Semantization_Interface/samples/parsers/CSV_to_RDF_Autori.py

## IMPORTS

# Utilities to read/write csv files
import csv



# Directories
import_dir = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/MPP/CSV/corretti/'
export_dir = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/MPP/RDF/'

# Custom class to store URIs + related infos for the ontologies/repositories

class RDFcoords:
    def __init__(self, uri, prefix, code = None):
        self.uri = uri
        self.prefix = prefix
        self.code = code


# Repositories
museoCoords = RDFcoords('<https://palazzopretorio.prato.it/it/le-opere/alcuni-capolavori/>', 'mpp:')
autCoords = RDFcoords('<https://palazzopretorio.prato.it/it/opere/autori/>', 'aut:')
foafCoords = RDFcoords('<http://xmlns.com/foaf/0.1/>', 'foaf:')

cidocCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/>', 'crm:')
aatCoords = RDFcoords('<http://vocab.getty.edu/aat/>', 'aat:')
nsCoords = RDFcoords('<http://www.w3.org/1999/02/22-rdf-syntax-ns#>', 'rdf:')
schemaCoords = RDFcoords('<http://www.schema.org/>', 'schema:')
rdfsCoords = RDFcoords('<http://www.w3.org/2000/01/rdf-schema#>', 'rdfs:')


# Basic utilities to format triples / shortened triples in TTL format
#
# Format full triple
def triple(subject, predicate, object1):
    line = subject + ' ' + predicate + ' ' + object1
    return line

# Format entry in predicate list (no subject)
def doublet(predicate, object1):
    line = '    ' + predicate + ' ' + object1
    return line

# Format entry in object list (object only)
def singlet(object1):
    line = '        ' + object1
    return line

# Line endings
continueLine1 = ' ;\n' # Before a predicate list, that is if the FOLLOWING triple has the same subject
continueLine2 = ' ,\n' # Before an object list, that is if the FOLLOWING triple has the same subject and predicate
closeLine = ' .\n' # To end a triple / a triples block


def writeTTLHeader(output):
    output.write('@prefix ' + museoCoords.prefix + ' ' + museoCoords.uri + closeLine)
    output.write('@prefix ' + foafCoords.prefix + ' ' + foafCoords.uri + closeLine)
    output.write('@prefix ' + autCoords.prefix + ' ' + autCoords.uri + closeLine)
    output.write('@prefix ' + cidocCoords.prefix + ' ' + cidocCoords.uri + closeLine)
    output.write('@prefix ' + aatCoords.prefix + ' ' + aatCoords.uri + closeLine)
    output.write('@prefix ' + schemaCoords.prefix + ' ' + schemaCoords.uri + closeLine)
    output.write('@prefix ' + nsCoords.prefix + ' ' + nsCoords.uri + closeLine)
    output.write('@prefix ' + rdfsCoords.prefix + ' ' + rdfsCoords.uri + closeLine)
    output.write('\n')


filePrefix = 'AR20AUT_'
fileType = 'Datini'
max_entries = None

def parsefromfile(infile, outfile):
    pyppa = infile.decode()
    csv_dicts = [{k: v for k, v in row.items()} for row in csv.DictReader(pyppa.splitlines(), skipinitialspace=True)]
    parse(csv_dicts, outfile)

def parse(dict_list, outfile):
    with open(outfile, 'w') as output:
        writeTTLHeader(output)
        first = True # In case something needs processing only once for the whole CSV input
        for ii, row in enumerate(dict_list):
            # The index ii is mainly used to limit the number of entries to process, for testing purposes

            url = row['URL']

