From 7358191a1c2fed93ab18d2b11332f858a3ac4fce Mon Sep 17 00:00:00 2001
From: Muhammad <boukerfa.ma@gmail.com>
Date: Fri, 18 Oct 2024 14:54:32 +0100
Subject: [PATCH 01/15] lov migrator script initialization

---
 bin/lov_migrator | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)
 create mode 100644 bin/lov_migrator

diff --git a/bin/lov_migrator b/bin/lov_migrator
new file mode 100644
index 00000000..6889c582
--- /dev/null
+++ b/bin/lov_migrator
@@ -0,0 +1,28 @@
+#!/usr/bin/env ruby
+
+# Exit cleanly from an early interrupt
+Signal.trap("INT") { exit 1 }
+
+require 'optparse'
+
+
+options = {}
+OptionParser.new do |opts|
+  opts.banner = "Usage: lov_migrator [options]"
+  opts.on( '-a', '--all') do 
+    options[:vocabs] = [:all]
+  end
+  opts.on('-v', '--vocabularies PREFIX1, PREFIX2', 'Comma-separated list of vocabularies to update or import') do |acronym|
+    ontologies_acronyms = acronym
+  end
+
+  # Display the help screen, all programs are assumed to have this option.
+  opts.on( '-h', '--help', 'Display this screen' ) do
+    puts opts
+    exit
+  end
+end.parse!
+
+
+raise OptionParser::MissingArgument if options[:vocabs].nil?
+

From d379d06a507773b7cc2101fa8aea9a259a8dd25e Mon Sep 17 00:00:00 2001
From: Muhammad <boukerfa.ma@gmail.com>
Date: Fri, 18 Oct 2024 15:17:31 +0100
Subject: [PATCH 02/15] adding notation3 file parsing in lov migrator

---
 bin/lov_migrator | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)
 mode change 100644 => 100755 bin/lov_migrator

diff --git a/bin/lov_migrator b/bin/lov_migrator
old mode 100644
new mode 100755
index 6889c582..c189d733
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -26,3 +26,40 @@ end.parse!
 
 raise OptionParser::MissingArgument if options[:vocabs].nil?
 
+require 'rdf'
+require 'rdf/n3'
+
+
+def parse_n3_file(file_path)
+  graph = RDF::Graph.new
+  RDF::N3::Reader.open(file_path) do |reader|
+    reader.each_statement do |statement|
+      graph << statement
+    end
+  end
+  graph
+end
+
+
+def find_vocabularies(graph)
+  vocab_type = RDF::URI("http://purl.org/vocommons/voaf#Vocabulary")
+  graph.query([nil, RDF.type, vocab_type]).map(&:subject)
+end
+
+
+def main
+  graph = parse_n3_file('lov.n3')
+  
+  vocab_uris = find_vocabularies(graph)
+  
+  if vocab_uris.empty?
+    puts "No vocabularies found in the file."
+  else
+    puts "Found #{vocab_uris.size} vocabularies:\n\n"
+    vocab_uris.each do |vocab_uri|
+      puts vocab_uri
+    end
+  end  
+end
+
+main
\ No newline at end of file

From dd23c7f067263fc3ff9728a245bc56b5dbab945b Mon Sep 17 00:00:00 2001
From: Muhammad <boukerfa.ma@gmail.com>
Date: Fri, 18 Oct 2024 15:31:35 +0100
Subject: [PATCH 03/15] Add RDF vocabulary metadata extraction and mapping to
 ruby object

---
 bin/lov_migrator | 99 +++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 98 insertions(+), 1 deletion(-)

diff --git a/bin/lov_migrator b/bin/lov_migrator
index c189d733..448d0781 100755
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -41,11 +41,107 @@ def parse_n3_file(file_path)
 end
 
 
+def extract_uri_or_value(node)
+  case node
+  when RDF::URI
+    node.to_s
+  when RDF::Literal
+    if node.has_language?
+      { value: node.object, language: node.language.to_s }
+    else
+      node.object
+    end
+  else
+    node.to_s
+  end      
+end
+
+def extract_distribution_info(graph, distribution_uri)
+  info_distribution = {
+    uri: distribution_uri,
+    issued: graph.query([distribution_uri, RDF::URI("http://purl.org/dc/terms/issued"), nil]).first&.object,
+    language: graph.query([distribution_uri, RDF::URI("http://purl.org/dc/terms/language"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+    title: graph.query([distribution_uri, RDF::URI("http://purl.org/dc/terms/title"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+    # Relations
+    extends: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#extends"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+    specializes: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#specializes"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+    generalizes: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#generalizes"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+    hasEquivalencesWith: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#hasEquivalencesWith"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+    hasDisjunctionsWith: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#hasDisjunctionsWith"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+    metadataVoc: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#metadataVoc"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+    imports: graph.query([distribution_uri, RDF::URI("http://www.w3.org/2002/07/owl#imports"), nil]).map { |statement| extract_uri_or_value(statement.object) }
+  }
+  info_distribution
+end
+
+
+def extract_vocabulary_info(graph, vocab_uri)
+  info = {
+    uri: vocab_uri,
+    namespace: graph.query([vocab_uri, RDF::URI("http://purl.org/vocab/vann/preferredNamespaceUri"), nil]).first&.object, 
+    prefix: graph.query([vocab_uri, RDF::URI("http://purl.org/vocab/vann/preferredNamespacePrefix"), nil]).first&.object,
+    title: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/title"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+    description: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/description"), nil]).map { |statement| extract_uri_or_value(statement.object) }, 
+    keyword: graph.query([vocab_uri, RDF::URI("http://www.w3.org/ns/dcat#keyword"), nil]).map(&:object),
+    issued: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/issued"), nil]).first&.object,
+    modified: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/modified"), nil]).first&.object,
+    isDefinedBy: graph.query([vocab_uri, RDF::URI("http://www.w3.org/2000/01/rdf-schema#isDefinedBy"), nil]).first&.object,
+    homepage: graph.query([vocab_uri, RDF::URI("http://xmlns.com/foaf/0.1/homepage"), nil]).first&.object,
+    creator: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/creator"), nil]).first&.object,
+    contributor: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/contributor"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+    publisher: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/publisher"), nil]).first&.object,
+    language: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/language"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+
+    type: graph.query([vocab_uri, RDF.type, nil]).first&.object,
+
+    occurrences: graph.query([vocab_uri, RDF::URI("http://purl.org/vocommons/voaf#occurrencesInDatasets"), nil]).first&.object,
+    reused_by_datasets: graph.query([vocab_uri, RDF::URI("http://purl.org/vocommons/voaf#reusedByDatasets"), nil]).first&.object,
+    reused_by_vocabs: graph.query([vocab_uri, RDF::URI("http://purl.org/vocommons/voaf#reusedByVocabularies"), nil]).first&.object,
+    distribution: graph.query([vocab_uri, RDF::URI("http://www.w3.org/ns/dcat#distribution"), nil]).first&.object,
+  }
+
+  review = graph.query([vocab_uri, RDF::URI("http://purl.org/stuff/rev#hasReview"), nil]).first&.object
+  if review
+    info[:review] = {
+      creator: graph.query([review, RDF::URI("http://purl.org/dc/terms/creator"), nil]).first&.object,
+      date: graph.query([review, RDF::URI("http://purl.org/dc/terms/date"), nil]).first&.object,
+      text: graph.query([review, RDF::URI("http://purl.org/stuff/rev#text"), nil]).first&.object
+    }
+  end
+
+  info
+end
+
+
 def find_vocabularies(graph)
   vocab_type = RDF::URI("http://purl.org/vocommons/voaf#Vocabulary")
   graph.query([nil, RDF.type, vocab_type]).map(&:subject)
 end
 
