From bd7d8c77bfbd7ad4e58ad044b54747009c20dba3 Mon Sep 17 00:00:00 2001
From: Accusys <accusys@momentry.dev>
Date: Fri, 26 Jun 2026 13:55:10 +0800
Subject: [PATCH] feat: add migrate_manual_file_identities.py

Migrate identities.file_uuid to file_identities table for consistent structure
---
 scripts/migrate_manual_file_identities.py | 106 ++++++++++++++++++++++
 1 file changed, 106 insertions(+)
 create mode 100644 scripts/migrate_manual_file_identities.py

diff --git a/scripts/migrate_manual_file_identities.py b/scripts/migrate_manual_file_identities.py
new file mode 100644
index 0000000..8183509
--- /dev/null
+++ b/scripts/migrate_manual_file_identities.py
@@ -0,0 +1,106 @@
+#!/opt/homebrew/bin/python3.11
+"""
+Migrate manual identities' file_uuid to file_identities table.
+
+After migration:
+- All identities use file_identities table for file linkage
+- identities.file_uuid column becomes deprecated
+
+Usage:
+    python3 scripts/migrate_manual_file_identities.py --schema public
+    python3 scripts/migrate_manual_file_identities.py --schema dev
+"""
+
+import argparse
+import os
+import psycopg2
+import psycopg2.extras
+import json
+from datetime import datetime, timezone
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Migrate manual identities to file_identities")
+    parser.add_argument("--schema", default="public", help="Database schema")
+    parser.add_argument("--db", default=os.getenv("DATABASE_URL", "postgresql://accusys@localhost:5432/momentry"))
+    args = parser.parse_args()
+
+    schema = args.schema
+    identities_table = f"{schema}.identities" if schema != "public" else "identities"
+    file_identities_table = f"{schema}.file_identities" if schema != "public" else "file_identities"
+
+    conn = psycopg2.connect(args.db)
+    cur = conn.cursor(cursor_factory=psycopg2.extras.RealDictCursor)
+
+    # Get manual identities with file_uuid
+    cur.execute(f"""
+        SELECT id, uuid, name, status, file_uuid, metadata, created_at
+        FROM {identities_table}
+        WHERE file_uuid IS NOT NULL
+    """)
+    identities = cur.fetchall()
+
+    print(f"[Migration] Found {len(identities)} identities with file_uuid")
+
+    migrated = 0
+    now = datetime.now(timezone.utc).isoformat()
+
+    for identity in identities:
+        file_uuid = identity["file_uuid"]
+        identity_id = identity["id"]
+
+        try:
+            # Check if already exists in file_identities
+            cur.execute(f"""
+                SELECT 1 FROM {file_identities_table}
+                WHERE file_uuid = %s AND identity_id = %s
+            """, (file_uuid, identity_id))
+            if cur.fetchone():
+                continue
+
+            # Insert into file_identities
+            cur.execute(f"""
+                INSERT INTO {file_identities_table} (
+                    file_uuid, identity_id, confidence, metadata, created_at
+                ) VALUES (%s, %s, %s, %s, %s)
+            """, (
+                file_uuid,
+                identity_id,
+                1.0,
+                psycopg2.extras.Json({
+                    "source": identity.get("source") or "manual",
+                    "migrated_from": "identities.file_uuid",
+                    "migrated_at": now,
+                }),
+                now,
+            ))
+            migrated += 1
+
+        except Exception as e:
+            print(f"  [WARN] Failed for {identity['name']}: {e}")
+
+    conn.commit()
+    print(f"[Migration] Created {migrated} new file_identities entries")
+
+    # Verify
+    cur.execute(f"""
+        SELECT source, COUNT(*) as total,
+               COUNT(file_uuid) as has_file_uuid
+        FROM {identities_table}
+        GROUP BY source
+    """)
+    print()
+    print("[Migration] Verification:")
+    for r in cur.fetchall():
+        print(f"  {r['source'] or 'NULL':15} total={r['total']}, file_uuid={r['has_file_uuid']}")
+
+    cur.execute(f"SELECT COUNT(*) FROM {file_identities_table}")
+    count = cur.fetchone()["count"]
+    print(f"  file_identities total: {count}")
+
+    cur.close()
+    conn.close()
+
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file