ETL 完成

This commit is contained in:
Neo
2026-01-18 22:37:38 +08:00
parent 8da6cb6563
commit 7ca19a4a2c
159 changed files with 31225 additions and 467 deletions

View File

@@ -0,0 +1,91 @@
# -*- coding: utf-8 -*-
from __future__ import annotations
import logging
import sys
from contextlib import contextmanager
from datetime import datetime
from pathlib import Path
from typing import Iterator, TextIO
class TeeStream:
def __init__(self, *streams: TextIO) -> None:
self._streams = streams
def write(self, data: str) -> int:
for stream in self._streams:
stream.write(data)
return len(data)
def flush(self) -> None:
for stream in self._streams:
stream.flush()
def isatty(self) -> bool:
return False
def fileno(self) -> int:
return self._streams[0].fileno()
def build_log_path(log_dir: Path, prefix: str, tag: str = "") -> Path:
suffix = f"_{tag}" if tag else ""
stamp = datetime.now().strftime("%Y%m%d_%H%M%S")
return log_dir / f"{prefix}{suffix}_{stamp}.log"
@contextmanager
def configure_logging(
name: str,
log_file: Path | None,
*,
level: str = "INFO",
console: bool = True,
tee_std: bool = True,
) -> Iterator[logging.Logger]:
logger = logging.getLogger(name)
logger.handlers.clear()
logger.setLevel(getattr(logging, level.upper(), logging.INFO))
logger.propagate = False
formatter = logging.Formatter(
"%(asctime)s [%(levelname)s] %(name)s: %(message)s",
"%Y-%m-%d %H:%M:%S",
)
original_stdout = sys.stdout
original_stderr = sys.stderr
log_fp: TextIO | None = None
try:
if log_file:
log_file.parent.mkdir(parents=True, exist_ok=True)
log_fp = open(log_file, "a", encoding="utf-8", buffering=1)
if tee_std:
if console:
sys.stdout = TeeStream(original_stdout, log_fp)
sys.stderr = TeeStream(original_stderr, log_fp)
else:
sys.stdout = log_fp
sys.stderr = log_fp
file_handler = logging.StreamHandler(log_fp)
file_handler.setFormatter(formatter)
logger.addHandler(file_handler)
if console:
console_handler = logging.StreamHandler(original_stdout)
console_handler.setFormatter(formatter)
logger.addHandler(console_handler)
yield logger
finally:
for handler in list(logger.handlers):
handler.flush()
handler.close()
logger.removeHandler(handler)
if log_fp:
log_fp.flush()
log_fp.close()
sys.stdout = original_stdout
sys.stderr = original_stderr