km-db 0.2.1 → 0.3.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +7 -0
- data/.ruby-version +1 -0
- data/Gemfile +2 -4
- data/Gemfile.lock +179 -20
- data/Procfile +2 -0
- data/Procfile.work +1 -0
- data/README.md +186 -0
- data/Rakefile +1 -0
- data/bin/kmdb-flush +13 -0
- data/bin/kmdb-import +13 -0
- data/bin/kmdb-partition +15 -0
- data/bin/kmdb-pool +8 -0
- data/bin/kmdb-realias +12 -0
- data/bin/kmdb-ui +6 -0
- data/bin/kmdb-work +17 -0
- data/config/amazon-rds-ca-cert.pem +260 -0
- data/config.ru +8 -0
- data/km-db.gemspec +17 -17
- data/lib/kmdb/{belongs_to_user.rb → concerns/belongs_to_user.rb} +3 -3
- data/lib/kmdb/concerns/has_properties.rb +35 -0
- data/lib/kmdb/jobs/find_files.rb +32 -0
- data/lib/kmdb/jobs/list_files.rb +37 -0
- data/lib/kmdb/jobs/locked.rb +10 -0
- data/lib/kmdb/jobs/parse_file.rb +109 -0
- data/lib/kmdb/jobs/record_batch.rb +65 -0
- data/lib/kmdb/jobs/redo_unaliasing.rb +31 -0
- data/lib/kmdb/jobs/unalias_user.rb +32 -0
- data/lib/kmdb/migrations/01_kmdb_initial.rb +78 -0
- data/lib/kmdb/migrations/02_kmdb_partitions.rb +28 -0
- data/lib/kmdb/migrations/03_kmdb_blacklist.rb +20 -0
- data/lib/kmdb/models/alias.rb +36 -0
- data/lib/kmdb/models/blacklisted_property.rb +20 -0
- data/lib/kmdb/models/custom_record.rb +53 -0
- data/lib/kmdb/models/dumpfile.rb +33 -0
- data/lib/kmdb/models/event.rb +56 -0
- data/lib/kmdb/models/event_batch.rb +72 -0
- data/lib/kmdb/models/global_uid.rb +42 -0
- data/lib/kmdb/models/ignored_user.rb +20 -0
- data/lib/kmdb/models/json_file.rb +56 -0
- data/lib/kmdb/models/key.rb +28 -0
- data/lib/kmdb/models/property.rb +44 -0
- data/lib/kmdb/models/s3_object.rb +54 -0
- data/lib/kmdb/models/user.rb +53 -0
- data/lib/kmdb/models/whitelisted_event.rb +20 -0
- data/lib/kmdb/parser.rb +4 -4
- data/lib/kmdb/redis.rb +17 -0
- data/lib/kmdb/resque.rb +38 -0
- data/lib/kmdb/s3_bucket.rb +33 -0
- data/lib/kmdb/services/partitioner.rb +65 -0
- data/lib/kmdb/version.rb +1 -1
- data/lib/kmdb.rb +31 -6
- metadata +236 -186
- data/README.markdown +0 -91
- data/bin/km_db_import +0 -36
- data/lib/kmdb/custom_record.rb +0 -54
- data/lib/kmdb/dumpfile.rb +0 -23
- data/lib/kmdb/event.rb +0 -39
- data/lib/kmdb/has_properties.rb +0 -33
- data/lib/kmdb/key.rb +0 -56
- data/lib/kmdb/migration.rb +0 -63
- data/lib/kmdb/parallel_parser.rb +0 -85
- data/lib/kmdb/property.rb +0 -33
- data/lib/kmdb/user.rb +0 -83
metadata
CHANGED
@@ -1,234 +1,284 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: km-db
|
3
|
-
version: !ruby/object:Gem::Version
|
4
|
-
|
5
|
-
prerelease:
|
6
|
-
segments:
|
7
|
-
- 0
|
8
|
-
- 2
|
9
|
-
- 1
|
10
|
-
version: 0.2.1
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.3.2
|
11
5
|
platform: ruby
|
12
|
-
authors:
|
13
|
-
-
|
6
|
+
authors:
|
7
|
+
- Julien Letessier
|
14
8
|
autorequire:
|
15
9
|
bindir: bin
|
16
10
|
cert_chain: []
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
dependencies:
|
21
|
-
- !ruby/object:Gem::Dependency
|
22
|
-
