ETL 完成
This commit is contained in:
@@ -25,46 +25,54 @@ class DatabaseOperations:
|
||||
|
||||
use_returning = "RETURNING" in sql.upper()
|
||||
|
||||
with self.conn.cursor() as c:
|
||||
if not use_returning:
|
||||
# 不带 RETURNING:直接批量执行即可
|
||||
if not use_returning:
|
||||
with self.conn.cursor() as c:
|
||||
psycopg2.extras.execute_batch(c, sql, rows, page_size=page_size)
|
||||
return (0, 0)
|
||||
|
||||
# 尝试向量化执行
|
||||
return (0, 0)
|
||||
|
||||
# 尝试向量化执行(execute_values + fetch returning)
|
||||
vectorized_failed = False
|
||||
m = re.search(r"VALUES\s*\((.*?)\)", sql, flags=re.IGNORECASE | re.DOTALL)
|
||||
if m:
|
||||
tpl = "(" + m.group(1) + ")"
|
||||
base_sql = sql[:m.start()] + "VALUES %s" + sql[m.end():]
|
||||
try:
|
||||
m = re.search(r"VALUES\s*\((.*?)\)", sql, flags=re.IGNORECASE | re.DOTALL)
|
||||
if m:
|
||||
tpl = "(" + m.group(1) + ")"
|
||||
base_sql = sql[:m.start()] + "VALUES %s" + sql[m.end():]
|
||||
|
||||
with self.conn.cursor() as c:
|
||||
ret = psycopg2.extras.execute_values(
|
||||
c, base_sql, rows, template=tpl, page_size=page_size, fetch=True
|
||||
)
|
||||
|
||||
if not ret:
|
||||
return (0, 0)
|
||||
|
||||
inserted = sum(1 for rec in ret if self._is_inserted(rec))
|
||||
return (inserted, len(ret) - inserted)
|
||||
if not ret:
|
||||
return (0, 0)
|
||||
inserted = sum(1 for rec in ret if self._is_inserted(rec))
|
||||
return (inserted, len(ret) - inserted)
|
||||
except Exception:
|
||||
# 向量化失败后,事务通常处于 aborted 状态,需要先 rollback 才能继续执行。
|
||||
vectorized_failed = True
|
||||
|
||||
if vectorized_failed:
|
||||
try:
|
||||
self.conn.rollback()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# 回退:逐行执行
|
||||
inserted = 0
|
||||
updated = 0
|
||||
|
||||
# 回退:逐行执行
|
||||
inserted = 0
|
||||
updated = 0
|
||||
with self.conn.cursor() as c:
|
||||
for r in rows:
|
||||
c.execute(sql, r)
|
||||
try:
|
||||
rec = c.fetchone()
|
||||
except Exception:
|
||||
rec = None
|
||||
|
||||
|
||||
if self._is_inserted(rec):
|
||||
inserted += 1
|
||||
else:
|
||||
updated += 1
|
||||
|
||||
return (inserted, updated)
|
||||
|
||||
return (inserted, updated)
|
||||
|
||||
@staticmethod
|
||||
def _is_inserted(rec) -> bool:
|
||||
|
||||
Reference in New Issue
Block a user