Parser/MPP/CSV_to_RDF/CSV_to_RDF_Date_normalizzazione.py

# Utilities to read/write csv files
import csv
# Utilities to handle character encodings
import unicodedata
# Ordered Dicts
from collections import OrderedDict

from urllib.request import urlopen
from bs4 import BeautifulSoup

import json

# OPZIONAL IMPORTS

# For timestamping/simple speed tests
from datetime import datetime
# Random number generator
from random import *
# System & command line utilities
import sys
# Json for the dictionary
import json

import_dir = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/MPP/CSV/corretti/'
export_dir = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/MPP/DATE/'

# 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:')
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.w3.org/2000/01/rdf-schema#>', 'rdfs:')
xsdCoords = RDFcoords('<http://www.w3.org/2001/XMLSchema#>', 'xsd:')
iconCoords = RDFcoords('<http://iconclass.org/>', 'ico:')
yearCoords = RDFcoords('<https://www.w3.org/TR/owl-time#year>', 'year:')
monthCoords = RDFcoords('<https://www.w3.org/TR/owl-time#month>', 'month:')
dayCoords = RDFcoords('<https://www.w3.org/TR/owl-time#day>', 'day:')
beginningCoords = RDFcoords('<https://www.w3.org/TR/owl-time#hasBeginning>', 'beg:')
endCoords = RDFcoords('<https://www.w3.org/TR/owl-time#hasEnd>', 'end:')
rdfsCoords = RDFcoords('<http://www.w3.org/2000/01/rdf-schema#>', 'rdfs:')

# Basic functions for triples / shortened triples in TTL format

def triple(subject, predicate, object1):
    line = subject + ' ' + predicate + ' ' + object1
    return line


def doublet(predicate, object1):
    line = '    ' + predicate + ' ' + object1
    return line


def singlet(object1):
    line = '        ' + object1
    return line


# Line endings in TTL format
continueLine1 = ' ;\n'
continueLine2 = ' ,\n'
closeLine = ' .\n'


def writeTTLHeader(output):
    output.write('@prefix ' + museoCoords.prefix + ' ' + museoCoords.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 ' + autCoords.prefix + ' ' + autCoords.uri + closeLine)
    output.write('@prefix ' + xsdCoords.prefix + ' ' + xsdCoords.uri + closeLine)
    output.write('@prefix ' + iconCoords.prefix + ' ' + iconCoords.uri + closeLine)
    output.write('@prefix ' + beginningCoords.prefix + ' ' + beginningCoords.uri + closeLine)
    output.write('@prefix ' + endCoords.prefix + ' ' + endCoords.uri + closeLine)
    output.write('@prefix ' + yearCoords.prefix + ' ' + yearCoords.uri + closeLine) 
    output.write('@prefix ' + monthCoords.prefix + ' ' + monthCoords.uri + closeLine)
    output.write('@prefix ' + dayCoords.prefix + ' ' + dayCoords.uri + closeLine)
    output.write('@prefix ' + rdfsCoords.prefix + ' ' + rdfsCoords.uri + closeLine)
    

    output.write('\n')


filePrefix = 'AR20AUT_'
fileType = 'DATINI'
max_entries = 1000000000


with open(import_dir + filePrefix + fileType + '.csv', newline="") as csv_file, open(export_dir + filePrefix + fileType + '_normalizzate.ttl', 'w') as output:
    reader = csv.DictReader(csv_file)
    writeTTLHeader(output)
    first = True
    ii = 0
    for row in reader:
        # The index ii is used to process a limited number of entries for testing purposes
        ii = ii + 1

        # if row['RVEL'] == '' or row['RVEL'] == '0':
            # E12 - P4 - E52
        # if row['DTSI'] != '':
        #         line = triple(museoCoords.prefix + row['DTSI'], yearCoords.prefix, '\"'+row['DTSI'] +'\"^^xsd:integer')+ closeLine
        #         output.write(line)
        #         # line = triple(museoCoords.prefix + row['DTSI'], monthCoords.prefix, '\"'+ '01' +'\"^^xsd:integer') + closeLine
        #         # output.write(line)
        #         # line = triple(museoCoords.prefix + row['DTSI'], dayCoords.prefix, '\"'+ '01' +'\"^^xsd:integer') + closeLine
        #         # output.write(line)
        #         line = triple(museoCoords.prefix + row['DTSI'], beginningCoords.prefix, '\"'+row['DTSI']+'0101'+'\"^^xsd:date') + closeLine
        #         output.write(line)  