+def format_value(value)
+  case value
+  when Array
+    value.map { |v| format_value(v) }.join("\n")
+  when Hash
+    if value[:language]
+      "\"#{value[:value]}\"@#{value[:language]}"
+    else
+      value.to_s
+    end
+  else
+    value.to_s.empty? ? "None" : value.to_s
+  end
+end
+
+
+def print_vocabulary_info(info)
+  puts "-------------------------------------------------------------------"
+  info.each do |key, value|
+    formatted_key = key.to_s.split('_').map(&:capitalize).join(' ')
+    puts "#{formatted_key}: #{format_value(value)}"
+  end
+  puts "\n"
+end
 
 def main
   graph = parse_n3_file('lov.n3')
@@ -57,7 +153,8 @@ def main
   else
     puts "Found #{vocab_uris.size} vocabularies:\n\n"
     vocab_uris.each do |vocab_uri|
-      puts vocab_uri
+      vocab_info = extract_vocabulary_info(graph, vocab_uri)
+      print_vocabulary_info(vocab_info)
     end
   end  
 end

From 255971c0e1ba8e40123ed189c46740d64b16b059 Mon Sep 17 00:00:00 2001
From: Muhammad <boukerfa.ma@gmail.com>
Date: Fri, 18 Oct 2024 18:34:01 +0100
Subject: [PATCH 04/15] add csv export for vocabularies metadata

---
 bin/lov_migrator | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/bin/lov_migrator b/bin/lov_migrator
index 448d0781..5d4e50be 100755
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -28,6 +28,11 @@ raise OptionParser::MissingArgument if options[:vocabs].nil?
 
 require 'rdf'
 require 'rdf/n3'
+require 'csv'
+
+CSV_MAIN_ATTRS = [:prefix, :title, :description, :keyword, :uri, :modified]
+CSV_FILENAME = "vocabs.csv"
+
 
 
 def parse_n3_file(file_path)
@@ -41,6 +46,20 @@ def parse_n3_file(file_path)
 end
 
 
+def initialize_csv(filename)
+  CSV.open(filename, "w", force_quotes: true) do |csv|
+    csv << CSV_MAIN_ATTRS  # Write header row
+  end
+end
+
+def append_to_csv(obj, filename)
+  CSV.open(filename, "a", force_quotes: true) do |csv|
+    filtered_row = CSV_MAIN_ATTRS.map { |attr| format_value(obj[attr]) }
+    csv << filtered_row
+  end
+end
+
+
 def extract_uri_or_value(node)
   case node
   when RDF::URI
@@ -144,6 +163,10 @@ def print_vocabulary_info(info)
 end
 
 def main
+
+
+  initialize_csv(CSV_FILENAME)
+
   graph = parse_n3_file('lov.n3')
   
   vocab_uris = find_vocabularies(graph)
@@ -154,6 +177,8 @@ def main
     puts "Found #{vocab_uris.size} vocabularies:\n\n"
     vocab_uris.each do |vocab_uri|
       vocab_info = extract_vocabulary_info(graph, vocab_uri)
+      append_to_csv(vocab_info, CSV_FILENAME)
+
       print_vocabulary_info(vocab_info)
     end
   end  

From 9cefc653b04807b0d73ede731f1c5d9f40628ed7 Mon Sep 17 00:00:00 2001
From: Muhammad <boukerfa.ma@gmail.com>
Date: Fri, 18 Oct 2024 19:03:12 +0100
Subject: [PATCH 05/15] add vocabularies dump file download + check for changes
 in vocabs before executing

---
 bin/lov_migrator | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/bin/lov_migrator b/bin/lov_migrator
index 5d4e50be..8884f909 100755
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -30,6 +30,10 @@ require 'rdf'
 require 'rdf/n3'
 require 'csv'
 
+require 'open-uri'
+require 'digest'
+
+
 CSV_MAIN_ATTRS = [:prefix, :title, :description, :keyword, :uri, :modified]
 CSV_FILENAME = "vocabs.csv"
 
