This commit is contained in:
Neo
2026-01-27 22:47:05 +08:00
parent a6ad343092
commit f5f9a7eb66
476 changed files with 381543 additions and 5819 deletions

View File

@@ -1,13 +1,14 @@
# -*- coding: utf-8 -*-
# -*- coding: utf-8 -*-
from .base_dwd_task import BaseDwdTask
from loaders.dimensions.member import MemberLoader
from models.parsers import TypeParser
import json
from utils.windowing import build_window_segments
class MembersDwdTask(BaseDwdTask):
"""
DWD Task: Process Member Records from ODS to Dimension Table
Source: billiards_ods.ods_member_profile
Source: billiards_ods.member_profiles
Target: billiards.dim_member
"""
@@ -17,53 +18,72 @@ class MembersDwdTask(BaseDwdTask):
def execute(self) -> dict:
self.logger.info(f"Starting {self.get_task_code()} task")
window_start, window_end, _ = self._get_time_window()
self.logger.info(f"Processing window: {window_start} to {window_end}")
base_start, base_end, _ = self._get_time_window()
segments = build_window_segments(
self.config,
base_start,
base_end,
tz=self.tz,
override_only=True,
)
if not segments:
segments = [(base_start, base_end)]
total_segments = len(segments)
if total_segments > 1:
self.logger.info(f"{self.get_task_code()}: ????? {total_segments} ?")
loader = MemberLoader(self.db)
store_id = self.config.get("app.store_id")
total_inserted = 0
total_updated = 0
total_errors = 0
# Iterate ODS Data
batches = self.iter_ods_rows(
table_name="billiards_ods.ods_member_profile",
columns=["site_id", "member_id", "payload", "fetched_at"],
start_time=window_start,
end_time=window_end
for idx, (window_start, window_end) in enumerate(segments, start=1):
self.logger.info(
f"Processing window {idx}/{total_segments}: {window_start} to {window_end}"
)
batches = self.iter_ods_rows(
table_name="billiards_ods.member_profiles",
columns=["site_id", "member_id", "payload", "fetched_at"],
start_time=window_start,
end_time=window_end
)
for batch in batches:
if not batch:
continue
parsed_rows = []
for row in batch:
payload = self.parse_payload(row)
if not payload:
continue
parsed = self._parse_member(payload, store_id)
if parsed:
parsed_rows.append(parsed)
if parsed_rows:
inserted, updated, skipped = loader.upsert_members(parsed_rows, store_id)
total_inserted += inserted
total_updated += updated
self.db.commit()
overall_start = segments[0][0]
overall_end = segments[-1][1]
self.logger.info(
f"Task {self.get_task_code()} completed. Inserted: {total_inserted}, Updated: {total_updated}"
)
for batch in batches:
if not batch:
continue
parsed_rows = []
for row in batch:
payload = self.parse_payload(row)
if not payload:
continue
parsed = self._parse_member(payload, store_id)
if parsed:
parsed_rows.append(parsed)
if parsed_rows:
inserted, updated, skipped = loader.upsert_members(parsed_rows, store_id)
total_inserted += inserted
total_updated += updated
self.db.commit()
self.logger.info(f"Task {self.get_task_code()} completed. Inserted: {total_inserted}, Updated: {total_updated}")
return {
"status": "success",
"inserted": total_inserted,
"updated": total_updated,
"window_start": window_start.isoformat(),
"window_end": window_end.isoformat()
"window_start": overall_start.isoformat(),
"window_end": overall_end.isoformat()
}
def _parse_member(self, raw: dict, store_id: int) -> dict:
@@ -87,3 +107,4 @@ class MembersDwdTask(BaseDwdTask):
except Exception as e:
self.logger.warning(f"Error parsing member: {e}")
return None