redata 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +235 -0
- data/Rakefile +2 -0
- data/bin/adjust +17 -0
- data/bin/console +14 -0
- data/bin/notice +20 -0
- data/bin/redata +20 -0
- data/bin/setup +8 -0
- data/lib/redata.rb +5 -0
- data/lib/redata/bucket.rb +27 -0
- data/lib/redata/config.rb +108 -0
- data/lib/redata/database.rb +92 -0
- data/lib/redata/log.rb +20 -0
- data/lib/redata/notice.rb +21 -0
- data/lib/redata/parser.rb +147 -0
- data/lib/redata/relation.rb +17 -0
- data/lib/redata/relation/export.rb +30 -0
- data/lib/redata/relation/table.rb +24 -0
- data/lib/redata/relation/view.rb +24 -0
- data/lib/redata/requires.rb +24 -0
- data/lib/redata/schema.rb +64 -0
- data/lib/redata/ssh.rb +28 -0
- data/lib/redata/tasks.rb +84 -0
- data/lib/redata/version.rb +3 -0
- data/redata.gemspec +29 -0
- metadata +172 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 58c04577fb55ac865dda405347811acf421dac3e
|
4
|
+
data.tar.gz: a1a33fb66a93f198aca56731417c2a2d90b65192
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 199b5da361e782c96ba4dbb1c5e465ca3fd7e9a8f4471776efb0915408ec9f43428aadfda25f5037e883c4798bbec4633c2e0aa7ddb76d59daafc3e8c0ed56dc
|
7
|
+
data.tar.gz: 551db6a70bbcdfd29a39aed84d69258d883afcbede934bc5f7fc08ed165b8c3978671f2cba2e8d26ee3bc5a6a8349cc4cde86028824241b01dfce1fa6e6dd092
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 goshan_tvi
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,235 @@
|
|
1
|
+
# Redata
|
2
|
+
|
3
|
+
Help you to controll data process in redshift with easy query and command line
|
4
|
+
|
5
|
+
|
6
|
+
## Installation
|
7
|
+
|
8
|
+
Add this line to your application's Gemfile:
|
9
|
+
|
10
|
+
```ruby
|
11
|
+
gem 'redata'
|
12
|
+
```
|
13
|
+
|
14
|
+
And then execute:
|
15
|
+
|
16
|
+
$ bundle install
|
17
|
+
|
18
|
+
Or install it yourself as:
|
19
|
+
|
20
|
+
$ gem install redata
|
21
|
+
|
22
|
+
## Usage
|
23
|
+
|
24
|
+
### Config
|
25
|
+
|
26
|
+
+ config `config/redata.yml` for general setting
|
27
|
+
|
28
|
+
```YAML
|
29
|
+
start_date: "2016-04-04" # default data start date
|
30
|
+
timezone: "Asia/Tokyo"
|
31
|
+
s3:
|
32
|
+
aws_access_key_id: {key_id}
|
33
|
+
aws_secret_access_key: {key_secret}
|
34
|
+
region: {s3_region}
|
35
|
+
bucket:
|
36
|
+
production: {bucket_name}
|
37
|
+
development: {bucket_name}
|
38
|
+
ssh: # this setting will be used in ssh mode when you access private database
|
39
|
+
HostName: {gateway_host}
|
40
|
+
IdentityFile: {~/.ssh/key.pem}
|
41
|
+
User: {username}
|
42
|
+
slack_bot: # this setting will be used for slack notice push
|
43
|
+
token: {bot_token}
|
44
|
+
channel: {slack_channel}
|
45
|
+
```
|
46
|
+
|
47
|
+
+ config `config/database.yml` for development and production environment in redshift database
|
48
|
+
eg.
|
49
|
+
|
50
|
+
```YAML
|
51
|
+
development:
|
52
|
+
host: localhost
|
53
|
+
username: user
|
54
|
+
password: ''
|
55
|
+
database: dev
|
56
|
+
export: # target platform db(mysql) which export data to
|
57
|
+
app: # platform name
|
58
|
+
username: root
|
59
|
+
password: ''
|
60
|
+
host: localhost
|
61
|
+
database: app
|
62
|
+
```
|
63
|
+
|
64
|
+
+ config `config/relations.rb` for data object in redshift and exporting process to mysql
|
65
|
+
eg.
|
66
|
+
|
67
|
+
```RUBY
|
68
|
+
Redata::Task.schema.config do
|
69
|
+
# Example of declaring a global table
|
70
|
+
table 'table_name'
|
71
|
+
# This declaration means
|
72
|
+
# query file: database/sources/table_name.sql
|
73
|
+
# redshift table: table_name
|
74
|
+
# update type: renewal, delete and re-create when update
|
75
|
+
# key used in command line: table_name
|
76
|
+
|
77
|
+
# Example of declaring a global table with customizing options
|
78
|
+
table 'new_table_name', :dir => 'dir', :file => 'query_file', :update => :append, :as => :alias
|
79
|
+
# This declaration means
|
80
|
+
# query file: database/sources/dir/query_file.sql
|
81
|
+
# redshift table: new_table_name
|
82
|
+
# update type: append, only appending to existing table
|
83
|
+
# key used in command line: alias
|
84
|
+
|
85
|
+
# view is same to table but the update type only has renewal mode
|
86
|
+
table 'view_name'
|
87
|
+
table 'new_view_name', :dir => 'dir', :file => 'query_file_oth', :as => :alias_oth
|
88
|
+
|
89
|
+
# Example of declaring with category
|
90
|
+
category :test_category do
|
91
|
+
table 'test_table'
|
92
|
+
# This declaration means
|
93
|
+
# query file: database/sources/test_category/test_table.sql
|
94
|
+
# redshift table: test_category_test_table
|
95
|
+
# update type: renewal
|
96
|
+
# key used in command line: test_category_test_table
|
97
|
+
|
98
|
+
table 'test_table_oth', :dir => 'dir', :file => 'query_file_oth', :update => append, :as => :alias_oth
|
99
|
+
# This declaration means
|
100
|
+
# query file: database/sources/dir/query_file_oth.sql
|
101
|
+
# redshift table: test_category_test_table
|
102
|
+
# update type: append
|
103
|
+
# key used in command line: test_category_alias_oth
|
104
|
+
|
105
|
+
# view is same to table without appending update type
|
106
|
+
view 'test_view'
|
107
|
+
view 'test_view_oth', :dir => 'dir', :file => 'query_file_oth', :as => :alias_view_oth
|
108
|
+
|
109
|
+
#Example of convertor declaration
|
110
|
+
export 'test_export'
|
111
|
+
# This declaration means
|
112
|
+
# convertor file: database/convertors/test_category/test_export.conv
|
113
|
+
# target mysql database name: test_category (Also see: export config in config/database.yml{:export})
|
114
|
+
# target mysql table: test_export
|
115
|
+
# update type: renewal, delete all records and insert new records
|
116
|
+
# key used in command line: test_category_test_export
|
117
|
+
|
118
|
+
#Example of convertor declaration
|
119
|
+
export 'test_export', :dir => 'dir', :file => 'conv_file', :update => 'append', :as => 'alias_export'
|
120
|
+
# This declaration means
|
121
|
+
# convertor file: database/convertors/dir/conv_file.conv
|
122
|
+
# target mysql database name: test_category
|
123
|
+
# target mysql table: test_export
|
124
|
+
# update type: append, append insert new records without deleting
|
125
|
+
# key used in command line: test_category_alias_export
|
126
|
+
end
|
127
|
+
|
128
|
+
end
|
129
|
+
```
|
130
|
+
|
131
|
+
### Query file
|
132
|
+
|
133
|
+
Query file was used for create table of view in redshift. It is almost like PostgreSQL file but with same new feature. And you have no need to write a create table/view query, the result after running query file will used to create a new table/view, for table, if you use append mode, the result will only be append-inserted to table.
