ClickHouse/tests/ci/build_download_helper.py

95 lines
3.7 KiB
Python
Raw Normal View History

2021-11-12 11:07:54 +00:00
#!/usr/bin/env python3
import os
import json
import logging
import sys
import time
import requests
from ci_config import CI_CONFIG
2021-11-12 11:07:54 +00:00
DOWNLOAD_RETRIES_COUNT = 5
def get_build_name_for_check(check_name):
return CI_CONFIG['tests_config'][check_name]['required_build']
2021-11-12 11:07:54 +00:00
def get_build_urls(build_name, reports_path):
2021-11-12 11:07:54 +00:00
for root, _, files in os.walk(reports_path):
for f in files:
if build_name in f :
2021-11-12 11:07:54 +00:00
logging.info("Found build report json %s", f)
with open(os.path.join(root, f), 'r', encoding='utf-8') as file_handler:
build_report = json.load(file_handler)
return build_report['build_urls']
return []
def dowload_build_with_progress(url, path):
logging.info("Downloading from %s to temp path %s", url, path)
for i in range(DOWNLOAD_RETRIES_COUNT):
try:
with open(path, 'wb') as f:
response = requests.get(url, stream=True)
response.raise_for_status()
total_length = response.headers.get('content-length')
if total_length is None or int(total_length) == 0:
logging.info("No content-length, will download file without progress")
f.write(response.content)
else:
dl = 0
total_length = int(total_length)
logging.info("Content length is %ld bytes", total_length)
for data in response.iter_content(chunk_size=4096):
dl += len(data)
f.write(data)
if sys.stdout.isatty():
done = int(50 * dl / total_length)
percent = int(100 * float(dl) / total_length)
eq_str = '=' * done
space_str = ' ' * (50 - done)
sys.stdout.write(f"\r[{eq_str}{space_str}] {percent}%")
sys.stdout.flush()
break
except Exception as ex:
sys.stdout.write("\n")
time.sleep(3)
logging.info("Exception while downloading %s, retry %s", ex, i + 1)
if os.path.exists(path):
os.remove(path)
else:
raise Exception(f"Cannot download dataset from {url}, all retries exceeded")
sys.stdout.write("\n")
logging.info("Downloading finished")
def download_builds(result_path, build_urls, filter_fn):
for url in build_urls:
if filter_fn(url):
fname = os.path.basename(url.replace('%2B', '+').replace('%20', ' '))
logging.info("Will download %s to %s", fname, result_path)
dowload_build_with_progress(url, os.path.join(result_path, fname))
def download_builds_filter(check_name, reports_path, result_path, filter_fn=lambda _: True):
build_name = get_build_name_for_check(check_name)
urls = get_build_urls(build_name, reports_path)
2021-11-12 19:57:26 +00:00
print(urls)
2021-11-12 11:07:54 +00:00
if not urls:
raise Exception("No build URLs found")
download_builds(result_path, urls, filter_fn)
def download_all_deb_packages(check_name, reports_path, result_path):
download_builds_filter(check_name, reports_path, result_path, lambda x: x.endswith('deb'))
def download_shared_build(check_name, reports_path, result_path):
download_builds_filter(check_name, reports_path, result_path, lambda x: x.endswith('shared_build.tgz'))
def download_unit_tests(check_name, reports_path, result_path):
download_builds_filter(check_name, reports_path, result_path, lambda x: x.endswith('unit_tests_dbms'))
def download_clickhouse_binary(check_name, reports_path, result_path):
download_builds_filter(check_name, reports_path, result_path, lambda x: x.endswith('clickhouse'))