Parser/FORMS/parsers/prebuilt_parsers/CSV_to_RDF_ASPO/datini/CSV_to_RDF_onomastica_datini_person_occupation.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/datini/'
export_dir = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/ASPO/RDF/datini/'

# 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 = 'association_occupation_DATINI_luoghi_restore'
fileType = ''
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
    for row in reader:
        # The index ii is used to process a limited number of entries for testing purposes
        ii = ii + 1
        id_aspo = row['recordid']
        aspoPlaceHolder = aspoCoords.prefix + id_aspo

        if row['occupation_1'] != '' and row['occupation_1'] != ' ' :
                occupazioni = []
                pipe = "|"
                if pipe in row['occupation_1']:
                    occupazioni = row['occupation_1'].split('|') 
                    for occupazione in occupazioni:
                        #Remove all white-space characters:
                        txt = occupazione
                        x = re.sub("\n", " ", txt)
                        y = re.sub("\s\s", "", x)
                        occ = re.sub(r'[^A-Za-z]','', y)
                        occupationPlaceHolder = '<http://www.archiviodistato.prato.it/' + occ.replace(" ","_") + '>'
                        line = triple(aspoPlaceHolder,
                                    schemaCoords.prefix + 'hasOccupation',
                                    occupationPlaceHolder) + closeLine
                        output.write(line)
                        line = triple(occupationPlaceHolder,
                                    nsCoords.prefix + 'type',
                                    schemaCoords.prefix + 'Occupation') + closeLine
                        output.write(line)
                        line = triple(occupationPlaceHolder,
                                    rdfsCoords.prefix + 'label',
                                    '\"' + y + '\"') + closeLine
                        output.write(line)
                        if row['ID_ente_1'] != '':
                            placeoccupationPlaceHolder = '<http://dev.restore.ovi.cnr.it/vocabularies/places/' + row['ID_ente_1'] + '>'
                            line = triple(aspoPlaceHolder,
                                                schemaCoords.prefix + 'workLocation',
                                                placeoccupationPlaceHolder) + closeLine
                            output.write(line)
                            line = triple(occupationPlaceHolder,
                                                schemaCoords.prefix + 'occupationLocation',
                                                placeoccupationPlaceHolder) + closeLine
                            output.write(line)
                        elif row['ID_ente_1'] == '' and row['place occupation 1 ENTE'] != '':
                            placeoccupazioni = []
                            pipe = "|"
                            if pipe in row['place occupation 1 ENTE']:
                                placeoccupazioni = row['place occupation 1 ENTE'].split('|') 
                                for placeoccupazione in placeoccupazioni:
                                    #Remove all white-space characters:
                                    txt = row['place occupation 1 ENTE']
                                    x = re.sub("\n", " ", txt)
                                    y = re.sub("\s\s", "", x)
                                    placeoccupationPlaceHolder = '<http://www.archiviodistato.prato.it/' + y.replace(" ","_").replace("'","").replace('\\','\\\\').replace('"','\\"') + '>'
                                    line = triple(aspoPlaceHolder,
                                                schemaCoords.prefix + 'workLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                    output.write(line)
                                    line = triple(occupationPlaceHolder,
                                                schemaCoords.prefix + 'occupationLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                    output.write(line)
                                    line = triple(placeoccupationPlaceHolder,
                                    rdfsCoords.prefix + 'label',
                                    '\"' + y + '\"') + closeLine
                                    output.write(line)
                                    line = triple(placeoccupationPlaceHolder,
                                    nsCoords.prefix + 'type',
                                    cidocCoords.prefix + 'E53_Place') + closeLine
                                    output.write(line)
                                    line = triple(aspoPlaceHolder,
                                    schemaCoords.prefix + 'jobTitle',
                                    '\"' + row['occupation_1'].lower() + ' presso ' + row['place occupation 1 ENTE'].lower() + '\"') + closeLine
                                    output.write(line)
                            else: 
                                placeoccupazioni = row['place occupation 1 ENTE'].split('|') 
                                txt = row['place occupation 1 ENTE']
                                x = re.sub("\n", " ", txt)
                                y = re.sub("\s\s", "", x)
                                placeoccupationPlaceHolder = '<http://www.archiviodistato.prato.it/' + y.replace(" ","_").replace("'","").replace('\\','\\\\').replace('"','\\"') + '>'
                                line = triple(aspoPlaceHolder,
                                                schemaCoords.prefix + 'workLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                output.write(line)
                                line = triple(occupationPlaceHolder,
                                                schemaCoords.prefix + 'occupationLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                output.write(line)
                                line = triple(placeoccupationPlaceHolder,
                                    rdfsCoords.prefix + 'label',
                                    '\"' + y + '\"') + closeLine
                                output.write(line)