|
134
|
+
eg.
|
135
|
+
|
136
|
+
```SQL
|
137
|
+
-- query file in data/sources/...
|
138
|
+
|
139
|
+
#include 'sub_query_a' --> :a -- include a sub query as object a from _sub_query_a.sql in same folder or database/shared/
|
140
|
+
#include 'sub_query_b' --> :b
|
141
|
+
|
142
|
+
|
143
|
+
select a.col1, a.col2, b.col1, b.col2, b.col3
|
144
|
+
from {a} -- use object a included from sub query file '_sub_query_a.sql'
|
145
|
+
join {b} on b.col1 = a.col1
|
146
|
+
-- If in append mode and this table was setted appending update type, then start_time getting from command input such as `-start_time 2016-11-08` will be used here. When missing input this param, as default [2 days ago] will be used.
|
147
|
+
-- Or if not append mode, start_date will be used as default (Also see config/redata.yml). set start_time when running command , if missing in command, default_start_date will be used
|
148
|
+
where a.col1 >= [start_time]
|
149
|
+
-- current time in setted timezone will be used (About timezon, also see config/redata.yml)
|
150
|
+
and a.col1 <= [current_time]
|
151
|
+
-- some params getting from command input such as `-param_from_command param_value`
|
152
|
+
and a.col2 = [param_from_command]
|
153
|
+
-- x days before today, x will be a integer
|
154
|
+
and b.col3 >= [x days ago]
|
155
|
+
```
|
156
|
+
|
157
|
+
### Convertor config file
|
158
|
+
|
159
|
+
Convertor file was used to generate a select query to get data from redshift and unload to S3. But you have no need to wirte a unload query. If you are using append mode, only data 2 days ago will be select.
|
160
|
+
eg.
|
161
|
+
|
162
|
+
```
|
163
|
+
source: redshift_source_table_or_view
|
164
|
+
columns:
|
165
|
+
cm_id
|
166
|
+
segment_type{'C' => 0, 'T' => 1, 'M1' => 2, 'M2' => 3, 'M3' => 4, 'F1' => 5, 'F2' => 6, 'F3' => 7}
|
167
|
+
v
|
168
|
+
e
|
169
|
+
base_ai
|
170
|
+
sample_num
|
171
|
+
grp
|
172
|
+
```
|
173
|
+
|
174
|
+
> convertor config file in `data/convertors/...`
|
175
|
+
> `source` means the source table in redshift
|
176
|
+
> `columns` means the source columns in source table
|
177
|
+
|
178
|
+
### Command
|
179
|
+
|
180
|
+
There are 3 executable file in bin/
|
181
|
+
- redata --> manage redshift table/view and export data to mysql
|
182
|
+
- adjust --> run some single sql query file in redshift or mysql
|
183
|
+
- notice --> push notice to slack etc.
|
184
|
+
|
185
|
+
#### redata
|
186
|
+
|
187
|
+
Usage: `redata [-options] [action] [object key] {platform}`
|
188
|
+
+ action
|
189
|
+
- create --> create a table/view or append data to table in redshift
|
190
|
+
- delete --> delete a table/view in redshift
|
191
|
+
- checkout --> export data in table/view of redshift into S3
|
192
|
+
- inject --> import data into mysql table from S3
|
193
|
+
+ object key --> object will be create/delete/checkout/inject declared in `config/relation.rb`
|
194
|
+
+ platform --> when injecting data into mysql, there may be several platform declared in `config/database.yml{:export}` for same database, here is setting which platform to use. *If the platform here could not be found in `database.yml` or have not set platform, the default export will be used.*
|
195
|
+
+ options
|
196
|
+
- -dir --> project directory, both absolute path and realtive path will be okay. default is current directory.
|
197
|
+
- -e --> environment: `production`, `development`, etc.
|
198
|
+
- -f --> force mode, use `CADCASE` when removing view or table in redshift
|
199
|
+
- -ssh --> use ssh accessing to private database with ssh config in `config/redata.yml`
|
200
|
+
- -append_mode --> use `append_mode`, the objects in relations.rb with appending update type will go to appending operation.
|
201
|
+
+ delete will only delete objects with renewal update type
|
202
|
+
+ create will append-insert data after `-start_time`(set in command) or default `2 days ago` for appending update type, still create table/view for renewal type
|
203
|
+
+ checkout will only fetch data after `-start_time` or default `2 days ago` to upload to S3, renewal type will still be uploaded all data
|
204
|
+
+ inject will insert data to mysql without `--delete` option, renewal still delete all firstly
|
205
|
+
- other options --> some params will be used in query file when declared, such `start_time`
|
206
|
+
|
207
|
+
#### adjust
|
208
|
+
|
209
|
+
Use adjust when you just want to run a query file without declaring in `config/relations.rb`
|
210
|
+
Usage: `adjust [-options] [database] [query file] {platform}`
|
211
|
+
+ database --> `redshift` or database declared in `config/database.yml{export}`
|
212
|
+
+ query file --> query file which will be run in `database/adjust/`, **without extends `.sql`**
|
213
|
+
+ platform --> same to `redata`
|
214
|
+
+ options
|
215
|
+
- -dir --> project directory, both absolute path and realtive path will be okay. default is current directory.
|
216
|
+
- -e --> environment: `production`, `development`, etc.
|
217
|
+
- -ssh --> use ssh accessing to private database with ssh config in `config/redata.yml`
|
218
|
+
- other options --> some params will be used in query file when declared, such `start_time`
|
219
|
+
|
220
|
+
#### notice
|
221
|
+
|
222
|
+
Usage: `notice [-options] [action]`
|
223
|
+
+ action: currently, there is only `update` action which means send 'finish updating' message to slack
|
224
|
+
+ options
|
225
|
+
- -e --> environment: `production`, `development`, etc. **Only production could send notice**
|
226
|
+
|
227
|
+
## Contributing
|
228
|
+
|
229
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/goshan/redata.
