summaryrefslogtreecommitdiff
path: root/cloudinit/sources/__init__.py
blob: 4b3bf62f9c12a945c1f11ded46ee8ce5185d6ae9 (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
# vi: ts=4 expandtab
#
#    Copyright (C) 2012 Canonical Ltd.
#    Copyright (C) 2012 Hewlett-Packard Development Company, L.P.
#    Copyright (C) 2012 Yahoo! Inc.
#
#    Author: Scott Moser <scott.moser@canonical.com>
#    Author: Juerg Haefliger <juerg.haefliger@hp.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/>.

import abc
import os

from cloudinit import importer
from cloudinit import log as logging
from cloudinit import type_utils
from cloudinit import user_data as ud
from cloudinit import util

from cloudinit.filters import launch_index

DEP_FILESYSTEM = "FILESYSTEM"
DEP_NETWORK = "NETWORK"
DS_PREFIX = 'DataSource'

LOG = logging.getLogger(__name__)


class DataSourceNotFoundException(Exception):
    pass


class DataSource(object):

    __metaclass__ = abc.ABCMeta

    def __init__(self, sys_cfg, distro, paths, ud_proc=None):
        self.sys_cfg = sys_cfg
        self.distro = distro
        self.paths = paths
        self.userdata = None
        self.metadata = None
        self.userdata_raw = None
        self.vendordata = None
        self.vendordata_raw = None

        # find the datasource config name.
        # remove 'DataSource' from classname on front, and remove 'Net' on end.
        # Both Foo and FooNet sources expect config in cfg['sources']['Foo']
        name = type_utils.obj_name(self)
        if name.startswith(DS_PREFIX):
            name = name[len(DS_PREFIX):]
        if name.endswith('Net'):
            name = name[0:-3]

        self.ds_cfg = util.get_cfg_by_path(self.sys_cfg,
                                          ("datasource", name), {})
        if not ud_proc:
            self.ud_proc = ud.UserDataProcessor(self.paths)
        else:
            self.ud_proc = ud_proc

    def __str__(self):
        return type_utils.obj_name(self)

    def get_userdata(self, apply_filter=False):
        if self.userdata is None:
            self.userdata = self.ud_proc.process(self.get_userdata_raw())
        if apply_filter:
            return self._filter_xdata(self.userdata)
        return self.userdata

    def get_vendordata(self):
        if self.vendordata is None:
            self.vendordata = self.ud_proc.process(self.get_vendordata_raw())
        return self.vendordata

    @property
    def launch_index(self):
        if not self.metadata:
            return None
        if 'launch-index' in self.metadata:
            return self.metadata['launch-index']
        return None

    def _filter_xdata(self, processed_ud):
        filters = [
            launch_index.Filter(util.safe_int(self.launch_index)),
        ]
        new_ud = processed_ud
        for f in filters:
            new_ud = f.apply(new_ud)
        return new_ud

    @property
    def is_disconnected(self):
        return False

    def get_userdata_raw(self):
        return self.userdata_raw

    def get_vendordata_raw(self):
        return self.vendordata_raw

    # the data sources' config_obj is a cloud-config formated
    # object that came to it from ways other than cloud-config
    # because cloud-config content would be handled elsewhere
    def get_config_obj(self):
        return {}

    def get_public_ssh_keys(self):
        return normalize_pubkey_data(self.metadata.get('public-keys'))

    def _remap_device(self, short_name):
        # LP: #611137
        # the metadata service may believe that devices are named 'sda'
        # when the kernel named them 'vda' or 'xvda'
        # we want to return the correct value for what will actually
        # exist in this instance
        mappings = {"sd": ("vd", "xvd")}
        for (nfrom, tlist) in mappings.iteritems():
            if not short_name.startswith(nfrom):
                continue
            for nto in tlist:
                cand = "/dev/%s%s" % (nto, short_name[len(nfrom):])
                if os.path.exists(cand):
                    return cand
        return None

    def device_name_to_device(self, _name):
        # translate a 'name' to a device
        # the primary function at this point is on ec2
        # to consult metadata service, that has
        #  ephemeral0: sdb
        # and return 'sdb' for input 'ephemeral0'
        return None

    def get_locale(self):
        return 'en_US.UTF-8'

