clearbit 0.2.7 → 0.3.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.github/CODEOWNERS +3 -0
- data/LICENSE +21 -0
- data/README.md +87 -3
- data/clearbit.gemspec +2 -0
- data/examples/name_domain.rb +4 -0
- data/examples/prospector.rb +5 -4
- data/examples/reveal.rb +11 -0
- data/examples/risk.rb +13 -0
- data/examples/risk_flag.rb +35 -0
- data/lib/clearbit.rb +4 -1
- data/lib/clearbit/analytics.rb +62 -0
- data/lib/clearbit/analytics/LICENSE +10 -0
- data/lib/clearbit/analytics/README.md +114 -0
- data/lib/clearbit/analytics/backoff_policy.rb +49 -0
- data/lib/clearbit/analytics/client.rb +189 -0
- data/lib/clearbit/analytics/defaults.rb +36 -0
- data/lib/clearbit/analytics/field_parser.rb +192 -0
- data/lib/clearbit/analytics/logging.rb +60 -0
- data/lib/clearbit/analytics/message_batch.rb +72 -0
- data/lib/clearbit/analytics/request.rb +134 -0
- data/lib/clearbit/analytics/response.rb +15 -0
- data/lib/clearbit/analytics/utils.rb +91 -0
- data/lib/clearbit/analytics/worker.rb +66 -0
- data/lib/clearbit/audiences.rb +14 -0
- data/lib/clearbit/enrichment.rb +1 -0
- data/lib/clearbit/enrichment/news.rb +18 -0
- data/lib/clearbit/name_domain.rb +17 -0
- data/lib/clearbit/risk.rb +1 -1
- data/lib/clearbit/version.rb +1 -1
- data/lib/clearbit/webhook.rb +3 -1
- data/spec/lib/clearbit/analytics_spec.rb +66 -0
- data/spec/lib/clearbit/prospector_spec.rb +12 -2
- data/spec/support/helpers.rb +3 -1
- metadata +27 -4
@@ -0,0 +1,49 @@
|
|
1
|
+
require 'clearbit/analytics/defaults'
|
2
|
+
|
3
|
+
module Clearbit
|
4
|
+
class Analytics
|
5
|
+
class BackoffPolicy
|
6
|
+
include Clearbit::Analytics::Defaults::BackoffPolicy
|
7
|
+
|
8
|
+
# @param [Hash] opts
|
9
|
+
# @option opts [Numeric] :min_timeout_ms The minimum backoff timeout
|
10
|
+
# @option opts [Numeric] :max_timeout_ms The maximum backoff timeout
|
11
|
+
# @option opts [Numeric] :multiplier The value to multiply the current
|
12
|
+
# interval with for each retry attempt
|
13
|
+
# @option opts [Numeric] :randomization_factor The randomization factor
|
14
|
+
# to use to create a range around the retry interval
|
15
|
+
def initialize(opts = {})
|
16
|
+
@min_timeout_ms = opts[:min_timeout_ms] || MIN_TIMEOUT_MS
|
17
|
+
@max_timeout_ms = opts[:max_timeout_ms] || MAX_TIMEOUT_MS
|
18
|
+
@multiplier = opts[:multiplier] || MULTIPLIER
|
19
|
+
@randomization_factor = opts[:randomization_factor] || RANDOMIZATION_FACTOR
|
20
|
+
|
21
|
+
@attempts = 0
|
22
|
+
end
|
23
|
+
|
24
|
+
# @return [Numeric] the next backoff interval, in milliseconds.
|
25
|
+
def next_interval
|
26
|
+
interval = @min_timeout_ms * (@multiplier**@attempts)
|
27
|
+
interval = add_jitter(interval, @randomization_factor)
|
28
|
+
|
29
|
+
@attempts += 1
|
30
|
+
|
31
|
+
[interval, @max_timeout_ms].min
|
32
|
+
end
|
33
|
+
|
34
|
+
private
|
35
|
+
|
36
|
+
def add_jitter(base, randomization_factor)
|
37
|
+
random_number = rand
|
38
|
+
max_deviation = base * randomization_factor
|
39
|
+
deviation = random_number * max_deviation
|
40
|
+
|
41
|
+
if random_number < 0.5
|
42
|
+
base - deviation
|
43
|
+
else
|
44
|
+
base + deviation
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
49
|
+
end
|
@@ -0,0 +1,189 @@
|
|
1
|
+
require 'thread'
|
2
|
+
require 'time'
|
3
|
+
|
4
|
+
require 'clearbit/analytics/defaults'
|
5
|
+
require 'clearbit/analytics/logging'
|
6
|
+
require 'clearbit/analytics/utils'
|
7
|
+
require 'clearbit/analytics/worker'
