browsertrix/backend/btrixcloud/utils.py
Tessa Walsh 21ae38362e
Add endpoints to read pages from older crawl WACZs into database (#1562)
Fixes #1597

New endpoints (replacing old migration) to re-add crawl pages to db from
WACZs.

After a few implementation attempts, we settled on using
[remotezip](https://github.com/gtsystem/python-remotezip) to handle
parsing of the zip files and streaming their contents line-by-line for
pages. I've also modified the sync log streaming to use remotezip as
well, which allows us to remove our own zip module and let remotezip
handle the complexity of parsing zip files.

Database inserts for pages from WACZs are batched 100 at a time to help
speed up the endpoint, and the task is kicked off using
asyncio.create_task so as not to block before giving a response.

StorageOps now contains a method for streaming the bytes of any file in
a remote WACZ, requiring only the presigned URL for the WACZ and the
name of the file to stream.
2024-03-19 14:14:21 -07:00

123 lines
3.0 KiB
Python

""" k8s utils """
import asyncio
import atexit
import csv
import io
import json
import signal
import os
import sys
from datetime import datetime
from typing import Optional, Dict, Union, List
from fastapi import HTTPException
from fastapi.responses import StreamingResponse
from slugify import slugify
def get_templates_dir():
"""return directory containing templates for loading"""
return os.path.join(os.path.dirname(__file__), "templates")
def from_k8s_date(string):
"""convert k8s date string to datetime"""
return datetime.fromisoformat(string[:-1]) if string else None
def to_k8s_date(dt_val):
"""convert datetime to string for k8s"""
return dt_val.isoformat("T") + "Z"
def dt_now():
"""get current ts"""
return datetime.utcnow().replace(microsecond=0, tzinfo=None)
def ts_now():
"""get current ts"""
return str(dt_now())
def run_once_lock(name):
"""run once lock via temp directory
- if dir doesn't exist, return true
- if exists, return false"""
lock_dir = "/tmp/." + name
try:
os.mkdir(lock_dir)
# pylint: disable=bare-except
except:
return False
# just in case, delete dir on exit
def del_dir():
print("release lock: " + lock_dir, flush=True)
os.rmdir(lock_dir)
atexit.register(del_dir)
return True
def register_exit_handler():
"""register exit handler to exit on SIGTERM"""
loop = asyncio.get_running_loop()
def exit_handler():
"""sigterm handler"""
print("SIGTERM received, exiting")
sys.exit(1)
loop.add_signal_handler(signal.SIGTERM, exit_handler)
def parse_jsonl_error_messages(errors):
"""parse json-l error strings from redis/db into json"""
parsed_errors = []
for error_line in errors:
if not error_line:
continue
try:
result = json.loads(error_line)
parsed_errors.append(result)
except json.JSONDecodeError as err:
print(
f"Error decoding json-l error line: {error_line}. Error: {err}",
flush=True,
)
return parsed_errors
def is_bool(stri: Optional[str]) -> bool:
"""Check if the string parameter is stringly true"""
if stri:
return stri.lower() in ("true", "1", "yes")
return False
def slug_from_name(name: str) -> str:
"""Generate slug from name"""
return slugify(name.replace("'", ""))
def stream_dict_list_as_csv(data: List[Dict[str, Union[str, int]]], filename: str):
"""Stream list of dictionaries as CSV with attachment filename header"""
if not data:
raise HTTPException(status_code=404, detail="crawls_not_found")
keys = data[0].keys()
buffer = io.StringIO()
dict_writer = csv.DictWriter(buffer, keys, quoting=csv.QUOTE_NONNUMERIC)
dict_writer.writeheader()
dict_writer.writerows(data)
return StreamingResponse(
iter([buffer.getvalue()]),
media_type="text/csv",
headers={"Content-Disposition": f"attachment;filename={filename}"},
)