            #placeHolders
            e21placeHolder = autCoords.prefix + url
            e62placeHolder = autCoords.prefix + url + '_E62'
            e42placeHolder = autCoords.prefix + row['AUTH']
            e67placeHolder = autCoords.prefix + url + '_E67'
            e69placeHolder = autCoords.prefix + url + '_E69'

            line = triple(e21placeHolder, nsCoords.prefix + 'type',
                        cidocCoords.prefix + 'E21_Person') + closeLine
            output.write(line)
            
            line = triple(e21placeHolder,
                            nsCoords.prefix + 'type',
                            foafCoords.prefix + 'person') + closeLine
            output.write(line)
            
            if row['AUTN'] != '':
                line = triple(e21placeHolder,
                                foafCoords.prefix + 'name',
                                '\"' + row['AUTN'] + '\"') + closeLine
                output.write(line)

            if row['AUTC'] != '':
                line = triple(e21placeHolder,
                                foafCoords.prefix + 'familyName',
                                '\"' + row['AUTC'] + '\"') + closeLine
                output.write(line)

            if row['AUTO'] != '':
                line = triple(e21placeHolder,
                                foafCoords.prefix + 'givenName',
                                '\"' + row['AUTO'] + '\"') + closeLine
                output.write(line)

            if row['AUTZ'] != '':
                line = triple(e21placeHolder,
                                foafCoords.prefix + 'gender',
                                '\"' + row['AUTZ'] + '\"') + closeLine
                output.write(line)

            line = triple(e21placeHolder, rdfsCoords.prefix + 'label',
                        '\"' + row['AUTN'] + ', ' + row['AUTA'] + '\"') + closeLine
            output.write(line)

            line = triple(e21placeHolder, cidocCoords.prefix + 'P3_has_note',
                        e62placeHolder) + closeLine
            output.write(line)

            line = triple(e62placeHolder, nsCoords.prefix + 'type',
                        cidocCoords.prefix + 'E62_String') + closeLine
            output.write(line)
            line = triple(e62placeHolder, rdfsCoords.prefix + 'label',
                        '\"Fonte: Museo di Palazzo Pretorio - Collezione Martini\"') + closeLine
            output.write(line)

            #E21 - P1 - E42
            line = triple(e21placeHolder, cidocCoords.prefix + 'P1_is_identified_by',
                        e42placeHolder) + closeLine
            output.write(line)
            line = triple(e42placeHolder, nsCoords.prefix + 'type',
                        cidocCoords.prefix + 'E42_Identifier') + closeLine
            output.write(line)
            line = triple(e42placeHolder, rdfsCoords.prefix + 'label',
                        '\"' + row['AUTH'] + '\"') + closeLine
            output.write(line)

            # E21 - P107i - E74
            if row['AUTU'] != '':
                group = []
                if '/' in row['AUTU']:
                    group = row['AUTU'].split('/')
                else:
                    group.append(row['AUTU'])

                for gr in group:
                    gg = gr.replace(' ', '')
                    e74placeHolder = museoCoords.prefix + gg
                    line = triple(e21placeHolder,
                                cidocCoords.prefix + 'P107i_is_current_or_former_member_of',
                                e74placeHolder) + closeLine
                    output.write(line)
                    line = triple(e74placeHolder,
                                nsCoords.prefix + 'type',
                                cidocCoords.prefix + 'E74_Group') + closeLine
                    output.write(line)
                    line = triple(e74placeHolder,
                                rdfsCoords.prefix + 'label',
                                '\"' + row['AUTU'] + '\"') + closeLine
                    output.write(line)

            #E21 - P98i - E67
            line = triple(e21placeHolder,
                        cidocCoords.prefix + 'P98i_was_born',
                        e67placeHolder) + closeLine
            output.write(line)
            line = triple(e67placeHolder,
                        nsCoords.prefix + 'type',
                        cidocCoords.prefix + 'E67_Birth') + closeLine
            output.write(line)
            line = triple(e67placeHolder,
                        rdfsCoords.prefix + 'label',
                        '\"Nascita di ' + row['AUTN'] + '\"') + closeLine
            output.write(line)

            line = triple(e21placeHolder,
                        cidocCoords.prefix + 'P100i_died_in',
                        e69placeHolder) + closeLine
            output.write(line)
            line = triple(e69placeHolder,
                        nsCoords.prefix + 'type',
                        cidocCoords.prefix + 'E69_Death') + closeLine
            output.write(line)
            line = triple(e69placeHolder,
                        rdfsCoords.prefix + 'label',
                        '\"Morte di ' + row['AUTN'] + '\"') + closeLine
            output.write(line)

