traces: new yaml format
[piglit.git] / framework / replay / download_utils.py
blob36322b000b6fb77d5921ef524fc2d458e5b1d78c
1 # coding=utf-8
3 # Copyright © 2020, 2022 Collabora Ltd
4 # Copyright © 2020 Valve Corporation.
6 # Permission is hereby granted, free of charge, to any person obtaining a
7 # copy of this software and associated documentation files (the "Software"),
8 # to deal in the Software without restriction, including without limitation
9 # the rights to use, copy, modify, merge, publish, distribute, sublicense,
10 # and/or sell copies of the Software, and to permit persons to whom the
11 # Software is furnished to do so, subject to the following conditions:
13 # The above copyright notice and this permission notice shall be included
14 # in all copies or substantial portions of the Software.
16 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
17 # OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
19 # THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
20 # OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
21 # ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
22 # OTHER DEALINGS IN THE SOFTWARE.
24 # SPDX-License-Identifier: MIT
26 import base64
27 import hashlib
28 import hmac
29 import xml.etree.ElementTree as ET
31 from typing import Dict
32 from email.utils import formatdate
33 from os import path
34 from time import time
35 import requests
36 from requests.adapters import HTTPAdapter, Retry
37 from framework.replay.local_file_adapter import LocalFileAdapter
38 from requests.utils import requote_uri
40 from framework import core, exceptions
41 from framework.replay.options import OPTIONS
44 __all__ = ['ensure_file']
46 minio_credentials = None
49 def sign_with_hmac(key, message):
50 key = key.encode("UTF-8")
51 message = message.encode("UTF-8")
53 signature = hmac.new(key, message, hashlib.sha1).digest()
55 return base64.encodebytes(signature).strip().decode()
58 def get_minio_credentials(url):
59 global minio_credentials
61 if minio_credentials is not None:
62 return (minio_credentials['AccessKeyId'],
63 minio_credentials['SecretAccessKey'],
64 minio_credentials['SessionToken'])
66 minio_credentials = {}
68 params = {'Action': 'AssumeRoleWithWebIdentity',
69 'Version': '2011-06-15',
70 'RoleArn': 'arn:aws:iam::123456789012:role/FederatedWebIdentityRole',
71 'RoleSessionName': OPTIONS.download['role_session_name'],
72 'DurationSeconds': 3600,
73 'WebIdentityToken': OPTIONS.download['jwt']}
74 r = requests.post('https://%s' % OPTIONS.download['minio_host'], params=params)
75 if r.status_code >= 400:
76 print(r.text)
77 r.raise_for_status()
79 root = ET.fromstring(r.text)
80 for attr in root.iter():
81 if attr.tag == '{https://sts.amazonaws.com/doc/2011-06-15/}AccessKeyId':
82 minio_credentials['AccessKeyId'] = attr.text
83 elif attr.tag == '{https://sts.amazonaws.com/doc/2011-06-15/}SecretAccessKey':
84 minio_credentials['SecretAccessKey'] = attr.text
85 elif attr.tag == '{https://sts.amazonaws.com/doc/2011-06-15/}SessionToken':
86 minio_credentials['SessionToken'] = attr.text
88 return (minio_credentials['AccessKeyId'],
89 minio_credentials['SecretAccessKey'],
90 minio_credentials['SessionToken'])
93 def get_authorization_headers(url, resource):
94 minio_key, minio_secret, minio_token = get_minio_credentials(url)
96 date = formatdate(timeval=None, localtime=False, usegmt=True)
97 to_sign = "GET\n\n\n%s\nx-amz-security-token:%s\n/%s/%s" % (date,
98 minio_token,
99 OPTIONS.download['minio_bucket'],
100 requote_uri(resource))
101 signature = sign_with_hmac(minio_secret, to_sign)
103 headers = {'Host': OPTIONS.download['minio_host'],
104 'Date': date,
105 'Authorization': 'AWS %s:%s' % (minio_key, signature),
106 'x-amz-security-token': minio_token}
107 return headers
110 def download(url: str, file_path: str, headers: Dict[str, str], attempts: int = 2) -> None:
111 """Downloads a URL content into a file
113 :param url: URL to download
114 :param file_path: Local file name to contain the data downloaded
115 :param attempts: Number of attempts
117 retries = Retry(
118 connect=attempts,
119 read=attempts,
120 redirect=attempts,
121 raise_on_redirect=False
123 session = requests.Session()
124 for protocol in ["http://", "https://"]:
125 adapter = HTTPAdapter(max_retries=retries)
126 session.mount(protocol, adapter)
127 for protocol in ["file://"]:
128 file_adapter = LocalFileAdapter()
129 session.mount(protocol, file_adapter)
131 with session.get(url,
132 allow_redirects=True,
133 stream=True,
134 headers=headers) as req:
135 with open(file_path, "wb") as file:
136 req.raise_for_status()
137 for chunk in req.iter_content(chunk_size=1048576):
138 if chunk:
139 file.write(chunk)
141 # Checking file integrity
142 try:
143 file_size = int(req.headers["Content-length"])
144 except KeyError:
145 print("Error getting Content-Length from server. "
146 "Skipping file size check.")
147 return
149 if file_size != path.getsize(file_path):
150 raise exceptions.PiglitFatalError(
151 f"Invalid filesize src {file_size}"
152 f"doesn't match {path.getsize(file_path)}"
156 def ensure_file(file_path):
157 destination_file_path = path.join(OPTIONS.db_path, file_path)
158 if OPTIONS.download['url'] is None:
159 if not path.exists(destination_file_path):
160 raise exceptions.PiglitFatalError(
161 '{} missing'.format(destination_file_path))
162 return
164 url = OPTIONS.download['url'].geturl()
166 if OPTIONS.download['caching_proxy_url'] is not None:
167 url = OPTIONS.download['caching_proxy_url'].geturl() + url
169 core.check_dir(path.dirname(destination_file_path))
171 if not OPTIONS.download['force'] and path.exists(destination_file_path):
172 return
174 print('[check_image] Downloading file {}'.format(
175 file_path), end=' ', flush=True)
177 if OPTIONS.download['minio_host']:
178 assert OPTIONS.download['minio_bucket']
179 assert OPTIONS.download['role_session_name']
180 assert OPTIONS.download['jwt']
181 headers = get_authorization_headers(url, file_path)
182 else:
183 headers = None
185 download_time = time()
187 download(url + file_path, destination_file_path, headers)
189 print('took %ds.' % (time() - download_time), flush=True)