|
230
|
+
|
231
|
+
|
232
|
+
## License
|
233
|
+
|
234
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
235
|
+
|
data/Rakefile
ADDED
data/bin/adjust
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require File.expand_path '../../lib/redata', __FILE__
|
4
|
+
|
5
|
+
|
6
|
+
query_file = Redata::RED.root.join 'database', 'adjust', "#{Redata::RED.params[1]}.sql"
|
7
|
+
tmp_script_file = Redata::RED.root.join 'tmp', 'queries', "adj_#{Redata::RED.params[0]}_#{Redata::RED.params[1]}.sql"
|
8
|
+
|
9
|
+
Redata::Log.action "QUERY: Run query file [#{query_file.relative_path_from Redata::RED.root}] in #{Redata::RED.params[0]}"
|
10
|
+
Redata::Parser.gen_adjust_file query_file, tmp_script_file
|
11
|
+
|
12
|
+
if Redata::RED.params[0] == "redshift"
|
13
|
+
Redata::DATABASE.connect_with_file tmp_script_file
|
14
|
+
else
|
15
|
+
Redata::DATABASE.connect_mysql_with_file tmp_script_file, Redata::RED.params[0], Redata::RED.params[2]
|
16
|
+
end
|
17
|
+
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "redata"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/notice
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'slack'
|
4
|
+
require File.expand_path '../../lib/redata', __FILE__
|
5
|
+
require File.expand_path '../../lib/redata/notice', __FILE__
|
6
|
+
|
7
|
+
|
8
|
+
|
9
|
+
if ['update'].include? Redata::RED.params[0]
|
10
|
+
notice = Redata::Notice.new
|
11
|
+
case Redata::RED.params[0]
|
12
|
+
when 'update'
|
13
|
+
if Redata::RED.production?
|
14
|
+
notice.send "今日の自動更新を完了しました!\n今のデータ期間は `2015-07-29 ~ #{Redata::RED.date_days_ago 3}` になってます"
|
15
|
+
else
|
16
|
+
Redata::Log.warning "WARNING: Could send notice only in production env"
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
data/bin/redata
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require File.expand_path '../../lib/redata', __FILE__
|
4
|
+
|
5
|
+
require Redata::RED.root.join('config', 'relations.rb').to_s
|
6
|
+
|
7
|
+
|
8
|
+
if ['create', 'delete', 'checkout', 'inject'].include? Redata::RED.params[0]
|
9
|
+
case Redata::RED.params[0]
|
10
|
+
when 'create'
|
11
|
+
Redata::Task.create_datasource Redata::RED.params[1]
|
12
|
+
when 'delete'
|
13
|
+
Redata::Task.delete_datasource Redata::RED.params[1]
|
14
|
+
when 'checkout'
|
15
|
+
Redata::Task.checkout_datasource Redata::RED.params[1]
|
16
|
+
when 'inject'
|
17
|
+
Redata::Task.inject Redata::RED.params[1], Redata::RED.params[2]
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
data/bin/setup
ADDED
data/lib/redata.rb
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
module Redata
|
2
|
+
class S3Bucket
|
3
|
+
def initialize
|
4
|
+
s3 = Aws::S3::Resource.new
|
5
|
+
@bucket = s3.bucket RED.s3['bucket']
|
6
|
+
end
|
7
|
+
|
8
|
+
def move(source, target)
|
9
|
+
from = @bucket.object source
|
10
|
+
to = @bucket.object target
|
11
|
+
from.move_to to if from.exists?
|
12
|
+
end
|
13
|
+
|
14
|
+
def exist?(file)
|
15
|
+
@bucket.object(file).exists?
|
16
|
+
end
|
17
|
+
|
18
|
+
def delete(file)
|
19
|
+
@bucket.object(file).delete if exist?(file)
|
20
|
+
end
|
21
|
+
|
22
|
+
def make_public(file, is_public)
|
23
|
+
acl = is_public ? 'public-read' : 'private'
|
24
|
+
@bucket.object(file).acl.put({:acl => acl}) if exist?(file)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
@@ -0,0 +1,108 @@
|
|
1
|
+
module Redata
|
2
|
+
class Config
|
3
|
+
attr_accessor :root, :env, :is_forced, :is_ssh, :is_append, :params, :locals
|
4
|
+
|
5
|
+
def initialize(argv=nil)
|
6
|
+
# params
|
7
|
+
@argv = parse_params argv
|
8
|
+
if !@argv[:dir]
|
9
|
+
@root = Pathname.new(Dir.pwd)
|
10
|
+
elsif Pathname.new(@argv[:dir]).absolute?
|
11
|
+
@root = Pathname.new(@argv[:dir])
|
12
|
+
else
|
13
|
+
@root = Pathname.new(Dir.pwd).join @argv[:dir]
|
14
|
+
end
|
15
|
+
@env = @argv[:env] || 'development'
|
16
|
+
@is_forced = @argv[:force]
|
17
|
+
@is_ssh = @argv[:ssh]
|
18
|
+
@is_append = @argv[:append_mode]
|
19
|
+
@locals = @argv[:locals]
|
20
|
+
@params = @argv[:params]
|
21
|
+
|
22
|
+
# config file
|
23
|
+
@config = YAML.load(ERB.new(File.read(@root.join 'config', 'redata.yml')).result(binding))
|
24
|
+
@s3_config = @config['s3']
|
25
|
+
@s3_config['bucket'] = @s3_config['bucket'][@env]
|
26
|
+
@s3_config['host'] = "https://s3-#{@s3_config['region']}.amazonaws.com/#{@s3_config['bucket']}"
|
27
|
+
Aws.config.update({
|
28
|
+
region: @s3_config['region'],
|
29
|
+
credentials: Aws::Credentials.new(@s3_config['aws_access_key_id'], @s3_config['aws_secret_access_key'])
|
30
|
+
})
|
31
|
+
@tz_local = Timezone[@config['timezone']]
|
32
|
+
@slack_token = @config['slack_bot']
|
33
|
+
end
|
34
|
+
|
35
|
+
def development?
|
36
|
+
@env == 'development'
|
37
|
+
end
|
38
|
+
|
39
|
+
def production?
