Parser/OVI/CSV_to_RDF/CSV_to_RDF_ovi_toponimi.py

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

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 csv
# Utilities to handle character encodings
import unicodedata
# Ordered Dicts
from collections import OrderedDict

import json

import string

import_dir = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/TOPONIMI/CSV/'
export_dir = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/TOPONIMI/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
aspoCoords = RDFcoords('<http://datini.archiviodistato.prato.it/la-ricerca/scheda/>', 'dat:')
placeCoords = RDFcoords('<http://www.archiviodistato.prato.it/accedi-e-consulta/aspoMV001/scheda/>', 'pl:')
oviCoords = RDFcoords('<http://www.ovi.cnr.it/>', 'ovi:')
cidocCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/>', 'crm:')
tgnCoords = RDFcoords('<http://vocab.getty.edu/tgn/>', 'tgn:')
nsCoords = RDFcoords('<http://www.w3.org/1999/02/22-rdf-syntax-ns#>', 'rdf:')
schemaCoords = RDFcoords('<http://www.w3.org/2000/01/rdf-schema#>', 'rdfs:')
devCoords = RDFcoords('<http://dev.restore.ovi.cnr.it/vocabularies/places/>', 'dev:')
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 ' + placeCoords.prefix + ' ' + placeCoords.uri + closeLine)
    output.write('@prefix ' + aspoCoords.prefix + ' ' + aspoCoords.uri + closeLine)
    output.write('@prefix ' + oviCoords.prefix + ' ' + oviCoords.uri + closeLine)
    output.write('@prefix ' + cidocCoords.prefix + ' ' + cidocCoords.uri + closeLine)
    output.write('@prefix ' + tgnCoords.prefix + ' ' + tgnCoords.uri + closeLine)
    output.write('@prefix ' + schemaCoords.prefix + ' ' + schemaCoords.uri + closeLine)
    output.write('@prefix ' + nsCoords.prefix + ' ' + nsCoords.uri + closeLine)
    output.write('@prefix ' + devCoords.prefix + ' ' + devCoords.uri + closeLine)
    output.write('@prefix ' + owlCoords.prefix + ' ' + owlCoords.uri + closeLine)

    output.write('\n')


filePrefix = 'toponimi_'
fileType = 'OVI_ASPO'
max_entries = 1000000000

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
    for row in reader:
        # The index ii is used to process a limited number of entries for testing purposes
        ii = ii + 1

        if row['ID ASPO'] != "":
            #placeHolders
            top = row['toponimo'].replace(" ", "_")
            toponimo = top.translate(str.maketrans('', '', string.punctuation))
            E73placeHolder = '<http://datini.archiviodistato.prato.it/la-ricerca/scheda/' + row['ID ASPO'] + '/E73_OVI>'
            topPlaceHolder = oviCoords.prefix + toponimo
            placePlaceHolder = devCoords.prefix + row['ID RESTORE']

            line = triple(E73placeHolder,
                          cidocCoords.prefix + 'P67_refers_to',
                          topPlaceHolder) + closeLine
            output.write(line)

            line = triple(topPlaceHolder,
                          nsCoords.prefix + 'type',
                          cidocCoords.prefix + 'E41_Appellation') + closeLine
            output.write(line)

            label = string.capwords(row['toponimo'])
            line = triple(topPlaceHolder,
                          schemaCoords.prefix + 'label',
                          '\"' + label + '\"') + closeLine
            output.write(line)

            line = triple(topPlaceHolder,
                          cidocCoords.prefix + 'P2_has_type',
                          '\"Toponimo\"') + closeLine
            output.write(line)

            line = triple(placePlaceHolder,
                          cidocCoords.prefix + 'P1_is_identified_by',
                          topPlaceHolder) + closeLine
            output.write(line)

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