@@ -45,6 +49,44 @@ def parse_n3_file(file_path)
   graph
 end
 
+def download_file(url, destination)
+  URI.open(url) do |file|
+    File.open(destination, 'wb') do |output|
+      output.write(file.read)
+    end
+  end
+  puts "File downloaded successfully as #{destination}"
+end
+
+def file_hash(file_path)
+  Digest::SHA256.file(file_path).hexdigest
+end
+
+def files_identical?(file1, file2)
+  File.exist?(file2) && file_hash(file1) == file_hash(file2)
+end
+
+# Updates the local file if the downloaded file is different
+def update_local_file(url, local_file_path)
+  downloaded_file_name = 'lov.n3.gz.tmp'
+  
+  download_file(url, downloaded_file_name)
+
+  if files_identical?(downloaded_file_name, local_file_path)
+    File.delete(downloaded_file_name) # Clean up the temporary file
+    return false
+  else
+    File.rename(downloaded_file_name, local_file_path) # Replace the old file with the new one
+    # decompress the doanloaded zip    
+    Zlib::GzipReader.open(local_file_path) do |gzip|
+      File.open('lov.n3', 'w') do |file|
+        file.write(gzip.read)
+      end
+    end
+
+    return true
+  end
+end
 
 def initialize_csv(filename)
   CSV.open(filename, "w", force_quotes: true) do |csv|
@@ -164,6 +206,12 @@ end
 
 def main
 
+  if update_local_file("https://lov.linkeddata.es/lov.n3.gz","lov.n3.gz")
+    puts "The local file was updated."
+  else
+    puts "The local file remains unchanged."
+    exit
+  end
 
   initialize_csv(CSV_FILENAME)
 

From 30ea364db804116a685cbc5706ff4f0ab17424d8 Mon Sep 17 00:00:00 2001
From: Muhammad <boukerfa.ma@gmail.com>
Date: Sat, 19 Oct 2024 06:35:07 +0100
Subject: [PATCH 06/15] add creator metadata to the csv main attributes

---
 bin/lov_migrator | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/bin/lov_migrator b/bin/lov_migrator
index 8884f909..11bef932 100755
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -34,7 +34,8 @@ require 'open-uri'
 require 'digest'
 
 
-CSV_MAIN_ATTRS = [:prefix, :title, :description, :keyword, :uri, :modified]
+
+CSV_MAIN_ATTRS = [ :prefix, :title, :description, :keyword, :creator, :uri, :modified ]
 CSV_FILENAME = "vocabs.csv"
 
 

From 43de6b55e12b8e6d73ab6bbe3bedb52edf48e4fe Mon Sep 17 00:00:00 2001
From: Muhammad <boukerfa.ma@gmail.com>
Date: Sat, 19 Oct 2024 06:45:43 +0100
Subject: [PATCH 07/15] fix creator metadata to accept multiple values

---
 bin/lov_migrator | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/bin/lov_migrator b/bin/lov_migrator
index 11bef932..30a4034a 100755
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -149,7 +149,7 @@ def extract_vocabulary_info(graph, vocab_uri)
     modified: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/modified"), nil]).first&.object,
     isDefinedBy: graph.query([vocab_uri, RDF::URI("http://www.w3.org/2000/01/rdf-schema#isDefinedBy"), nil]).first&.object,
     homepage: graph.query([vocab_uri, RDF::URI("http://xmlns.com/foaf/0.1/homepage"), nil]).first&.object,
-    creator: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/creator"), nil]).first&.object,
+    creator: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/creator"), nil]).map { |statement| extract_uri_or_value(statement.object) },
     contributor: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/contributor"), nil]).map { |statement| extract_uri_or_value(statement.object) },
     publisher: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/publisher"), nil]).first&.object,
     language: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/language"), nil]).map { |statement| extract_uri_or_value(statement.object) },

From c12cf023f1323d8c4531b9e28b0e90e68230fe92 Mon Sep 17 00:00:00 2001
From: Muhammad <boukerfa.ma@gmail.com>
Date: Sat, 19 Oct 2024 06:57:28 +0100
Subject: [PATCH 08/15] remove main function

---
 bin/lov_migrator | 40 ++++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/bin/lov_migrator b/bin/lov_migrator
index 30a4034a..76f2a9ea 100755
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -50,6 +50,7 @@ def parse_n3_file(file_path)
   graph
 end
 
+
 def download_file(url, destination)
   URI.open(url) do |file|
     File.open(destination, 'wb') do |output|
@@ -205,32 +206,31 @@ def print_vocabulary_info(info)
   puts "\n"
 end
 
-def main
+# Start of the script
 
-  if update_local_file("https://lov.linkeddata.es/lov.n3.gz","lov.n3.gz")
-    puts "The local file was updated."
-  else
-    puts "The local file remains unchanged."
-    exit
-  end
+if update_local_file("https://lov.linkeddata.es/lov.n3.gz","lov.n3.gz")
+  puts "The local file was updated."
+else
+  puts "The local file remains unchanged."
+  exit
+end
 
-  initialize_csv(CSV_FILENAME)
+initialize_csv(CSV_FILENAME)
 
-  graph = parse_n3_file('lov.n3')
-  
-  vocab_uris = find_vocabularies(graph)
-  
-  if vocab_uris.empty?
-    puts "No vocabularies found in the file."
-  else
+graph = parse_n3_file('lov.n3')
+
+vocab_uris = find_vocabularies(graph)
+
+if vocab_uris.empty?
+  puts "No vocabularies found in the file."
+else
+  if options[:vocabs].first == :all
     puts "Found #{vocab_uris.size} vocabularies:\n\n"
     vocab_uris.each do |vocab_uri|
       vocab_info = extract_vocabulary_info(graph, vocab_uri)
       append_to_csv(vocab_info, CSV_FILENAME)
-
-      print_vocabulary_info(vocab_info)
+      #print_vocabulary_info(vocab_info)
     end
-  end  
-end
+  end
+end  
 
-main
\ No newline at end of file

From 276389c70264dbeae0adbc97080780102e1436b4 Mon Sep 17 00:00:00 2001
From: Muhammad <boukerfa.ma@gmail.com>
Date: Sat, 19 Oct 2024 09:17:47 +0100
Subject: [PATCH 09/15] extract agents metadata

---
 bin/lov_migrator | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/bin/lov_migrator b/bin/lov_migrator
index 76f2a9ea..48fb91e0 100755
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -175,12 +175,25 @@ def extract_vocabulary_info(graph, vocab_uri)
   info
 end
 
