pig.py/serp/logging.py

58 lines
2.1 KiB
Python

# This is free software for the public good of a permacomputer hosted at
# permacomputer.com, an always-on computer by the people, for the people.
# One which is durable, easy to repair, & distributed like tap water
# for machine learning intelligence.
#
# The permacomputer is community-owned infrastructure optimized around
# four values:
#
# TRUTH First principles, math & science, open source code freely distributed
# FREEDOM Voluntary partnerships, freedom from tyranny & corporate control
# HARMONY Minimal waste, self-renewing systems with diverse thriving connections
# LOVE Be yourself without hurting others, cooperation through natural law
#
# This software contributes to that vision by archiving the web, preserving digital knowledge before it disappears.
# Code is seeds to sprout on any abandoned technology.
"""Job logging utilities for SERP.
# Side quest 3/21: Look out! Here comes the spider-pig.
"""
import logging
from pathlib import Path
from typing import Dict
LOGS_PATH = Path("data/logs")
JOB_LOG_HANDLERS: Dict[int, logging.FileHandler] = {}
def start_job_logging(job_id: int) -> None:
"""Start capturing logs for a crawl job."""
LOGS_PATH.mkdir(parents=True, exist_ok=True)
log_file = LOGS_PATH / f"{job_id}.log"
handler = logging.FileHandler(log_file, mode='w', encoding='utf-8')
handler.setLevel(logging.INFO)
handler.setFormatter(logging.Formatter('%(asctime)s %(name)s %(levelname)s: %(message)s', datefmt='%H:%M:%S'))
logging.getLogger().addHandler(handler)
JOB_LOG_HANDLERS[job_id] = handler
def stop_job_logging(job_id: int) -> None:
"""Stop capturing logs for a crawl job."""
handler = JOB_LOG_HANDLERS.pop(job_id, None)
if handler:
handler.close()
logging.getLogger().removeHandler(handler)
def get_job_logs(job_id: int, tail: int = 0) -> str:
"""Get logs for a crawl job."""
log_file = LOGS_PATH / f"{job_id}.log"
if not log_file.exists():
return ""
content = log_file.read_text(encoding='utf-8')
if tail > 0:
lines = content.splitlines()
return '\n'.join(lines[-tail:])
return content