summaryrefslogtreecommitdiff
path: root/cloudinit/sources/DataSourceMAAS.py
blob: 612d8ffa12d37c84ad71fd493c63a96ab796ef98 (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
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
# vi: ts=4 expandtab
#
#    Copyright (C) 2012 Canonical Ltd.
#    Copyright (C) 2012 Yahoo! Inc.
#
#    Author: Scott Moser <scott.moser@canonical.com>
#    Author: Joshua Harlow <harlowja@yahoo-inc.com>
#
#    This program is free software: you can redistribute it and/or modify
#    it under the terms of the GNU General Public License version 3, as
#    published by the Free Software Foundation.
#
#    This program 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 this program.  If not, see <http://www.gnu.org/licenses/>.

from email.utils import parsedate
import errno
import oauth.oauth as oauth
import os
import time
import urllib2

from cloudinit import log as logging
from cloudinit import sources
from cloudinit import url_helper as uhelp
from cloudinit import util

LOG = logging.getLogger(__name__)
MD_VERSION = "2012-03-01"


class DataSourceMAAS(sources.DataSource):
    """
    DataSourceMAAS reads instance information from MAAS.
    Given a config metadata_url, and oauth tokens, it expects to find
    files under the root named:
      instance-id
      user-data
      hostname
    """
    def __init__(self, sys_cfg, distro, paths):
        sources.DataSource.__init__(self, sys_cfg, distro, paths)
        self.base_url = None
        self.seed_dir = os.path.join(paths.seed_dir, 'maas')
        self.oauth_clockskew = None

    def __str__(self):
        root = sources.DataSource.__str__(self)
        return "%s [%s]" % (root, self.base_url)

    def get_data(self):
        mcfg = self.ds_cfg

        try:
            (userdata, metadata) = read_maas_seed_dir(self.seed_dir)
            self.userdata_raw = userdata
            self.metadata = metadata
            self.base_url = self.seed_dir
            return True
        except MAASSeedDirNone:
            pass
        except MAASSeedDirMalformed as exc:
            LOG.warn("%s was malformed: %s" % (self.seed_dir, exc))
            raise

        # If there is no metadata_url, then we're not configured
        url = mcfg.get('metadata_url', None)
        if not url:
            return False

        try:
            if not self.wait_for_metadata_service(url):
                return False

            self.base_url = url

            (userdata, metadata) = read_maas_seed_url(self.base_url,
                                                      self.md_headers)
            self.userdata_raw = userdata
            self.metadata = metadata
            return True
        except Exception:
            util.logexc(LOG, "Failed fetching metadata from url %s", url)
            return False

    def md_headers(self, url):
        mcfg = self.ds_cfg

        # If we are missing token_key, token_secret or consumer_key
        # then just do non-authed requests
        for required in ('token_key', 'token_secret', 'consumer_key'):
            if required not in mcfg:
                return {}

        consumer_secret = mcfg.get('consumer_secret', "")

        timestamp = None
        if self.oauth_clockskew:
            timestamp = int(time.time()) + self.oauth_clockskew

        return oauth_headers(url=url,
                             consumer_key=mcfg['consumer_key'],
                             token_key=mcfg['token_key'],
                             token_secret=mcfg['token_secret'],
                             consumer_secret=consumer_secret,
                             timestamp=timestamp)

    def wait_for_metadata_service(self, url):
        mcfg = self.ds_cfg

        max_wait = 120
        try:
            max_wait = int(mcfg.get("max_wait", max_wait))
        except Exception:
            util.logexc(LOG, "Failed to get max wait. using %s", max_wait)

        if max_wait == 0:
            return False

        timeout = 50
        try:
            if timeout in mcfg:
                timeout = int(mcfg.get("timeout", timeout))
        except Exception:
            LOG.warn("Failed to get timeout, using %s" % timeout)

        starttime = time.time()
        check_url = "%s/%s/meta-data/instance-id" % (url, MD_VERSION)
        urls = [check_url]
        url = uhelp.wait_for_url(urls=urls, max_wait=max_wait,
                                 timeout=timeout, exception_cb=self._except_cb,
                                 headers_cb=self.md_headers)

