{ "cells": [ { "cell_type": "code", "execution_count": 25, "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": 26, "metadata": {}, "outputs": [], "source": [ "import_dir = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/ASPO/CSV/datini/'\n", "export_dir = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/ASPO/RDF/datini/'" ] }, { "cell_type": "code", "execution_count": 27, "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", "\n", "# Repositories\n", "datiniCoords = RDFcoords('', 'dt:')\n", "# W3/CIDOC Predicates\n", "hasTypeCoords = RDFcoords('', 'tp:')\n", "hasTypePCoords = RDFcoords('', 'te:')\n", "carriesCoords = RDFcoords('', 'ca:')\n", "identifiedByCoords = RDFcoords('', 'ib:')\n", "labelCoords = RDFcoords('', 'lb:')\n", "hasNoteCoords = RDFcoords('', 'no:')\n", "hasTypeNCoords = RDFcoords('', 'tn:')\n", "hasCurrentPermanentLocationCoords = RDFcoords('', 'ap:')\n", "hasCurrentOwnerCoords = RDFcoords('', 'ow:')\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", "stringCoords = RDFcoords('', 'sr:', 'E62')\n", "placeCoords = RDFcoords('', 'pl:', 'E53')\n", "groupCoords = RDFcoords('', 'gp:', 'E74')" ] }, { "cell_type": "code", "execution_count": 28, "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": 29, "metadata": {}, "outputs": [], "source": [ "def writeTTLHeader(output):\n", " output.write('@prefix ' + datiniCoords.prefix + ' ' + datiniCoords.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 ' + typeCoords.prefix + ' ' + typeCoords.uri + closeLine)\n", " output.write('@prefix ' + hasNoteCoords.prefix + ' ' + hasNoteCoords.uri + closeLine)\n", " output.write('@prefix ' + hasTypeNCoords.prefix + ' ' + hasTypeNCoords.uri + closeLine)\n", " output.write('@prefix ' + stringCoords.prefix + ' ' + stringCoords.uri + closeLine)\n", " output.write('@prefix ' + hasCurrentPermanentLocationCoords.prefix + ' ' + hasCurrentPermanentLocationCoords.uri + closeLine)\n", " output.write('@prefix ' + placeCoords.prefix + ' ' + placeCoords.uri + closeLine)\n", " output.write('@prefix ' + hasCurrentOwnerCoords.prefix + ' ' + hasCurrentOwnerCoords.uri + closeLine)\n", " output.write('@prefix ' + groupCoords.prefix + ' ' + groupCoords.uri + closeLine)\n", " output.write('\\n')\n" ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [], "source": [ "filePrefix = 'data_'\n", "fileType = 'subfonds'\n", "max_entries = 1000000000\n", "\n", "with open(import_dir + filePrefix + fileType + '.csv', newline=\"\") as csv_file, open(export_dir + filePrefix + fileType + '.ttl', 'w') as output:\n", " reader = csv.DictReader(csv_file)\n", " writeTTLHeader(output)\n", " first = True\n", " ii = 0\n", " E74placeHolder = ''\n", " line = triple(E74placeHolder, hasTypeCoords.prefix, groupCoords.prefix ) + closeLine\n", " output.write(line) \n", " line = triple(E74placeHolder, labelCoords.prefix, \"\\\"Archivio di Stato di Prato\\\"\") + closeLine\n", " output.write(line)\n", " currentLocation = \"\\\"Fondo Datini, Archivio di Stato di Prato, Prato (PO)\\\"\"\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", " # E22 Man Made Object\n", " line = triple(datiniCoords.prefix + row['id'], hasTypeCoords.prefix, manMadeObjectCoords.prefix) + closeLine\n", " output.write(line)\n", " line = triple(datiniCoords.prefix + row['id'], labelCoords.prefix, '\\\"Documento fisico: ' + row['titolo_aspo'].replace('\\\\','\\\\\\\\').replace('\"','\\\\\"')+ '\\\"') + closeLine\n", " output.write(line)\n", " # E73 Information Object\n", " e73placeHolder = \"\"\n", " line = triple(datiniCoords.prefix + row['id'], carriesCoords.prefix, e73placeHolder) + closeLine\n", " output.write(line)\n", " line = triple(e73placeHolder, hasTypeCoords.prefix, informationObjectCoords.prefix) + closeLine\n", " output.write(line)\n", " line = triple(e73placeHolder, labelCoords.prefix, '\\\"Contenuto informativo: ' + row['titolo_aspo'].replace('\\\\','\\\\\\\\').replace('\"','\\\\\"')+ '\\\"') + closeLine\n", " output.write(line)\n", " # E35 Title \n", " if(row['titolo_aspo'] != 'None'):\n", " e35placeHolder1 = \"\"\n", " line = triple(e73placeHolder, identifiedByCoords.prefix, e35placeHolder1) + closeLine\n", " output.write(line)\n", " line = triple(e35placeHolder1, hasTypeCoords.prefix, titleCoords.prefix) + closeLine\n", " output.write(line)\n", " line = triple(e35placeHolder1, labelCoords.prefix, '\\\"' + row['titolo_aspo'].replace('\\\\','\\\\\\\\').replace('\"','\\\\\"')+ '\\\"') + closeLine\n", " output.write(line)\n", " # E55 Type\n", " if(row['genere'] != ''):\n", " tipologie = []\n", " pipe = \"|\" \n", " if pipe in row['genere']:\n", " tipologie = row['genere'].split('|')\n", " for type in tipologie:\n", " tipo = type\n", " e55placeHolder = \"\"\n", " line = triple(datiniCoords.prefix + row['id'], hasTypePCoords.prefix, e55placeHolder) + closeLine\n", " output.write(line)\n", " else:\n", " e55placeHolder = \"\"\n", " line = triple(datiniCoords.prefix + row['id'], hasTypePCoords.prefix, e55placeHolder) + closeLine\n", " output.write(line)\n", " # E42 Identifier\n", " e42placeHolderID = \"\"\n", " line = triple(datiniCoords.prefix + row['id'], identifiedByCoords.prefix, e42placeHolderID) + closeLine\n", " output.write(line)\n", " line = triple(e42placeHolderID, hasTypeCoords.prefix, identifierCoords.prefix) + closeLine\n", " output.write(line)\n", " line = triple(e42placeHolderID, labelCoords.prefix, '\\\"' + row['id'].replace(\" \", \"\") + '\\\"') + closeLine \n", " output.write(line) \n", " # E22 - P52 - E74\n", " line = triple(datiniCoords.prefix + row['id'], hasCurrentOwnerCoords.prefix, E74placeHolder) + closeLine\n", " output.write(line)\n", " # E22 - P54 - E53\n", " line = triple(datiniCoords.prefix + row['id'], hasCurrentPermanentLocationCoords.prefix, currentLocation) + closeLine\n", " output.write(line)\n", " output.write('\\n')\n", " #\n", " # Limit number of entries processed (if desired)\n", " if(ii>max_entries):\n", " break\n", " " ] } ], "metadata": { "interpreter": { "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49" }, "kernelspec": { "display_name": "Python 3.9.0 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": "3.10.4" }, "metadata": { "interpreter": { "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6" } } }, "nbformat": 4, "nbformat_minor": 2 }