summaryrefslogtreecommitdiffstats
path: root/build
diff options
context:
space:
mode:
authorMilan Verespej <m.verespej@partner.samsung.com>2019-06-18 13:46:48 +0200
committerMilan Verespej <m.verespej@partner.samsung.com>2019-06-18 18:43:48 +0200
commit4c7e8924320654de60efd5096d6678549ca5ac05 (patch)
tree62ca36db448547be5036da3321f3f54204bd1787 /build
parent2e1328a8867190f203043fb5758dc8117ba3d673 (diff)
Refactor npm packages download
Series of commits to improve python download scripts. Issue-ID: OOM-1803 Change-Id: I199660ab121038780c34065f78538bb4e7b07eb5 Signed-off-by: Milan Verespej <m.verespej@partner.samsung.com>
Diffstat (limited to 'build')
-rw-r--r--build/download/http_downloader.py4
-rwxr-xr-xbuild/download/npm_downloader.py134
2 files changed, 136 insertions, 2 deletions
diff --git a/build/download/http_downloader.py b/build/download/http_downloader.py
index 69adc4dd..ba2c0f7e 100644
--- a/build/download/http_downloader.py
+++ b/build/download/http_downloader.py
@@ -36,8 +36,8 @@ log = logging.getLogger(__name__)
class HttpDownloader(ConcurrentDownloader):
- def __init__(self, *list_args, workers=None):
- super().__init__('http files', *list_args, workers=workers)
+ def __init__(self, *list_args, list_type='http_files', workers=None):
+ super().__init__(list_type, *list_args, workers=workers)
@property
def check_table(self):
diff --git a/build/download/npm_downloader.py b/build/download/npm_downloader.py
new file mode 100755
index 00000000..369af72a
--- /dev/null
+++ b/build/download/npm_downloader.py
@@ -0,0 +1,134 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# COPYRIGHT NOTICE STARTS HERE
+
+# Copyright 2019 © Samsung Electronics Co., Ltd.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# COPYRIGHT NOTICE ENDS HERE
+
+import argparse
+import datetime
+import hashlib
+import logging
+import os
+import sys
+import timeit
+
+from retrying import retry
+
+import http_downloader
+import http_file
+
+log = logging.getLogger(__name__)
+
+
+class NpmDownloader(http_downloader.HttpDownloader):
+ def __init__(self, npm_registry, *list_args, workers=None):
+ super().__init__(*list_args, list_type='npm packages', workers=workers)
+ self._registry = npm_registry
+
+ def _download_item(self, item):
+ """
+ Download npm package
+ :param item: http file to be downloaded (tuple: (npm_name@version, dst_dir))
+ """
+ log.info('Downloading: {}'.format(item[0]))
+ npm_name, npm_version = item[0].split('@')
+ dst_path = '{}/{}-{}.tgz'.format(item[1], npm_name, npm_version)
+ try:
+ tarball = http_file.HttpFile(item[0], self._get_npm(*item[0].split('@')), dst_path)
+ tarball.save_to_file()
+ except Exception as err:
+ log.exception('Failed: {}'.format(item[0]))
+ if os.path.isfile(dst_path):
+ os.remove(dst_path)
+ raise err
+ log.info('Downloaded: {}'.format(item[0]))
+
+ @retry(stop_max_attempt_number=5, wait_fixed=5000)
+ def _get_npm(self, npm_name, npm_version):
+ """
+ Download and save npm tarball to disk
+ :param npm_name: name of npm package
+ :param npm_version: version of npm package
+ """
+ npm_url = '{}/{}/{}'.format(self._registry, npm_name, npm_version)
+ npm_req = self._make_get_request(npm_url)
+ npm_json = npm_req.json()
+ tarball_url = npm_json['dist']['tarball']
+ shasum = npm_json['dist']['shasum']
+ tarball_req = self._make_get_request(tarball_url)
+ tarball = tarball_req.content
+ if hashlib.sha1(tarball).hexdigest() == shasum:
+ return tarball
+ else:
+ raise Exception(
+ '{}@{}: Wrong checksum. Retrying...'.format(npm_name, npm_version))
+
+ def _is_missing(self, item):
+ """
+ Check if item is missing (not downloaded)
+ :param item: item to check
+ :return: boolean
+ """
+ return not os.path.isfile('{}/{}-{}.tgz'.format(self._data_list[item], *item.split('@')))
+
+
+def run_cli():
+ """
+ Run as cli tool
+ """
+ parser = argparse.ArgumentParser(description='Download npm packages from list')
+ parser.add_argument('npm_list', metavar='npm-list',
+ help='File with list of npm packages to download.')
+ parser.add_argument('--registry', '-r', default='https://registry.npmjs.org',
+ help='Download destination')
+ parser.add_argument('--output-dir', '-o', default=os.getcwd(),
+ help='Download destination')
+ parser.add_argument('--check', '-c', action='store_true', default=False,
+ help='Check what is missing. No download.')
+ parser.add_argument('--debug', action='store_true', default=False,
+ help='Turn on debug output')
+ parser.add_argument('--workers', type=int, default=None,
+ help='Set maximum workers for parallel download (default: cores * 5)')
+
+ args = parser.parse_args()
+
+ if args.debug:
+ logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+ else:
+ logging.basicConfig(stream=sys.stdout, level=logging.INFO, format='%(message)s')
+
+ downloader = NpmDownloader(args.registry, [args.npm_list, args.output_dir], workers=args.workers)
+
+ if args.check:
+ log.info('Check mode. No download will be executed.')
+ log.info(downloader.check_table)
+ sys.exit(0)
+
+ timer_start = timeit.default_timer()
+ try:
+ downloader.download()
+ except RuntimeError:
+ log.error('Error occurred.')
+ sys.exit(1)
+ finally:
+ log.info('Downloading finished in {}'.format(
+ datetime.timedelta(seconds=timeit.default_timer() - timer_start)))
+
+
+if __name__ == '__main__':
+ run_cli()