                                line = triple(placeoccupationPlaceHolder,
                                    nsCoords.prefix + 'type',
                                    cidocCoords.prefix + 'E53_Place') + closeLine
                                output.write(line)
                                line = triple(aspoPlaceHolder,
                                    schemaCoords.prefix + 'jobTitle',
                                    '\"' + row['occupation_1'].lower() + ' presso ' + row['place occupation 1 ENTE'].lower() + '\"') + closeLine
                                output.write(line)              
                else:
                    #Remove all white-space characters:
                    txt = row['occupation_1']
                    x = re.sub("\n", " ", txt)
                    y = re.sub("\s\s", "", x)
                    occ = re.sub(r'[^A-Za-z]','', y)
                    occupationPlaceHolder = '<http://www.archiviodistato.prato.it/' + occ.replace(" ","_") + '>'
                    line = triple(aspoPlaceHolder,
                                schemaCoords.prefix + 'hasOccupation',
                                occupationPlaceHolder) + closeLine
                    output.write(line)
                    line = triple(occupationPlaceHolder,
                                nsCoords.prefix + 'type',
                                schemaCoords.prefix + 'Occupation') + closeLine
                    output.write(line)
                    line = triple(occupationPlaceHolder,
                                rdfsCoords.prefix + 'label',
                                '\"' + y + '\"') + closeLine
                    output.write(line)
                    if row['ID_ente_1'] != '':
                            placeoccupationPlaceHolder = '<http://dev.restore.ovi.cnr.it/vocabularies/places/' + row['ID_ente_1'] + '>'
                            line = triple(aspoPlaceHolder,
                                                schemaCoords.prefix + 'workLocation',
                                                placeoccupationPlaceHolder) + closeLine
                            output.write(line)
                            line = triple(occupationPlaceHolder,
                                                schemaCoords.prefix + 'occupationLocation',
                                                placeoccupationPlaceHolder) + closeLine
                            output.write(line)
                    elif row['ID_ente_1'] == '' and row['place occupation 1 ENTE'] != '':
                            placeoccupazioni = []
                            pipe = "|"
                            if pipe in row['place occupation 1 ENTE']:
                                placeoccupazioni = row['place occupation 1 ENTE'].split('|') 
                                for placeoccupazione in placeoccupazioni:
                                    #Remove all white-space characters:
                                    txt = row['place occupation 1 ENTE']
                                    x = re.sub("\n", " ", txt)
                                    y = re.sub("\s\s", "", x)
                                    placeoccupationPlaceHolder = '<http://www.archiviodistato.prato.it/' + y.replace(" ","_").replace("'","").replace('\\','\\\\').replace('"','\\"') + '>'
                                    line = triple(aspoPlaceHolder,
                                                schemaCoords.prefix + 'workLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                    output.write(line)
                                    line = triple(occupationPlaceHolder,
                                                schemaCoords.prefix + 'occupationLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                    output.write(line)
                                    line = triple(placeoccupationPlaceHolder,
                                    rdfsCoords.prefix + 'label',
                                    '\"' + y + '\"') + closeLine
                                    output.write(line)
                                    line = triple(placeoccupationPlaceHolder,
                                    nsCoords.prefix + 'type',
                                    cidocCoords.prefix + 'E53_Place') + closeLine
                                    output.write(line)
                                    line = triple(aspoPlaceHolder,
                                    schemaCoords.prefix + 'jobTitle',
                                    '\"' + row['occupation_1'].lower() + ' presso ' + row['place occupation 1 ENTE'].lower() + '\"') + closeLine
                                    output.write(line)
                            else: 
                                placeoccupazioni = row['place occupation 1 ENTE'].split('|') 
                                txt = row['place occupation 1 ENTE']
                                x = re.sub("\n", " ", txt)
                                y = re.sub("\s\s", "", x)
                                placeoccupationPlaceHolder = '<http://www.archiviodistato.prato.it/' + y.replace(" ","_").replace("'","").replace('\\','\\\\').replace('"','\\"') + '>'
                                line = triple(aspoPlaceHolder,
                                                schemaCoords.prefix + 'workLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                output.write(line)
                                line = triple(occupationPlaceHolder,
                                                schemaCoords.prefix + 'occupationLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                output.write(line)
                                line = triple(placeoccupationPlaceHolder,
                                    rdfsCoords.prefix + 'label',
                                    '\"' + y + '\"') + closeLine
                                output.write(line)
                                line = triple(placeoccupationPlaceHolder,
                                    nsCoords.prefix + 'type',
                                    cidocCoords.prefix + 'E53_Place') + closeLine
                                output.write(line)
                                line = triple(aspoPlaceHolder,
                                    schemaCoords.prefix + 'jobTitle',
