dataduck 1.1.0 → 1.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/docs/tables/README.md +39 -1
- data/lib/dataduck/commands.rb +4 -1
- data/lib/dataduck/redshift_destination.rb +2 -1
- data/lib/dataduck/table.rb +4 -0
- data/lib/dataduck/version.rb +1 -1
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: a48e9e513313a27d24f94c23e4f2659ebecf1c1d
|
4
|
+
data.tar.gz: a89623ebfe52f3dd24bb239aea5e366aeed0e99f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 07c9acd3135428eda030cf6fe7270ee0e827448f6227761627c2ef546cc861faef4dd0151a446aa91b2ba5267e1014d45dac5c2b27daae5e58d09d0116b63a0c
|
7
|
+
data.tar.gz: 468134eb9bdffbc2996c9a7060449bca8625d5a8597a2dc81ed0ea04c3d1aa26cb7932580f33ea1da440d645534fa54c4a0f4d30720cb75f7ad006fbacc6ac89
|
data/docs/tables/README.md
CHANGED
@@ -45,9 +45,47 @@ and leave the rest of the process (and the Redshift loading) up to DataDuck.
|
|
45
45
|
## The `extract!` method
|
46
46
|
|
47
47
|
The `extract!` method takes one argument: the destination. It then extracts the data from the source necessary to load
|
48
|
-
data into the destination. If you are writing your own Table class with some custom third party API, you will probably
|
48
|
+
data into the destination. If you are writing your own Table class with some custom third party API, you will probably
|
49
49
|
want to overwrite this method.
|
50
50
|
|
51
|
+
## Overriding indexes (sortkeys)
|
52
|
+
|
53
|
+
By sortkey, Redshift means what other databases would generally call indexes. DataDuck ETL will use `id` and `created_at` as sortkeys by default. If you would like to specify your own, simply overwrite the `indexes` method on your table, like this example:
|
54
|
+
|
55
|
+
```ruby
|
56
|
+
class Decks < DataDuck::Table
|
57
|
+
# source info goes here
|
58
|
+
|
59
|
+
def indexes
|
60
|
+
["id", "user_id"]
|
61
|
+
end
|
62
|
+
|
63
|
+
# output info goes here
|
64
|
+
end
|
65
|
+
```
|
66
|
+
|
67
|
+
## Overriding distkeys and diststyles
|
68
|
+
|
69
|
+
For large datasets, Redshift can distribute the data across multiple compute nodes according to your distkey and diststyle. To use these, simply overwrite the distribution_key and distribution_style methods.
|
70
|
+
|
71
|
+
```ruby
|
72
|
+
class Decks < DataDuck::Table
|
73
|
+
# source info goes here
|
74
|
+
|
75
|
+
def distribution_key
|
76
|
+
"company_id"
|
77
|
+
end
|
78
|
+
|
79
|
+
def distribution_style
|
80
|
+
"all"
|
81
|
+
end
|
82
|
+
|
83
|
+
# output info goes here
|
84
|
+
end
|
85
|
+
```
|
86
|
+
|
87
|
+
For more info, read: [http://docs.aws.amazon.com/redshift/latest/dg/t_Distributing_data.html](Distributing Data)
|
88
|
+
|
51
89
|
## Example Table
|
52
90
|
|
53
91
|
The following is an example table.
|
data/lib/dataduck/commands.rb
CHANGED
@@ -240,7 +240,10 @@ module DataDuck
|
|
240
240
|
puts "Connection successful. Detected #{ table_names.length } tables."
|
241
241
|
puts "Creating scaffolding..."
|
242
242
|
table_names.each do |table_name|
|
243
|
-
|
243
|
+
begin
|
244
|
+
DataDuck::Commands.quickstart_create_table(table_name, db_source)
|
245
|
+
rescue
|
246
|
+
end
|
244
247
|
end
|
245
248
|
|
246
249
|
config_obj = {
|
@@ -72,9 +72,10 @@ module DataDuck
|
|
72
72
|
props_string = props_array.join(', ')
|
73
73
|
|
74
74
|
distribution_clause = table.distribution_key ? "DISTKEY(#{ table.distribution_key })" : ""
|
75
|
+
distribution_style_clause = table.distribution_style ? "DISTSTYLE #{ distribution_style }" : ""
|
75
76
|
index_clause = table.indexes.length > 0 ? "INTERLEAVED SORTKEY (#{ table.indexes.join(',') })" : ""
|
76
77
|
|
77
|
-
"CREATE TABLE IF NOT EXISTS #{ table_name } (#{ props_string }) #{ distribution_clause } #{ index_clause }"
|
78
|
+
"CREATE TABLE IF NOT EXISTS #{ table_name } (#{ props_string }) #{ distribution_clause } #{ distribution_style_clause } #{ index_clause }"
|
78
79
|
end
|
79
80
|
|
80
81
|
def create_output_tables!(table)
|
data/lib/dataduck/table.rb
CHANGED
data/lib/dataduck/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: dataduck
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jeff Pickhardt
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2017-03-14 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -295,7 +295,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
295
295
|
version: '0'
|
296
296
|
requirements: []
|
297
297
|
rubyforge_project:
|
298
|
-
rubygems_version: 2.
|
298
|
+
rubygems_version: 2.6.8
|
299
299
|
signing_key:
|
300
300
|
specification_version: 4
|
301
301
|
summary: A straightforward, effective ETL framework.
|