requirement: &id001 !ruby/object:Gem::Requirement
|
23
|
-
none: false
|
24
|
-
requirements:
|
25
|
-
- - ">="
|
26
|
-
- !ruby/object:Gem::Version
|
27
|
-
hash: 23
|
28
|
-
segments:
|
29
|
-
- 1
|
30
|
-
- 0
|
31
|
-
- 0
|
32
|
-
version: 1.0.0
|
33
|
-
prerelease: false
|
11
|
+
date: 2015-06-18 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
34
14
|
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
35
20
|
type: :development
|
36
|
-
version_requirements: *id001
|
37
|
-
- !ruby/object:Gem::Dependency
|
38
|
-
requirement: &id002 !ruby/object:Gem::Requirement
|
39
|
-
none: false
|
40
|
-
requirements:
|
41
|
-
- - ~>
|
42
|
-
- !ruby/object:Gem::Version
|
43
|
-
hash: 31
|
44
|
-
segments:
|
45
|
-
- 2
|
46
|
-
- 4
|
47
|
-
- 0
|
48
|
-
version: 2.4.0
|
49
21
|
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
50
28
|
name: rspec
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 2.4.0
|
51
34
|
type: :development
|
52
|
-
version_requirements: *id002
|
53
|
-
- !ruby/object:Gem::Dependency
|
54
|
-
requirement: &id003 !ruby/object:Gem::Requirement
|
55
|
-
none: false
|
56
|
-
requirements:
|
57
|
-
- - ">="
|
58
|
-
- !ruby/object:Gem::Version
|
59
|
-
hash: 3
|
60
|
-
segments:
|
61
|
-
- 0
|
62
|
-
version: "0"
|
63
35
|
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 2.4.0
|
41
|
+
- !ruby/object:Gem::Dependency
|
64
42
|
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
65
48
|
type: :development
|
66
|
-
version_requirements: *id003
|
67
|
-
- !ruby/object:Gem::Dependency
|
68
|
-
requirement: &id004 !ruby/object:Gem::Requirement
|
69
|
-
none: false
|
70
|
-
requirements:
|
71
|
-
- - ">="
|
72
|
-
- !ruby/object:Gem::Version
|
73
|
-
hash: 3
|
74
|
-
segments:
|
75
|
-
- 0
|
76
|
-
version: "0"
|
77
|
-
prerelease: false
|
78
|
-
name: json
|
79
|
-
type: :development
|
80
|
-
version_requirements: *id004
|
81
|
-
- !ruby/object:Gem::Dependency
|
82
|
-
requirement: &id005 !ruby/object:Gem::Requirement
|
83
|
-
none: false
|
84
|
-
requirements:
|
85
|
-
- - ">="
|
86
|
-
- !ruby/object:Gem::Version
|
87
|
-
hash: 3
|
88
|
-
segments:
|
89
|
-
- 0
|
90
|
-
version: "0"
|
91
49
|
prerelease: false
|
92
|
-
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: pry
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
93
62
|
type: :development
|
94
|
-
version_requirements: *id005
|
95
|
-
- !ruby/object:Gem::Dependency
|
96
|
-
requirement: &id006 !ruby/object:Gem::Requirement
|
97
|
-
none: false
|
98
|
-
requirements:
|
99
|
-
- - ">="
|
100
|
-
- !ruby/object:Gem::Version
|
101
|
-
hash: 3
|
102
|
-
segments:
|
103
|
-
- 0
|
104
|
-
version: "0"
|
105
63
|
prerelease: false
|
106
|
-
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: oj
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
107
76
|
type: :runtime
|
108
|
-
version_requirements: *id006
|
109
|
-
- !ruby/object:Gem::Dependency
|
110
|
-
requirement: &id007 !ruby/object:Gem::Requirement
|
111
|
-
none: false
|
112
|
