Parser/MPP/CSV_to_RDF/CSV_to_RDF_Datini_cataloghi.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/Google Drive/OVI-CNR/CSV/MPP/corretti/'
export_dir = '/Users/federicaspinelli/Google Drive/OVI-CNR/RDF/MPP/'


# 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('<http://palazzopretorio.prato.it/it/le-opere/alcuni-capolavori/>', 'mpp:')
autCoords = RDFcoords('<http://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:')


# 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('\n')


filePrefix = '00_SR20OA_'
fileType = 'Datini'
max_entries = 1000000000

def get_aut_url(code):
    aut_file = open(import_dir + 'AR20AUT_' + fileType + '.csv', newline="")
    reader = csv.DictReader(aut_file)
    for row in reader:
        auth = int(row['AUTH'])
        cod = int(code)
        role = ''
        if row['AUTQ'] != '':
            role = row['AUTQ']
        else:
            role = ''
        if auth == cod:
            return [row['URL'], role]

def get_role(role):
    role_file = open('/Users/federicaspinelli/Google Drive/OVI-CNR/CSV/MPP/AAT_RUOLI.csv', newline="")
    reader = csv.DictReader(role_file)
    for row in reader:
        if row['Label'] == role:
            return row['AAT']

def get_elem(mtc):
    mtc_file = open('/Users/federicaspinelli/Google Drive/OVI-CNR/CSV/MPP/AAT_MTC.csv', newline="")
    reader = csv.DictReader(mtc_file)
    for row in reader:
        if row['MTC'] == mtc:
            return [row['AAT'], row['Type']]

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

        sb = ''
        subj = ''
        pp = row['OGTD'] + ' (' + row['ACC'] + ') '
        if row['SGTI'] != '':
            sb = pp + row['SGTI']
        if row['LDCN'] != '':
            subj = sb + ' in ' + row['LDCN']
        else:
            subj = sb

        # Triplify the 'codice' -- should exist for every entry
        codice = ''
        if (row['NCTR'] != '' and row['NCTN'] != ''):
            codice = row['NCTR'] + row['NCTN']

        codiceP = ''
        if (row['AUTH'] != ''):
            codiceP = row['AUTH']

        place = ''
        if (row['PRVC'] != ''):
            place = row['PRVC']

        columnName = list(row)
        url = row['URL']


        # placeHolders
        datplaceHolder = museoCoords.prefix + url
        e1placeHolder = museoCoords.prefix + url + '_E1'
        e3placeHolder = museoCoords.prefix + url + 'E3'
        e10placeHolder = museoCoords.prefix + url + '_E10'
        e12placeHolder = museoCoords.prefix + url + '_E12'
        e13placeHolder = museoCoords.prefix + url + '_E13'
        e21placeHolder = museoCoords.prefix + url + '_InE21'
        e25placeHolder = museoCoords.prefix + url + '_E25'
        e34placeHolder = museoCoords.prefix + url + '_E34'
        e35placeHolder1 = museoCoords.prefix + url + '_E35'
        e42placeHolder = museoCoords.prefix + url + '_E42'
        e42CplaceHolder = museoCoords.prefix + url + '_E42_MPP'
        e65placeHolder = museoCoords.prefix + url + '_InE65'
        e73placeHolder = museoCoords.prefix + url + '_E73'
        e74placeHolder = museoCoords.prefix + url + '_E74'

        if (codice != ''):
            line = triple(datplaceHolder, cidocCoords.prefix + 'P1_is_identified_by', '\"' + codice + '\"') + closeLine
            output.write(line)
        output.write('\n')
        #
        #
        # Limit number of entries processed (if desired)
        if (ii > max_entries):
            break