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
|
# Copyright (c) 2017 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 gzip
import logging
from os import rename, remove
from os.path import join, getsize
from shutil import move
from zipfile import ZipFile, is_zipfile, BadZipfile
from httplib import responses
from requests import get, codes, RequestException, Timeout, TooManyRedirects, \
HTTPError, ConnectionError
from errors import PresentationError
# 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_data_files(spec):
"""Download all data specified in the specification file in the section
type: input --> builds.
:param spec: Specification.
:type spec: Specification
:raises: PresentationError if there is no url defined for the job.
"""
for job, builds in spec.builds.items():
for build in builds:
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:
logging.error("Not supported file format.")
continue
elif job.startswith("hc2vpp-"):
url = spec.environment["urls"]["URL[JENKINS,HC]"]
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)
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))
logging.info(
"Downloading the file '{0}' to '{1}' ...".format(url, new_name))
status = "failed"
try:
response = get(url, stream=True)
code = response.status_code
# temporary workaround, remove when output.log.xml is not needed
if code != codes["OK"] and \
spec.input["file-name"].endswith(".gz"):
url = '.'.join(url.split('.')[:-1]) + ".log.gz"
response = get(url, stream=True)
code = response.status_code
if code != codes["OK"]:
logging.warning(
"Jenkins: {0}: {1}.".format(code, responses[code]))
logging.info("Trying to download from Nexus:")
spec.set_input_state(job, build["build"], "not found")
if code == codes["not_found"]:
release = re.search(REGEX_RELEASE, job).group(2)
nexus_file_name = "{job}{sep}{build}{sep}{name}".\
format(job=job, sep=SEPARATOR, build=build["build"],
name=file_name)
url = "{url}/rls{release}/{dir}/{file}".\
format(url=spec.environment["urls"]["URL[NEXUS]"],
release=release,
dir=spec.environment["urls"]["DIR[NEXUS]"],
file=nexus_file_name)
logging.info("Downloading the file '{0}' to '{1}' ...".
format(url, new_name))
response = get(url, stream=True)
code = response.status_code
if code != codes["OK"]:
logging.error(
"Nexus: {0}: {1}".format(code, responses[code]))
spec.set_input_state(
job, build["build"], "not found")
continue
file_handle = open(new_name, "wb")
for chunk in response.iter_content(chunk_size=CHUNK_SIZE):
if chunk:
file_handle.write(chunk)
file_handle.close()
if spec.input["file-name"].endswith(".zip"):
expected_length = None
try:
expected_length = int(response.
headers["Content-Length"])
logging.debug(" Expected file size: {0}B".
format(expected_length))
except KeyError:
logging.debug(" No information about expected size.")
real_length = getsize(new_name)
logging.debug(" Downloaded size: {0}B".format(real_length))
if expected_length:
if real_length == expected_length:
status = "downloaded"
logging.info("{0}: {1}".format(code,
responses[code]))
else:
logging.error("The file size differs from the "
"expected size.")
else:
status = "downloaded"
logging.info("{0}: {1}".format(code, responses[code]))
elif spec.input["file-name"].endswith(".gz"):
rename(new_name, new_name[:-3])
with open(new_name[:-3], 'r') as xml_file:
with gzip.open(new_name, 'wb') as gz_file:
gz_file.write(xml_file.read())
new_name = new_name[:-3]
status = "downloaded"
logging.info("{0}: {1}".format(code, responses[code]))
except ConnectionError as err:
logging.error("Not possible to connect to '{0}'.".format(url))
logging.debug(err)
except HTTPError as err:
logging.error("Invalid HTTP response from '{0}'.".format(url))
logging.debug(err)
except TooManyRedirects as err:
logging.error("Request exceeded the configured number "
"of maximum re-directions.")
logging.debug(err)
except Timeout as err:
logging.error("Request timed out.")
logging.debug(err)
except RequestException as err:
logging.error("Unexpected HTTP request exception.")
logging.debug(err)
except (IOError, ValueError, KeyError) as err:
logging.error("Download failed.")
logging.debug("Reason: {0}".format(err))
spec.set_input_state(job, build["build"], status)
spec.set_input_file_name(job, build["build"], new_name)
if status == "failed":
logging.info("Removing the file '{0}'".format(new_name))
try:
remove(new_name)
except OSError as err:
logging.warning(str(err))
spec.set_input_file_name(job, build["build"], None)
unzip_files(spec)
def unzip_files(spec):
"""Unzip downloaded zip files
:param spec: Specification.
:type spec: Specification
:raises: PresentationError if the zip file does not exist or it is not a
zip file.
"""
if spec.is_debug:
data_file = spec.debug["extract"]
else:
data_file = spec.input["extract"]
for job, builds in spec.builds.items():
for build in builds:
if build["status"] == "failed" or build["status"] == "not found":
continue
try:
status = "failed"
directory = spec.environment["paths"]["DIR[WORKING,DATA]"]
file_name = join(build["file-name"])
if build["status"] == "downloaded":
logging.info("Unziping: '{0}' from '{1}'.".
format(data_file, file_name))
new_name = "{0}{1}{2}".format(file_name.rsplit('.')[-2],
SEPARATOR,
data_file.split("/")[-1])
try:
if is_zipfile(file_name):
with ZipFile(file_name, 'r') as zip_file:
zip_file.extract(data_file, directory)
logging.info("Moving {0} to {1} ...".
format(join(directory, data_file),
directory))
move(join(directory, data_file), directory)
logging.info("Renaming the file '{0}' to '{1}'".
format(join(directory,
data_file.split("/")[-1]),
new_name))
rename(join(directory, data_file.split("/")[-1]),
new_name)
spec.set_input_file_name(job, build["build"],
new_name)
status = "unzipped"
spec.set_input_state(job, build["build"], status)
except (BadZipfile, RuntimeError) as err:
logging.error("Failed to unzip the file '{0}': {1}.".
format(file_name, str(err)))
except OSError as err:
logging.error("Failed to rename the file '{0}': {1}.".
format(data_file, str(err)))
finally:
if status == "failed":
spec.set_input_file_name(job, build["build"], None)
else:
raise PresentationError("The file '{0}' does not exist or "
"it is not a zip file".
format(file_name))
spec.set_input_state(job, build["build"], status)
except KeyError:
pass
|
