数据库数据校验写入等逻辑更新。

2026-02-01 03:46:16 +08:00
parent 9948000b71
commit 076f5755ca
128 changed files with 494310 additions and 2819 deletions
--- a/tmp/table_analysis/dim_site.txt
+++ b/tmp/table_analysis/dim_site.txt
@@ -0,0 +1,129 @@
+================================================================================
+Table: billiards_dwd.dim_site
+Primary Key: site_id, scd2_start_time
+================================================================================
+
+## COLUMNS
+--------------------------------------------------------------------------------
+site_id: bigint | nullable=NO | PK
+org_id: bigint | nullable=YES | 
+tenant_id: bigint | nullable=YES | 
+shop_name: text | nullable=YES | 
+site_label: text | nullable=YES | 
+full_address: text | nullable=YES | 
+address: text | nullable=YES | 
+longitude: numeric(10,6) | nullable=YES | 
+latitude: numeric(10,6) | nullable=YES | 
+tenant_site_region_id: bigint | nullable=YES | 
+business_tel: text | nullable=YES | 
+site_type: integer | nullable=YES | 
+shop_status: integer | nullable=YES | 
+scd2_start_time: timestamp with time zone | nullable=NO | PK
+scd2_end_time: timestamp with time zone | nullable=YES | 
+scd2_is_current: integer | nullable=YES | 
+scd2_version: integer | nullable=YES | 
+
+## VALUE ANALYSIS (for enum detection)
+--------------------------------------------------------------------------------
+
+site_id:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    2790685415443269: 1
+
+org_id:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    2790684179467077: 1
+
+tenant_id:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    2790683160709957: 1
+
+shop_name:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    朗朗桌球: 1
+
+site_label:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    A: 1
+
+full_address:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    广东省广州市天河区丽阳街12号: 1
+
+address:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    广东省广州市天河区天园街道朗朗桌球: 1
+
+tenant_site_region_id:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    156440100: 1
+
+business_tel:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    13316068642: 1
+
+site_type:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    1: 1
+
+shop_status:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    1: 1
+
+scd2_is_current:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    1: 1
+
+scd2_version:
+  Total: 1, Non-null: 1, Distinct: 1
+  *** LIKELY ENUM (distinct <= 15) ***
+  Top values:
+    1: 1
+
+## SAMPLE DATA (first 10 rows)
+--------------------------------------------------------------------------------
+Columns: ['site_id', 'org_id', 'tenant_id', 'shop_name', 'site_label', 'full_address', 'address', 'longitude', 'latitude', 'tenant_site_region_id', 'business_tel', 'site_type', 'shop_status', 'scd2_start_time', 'scd2_end_time', 'scd2_is_current', 'scd2_version']
+
+Row 1:
+  site_id: 2790685415443269
+  org_id: 2790684179467077
+  tenant_id: 2790683160709957
+  shop_name: 朗朗桌球
+  site_label: A
+  full_address: 广东省广州市天河区丽阳街12号
+  address: 广东省广州市天河区天园街道朗朗桌球
+  longitude: 113.360321
+  latitude: 23.133629
+  tenant_site_region_id: 156440100
+  business_tel: 13316068642
+  site_type: 1
+  shop_status: 1
+  scd2_start_time: 2025-12-14 21:20:28.731914+08:00
+  scd2_end_time: 9999-12-31 00:00:00+08:00
+  scd2_is_current: 1
+  scd2_version: 1
+