|
40
|
+
@env == 'production'
|
41
|
+
end
|
42
|
+
|
43
|
+
def default_start_date
|
44
|
+
@config['start_date']
|
45
|
+
end
|
46
|
+
|
47
|
+
def ssh
|
48
|
+
@config['ssh']
|
49
|
+
end
|
50
|
+
|
51
|
+
def s3
|
52
|
+
@s3_config
|
53
|
+
end
|
54
|
+
|
55
|
+
def slack
|
56
|
+
@slack_token
|
57
|
+
end
|
58
|
+
|
59
|
+
def current_time
|
60
|
+
@tz_local.utc_to_local(Time.now.utc).strftime('%Y-%m-%d %H:%M:%S')
|
61
|
+
end
|
62
|
+
|
63
|
+
def default_append_date
|
64
|
+
# 2 days ago bacause there is only data 2 days ago in redshift
|
65
|
+
@tz_local.utc_to_local(Time.now.utc-2*24*3600).strftime('%Y-%m-%d')
|
66
|
+
end
|
67
|
+
|
68
|
+
def date_days_ago(days)
|
69
|
+
@tz_local.utc_to_local(Time.now.utc-days*24*3600).strftime('%Y-%m-%d')
|
70
|
+
end
|
71
|
+
|
72
|
+
private
|
73
|
+
def parse_params(argv)
|
74
|
+
new_argv = {:params => [], :locals => {}}
|
75
|
+
return new_argv unless argv
|
76
|
+
i = 0
|
77
|
+
while i < argv.count
|
78
|
+
case argv[i]
|
79
|
+
when '-dir'
|
80
|
+
i += 1
|
81
|
+
new_argv[:dir] = argv[i]
|
82
|
+
when '-e'
|
83
|
+
i += 1
|
84
|
+
new_argv[:env] = argv[i]
|
85
|
+
when '-f'
|
86
|
+
new_argv[:force] = true
|
87
|
+
when '-ssh'
|
88
|
+
new_argv[:ssh] = true
|
89
|
+
when '-append_mode'
|
90
|
+
new_argv[:append_mode] = true
|
91
|
+
else
|
92
|
+
if argv[i] =~ /-(.+)/
|
93
|
+
key = argv[i].match(/-(.+)/)[1]
|
94
|
+
i += 1
|
95
|
+
new_argv[:locals][key.to_sym] = argv[i]
|
96
|
+
else
|
97
|
+
new_argv[:params].push argv[i]
|
98
|
+
end
|
99
|
+
end
|
100
|
+
i += 1
|
101
|
+
end
|
102
|
+
new_argv
|
103
|
+
end
|
104
|
+
end
|
105
|
+
|
106
|
+
RED = Config.new ARGV
|
107
|
+
end
|
108
|
+
|
@@ -0,0 +1,92 @@
|
|
1
|
+
module Redata
|
2
|
+
class DataBase
|
3
|
+
REDSHIFT_PORT = 5439
|
4
|
+
|
5
|
+
def initialize
|
6
|
+
@config = YAML.load(ERB.new(File.read(RED.root.join 'config', 'database.yml')).result(binding))[RED.env]
|
7
|
+
Log.error! "ERROR: Database of #{RED.env} was not declared in config/database.yml" unless @config
|
8
|
+
|
9
|
+
@ssh = Ssh.new
|
10
|
+
end
|
11
|
+
|
12
|
+
def connect_with_file(file)
|
13
|
+
cmd = make_redshift_cmd
|
14
|
+
if @ssh.run_with_ssh?
|
15
|
+
@ssh.upload_file file
|
16
|
+
@ssh.run_command "export PGPASSWORD='#{ENV['PGPASSWORD']}';#{cmd} -f ~/tmp/#{file.basename}"
|
17
|
+
else
|
18
|
+
system "#{cmd} -f #{file}"
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
def connect_with_query(query)
|
23
|
+
cmd = make_redshift_cmd
|
24
|
+
if @ssh.run_with_ssh?
|
25
|
+
@ssh.run_command "export PGPASSWORD='#{ENV['PGPASSWORD']}';#{cmd} -c '#{query}'"
|
26
|
+
else
|
27
|
+
system "#{cmd} -c '#{query}'"
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
def inject_to_mysql(config, platform)
|
32
|
+
if @ssh.run_with_ssh?
|
33
|
+
@ssh.upload_file config.tmp_data_file, config.name
|
34
|
+
data_file = "~/tmp/#{config.name}"
|
35
|
+
else
|
36
|
+
data_file = config.tmp_data_file
|
37
|
+
end
|
38
|
+
|
39
|
+
is_append = RED.is_append && config.update_type == :append
|
40
|
+
cmd = "mysqlimport #{make_mysql_cmd_config(config.category.to_s, platform)} #{data_file} --local #{is_append ? '' : '--delete'} --fields-terminated-by='\\t' --fields-enclosed-by='\\\"' --lines-terminated-by='\\n'"
|
41
|
+
|
42
|
+
if @ssh.run_with_ssh?
|
43
|
+
@ssh.run_command cmd
|
44
|
+
else
|
45
|
+
system "#{cmd}"
|
46
|
+
end
|
47
|
+
|
48
|
+
end
|
49
|
+
|
50
|
+
def connect_mysql_with_file(query_file, category, platform)
|
51
|
+
if @ssh.run_with_ssh?
|
52
|
+
@ssh.upload_file query_file, query_file.basename
|
53
|
+
data_file = "~/tmp/#{query_file.basename}"
|
54
|
+
else
|
55
|
+
data_file = query_file
|
56
|
+
end
|
57
|
+
|
58
|
+
cmd = "mysql #{make_mysql_cmd_config(category, platform)} < #{data_file}"
|
59
|
+
|
60
|
+
if @ssh.run_with_ssh?
|
61
|
+
@ssh.run_command cmd
|
62
|
+
else
|
63
|
+
system cmd
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
private
|
68
|
+
def make_redshift_cmd
|
69
|
+
ENV['PGPASSWORD'] = @config['password']
|
70
|
+
return "psql -h #{@config['host']} -p #{REDSHIFT_PORT} -U #{@config['username']} -d #{@config['database']}"
|
71
|
+
end
|
72
|
+
|
73
|
+
def make_mysql_cmd_config(category, platform)
|
74
|
+
export_db_config = @config['export'][category]
|
75
|
+
Log.error! "ERROR: Export config of #{category} was not found in config/database.yml" unless export_db_config
|
76
|
+
if platform
|
77
|
+
if export_db_config[platform]
|
78
|
+
export_db_config = export_db_config[platform]
|
79
|
+
else
|
80
|
+
Log.warning "WARNING: Platform #{platform} was not declared in config/database.yml, ignore platform setting"
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
84
|
+
return "-h#{export_db_config['host']} -u#{export_db_config['username']} #{export_db_config['password'].empty? ? '' : '-p'+export_db_config['password']} #{export_db_config['database']}"
|
85
|
+
end
|
86
|
+
|
87
|
+
end
|
88
|
+
|
89
|
+
DATABASE = DataBase.new
|
90
|
+
end
|
91
|
+
|
92
|
+
|
data/lib/redata/log.rb
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
module Redata
|
2
|
+
class Log
|
3
|
+
def self.error!(msg)
|
4
|
+
puts "[#{RED.current_time}] #{msg.red}"
|
5
|
+
exit 1
|
6
|
+
end
|
7
|
+
|
8
|
+
def self.warning(msg)
|
9
|
+
puts "[#{RED.current_time}] #{msg.yellow}"
|
10
|
+
end
|
11
|
+
|
12
|
+
def self.action(msg)
|
13
|
+
puts "[#{RED.current_time}] #{msg.cyan}"
|
14
|
+
end
|
15
|
+
|
16
|
+
def self.log(msg)
|
17
|
+
puts "[#{RED.current_time}] #{msg}"
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
module Redata
|
2
|
+
class Notice
|
3
|
+
def initialize
|
4
|
+
Log.error! "ERROR: slack bot token missing" if !RED.slack['token'] || RED.slack['token'].empty?
