dataduck 1.1.0 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4c85a45aea48dc00fdef79467a5148e71a32c691
-  data.tar.gz: 3c6a10310fcde7ca07efee6ed127d5339174b3dd
+  metadata.gz: a48e9e513313a27d24f94c23e4f2659ebecf1c1d
+  data.tar.gz: a89623ebfe52f3dd24bb239aea5e366aeed0e99f
 SHA512:
-  metadata.gz: 14b0a7a521cf17446418dbf7536bbf60cebe32e38e2eae34464b96980d1e6318aa5f21be430cda827098771c63dd607f1b7b3fc21f1b27f2590e9bfe3ea2bd7b
-  data.tar.gz: fd14a28b61f6e75c4f5af591c39ec72b20abcfaf659de7ef0e63cf80c943f42f02567e61a1c2757e368e6ba322a90c2279f057d070ab68d93d9d0605551499ad
+  metadata.gz: 07c9acd3135428eda030cf6fe7270ee0e827448f6227761627c2ef546cc861faef4dd0151a446aa91b2ba5267e1014d45dac5c2b27daae5e58d09d0116b63a0c
+  data.tar.gz: 468134eb9bdffbc2996c9a7060449bca8625d5a8597a2dc81ed0ea04c3d1aa26cb7932580f33ea1da440d645534fa54c4a0f4d30720cb75f7ad006fbacc6ac89

data/docs/tables/README.md

@@ -45,9 +45,47 @@ and leave the rest of the process (and the Redshift loading) up to DataDuck.
 ## The `extract!` method
 
 The `extract!` method takes one argument: the destination. It then extracts the data from the source necessary to load
-data into the destination. If you are writing your own Table class with some custom third party API, you will probably 
+data into the destination. If you are writing your own Table class with some custom third party API, you will probably
 want to overwrite this method.
 
+## Overriding indexes (sortkeys)
+
+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:
+
+```ruby
+class Decks < DataDuck::Table
+  # source info goes here
+
+  def indexes
+    ["id", "user_id"]
+  end
+
+  # output info goes here
+end
+```
+
+## Overriding distkeys and diststyles
+
+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.
+
+```ruby
+class Decks < DataDuck::Table
+  # source info goes here
+
+  def distribution_key
+    "company_id"
+  end
+
+  def distribution_style
+    "all"
+  end
+
+  # output info goes here
+end
+```
+
+For more info, read: [http://docs.aws.amazon.com/redshift/latest/dg/t_Distributing_data.html](Distributing Data)
+
 ## Example Table
 
 The following is an example table.

data/lib/dataduck/commands.rb

@@ -240,7 +240,10 @@ module DataDuck
       puts "Connection successful. Detected #{ table_names.length } tables."
       puts "Creating scaffolding..."
       table_names.each do |table_name|
-        DataDuck::Commands.quickstart_create_table(table_name, db_source)
+        begin
+          DataDuck::Commands.quickstart_create_table(table_name, db_source)
+        rescue
+        end
       end
 
       config_obj = {

data/lib/dataduck/redshift_destination.rb

@@ -72,9 +72,10 @@ module DataDuck
       props_string = props_array.join(', ')
 
       distribution_clause = table.distribution_key ? "DISTKEY(#{ table.distribution_key })" : ""
+      distribution_style_clause = table.distribution_style ? "DISTSTYLE #{ distribution_style }" : ""
       index_clause = table.indexes.length > 0 ? "INTERLEAVED SORTKEY (#{ table.indexes.join(',') })" : ""
 
-      "CREATE TABLE IF NOT EXISTS #{ table_name } (#{ props_string }) #{ distribution_clause } #{ index_clause }"
+      "CREATE TABLE IF NOT EXISTS #{ table_name } (#{ props_string }) #{ distribution_clause } #{ distribution_style_clause } #{ index_clause }"
     end
 
     def create_output_tables!(table)

data/lib/dataduck/table.rb

@@ -70,6 +70,10 @@ module DataDuck
       end
     end
 
+    def distribution_style
+      nil
+    end
+
     def etl!(destinations, options = {})
       if destinations.length != 1
         raise ArgumentError.new("DataDuck can only etl to one destination at a time for now.")

data/lib/dataduck/version.rb

@@ -1,7 +1,7 @@
 module DataDuck
   if !defined?(DataDuck::VERSION)
     VERSION_MAJOR = 1
-    VERSION_MINOR = 1
+    VERSION_MINOR = 2
     VERSION_PATCH = 0
     VERSION = [VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH].join('.')
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: dataduck
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.2.0
 platform: ruby
 authors:
 - Jeff Pickhardt
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-09-05 00:00:00.000000000 Z
+date: 2017-03-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -295,7 +295,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.6
+rubygems_version: 2.6.8
 signing_key: 
 specification_version: 4
 summary: A straightforward, effective ETL framework.