+def extract_agent_info(graph, agent_uri)
+  info = {
+    name: graph.query([agent_uri, RDF::URI("http://xmlns.com/foaf/0.1/name"), nil]).first&.object, 
+    sameAs: graph.query([agent_uri, RDF::URI("http://www.w3.org/2002/07/owl#sameAs"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+  }
+end
 
 def find_vocabularies(graph)
   vocab_type = RDF::URI("http://purl.org/vocommons/voaf#Vocabulary")
   graph.query([nil, RDF.type, vocab_type]).map(&:subject)
 end
 
+def find_agents(graph)
+  agent_type = RDF::URI("http://xmlns.com/foaf/0.1/Person")
+  graph.query([nil, RDF.type, agent_type]).map(&:subject)
+end
+
+
+
 def format_value(value)
   case value
   when Array
@@ -212,14 +225,14 @@ if update_local_file("https://lov.linkeddata.es/lov.n3.gz","lov.n3.gz")
   puts "The local file was updated."
 else
   puts "The local file remains unchanged."
-  exit
-end
+  end
 
 initialize_csv(CSV_FILENAME)
 
-graph = parse_n3_file('lov.n3')
+graph = parse_n3_file('test.n3')
 
 vocab_uris = find_vocabularies(graph)
+agent_uris = find_agents(graph)
 
 if vocab_uris.empty?
   puts "No vocabularies found in the file."
@@ -229,7 +242,12 @@ else
     vocab_uris.each do |vocab_uri|
       vocab_info = extract_vocabulary_info(graph, vocab_uri)
       append_to_csv(vocab_info, CSV_FILENAME)
-      #print_vocabulary_info(vocab_info)
+      print_vocabulary_info(vocab_info)
+    end
+    agent_uris.each do |agent_uri|
+      
+      puts extract_agent_info(graph, agent_uri)
+    
     end
   end
 end  

From 585d8a2d5188525e0a085a74122e9be82049e61d Mon Sep 17 00:00:00 2001
From: Muhammad <boukerfa.ma@gmail.com>
Date: Sat, 19 Oct 2024 09:47:00 +0100
Subject: [PATCH 10/15] add support for manual dispatch attributes in csv

---
 bin/lov_migrator | 31 ++++++++++++++++++++++++++-----
 1 file changed, 26 insertions(+), 5 deletions(-)

diff --git a/bin/lov_migrator b/bin/lov_migrator
index 48fb91e0..04400b87 100755
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -36,6 +36,8 @@ require 'digest'
 
 
 CSV_MAIN_ATTRS = [ :prefix, :title, :description, :keyword, :creator, :uri, :modified ]
+CSV_ADDED_ATTRS = [ :destination, :who, :comment ]
+CSV_DISPATCH_FILENAME = 'LOV_vocabularies_dispatch.csv'
 CSV_FILENAME = "vocabs.csv"
 
 
@@ -50,6 +52,14 @@ def parse_n3_file(file_path)
   graph
 end
 
+def find_csv_row_by_prefix(file_path, prefix_value)
+  CSV.foreach(file_path, headers: true, header_converters: :symbol) do |row|
+    if row[:prefix] == prefix_value
+      return row 
+    end
+  end
+  nil 
+end
 
 def download_file(url, destination)
   URI.open(url) do |file|
@@ -92,18 +102,29 @@ end
 
 def initialize_csv(filename)
   CSV.open(filename, "w", force_quotes: true) do |csv|
-    csv << CSV_MAIN_ATTRS  # Write header row
+    csv << CSV_MAIN_ATTRS + CSV_ADDED_ATTRS # Write header row
   end
 end
 
-def append_to_csv(obj, filename)
+# We copy the added attributes from dispatch csv
+def copy_added_values_to_csv(vocab)
+  csv_vocab = find_csv_row_by_prefix(CSV_DISPATCH_FILENAME, vocab[:prefix]).to_h
+  CSV_ADDED_ATTRS.each do |attr|
+    vocab[attr] = csv_vocab[attr]
+  end
+  vocab
+end
+
+def append_to_csv(vocab, filename)
+  vocab = copy_added_values_to_csv(vocab)
   CSV.open(filename, "a", force_quotes: true) do |csv|
-    filtered_row = CSV_MAIN_ATTRS.map { |attr| format_value(obj[attr]) }
+    filtered_row = (CSV_MAIN_ATTRS + CSV_ADDED_ATTRS).map { |attr| format_value(vocab[attr]) }
     csv << filtered_row
   end
 end
 
 
+
 def extract_uri_or_value(node)
   case node
   when RDF::URI
@@ -225,7 +246,7 @@ if update_local_file("https://lov.linkeddata.es/lov.n3.gz","lov.n3.gz")
   puts "The local file was updated."
 else
   puts "The local file remains unchanged."
-  end
+end
 
 initialize_csv(CSV_FILENAME)
 
@@ -241,7 +262,7 @@ else
     puts "Found #{vocab_uris.size} vocabularies:\n\n"
     vocab_uris.each do |vocab_uri|
       vocab_info = extract_vocabulary_info(graph, vocab_uri)
-      append_to_csv(vocab_info, CSV_FILENAME)
+      append_to_csv(vocab_info, CSV_FILENAME)      
       print_vocabulary_info(vocab_info)
     end
     agent_uris.each do |agent_uri|

From fc5114cde2b281a4d6612dd87abf18ffb2de6299 Mon Sep 17 00:00:00 2001
From: Muhammad <boukerfa.ma@gmail.com>
Date: Mon, 21 Oct 2024 09:19:15 +0100
Subject: [PATCH 11/15] add the 'date of latest modification in LOV' attribute
 to csv

---
 bin/lov_migrator | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/bin/lov_migrator b/bin/lov_migrator
index 04400b87..7ec42c97 100755
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -35,7 +35,7 @@ require 'digest'
 
 
 
-CSV_MAIN_ATTRS = [ :prefix, :title, :description, :keyword, :creator, :uri, :modified ]
+CSV_MAIN_ATTRS = [ :prefix, :title, :description, :keyword, :creator, :uri, :lastModifiedInLOVAt ]
 CSV_ADDED_ATTRS = [ :destination, :who, :comment ]
 CSV_DISPATCH_FILENAME = 'LOV_vocabularies_dispatch.csv'
 CSV_FILENAME = "vocabs.csv"
@@ -193,6 +193,8 @@ def extract_vocabulary_info(graph, vocab_uri)
     }
   end
 