|
5
|
+
@slack = Slack::Client.new :token => RED.slack['token']
|
6
|
+
channel_exist = false
|
7
|
+
@slack.channels_list['channels'].each do |channel|
|
8
|
+
channel_exist = true if channel['name'] == RED.slack['channel']
|
9
|
+
end
|
10
|
+
Log.error! "ERROR: slack channel #{RED.slack['channel']} not exists" unless channel_exist
|
11
|
+
end
|
12
|
+
|
13
|
+
def send(msg)
|
14
|
+
@slack.chat_postMessage({
|
15
|
+
:channel => RED.slack['channel'],
|
16
|
+
:text => "<!here> #{msg}",
|
17
|
+
:as_user => true
|
18
|
+
})
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
@@ -0,0 +1,147 @@
|
|
1
|
+
module Redata
|
2
|
+
class Parser
|
3
|
+
INCLUDE_REGEX = /#include (.*)-->(.*)/
|
4
|
+
REF_REGEX = /{([^{}]+)}/
|
5
|
+
REF_SPLIT_REGEX = /\s*{[^{}]+}\s*/
|
6
|
+
START_TIME_REGEX = /\[start_time\]/
|
7
|
+
TIME_OFFSET_REGEX = /\[(\d+) days ago\]/
|
8
|
+
CURRENT_TIME_REGEX = /\[current_time\]/
|
9
|
+
LOCALS_REGEX = /\[([^\[\]]+)\]/
|
10
|
+
|
11
|
+
CONV_TABLE_REGEX = /source:(.*)/
|
12
|
+
CONV_COLUMN_REGEX = /columns:\s*/
|
13
|
+
CONV_SWITCHDEF_REGEX = /(.+){(.*)}/
|
14
|
+
CONV_SWITCH_REGEX = /([^,]+)=>([^,]+)/
|
15
|
+
CONV_TIMESTAMP_REGEX = /\[time_stamp\]/
|
16
|
+
|
17
|
+
def self.gen_redshift_query(config, start_time=nil)
|
18
|
+
Log.error! "ERROR: Query file '#{config.query_file.relative_path_from RED.root}' not exists" unless config.query_file.exist?
|
19
|
+
|
20
|
+
File.open config.tmp_script_file, 'w' do |f|
|
21
|
+
if start_time && config.type == :table
|
22
|
+
f.puts "INSERT INTO #{config.source_name} ("
|
23
|
+
else
|
24
|
+
start_time = RED.default_start_date
|
25
|
+
f.puts "CREATE #{config.type} #{config.source_name} AS ("
|
26
|
+
end
|
27
|
+
self.parse_redshift_file config.query_file, f, start_time
|
28
|
+
f.puts ");"
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
def self.gen_export_query(config, start_time=nil)
|
33
|
+
Log.error! "ERROR: Convertor config '#{config.conv_file.relative_path_from RED.root}' not exists" unless config.conv_file.exist?
|
34
|
+
|
35
|
+
File.open config.tmp_script_file, 'w' do |f|
|
36
|
+
f.puts "UNLOAD ('"
|
37
|
+
f.puts self.parse_convertor_file config.conv_file
|
38
|
+
f.puts "where date >= \\'#{start_time}\\'" if start_time
|
39
|
+
f.puts "') to 's3://#{RED.s3['bucket']}/#{config.bucket_file}'"
|
40
|
+
f.puts "CREDENTIALS 'aws_access_key_id=#{RED.s3['aws_access_key_id']};aws_secret_access_key=#{RED.s3['aws_secret_access_key']}'"
|
41
|
+
f.puts "ESCAPE ALLOWOVERWRITE PARALLEL OFF DELIMITER AS '\\t';"
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
def self.gen_adjust_file(query_file, tmp_script_file)
|
46
|
+
Log.error! "ERROR: Query file '#{query_file.relative_path_from RED.root}' not exists" unless query_file.exist?
|
47
|
+
|
48
|
+
File.open tmp_script_file, 'w' do |f|
|
49
|
+
self.parse_redshift_file query_file, f, RED.default_start_date
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
|
54
|
+
private
|
55
|
+
def self.parse_redshift_file(in_file, out, start_time)
|
56
|
+
links = {}
|
57
|
+
File.open(in_file).each.with_index do |line, index|
|
58
|
+
if line =~ INCLUDE_REGEX
|
59
|
+
# parse include syntax
|
60
|
+
res = line.scan(INCLUDE_REGEX).first
|
61
|
+
sub = res[0].gsub /[\s|\'|\"]+/, ''
|
62
|
+
link = res[1].gsub /[\s|:]+/, ''
|
63
|
+
Log.error! "QUERY ERROR: #{in_file.relative_path_from RED.root}:#{index+1}: include query is missing file or alias" if sub.empty? || link.empty?
|
64
|
+
|
65
|
+
sub_file = in_file.parent.join "_#{sub}.sql"
|
66
|
+
sub_file = RED.root.join 'database', 'shared', "_#{sub}.sql" unless sub_file.exist?
|
67
|
+
Log.error! "QUERY ERROR: #{in_file.relative_path_from RED.root}:#{index+1}: included file _#{sub}.sql could not be found in ./ or {root}/database/shared/" unless sub_file.exist?
