{ "cells": [ { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [], "source": [ "# Utilities to read/write csv files\n", "import csv\n", "# Utilities to handle character encodings\n", "import unicodedata\n", "# Ordered Dicts\n", "from collections import OrderedDict\n", "\n", "import json\n", "\n", "\n", "# OPZIONAL IMPORTS\n", "\n", "# For timestamping/simple speed tests\n", "from datetime import datetime\n", "# Random number generator\n", "from random import *\n", "# System & command line utilities\n", "import sys\n", "# Json for the dictionary\n", "import json" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [], "source": [ "import_dir = '/Users/federicaspinelli/Google Drive/OVI-CNR/CSV/ASPO/gettatelli/'\n", "export_dir = '/Users/federicaspinelli/Google Drive/OVI-CNR/RDF/ASPO/gettatelli/'" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [], "source": [ "# Custom class to store URIs + related infos for the ontologies/repositories\n", "\n", "class RDFcoords:\n", " def __init__(self, uri, prefix, code = None):\n", " self.uri = uri\n", " self.prefix = prefix\n", " self.code = code\n", "\n", "# Repositories\n", "datiniCoords = RDFcoords('', 'dt:')\n", "personAuthCoords = RDFcoords('', 'pa:')\n", "# W3/CIDOC Predicates\n", "hasTypeCoords = RDFcoords('', 'tp:')\n", "hasNoteCoords = RDFcoords('', 'no:')\n", "hasTypePCoords = RDFcoords('', 'te:')\n", "carriesCoords = RDFcoords('', 'ca:')\n", "identifiedByCoords = RDFcoords('', 'ib:')\n", "labelCoords = RDFcoords('', 'lb:')\n", "wasBroughtCoords = RDFcoords('', 'wb:')\n", "wasBornCoords = RDFcoords('', 'wbc:')\n", "diedCoords = RDFcoords('', 'di:')\n", "wasPresentCoords = RDFcoords('', 'wp:')\n", "carriedByCoords = RDFcoords('', 'cb:')\n", "noteCoords = RDFcoords('', 'nt:')\n", "hasTimeSpanCoords = RDFcoords('', 'hs:')\n", "consistCoords = RDFcoords('', 'cf:')\n", "hasConditionCoords = RDFcoords('', 'hc:')\n", "foafCoords = RDFcoords('', 'foaf:')\n", "nsCoords = RDFcoords('', 'rdf:')\n", "\n", "# CIDOC Objects\n", "manMadeObjectCoords = RDFcoords('', 'mo:', 'E22')\n", "informationObjectCoords = RDFcoords('', 'io:', 'E73')\n", "titleCoords = RDFcoords('', 'ti:' ,'E35')\n", "placeAppellationCoords = RDFcoords('', 'pa:', 'E44')\n", "identifierCoords = RDFcoords('', 'id:', 'E42')\n", "typeCoords = RDFcoords('', 'ty:', 'E55')\n", "creationCoords = RDFcoords('', 'cr:', 'E65')\n", "personCoords = RDFcoords('', 'ps:', 'E21')\n", "stringCoords = RDFcoords('', 'st:', 'E62')\n", "birthCoords = RDFcoords('', 'th:', 'E67')\n", "deathCoords = RDFcoords('', 'dh:', 'E69')\n", "timeSpanCoords = RDFcoords('', 'ts:', 'E52')\n", "materialCoords = RDFcoords('', 'mt:', 'E57')\n", "conditionCoords = RDFcoords('', 'cs:', 'E3')\n", "entityCoords = RDFcoords('', 'ey:', 'E1')\n", "refersCoords = RDFcoords('', 'rt:')\n", "refersHasTypeCoords = RDFcoords('', 'rh:')\n", "\n" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [], "source": [ "# Basic functions for triples / shortened triples in TTL format\n", "\n", "def triple(subject, predicate, object1):\n", " line = subject + ' ' + predicate + ' ' + object1\n", " return line\n", "\n", "def doublet(predicate, object1):\n", " line = ' ' + predicate + ' ' + object1\n", " return line\n", "\n", "def singlet(object1):\n", " line = ' ' + object1\n", " return line\n", "\n", "# Line endings in TTL format\n", "continueLine1 = ' ;\\n'\n", "continueLine2 = ' ,\\n'\n", "closeLine = ' .