splitnames.py

import re
def split_names(s,exceptions=['Gil', 'Lew', 'Liz', 'Paz', 'Rey', 'Rio', 'Roa', 'Rua', 'Sus', 'Zea'],
                nacionality='Colombiana'):
    """
    Extract the parts of the full name `s` in the format ([] → optional):
    
    [SMALL_CONECTORS] FIRST_LAST_NAME [SMALL_CONECTORS] [SECOND_LAST_NAME] NAMES
    
    If len(s) == 3 → Not Ibero-America name is asked
    
    Add short last names to `exceptions` list if necessary
    
    Works with:
    ----
        s='DANIEL ANDRES LA ROTTA FORERO'
        s='MARIA DEL CONSUELO MONTES RAMIREZ'
        s='RICARDO DE LA MERCED CALLEJAS POSADA'
        s='MARIA DEL CARMEN DE LA CUESTA BENJUMEA'
        s='NICOLAS CARLOS MARTI JARAMILLO OCAMPO'
        s='DIEGO ALEJANDRO RESTREPO QUINTERO'
        s='JAIRO HUMBERTO RESTREPO ZEA'
        s='MARLEN JIMENEZ DEL RIO'        
    Fails with more than 2 last names:
    ----
        s='ANDRES MAURICIO RANGEL MARTINEZ VILLAL'
    """
    s=s.title()
    sl=re.sub('(\s\w{1,3})\s',r'\1::',s,re.UNICODE)
    sl=re.sub('(\s\w{1,3}\::\w{1,3})\s',r'\1::',sl,re.UNICODE)
    sl=re.sub('^(\w{1,3})\s',r'\1::' ,sl,re.UNICODE)
    #Clean exceptions
    #Extract short names list
    lst=[s for s in re.split( '(\w{1,3})\:\:',sl ) if len(s)>=1 and len(s)<=3 ]
    #intersection with exceptions list
    exc=[value for value in exceptions if value in lst]
    if exc:
        for e in exc:
            sl=sl.replace(f'{e}::',f'{e} ')
            
    #if sl.find('-')>-1:
    #sll=[s.replace('-',' ') for s in sl.split()]
    #
    sll=sl.split()
    if len(s.split())==3:
        IBERO=True
        if nacionality in ['Extranjero - otra', 'Brasilera']:
            NOT_IA=input(f'Is {s} from Ibero-America? (y/n)')
            if NOT_IA.lower()=='n' or NOT_IA.lower()=='not' or NOT_IA.lower()=='no':
                IBERO=False
        if IBERO:
            sll=['']+s.split()
        else:
            sll=s.split()+['']
    if len(s.split())==2: 
        sll=['']+s.split()+['']

        
    d={'NOMBRE COMPLETO' : ' '.join([x for x in sll[2:] if x]+
                                    [x for x in sll[:2] if x]).replace('::',' '),
     'PRIMER APELLIDO' : sll[-2].replace('::',' '), 
     'SEGUNDO APELLIDO': sll[-1].replace('::',' '), 
     'NOMBRES'         :' '.join([x for x in sll[:-2] if x]).replace('::',' '), 
     'INICIALES'       :' '.join( [i[0]+'.' for i in ' '.join(
                                [x for x in sll[:-2] if x]).replace('::',' ').split() ] )
    }
    return d
assert split_names('DANIEL ANDRES LA ROTTA FORERO')['NOMBRES']=='Daniel Andres'
assert split_names('Jairo Humberto Zea Restrepo')['NOMBRES']=='Jairo Humberto'
assert split_names('RICARDO DE LA MERCED CALLEJAS POSADA')['NOMBRES']=='Ricardo De La Merced'
assert (split_names('MARIA DEL CARMEN DE LA CUESTA BENJUMEA')['NOMBRES']== 'Maria Del Carmen'  and
         split_names('MARIA DEL CARMEN DE LA CUESTA BENJUMEA')['PRIMER APELLIDO']=='De La Cuesta')
assert split_names('NICOLAS CARLOS MARTI JARAMILLO OCAMPO')['NOMBRES']=='Nicolas Carlos Marti'
assert split_names('DIEGO ALEJANDRO RESTREPO QUINTERO')['NOMBRES']=='Diego Alejandro'
assert split_names('DIEGO RESTREPO QUINTERO',nacionality='Colombiana')['NOMBRES']=='Diego'
assert split_names('DIEGO RESTREPO',nacionality='Colombiana')['NOMBRES']=='Diego'
assert split_names('Anand Jagadeesh Puppala',nacionality='Extranjero - otra')['NOMBRES']=='Anand Jagadeesh'