Parser/Museo/CSV_to_RDF/CSV_to_RDF_mpp_MaterialAndTechnique.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_dir = '/Users/alessiaspadi/Documents/RESTORE/temp_MPP/tabelle/Datini/mod/'
export_dir = '/Users/alessiaspadi/Documents/RESTORE/temp_MPP/tabelle/Datini/mod/E57_'


# 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.comune.prato.it/it/le-opere/alcuni-capolavori/>', 'mpp:')

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:')


# 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('\n')


filePrefix = 'SR20OA_'
fileType = 'Datini'
max_entries = 1000000000

def get_elem(mtc):
    mtc_file = open('/Users/alessiaspadi/Documents/RESTORE/temp_MPP/tabelle/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

        url = row['URL']

        #placeHolders
        datplaceHolder = museoCoords.prefix + url
        e12placeHolder = museoCoords.prefix + url + '_E12'

        if row['MTC'] != '':
            mtcs = []
            if '/' in row['MTC']:
                mtcs = row['MTC'].split('/')
            else:
                mtcs.append(row['MTC'])

            for tc in mtcs:
                mtc = tc.lstrip()
                el = get_elem(mtc)
                if el[1] == 'MTC/M':

                    line = triple(datplaceHolder,
                                  cidocCoords.prefix + 'P45_consists_of',
                                  aatCoords.prefix + el[0]) + closeLine
                    output.write(line)
                    line = triple(aatCoords.prefix + el[0],
                                  nsCoords.prefix + 'type',
                                  cidocCoords.prefix + 'E57_Material') + closeLine
                    output.write(line)
                    line = triple(aatCoords.prefix + el[0],
                                  schemaCoords.prefix + 'label',
                                  '\"' + mtc + '\"') + closeLine
                    output.write(line)

                else:   #E12 Production - P32 used technique - E55 Type
                    line = triple(e12placeHolder,
                                  cidocCoords.prefix + 'P32_used_general_technique',
                                  aatCoords.prefix + el[0]) + closeLine
                    output.write(line)
                    line = triple(aatCoords.prefix + el[0],
                                  nsCoords.prefix + 'type',
                                  cidocCoords.prefix + 'E55_Type') + closeLine
                    output.write(line)
                    line = triple(aatCoords.prefix + el[0],
                                  schemaCoords.prefix + 'label',
                                  '\"' + mtc + '\"') + closeLine
                    output.write(line)

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