|
68
|
+
|
69
|
+
Log.error! "QUERY ERROR: #{in_file.relative_path_from RED.root}:#{index+1}: alias #{link} was declared multiple times" if links[link]
|
70
|
+
|
71
|
+
links[link] = sub_file
|
72
|
+
elsif line =~ REF_REGEX
|
73
|
+
# parse {ref} syntax
|
74
|
+
res = line.scan REF_REGEX
|
75
|
+
refs = res.map{|r| r.first.gsub /\s+/, ''}
|
76
|
+
origins = line.split REF_SPLIT_REGEX
|
77
|
+
|
78
|
+
out.puts origins[0].gsub(';', '')
|
79
|
+
refs.each_with_index do |ref, i|
|
80
|
+
Log.error! "QUERY ERROR: #{in_file}:#{index+1}:\nsub query #{ref} not found." unless links[ref]
|
81
|
+
out.puts "("
|
82
|
+
self.parse_redshift_file links[ref], out, start_time
|
83
|
+
out.puts ") as #{ref}"
|
84
|
+
out.puts origins[i+1].gsub(';', '') if origins[i+1]
|
85
|
+
end
|
86
|
+
elsif line =~ START_TIME_REGEX
|
87
|
+
# parse [start_time] syntax
|
88
|
+
out.puts line.gsub(START_TIME_REGEX, "'#{start_time}'").gsub(';', '')
|
89
|
+
elsif line =~ TIME_OFFSET_REGEX
|
90
|
+
# parse [3 days ago]
|
91
|
+
res = line.scan(TIME_OFFSET_REGEX).each do |res|
|
92
|
+
line = line.gsub "[#{res[0]} days ago]", "#{RED.date_days_ago(res[0].to_i)}"
|
93
|
+
end
|
94
|
+
out.puts line
|
95
|
+
elsif line =~ CURRENT_TIME_REGEX
|
96
|
+
line = line.gsub "[current_time]", "#{RED.current_time}"
|
97
|
+
out.puts line
|
98
|
+
elsif line =~ LOCALS_REGEX
|
99
|
+
# parse [locals] syntax
|
100
|
+
line.scan(LOCALS_REGEX).each do |res|
|
101
|
+
key = res.first
|
102
|
+
Log.error! "QUERY ERROR: Local params #{key} was missing." unless RED.locals[key.to_sym]
|
103
|
+
line = line.gsub "[#{key}]", "'#{RED.locals[key.to_sym]}'"
|
104
|
+
end
|
105
|
+
out.puts line.gsub ';', ''
|
106
|
+
else
|
107
|
+
# other, print absolutely
|
108
|
+
out.puts line.gsub ';', ''
|
109
|
+
end
|
110
|
+
end
|
111
|
+
end
|
112
|
+
|
113
|
+
def self.parse_convertor_file(in_file)
|
114
|
+
is_parsing_column = false
|
115
|
+
columns = []
|
116
|
+
source = ""
|
117
|
+
File.open(in_file).each.with_index do |line, index|
|
118
|
+
if line =~ CONV_TABLE_REGEX
|
119
|
+
# parse table declare
|
120
|
+
res = line.scan(CONV_TABLE_REGEX).first
|
121
|
+
source = res[0].gsub /\s+/, ''
|
122
|
+
is_parsing_column = false
|
123
|
+
elsif line =~ CONV_COLUMN_REGEX
|
124
|
+
is_parsing_column = true
|
125
|
+
elsif is_parsing_column
|
126
|
+
line.gsub! /\s+/, ''
|
127
|
+
if line =~ CONV_SWITCHDEF_REGEX
|
128
|
+
res = line.scan(CONV_SWITCHDEF_REGEX).first
|
129
|
+
res[1].gsub!("'", "\\\\'")
|
130
|
+
switches = res[1].scan CONV_SWITCH_REGEX
|
131
|
+
switches.map! do |m|
|
132
|
+
"when #{m[0]} then #{m[1]}"
|
133
|
+
end
|
134
|
+
columns.push "case #{res[0]} #{switches.join ' '} end as #{res[0]}"
|
135
|
+
elsif line =~ CONV_TIMESTAMP_REGEX
|
136
|
+
columns.push "\\'#{(Time.now+9*3600).strftime("%Y-%m-%d %H:%M:%S")}\\'"
|
137
|
+
columns.push "\\'#{(Time.now+9*3600).strftime("%Y-%m-%d %H:%M:%S")}\\'"
|
138
|
+
else
|
139
|
+
columns.push line.gsub("'", "\\\\'").gsub('NULL', "\\\\'NULL\\\\'") unless line.empty?
|
140
|
+
end
|
141
|
+
end
|
142
|
+
end
|
143
|
+
"select #{columns.join ','} from #{source}"
|
144
|
+
end
|
145
|
+
|
146
|
+
end
|
147
|
+
end
|
@@ -0,0 +1,17 @@
|
|
1
|
+
module Redata
|
2
|
+
class Relation
|
3
|
+
attr_accessor :category, :name, :key, :file, :dir, :type, :update_type
|
4
|
+
def initialize(category, name, setting)
|
5
|
+
@category = category
|
6
|
+
@name = name
|
7
|
+
@key = setting[:as] || @name.to_sym
|
8
|
+
@file = setting[:file] || @name
|
9
|
+
@dir = setting[:dir] || (@category == :main ? nil : @category.to_s)
|
10
|
+
end
|
11
|
+
|
12
|
+
def global_key
|
13
|
+
@category == :main ? @key : "#{@category}_#{@key}".to_sym
|
14
|
+
end
|
15
|
+
|
16
|
+
end
|
17
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
module Redata
|
2
|
+
class Export < Relation
|
3
|
+
def initialize(category, name, setting)
|
4
|
+
super category, name, setting
|
5
|
+
@type = :export
|
6
|
+
@update_type = setting[:update] || :renewal
|
7
|
+
end
|
8
|
+
|
9
|
+
def conv_file
|
10
|
+
conv_file = RED.root.join 'database', 'convertors'
|
11
|
+
conv_file = conv_file.join @dir if @dir
|
12
|
+
conv_file = conv_file.join "#{@file}.conv"
|
13
|
+
conv_file
|
14
|
+
end
|
15
|
+
|
16
|
+
def tmp_script_file
|
17
|
+
RED.root.join 'tmp', "queries", "red#{@type}_#{@category}_#{@name}.sql"
|
18
|
+
end
|
19
|
+
|
20
|
+
def tmp_data_file
|
21
|
+
RED.root.join 'tmp', "data", "#{@name}.tsv"
|
22
|
+
end
|
23
|
+
|
24
|
+
def bucket_file
|
25
|
+
bucket_dir = RED.default_append_date
|
26
|
+