|
8
|
+
|
9
|
+
module Clearbit
|
10
|
+
class Analytics
|
11
|
+
class Client
|
12
|
+
include Clearbit::Analytics::Utils
|
13
|
+
include Clearbit::Analytics::Logging
|
14
|
+
|
15
|
+
# @param [Hash] opts
|
16
|
+
# @option opts [String] :write_key Your project's write_key
|
17
|
+
# @option opts [FixNum] :max_queue_size Maximum number of calls to be
|
18
|
+
# remain queued.
|
19
|
+
# @option opts [Proc] :on_error Handles error calls from the API.
|
20
|
+
def initialize(opts = {})
|
21
|
+
symbolize_keys!(opts)
|
22
|
+
|
23
|
+
@queue = Queue.new
|
24
|
+
@write_key = opts[:write_key]
|
25
|
+
@max_queue_size = opts[:max_queue_size] || Defaults::Queue::MAX_SIZE
|
26
|
+
@worker_mutex = Mutex.new
|
27
|
+
@worker = Worker.new(@queue, @write_key, opts)
|
28
|
+
|
29
|
+
check_write_key!
|
30
|
+
|
31
|
+
at_exit { @worker_thread && @worker_thread[:should_exit] = true }
|
32
|
+
end
|
33
|
+
|
34
|
+
# Synchronously waits until the worker has flushed the queue.
|
35
|
+
#
|
36
|
+
# Use only for scripts which are not long-running, and will specifically
|
37
|
+
# exit
|
38
|
+
def flush
|
39
|
+
while !@queue.empty? || @worker.is_requesting?
|
40
|
+
ensure_worker_running
|
41
|
+
sleep(0.1)
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
# @!macro common_attrs
|
46
|
+
# @option attrs [String] :anonymous_id ID for a user when you don't know
|
47
|
+
# who they are yet. (optional but you must provide either an
|
48
|
+
# `anonymous_id` or `user_id`)
|
49
|
+
# @option attrs [Hash] :context ({})
|
50
|
+
# @option attrs [Hash] :integrations What integrations this event
|
51
|
+
# goes to (optional)
|
52
|
+
# @option attrs [String] :message_id ID that uniquely
|
53
|
+
# identifies a message across the API. (optional)
|
54
|
+
# @option attrs [Time] :timestamp When the event occurred (optional)
|
55
|
+
# @option attrs [String] :user_id The ID for this user in your database
|
56
|
+
# (optional but you must provide either an `anonymous_id` or `user_id`)
|
57
|
+
# @option attrs [Hash] :options Options such as user traits (optional)
|
58
|
+
|
59
|
+
# Tracks an event
|
60
|
+
#
|
61
|
+
# @see https://segment.com/docs/sources/server/ruby/#track
|
62
|
+
#
|
63
|
+
# @param [Hash] attrs
|
64
|
+
#
|
65
|
+
# @option attrs [String] :event Event name
|
66
|
+
# @option attrs [Hash] :properties Event properties (optional)
|
67
|
+
# @macro common_attrs
|
68
|
+
def track(attrs)
|
69
|
+
symbolize_keys! attrs
|
70
|
+
enqueue(FieldParser.parse_for_track(attrs))
|
71
|
+
end
|
72
|
+
|
73
|
+
# Identifies a user
|
74
|
+
#
|
75
|
+
# @see https://segment.com/docs/sources/server/ruby/#identify
|
76
|
+
#
|
77
|
+
# @param [Hash] attrs
|
78
|
+
#
|
79
|
+
# @option attrs [Hash] :traits User traits (optional)
|
80
|
+
# @macro common_attrs
|
81
|
+
def identify(attrs)
|
82
|
+
symbolize_keys! attrs
|
83
|
+
enqueue(FieldParser.parse_for_identify(attrs))
|
84
|
+
end
|
85
|
+
|
86
|
+
# Aliases a user from one id to another
|
87
|
+
#
|
88
|
+
# @see https://segment.com/docs/sources/server/ruby/#alias
|
89
|
+
#
|
90
|
+
# @param [Hash] attrs
|
91
|
+
#
|
92
|
+
# @option attrs [String] :previous_id The ID to alias from
|
93
|
+
# @macro common_attrs
|
94
|
+
def alias(attrs)
|
95
|
+
symbolize_keys! attrs
|
96
|
+
enqueue(FieldParser.parse_for_alias(attrs))