                                    '\"' + row['occupation_1'].lower() + ' presso ' + row['place occupation 1 ENTE'].lower() + '\"') + closeLine
                                output.write(line)              
            
        if row['occupation_2'] != '' and row['occupation_2'] != ' ' :
                occupazioni = []
                pipe = "|"
                if pipe in row['occupation_2']:
                    occupazioni = row['occupation_2'].split('|') 
                    for occupazione in occupazioni:
                        #Remove all white-space characters:
                        txt = occupazione
                        x = re.sub("\n", " ", txt)
                        y = re.sub("\s\s", "", x)
                        occ = re.sub(r'[^A-Za-z]','', y)
                        occupationPlaceHolder = '<http://www.archiviodistato.prato.it/' + occ.replace(" ","_") + '>'
                        line = triple(aspoPlaceHolder,
                                    schemaCoords.prefix + 'hasOccupation',
                                    occupationPlaceHolder) + closeLine
                        output.write(line)
                        line = triple(occupationPlaceHolder,
                                    nsCoords.prefix + 'type',
                                    schemaCoords.prefix + 'Occupation') + closeLine
                        output.write(line)
                        line = triple(occupationPlaceHolder,
                                    rdfsCoords.prefix + 'label',
                                    '\"' + y + '\"') + closeLine
                        output.write(line)
                        
                        if row['ID_ente_2'] != '':
                            placeoccupationPlaceHolder = '<http://dev.restore.ovi.cnr.it/vocabularies/places/' + row['ID_ente_2'] + '>'
                            line = triple(aspoPlaceHolder,
                                                schemaCoords.prefix + 'workLocation',
                                                placeoccupationPlaceHolder) + closeLine
                            output.write(line)
                            line = triple(occupationPlaceHolder,
                                                schemaCoords.prefix + 'occupationLocation',
                                                placeoccupationPlaceHolder) + closeLine
                            output.write(line)
                        elif row['place occupation 2 ENTE'] != '':
                            placeoccupazioni = []
                            pipe = "|"
                            if pipe in row['place occupation 2 ENTE']:
                                placeoccupazioni = row['place occupation 2 ENTE'].split('|') 
                                for placeoccupazione in placeoccupazioni:
                                    #Remove all white-space characters:
                                    txt = row['place occupation 2 ENTE']
                                    x = re.sub("\n", " ", txt)
                                    y = re.sub("\s\s", "", x)
                                    placeoccupationPlaceHolder = '<http://www.archiviodistato.prato.it/' + y.replace(" ","_").replace("'","").replace('\\','\\\\').replace('"','\\"') + '>'
                                    line = triple(aspoPlaceHolder,
                                                schemaCoords.prefix + 'workLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                    output.write(line)
                                    line = triple(occupationPlaceHolder,
                                                schemaCoords.prefix + 'occupationLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                    output.write(line)
                                    line = triple(placeoccupationPlaceHolder,
                                    rdfsCoords.prefix + 'label',
                                    '\"' + y + '\"') + closeLine
                                    output.write(line)
                                    line = triple(placeoccupationPlaceHolder,
                                    nsCoords.prefix + 'type',
                                    cidocCoords.prefix + 'E53_Place') + closeLine
                                    output.write(line)
                                    line = triple(aspoPlaceHolder,
                                    schemaCoords.prefix + 'jobTitle',
                                    '\"' + row['occupation_2'].lower() + ' presso ' + row['place occupation 2 ENTE'].lower() + '\"') + closeLine
                                    output.write(line)
                            else: 
                                placeoccupazioni = row['place occupation 2 ENTE'].split('|') 
                                txt = row['place occupation 2 ENTE']
                                x = re.sub("\n", " ", txt)
                                y = re.sub("\s\s", "", x)
                                placeoccupationPlaceHolder = '<http://www.archiviodistato.prato.it/' + y.replace(" ","_").replace("'","").replace('\\','\\\\').replace('"','\\"') + '>'
                                line = triple(aspoPlaceHolder,
                                                schemaCoords.prefix + 'workLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                output.write(line)
                                line = triple(occupationPlaceHolder,
                                                schemaCoords.prefix + 'occupationLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                output.write(line)
                                line = triple(placeoccupationPlaceHolder,
                                    rdfsCoords.prefix + 'label',
                                    '\"' + y + '\"') + closeLine
                                output.write(line)
                                line = triple(placeoccupationPlaceHolder,
                                    nsCoords.prefix + 'type',
                                    cidocCoords.prefix + 'E53_Place') + closeLine
                                output.write(line)
                                line = triple(aspoPlaceHolder,
                                    schemaCoords.prefix + 'jobTitle',
