aboutsummaryrefslogtreecommitdiffstats
path: root/resources/tools/presentation/input_data_files.py
blob: 3ab99c3845dc341a94d183b9601c28b670524f68 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
# Copyright (c) 2018 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:
#
#     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.

"""Inputs
Download all data.
"""

import re
import requests

from os import rename, mkdir
from os.path import join
from zipfile import ZipFile, is_zipfile, BadZipfile
from httplib import responses
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry
from requests import codes, RequestException, Timeout, TooManyRedirects, \
    HTTPError, ConnectionError

from errors import PresentationError
from utils import execute_command

# Chunk size used for file download
CHUNK_SIZE = 512

# Separator used in file names
SEPARATOR = "__"

REGEX_RELEASE = re.compile(r'(\D*)(\d{4}|master)(\D*)')


def _download_file(url, file_name, log):
    """Download a file with input data.

    :param url: URL to the file to download.
    :param file_name: Name of file to download.
    :param log: List of log messages.
    :type url: str
    :type file_name: str
    :type log: list of tuples (severity, msg)
    :returns: True if the download was successful, otherwise False.
    :rtype: bool
    """

    def requests_retry_session(retries=3,
                               backoff_factor=0.3,
                               status_forcelist=(500, 502, 504)):
        """

        :param retries:
        :param backoff_factor:
        :param status_forcelist:
        :returns:
        """

        retry = Retry(
            total=retries,
            read=retries,
            connect=retries,
            backoff_factor=backoff_factor,
            status_forcelist=status_forcelist,
        )
        adapter = HTTPAdapter(max_retries=retry)
        session = requests.Session()
        session.mount('http://', adapter)
        session.mount('https://', adapter)
        return session

    success = False
    try:
        log.append(("INFO", "    Connecting to '{0}' ...".format(url)))
        response = requests_retry_session().get(url, stream=True)
        code = response.status_code
        log.append(("INFO", "    {0}: {1}".format(code, responses[code])))

        if code != codes["OK"]:
            url = url.replace("_info", "")
            log.append(("INFO", "    Connecting to '{0}' ...".format(url)))
            response = requests_retry_session().get(url, stream=True)
            code = response.status_code
            log.append(("INFO", "    {0}: {1}".format(code, responses[code])))
            if code != codes["OK"]:
                return False, file_name
            file_name = file_name.replace("_info", "")

        log.append(("INFO", "    Downloading the file '{0}' to '{1}' ...".
                    format(url, file_name)))

        with open(file_name, "wb") as file_handle:
            for chunk in response.iter_content(chunk_size=CHUNK_SIZE):
                if chunk:
                    file_handle.write(chunk)
        success = True
    except ConnectionError as err:
        log.append(("ERROR", "Not possible to connect to '{0}'.".format(url)))
        log.append(("DEBUG", repr(err)))
    except HTTPError as err:
        log.append(("ERROR", "Invalid HTTP response from '{0}'.".format(url)))
        log.append(("DEBUG", repr(err)))
    except TooManyRedirects as err:
        log.append(("ERROR", "Request exceeded the configured number "
                             "of maximum re-directions."))
        log.append(("DEBUG", repr(err)))
    except Timeout as err:
        log.append(("ERROR", "Request timed out."))
        log.append(("DEBUG", repr(err)))
    except RequestException as err:
        log.append(("ERROR", "Unexpected HTTP request exception."))
        log.append(("DEBUG", repr(err)))
    except (IOError, ValueError, KeyError) as err:
        log.append(("ERROR", "Download failed."))
        log.append(("DEBUG", repr(err)))

    log.append(("INFO", "    Download finished."))
    return success, file_name


def _unzip_file(spec, build, pid, log):
    """Unzip downloaded source file.