            #E67 - P7 - E53
            if row['AUTL'] != '':
                line = triple(e67placeHolder,
                            cidocCoords.prefix + 'P7_took_place_at',
                            museoCoords.prefix + row['AUTL']) + closeLine
                output.write(line)
                line = triple(museoCoords.prefix + row['AUTL'],
                            nsCoords.prefix + 'type',
                            cidocCoords.prefix + 'E53_Place') + closeLine
                output.write(line)
                line = triple(museoCoords.prefix + row['AUTL'],
                            rdfsCoords.prefix + 'label',
                            '\"' + row['AUTL'] + '\"') + closeLine
                output.write(line)

            # E67 - P4 - E52

            if row['AUTD'] != '':
                tt = row['AUTD'].replace(' ', '')
                tim = tt.replace('/', '')
                time = tim.replace('.', '')
                line = triple(e67placeHolder,
                            cidocCoords.prefix + 'P4_has_time-span',
                            museoCoords.prefix + time) + closeLine
                output.write(line)
                line = triple(museoCoords.prefix + time,
                            nsCoords.prefix + 'type',
                            cidocCoords.prefix + 'E52_Time-Span') + closeLine
                output.write(line)
                line = triple(museoCoords.prefix + time,
                            rdfsCoords.prefix + 'label',
                            '\"' + row['AUTD'] + '\"') + closeLine
                output.write(line)

            # E69 - P7 - E53
            if row['AUTX'] != '':
                line = triple(e69placeHolder,
                            cidocCoords.prefix + 'P7_took_place_at',
                            museoCoords.prefix + row['AUTX']) + closeLine
                output.write(line)
                line = triple(museoCoords.prefix + row['AUTX'],
                            nsCoords.prefix + 'type',
                            cidocCoords.prefix + 'E53_Place') + closeLine
                output.write(line)
                line = triple(museoCoords.prefix + row['AUTX'],
                            rdfsCoords.prefix + 'label',
                            '\"' + row['AUTX'] + '\"') + closeLine
                output.write(line)

            # E69 - P4 - E52
            if row['AUTT'] != '':
                tt = row['AUTT'].replace(' ', '')
                tim = tt.replace('/', '')
                time = tim.replace('.', '')
                line = triple(e69placeHolder,
                            cidocCoords.prefix + 'P4_has_time-span',
                            museoCoords.prefix + time) + closeLine
                output.write(line)
                line = triple(museoCoords.prefix + time,
                            nsCoords.prefix + 'type',
                            cidocCoords.prefix + 'E52_Time-Span') + closeLine
                output.write(line)
                line = triple(museoCoords.prefix + time,
                            rdfsCoords.prefix + 'label',
                            '\"' + row['AUTT'] + '\"') + closeLine
                output.write(line)
            
            # E21 - occupation 
            if row['AUTQ'] != '':
                line = triple(e21placeHolder,
                            schemaCoords.prefix + 'hasOccupation',
                            museoCoords.prefix + row['AUTQ']) + closeLine
                output.write(line)
                line = triple(museoCoords.prefix + row['AUTQ'],
                            nsCoords.prefix + 'type',
                            schemaCoords.prefix + 'Occupation') + closeLine
                output.write(line)
                line = triple(museoCoords.prefix + row['AUTQ'],
                            rdfsCoords.prefix + 'label',
                            '\"' + row['AUTQ'] + '\"') + closeLine
                output.write(line)

            # E21 - P139 - E41
            if row['AUTV'] != '':
                autv = []
                if '/' in row['AUTV']:
                    autv = row['AUTV'].split('/')
                else:
                    autv.append(row['AUTV'])
                autvplaceHolder = museoCoords.prefix + row['AUTV'].replace(' ', '-').replace('\'', '')
                line = triple(e21placeHolder,
                            cidocCoords.prefix + 'P139_has_alternative-form',
                            '\"' + row['AUTV'] + '\"') + closeLine
                output.write(line)

            output.write('\n')
            #
            #
            # To limit number of entries processed (if desired for testing purposes)
            if (max_entries is not None and ii > max_entries):
                break