                                    '\"' + row['occupation_2'].lower() + ' presso ' + row['place occupation 2 ENTE'].lower() + '\"') + closeLine
                                output.write(line)              
                else:
                    #Remove all white-space characters:
                    txt = row['occupation_2']
                    x = re.sub("\n", " ", txt)
                    y = re.sub("\s\s", "", x)
                    occ = re.sub(r'[^A-Za-z]','', y)
                    occupationPlaceHolder = '<http://www.archiviodistato.prato.it/' + occ.replace(" ","_") + '>'
                    line = triple(aspoPlaceHolder,
                                schemaCoords.prefix + 'hasOccupation',
                                occupationPlaceHolder) + closeLine
                    output.write(line)
                    line = triple(occupationPlaceHolder,
                                nsCoords.prefix + 'type',
                                schemaCoords.prefix + 'Occupation') + closeLine
                    output.write(line)
                    line = triple(occupationPlaceHolder,
                                rdfsCoords.prefix + 'label',
                                '\"' + y + '\"') + closeLine
                    output.write(line)
                    if row['ID_ente_2'] != '':
                            placeoccupationPlaceHolder = '<http://dev.restore.ovi.cnr.it/vocabularies/places/' + row['ID_ente_2'] + '>'
                            line = triple(aspoPlaceHolder,
                                                schemaCoords.prefix + 'workLocation',
                                                placeoccupationPlaceHolder) + closeLine
                            output.write(line)
                            line = triple(occupationPlaceHolder,
                                                schemaCoords.prefix + 'occupationLocation',
                                                placeoccupationPlaceHolder) + closeLine
                            output.write(line)
                    elif row['ID_ente_2'] == '' and row['place occupation 2 ENTE'] != '':
                        placeoccupazioni = []
                        pipe = "|"
                        if pipe in row['place occupation 2 ENTE']:
                                placeoccupazioni = row['place occupation 2 ENTE'].split('|') 
                                for placeoccupazione in placeoccupazioni:
                                    #Remove all white-space characters:
                                    txt = row['place occupation 2 ENTE']
                                    x = re.sub("\n", " ", txt)
                                    y = re.sub("\s\s", "", x)
                                    placeoccupationPlaceHolder = '<http://www.archiviodistato.prato.it/' + y.replace(" ","_").replace("'","").replace('\\','\\\\').replace('"','\\"') + '>'
                                    line = triple(aspoPlaceHolder,
                                                schemaCoords.prefix + 'workLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                    output.write(line)
                                    line = triple(occupationPlaceHolder,
                                                schemaCoords.prefix + 'occupationLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                    output.write(line)
                                    line = triple(placeoccupationPlaceHolder,
                                    rdfsCoords.prefix + 'label',
                                    '\"' + y + '\"') + closeLine
                                    output.write(line)
                                    line = triple(placeoccupationPlaceHolder,
                                    nsCoords.prefix + 'type',
                                    cidocCoords.prefix + 'E53_Place') + closeLine
                                    output.write(line)
                                    line = triple(aspoPlaceHolder,
                                    schemaCoords.prefix + 'jobTitle',
                                    '\"' + row['occupation_2'].lower() + ' presso ' + row['place occupation 2 ENTE'].lower() + '\"') + closeLine
                                    output.write(line)
                        else: 
                                placeoccupazioni = row['place occupation 2 ENTE'].split('|') 
                                txt = row['place occupation 2 ENTE']
                                x = re.sub("\n", " ", txt)
                                y = re.sub("\s\s", "", x)
                                placeoccupationPlaceHolder = '<http://www.archiviodistato.prato.it/' + y.replace(" ","_").replace("'","").replace('\\','\\\\').replace('"','\\"') + '>'
                                line = triple(aspoPlaceHolder,
                                                schemaCoords.prefix + 'workLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                output.write(line)
                                line = triple(occupationPlaceHolder,
                                                schemaCoords.prefix + 'occupationLocation',
                                                placeoccupationPlaceHolder) + closeLine
                                output.write(line)
                                line = triple(placeoccupationPlaceHolder,
                                    rdfsCoords.prefix + 'label',
                                    '\"' + y + '\"') + closeLine
                                output.write(line)
                                line = triple(placeoccupationPlaceHolder,
                                    nsCoords.prefix + 'type',
                                    cidocCoords.prefix + 'E53_Place') + closeLine
                                output.write(line)
                                line = triple(aspoPlaceHolder,
                                    schemaCoords.prefix + 'jobTitle',
                                    '\"' + row['occupation_2'].lower() + ' presso ' + row['place occupation 2 ENTE'].lower() + '\"') + closeLine
                                output.write(line)              
            
        output.write('\n')
        #
        # Limit number of entries processed (if desired)
        if (ii > max_entries):
            break