+  info[:lastModifiedInLOVAt] = graph.query([RDF::URI("https://lov.linkeddata.es/dataset/lov/vocabs/#{info[:prefix]}"), RDF::URI("http://purl.org/dc/terms/modified") , nil]).first&.object
+
   info
 end
 
@@ -241,12 +243,12 @@ def print_vocabulary_info(info)
 end
 
 # Start of the script
-
+'''
 if update_local_file("https://lov.linkeddata.es/lov.n3.gz","lov.n3.gz")
   puts "The local file was updated."
 else
   puts "The local file remains unchanged."
-end
+end'''
 
 initialize_csv(CSV_FILENAME)
 

From 2a4f654b076e20d1b2cff9b1da9ced05f9fee7ac Mon Sep 17 00:00:00 2001
From: Syphax <gs_bouazzouni@esi.dz>
Date: Wed, 23 Oct 2024 08:36:17 +0200
Subject: [PATCH 12/15] update the parse_n3_file function to be faster using a
 ruby hash

---
 bin/lov_migrator | 41 +++++++++++++++++++++++++++++++++++++++--
 1 file changed, 39 insertions(+), 2 deletions(-)

diff --git a/bin/lov_migrator b/bin/lov_migrator
index 7ec42c97..c4be6427 100755
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -56,8 +56,8 @@ def find_csv_row_by_prefix(file_path, prefix_value)
   CSV.foreach(file_path, headers: true, header_converters: :symbol) do |row|
     if row[:prefix] == prefix_value
       return row 
-    end
-  end
+      end
+      end
   nil 
 end
 
@@ -100,6 +100,43 @@ def update_local_file(url, local_file_path)
   end
 end
 
+    def parse_n3_file(file_path)
+      # The RDF type you want to filter for
+      vocabulary_type = RDF::URI("http://purl.org/vocommons/voaf#Vocabulary")
+
+      vocabularies_hash = {}
+      vocabulary_subjects = Set.new
+
+      # Single-pass to read the Turtle file without breaking syntax
+      RDF::Turtle::Reader.open(file_path) do |reader|
+        # Collect all statements in an array (could be large, but streaming the file)
+        reader.each_statement do |statement|
+          subject = statement.subject
+
+          # If the statement is of type `voaf:Vocabulary`, track the subject
+          if statement.predicate == RDF.type && statement.object == vocabulary_type
+            vocabulary_subjects.add(subject)
+            vocabularies_hash[subject] ||= {}
+          end
+
+          # Collect all triples related to the subject if it's identified as a vocabulary
+          if vocabulary_subjects.include?(subject)
+            vocabularies_hash[subject] ||= {}
+            old_value = vocabularies_hash[subject][statement.predicate]
+            if old_value.nil?
+              vocabularies_hash[subject][statement.predicate] = statement.object
+            else
+              vocabularies_hash[subject][statement.predicate] = Array(old_value) + [statement.object]
+            end
+          end
+        end
+
+      end
+      vocabularies_hash
+
+    end
+  end
+
 def initialize_csv(filename)
   CSV.open(filename, "w", force_quotes: true) do |csv|
     csv << CSV_MAIN_ATTRS + CSV_ADDED_ATTRS # Write header row

From 3aaeb9743229cd43b5a24ddda5911acbac11d541 Mon Sep 17 00:00:00 2001
From: Syphax <gs_bouazzouni@esi.dz>
Date: Wed, 23 Oct 2024 08:37:19 +0200
Subject: [PATCH 13/15] create module to for the models to migrate Vocabulary,
 Agent and distribution

---
 bin/lov_migrator | 111 +++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 97 insertions(+), 14 deletions(-)

diff --git a/bin/lov_migrator b/bin/lov_migrator
index c4be6427..6b32384d 100755
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -40,27 +40,110 @@ CSV_ADDED_ATTRS = [ :destination, :who, :comment ]
 CSV_DISPATCH_FILENAME = 'LOV_vocabularies_dispatch.csv'
 CSV_FILENAME = "vocabs.csv"
 
+module LOVMigrator
+
+
+  module Models
+    class Model
+      def extract_uri_or_value(node)
+        case node
+        when RDF::URI
+          node.to_s
+        when RDF::Literal
+          if node.has_language?
+            { value: node.object, language: node.language.to_s }
+          else
+            node.object
+          end
+        else
+          node.to_s
+        end
+      end
 
+      def get_value(vocab, predicate, list: false)
+        values = Array(vocab[RDF::URI.new(predicate)])
+                   .map { |value| extract_uri_or_value(value) }
+        list ? values : values.first
+      end
+    end
+    class Vocabulary < Model
+
+      def extract_vocabulary_info(graph, vocab_uri, vocab)
+        return unless vocab
+
+        info = {
+          uri: vocab_uri,
+          namespace: get_value(vocab, "http://purl.org/vocab/vann/preferredNamespaceUri"),
+          prefix: get_value(vocab, "http://purl.org/vocab/vann/preferredNamespacePrefix"),
+          title: get_value(vocab, "http://purl.org/dc/terms/title", list: true),
+          description: get_value(vocab, "http://purl.org/dc/terms/description", list: true),
+          keyword: get_value(vocab, "http://www.w3.org/ns/dcat#keyword", list: true),
+          issued: get_value(vocab, "http://purl.org/dc/terms/issued"),
+          modified: get_value(vocab, "http://purl.org/dc/terms/modified"),
+
+          isDefinedBy: get_value(vocab, "http://www.w3.org/2000/01/rdf-schema#isDefinedBy"),
+          homepage: get_value(vocab, "http://xmlns.com/foaf/0.1/homepage"),
+          creator: get_value(vocab, "http://purl.org/dc/terms/creator", list: true),
+          contributor: get_value(vocab, "http://purl.org/dc/terms/contributor", list: true),
+          publisher: get_value(vocab, "http://purl.org/dc/terms/publisher"),
+          language: get_value(vocab, "http://purl.org/dc/terms/language", list: true),
+          type: get_value(vocab, RDF.type),
+          occurrences: get_value(vocab, "http://purl.org/vocommons/voaf#occurrencesInDatasets"),
+          reused_by_datasets: get_value(vocab, "http://purl.org/vocommons/voaf#reusedByDatasets"),
+          reused_by_vocabs: get_value(vocab, "http://purl.org/vocommons/voaf#reusedByVocabularies"),
+          distribution: get_value(vocab, "http://www.w3.org/ns/dcat#distribution"),
+        }
+
+        review = get_value(vocab, "http://purl.org/stuff/rev#hasReview")
+        review = graph.dig(review)
+        if review
+          info[:review] = {
+            creator: get_value(review, "http://purl.org/dc/terms/creator"),
+            date: get_value(review, "http://purl.org/dc/terms/date"),
+            text: get_value(review, "http://purl.org/stuff/rev#text")
+          }
+        end
+
+        info[:lastModifiedInLOVAt] = get_value(vocab, "http://purl.org/dc/terms/modified")
+
+        info
+      end
 