        if url:
            LOG.debug("Using metadata source: '%s'", url)
        else:
            LOG.critical("Giving up on md from %s after %i seconds",
                            urls, int(time.time() - starttime))

        return bool(url)

    def _except_cb(self, msg, exception):
        if not (isinstance(exception, urllib2.HTTPError) and
                (exception.code == 403 or exception.code == 401)):
            return
        if 'date' not in exception.headers:
            LOG.warn("date field not in %d headers" % exception.code)
            return

        date = exception.headers['date']

        try:
            ret_time = time.mktime(parsedate(date))
        except:
            LOG.warn("failed to convert datetime '%s'")
            return

        self.oauth_clockskew = int(ret_time - time.time())
        LOG.warn("set oauth clockskew to %d" % self.oauth_clockskew)
        return


def read_maas_seed_dir(seed_d):
    """
    Return user-data and metadata for a maas seed dir in seed_d.
    Expected format of seed_d are the following files:
      * instance-id
      * local-hostname
      * user-data
    """
    if not os.path.isdir(seed_d):
        raise MAASSeedDirNone("%s: not a directory")

    files = ('local-hostname', 'instance-id', 'user-data', 'public-keys')
    md = {}
    for fname in files:
        try:
            md[fname] = util.load_file(os.path.join(seed_d, fname))
        except IOError as e:
            if e.errno != errno.ENOENT:
                raise

    return check_seed_contents(md, seed_d)


def read_maas_seed_url(seed_url, header_cb=None, timeout=None,
    version=MD_VERSION):
    """
    Read the maas datasource at seed_url.
    header_cb is a method that should return a headers dictionary that will
    be given to urllib2.Request()

    Expected format of seed_url is are the following files:
      * <seed_url>/<version>/meta-data/instance-id
      * <seed_url>/<version>/meta-data/local-hostname
      * <seed_url>/<version>/user-data
    """
    base_url = "%s/%s" % (seed_url, version)
    file_order = [
        'local-hostname',
        'instance-id',
        'public-keys',
        'user-data',
    ]
    files = {
        'local-hostname': "%s/%s" % (base_url, 'meta-data/local-hostname'),
        'instance-id': "%s/%s" % (base_url, 'meta-data/instance-id'),
        'public-keys': "%s/%s" % (base_url, 'meta-data/public-keys'),
        'user-data': "%s/%s" % (base_url, 'user-data'),
    }
    md = {}
    for name in file_order:
        url = files.get(name)
        if header_cb:
            headers = header_cb(url)
        else:
            headers = {}
        try:
            resp = uhelp.readurl(url, headers=headers, timeout=timeout)
            if resp.ok():
                md[name] = str(resp)
            else:
                LOG.warn(("Fetching from %s resulted in"
                          " an invalid http code %s"), url, resp.code)
        except urllib2.HTTPError as e:
            if e.code != 404:
                raise
    return check_seed_contents(md, seed_url)


def check_seed_contents(content, seed):
    """Validate if content is Is the content a dict that is valid as a
       return for a datasource.
       Either return a (userdata, metadata) tuple or
       Raise MAASSeedDirMalformed or MAASSeedDirNone
    """
    md_required = ('instance-id', 'local-hostname')
    if len(content) == 0:
        raise MAASSeedDirNone("%s: no data files found" % seed)

    found = list(content.keys())
    missing = [k for k in md_required if k not in found]
    if len(missing):
        raise MAASSeedDirMalformed("%s: missing files %s" % (seed, missing))

    userdata = content.get('user-data', "")
    md = {}
    for (key, val) in content.iteritems():
        if key == 'user-data':
            continue
        md[key] = val

    return (userdata, md)


def oauth_headers(url, consumer_key, token_key, token_secret, consumer_secret,
                  timestamp=None):
    consumer = oauth.OAuthConsumer(consumer_key, consumer_secret)
    token = oauth.OAuthToken(token_key, token_secret)

