Name Parsing in PHP

parse_name.php

<?php

/**
 * This "Parse" class contains one method, "parseFullName", 
 * which takes a full name as a single string (including 
 * titles and name suffixes) and parses it into a separated
 * name array for a CakePHP project of mine which uses a
 * "Member" model.
 *
 * Please feel free to critique! If you use this in your work,
 * I'd love it if you would reference me in your code and any
 * write-ups you produce about the code which uses this or the
 * general algorithm behind it.
 *
 * Thanks,
 * Parker Moore
 * https://github.com/parkr
 */
class Parse {
	
	public $namePrefixes = array(
		"Ms", "Miss", "Mrs", 
		"Mr", "Master",
		"Rev", "Reverend", "Rt Rev", "Right Reverend",
		"Fr", "Father",
		"Dr", "Doctor",
		"Atty", "Attorney",
		"Prof", "Professor",
		"Hon", "Honorable",
		"Pres", "President",
		"Gov", "Governor",
		"Coach",
		"Ofc", "Officer",
		"Msgr", "Monsignor",
		"Sr", "Sister",
		"Br", "Brother",
		"Supt", "Superintendent",
		"Rep", "Representative",
		"Sen", "Senator",
		"Amb", "Ambassador",
		"Treas", "Treasurer",
		"Sec", "Secretary",
		"Pvt", "Private",
		"Cpl", "Corporal",
		"Sgt", "Sargent",
		"Adm", "Administrative",
		"Maj", "Major",
		"Capt", "Captain",
		"Cmdr", "Commander",
		"Lt", "Lieutenant",
		"Lt Col", "Lieutenant Colonel",
		"Col", "Colonel",
		"Gen", "General"
	);

	public $nameSuffixes = array(
		// Pedigrees
		"jr.", "jr", "junior", "Jr.", "Jr", "Junior",
		"sr.", "sr", "senior", "Sr.", "Sr", "Senior",
		"I", "II", "III", "IV", "V", "VI", "VII", "VIII", "IX", "X",
		// Professional suffixes
		"A.B", "B.A.", "B.F.A.", "B.Tech.", "LL.B.", "B.Sc.", "B.Eng.",
		"AB", "BA", "BFA", "BTech", "LLB", "BSc", "BEng",
		"M.A.", "M.F.A.", "LL.M.", "M.L.A.", "M.B.A.", "M.Sc.", "M.Eng.",
		"MA", "MFA", "LLM", "MLA", "MBA", "MSc", "MEng",
		"J.D.", "M.D.", "D.O.", "D.C.", "Ph.D.", "D.Phil.", "LL.D", "Eng.D.",
		"JD", "MD", "DO", "DC", "PhD", "DPhil", "LLD", "EngD",
		"esq", "Esq", "Esq.", "esq.", "esquire", "Esquire"
	);

	public function parseFullName($name, $member){
		// clean up name
		$name = str_replace(".", "", $name);	
		
		// split into pieces
		$pieces = explode(" ", $name);
		
		// parse based on # of pieces in name
		switch(count($pieces)){
			case 5:
				// Mr John William Doe (Jr.|Sr.|III|Esq)
				if(in_array($pieces[4], $this->nameSuffixes)){
					if(in_array($pieces[0], $this->namePrefixes)){
						$member["Member"]['title'] = $pieces[0];
						$member["Member"]['first_name'] = $pieces[1];
						$member["Member"]['middle'] = $pieces[2];
						$member["Member"]['last_name'] = $pieces[3];
						$member["Member"]['suffix'] = $pieces[4];
					}else{
						$member["Member"]['first_name'] = $pieces[0];
						$member["Member"]['middle'] = $pieces[1];
						$member["Member"]['last_name'] = $pieces[2]." ".$pieces[3];
						$member["Member"]['suffix'] = $pieces[4];
					}
				}else{
					if(in_array($pieces[0], $this->namePrefixes)){
						$member["Member"]['title'] = $pieces[0];
						$member["Member"]['first_name'] = $pieces[1];
						$member["Member"]['middle'] = $pieces[2];
						$member["Member"]['last_name'] = $pieces[3]." ".$pieces[4];
					}else{
						$member["Member"]['first_name'] = $pieces[0];
						$member["Member"]['middle'] = $pieces[1]." ".$pieces[2];
						$member["Member"]['last_name'] = $pieces[3]." ".$pieces[4];
					}	
				}
				return $member;
			case 4:
				// Mr John William Doe
				// John William Henry Doe
				// Elí Arroyo López (two last names)
				// John William Doe (Jr.|Sr.|III|Esq)
				if(in_array($pieces[3], $this->nameSuffixes)){
					// second case
					// John William Doe (Jr.|Sr.|III|Esq)
					$member["Member"]['first_name'] = $pieces[0];
					$member["Member"]['middle'] = $pieces[1];
					$member["Member"]['last_name'] = $pieces[2];
					$member["Member"]['suffix'] = $pieces[3];
				}else{
					if(in_array($pieces[0], $this->namePrefixes)){
						$member["Member"]['title'] = $pieces[0];
						$member["Member"]['first_name'] = $pieces[1];
						$member["Member"]['middle'] = $pieces[2];
						$member["Member"]['last_name'] = $pieces[3];
					}else{
						// Two last names or two middle names! No way to tell.
						$member["Member"]['last_name'] = $pieces[3];
						$member["Member"]['first_name'] = implode(" ", array_slice($pieces, 0, 3));
					}
				}
				return $member;
			case 3:
				// John William Doe
				// Mr John Doe
				// John Doe[,] (Jr.|Sr.|III|Esq)
				if(in_array($pieces[2], $this->nameSuffixes)){
					$member["Member"]['first_name'] = $pieces[0];
					$member["Member"]['last_name'] = $pieces[1];
					$member["Member"]['suffix'] = $pieces[2];
				}else{
					if(in_array($pieces[0], $this->namePrefixes)){
						$member["Member"]['title'] = $pieces[0];
						$member["Member"]['first_name'] = $pieces[1];
						$member["Member"]['last_name'] = $pieces[2];
					}else{
						// Two last names or two middle names! No way to tell.
						$member["Member"]['first_name'] = $pieces[0];
						$member["Member"]['middle'] = $pieces[1];
						$member["Member"]['last_name'] = $pieces[2];
					}
				}
				return $member;
			case 2:
				// John Doe
				$member["Member"]['first_name'] = $pieces[0];
				$member["Member"]['last_name'] = $pieces[1];
				return $member;
		}
	}
}

?>