def _prepare_download(
resp: Response,
link: Link,
progress_bar: str,
) -> Iterable[bytes]:
total_length = _get_http_response_size(resp)
if link.netloc == PyPI.file_storage_domain:
url = link.show_url
else:
url = link.url_without_fragment
logged_url = redact_auth_from_url(url)
if total_length:
logged_url = "{} ({})".format(logged_url, format_size(total_length))
if is_from_cache(resp):
logger.info("Using cached %s", logged_url)
else:
logger.info("Downloading %s", logged_url)
if logger.getEffectiveLevel() > logging.INFO:
show_progress = False
elif is_from_cache(resp):
show_progress = False
elif not total_length:
show_progress = True
elif total_length > (40 * 1000):
show_progress = True
else:
show_progress = False
chunks = response_chunks(resp, CONTENT_CHUNK_SIZE)
if not show_progress:
return chunks
renderer = get_download_progress_renderer(bar_type=progress_bar, size=total_length)
return renderer(chunks)
def _prepare_download(
resp, # type: Response
link, # type: Link
progress_bar # type: str
):
# type: (...) -> Iterable[bytes]
total_length = _get_http_response_size(resp)
if link.netloc == PyPI.file_storage_domain:
url = link.show_url
else:
url = link.url_without_fragment
logged_url = redact_auth_from_url(url)
if total_length:
logged_url = '{} ({})'.format(logged_url, format_size(total_length))
if is_from_cache(resp):
logger.info("Using cached %s", logged_url)
else:
logger.info("Downloading %s", logged_url)
if logger.getEffectiveLevel() > logging.INFO:
show_progress = False
elif is_from_cache(resp):
show_progress = False
elif not total_length:
show_progress = True
elif total_length > (40 * 1000):
show_progress = True
else:
show_progress = False
chunks = response_chunks(resp, CONTENT_CHUNK_SIZE)
if not show_progress:
return chunks
return DownloadProgressProvider(progress_bar, max=total_length)(chunks)
def download_speed(self):
# Avoid zero division errors...
if self.avg == 0.0:
return "..."
return format_size(1 / self.avg) + "/s"
def downloaded(self):
return format_size(self.index)
def format_directory_size(path: str) -> str:
return format_size(directory_size(path))
def format_file_size(path: str) -> str:
return format_size(file_size(path))
def _download_url(resp, link, content_file, hashes, progress_bar):
try:
total_length = int(resp.headers['content-length'])
except (ValueError, KeyError, TypeError):
total_length = 0
cached_resp = getattr(resp, "from_cache", False)
if logger.getEffectiveLevel() > logging.INFO:
show_progress = False
elif cached_resp:
show_progress = False
elif total_length > (40 * 1000):
show_progress = True
elif not total_length:
show_progress = True
else:
show_progress = False
show_url = link.show_url
def resp_read(chunk_size):
try:
# Special case for urllib3.
for chunk in resp.raw.stream(
chunk_size,
# We use decode_content=False here because we don't
# want urllib3 to mess with the raw bytes we get
# from the server. If we decompress inside of
# urllib3 then we cannot verify the checksum
# because the checksum will be of the compressed
# file. This breakage will only occur if the
# server adds a Content-Encoding header, which
# depends on how the server was configured:
# - Some servers will notice that the file isn't a
# compressible file and will leave the file alone
# and with an empty Content-Encoding
# - Some servers will notice that the file is
# already compressed and will leave the file
# alone and will add a Content-Encoding: gzip
# header
# - Some servers won't notice anything at all and
# will take a file that's already been compressed
# and compress it again and set the
# Content-Encoding: gzip header
#
# By setting this not to decode automatically we
# hope to eliminate problems with the second case.
decode_content=False):
yield chunk
except AttributeError:
# Standard file-like object.
while True:
chunk = resp.raw.read(chunk_size)
if not chunk:
break
yield chunk
def written_chunks(chunks):
for chunk in chunks:
content_file.write(chunk)
yield chunk
progress_indicator = _progress_indicator
if link.netloc == PyPI.netloc:
url = show_url
else:
url = link.url_without_fragment
if show_progress: # We don't show progress on cached responses
progress_indicator = DownloadProgressProvider(progress_bar,
max=total_length)
if total_length:
logger.info("Downloading %s (%s)", url, format_size(total_length))
else:
logger.info("Downloading %s", url)
elif cached_resp:
logger.info("Using cached %s", url)
else:
logger.info("Downloading %s", url)
logger.debug('Downloading from URL %s', link)
downloaded_chunks = written_chunks(
progress_indicator(resp_read(CONTENT_CHUNK_SIZE), CONTENT_CHUNK_SIZE))
if hashes:
hashes.check_against_chunks(downloaded_chunks)
else:
consume(downloaded_chunks)
def download_speed(self):
# Avoid zero division errors...
if self.avg == 0.0:
return "..."
return format_size(1 / self.avg) + "/s"
def downloaded(self):
return format_size(self.index)
def download_speed(self) -> str:
# Avoid zero division errors...
if self.avg == 0.0: # type: ignore
return "..."
return format_size(1 / self.avg) + "/s" # type: ignore
def downloaded(self) -> str:
return format_size(self.index) # type: ignore
def _download_url(resp, link, content_file, hashes, progress_bar):
try:
total_length = int(resp.headers['content-length'])
except (ValueError, KeyError, TypeError):
total_length = 0
cached_resp = getattr(resp, "from_cache", False)
if logger.getEffectiveLevel() > logging.INFO:
show_progress = False
elif cached_resp:
show_progress = False
elif total_length > (40 * 1000):
show_progress = True
elif not total_length:
show_progress = True
else:
show_progress = False
show_url = link.show_url
def resp_read(chunk_size):
try:
# Special case for urllib3.
for chunk in resp.raw.stream(
chunk_size,
# We use decode_content=False here because we don't
# want urllib3 to mess with the raw bytes we get
# from the server. If we decompress inside of
# urllib3 then we cannot verify the checksum
# because the checksum will be of the compressed
# file. This breakage will only occur if the
# server adds a Content-Encoding header, which
# depends on how the server was configured:
# - Some servers will notice that the file isn't a
# compressible file and will leave the file alone
# and with an empty Content-Encoding
# - Some servers will notice that the file is
# already compressed and will leave the file
# alone and will add a Content-Encoding: gzip
# header
# - Some servers won't notice anything at all and
# will take a file that's already been compressed
# and compress it again and set the
# Content-Encoding: gzip header
#
# By setting this not to decode automatically we
# hope to eliminate problems with the second case.
decode_content=False):
yield chunk
except AttributeError:
# Standard file-like object.
while True:
chunk = resp.raw.read(chunk_size)
if not chunk:
break
yield chunk
def written_chunks(chunks):
for chunk in chunks:
content_file.write(chunk)
yield chunk
progress_indicator = _progress_indicator
if link.netloc == PyPI.netloc:
url = show_url
else:
url = link.url_without_fragment
if show_progress: # We don't show progress on cached responses
progress_indicator = DownloadProgressProvider(progress_bar,
max=total_length)
if total_length:
logger.info("Downloading %s (%s)", url, format_size(total_length))
else:
logger.info("Downloading %s", url)
elif cached_resp:
logger.info("Using cached %s", url)
else:
logger.info("Downloading %s", url)
logger.debug('Downloading from URL %s', link)
downloaded_chunks = written_chunks(
progress_indicator(
resp_read(CONTENT_CHUNK_SIZE),
CONTENT_CHUNK_SIZE
)
)
if hashes:
hashes.check_against_chunks(downloaded_chunks)
else:
consume(downloaded_chunks)