|
97
|
+
end
|
98
|
+
|
99
|
+
# Associates a user identity with a group.
|
100
|
+
#
|
101
|
+
# @see https://segment.com/docs/sources/server/ruby/#group
|
102
|
+
#
|
103
|
+
# @param [Hash] attrs
|
104
|
+
#
|
105
|
+
# @option attrs [String] :group_id The ID of the group
|
106
|
+
# @option attrs [Hash] :traits User traits (optional)
|
107
|
+
# @macro common_attrs
|
108
|
+
def group(attrs)
|
109
|
+
symbolize_keys! attrs
|
110
|
+
enqueue(FieldParser.parse_for_group(attrs))
|
111
|
+
end
|
112
|
+
|
113
|
+
# Records a page view
|
114
|
+
#
|
115
|
+
# @see https://segment.com/docs/sources/server/ruby/#page
|
116
|
+
#
|
117
|
+
# @param [Hash] attrs
|
118
|
+
#
|
119
|
+
# @option attrs [String] :name Name of the page
|
120
|
+
# @option attrs [Hash] :properties Page properties (optional)
|
121
|
+
# @macro common_attrs
|
122
|
+
def page(attrs)
|
123
|
+
symbolize_keys! attrs
|
124
|
+
enqueue(FieldParser.parse_for_page(attrs))
|
125
|
+
end
|
126
|
+
|
127
|
+
# Records a screen view (for a mobile app)
|
128
|
+
#
|
129
|
+
# @param [Hash] attrs
|
130
|
+
#
|
131
|
+
# @option attrs [String] :name Name of the screen
|
132
|
+
# @option attrs [Hash] :properties Screen properties (optional)
|
133
|
+
# @option attrs [String] :category The screen category (optional)
|
134
|
+
# @macro common_attrs
|
135
|
+
def screen(attrs)
|
136
|
+
symbolize_keys! attrs
|
137
|
+
enqueue(FieldParser.parse_for_screen(attrs))
|
138
|
+
end
|
139
|
+
|
140
|
+
# @return [Fixnum] number of messages in the queue
|
141
|
+
def queued_messages
|
142
|
+
@queue.length
|
143
|
+
end
|
144
|
+
|
145
|
+
private
|
146
|
+
|
147
|
+
# private: Enqueues the action.
|
148
|
+
#
|
149
|
+
# returns Boolean of whether the item was added to the queue.
|
150
|
+
def enqueue(action)
|
151
|
+
# add our request id for tracing purposes
|
152
|
+
action[:messageId] ||= uid
|
153
|
+
|
154
|
+
if @queue.length < @max_queue_size
|
155
|
+
@queue << action
|
156
|
+
ensure_worker_running
|
157
|
+
|
158
|
+
true
|
159
|
+
else
|
160
|
+
logger.warn(
|
161
|
+
'Queue is full, dropping events. The :max_queue_size ' \
|
162
|
+
'configuration parameter can be increased to prevent this from ' \
|
163
|
+
'happening.'
|
164
|
+
)
|
165
|
+
false
|
166
|
+
end
|
167
|
+
end
|
168
|
+
|
169
|
+
# private: Checks that the write_key is properly initialized
|
170
|
+
def check_write_key!
|
171
|
+
raise ArgumentError, 'Write key must be initialized' if @write_key.nil?
|
172
|
+
end
|
173
|
+
|
174
|
+
def ensure_worker_running
|
175
|
+
return if worker_running?
|
176
|
+
@worker_mutex.synchronize do
|
177
|
+
return if worker_running?
|
178
|
+
@worker_thread = Thread.new do
|
179
|
+
@worker.run
|
180
|
+
end
|
181
|
+
end
|
182
|
+
end
|
183
|
+
|
184
|
+
def worker_running?
|
185
|
+
@worker_thread && @worker_thread.alive?