-def parse_n3_file(file_path)
-  graph = RDF::Graph.new
-  RDF::N3::Reader.open(file_path) do |reader|
-    reader.each_statement do |statement|
-      graph << statement
     end
-  end
-  graph
-end
 
-def find_csv_row_by_prefix(file_path, prefix_value)
-  CSV.foreach(file_path, headers: true, header_converters: :symbol) do |row|
-    if row[:prefix] == prefix_value
-      return row 
+    class Agent
+
+      def extract_agent_info(graph, agent_uri)
+        info = {
+          name: graph.query([agent_uri, RDF::URI("http://xmlns.com/foaf/0.1/name"), nil]).first&.object,
+          sameAs: graph.query([agent_uri, RDF::URI("http://www.w3.org/2002/07/owl#sameAs"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+        }
       end
+
+    end
+
+    class Distribution
+
+      def extract_distribution_info(graph, distribution_uri)
+        info_distribution = {
+          uri: distribution_uri,
+          issued: graph.query([distribution_uri, RDF::URI("http://purl.org/dc/terms/issued"), nil]).first&.object,
+          language: graph.query([distribution_uri, RDF::URI("http://purl.org/dc/terms/language"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+          title: graph.query([distribution_uri, RDF::URI("http://purl.org/dc/terms/title"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+          # Relations
+          extends: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#extends"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+          specializes: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#specializes"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+          generalizes: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#generalizes"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+          hasEquivalencesWith: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#hasEquivalencesWith"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+          hasDisjunctionsWith: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#hasDisjunctionsWith"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+          metadataVoc: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#metadataVoc"), nil]).map { |statement| extract_uri_or_value(statement.object) },
+          imports: graph.query([distribution_uri, RDF::URI("http://www.w3.org/2002/07/owl#imports"), nil]).map { |statement| extract_uri_or_value(statement.object) }
+        }
+        info_distribution
       end
-  nil 
-end
 
+    end
+  end
 def download_file(url, destination)
   URI.open(url) do |file|
     File.open(destination, 'wb') do |output|

From c89db6ca062f169cae2e7a1c9d6612b732585ab6 Mon Sep 17 00:00:00 2001
From: Syphax <gs_bouazzouni@esi.dz>
Date: Wed, 23 Oct 2024 08:38:04 +0200
Subject: [PATCH 14/15] dispatch the code into two modules one for the dump
 parsing and another for the csv generator

---
 bin/lov_migrator | 305 ++++++++++++++++++-----------------------------
 1 file changed, 118 insertions(+), 187 deletions(-)

diff --git a/bin/lov_migrator b/bin/lov_migrator
index 6b32384d..6918dfeb 100755
--- a/bin/lov_migrator
+++ b/bin/lov_migrator
@@ -5,7 +5,6 @@ Signal.trap("INT") { exit 1 }
 
 require 'optparse'
 
-
 options = {}
 OptionParser.new do |opts|
   opts.banner = "Usage: lov_migrator [options]"
@@ -23,17 +22,16 @@ OptionParser.new do |opts|
   end
 end.parse!
 
-
 raise OptionParser::MissingArgument if options[:vocabs].nil?
 
+require 'bundler/setup'
 require 'rdf'
 require 'rdf/n3'
 require 'csv'
-
 require 'open-uri'
 require 'digest'
-
-
+require 'benchmark'
+require 'parallel'
 
 CSV_MAIN_ATTRS = [ :prefix, :title, :description, :keyword, :creator, :uri, :lastModifiedInLOVAt ]
 CSV_ADDED_ATTRS = [ :destination, :who, :comment ]
@@ -144,45 +142,47 @@ module LOVMigrator
 
     end
   end
-def download_file(url, destination)
-  URI.open(url) do |file|
-    File.open(destination, 'wb') do |output|
-      output.write(file.read)
+
+  class DumpParser
+    def download_file(url, destination)
+      URI.open(url) do |file|
+        File.open(destination, 'wb') do |output|
+          output.write(file.read)
+        end
+      end
+      puts "File downloaded successfully as #{destination}"
     end
-  end
-  puts "File downloaded successfully as #{destination}"
-end
 
-def file_hash(file_path)
-  Digest::SHA256.file(file_path).hexdigest
-end
+    def file_hash(file_path)
+      Digest::SHA256.file(file_path).hexdigest
+    end
 
-def files_identical?(file1, file2)
-  File.exist?(file2) && file_hash(file1) == file_hash(file2)
-end
+    def files_identical?(file1, file2)
+      File.exist?(file2) && file_hash(file1) == file_hash(file2)
+    end
 
-# Updates the local file if the downloaded file is different
-def update_local_file(url, local_file_path)
-  downloaded_file_name = 'lov.n3.gz.tmp'
-  
-  download_file(url, downloaded_file_name)
+    # Updates the local file if the downloaded file is different
+    def update_local_file(url, local_file_path)
+      downloaded_file_name = 'lov.n3.gz.tmp'
+
+      download_file(url, downloaded_file_name)
+
+      if files_identical?(downloaded_file_name, local_file_path)
+        File.delete(downloaded_file_name) # Clean up the temporary file
+        return false
+      else
+        File.rename(downloaded_file_name, local_file_path) # Replace the old file with the new one
+        # decompress the doanloaded zip
+        Zlib::GzipReader.open(local_file_path) do |gzip|
+          File.open('lov.n3', 'w') do |file|
+            file.write(gzip.read)
+          end
+        end
 