-
requirements:
|
113
|
-
- - ">="
|
114
|
-
- !ruby/object:Gem::Version
|
115
|
-
hash: 3
|
116
|
-
segments:
|
117
|
-
- 0
|
118
|
-
version: "0"
|
119
77
|
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
120
84
|
name: progressbar
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
121
90
|
type: :runtime
|
122
|
-
version_requirements: *id007
|
123
|
-
- !ruby/object:Gem::Dependency
|
124
|
-
requirement: &id008 !ruby/object:Gem::Requirement
|
125
|
-
none: false
|
126
|
-
requirements:
|
127
|
-
- - ">="
|
128
|
-
- !ruby/object:Gem::Version
|
129
|
-
hash: 3
|
130
|
-
segments:
|
131
|
-
- 0
|
132
|
-
version: "0"
|
133
|
-
prerelease: false
|
134
|
-
name: parallel
|
135
|
-
type: :runtime
|
136
|
-
version_requirements: *id008
|
137
|
-
- !ruby/object:Gem::Dependency
|
138
|
-
requirement: &id009 !ruby/object:Gem::Requirement
|
139
|
-
none: false
|
140
|
-
requirements:
|
141
|
-
- - ">="
|
142
|
-
- !ruby/object:Gem::Version
|
143
|
-
hash: 3
|
144
|
-
segments:
|
145
|
-
- 0
|
146
|
-
version: "0"
|
147
91
|
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
148
98
|
name: andand
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - ">="
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
149
104
|
type: :runtime
|
150
|
-
version_requirements: *id009
|
151
|
-
- !ruby/object:Gem::Dependency
|
152
|
-
requirement: &id010 !ruby/object:Gem::Requirement
|
153
|
-
none: false
|
154
|
-
requirements:
|
155
|
-
- - ~>
|
156
|
-
- !ruby/object:Gem::Version
|
157
|
-
hash: 27
|
158
|
-
segments:
|
159
|
-
- 2
|
160
|
-
- 3
|
161
|
-
- 12
|
162
|
-
version: 2.3.12
|
163
105
|
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
- !ruby/object:Gem::Dependency
|
164
112
|
name: activerecord
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - "~>"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '4.1'
|
165
118
|
type: :runtime
|
166
|
-
|
167
|
-
|
168
|
-
|
169
|
-
-
|
170
|
-
|
171
|
-
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - "~>"
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '4.1'
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: resque
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - ">="
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '0'
|
132
|
+
type: :runtime
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - ">="
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '0'
|
139
|
+
- !ruby/object:Gem::Dependency
|
140
|
+
name: resque-lock
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - ">="
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: '0'
|
146
|
+
type: :runtime
|
147
|
+
prerelease: false
|
148
|
+
version_requirements: !ruby/object:Gem::Requirement
|
149
|
+
requirements:
|
150
|
+
- - ">="
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: '0'
|
153
|
+
- !ruby/object:Gem::Dependency
|
154
|
+
name: foreman
|
155
|
+
requirement: !ruby/object:Gem::Requirement
|
156
|
+
requirements:
|
157
|
+
- - ">="
|
158
|
+
- !ruby/object:Gem::Version
