Parser/Museo/CSV_to_RDF/CSV_to_RDF_mpp_Move.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/Ospedale/mod/'
export_dir = '/Users/alessiaspadi/Documents/RESTORE/temp_MPP/tabelle/Ospedale/mod/E9_'


# 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 = 'Ospedale'
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['RVEL'] == '' or row['RVEL'] == '0':

            # Triplify the 'codice' -- should exist for every entry

            codice = ''
            if (row['NCTR'] != '' and row['NCTN'] != ''):
                codice = row['NCTR'] + row['NCTN']

            url = row['URL']

            # placeHolders
            datplaceHolder = museoCoords.prefix + url
            e53placeHolder = museoCoords.prefix + url + '_E53'
            e9placeHolder = museoCoords.prefix + url + '_E9'

            columnName = list(row)
            tcl = []
            for name in columnName:
                if 'TCL' in name:
                    tcl.append(name)

            j=0

            for el in tcl:
                if row[el] != '':
                    j = j+1

            last = str(j-1)

            n = len(tcl) - 1

            for i in range(n - 1):

                k = str(i + 1)

                if i + 1 == 1:
                    w = ''
                else:
                    w = i

                f = str(w)

                if row['TCL' + k] != '':

                    pastLocation = ''
                    newLocation = ''
                    pl = ''

                    if row['PRCD' + k] != '':
                        newLocation = ' a ' + row['PRCD' + k]

                    if row['PRCD' + f] != '':
                        pastLocation = ' da ' + row['PRCD' + f]
                        pl = row['PRCD' + f].replace(' ', '')

                    newe9placeHolder = museoCoords.prefix + url + "_E9_" + k

                    line = triple(datplaceHolder,
                                  cidocCoords.prefix + 'P25i_moved_by',
                                  newe9placeHolder) + closeLine
                    output.write(line)
                    line = triple(newe9placeHolder,
                                  nsCoords.prefix + 'type',
                                  cidocCoords.prefix + 'E9_Move') + closeLine
                    output.write(line)
                    line = triple(newe9placeHolder,
                                  schemaCoords.prefix + 'label',
                                  '\"Trasferimento di ' + row['SGTI'] + pastLocation +
                                  newLocation + '\"') + closeLine
                    output.write(line)

                    timespan = ''
                    ts = ''

                    if row['PRDI' + f] != '':
                        timespan = row['PRDI' + f]

                    if row['PRDU' + f] != '':
                        timespan = timespan + ' - ' + row['PRDU' + f]

                    tt = timespan.replace(' ', '')
                    ts = tt.replace('/', '')

                    timespanPlaceholder = museoCoords.prefix + url + '_' + ts
                    pastLocationPlaceholder = museoCoords.prefix + url + '_' + pl
                    newLoc = row['PRCD' + k].replace(' ', '')
                    newLocationPlaceholder = museoCoords.prefix + url + '_' + newLoc

                    # E9 P4 E52

                    line = triple(newe9placeHolder,
                                  cidocCoords.prefix + 'P4_has_time-span',
                                  timespanPlaceholder) + closeLine
                    output.write(line)
                    line = triple(timespanPlaceholder,
                                  nsCoords.prefix + 'type',
                                  cidocCoords.prefix + 'E52_Time-Span') + closeLine
                    output.write(line)
                    line = triple(timespanPlaceholder,
                                  schemaCoords.prefix + 'label',
                                  '\"' + timespan + '\"') + closeLine
                    output.write(line)

                    # E9 P26 E53 (moved to)

                    if newLocationPlaceholder != '':
                        line = triple(newe9placeHolder,
                                      cidocCoords.prefix + 'P26_moved_to',
                                      newLocationPlaceholder) + closeLine
                        output.write(line)

