From a4ee241eec7f8a4670fef7b17c181f5c1d934e18 Mon Sep 17 00:00:00 2001 From: Tibor Frank Date: Thu, 15 Apr 2021 13:38:01 +0200 Subject: PAL: Add a new download path - "{job}/{build}/{filename}" Change-Id: Ibdd86a708e17df32b4866e058614da5e9814a8f0 Signed-off-by: Tibor Frank (cherry picked from commit 82a13664db8e18e12ccff542e24e5a0dbe2fbce4) --- resources/tools/presentation/input_data_files.py | 150 ++++++++++++--------- resources/tools/presentation/specification.yaml | 6 +- .../tools/presentation/specification_CPTA.yaml | 7 +- .../tools/presentation/specification_local.yaml | 4 +- 4 files changed, 99 insertions(+), 68 deletions(-) diff --git a/resources/tools/presentation/input_data_files.py b/resources/tools/presentation/input_data_files.py index 8b941f2f94..d4cc8c64e6 100644 --- a/resources/tools/presentation/input_data_files.py +++ b/resources/tools/presentation/input_data_files.py @@ -1,4 +1,4 @@ -# Copyright (c) 2020 Cisco and/or its affiliates. +# Copyright (c) 2021 Cisco and/or its affiliates. # 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: @@ -21,7 +21,7 @@ import gzip from os import rename, mkdir from os.path import join -from http.client import responses +from http.client import responses, HTTPException from zipfile import ZipFile, is_zipfile, BadZipfile import requests @@ -30,6 +30,8 @@ from requests.adapters import HTTPAdapter, Retry from requests.exceptions import RequestException from requests import codes +from urllib3.exceptions import HTTPError + from pal_errors import PresentationError @@ -42,15 +44,19 @@ SEPARATOR = u"__" REGEX_RELEASE = re.compile(r'(\D*)(\d{4}|master)(\D*)') -def _download_file(url, file_name, arch=False): +def _download_file(url, file_name, arch=False, verify=True, repeat=1): """Download a file with input data. :param url: URL to the file to download. :param file_name: Name of file to download. - :param arch: If True, also .gz file is downloaded + :param arch: If True, also .gz file is downloaded. + :param verify: If true, verify the certificate. + :param repeat: The number of attempts to download the file. :type url: str :type file_name: str :type arch: bool + :type verify: bool + :type repeat: int :returns: True if the download was successful, otherwise False. :rtype: bool """ @@ -86,56 +92,62 @@ def _download_file(url, file_name, arch=False): return session success = False - session = None - try: - logging.info(f" Connecting to {url} ...") - session = requests_retry_session() - response = session.get(url, stream=True) - code = response.status_code - logging.info(f" {code}: {responses[code]}") - - if code != codes[u"OK"]: - if session: - session.close() - url = url.replace(u"_info", u"") + while repeat: + repeat -= 1 + session = None + try: logging.info(f" Connecting to {url} ...") session = requests_retry_session() - response = session.get(url, stream=True) + response = session.get(url, stream=True, verify=verify) code = response.status_code logging.info(f" {code}: {responses[code]}") - if code != codes[u"OK"]: - return False, file_name - file_name = file_name.replace(u"_info", u"") - - dst_file_name = file_name.replace(u".gz", u"") - logging.info(f" Downloading the file {url} to {dst_file_name} ...") - with open(dst_file_name, u"wb") as file_handle: - for chunk in response.iter_content(chunk_size=CHUNK_SIZE): - if chunk: - file_handle.write(chunk) - if arch and u".gz" in file_name: + if code != codes[u"OK"]: + if session: + session.close() + url = url.replace(u"_info", u"") + logging.info(f" Connecting to {url} ...") + session = requests_retry_session() + response = session.get(url, stream=True, verify=verify) + code = response.status_code + logging.info(f" {code}: {responses[code]}") + if code != codes[u"OK"]: + return False, file_name + file_name = file_name.replace(u"_info", u"") + + dst_file_name = file_name.replace(u".gz", u"") + logging.info(f" Downloading the file {url} to {dst_file_name}") + with open(dst_file_name, u"wb") as file_handle: + for chunk in response.iter_content(chunk_size=CHUNK_SIZE): + if chunk: + file_handle.write(chunk) + + if arch and u".gz" in file_name: + if session: + session.close() + logging.info(f" Downloading the file {url} to {file_name}") + session = requests_retry_session() + response = session.get(url, stream=True, verify=verify) + if response.status_code == codes[u"OK"]: + with open(file_name, u"wb") as file_handle: + file_handle.write(response.raw.read()) + else: + logging.error( + f"Not possible to download the file " + f"{url} to {file_name}" + ) + + success = True + repeat = 0 + except (HTTPException, HTTPError) as err: + logging.error(f"Connection broken:\n{repr(err)}") + except RequestException as err: + logging.error(f"HTTP Request exception:\n{repr(err)}") + except (IOError, ValueError, KeyError) as err: + logging.error(f"Download failed.\n{repr(err)}") + finally: if session: session.close() - logging.info(f" Downloading the file {url} to {file_name} ...") - session = requests_retry_session() - response = session.get(url, stream=True) - if response.status_code == codes[u"OK"]: - with open(file_name, u"wb") as file_handle: - file_handle.write(response.raw.read()) - else: - logging.error( - f"Not possible to download the file {url} to {file_name}" - ) - - success = True - except RequestException as err: - logging.error(f"HTTP Request exception:\n{repr(err)}") - except (IOError, ValueError, KeyError) as err: - logging.error(f"Download failed.\n{repr(err)}") - finally: - if session: - session.close() logging.info(u" Download finished.") return success, file_name @@ -200,27 +212,44 @@ def download_and_unzip_data_file(spec, job, build, pid): :rtype: bool """ - # Try to download .gz from logs.fd.io + success = False file_name = spec.input[u"file-name"] - url = u"{0}/{1}".format( - spec.environment[u'urls'][u'URL[NEXUS,LOG]'], - spec.input[u'download-path'].format( - job=job, build=build[u'build'], filename=file_name - ) - ) new_name = join( spec.environment[u"paths"][u"DIR[WORKING,DATA]"], f"{job}{SEPARATOR}{build[u'build']}{SEPARATOR}{file_name}" ) - - logging.info(f"Trying to download {url}") - arch = bool(spec.configuration.get(u"archive-inputs", True)) - success, downloaded_name = _download_file(url, new_name, arch=arch) + downloaded_name = u"" + + # Try to download .gz from s3_storage + for path in spec.input[u'download-path']: + url = u"{0}/{1}".format( + spec.environment[u'urls'][u'URL[S3_STORAGE,LOG]'], + path.format(job=job, build=build[u'build'], filename=file_name) + ) + logging.info(f"Trying to download {url}") + success, downloaded_name = _download_file( + url, new_name, arch=arch, verify=False, repeat=3 + ) + if success: + break if not success: + # Try to download .gz from logs.fd.io + for path in spec.input[u'download-path']: + url = u"{0}/{1}".format( + spec.environment[u'urls'][u'URL[NEXUS,LOG]'], + path.format(job=job, build=build[u'build'], filename=file_name) + ) + logging.info(f"Trying to download {url}") + success, downloaded_name = _download_file( + url, new_name, arch=arch, verify=True, repeat=3 + ) + if success: + break + if not success: # Try to download .gz or .zip from docs.fd.io file_name = (spec.input[u"file-name"], spec.input[u"zip-file-name"]) release = re.search(REGEX_RELEASE, job).group(2) @@ -254,14 +283,11 @@ def download_and_unzip_data_file(spec, job, build, pid): break if not success: - # Try to download .zip from jenkins.fd.io file_name = spec.input[u"zip-file-name"] download_path = spec.input[u"zip-download-path"] if job.startswith(u"csit-"): url = spec.environment[u"urls"][u"URL[JENKINS,CSIT]"] - elif job.startswith(u"hc2vpp-"): - url = spec.environment[u"urls"][u"URL[JENKINS,HC]"] else: raise PresentationError(f"No url defined for the job {job}.") @@ -273,9 +299,7 @@ def download_and_unzip_data_file(spec, job, build, pid): spec.environment[u"paths"][u"DIR[WORKING,DATA]"], f"{job}{SEPARATOR}{build[u'build']}{SEPARATOR}{file_name}" ) - logging.info(f"Downloading {url}") - success, downloaded_name = _download_file(url, new_name) if success and downloaded_name.endswith(u".zip"): diff --git a/resources/tools/presentation/specification.yaml b/resources/tools/presentation/specification.yaml index 59013e54a0..6984d052e0 100644 --- a/resources/tools/presentation/specification.yaml +++ b/resources/tools/presentation/specification.yaml @@ -98,7 +98,7 @@ urls: URL[JENKINS,CSIT]: "https://jenkins.fd.io/view/csit/job" - URL[JENKINS,HC]: "https://jenkins.fd.io/view/hc2vpp/job" + URL[S3_STORAGE,LOG]: "https://logs.nginx.service.consul/vex-yul-rot-jenkins-1" URL[NEXUS,LOG]: "https://logs.fd.io/production/vex-yul-rot-jenkins-1" URL[NEXUS,DOC]: "https://docs.fd.io/csit" DIR[NEXUS,DOC]: "report/_static/archive" @@ -2559,7 +2559,9 @@ arch-file-format: - ".gz" - ".zip" - download-path: "{job}/{build}/archives/{filename}" + download-path: + - "{job}/{build}/{filename}" + - "{job}/{build}/archives/{filename}" extract: "output.xml" zip-file-name: "robot-plugin.zip" diff --git a/resources/tools/presentation/specification_CPTA.yaml b/resources/tools/presentation/specification_CPTA.yaml index 41d5987201..82b6ed6362 100644 --- a/resources/tools/presentation/specification_CPTA.yaml +++ b/resources/tools/presentation/specification_CPTA.yaml @@ -1,4 +1,4 @@ -# Copyright (c) 2020 Cisco and/or its affiliates. +# Copyright (c) 2021 Cisco and/or its affiliates. # 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: @@ -44,6 +44,7 @@ urls: URL[JENKINS,CSIT]: "https://jenkins.fd.io/view/csit/job" + URL[S3_STORAGE,LOG]: "https://logs.nginx.service.consul/vex-yul-rot-jenkins-1" URL[NEXUS,LOG]: "https://logs.fd.io/production/vex-yul-rot-jenkins-1" URL[NEXUS,DOC]: "https://docs.fd.io/csit" DIR[NEXUS,DOC]: "trending/_static/archive" @@ -341,7 +342,9 @@ general: file-name: "output_info.xml.gz" file-format: ".gz" - download-path: "{job}/{build}/archives/{filename}" + download-path: + - "{job}/{build}/archives/{filename}" + - "{job}/{build}/{filename}" extract: "output.xml" # Number of days from now to the past. Only files generated in this # time period are used. diff --git a/resources/tools/presentation/specification_local.yaml b/resources/tools/presentation/specification_local.yaml index 393228c1a5..1971919532 100644 --- a/resources/tools/presentation/specification_local.yaml +++ b/resources/tools/presentation/specification_local.yaml @@ -892,7 +892,9 @@ arch-file-format: - ".gz" - ".zip" - download-path: "{job}/{build}/archives/{filename}" + download-path: + - "{job}/{build}/archives/{filename}" + - "{job}/{build}/{filename}" extract: "output.xml" # Specifies the secondary source - Jenkins, it is used if the source file -- cgit 1.2.3-korg