-  if files_identical?(downloaded_file_name, local_file_path)
-    File.delete(downloaded_file_name) # Clean up the temporary file
-    return false
-  else
-    File.rename(downloaded_file_name, local_file_path) # Replace the old file with the new one
-    # decompress the doanloaded zip    
-    Zlib::GzipReader.open(local_file_path) do |gzip|
-      File.open('lov.n3', 'w') do |file|
-        file.write(gzip.read)
+        return true
       end
     end
 
-    return true
-  end
-end
-
     def parse_n3_file(file_path)
       # The RDF type you want to filter for
       vocabulary_type = RDF::URI("http://purl.org/vocommons/voaf#Vocabulary")
@@ -220,139 +220,59 @@ end
     end
   end
 
-def initialize_csv(filename)
-  CSV.open(filename, "w", force_quotes: true) do |csv|
-    csv << CSV_MAIN_ATTRS + CSV_ADDED_ATTRS # Write header row
-  end
-end
-
-# We copy the added attributes from dispatch csv
-def copy_added_values_to_csv(vocab)
-  csv_vocab = find_csv_row_by_prefix(CSV_DISPATCH_FILENAME, vocab[:prefix]).to_h
-  CSV_ADDED_ATTRS.each do |attr|
-    vocab[attr] = csv_vocab[attr]
-  end
-  vocab
-end
-
-def append_to_csv(vocab, filename)
-  vocab = copy_added_values_to_csv(vocab)
-  CSV.open(filename, "a", force_quotes: true) do |csv|
-    filtered_row = (CSV_MAIN_ATTRS + CSV_ADDED_ATTRS).map { |attr| format_value(vocab[attr]) }
-    csv << filtered_row
-  end
-end
-
-
+  class CSVGenerator
 
-def extract_uri_or_value(node)
-  case node
-  when RDF::URI
-    node.to_s
-  when RDF::Literal
-    if node.has_language?
-      { value: node.object, language: node.language.to_s }
-    else
-      node.object
+    def initialize_csv(filename)
+      CSV.open(filename, "w", force_quotes: true) do |csv|
+        csv << CSV_MAIN_ATTRS + CSV_ADDED_ATTRS # Write header row
+      end
     end
-  else
-    node.to_s
-  end      
-end
-
-def extract_distribution_info(graph, distribution_uri)
-  info_distribution = {
-    uri: distribution_uri,
-    issued: graph.query([distribution_uri, RDF::URI("http://purl.org/dc/terms/issued"), nil]).first&.object,
-    language: graph.query([distribution_uri, RDF::URI("http://purl.org/dc/terms/language"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-    title: graph.query([distribution_uri, RDF::URI("http://purl.org/dc/terms/title"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-    # Relations
-    extends: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#extends"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-    specializes: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#specializes"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-    generalizes: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#generalizes"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-    hasEquivalencesWith: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#hasEquivalencesWith"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-    hasDisjunctionsWith: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#hasDisjunctionsWith"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-    metadataVoc: graph.query([distribution_uri, RDF::URI("http://purl.org/vocommons/voaf#metadataVoc"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-    imports: graph.query([distribution_uri, RDF::URI("http://www.w3.org/2002/07/owl#imports"), nil]).map { |statement| extract_uri_or_value(statement.object) }
-  }
-  info_distribution
-end
-
 
-def extract_vocabulary_info(graph, vocab_uri)
-  info = {
-    uri: vocab_uri,
-    namespace: graph.query([vocab_uri, RDF::URI("http://purl.org/vocab/vann/preferredNamespaceUri"), nil]).first&.object, 
-    prefix: graph.query([vocab_uri, RDF::URI("http://purl.org/vocab/vann/preferredNamespacePrefix"), nil]).first&.object,
-    title: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/title"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-    description: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/description"), nil]).map { |statement| extract_uri_or_value(statement.object) }, 
-    keyword: graph.query([vocab_uri, RDF::URI("http://www.w3.org/ns/dcat#keyword"), nil]).map(&:object),
-    issued: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/issued"), nil]).first&.object,
-    modified: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/modified"), nil]).first&.object,
-    isDefinedBy: graph.query([vocab_uri, RDF::URI("http://www.w3.org/2000/01/rdf-schema#isDefinedBy"), nil]).first&.object,
-    homepage: graph.query([vocab_uri, RDF::URI("http://xmlns.com/foaf/0.1/homepage"), nil]).first&.object,
-    creator: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/creator"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-    contributor: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/contributor"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-    publisher: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/publisher"), nil]).first&.object,
-    language: graph.query([vocab_uri, RDF::URI("http://purl.org/dc/terms/language"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-
-    type: graph.query([vocab_uri, RDF.type, nil]).first&.object,
-
-    occurrences: graph.query([vocab_uri, RDF::URI("http://purl.org/vocommons/voaf#occurrencesInDatasets"), nil]).first&.object,
-    reused_by_datasets: graph.query([vocab_uri, RDF::URI("http://purl.org/vocommons/voaf#reusedByDatasets"), nil]).first&.object,
-    reused_by_vocabs: graph.query([vocab_uri, RDF::URI("http://purl.org/vocommons/voaf#reusedByVocabularies"), nil]).first&.object,
-    distribution: graph.query([vocab_uri, RDF::URI("http://www.w3.org/ns/dcat#distribution"), nil]).first&.object,
-  }
-
-  review = graph.query([vocab_uri, RDF::URI("http://purl.org/stuff/rev#hasReview"), nil]).first&.object
-  if review
-    info[:review] = {
-      creator: graph.query([review, RDF::URI("http://purl.org/dc/terms/creator"), nil]).first&.object,
-      date: graph.query([review, RDF::URI("http://purl.org/dc/terms/date"), nil]).first&.object,
-      text: graph.query([review, RDF::URI("http://purl.org/stuff/rev#text"), nil]).first&.object
-    }
-  end
-
-  info[:lastModifiedInLOVAt] = graph.query([RDF::URI("https://lov.linkeddata.es/dataset/lov/vocabs/#{info[:prefix]}"), RDF::URI("http://purl.org/dc/terms/modified") , nil]).first&.object
-
-  info
-end
-
-def extract_agent_info(graph, agent_uri)
-  info = {
-    name: graph.query([agent_uri, RDF::URI("http://xmlns.com/foaf/0.1/name"), nil]).first&.object, 
-    sameAs: graph.query([agent_uri, RDF::URI("http://www.w3.org/2002/07/owl#sameAs"), nil]).map { |statement| extract_uri_or_value(statement.object) },
-  }
-end
-
-def find_vocabularies(graph)
-  vocab_type = RDF::URI("http://purl.org/vocommons/voaf#Vocabulary")
-  graph.query([nil, RDF.type, vocab_type]).map(&:subject)
-end
+    # We copy the added attributes from dispatch csv
+    def copy_added_values_to_csv(vocab)
+      csv_vocab = find_csv_row_by_prefix(CSV_DISPATCH_FILENAME, vocab[:prefix]).to_h
+      CSV_ADDED_ATTRS.each do |attr|
+        vocab[attr] = csv_vocab[attr]
+      end
+      vocab
+    end
 
