pmbootstrap-meow/pmb/helpers/http.py
Oliver Smith 7269d05b20
pmb.helpers.repo.download: proper error for 404 (MR 2462)
Flush the progress bar displayed by the function before logging a
warning message for 404 not found responses from the server. Without
flushing, this message gets lost.

In addition to the warning, display a NOTE and ERROR at the end to
explain what went wrong:

  [20:16:50] Update package index for x86_64 (4 file(s))
  [20:16:51] WARNING: file not found: http://mirror.postmarketos.org/postmarketos_get_404_test/edge/main/x86_64/APKINDEX.tar.gz
  [20:16:51] NOTE: check the [mirrors] section in 'pmbootstrap config'
  [20:16:51] ERROR: getting APKINDEX from binary package mirror failed!

Without handling this properly, pmbootstrap would fail slightly later
with a much less useful error:

  [15:14:28] ERROR: expected str, bytes or os.PathLike object, not NoneType

Fixes: pmbootstrap issue 2424
2024-10-27 20:52:13 +01:00

109 lines
3.7 KiB
Python

# Copyright 2023 Oliver Smith
# SPDX-License-Identifier: GPL-3.0-or-later
import hashlib
import json
from pmb.helpers import logging
import os
from pathlib import Path
import shutil
import urllib.request
import pmb.helpers.cli
from pmb.core.context import get_context
import pmb.helpers.run
def cache_file(prefix: str, url: str) -> Path:
prefix = prefix.replace("/", "_")
return Path(f"{prefix}_{hashlib.sha256(url.encode('utf-8')).hexdigest()}")
def download(
url, prefix, cache=True, loglevel=logging.INFO, allow_404=False, flush_progress_bar_on_404=False
):
"""Download a file to disk.
:param url: the http(s) address of to the file to download
:param prefix: for the cache, to make it easier to find (cache files
get a hash of the URL after the prefix)
:param cache: if True, and url is cached, do not download it again
:param loglevel: change to logging.DEBUG to only display the download
message in 'pmbootstrap log', not in stdout.
We use this when downloading many APKINDEX files at once, no
point in showing a dozen messages.
:param allow_404: do not raise an exception when the server responds with a 404 Not Found error.
Only display a warning on stdout (no matter if loglevel is changed).
:param flush_progress_bar_on_404: download happens while a progress bar is
displayed, flush it before printing a warning for 404
:returns: path to the downloaded file in the cache or None on 404
"""
# Create cache folder
context = get_context()
if not os.path.exists(context.config.work / "cache_http"):
pmb.helpers.run.user(["mkdir", "-p", context.config.work / "cache_http"])
# Check if file exists in cache
path = context.config.work / "cache_http" / cache_file(prefix, url)
if os.path.exists(path):
if cache:
return path
pmb.helpers.run.user(["rm", path])
# Offline and not cached
if context.offline:
raise RuntimeError("File not found in cache and offline flag is" f" enabled: {url}")
# Download the file
logging.log(loglevel, "Download " + url)
try:
with urllib.request.urlopen(url) as response:
with open(path, "wb") as handle:
shutil.copyfileobj(response, handle)
# Handle 404
except urllib.error.HTTPError as e:
if e.code == 404 and allow_404:
if flush_progress_bar_on_404:
pmb.helpers.cli.progress_flush()
logging.warning("WARNING: file not found: " + url)
return None
raise
# Return path in cache
return path
def retrieve(url, headers=None, allow_404=False):
"""Fetch the content of a URL and returns it as string.
:param url: the http(s) address of to the resource to fetch
:param headers: dict of HTTP headers to use
:param allow_404: do not raise an exception when the server responds with a
404 Not Found error. Only display a warning
:returns: str with the content of the response
"""
# Download the file
logging.verbose("Retrieving " + url)
if headers is None:
headers = {}
req = urllib.request.Request(url, headers=headers)
try:
with urllib.request.urlopen(req) as response:
return response.read()
# Handle 404
except urllib.error.HTTPError as e:
if e.code == 404 and allow_404:
logging.warning("WARNING: failed to retrieve content from: " + url)
return None
raise
def retrieve_json(*args, **kwargs):
"""Fetch the contents of a URL, parse it as JSON and return it.
See retrieve() for the list of all parameters.
"""
return json.loads(retrieve(*args, **kwargs))