|
159
|
+
version: '0'
|
160
|
+
type: :runtime
|
161
|
+
prerelease: false
|
162
|
+
version_requirements: !ruby/object:Gem::Requirement
|
163
|
+
requirements:
|
164
|
+
- - ">="
|
165
|
+
- !ruby/object:Gem::Version
|
166
|
+
version: '0'
|
167
|
+
- !ruby/object:Gem::Dependency
|
168
|
+
name: fog
|
169
|
+
requirement: !ruby/object:Gem::Requirement
|
170
|
+
requirements:
|
171
|
+
- - ">="
|
172
|
+
- !ruby/object:Gem::Version
|
173
|
+
version: '0'
|
174
|
+
type: :runtime
|
175
|
+
prerelease: false
|
176
|
+
version_requirements: !ruby/object:Gem::Requirement
|
177
|
+
requirements:
|
178
|
+
- - ">="
|
179
|
+
- !ruby/object:Gem::Version
|
180
|
+
version: '0'
|
181
|
+
- !ruby/object:Gem::Dependency
|
182
|
+
name: mysql2
|
183
|
+
requirement: !ruby/object:Gem::Requirement
|
184
|
+
requirements:
|
185
|
+
- - ">="
|
186
|
+
- !ruby/object:Gem::Version
|
187
|
+
version: '0'
|
188
|
+
type: :runtime
|
189
|
+
prerelease: false
|
190
|
+
version_requirements: !ruby/object:Gem::Requirement
|
191
|
+
requirements:
|
192
|
+
- - ">="
|
193
|
+
- !ruby/object:Gem::Version
|
194
|
+
version: '0'
|
195
|
+
description:
|
196
|
+
email:
|
197
|
+
- julien.letessier@gmail.com
|
198
|
+
executables:
|
199
|
+
- kmdb-flush
|
200
|
+
- kmdb-import
|
201
|
+
- kmdb-partition
|
202
|
+
- kmdb-pool
|
203
|
+
- kmdb-realias
|
204
|
+
- kmdb-ui
|
205
|
+
- kmdb-work
|
172
206
|
extensions: []
|
173
|
-
|
174
207
|
extra_rdoc_files: []
|
175
|
-
|
176
|
-
|
208
|
+
files:
|
209
|
+
- ".gitignore"
|
210
|
+
- ".ruby-version"
|
177
211
|
- Gemfile
|
178
212
|
- Gemfile.lock
|
179
|
-
-
|
213
|
+
- Procfile
|
214
|
+
- Procfile.work
|
215
|
+
- README.md
|
180
216
|
- Rakefile
|
181
|
-
- bin/
|
217
|
+
- bin/kmdb-flush
|
218
|
+
- bin/kmdb-import
|
219
|
+
- bin/kmdb-partition
|
220
|
+
- bin/kmdb-pool
|
221
|
+
- bin/kmdb-realias
|
222
|
+
- bin/kmdb-ui
|
223
|
+
- bin/kmdb-work
|
224
|
+
- config.ru
|
225
|
+
- config/amazon-rds-ca-cert.pem
|
182
226
|
- km-db.gemspec
|
183
227
|
- lib/kmdb.rb
|
184
|
-
- lib/kmdb/belongs_to_user.rb
|
185
|
-
- lib/kmdb/
|
186
|
-
- lib/kmdb/
|
187
|
-
- lib/kmdb/
|
188
|
-
- lib/kmdb/
|
189
|
-
- lib/kmdb/
|
190
|
-
- lib/kmdb/
|
191
|
-
- lib/kmdb/
|
228
|
+
- lib/kmdb/concerns/belongs_to_user.rb
|
229
|
+
- lib/kmdb/concerns/has_properties.rb
|
230
|
+
- lib/kmdb/jobs/find_files.rb
|
231
|
+
- lib/kmdb/jobs/list_files.rb
|
232
|
+
- lib/kmdb/jobs/locked.rb
|
233
|
+
- lib/kmdb/jobs/parse_file.rb
|
234
|
+
- lib/kmdb/jobs/record_batch.rb
|
235
|
+
- lib/kmdb/jobs/redo_unaliasing.rb
|
236
|
+
- lib/kmdb/jobs/unalias_user.rb
|
237
|
+
- lib/kmdb/migrations/01_kmdb_initial.rb
|
238
|
+
- lib/kmdb/migrations/02_kmdb_partitions.rb
|
239
|
+
- lib/kmdb/migrations/03_kmdb_blacklist.rb
|
240
|
+
- lib/kmdb/models/alias.rb
|
241
|
+
- lib/kmdb/models/blacklisted_property.rb
|
242
|
+
- lib/kmdb/models/custom_record.rb
|
243
|
+
- lib/kmdb/models/dumpfile.rb
|
244
|
+
- lib/kmdb/models/event.rb
|