\\n'" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [], "source": [ "def writeTTLHeader(output):\n", " output.write('@prefix ' + datiniCoords.prefix + ' ' + datiniCoords.uri + closeLine)\n", " output.write('@prefix ' + personAuthCoords.prefix + ' ' + personAuthCoords.uri + closeLine)\n", " output.write('@prefix ' + hasTypeCoords.prefix + ' ' + hasTypeCoords.uri + closeLine)\n", " output.write('@prefix ' + hasTypePCoords.prefix + ' ' + hasTypePCoords.uri + closeLine)\n", " output.write('@prefix ' + manMadeObjectCoords.prefix + ' ' + manMadeObjectCoords.uri + closeLine)\n", " output.write('@prefix ' + carriesCoords.prefix + ' ' + carriesCoords.uri + closeLine)\n", " output.write('@prefix ' + informationObjectCoords.prefix + ' ' + informationObjectCoords.uri + closeLine)\n", " output.write('@prefix ' + identifiedByCoords.prefix + ' ' + identifiedByCoords.uri + closeLine)\n", " output.write('@prefix ' + titleCoords.prefix + ' ' + titleCoords.uri + closeLine)\n", " output.write('@prefix ' + labelCoords.prefix + ' ' + labelCoords.uri + closeLine)\n", " output.write('@prefix ' + identifierCoords.prefix + ' ' + identifierCoords.uri + closeLine)\n", " output.write('@prefix ' + wasBroughtCoords.prefix + ' ' + wasBroughtCoords.uri + closeLine)\n", " output.write('@prefix ' + typeCoords.prefix + ' ' + typeCoords.uri + closeLine)\n", " output.write('@prefix ' + carriedByCoords.prefix + ' ' + carriedByCoords.uri + closeLine)\n", " output.write('@prefix ' + personCoords.prefix + ' ' + personCoords.uri + closeLine)\n", " output.write('@prefix ' + stringCoords.prefix + ' ' + stringCoords.uri + closeLine)\n", " output.write('@prefix ' + noteCoords.prefix + ' ' + noteCoords.uri + closeLine)\n", " output.write('@prefix ' + wasBornCoords.prefix + ' ' + wasBornCoords.uri + closeLine)\n", " output.write('@prefix ' + diedCoords.prefix + ' ' + diedCoords.uri + closeLine)\n", " output.write('@prefix ' + wasPresentCoords.prefix + ' ' + wasPresentCoords.uri + closeLine)\n", " output.write('@prefix ' + birthCoords.prefix + ' ' + birthCoords.uri + closeLine)\n", " output.write('@prefix ' + deathCoords.prefix + ' ' + deathCoords.uri + closeLine)\n", " output.write('@prefix ' + hasTimeSpanCoords.prefix + ' ' + hasTimeSpanCoords.uri + closeLine)\n", " output.write('@prefix ' + timeSpanCoords.prefix + ' ' + timeSpanCoords.uri + closeLine)\n", " output.write('@prefix ' + materialCoords.prefix + ' ' + materialCoords.uri + closeLine)\n", " output.write('@prefix ' + consistCoords.prefix + ' ' + consistCoords.uri + closeLine)\n", " output.write('@prefix ' + conditionCoords.prefix + ' ' + conditionCoords.uri + closeLine)\n", " output.write('@prefix ' + hasConditionCoords.prefix + ' ' + hasConditionCoords.uri + closeLine)\n", " output.write('@prefix ' + refersCoords.prefix + ' ' + refersCoords.uri + closeLine) \n", " output.write('@prefix ' + entityCoords.prefix + ' ' + entityCoords.uri + closeLine)\n", " output.write('@prefix ' + refersHasTypeCoords.prefix + ' ' + refersHasTypeCoords.uri + closeLine)\n", " output.write('@prefix ' + hasNoteCoords.prefix + ' ' + hasNoteCoords.uri + closeLine)\n", " output.write('@prefix ' + creationCoords.prefix + ' ' + creationCoords.uri + closeLine)\n", " output.write('@prefix ' + foafCoords.prefix + ' ' + foafCoords.uri + closeLine)\n", " output.write('@prefix ' + nsCoords.prefix + ' ' + nsCoords.uri + closeLine)\n", "\n", " output.write('\\n')\n" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [], "source": [ "filePrefix = 'data_'\n", "fileType = 'item'\n", "max_entries = 1000000000\n", "\n", "with open(import_dir + filePrefix + fileType + '.csv', newline=\"\") as csv_file, open(export_dir + filePrefix + fileType + '_person.ttl', 'w') as output:\n", " reader = csv.DictReader(csv_file)\n", " writeTTLHeader(output)\n", " first = True\n", " ii = 0\n", " for row in reader:\n", " # The index ii is used to process a limited number of entries for testing purposes\n", " ii = ii+1\n", " # Skip the first line as it carries info we don't want to triplify\n", " if(first):\n", " first = False\n", " continue\n", " \n", " e21placeHolder = ''\n", " e22placeHolder = \"\"\n", " e65placeHolder = \"\"\n", "\n", " line = triple(e65placeHolder, refersCoords.prefix, e21placeHolder) + closeLine\n", " output.write(line)\n", " e55placeHolder = '\"\n", " line = triple(e21placeHolder, hasTypePCoords.prefix, e55placeHolder) + closeLine\n", " output.write(line)\n", " line = triple(e55placeHolder, labelCoords.prefix, '\\\"Gettatello\\\"') + closeLine\n", " output.write(line)\n", " \n", " # If the 'persname' property is not empty for the given entry, write down triples\n", " bambino = ''\n", " if(row['cognome_bambino'] != ''):\n", " bambino = bambino + row['cognome_bambino'] + ' '\n", " if(row['nome_bambino'] != ''):\n", " bambino = bambino + row['nome_bambino']\n", " if(bambino != ''):\n", " line = triple(e21placeHolder, hasTypeCoords.prefix, personCoords.prefix) + closeLine\n", " output.write(line)\n", " line = triple(e21placeHolder, foafCoords.prefix + 'givenName', '\\\"' + bambino + '\\\"') + closeLine\n", " output.write(line)\n", " line = triple(e21placeHolder, labelCoords.prefix, '\\\"' + bambino + '\\\"') + closeLine\n", " output.write(line)\n", " e62placeHolder = ''\n", " line = triple(e21placeHolder, noteCoords.prefix, e62placeHolder) + closeLine\n", " output.write(line)\n", " line = triple(e62placeHolder, hasTypeCoords.prefix, stringCoords.prefix) + closeLine\n", " output.write(line)\n", " line = triple(e62placeHolder, labelCoords.prefix, '\\\"Fonte: Archivio di Stato di Prato - Fondo Ospedale della Misericordia e Dolce\\\"') + closeLine\n", " output.write(line)\n", "\n", " #Matricola Bambino\n", " e42placeHolder = ''\n", " if(row['matricola'] != ''):\n", " line = triple(e21placeHolder, identifiedByCoords.prefix, e42placeHolder) + closeLine\n", " output.write(line)\n", " line = triple(e42placeHolder, hasTypeCoords.prefix, identifierCoords.prefix) + closeLine\n", " output.write(line)\n", " line = triple(e42placeHolder, labelCoords.prefix, '\\\"Matricola: ' + row['matricola'] + '\\\"') + closeLine\n", " output.write(line)\n", " \n", " #Nascita\n", " if row['data_nascita'] != '':\n", " e67placeHolder = ''\n", " line = triple(e21placeHolder, wasBornCoords.prefix, e67placeHolder) + closeLine\n", " output.write(line)\n", " line = triple(e67placeHolder, hasTypeCoords.prefix, birthCoords.prefix) + closeLine\n", " output.write(line)\n", " line = triple(e67placeHolder, labelCoords.prefix, '\\\"Nascita di ' + bambino + '\\\"') + closeLine\n", " output.write(line)\n", "\n", " e52NplaceHolder = ''\n", " \n", " line = triple(e67placeHolder, hasTimeSpanCoords.prefix, e52NplaceHolder) + closeLine\n", " output.write(line)\n", " line = triple(e52NplaceHolder, hasTypeCoords.prefix, timeSpanCoords.prefix ) + closeLine\n", " output.write(line)\n", " line = triple(e52NplaceHolder, labelCoords.prefix, '\\\"' + row['data_nascita'] + '\\\"' ) + closeLine\n", " output.write(line)\n", "\n", " #Morte\n", " if row['data_morte'] != '':\n", " e69placeHolder = ''\n", " line = triple(e21placeHolder, diedCoords.prefix, e69placeHolder) + closeLine\n", " output.write(line)\n", " line = triple(e69placeHolder, hasTypeCoords.prefix, deathCoords.prefix) + closeLine\n", " output.write(line)\n", " line = triple(e69placeHolder, labelCoords.prefix, '\\\"Morte di ' + bambino + '\\\"') + closeLine\n", " output.write(line)\n", " \n", " e52MplaceHolder = ''\n", " \n", " line = triple(e69placeHolder, hasTimeSpanCoords.prefix, e52MplaceHolder) + closeLine\n", " output.write(line)\n", " line = triple(e52MplaceHolder, hasTypeCoords.prefix, timeSpanCoords.prefix ) + closeLine\n", " output.write(line)\n", " line = triple(e52MplaceHolder, labelCoords.prefix, '\\\"' + row['data_morte'] + '\\\"' ) + closeLine\n", " output.write(line)\n", " \n", " #Ritrovamento\n", " if row['data_ritrovamento'] != '':\n", " e5placeHolder = ''\n", " line = triple(e5placeHolder, labelCoords.prefix, '\\\"Ritrovamento\\\"') + closeLine\n", " output.write(line)\n", " line = triple(e21placeHolder, wasPresentCoords.prefix, e5placeHolder) + closeLine\n", " output.write(line)\n", " e5RplaceHolder = ''\n", " line = triple(e5RplaceHolder, nsCoords.prefix + 'type', '\\\"Ritrovamento\\\"') + closeLine\n", " output.write(line)\n", " line = triple(e5placeHolder, hasTypeCoords.prefix, '\\\"Ritrovamento di ' + bambino + '\\\"') + closeLine\n", " output.write(line)\n", "\n", " e52RplaceHolder = ''\n", " line = triple(e5placeHolder, hasTimeSpanCoords.prefix, e52RplaceHolder) + closeLine\n", " output.write(line)\n", " line = triple(e52RplaceHolder, hasTypeCoords.prefix, timeSpanCoords.prefix ) + closeLine\n", " output.write(line)\n", " line = triple(e52RplaceHolder, labelCoords.prefix, '\\\"' + row['data_ritrovamento'] + '\\\"' ) + closeLine\n", " output.write(line)\n", "\n", " #Ricongiungimento\n", " if row['data_ricongiungimento'] != '':\n", " e5placeHolder = ''\n", " line = triple(e21placeHolder, wasPresentCoords.prefix, e5placeHolder) + closeLine\n", " output.write(line)\n", " e5RCplaceHolder = ''\n", " line = triple(e5RCplaceHolder, nsCoords.prefix + 'type', '\\\"Ricongiungimento\\\"') + closeLine\n", " output.write(line)\n", " line = triple(e5placeHolder, labelCoords.prefix, '\\\"Ricongiungimento\\\"') + closeLine\n", " output.write(line)\n", " line = triple(e5placeHolder, hasTypeCoords.prefix, '\\\"Ricongiungimento di ' + bambino + '\\\"') + closeLine\n", " output.write(line)\n", "\n", " e52RCplaceHolder = '' \n", " line = triple(e5placeHolder, hasTimeSpanCoords.prefix, e52RCplaceHolder) + closeLine\n", " output.write(line)\n", " line = triple(e52RCplaceHolder, hasTypeCoords.prefix, timeSpanCoords.prefix ) + closeLine\n", " output.write(line)\n", " line = triple(e52RCplaceHolder, labelCoords.prefix, '\\\"' + row['data_ricongiungimento'] + '\\\"' ) + closeLine\n", " output.write(line)\n", " \n", " #Adozione\n", " if row['data_adozione'] != '':\n", " e5placeHolder = ''\n", " line = triple(e21placeHolder, wasPresentCoords.prefix, e5placeHolder) + closeLine\n", " output.write(line)\n", " e5AplaceHolder = ''\n", " line = triple(e5AplaceHolder, nsCoords.prefix + 'type', '\\\"Adozione\\\"') + closeLine\n", " output.write(line)\n", " line = triple(e5placeHolder, labelCoords.prefix, '\\\"Adozione\\\"') + closeLine\n", " output.write(line)\n", " line = triple(e5placeHolder, hasTypeCoords.prefix, '\\\"Adozione di ' + bambino + '\\\"') + closeLine\n", " output.write(line)\n", "\n", " e52AplaceHolder = ''\n", " line = triple(e5placeHolder, hasTimeSpanCoords.prefix, e52AplaceHolder) + closeLine\n", " output.write(line)\n", " line = triple(e52AplaceHolder, hasTypeCoords.prefix, timeSpanCoords.prefix ) + closeLine\n", " output.write(line)\n", " line = triple(e52AplaceHolder, labelCoords.prefix, '\\\"' + row['data_adozione'] + '\\\"' ) + closeLine\n", " output.write(line)\n", "\n", " #Anno unico\n", " e52UplaceHolder = ''\n", " line = triple(e52UplaceHolder, refersCoords.prefix, e21placeHolder, ) + closeLine\n", " output.write(line) \n", " line = triple(e52UplaceHolder, hasTimeSpanCoords.prefix, '\\\"' + row['data_periodo'] + '\\\"') + closeLine\n", " output.write(line)\n", " line = triple(e52UplaceHolder, labelCoords.prefix, '\\\"' + row['data_periodo'] + '\\\"') + closeLine\n", " output.write(line)\n", " line = triple(e52UplaceHolder, hasTypeCoords.prefix, timeSpanCoords.prefix ) + closeLine\n", " output.write(line)\n", "\n", " output.write('\\n')\n", " #\n", " #\n", " # Limit number of entries processed (if desired)\n", " if(ii>max_entries):\n", " break\n", " " ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "interpreter": { "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6" }, "kernelspec": { "display_name": "Python 3.7.3 64-bit", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.0" }, "metadata": { "interpreter": { "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6" } } }, "nbformat": 4, "nbformat_minor": 2 }