    :param spec: Specification read form the specification file.
    :param build: Information about the build.
    :param log: List of log messages.
    :type spec: Specification
    :type build: dict
    :type log: list of tuples (severity, msg)
    :returns: True if the download was successful, otherwise False.
    :rtype: bool
    """

    data_file = spec.input["extract"]
    file_name = build["file-name"]
    directory = spec.environment["paths"]["DIR[WORKING,DATA]"]
    tmp_dir = join(directory, str(pid))
    try:
        mkdir(tmp_dir)
    except OSError:
        pass
    new_name = "{0}{1}{2}".format(file_name.rsplit('.')[-2],
                                  SEPARATOR,
                                  data_file.split("/")[-1])

    log.append(("INFO", "    Unzipping: '{0}' from '{1}'.".
                format(data_file, file_name)))
    try:
        with ZipFile(file_name, 'r') as zip_file:
            zip_file.extract(data_file, tmp_dir)
        log.append(("INFO", "    Renaming the file '{0}' to '{1}'".
                    format(join(tmp_dir, data_file), new_name)))
        rename(join(tmp_dir, data_file), new_name)
        build["file-name"] = new_name
        return True
    except (BadZipfile, RuntimeError) as err:
        log.append(("ERROR", "Failed to unzip the file '{0}': {1}.".
                    format(file_name, str(err))))
        return False
    except OSError as err:
        log.append(("ERROR", "Failed to rename the file '{0}': {1}.".
                    format(data_file, str(err))))
        return False


def download_and_unzip_data_file(spec, job, build, pid, log):
    """Download and unzip a source file.

    :param spec: Specification read form the specification file.
    :param job: Name of the Jenkins job.
    :param build: Information about the build.
    :param pid: PID of the process executing this method.
    :param log: List of log messages.
    :type spec: Specification
    :type job: str
    :type build: dict
    :type pid: int
    :type log: list of tuples (severity, msg)
    :returns: True if the download was successful, otherwise False.
    :rtype: bool
    """

    if job.startswith("csit-"):
        if spec.input["file-name"].endswith(".zip"):
            url = spec.environment["urls"]["URL[JENKINS,CSIT]"]
        elif spec.input["file-name"].endswith(".gz"):
            url = spec.environment["urls"]["URL[NEXUS,LOG]"]
        else:
            log.append(("ERROR", "Not supported file format."))
            return False
    elif job.startswith("hc2vpp-"):
        url = spec.environment["urls"]["URL[JENKINS,HC]"]
    elif job.startswith("intel-dnv-"):
        url = spec.environment["urls"]["URL[VIRL,DNV]"].format(release=job[-4:])
    else:
        raise PresentationError("No url defined for the job '{}'.".format(job))
    file_name = spec.input["file-name"]
    full_name = spec.input["download-path"]. \
        format(job=job, build=build["build"], filename=file_name)
    if not job.startswith("intel-dnv-"):
        url = "{0}/{1}".format(url, full_name)
    new_name = join(spec.environment["paths"]["DIR[WORKING,DATA]"],
                    "{job}{sep}{build}{sep}{name}".
                    format(job=job, sep=SEPARATOR, build=build["build"],
                           name=file_name))

    # Download the file from the defined source (Jenkins, logs.fd.io):
    success, downloaded_name = _download_file(url, new_name, log)
    if success:
        new_name = downloaded_name

    if success and new_name.endswith(".zip"):
        if not is_zipfile(new_name):
            success = False

    # If not successful, download from docs.fd.io:
    if not success:
        log.append(("INFO", "    Trying to download from https://docs.fd.io:"))
        release = re.search(REGEX_RELEASE, job).group(2)
        for rls in (release, "master"):
            nexus_file_name = "{job}{sep}{build}{sep}{name}". \
                format(job=job, sep=SEPARATOR, build=build["build"],
                       name=file_name)
            try:
                rls = "rls{0}".format(int(rls))
            except ValueError:
                pass
            url = "{url}/{release}/{dir}/{file}". \
                format(url=spec.environment["urls"]["URL[NEXUS]"],
                       release=rls,
                       dir=spec.environment["urls"]["DIR[NEXUS]"],
                       file=nexus_file_name)
            success, new_name = _download_file(url, new_name, log)
            if success:
                break

    if success:
        build["file-name"] = new_name
    else:
        return False

    if spec.input["file-name"].endswith(".gz"):
        if "docs.fd.io" in url:
            execute_command("gzip --decompress --keep --force {0}".
                            format(new_name))
        else:
            rename(new_name, new_name[:-3])
            if spec.configuration.get("archive-inputs", True):
                execute_command("gzip --keep {0}".format(new_name[:-3]))
        build["file-name"] = new_name[:-3]

    if new_name.endswith(".zip"):
        if is_zipfile(new_name):
            return _unzip_file(spec, build, pid, log)
        else:
            log.append(("ERROR",
                        "Zip file '{0}' is corrupted.".format(new_name)))
            return False
    else:
        return True