    @property
    def availability_zone(self):
        return self.metadata.get('availability-zone',
                                 self.metadata.get('availability_zone'))

    def get_instance_id(self):
        if not self.metadata or 'instance-id' not in self.metadata:
            # Return a magic not really instance id string
            return "iid-datasource"
        return str(self.metadata['instance-id'])

    def get_hostname(self, fqdn=False, resolve_ip=False):
        defdomain = "localdomain"
        defhost = "localhost"
        domain = defdomain

        if not self.metadata or not 'local-hostname' in self.metadata:
            # this is somewhat questionable really.
            # the cloud datasource was asked for a hostname
            # and didn't have one. raising error might be more appropriate
            # but instead, basically look up the existing hostname
            toks = []
            hostname = util.get_hostname()
            fqdn = util.get_fqdn_from_hosts(hostname)
            if fqdn and fqdn.find(".") > 0:
                toks = str(fqdn).split(".")
            elif hostname:
                toks = [hostname, defdomain]
            else:
                toks = [defhost, defdomain]
        else:
            # if there is an ipv4 address in 'local-hostname', then
            # make up a hostname (LP: #475354) in format ip-xx.xx.xx.xx
            lhost = self.metadata['local-hostname']
            if util.is_ipv4(lhost):
                toks = []
                if resolve_ip:
                    toks = util.gethostbyaddr(lhost)

                if toks:
                    toks = str(toks).split('.')
                else:
                    toks = ["ip-%s" % lhost.replace(".", "-")]
            else:
                toks = lhost.split(".")

        if len(toks) > 1:
            hostname = toks[0]
            domain = '.'.join(toks[1:])
        else:
            hostname = toks[0]

        if fqdn:
            return "%s.%s" % (hostname, domain)
        else:
            return hostname

    def get_package_mirror_info(self):
        return self.distro.get_package_mirror_info(
            availability_zone=self.availability_zone)


def normalize_pubkey_data(pubkey_data):
    keys = []

    if not pubkey_data:
        return keys

    if isinstance(pubkey_data, (basestring, str)):
        return str(pubkey_data).splitlines()

    if isinstance(pubkey_data, (list, set)):
        return list(pubkey_data)

    if isinstance(pubkey_data, (dict)):
        for (_keyname, klist) in pubkey_data.iteritems():
            # lp:506332 uec metadata service responds with
            # data that makes boto populate a string for 'klist' rather
            # than a list.
            if isinstance(klist, (str, basestring)):
                klist = [klist]
            if isinstance(klist, (list, set)):
                for pkey in klist:
                    # There is an empty string at
                    # the end of the keylist, trim it
                    if pkey:
                        keys.append(pkey)

    return keys


def find_source(sys_cfg, distro, paths, ds_deps, cfg_list, pkg_list):
    ds_list = list_sources(cfg_list, ds_deps, pkg_list)
    ds_names = [type_utils.obj_name(f) for f in ds_list]
    LOG.debug("Searching for data source in: %s", ds_names)

    for cls in ds_list:
        try:
            LOG.debug("Seeing if we can get any data from %s", cls)
            s = cls(sys_cfg, distro, paths)
            if s.get_data():
                return (s, type_utils.obj_name(cls))
        except Exception:
            util.logexc(LOG, "Getting data from %s failed", cls)

    msg = ("Did not find any data source,"
           " searched classes: (%s)") % (", ".join(ds_names))
    raise DataSourceNotFoundException(msg)


# Return a list of classes that have the same depends as 'depends'
# iterate through cfg_list, loading "DataSource*" modules
# and calling their "get_datasource_list".
# Return an ordered list of classes that match (if any)
def list_sources(cfg_list, depends, pkg_list):
    src_list = []
    LOG.debug(("Looking for for data source in: %s,"
               " via packages %s that matches dependencies %s"),
              cfg_list, pkg_list, depends)
    for ds_name in cfg_list:
        if not ds_name.startswith(DS_PREFIX):
            ds_name = '%s%s' % (DS_PREFIX, ds_name)
        m_locs = importer.find_module(ds_name,
                                      pkg_list,
                                      ['get_datasource_list'])
        for m_loc in m_locs:
            mod = importer.import_module(m_loc)
            lister = getattr(mod, "get_datasource_list")
            matches = lister(depends)
            if matches:
                src_list.extend(matches)
                break
    return src_list


# 'depends' is a list of dependencies (DEP_FILESYSTEM)
# ds_list is a list of 2 item lists
# ds_list = [
#   ( class, ( depends-that-this-class-needs ) )
# }
# It returns a list of 'class' that matched these deps exactly
# It mainly is a helper function for DataSourceCollections
def list_from_depends(depends, ds_list):
    ret_list = []
    depset = set(depends)
    for (cls, deps) in ds_list:
        if depset == set(deps):
            ret_list.append(cls)
    return ret_list