clean docs

scripts/sync_migration_state.py

@@ -0,0 +1,63 @@
+#!/usr/bin/env python3
+"""Sync migration_state with actual data in PostgreSQL tables."""
+
+import sys
+sys.path.insert(0, '/home/alex/devel/mysql2postgres')
+
+from src.connectors.postgres_connector import PostgreSQLConnector
+from src.migrator.state_manager import StateManager
+
+def sync_table_state(table_name: str):
+    """Sync migration_state for a table with its actual data."""
+    with PostgreSQLConnector() as pg_conn:
+        cursor = pg_conn.connection.cursor()
+
+        # Find the row with MAX(created_at) - most recently inserted
+        # Exclude corrupted data (Java strings)
+        cursor.execute(f"""
+            SELECT unit_name, tool_name_id,
+                   DATE(event_timestamp)::text as event_date,
+                   event_timestamp::time::text as event_time,
+                   created_at,
+                   event_timestamp
+            FROM {table_name}
+            WHERE unit_name NOT LIKE '[L%'  -- Exclude corrupted Java strings
+            ORDER BY created_at DESC
+            LIMIT 1
+        """)
+
+        result = cursor.fetchone()
+        if not result:
+            print(f"No data found in {table_name}")
+            return
+
+        unit_name, tool_name_id, event_date, event_time, created_at, event_timestamp = result
+
+        print(f"\n{table_name.upper()}:")
+        print(f"  Most recently inserted row (by created_at):")
+        print(f"    created_at: {created_at}")
+        print(f"    event_timestamp: {event_timestamp}")
+        print(f"    Consolidation key: ({unit_name}, {tool_name_id}, {event_date}, {event_time})")
+
+        # Update global migration_state with this key
+        state_mgr = StateManager(pg_conn, table_name, partition_name="_global")
+
+        last_key = {
+            "unit_name": unit_name,
+            "tool_name_id": tool_name_id,
+            "event_date": event_date,
+            "event_time": event_time
+        }
+
+        state_mgr.update_state(last_key=last_key)
+        print(f"  ✓ Updated migration_state with this key")
+
+if __name__ == "__main__":
+    print("Syncing migration_state with actual PostgreSQL data...")
+    print("="*80)
+
+    sync_table_state("elabdatadisp")
+    sync_table_state("rawdatacor")
+
+    print("\n" + "="*80)
+    print("✓ Done! Incremental migration will now start from the correct position.")