        # e12FplaceHolder = ''
        # if row['DTSI'] != row['DTSF']:
        #     e12FplaceHolder = museoCoords.prefix + row['URL'] + '_E12F'
        # if e12FplaceHolder != '':
        #         line = triple(museoCoords.prefix + row['DTSF'], yearCoords.prefix, '\"'+row['DTSF'] +'\"^^xsd:integer') + closeLine
        #         output.write(line)
        #         # line = triple(museoCoords.prefix + row['DTSF'], monthCoords.prefix, '\"'+ '12' +'\"^^xsd:integer') + closeLine
        #         # output.write(line)
        #         # line = triple(museoCoords.prefix + row['DTSF'], dayCoords.prefix, '\"'+ '31' +'\"^^xsd:integer') + closeLine
        #         # output.write(line)
        #         line = triple(museoCoords.prefix + row['DTSF'], endCoords.prefix, '\"'+row['DTSF']+'1231'+'\"^^xsd:date') + closeLine
        #         output.write(line)  
        if row['AUTD'] != '':
            tt = row['AUTD'].replace(' ', '')
            tim = tt.replace('/', '')
            time = tim.replace('.', '')
            # line = triple(museoCoords.prefix + time, yearCoords.prefix, '\"'+row['AUTD'] +'\"^^xsd:integer') + closeLine
            # output.write(line)
            # line = triple(museoCoords.prefix + time, beginningCoords.prefix, '\"'+row['AUTD']+'0101'+'\"^^xsd:date') + closeLine
            # output.write(line)
            line = triple(museoCoords.prefix + time, endCoords.prefix, '\"'+row['AUTD']+'1231'+'\"^^xsd:date') + closeLine
            output.write(line)

        if row['AUTT'] != '':
            tt = row['AUTT'].replace(' ', '')
            tim = tt.replace('/', '')
            time = tim.replace('.', '')
            # line = triple(museoCoords.prefix + time, yearCoords.prefix, '\"'+row['AUTT'] +'\"^^xsd:integer') + closeLine
            # output.write(line)
            # line = triple(museoCoords.prefix + time, endCoords.prefix, '\"'+row['AUTT']+'1231'+'\"^^xsd:date') + closeLine
            # output.write(line)
            line = triple(museoCoords.prefix + time, beginningCoords.prefix, '\"'+row['AUTT']+'0101'+'\"^^xsd:date') + closeLine
            output.write(line)
        
        

 
        output.write('\n')
        #
        #
        # Limit number of entries processed (if desired)
        if(ii>max_entries):
            break
        
    # if row['PRDI' + f] != '':
    #                     timespan = row['PRDI' + f]

    #                     tt = timespan.replace(' ', '')
    #                     tp = tt.replace('.', '')
    #                     ts = tp.replace('/', '')

    #                     timespanPlaceholder = museoCoords.prefix + '_' + ts

    #                     # E10 P4 E52

    #                     line = triple(newe10placeHolder,
    #                                   cidocCoords.prefix + 'P4_has_time-span',
    #                                   timespanPlaceholder) + closeLine
    #                     output.write(line)
    #                     line = triple(timespanPlaceholder,
    #                                   nsCoords.prefix + 'type',
    #                                   cidocCoords.prefix + 'E52_Time-Span') + closeLine
    #                     output.write(line)
    #                     line = triple(timespanPlaceholder,
    #                                   schemaCoords.prefix + 'label',
    #                                   '\"' + timespan + '\"') + closeLine
    #                     output.write(line)

    #         if row['PRDU' + last] != '':
    #             timespan = row['PRDU' + last]

    #             tt = timespan.replace(' ', '')
    #             ts = tt.replace('/', '')

    #             timespanPlaceholder = museoCoords.prefix + '_' + ts

    #             # E10 P4 E52

    #             line = triple(e10placeHolder,
    #                           cidocCoords.prefix + 'P4_has_time-span',
    #                           timespanPlaceholder) + closeLine
    #             output.write(line)
    #             line = triple(timespanPlaceholder,
    #                           nsCoords.prefix + 'type',
    #                           cidocCoords.prefix + 'E52_Time-Span') + closeLine
    #             output.write(line)
    #             line = triple(timespanPlaceholder,
    #                           schemaCoords.prefix + 'label',
    #                           '\"' + timespan + '\"') + closeLine
    #             output.write(line)