bucket_dir = RED.locals[:start_time] if RED.is_append && @update_type == :append && RED.locals[:start_time]
|
27
|
+
"#{bucket_dir}/#{@category}/#{@name}.tsv"
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
module Redata
|
2
|
+
class Table < Relation
|
3
|
+
def initialize(category, name, setting)
|
4
|
+
super category, name, setting
|
5
|
+
@type = :table
|
6
|
+
@update_type = setting[:update] || :renewal
|
7
|
+
end
|
8
|
+
|
9
|
+
def source_name
|
10
|
+
@category == :main ? @name : "#{@category}_#{@name}"
|
11
|
+
end
|
12
|
+
|
13
|
+
def query_file
|
14
|
+
query_file = RED.root.join 'database', 'sources'
|
15
|
+
query_file = query_file.join @dir if @dir
|
16
|
+
query_file = query_file.join "#{@file}.sql"
|
17
|
+
query_file
|
18
|
+
end
|
19
|
+
|
20
|
+
def tmp_script_file
|
21
|
+
RED.root.join 'tmp', "queries", "red#{@type}_#{@category}_#{@name}.sql"
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
module Redata
|
2
|
+
class View < Relation
|
3
|
+
def initialize(category, name, setting)
|
4
|
+
super category, name, setting
|
5
|
+
@type = :view
|
6
|
+
@update_type = :renewal
|
7
|
+
end
|
8
|
+
|
9
|
+
def source_name
|
10
|
+
@category == :main ? @name : "#{@category}_#{@name}"
|
11
|
+
end
|
12
|
+
|
13
|
+
def query_file
|
14
|
+
query_file = RED.root.join 'database', 'sources'
|
15
|
+
query_file = query_file.join @dir if @dir
|
16
|
+
query_file = query_file.join "#{@file}.sql"
|
17
|
+
query_file
|
18
|
+
end
|
19
|
+
|
20
|
+
def tmp_script_file
|
21
|
+
RED.root.join 'tmp', "queries", "red#{@type}_#{@category}_#{@name}.sql"
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# ruby default lib
|
2
|
+
require 'pathname'
|
3
|
+
require 'yaml'
|
4
|
+
require 'erb'
|
5
|
+
|
6
|
+
# gem lib
|
7
|
+
require 'json'
|
8
|
+
require 'colorize'
|
9
|
+
require 'aws-sdk'
|
10
|
+
require 'timezone'
|
11
|
+
|
12
|
+
# local lib
|
13
|
+
require 'redata/config'
|
14
|
+
require 'redata/log'
|
15
|
+
require 'redata/ssh'
|
16
|
+
require 'redata/database'
|
17
|
+
require 'redata/bucket'
|
18
|
+
require 'redata/relation'
|
19
|
+
require 'redata/relation/table'
|
20
|
+
require 'redata/relation/view'
|
21
|
+
require 'redata/relation/export'
|
22
|
+
require 'redata/schema'
|
23
|
+
require 'redata/parser'
|
24
|
+
require 'redata/tasks'
|
@@ -0,0 +1,64 @@
|
|
1
|
+
module Redata
|
2
|
+
class Schema
|
3
|
+
def initialize
|
4
|
+
@category = :main
|
5
|
+
@order = []
|
6
|
+
@index = {}
|
7
|
+
end
|
8
|
+
|
9
|
+
def config(&block)
|
10
|
+
self.instance_eval &block
|
11
|
+
end
|
12
|
+
|
13
|
+
def category(prefix, &block)
|
14
|
+
@category = prefix
|
15
|
+
self.instance_eval &block
|
16
|
+
@category = :main
|
17
|
+
end
|
18
|
+
|
19
|
+
def view(view, setting={})
|
20
|
+
register view, :view, setting
|
21
|
+
end
|
22
|
+
|
23
|
+
def table(table, setting={})
|
24
|
+
register table, :table, setting
|
25
|
+
end
|
26
|
+
|
27
|
+
def export(target, setting={})
|
28
|
+
register target, :export, setting
|
29
|
+
end
|
30
|
+
|
31
|
+
def insert(target, setting={})
|
32
|
+
register target, :insert, setting
|
33
|
+
end
|
34
|
+
|
35
|
+
def config_with(key)
|
36
|
+
config = @index[key]
|
37
|
+
return nil unless config
|
38
|
+
config
|
39
|
+
end
|
40
|
+
|
41
|
+
def category_configs(category, types=[])
|
42
|
+
res = []
|
43
|
+
@order.each do |global_key|
|
44
|
+
config = @index[global_key]
|
45
|
+
res.push config if (!category || config.category == category) && (types.empty? || types.include?(config.type))
|
46
|
+
end
|
47
|
+
res
|
48
|
+
end
|
49
|
+
|
50
|
+
private
|
51
|
+
def register(name, type, setting={})
|
52
|
+
cla = Redata.const_get type.capitalize
|
53
|
+
relation = cla.new @category, name, setting
|
54
|
+
|
55
|
+
if @index[relation.global_key]
|
56
|
+
Log.log "in #{caller.first}"
|
57
|
+
Log.error! "ERROR: Duplicated view alias '#{global_key}'"
|
58
|
+
end
|
59
|
+
|
60
|
+
@index[relation.global_key] = relation
|
61
|
+
@order.push relation.global_key
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
data/lib/redata/ssh.rb
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
module Redata
|
2
|
+
class Ssh
|
3
|
+
def initialize
|
4
|
+
@ssh = RED.ssh
|
5
|
+
end
|
6
|
+
|
7
|
+
def run_with_ssh?
|
8
|
+
if RED.is_ssh && @ssh && !RED.production?
|
9
|
+
Log.warning "WARNING: Using gateway server #{@ssh['HostName']}"
|
10
|
+
return true
|
11
|
+
end
|
12
|
+
|
13
|
+
if RED.is_ssh
|
14
|
+
Log.warning "WARNING: SSH config file was not found. Ignore this config." unless @ssh
|
15
|
+
Log.warning "WARNING: Could not use ssh mode in production. Ignore this config." if RED.production?