|
186
|
+
end
|
187
|
+
end
|
188
|
+
end
|
189
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
module Clearbit
|
2
|
+
class Analytics
|
3
|
+
module Defaults
|
4
|
+
module Request
|
5
|
+
HOST = 'x.clearbit.com'
|
6
|
+
PORT = 443
|
7
|
+
PATH = '/v1/import'
|
8
|
+
SSL = true
|
9
|
+
HEADERS = { 'Accept' => 'application/json',
|
10
|
+
'Content-Type' => 'application/json',
|
11
|
+
'User-Agent' => "clearbit-ruby/#{Clearbit::VERSION}" }
|
12
|
+
RETRIES = 10
|
13
|
+
end
|
14
|
+
|
15
|
+
module Queue
|
16
|
+
MAX_SIZE = 10000
|
17
|
+
end
|
18
|
+
|
19
|
+
module Message
|
20
|
+
MAX_BYTES = 32768 # 32Kb
|
21
|
+
end
|
22
|
+
|
23
|
+
module MessageBatch
|
24
|
+
MAX_BYTES = 512_000 # 500Kb
|
25
|
+
MAX_SIZE = 100
|
26
|
+
end
|
27
|
+
|
28
|
+
module BackoffPolicy
|
29
|
+
MIN_TIMEOUT_MS = 100
|
30
|
+
MAX_TIMEOUT_MS = 10000
|
31
|
+
MULTIPLIER = 1.5
|
32
|
+
RANDOMIZATION_FACTOR = 0.5
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
@@ -0,0 +1,192 @@
|
|
1
|
+
module Clearbit
|
2
|
+
class Analytics
|
3
|
+
# Handles parsing fields according to the Segment Spec
|
4
|
+
#
|
5
|
+
# @see https://segment.com/docs/spec/
|
6
|
+
class FieldParser
|
7
|
+
class << self
|
8
|
+
include Clearbit::Analytics::Utils
|
9
|
+
|
10
|
+
# In addition to the common fields, track accepts:
|
11
|
+
#
|
12
|
+
# - "event"
|
13
|
+
# - "properties"
|
14
|
+
def parse_for_track(fields)
|
15
|
+
common = parse_common_fields(fields)
|
16
|
+
|
17
|
+
event = fields[:event]
|
18
|
+
properties = fields[:properties] || {}
|
19
|
+
|
20
|
+
check_presence!(event, 'event')
|
21
|
+
check_is_hash!(properties, 'properties')
|
22
|
+
|
23
|
+
isoify_dates! properties
|
24
|
+
|
25
|
+
common.merge({
|
26
|
+
:type => 'track',
|
27
|
+
:event => event.to_s,
|
28
|
+
:properties => properties
|
29
|
+
})
|
30
|
+
end
|
31
|
+
|
32
|
+
# In addition to the common fields, identify accepts:
|
33
|
+
#
|
34
|
+
# - "traits"
|
35
|
+
def parse_for_identify(fields)
|
36
|
+
common = parse_common_fields(fields)
|
37
|
+
|
38
|
+
traits = fields[:traits] || {}
|
39
|
+
check_is_hash!(traits, 'traits')
|
40
|
+
isoify_dates! traits
|
41
|
+
|
42
|
+
common.merge({
|
43
|
+
:type => 'identify',
|
44
|
+
:traits => traits
|
45
|
+
})
|
46
|
+
end
|
47
|
+
|
48
|
+
# In addition to the common fields, alias accepts:
|
49
|
+
#
|
50
|
+
# - "previous_id"
|
51
|
+
def parse_for_alias(fields)
|
52
|
+
common = parse_common_fields(fields)
|
53
|
+
|
54
|
+
previous_id = fields[:previous_id]
|
55
|
+
check_presence!(previous_id, 'previous_id')
|
56
|
+
|
57
|
+
common.merge({
|
58
|
+
:type => 'alias',
|
59
|
+
:previousId => previous_id
|
60
|
+
})
|
61
|
+
end
|
62
|
+
|
63
|
+
# In addition to the common fields, group accepts:
|
64
|
+
#
|
65
|
+
# - "group_id"
|
66
|
+
# - "traits"
|
67
|
+
def parse_for_group(fields)
|
68
|
+
common = parse_common_fields(fields)
|
69
|
+
|
70
|
+
group_id = fields[:group_id]
|
71
|
+
traits = fields[:traits] || {}
|
72
|
+
|
73
|
+
check_presence!(group_id, 'group_id')
|
74
|
+
check_is_hash!(traits, 'traits')
|
75
|
+
|
76
|
+
isoify_dates! traits
|
77
|
+
|
78
|
+
common.merge({
|
79
|
+
:type => 'group',
|
80
|
+
:groupId => group_id,
|
81
|
+
:traits => traits
|
82
|
+
})
|
83
|
+
end
|
84
|
+
|
85
|
+
# In addition to the common fields, page accepts:
|
86
