summaryrefslogtreecommitdiffstats
path: root/hacking/azp/download.py
blob: 117e9da5b7a3891572c1b44aa9031b272432668b (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
#!/usr/bin/env python
# PYTHON_ARGCOMPLETE_OK

# (c) 2016 Red Hat, Inc.
#
# This file is part of Ansible
#
# Ansible is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# Ansible is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Ansible.  If not, see <http://www.gnu.org/licenses/>.
"""CLI tool for downloading results from Azure Pipelines CI runs."""

from __future__ import (absolute_import, division, print_function)
__metaclass__ = type

# noinspection PyCompatibility
import argparse
import json
import os
import re
import sys
import io
import zipfile

import requests

try:
    import argcomplete
except ImportError:
    argcomplete = None

# Following changes should be made to improve the overall style:
# TODO use new style formatting method.
# TODO use requests session.
# TODO type hints.
# TODO pathlib.


def main():
    """Main program body."""

    args = parse_args()
    download_run(args)


def run_id_arg(arg):
    m = re.fullmatch(r"(?:https:\/\/dev\.azure\.com\/ansible\/ansible\/_build\/results\?buildId=)?(\d+)", arg)
    if not m:
        raise ValueError("run does not seems to be a URI or an ID")
    return m.group(1)


def parse_args():
    """Parse and return args."""

    parser = argparse.ArgumentParser(description='Download results from a CI run.')

    parser.add_argument('run', metavar='RUN', type=run_id_arg, help='AZP run id or URI')

    parser.add_argument('-v', '--verbose',
                        dest='verbose',
                        action='store_true',
                        help='show what is being downloaded')

    parser.add_argument('-t', '--test',
                        dest='test',
                        action='store_true',
                        help='show what would be downloaded without downloading')

    parser.add_argument('-p', '--pipeline-id', type=int, default=20, help='pipeline to download the job from')

    parser.add_argument('--artifacts',
                        action='store_true',
                        help='download artifacts')

    parser.add_argument('--console-logs',
                        action='store_true',
                        help='download console logs')

    parser.add_argument('--run-metadata',
                        action='store_true',
                        help='download run metadata')

    parser.add_argument('--all',
                        action='store_true',
                        help='download everything')

    parser.add_argument('--match-artifact-name',
                        default=re.compile('.*'),
                        type=re.compile,
                        help='only download artifacts which names match this regex')

    parser.add_argument('--match-job-name',
                        default=re.compile('.*'),
                        type=re.compile,
                        help='only download artifacts from jobs which names match this regex')

    if argcomplete:
        argcomplete.autocomplete(parser)

    args = parser.parse_args()

    if args.all:
        args.artifacts = True
        args.run_metadata = True
        args.console_logs = True

    selections = (
        args.artifacts,
        args.run_metadata,
        args.console_logs
    )

    if not any(selections):
        parser.error('At least one download option is required.')

    return args


def download_run(args):
    """Download a run."""

    output_dir = '%s' % args.run

    if not args.test and not os.path.exists(output_dir):
        os.makedirs(output_dir)

    if args.run_metadata:
        run_url = 'https://dev.azure.com/ansible/ansible/_apis/pipelines/%s/runs/%s?api-version=6.0-preview.1' % (args.pipeline_id, args.run)
        run_info_response = requests.get(run_url)
        run_info_response.raise_for_status()
        run = run_info_response.json()

        path = os.path.join(output_dir, 'run.json')
        contents = json.dumps(run, sort_keys=True, indent=4)

        if args.verbose:
            print(path)

        if not args.test:
            with open(path, 'w') as metadata_fd:
                metadata_fd.write(contents)

    timeline_response = requests.get('https://dev.azure.com/ansible/ansible/_apis/build/builds/%s/timeline?api-version=6.0' % args.run)
    timeline_response.raise_for_status()
    timeline = timeline_response.json()
    roots = set()
    by_id = {}
    children_of = {}
    parent_of = {}
    for r in timeline['records']:
        thisId = r['id']
        parentId = r['parentId']

        by_id[thisId] = r

        if parentId is None:
            roots.add(thisId)
        else:
            parent_of[thisId] = parentId
            children_of[parentId] = children_of.get(parentId, []) + [thisId]

    allowed = set()

    def allow_recursive(ei):
        allowed.add(ei)
        for ci in children_of.get(ei, []):
            allow_recursive(ci)

    for ri in roots:
        r = by_id[ri]
        allowed.add(ri)
        for ci in children_of.get(r['id'], []):
            c = by_id[ci]
            if not args.match_job_name.match("%s %s" % (r['name'], c['name'])):
                continue
            allow_recursive(c['id'])

    if args.artifacts:
        artifact_list_url = 'https://dev.azure.com/ansible/ansible/_apis/build/builds/%s/artifacts?api-version=6.0' % args.run
        artifact_list_response = requests.get(artifact_list_url)
        artifact_list_response.raise_for_status()
        for artifact in artifact_list_response.json()['value']:
            if artifact['source'] not in allowed or not args.match_artifact_name.match(artifact['name']):
                continue
            if args.verbose:
                print('%s/%s' % (output_dir, artifact['name']))
            if not args.test:
                response = requests.get(artifact['resource']['downloadUrl'])
                response.raise_for_status()
                archive = zipfile.ZipFile(io.BytesIO(response.content))
                archive.extractall(path=output_dir)

    if args.console_logs:
        for r in timeline['records']:
            if not r['log'] or r['id'] not in allowed or not args.match_artifact_name.match(r['name']):
                continue
            names = []
            parent_id = r['id']
            while parent_id is not None:
                p = by_id[parent_id]
                name = p['name']
                if name not in names:
                    names = [name] + names
                parent_id = parent_of.get(p['id'], None)

            path = " ".join(names)

            # Some job names have the separator in them.
            path = path.replace(os.sep, '_')

            log_path = os.path.join(output_dir, '%s.log' % path)
            if args.verbose:
                print(log_path)
            if not args.test:
                log = requests.get(r['log']['url'])
                log.raise_for_status()
                open(log_path, 'wb').write(log.content)


if __name__ == '__main__':
    main()