245
|
+
- lib/kmdb/models/event_batch.rb
|
246
|
+
- lib/kmdb/models/global_uid.rb
|
247
|
+
- lib/kmdb/models/ignored_user.rb
|
248
|
+
- lib/kmdb/models/json_file.rb
|
249
|
+
- lib/kmdb/models/key.rb
|
250
|
+
- lib/kmdb/models/property.rb
|
251
|
+
- lib/kmdb/models/s3_object.rb
|
252
|
+
- lib/kmdb/models/user.rb
|
253
|
+
- lib/kmdb/models/whitelisted_event.rb
|
192
254
|
- lib/kmdb/parser.rb
|
193
|
-
- lib/kmdb/
|
194
|
-
- lib/kmdb/
|
255
|
+
- lib/kmdb/redis.rb
|
256
|
+
- lib/kmdb/resque.rb
|
257
|
+
- lib/kmdb/s3_bucket.rb
|
258
|
+
- lib/kmdb/services/partitioner.rb
|
195
259
|
- lib/kmdb/user_error.rb
|
196
260
|
- lib/kmdb/version.rb
|
197
|
-
has_rdoc: true
|
198
261
|
homepage: https://github.com/housetrip/km-db
|
199
262
|
licenses: []
|
200
|
-
|
263
|
+
metadata: {}
|
201
264
|
post_install_message:
|
202
265
|
rdoc_options: []
|
203
|
-
|
204
|
-
require_paths:
|
266
|
+
require_paths:
|
205
267
|
- lib
|
206
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
207
|
-
|
208
|
-
requirements:
|
268
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
269
|
+
requirements:
|
209
270
|
- - ">="
|
210
|
-
- !ruby/object:Gem::Version
|
211
|
-
|
212
|
-
|
213
|
-
|
214
|
-
version: "0"
|
215
|
-
required_rubygems_version: !ruby/object:Gem::Requirement
|
216
|
-
none: false
|
217
|
-
requirements:
|
271
|
+
- !ruby/object:Gem::Version
|
272
|
+
version: '0'
|
273
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
274
|
+
requirements:
|
218
275
|
- - ">="
|
219
|
-
- !ruby/object:Gem::Version
|
220
|
-
|
221
|
-
segments:
|
222
|
-
- 1
|
223
|
-
- 3
|
224
|
-
- 6
|
225
|
-
version: 1.3.6
|
276
|
+
- !ruby/object:Gem::Version
|
277
|
+
version: '0'
|
226
278
|
requirements: []
|
227
|
-
|
228
279
|
rubyforge_project:
|
229
|
-
rubygems_version:
|
280
|
+
rubygems_version: 2.2.2
|
230
281
|
signing_key:
|
231
|
-
specification_version:
|
282
|
+
specification_version: 4
|
232
283
|
summary: Process KISSmetrics data dumps
|
233
284
|
test_files: []
|
234
|
-
|
data/README.markdown
DELETED
@@ -1,91 +0,0 @@
|
|
1
|
-
The `km-db` gem should be useful to KissMetrics (KM) users.
|
2
|
-
Its aim is to efficiently process data obtained with KM's "Data Export" feature.
|
3
|
-
|
4
|
-
It is meant to :
|
5
|
-
|
6
|
-
* import KM event dumps into a SQL database (preferably MySQL / PostgreSQL)
|
7
|
-
* quickly process KM event dumps
|
8
|
-
|
9
|
-
Once imported, you can run complex queries against your visit history, for instance run multivariate analysis.
|
10
|
-
|
11
|
-
Beware though, KM data can be huge, and processing it is taxing !
|
12
|
-
|
13
|
-
|
14
|
-
Installing
|
15
|
-
----------
|
16
|
-
|
17
|
-
Add this to your Gemfile if you're using Bundler:
|
18
|
-
|
19
|
-
gem 'km-db', :git => 'git://github.com/HouseTrip/km-db.git'
|
20
|
-
|
21
|
-
|
22
|
-
Importing data
|
23
|
-
--------------
|
24
|
-
|
25
|
-
Running reports on raw logs can be less effective than running against a (relational) database.
