is_quadstore

bear/config.json

@@ -1,11 +1,13 @@
 {
     "dataset": {
-        "triplestore_urls": ["http://127.0.0.1:9999/blazegraph/sparql"],
-        "file_paths": []
+        "triplestore_urls": ["http://127.0.0.1:29999/blazegraph/sparql"],
+        "file_paths": [],
+        "is_quadstore": true
     },
     "provenance": {
-        "triplestore_urls": ["http://127.0.0.1:19999/blazegraph/sparql"],
-        "file_paths": []
+        "triplestore_urls": ["http://127.0.0.1:39999/blazegraph/sparql"],
+        "file_paths": [],
+        "is_quadstore": true
     },
     "blazegraph_full_text_search": "yes",
     "fuseki_full_text_search": "no",

bear/explore_cb_data.py

@@ -0,0 +1,30 @@
+import argparse
+import gzip
+import os
+
+def search_string_in_nt_files(folder_path, search_string):
+    for root, _, files in os.walk(folder_path):
+        for filename in files:
+            if filename.endswith('.gz'):
+                file_path = os.path.join(root, filename)
+                try:
+                    with gzip.open(file_path, 'rt', encoding='utf-8') as gz_file:
+                        for line in gz_file:
+                            if search_string in line:
+                                print(line.strip(), filename)
+                except Exception as e:
+                    print(f"Errore durante la lettura del file {file_path}: {e}")
+
+def main():
+    parser = argparse.ArgumentParser(description="Cerca una stringa nei file .gz contenenti file .nt")
+    parser.add_argument("folder_path", help="Percorso della cartella contenente i file .gz")
+    parser.add_argument("search_string", help="Stringa da cercare nei file .nt")
+
+    args = parser.parse_args()
+    folder_path = args.folder_path
+    search_string = args.search_string
+
+    search_string_in_nt_files(folder_path, search_string)
+
+if __name__ == "__main__":
+    main()

bear/find_highest_numbered_file.py

@@ -0,0 +1,34 @@
+import os
+import argparse
+
+def find_highest_numbered_file(directory):
+    highest_numbered_file = None
+    highest_number = -1
+
+    for filename in os.listdir(directory):
+        if filename.endswith(".nt.gz"):
+            try:
+                file_number = int(filename.split('.')[0])
+                if file_number > highest_number:
+                    highest_numbered_file = filename
+                    highest_number = file_number
+            except ValueError:
+                pass
+
+    return highest_numbered_file
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Trova il file con il numero più alto nel nome nella directory.")
+    parser.add_argument("directory", help="La directory in cui cercare il file con il numero più alto nel nome.")
+
+    args = parser.parse_args()
+    directory = args.directory
+
+    if not os.path.exists(directory):
+        print(f"La directory '{directory}' non esiste.")
+    else:
+        highest_numbered_file = find_highest_numbered_file(directory)
+        if highest_numbered_file:
+            print(f"Il file con il numero più alto nel nome nella directory '{directory}' è: {highest_numbered_file}")
+        else:
+            print(f"Nessun file trovato nella directory '{directory}' con numeri nel nome.")

bear/find_snapshots.py

@@ -1,3 +1,4 @@
+import argparse
 import json
 import os
 import re
@@ -20,7 +21,7 @@ def find_generated_at_time(filename):
 
     return results
 
-def main(directory):
+def main(directory, output_file):
     """
     Esplora tutti i file .nq nella directory specificata e cerca gli oggetti dei predicati prov:generatedAtTime.
     """
@@ -40,10 +41,13 @@ def main(directory):
 
     timestamps_sorted = sorted(list(timestamps))
 
-    with open("timestamps.json", "w", encoding='utf-8') as json_file:
+    with open(output_file, "w", encoding='utf-8') as json_file:
         json.dump({str(i+1): ts for i, ts in enumerate(timestamps_sorted)}, json_file, ensure_ascii=False, indent=4)
 
 
 if __name__ == "__main__":
-    directory = input("Inserisci il percorso della cartella da esplorare: ")
-    main(directory)
+    parser = argparse.ArgumentParser(description="Find prov:generatedAtTime objects in .nq files.")
+    parser.add_argument("directory", type=str, help="The directory to explore for .nq files")
+    parser.add_argument("--output", type=str, default="timestamps.json", help="Output file path (default: timestamps.json)")
+    args = parser.parse_args()
+    main(args.directory, args.output)