|
16
|
+
end
|
17
|
+
return false
|
18
|
+
end
|
19
|
+
|
20
|
+
def upload_file(file, target_file=nil)
|
21
|
+
system "scp -i #{@ssh['IdentityFile']} #{file} #{@ssh['User']}@#{@ssh['HostName']}:~/tmp/#{target_file}"
|
22
|
+
end
|
23
|
+
|
24
|
+
def run_command(cmd)
|
25
|
+
system "ssh -i #{@ssh['IdentityFile']} #{@ssh['User']}@#{@ssh['HostName']} \"#{cmd}\""
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
data/lib/redata/tasks.rb
ADDED
@@ -0,0 +1,84 @@
|
|
1
|
+
module Redata
|
2
|
+
class Task
|
3
|
+
@@schema = Schema.new
|
4
|
+
|
5
|
+
def self.schema
|
6
|
+
@@schema
|
7
|
+
end
|
8
|
+
|
9
|
+
def self.create_datasource(key)
|
10
|
+
self.parse_key(key, [:table, :view]).each do |config|
|
11
|
+
if RED.is_append && config.update_type == :append
|
12
|
+
start_time = RED.locals[:start_time] || RED.default_append_date
|
13
|
+
Parser.gen_redshift_query config, start_time
|
14
|
+
Log.action "QUERY: Append data after #{start_time} into [#{config.source_name}]"
|
15
|
+
DATABASE.connect_with_file config.tmp_script_file
|
16
|
+
else
|
17
|
+
Parser.gen_redshift_query config
|
18
|
+
Log.action "QUERY: Create #{config.type} [#{config.source_name}]"
|
19
|
+
DATABASE.connect_with_file config.tmp_script_file
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
def self.delete_datasource(key)
|
25
|
+
self.parse_key(key, [:table, :view]).reverse.each do |config|
|
26
|
+
unless RED.is_append && config.update_type == :append
|
27
|
+
Log.action "QUERY: Drop #{config.type} [#{config.source_name}]"
|
28
|
+
Log.warning "WARNING: CASCADE mode will also drop other sources that depend on this #{config.type}" if RED.is_forced
|
29
|
+
DATABASE.connect_with_query "DROP #{config.type} #{config.source_name} #{RED.is_forced ? 'CASCADE' : 'RESTRICT'}"
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
def self.checkout_datasource(key)
|
35
|
+
self.parse_key(key, [:export]).each do |config|
|
36
|
+
if RED.is_append && config.update_type == :append
|
37
|
+
start_time = RED.locals[:start_time] || RED.default_append_date
|
38
|
+
Parser.gen_export_query config, start_time
|
39
|
+
Log.action "QUERY: Checkout data after #{start_time} to bucket [#{config.bucket_file}]"
|
40
|
+
else
|
41
|
+
Parser.gen_export_query config
|
42
|
+
Log.action "QUERY: Checkout data to bucket [#{config.bucket_file}]"
|
43
|
+
end
|
44
|
+
DATABASE.connect_with_file config.tmp_script_file
|
45
|
+
bucket = S3Bucket.new
|
46
|
+
bucket.move "#{config.bucket_file}000", config.bucket_file
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
def self.inject(key, platform=nil)
|
51
|
+
self.parse_key(key, [:export]).each do |config|
|
52
|
+
Log.action "BUCKET: Make [#{config.bucket_file}] public"
|
53
|
+
bucket = S3Bucket.new
|
54
|
+
bucket.make_public config.bucket_file, true
|
55
|
+
|
56
|
+
Log.action "DOWNLOAD: Downlaod [#{config.bucket_file}] from bucket"
|
57
|
+
system "wget #{RED.s3['host']}/#{config.bucket_file} -O #{config.tmp_data_file} --quiet"
|
58
|
+
|
59
|
+
Log.action "BUCKET: Make [#{config.bucket_file}] private"
|
60
|
+
bucket.make_public config.bucket_file, false
|
61
|
+
|
62
|
+
Log.action "QUERY: Inject data to [#{config.name}] of #{config.category}"
|
63
|
+
DATABASE.inject_to_mysql config, platform
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
|
68
|
+
private
|
69
|
+
def self.parse_key(key, types)
|
70
|
+
key = key.to_sym if key
|
71
|
+
configs = []
|
72
|
+
|
73
|
+
configs = @@schema.category_configs(key, types)
|
74
|
+
if configs.empty?
|
75
|
+
config = @@schema.config_with key if key
|
76
|
+
Log.error! "ERROR: Data source relation #{key} was not defined in config/relations.rb" unless config
|
77
|
+
configs.push config
|
78
|
+
end
|
79
|
+
configs
|
80
|
+
end
|
81
|
+
|
82
|
+
end
|
83
|
+
end
|
84
|
+
|
data/redata.gemspec
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'redata/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "redata"
|
8
|
+
spec.version = Redata::VERSION
|
9
|
+
spec.authors = ["goshan"]
|
10
|
+
spec.email = ["goshan.hanqiu@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{a AWS Redshift data process controller}
|
13
|
+
spec.description = %q{Controll data process by sub query and easy command line}
|
14
|
+
spec.homepage = "https://github.com/goshan/redata"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
18
|
+
spec.executables = ["redata", "adjust", "notice"]
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.12"
|
22
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
23
|
+
|
24
|
+
spec.add_runtime_dependency "json", "~> 2.0"
|
25
|
+
spec.add_runtime_dependency "colorize", "~> 0.8"
|
26
|
+
spec.add_runtime_dependency "aws-sdk", "~> 2.6"
|
27
|
+
spec.add_runtime_dependency "timezone", "~> 1.2"
|
28
|
+
spec.add_runtime_dependency "slack-api", "~> 1.2"
|
29
|
+
end
|
metadata
ADDED
@@ -0,0 +1,172 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: redata
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- goshan
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-12-09 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.12'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.12'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: json
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '2.0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '2.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: colorize
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0.8'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0.8'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: aws-sdk
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '2.6'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '2.6'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: timezone
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '1.2'
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '1.2'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: slack-api
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '1.2'
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '1.2'
|
111
|
+
description: Controll data process by sub query and easy command line
|
112
|
+
email:
|
113
|
+
- goshan.hanqiu@gmail.com
|
114
|
+
executables:
|
115
|
+
- redata
|
116
|
+
- adjust
|
117
|
+
- notice
|
118
|
+
extensions: []
|
119
|
+
extra_rdoc_files: []
|
120
|
+
files:
|
121
|
+
- ".gitignore"
|
122
|
+
- Gemfile
|
123
|
+
- LICENSE.txt
|
124
|
+
- README.md
|
125
|
+
- Rakefile
|
126
|
+
- bin/adjust
|
127
|
+
- bin/console
|
128
|
+
- bin/notice
|
129
|
+
- bin/redata
|
130
|
+
- bin/setup
|
131
|
+
- lib/redata.rb
|
132
|
+
- lib/redata/bucket.rb
|
133
|
+
- lib/redata/config.rb
|
134
|
+
- lib/redata/database.rb
|
135
|
+
- lib/redata/log.rb
|
136
|
+
- lib/redata/notice.rb
|
137
|
+
- lib/redata/parser.rb
|
138
|
+
- lib/redata/relation.rb
|
139
|
+
- lib/redata/relation/export.rb
|
140
|
+
- lib/redata/relation/table.rb
|
141
|
+
- lib/redata/relation/view.rb
|
142
|
+
- lib/redata/requires.rb
|
143
|
+
- lib/redata/schema.rb
|
144
|
+
- lib/redata/ssh.rb
|
145
|
+
- lib/redata/tasks.rb
|
146
|
+
- lib/redata/version.rb
|
147
|
+
- redata.gemspec
|
148
|
+
homepage: https://github.com/goshan/redata
|
149
|
+
licenses:
|
150
|
+
- MIT
|
151
|
+
metadata: {}
|
152
|
+
post_install_message:
|
153
|
+
rdoc_options: []
|
154
|
+
require_paths:
|
155
|
+
- lib
|
156
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
157
|
+
requirements:
|
158
|
+
- - ">="
|
159
|
+
- !ruby/object:Gem::Version
|
160
|
+
version: '0'
|
161
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
162
|
+
requirements:
|
163
|
+
- - ">="
|
164
|
+
- !ruby/object:Gem::Version
|
165
|
+
version: '0'
|
166
|
+
requirements: []
|
167
|
+
rubyforge_project:
|
168
|
+
rubygems_version: 2.4.5
|
169
|
+
signing_key:
|
170
|
+
specification_version: 4
|
171
|
+
summary: a AWS Redshift data process controller
|
172
|
+
test_files: []
|