|
26
|
-
`km-db` provides a `km_db_import` executable. Run it with:
|
27
|
-
|
28
|
-
$ bundle exec km_db_import <data-dump-directory>…
|
29
|
-
|
30
|
-
By default, you events will be imported in `test.db`, a SQLite database.
|
31
|
-
|
32
|
-
You can create `km_db.yml` or `config/km_db.yml` to have it import using another adapter, for instance:
|
33
|
-
|
34
|
-
---- km_db.yml ----
|
35
|
-
adapter: mysql2
|
36
|
-
database: km_events
|
37
|
-
user: root
|
38
|
-
|
39
|
-
Remember to add `sqlite3-ruby` or `mysql2` to your Gemfile.
|
40
|
-
|
41
|
-
|
42
|
-
Using imported data
|
43
|
-
-------------------
|
44
|
-
|
45
|
-
The `KMDB` module exposes four `ActiveRecord` classes:
|
46
|
-
`Event`, `Property`, `User` are the main domain objects.
|
47
|
-
`Key` is used to intern strings (event and property names) for performance.
|
48
|
-
|
49
|
-
### Finding events and properties
|
50
|
-
|
51
|
-
All visits during Jan. 2012:
|
52
|
-
|
53
|
-
KMDB::Event.before('2012-02-1').after('2012-01-01').named('visited site').by_date
|
54
|
-
|
55
|
-
All of a user's visit:
|
56
|
-
|
57
|
-
KMDB::User.last.events.named('visited site')
|
58
|
-
|
59
|
-
A user's referers:
|
60
|
-
|
61
|
-
KMDB::User.last.properties.named('referer').map(&:value)
|
62
|
-
|
63
|
-
Load some properties with events (uses a left join by default):
|
64
|
-
|
65
|
-
KMDB::User.last.events.with_properties('a prop', 'another prop').map(&:another_prop)
|
66
|
-
|
67
|
-
Note that many more complex queries will require building SQL queries directly.
|
68
|
-
|
69
|
-
|
70
|
-
Processing data
|
71
|
-
---------------
|
72
|
-
|
73
|
-
You don't have to import to filter your data.
|
74
|
-
|
75
|
-
The two classes you're looking for are `KMDB::Parser` and `KMDB::ParallelParser`.
|
76
|
-
The latter runs your filter task on all available CPUs, using the `parallel` gem.
|
77
|
-
|
78
|
-
The following example counts the number of *aliasing* events in all JSON files under `dumps/`:
|
79
|
-
|
80
|
-
require 'rubygems'
|
81
|
-
require 'kmdb'
|
82
|
-
|
83
|
-
counter = 0
|
84
|
-
parser = KMDB::Parser.new
|
85
|
-
parser.add_filter do |text,event|
|
86
|
-
counter += 1 if event['_p2']
|
87
|
-
end
|
88
|
-
parser.run('dumps/')
|
89
|
-
puts counter
|
90
|
-
|
91
|
-
Note that it will not work with `ParallelParser`, as the `counter` variable will be different for each process.
|
data/bin/km_db_import
DELETED
@@ -1,36 +0,0 @@
|
|
1
|
-
#!/usr/bin/env ruby
|
2
|
-
=begin
|
3
|
-
|
4
|
-
Import KM events from the raw dumps.