                    # E9 P27 E53

                    pastLocationLabel = row['PRCD' + f]

                    if row['PRCU' + f] != '':
                        pastLocationLabel = pastLocationLabel + ', ' + row['PRCU' + f]

                    if row['PRVC' + f] != '':
                        pastLocationLabel = pastLocationLabel + ', ' + row['PRVC' + f]

                    if row['PRVP' + f] != '':
                        pastLocationLabel = pastLocationLabel + ' (' + row['PRVP' + f] + ')'

                    if row['PRVR' + f] != '':
                        pastLocationLabel = pastLocationLabel + ', ' + row['PRVR' + f]

                    if row['PRVS' + f] != '':
                        pastLocationLabel = pastLocationLabel + ', ' + row['PRVS' + f]

                    line = triple(newe9placeHolder,
                                  cidocCoords.prefix + 'P27_moved_from',
                                  pastLocationPlaceholder) + closeLine
                    output.write(line)
                    line = triple(pastLocationPlaceholder,
                                  nsCoords.prefix + 'type',
                                  cidocCoords.prefix + 'E74_Group') + closeLine
                    output.write(line)
                    line = triple(pastLocationPlaceholder,
                                  schemaCoords.prefix + 'label',
                                  '\"' + pastLocationLabel + '\"') + closeLine
                    output.write(line)

            pastLocation = ''
            newLocation = ''
            pl = ''

            if row['LDCN'] != '':
                newLocation = ' a ' + row['LDCN']

            if row['PRCD' + last] != '':
                pastLocation = ' da ' + row['PRCD' + last]
                pl = row['PRCD' + last].replace(' ', '')

            line = triple(datplaceHolder,
                          cidocCoords.prefix + 'P25i_moved_by',
                          e9placeHolder) + closeLine
            output.write(line)
            line = triple(e9placeHolder,
                          nsCoords.prefix + 'type',
                          cidocCoords.prefix + 'E9_Move') + closeLine
            output.write(line)
            line = triple(e9placeHolder,
                          schemaCoords.prefix + 'label',
                          '\"Trasferimento di ' + row['SGTI'] + pastLocation +
                          newLocation + '\"') + closeLine
            output.write(line)

            timespan = ''
            ts = ''

            if row['PRDI' + last] != '':
                timespan = row['PRDI' + last]

            if row['PRDU' + last] != '':
                timespan = timespan + ' - ' + row['PRDU' + last]

            tt = timespan.replace(' ', '')
            ts = tt.replace('/', '')

            timespanPlaceholder = museoCoords.prefix + url + '_' + ts
            pastLocationPlaceholder = museoCoords.prefix + url + '_' + pl
            newLocationPlaceholder = e53placeHolder

            # E9 P4 E52

            line = triple(e9placeHolder,
                          cidocCoords.prefix + 'P4_has_time-span',
                          timespanPlaceholder) + closeLine
            output.write(line)
            line = triple(timespanPlaceholder,
                          nsCoords.prefix + 'type',
                          cidocCoords.prefix + 'E52_Time-Span') + closeLine
            output.write(line)
            line = triple(timespanPlaceholder,
                          schemaCoords.prefix + 'label',
                          '\"' + timespan + '\"') + closeLine
            output.write(line)

            # E9 P26 E53 (moved to)

            if newLocationPlaceholder != '':
                line = triple(e9placeHolder,
                              cidocCoords.prefix + 'P26_moved_to',
                              newLocationPlaceholder) + closeLine
                output.write(line)

            # E9 P27 E53

            pastLocationLabel = row['PRCD' + last] + ', ' + row['PRCU' + last] + ', ' + row['PRVC' + last] \
                                + ' (' + row['PRVP' + last] + '), ' + row['PRVR' + last] + \
                                ', ' + row['PRVS' + last]

            line = triple(e9placeHolder,
                          cidocCoords.prefix + 'P27_moved_from',
                          pastLocationPlaceholder) + closeLine
            output.write(line)
            line = triple(pastLocationPlaceholder,
                          nsCoords.prefix + 'type',
                          cidocCoords.prefix + 'E74_Group') + closeLine
            output.write(line)
            line = triple(pastLocationPlaceholder,
                          schemaCoords.prefix + 'label',
                          '\"' + pastLocationLabel + '\"') + closeLine
            output.write(line)

            output.write('\n')

        #
        #
        # Limit number of entries processed (if desired)
        if (ii > max_entries):
            break