aboutsummaryrefslogtreecommitdiffstats
path: root/app/discover/scanner.py
blob: 1fbcc688beaf63e5fe2e200e8efdcb653d0f651e (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
###############################################################################
# Copyright (c) 2017 Koren Lev (Cisco Systems), Yaron Yogev (Cisco Systems)   #
# and others                                                                  #
#                                                                             #
# All rights reserved. This program and the accompanying materials            #
# are made available under the terms of the Apache License, Version 2.0       #
# which accompanies this distribution, and is available at                    #
# http://www.apache.org/licenses/LICENSE-2.0                                  #
###############################################################################
# base class for scanners

import json
import os
import queue
import traceback

from discover.clique_finder import CliqueFinder
from discover.configuration import Configuration
from discover.fetcher import Fetcher
from discover.link_finders.find_links_metadata_parser import \
    FindLinksMetadataParser
from discover.scan_error import ScanError
from discover.scan_metadata_parser import ScanMetadataParser
from utils.inventory_mgr import InventoryMgr
from utils.ssh_connection import SshError


class Scanner(Fetcher):
    config = None
    environment = None
    env = None
    root_patern = None
    scan_queue = queue.Queue()
    scan_queue_track = {}

    # keep errors indication per environment
    found_errors = {}

    def __init__(self):
        """
        Scanner is the base class for scanners.
        """
        super().__init__()
        self.config = Configuration()
        self.inv = InventoryMgr()
        self.scanners_package = None
        self.scanners = {}
        self.link_finders = []
        self.load_scanners_metadata()
        self.load_link_finders_metadata()

    def scan(self, scanner_type, obj, id_field="id",
             limit_to_child_id=None, limit_to_child_type=None):
        types_to_fetch = self.get_scanner(scanner_type)
        types_children = []
        if not limit_to_child_type:
            limit_to_child_type = []
        elif isinstance(limit_to_child_type, str):
            limit_to_child_type = [limit_to_child_type]
        try:
            for t in types_to_fetch:
                if limit_to_child_type and t["type"] not in limit_to_child_type:
                    continue
                children = self.scan_type(t, obj, id_field)
                if limit_to_child_id:
                    children = [c for c in children
                                if c[id_field] == limit_to_child_id]
                    if not children:
                        continue
                types_children.append({"type": t["type"],
                                      "children": children})
        except ValueError:
            return False
        except SshError:
            # mark the error
            self.found_errors[self.get_env()] = True
        if limit_to_child_id and len(types_children) > 0:
            t = types_children[0]
            children = t["children"]
            return children[0]
        return obj

    def check_type_env(self, type_to_fetch):
        # check if type is to be run in this environment
        if "environment_condition" not in type_to_fetch:
            return True
        env_cond = type_to_fetch.get("environment_condition", {})
        if not env_cond:
            return True
        if not isinstance(env_cond, dict):
            self.log.warn('illegal environment_condition given '
                          'for type {}'.format(type_to_fetch['type']))
            return True
        conf = self.config.get_env_config()
        for attr, required_val in env_cond.items():
            if attr == "mechanism_drivers":
                if "mechanism_drivers" not in conf:
                    self.log.warn('illegal environment configuration: '
                                  'missing mechanism_drivers')
                    return False
                if not isinstance(required_val, list):
                    required_val = [required_val]
                return bool(set(required_val) & set(conf["mechanism_drivers"]))
            elif attr not in conf or conf[attr] != required_val:
                return False
        # no check failed
        return True

    def scan_type(self, type_to_fetch, parent, id_field):
        # check if type is to be run in this environment
        if not self.check_type_env(type_to_fetch):
            return []

        if not parent:
            obj_id = None
        else:
            obj_id = str(parent[id_field])
            if not obj_id or not obj_id.rstrip():
                raise ValueError("Object missing " + id_field + " attribute")

        # get Fetcher instance
        fetcher = type_to_fetch["fetcher"]
        fetcher.set_env(self.get_env())

        # get children_scanner instance
        children_scanner = type_to_fetch.get("children_scanner")

        escaped_id = fetcher.escape(str(obj_id)) if obj_id else obj_id
        self.log.info(
            "scanning : type=%s, parent: (type=%s, name=%s, id=%s)",
            type_to_fetch["type"],
            parent.get('type', 'environment'),
            parent.get('name', ''),
            escaped_id)