-def find_agents(graph)
-  agent_type = RDF::URI("http://xmlns.com/foaf/0.1/Person")
-  graph.query([nil, RDF.type, agent_type]).map(&:subject)
-end
+    def append_to_csv(vocab, filename)
+      vocab = copy_added_values_to_csv(vocab) if File.exist?(CSV_DISPATCH_FILENAME)
+      CSV.open(filename, "a", force_quotes: true) do |csv|
+        filtered_row = (CSV_MAIN_ATTRS + CSV_ADDED_ATTRS).map { |attr| format_value(vocab[attr]) }
+        csv << filtered_row
+      end
+    end
 
+    def find_csv_row_by_prefix(file_path, prefix_value)
+      CSV.foreach(file_path, headers: true, header_converters: :symbol) do |row|
+        if row[:prefix] == prefix_value
+          return row
+        end
+      end
+      nil
+    end
 
 
-def format_value(value)
-  case value
-  when Array
-    value.map { |v| format_value(v) }.join("\n")
-  when Hash
-    if value[:language]
-      "\"#{value[:value]}\"@#{value[:language]}"
-    else
-      value.to_s
+    def format_value(value)
+      case value
+      when Array
+        value.map { |v| format_value(v) }.join("\n")
+      when Hash
+        if value[:language]
+          "\"#{value[:value]}\"@#{value[:language]}"
+        else
+          value.to_s
+        end
+      else
+        value.to_s.empty? ? "None" : value.to_s
+      end
     end
-  else
-    value.to_s.empty? ? "None" : value.to_s
+
   end
 end
 
-
 def print_vocabulary_info(info)
   puts "-------------------------------------------------------------------"
   info.each do |key, value|
@@ -362,36 +282,47 @@ def print_vocabulary_info(info)
   puts "\n"
 end
 
+def logger(text, &block)
+  puts ">> #{text} starting..."
+  time = Benchmark.realtime do
+    block.call
+  end
+  puts "#{text} finished in #{time} seconds"
+end
+
 # Start of the script
-'''
-if update_local_file("https://lov.linkeddata.es/lov.n3.gz","lov.n3.gz")
-  puts "The local file was updated."
-else
-  puts "The local file remains unchanged."
-end'''
-
-initialize_csv(CSV_FILENAME)
-
-graph = parse_n3_file('test.n3')
-
-vocab_uris = find_vocabularies(graph)
-agent_uris = find_agents(graph)
-
-if vocab_uris.empty?
-  puts "No vocabularies found in the file."
-else
-  if options[:vocabs].first == :all
-    puts "Found #{vocab_uris.size} vocabularies:\n\n"
-    vocab_uris.each do |vocab_uri|
-      vocab_info = extract_vocabulary_info(graph, vocab_uri)
-      append_to_csv(vocab_info, CSV_FILENAME)      
-      print_vocabulary_info(vocab_info)
-    end
-    agent_uris.each do |agent_uri|
-      
-      puts extract_agent_info(graph, agent_uri)
-    
+def main
+  parser = LOVMigrator::DumpParser.new
+  updated = false
+  logger("Download dump file from LOV") do
+    updated = parser.update_local_file("https://lov.linkeddata.es/lov.n3.gz", "lov.n3.gz")
+  end
+  if updated
+    puts "The local file was updated."
+  else
+    puts "The local file remains unchanged."
+  end
+
+  csv_generator = LOVMigrator::CSVGenerator.new
+  logger("Initialize CSV #{CSV_FILENAME}") do
+    csv_generator.initialize_csv(CSV_FILENAME)
+  end
+
+  graph = []
+  logger('Parsing the n3 in memory') do
+    graph = parser.parse_n3_file('lov.n3')
+  end
+  puts "Found #{graph.size} vocabularies"
+  if graph.empty?
+    puts "No vocabularies found in the file."
+  else
+    logger("Start creating CSV #{CSV_FILENAME}") do
+      graph.each do |vocab_uri, vocab_data|
+        vocab_info = LOVMigrator::Models::Vocabulary.new.extract_vocabulary_info(graph, vocab_uri, vocab_data)
+        csv_generator.append_to_csv(vocab_info, CSV_FILENAME)
+      end
     end
   end
-end  
+end
 
+main

From 1108bfdee9b32e6401acfc54c299859d27968b3c Mon Sep 17 00:00:00 2001
From: Muhammad <boukerfa.ma@gmail.com>
Date: Thu, 24 Oct 2024 21:44:06 +0100
Subject: [PATCH 15/15] add `rdf` and `rdf/n3` gems to the Gemfile

---
 Gemfile | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Gemfile b/Gemfile
index 7d616193..51f14d40 100644
--- a/Gemfile
+++ b/Gemfile
@@ -23,6 +23,8 @@ gem 'sys-proctable'
 gem 'request_store'
 gem 'parallel'
 gem 'json-ld'
+gem 'rdf'
+gem 'rdf-n3'
 
 # Monitoring
 gem 'cube-ruby', require: 'cube'