|
|
@@ -1,205 +0,0 @@
|
|
|
-{
|
|
|
- "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/datini/'\n",
|
|
|
- "export_dir = '/Users/federicaspinelli/Google Drive/OVI:CNR/RDF/ASPO/datini/'"
|
|
|
- ]
|
|
|
- },
|
|
|
- {
|
|
|
- "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",
|
|
|
- "\n",
|
|
|
- "# Repositories\n",
|
|
|
- "datiniCoords = RDFcoords('<http://datini.archiviodistato.prato.it/la-ricerca/scheda/>', 'dt:')\n",
|
|
|
- "# W3/CIDOC Predicates\n",
|
|
|
- "hasTypeCoords = RDFcoords('<http://www.w3.org/1999/02/22-rdf-syntax-ns#type>', 'tp:')\n",
|
|
|
- "hasTypePCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/P2_has_type>', 'te:')\n",
|
|
|
- "carriesCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/P128_carries>', 'ca:')\n",
|
|
|
- "identifiedByCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/P1_is_identified_by>', 'ib:')\n",
|
|
|
- "labelCoords = RDFcoords('<http://www.w3.org/2000/01/rdf-schema#label>', 'lb:')\n",
|
|
|
- "\n",
|
|
|
- "# CIDOC Objects\n",
|
|
|
- "manMadeObjectCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/E22_Man-Made_Object>', 'mo:', 'E22')\n",
|
|
|
- "informationObjectCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/E73_Information_Object>', 'io:', 'E73')\n",
|
|
|
- "titleCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/E35_Title>', 'ti:' ,'E35')\n",
|
|
|
- "placeAppellationCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/E44_Place_appellation>', 'pa:', 'E44')\n",
|
|
|
- "identifierCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/E42_Identifier>', 'id:', 'E42')\n",
|
|
|
- "typeCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/E55_Type>', 'ty:', 'E55')"
|
|
|
- ]
|
|
|
- },
|
|
|
- {
|
|
|
- "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 ' + 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('\\n')\n"
|
|
|
- ]
|
|
|
- },
|
|
|
- {
|
|
|
- "cell_type": "code",
|
|
|
- "execution_count": 24,
|
|
|
- "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",
|
|
|
- " 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",
|
|
|
- " # Write E22 Man Made Object & E73 Information Object -- should exist for every entry?\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",
|
|
|
- " e37placeHolder = \"<http://datini.archiviodistato.prato.it/la-ricerca/scheda/\" + row['id'] + \"/\" + informationObjectCoords.code + \">\"\n",
|
|
|
- " line = triple(datiniCoords.prefix + row['id'], carriesCoords.prefix, e37placeHolder) + closeLine\n",
|
|
|
- " output.write(line)\n",
|
|
|
- " line = triple(e37placeHolder, hasTypeCoords.prefix, informationObjectCoords.prefix) + closeLine\n",
|
|
|
- " output.write(line)\n",
|
|
|
- " line = triple(e37placeHolder, labelCoords.prefix, '\\\"Contenuto informativo: ' + row['titolo_aspo'].replace('\\\\','\\\\\\\\').replace('\"','\\\\\"')+ '\\\"') + closeLine\n",
|
|
|
- " output.write(line)\n",
|
|
|
- " #\n",
|
|
|
- " # If the 'titolo_aspo' property is not empty for the given entry, write down title-related triples\n",
|
|
|
- " if(row['titolo_aspo'] != 'None'):\n",
|
|
|
- " e35placeHolder1 = \"<http://datini.archiviodistato.prato.it/la-ricerca/scheda/\" + row['id'] + \"/\" + titleCoords.code + \">\"\n",
|
|
|
- " line = triple(e37placeHolder, 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",
|
|
|
- " \n",
|
|
|
- " output.write('\\n')\n",
|
|
|
- " #\n",
|
|
|
- " #\n",
|
|
|
- " # Limit number of entries processed (if desired)\n",
|
|
|
- " if(ii>max_entries):\n",
|
|
|
- " break\n",
|
|
|
- " "
|
|
|
- ]
|
|
|
- }
|
|
|
- ],
|
|
|
- "metadata": {
|
|
|
- "interpreter": {
|
|
|
- "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
|
|
|
- },
|
|
|
- "kernelspec": {
|
|
|
- "display_name": "Python 3",
|
|
|
- "language": "python",
|
|
|
- "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": "3.8.10"
|
|
|
- },
|
|
|
- "metadata": {
|
|
|
- "interpreter": {
|
|
|
- "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
|
|
|
- }
|
|
|
- }
|
|
|
- },
|
|
|
- "nbformat": 4,
|
|
|
- "nbformat_minor": 2
|
|
|
-}
|