        # fetch OpenStack data from environment by CLI, API or MySQL
        # or physical devices data from ACI API
        # It depends on the Fetcher's config.
        try:
            db_results = fetcher.get(escaped_id)
        except SshError:
            self.found_errors[self.get_env()] = True
            return []
        except Exception as e:
            self.log.error("Error while scanning : " +
                           "fetcher=%s, " +
                           "type=%s, " +
                           "parent: (type=%s, name=%s, id=%s), " +
                           "error: %s",
                           fetcher.__class__.__name__,
                           type_to_fetch["type"],
                           "environment" if "type" not in parent
                           else parent["type"],
                           "" if "name" not in parent else parent["name"],
                           escaped_id,
                           e)
            traceback.print_exc()
            raise ScanError(str(e))

        # format results
        if isinstance(db_results, dict):
            results = db_results["rows"] if db_results["rows"] else [db_results]
        elif isinstance(db_results, str):
            results = json.loads(db_results)
        else:
            results = db_results

        # get child_id_field
        try:
            child_id_field = type_to_fetch["object_id_to_use_in_child"]
        except KeyError:
            child_id_field = "id"

        environment = self.get_env()
        children = []

        for o in results:
            saved = self.inv.save_inventory_object(o,
                                                   parent=parent,
                                                   environment=environment,
                                                   type_to_fetch=type_to_fetch)

            if saved:
                # add objects into children list.
                children.append(o)

                # put children scanner into queue
                if children_scanner:
                    self.queue_for_scan(o, child_id_field, children_scanner)
        return children

    # scanning queued items, rather than going depth-first (DFS)
    # this is done to allow collecting all required data for objects
    # before continuing to next level
    # for example, get host ID from API os-hypervisors call, so later
    # we can use this ID in the "os-hypervisors/<ID>/servers" call
    @staticmethod
    def queue_for_scan(o, child_id_field, children_scanner):
        if o["id"] in Scanner.scan_queue_track:
            return
        Scanner.scan_queue_track[o["type"] + ";" + o["id"]] = 1
        Scanner.scan_queue.put({"object": o,
                                "child_id_field": child_id_field,
                                "scanner": children_scanner})

    def run_scan(self, scanner_type, obj, id_field, child_id, child_type):
        results = self.scan(scanner_type, obj, id_field, child_id, child_type)

        # run children scanner from queue.
        self.scan_from_queue()
        return results

    def scan_from_queue(self):
        while not Scanner.scan_queue.empty():
            item = Scanner.scan_queue.get()
            scanner_type = item["scanner"]

            # scan the queued item
            self.scan(scanner_type, item["object"], item["child_id_field"])
        self.log.info("Scan complete")

    def scan_links(self):
        self.log.info("scanning for links")
        for fetcher in self.link_finders:
            fetcher.set_env(self.get_env())
            fetcher.add_links()

    def scan_cliques(self):
        clique_scanner = CliqueFinder()
        clique_scanner.set_env(self.get_env())
        clique_scanner.find_cliques()

    def deploy_monitoring_setup(self):
        ret = self.inv.monitoring_setup_manager.handle_pending_setup_changes()
        if not ret:
            self.found_errors[self.get_env()] = True

    def get_run_app_path(self):
        conf = self.config.get_env_config()
        run_app_path = conf.get('run_app_path', '')
        if not run_app_path:
            run_app_path = conf.get('app_path', '/etc/calipso')
        return run_app_path

    def load_scanners_metadata(self):
        parser = ScanMetadataParser(self.inv)
        scanners_file = os.path.join(self.get_run_app_path(),
                                     'config',
                                     ScanMetadataParser.SCANNERS_FILE)

        metadata = parser.parse_metadata_file(scanners_file)
        self.scanners_package = metadata[ScanMetadataParser.SCANNERS_PACKAGE]
        self.scanners = metadata[ScanMetadataParser.SCANNERS]

    def load_link_finders_metadata(self):
        parser = FindLinksMetadataParser()
        conf = self.config.get_env_config()
        finders_file = os.path.join(self.get_run_app_path(),
                                    'config',
                                    FindLinksMetadataParser.FINDERS_FILE)
        metadata = parser.parse_metadata_file(finders_file)
        self.link_finders = metadata[FindLinksMetadataParser.LINK_FINDERS]

    def get_scanner_package(self):
        return self.scanners_package

    def get_scanner(self, scanner_type: str) -> dict:
        return self.scanners.get(scanner_type)