    if timestamp is None:
        ts = int(time.time())
    else:
        ts = timestamp

    params = {
        'oauth_version': "1.0",
        'oauth_nonce': oauth.generate_nonce(),
        'oauth_timestamp': ts,
        'oauth_token': token.key,
        'oauth_consumer_key': consumer.key,
    }
    req = oauth.OAuthRequest(http_url=url, parameters=params)
    req.sign_request(oauth.OAuthSignatureMethod_PLAINTEXT(),
                     consumer, token)
    return req.to_header()


class MAASSeedDirNone(Exception):
    pass


class MAASSeedDirMalformed(Exception):
    pass


# Used to match classes to dependencies
datasources = [
  (DataSourceMAAS, (sources.DEP_FILESYSTEM, sources.DEP_NETWORK)),
]


# Return a list of data sources that match this set of dependencies
def get_datasource_list(depends):
    return sources.list_from_depends(depends, datasources)


if __name__ == "__main__":
    def main():
        """
        Call with single argument of directory or http or https url.
        If url is given additional arguments are allowed, which will be
        interpreted as consumer_key, token_key, token_secret, consumer_secret
        """
        import argparse
        import pprint

        parser = argparse.ArgumentParser(description='Interact with MAAS DS')
        parser.add_argument("--config", metavar="file",
            help="specify DS config file", default=None)
        parser.add_argument("--ckey", metavar="key",
            help="the consumer key to auth with", default=None)
        parser.add_argument("--tkey", metavar="key",
            help="the token key to auth with", default=None)
        parser.add_argument("--csec", metavar="secret",
            help="the consumer secret (likely '')", default="")
        parser.add_argument("--tsec", metavar="secret",
            help="the token secret to auth with", default=None)
        parser.add_argument("--apiver", metavar="version",
            help="the apiver to use ("" can be used)", default=MD_VERSION)

        subcmds = parser.add_subparsers(title="subcommands", dest="subcmd")
        subcmds.add_parser('crawl', help="crawl the datasource")
        subcmds.add_parser('get', help="do a single GET of provided url")
        subcmds.add_parser('check-seed', help="read andn verify seed at url")

        parser.add_argument("url", help="the data source to query")

        args = parser.parse_args()

        creds = {'consumer_key': args.ckey, 'token_key': args.tkey,
            'token_secret': args.tsec, 'consumer_secret': args.csec}

        if args.config:
            cfg = util.read_conf(args.config)
            if 'datasource' in cfg:
                cfg = cfg['datasource']['MAAS']
            for key in creds.keys():
                if key in cfg and creds[key] is None:
                    creds[key] = cfg[key]

        def geturl(url, headers_cb):
            req = urllib2.Request(url, data=None, headers=headers_cb(url))
            return (urllib2.urlopen(req).read())

        def printurl(url, headers_cb):
            print "== %s ==\n%s\n" % (url, geturl(url, headers_cb))

        def crawl(url, headers_cb=None):
            if url.endswith("/"):
                for line in geturl(url, headers_cb).splitlines():
                    if line.endswith("/"):
                        crawl("%s%s" % (url, line), headers_cb)
                    else:
                        printurl("%s%s" % (url, line), headers_cb)
            else:
                printurl(url, headers_cb)

        def my_headers(url):
            headers = {}
            if creds.get('consumer_key', None) is not None:
                headers = oauth_headers(url, **creds)
            return headers

        if args.subcmd == "check-seed":
            if args.url.startswith("http"):
                (userdata, metadata) = read_maas_seed_url(args.url,
                    header_cb=my_headers, version=args.apiver)
            else:
                (userdata, metadata) = read_maas_seed_url(args.url)
            print "=== userdata ==="
            print userdata
            print "=== metadata ==="
            pprint.pprint(metadata)

        elif args.subcmd == "get":
            printurl(args.url, my_headers)

        elif args.subcmd == "crawl":
            if not args.url.endswith("/"):
                args.url = "%s/" % args.url
            crawl(args.url, my_headers)

    main()