|
5
|
-
|
6
|
-
=end
|
7
|
-
|
8
|
-
require 'rubygems'
|
9
|
-
require 'kmdb'
|
10
|
-
|
11
|
-
if KMDB::Event.connection.class.to_s =~ /(mysql|pgsql)/i
|
12
|
-
parser_class = KMDB::ParallelParser
|
13
|
-
else
|
14
|
-
parser_class = KMDB::Parser
|
15
|
-
end
|
16
|
-
|
17
|
-
parser = parser_class.new(:resume => 'import',
|
18
|
-
:verbose => true)
|
19
|
-
|
20
|
-
# import events by category
|
21
|
-
parser.add_filter { |text, event|
|
22
|
-
if event['_p2']
|
23
|
-
KMDB::User.alias! event['_p'], event['_p2']
|
24
|
-
elsif event['_n']
|
25
|
-
KMDB::Event.record event
|
26
|
-
else
|
27
|
-
KMDB::Property.set event
|
28
|
-
end
|
29
|
-
|
30
|
-
event
|
31
|
-
}
|
32
|
-
|
33
|
-
parser.run(ARGV) # heavy lifting here
|
34
|
-
KMDB::Event.connection.reconnect! # reconnect to database (breaks because of processes forking off)
|
35
|
-
KMDB::User.resolve_alias_chains! # detect and filter alias chains
|
36
|
-
KMDB::Key.fix_duplicates! # remove key duplicates
|
data/lib/kmdb/custom_record.rb
DELETED
@@ -1,54 +0,0 @@
|
|
1
|
-
=begin
|
2
|
-
|
3
|
-
Base class for KM data.
|
4
|
-
Connect to a secondary database to store events, users, & properties.
|
5
|
-
|
6
|
-
FIXME: the database connection is hard-coded for now.
|
7
|
-
|
8
|
-
=end
|
9
|
-
|
10
|
-
require 'active_record'
|
11
|
-
require 'erb'
|
12
|
-
require 'yaml'
|
13
|
-
require 'kmdb/migration'
|
14
|
-
|
15
|
-
|
16
|
-
module KMDB
|
17
|
-
class CustomRecord < ActiveRecord::Base
|
18
|
-
DefaultConfig = {
|
19
|
-
'adapter' => 'sqlite3',
|
20
|
-
'database' => "test.db"
|
21
|
-
}
|
22
|
-
|
23
|
-
def self.disable_index
|
24
|
-
connection.execute %Q{
|
25
|
-
ALTER TABLE `#{table_name}` DISABLE KEYS;
|
26
|
-
}
|
27
|
-
end
|
28
|
-
|
29
|
-
def self.enable_index
|
30
|
-
connection.execute %Q{
|
31
|
-
ALTER TABLE `#{table_name}` ENABLE KEYS;
|
32
|
-
}
|
33
|
-
end
|
34
|
-
|
35
|
-
def self.find_or_create(options)
|
36
|
-
find(:first, :conditions => options) || create(options)
|
37
|
-
end
|
38
|
-
|
39
|
-
def self.connect_to_km_db!
|
40
|
-
config = DefaultConfig.dup
|
41
|
-
['km_db.yml', 'config/km_db.yml'].each do |config_path|
|
42
|
-
next unless File.exist?(config_path)
|
43
|
-
config.merge! YAML.load(ERB.new(File.open(config_path).read).result)
|
44
|
-
break
|
45
|
-
end
|
46
|
-
establish_connection(config)
|
47
|
-
|
48
|
-
unless connection.table_exists?('events')
|
49
|
-
SetupEventsDatabase.up
|
50
|
-
self.reset_column_information
|
51
|
-
end
|
52
|
-
end
|
53
|
-
end
|
54
|
-
end
|
data/lib/kmdb/dumpfile.rb
DELETED
@@ -1,23 +0,0 @@
|
|
1
|
-
require 'kmdb/custom_record'
|
2
|
-
|
3
|
-
module KMDB
|
4
|
-
class Dumpfile < CustomRecord
|
5
|
-
set_table_name "dumpfiles"
|
6
|
-
|
7
|
-
validates_presence_of :offset
|
8
|
-
validates_presence_of :path
|
9
|
-
|
10
|
-
def set(offset)
|
11
|
-
update_attributes!(:offset => offset)
|
12
|
-
end
|
13
|
-
|
14
|
-
def offset
|
15
|
-
attributes['offset'] || 0
|
16
|
-
end
|
17
|
-
|
18
|
-
def self.get(pathname, job = nil)
|
19
|
-
job ||= 'nil'
|
20
|
-
find_or_create(:path => pathname.cleanpath.to_s, :job => job)
|
21
|
-
end
|
22
|
-
end
|
23
|
-
end
|