Parser/FORMS/parsers/prebuilt_parsers/CSV_to_RDF_ASPO/ospedale/CSV_to_RDF_onomastica_ospedale_family.py

#Parser to convert the Datini onomastics CSV file into TTL format

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

import json
import re


# 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/ASPO/CSV/ospedale/'
export_dir = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/ASPO/RDF/ospedale/'

# 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
aspoCoords = RDFcoords('<http://www.archiviodistato.prato.it/accedi-e-consulta/aspoMV001/scheda/>', 'aspo:')
foafCoords = RDFcoords('<http://xmlns.com/foaf/0.1/>', 'foaf:')
cidocCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/>', 'crm:')
schemaCoords = RDFcoords('<http://schema.org/>', 'schema:')
personCoords = RDFcoords('<http://www.w3.org/ns/person#>', 'person:')
nsCoords = RDFcoords('<http://www.w3.org/1999/02/22-rdf-syntax-ns#>', 'rdf:')
rdfsCoords = RDFcoords('<http://www.w3.org/2000/01/rdf-schema#>', 'rdfs:')
owlCoords = RDFcoords('<http://www.w3.org/2002/07/owl#>', 'owl:')

# 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 ' + aspoCoords.prefix + ' ' + aspoCoords.uri + closeLine)
    output.write('@prefix ' + foafCoords.prefix + ' ' + foafCoords.uri + closeLine)
    output.write('@prefix ' + cidocCoords.prefix + ' ' + cidocCoords.uri + closeLine)
    output.write('@prefix ' + personCoords.prefix + ' ' + personCoords.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('@prefix ' + owlCoords.prefix + ' ' + owlCoords.uri + closeLine)
    output.write('\n')


filePrefix = 'OSPEDALE - onomastica '
fileType = '- family'
max_entries = 10000000000000

with open(import_dir + filePrefix + fileType + '.csv', newline="") as csv_file, open(
        export_dir + filePrefix + fileType + '.ttl', 'w') as output:
    reader = csv.DictReader(csv_file)
    writeTTLHeader(output)
    first = True
    ii = 0
    e55placeHolder = '<http://www.archiviodistato.prato.it/famiglia>'
    line = triple(e55placeHolder,
                          rdfsCoords.prefix + 'label',
                          '\"Famiglia\"') + closeLine
    output.write(line)
    for row in reader:
        # The index ii is used to process a limited number of entries for testing purposes
        ii = ii + 1
        if row['entityType'] == 'family':
            id_aspo = row['recordId']
            aspoPlaceHolder = aspoCoords.prefix + id_aspo
            line = triple(aspoPlaceHolder, 
                          nsCoords.prefix + 'type', 
                          cidocCoords.prefix + 'E74_Group') + closeLine
            output.write(line)
            line = triple(aspoPlaceHolder,
                          nsCoords.prefix + 'type',
                          foafCoords.prefix + 'Group') + closeLine
            output.write(line)

            line = triple(aspoPlaceHolder,
                          cidocCoords.prefix + 'P1_is_identified_by',
                          aspoPlaceHolder + "_E42") + closeLine
            output.write(line)

            line = triple(aspoPlaceHolder + "_E42",
                          nsCoords.prefix + 'type',
                          cidocCoords.prefix + 'E42_Identifier') + closeLine
            output.write(line)
            line = triple(aspoPlaceHolder + "_E42",
                          rdfsCoords.prefix + 'label',
                          '\"' + id_aspo + '\"') + closeLine
            output.write(line)

            line = triple(aspoPlaceHolder,
                          foafCoords.prefix + 'name',
                          '\"' + row['nameEntry@normal'].replace("\"", "") + '\"') + closeLine
            output.write(line)

            line = triple(aspoPlaceHolder,
                          rdfsCoords.prefix + 'label',
                          '\"' + row['nameEntry@normal'].replace("\"", "") + '\"') + closeLine
            output.write(line)
            
            line = triple(aspoPlaceHolder,
                              cidocCoords.prefix + 'P2_has_type',
                              e55placeHolder) + closeLine
            output.write(line)

            output.write('\n')
        #
        # Limit number of entries processed (if desired)
        if (ii > max_entries):
            break