Add RDF import script for Supabase

import_rdf_to_supabase.py

@@ -0,0 +1,108 @@
+#!/usr/bin/env python3
+"""
+Import Turtle RDF data into Supabase
+"""
+import requests
+from rdflib import Graph, Literal, URIRef, Namespace
+from pathlib import Path
+
+SUPABASE_URL = "https://zmluirvqfkmfazqitqgi.supabase.co"
+# Use service role key for insert operations
+SUPABASE_KEY = "sb_secret_2CWvKTeiJ-gbQn5AGCI8YQ_vOujwVnt"
+
+headers = {
+    'apikey': SUPABASE_KEY,
+    'Authorization': f'Bearer {SUPABASE_KEY}',
+    'Content-Type': 'application/json',
+    'Prefer': 'resolution=merge-duplicates'
+}
+
+# Namespace mapping - old github to new syscred.uqam.ca
+OLD_NS = "https://github.com/DominiqueLoyer/systemFactChecking#"
+NEW_NS = "https://syscred.uqam.ca/ontology#"
+
+def transform_uri(uri):
+    """Transform old github namespace to new syscred namespace"""
+    uri = str(uri)
+    if OLD_NS in uri:
+        return uri.replace(OLD_NS, NEW_NS)
+    return uri
+
+# Parse Turtle files
+print("=== Parsing Turtle files ===")
+g = Graph()
+
+# Parse base ontology
+base_file = Path("ontology/sysCRED_onto26avrtil.ttl")
+if base_file.exists():
+    print(f"Loading: {base_file}")
+    g.parse(str(base_file), format='turtle')
+
+# Parse data ontology
+data_file = Path("ontology/sysCRED_data.ttl")
+if data_file.exists():
+    print(f"Loading: {data_file}")
+    g.parse(str(data_file), format='turtle')
+
+print(f"Total triples parsed: {len(g)}")
+
+# Transform and insert
+print("\n=== Inserting into Supabase (rdf_triples table) ===")
+
+batch = []
+batch_size = 100
+total_inserted = 0
+
+for i, (s, p, o) in enumerate(g):
+    # Transform URIs
+    subject = transform_uri(s)
+    predicate = transform_uri(p)
+    obj_value = transform_uri(o) if isinstance(o, URIRef) else str(o)
+    obj_type = 'literal' if isinstance(o, Literal) else 'uri'
+    graph_name = 'base' if OLD_NS in str(s) or 'Expert' in str(s) else 'data'
+    
+    batch.append({
+        'subject': subject[:500],
+        'predicate': predicate[:500],
+        'object': obj_value,
+        'object_type': obj_type,
+        'graph_name': graph_name
+    })
+    
+    # Insert in batches
+    if len(batch) >= batch_size:
+        response = requests.post(
+            f"{SUPABASE_URL}/rest/v1/rdf_triples",
+            headers=headers,
+            json=batch
+        )
+        if response.status_code in [200, 201]:
+            total_inserted += len(batch)
+            print(f"  Inserted batch {total_inserted//batch_size}: {len(batch)} triples")
+        else:
+            print(f"  Error: {response.status_code} - {response.text[:100]}")
+        batch = []
+
+# Insert remaining
+if batch:
+    response = requests.post(
+        f"{SUPABASE_URL}/rest/v1/rdf_triples",
+        headers=headers,
+        json=batch
+    )
+    if response.status_code in [200, 201]:
+        total_inserted += len(batch)
+        print(f"  Inserted final batch: {len(batch)} triples")
+    else:
+        print(f"  Error: {response.status_code}")
+
+print(f"\n✓ Total inserted: {total_inserted}")
+
+# Verify
+print("\n=== Verifying ===")
+response = requests.get(
+    f"{SUPABASE_URL}/rest/v1/rdf_triples?select=id",
+    headers={'apikey': SUPABASE_KEY, 'Authorization': f'Bearer {SUPABASE_KEY}'}
+)
+if response.status_code == 200:
+    print(f"Total in rdf_triples: {len(response.json())}")