|
+
#
|
87
|
+
# - "name"
|
88
|
+
# - "properties"
|
89
|
+
def parse_for_page(fields)
|
90
|
+
common = parse_common_fields(fields)
|
91
|
+
|
92
|
+
name = fields[:name] || ''
|
93
|
+
properties = fields[:properties] || {}
|
94
|
+
|
95
|
+
check_is_hash!(properties, 'properties')
|
96
|
+
|
97
|
+
isoify_dates! properties
|
98
|
+
|
99
|
+
common.merge({
|
100
|
+
:type => 'page',
|
101
|
+
:name => name.to_s,
|
102
|
+
:properties => properties
|
103
|
+
})
|
104
|
+
end
|
105
|
+
|
106
|
+
# In addition to the common fields, screen accepts:
|
107
|
+
#
|
108
|
+
# - "name"
|
109
|
+
# - "properties"
|
110
|
+
# - "category" (Not in spec, retained for backward compatibility"
|
111
|
+
def parse_for_screen(fields)
|
112
|
+
common = parse_common_fields(fields)
|
113
|
+
|
114
|
+
name = fields[:name]
|
115
|
+
properties = fields[:properties] || {}
|
116
|
+
category = fields[:category]
|
117
|
+
|
118
|
+
check_presence!(name, 'name')
|
119
|
+
check_is_hash!(properties, 'properties')
|
120
|
+
|
121
|
+
isoify_dates! properties
|
122
|
+
|
123
|
+
parsed = common.merge({
|
124
|
+
:type => 'screen',
|
125
|
+
:name => name,
|
126
|
+
:properties => properties
|
127
|
+
})
|
128
|
+
|
129
|
+
parsed[:category] = category if category
|
130
|
+
|
131
|
+
parsed
|
132
|
+
end
|
133
|
+
|
134
|
+
private
|
135
|
+
|
136
|
+
def parse_common_fields(fields)
|
137
|
+
timestamp = fields[:timestamp] || Time.new
|
138
|
+
message_id = fields[:message_id].to_s if fields[:message_id]
|
139
|
+
context = fields[:context] || {}
|
140
|
+
|
141
|
+
check_user_id! fields
|
142
|
+
check_timestamp! timestamp
|
143
|
+
|
144
|
+
add_context! context
|
145
|
+
|
146
|
+
parsed = {
|
147
|
+
:context => context,
|
148
|
+
:messageId => message_id,
|
149
|
+
:timestamp => datetime_in_iso8601(timestamp)
|
150
|
+
}
|
151
|
+
|
152
|
+
parsed[:userId] = fields[:user_id] if fields[:user_id]
|
153
|
+
parsed[:anonymousId] = fields[:anonymous_id] if fields[:anonymous_id]
|
154
|
+
parsed[:integrations] = fields[:integrations] if fields[:integrations]
|
155
|
+
|
156
|
+
# Not in spec, retained for backward compatibility
|
157
|
+
parsed[:options] = fields[:options] if fields[:options]
|
158
|
+
|
159
|
+
parsed
|
160
|
+
end
|
161
|
+
|
162
|
+
def check_user_id!(fields)
|
163
|
+
unless fields[:user_id] || fields[:anonymous_id]
|
164
|
+
raise ArgumentError, 'Must supply either user_id or anonymous_id'
|
165
|
+
end
|
166
|
+
end
|
167
|
+
|
168
|
+
def check_timestamp!(timestamp)
|
169
|
+
raise ArgumentError, 'Timestamp must be a Time' unless timestamp.is_a? Time
|
170
|
+
end
|
171
|
+
|
172
|
+
def add_context!(context)
|
173
|
+
context[:library] = { :name => 'clearbit-ruby', :version => Clearbit::VERSION.to_s }
|
174
|
+
end
|
175
|
+
|
176
|
+
# private: Ensures that a string is non-empty
|
177
|
+
#
|
178
|
+
# obj - String|Number that must be non-blank
|
179
|
+
# name - Name of the validated value
|
180
|
+
def check_presence!(obj, name)
|
181
|
+
if obj.nil? || (obj.is_a?(String) && obj.empty?)
|
182
|
+
raise ArgumentError, "#{name} must be given"
|
183
|
+
end
|
184
|
+
end
|
185
|
+
|
186
|
+
def check_is_hash!(obj, name)
|
187
|
+
raise ArgumentError, "#{name} must be a Hash" unless obj.is_a? Hash
|
188
|
+
end
|
189
|
+
end
|
190
|
+
end
|
191
|
+
end
|
192
|
+
end
|