 (temp:$temp)";
 			// now presume first element is genus, second (if present) is species, remainder
 			//   (if present) is authority
 			// look for genus name
-			$ar = explode( " ", $temp, 2);
+			$ar = explode(' ', $temp, 2);
 			if ( count( $ar ) ) {
 				$temp_genus = $ar[0];
 				$temp = @$ar[1];
 			} else {
+			}
 			//$this->debug['parse'][] = "2b7 (temp_genus:$temp_genus) (temp:$temp)";
 			// look for species epithet and authority
-			$ar = explode( " ", $temp, 2);
+			$ar = explode(' ', $temp, 2);
 			if ( count( $ar ) ) {
 				$temp_species = $ar[0];
 				$temp_authority = @$ar[1];
-                	$temp_infra=substr($temp_authority,$pos+strlen($infra));
+					$temp_infra=substr($temp_authority,$pos+strlen($infra));
-                    $temp_authority=substr($temp_authority,0,$pos);
+					$temp_authority=substr($temp_authority,0,$pos);
-                    $temp_infra=trim($temp_infra);
+					$temp_infra=trim($temp_infra);
-                    $temp_infra_type=$infra;
+					$temp_infra_type=$infra;
-                    // look for infra epithet and authority
+					// look for infra epithet and authority
-                    $ar = explode(" ", $temp_infra, 2);
+					$ar = explode(' ', $temp_infra, 2);
-                    if ( count( $ar ) ) {
+					if ( count( $ar ) ) {
-                    	$temp_infra = $ar[0];
+						$temp_infra = $ar[0];
-                        $temp_infra_authority = @$ar[1];
+						$temp_infra_authority = @$ar[1];
+					}
-                    break; // on s'arrete au premier trouve
+					break; // on s'arrete au premier trouve
-            	$temp_infra_authority=$this->parse_auth($temp_infra_authority);
+				$temp_infra_authority=$this->parse_auth($temp_infra_authority);
+			}
 			//$this->debug['parse'][] = "2b11 (temp_genus:$temp_genus) (temp_species:$temp_species) (temp_authority:$temp_authority) (temp_infra:$temp_infra) (temp_infra_authority:$temp_infra_authority) (temp:$temp)";
 			return array("genus"=>$temp_genus, "species"=>$temp_species, "authority"=>$temp_authority, "infra"=>$temp_infra, "infra_authority"=>$temp_infra_authority, "infra_type"=>$temp_infra_type);
+		}
-	} // End NameParser
-} // End Class
-?>
+	}
+}

Subversion Repositories eFlore/Applications.cel

(root)/trunk/jrest/bibliotheque/NameParser.php @ 3919 – Rev 2459 → 2462