From 237c09262f50dc67ee3fecb67c01826fa99d3085 Mon Sep 17 00:00:00 2001
From: yumoqing <yumoqing@gmail.com>
Date: Tue, 21 Jul 2026 15:05:02 +0800
Subject: [PATCH] =?UTF-8?q?fix:=20init=5Fdata.py=E8=A1=A5=E5=85=A8?=
 =?UTF-8?q?=E7=BC=BA=E5=A4=B1=E5=AD=97=E6=AE=B5+userorgid=E4=B8=BANone?=
 =?UTF-8?q?=E5=85=9C=E5=BA=95(=E7=A9=BA=E4=B8=B2),=E6=94=AF=E6=8C=81?=
 =?UTF-8?q?=E9=87=8D=E5=A4=8D=E6=89=A7=E8=A1=8C?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 scripts/init_data.py | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/scripts/init_data.py b/scripts/init_data.py
index f9065d4..5d3d6c8 100644
--- a/scripts/init_data.py
+++ b/scripts/init_data.py
@@ -54,7 +54,7 @@ async def batch_sync_call_fact(sor, source_table, batch_size=1000):
         if not rows:
             break
 
-        print(f'  [{source_table}] batch offset={offset} rows={len(rows)}')
+        print('  [' + source_table + '] batch offset=' + str(offset) + ' rows=' + str(len(rows)))
 
         for r in rows:
             r = DictObject(r)
@@ -73,16 +73,21 @@ async def batch_sync_call_fact(sor, source_table, batch_size=1000):
                 total_skipped += 1
                 continue
 
+            currency = getattr(r, 'amount_currency', None) or 'CNY'
+            amount = getattr(r, 'amount', 0) or 0
+            userorgid = getattr(r, 'userorgid', None)
+            distributor_orgid = getattr(r, 'distributor_orgid', None)
+
             ns = {
                 'id': getID(),
                 'luid': r.id,
                 'llmid': r.llmid,
-                'model': r.llm_model,
+                'model': r.llm_model or '',
                 'catelogid': r.catelogid or '',
-                'userid': r.userid,
-                'userorgid': r.userorgid,
-                'ownerid': r.ownerid,
-                'providerid': r.providerid,
+                'userid': r.userid or '',
+                'userorgid': userorgid or '',
+                'ownerid': r.ownerid or '',
+                'providerid': r.providerid or '',
                 'call_date': r.use_date or call_time.strftime('%Y-%m-%d'),
                 'call_hour': call_time.hour,
                 'call_time': r.use_time,
@@ -91,15 +96,18 @@ async def batch_sync_call_fact(sor, source_table, batch_size=1000):
                 'prompt_tokens': prompt_tokens,
                 'completion_tokens': completion_tokens,
                 'status': r.status or 'SUCCEEDED',
-                'amount': r.amount or 0,
-                'currency': getattr(r, 'amount_currency', None) or 'CNY',
+                'amount': amount,
+                'currency': currency,
+                'amount_cny': amount,
+                'distributor_orgid': distributor_orgid or '',
+                'sale_userid': '',
             }
             await sor.C('dm_model_call_fact', ns)
             total_inserted += 1
 
         offset += batch_size
 
-    print(f'  [{source_table}] done: inserted={total_inserted}, skipped={total_skipped}')
+    print('  [' + source_table + '] done: inserted=' + str(total_inserted) + ', skipped=' + str(total_skipped))
     return total_inserted, total_skipped
 
 
@@ -112,7 +120,7 @@ async def batch_aggregate_history(sor):
         {}
     )
     dates = [r['call_date'].strftime('%Y-%m-%d') if hasattr(r['call_date'], 'strftime') else str(r['call_date']) for r in rows]
-    print(f'  aggregating {len(dates)} distinct dates...')
+    print('  aggregating ' + str(len(dates)) + ' distinct dates...')
 
     for d in dates:
         await aggregate_daily_perf(sor, stat_date=d)