athens 0.1.0 → 0.3.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '02197372c02d45a05efd88997b4cd8c01d66c869eafd6ca867f86da791ffe7b4'
-  data.tar.gz: 1753f4f6986c4fedf82f09d9a6d9ebe0b9fb630d59261011fc3c0667108e4ed0
+  metadata.gz: fa391fbff6c5016740bc28cfb0692fcc79ee2e1361d31541a635691e6cbbc8a7
+  data.tar.gz: ef1fbb6307221f616576e844ced0ed9398ff9e6db436fde0142e58c89be8c9f5
 SHA512:
-  metadata.gz: facc871951901270b2b61410ae471cd6d62fcb33d2a914da76855e41fbccfb5039ee4e0d086deced77bcf39bf8c07fe865c635d6659093a2acac181291c78c2a
-  data.tar.gz: feca9c73d6145784b74dc4ce5442c2b764efda51719ff58e5fa6896d8dfd89186224d7aaa4f9ae282d58043bf5aa4f0e3576998d40ec0d9983c51d917d6d8022
+  metadata.gz: e37d29e7d93b1aa61d6266b5feccc3789087f697c1751830893adc4c795761f587bafdaa44f34de6b5786712d8983e66511d3d0f10fa1b0922ec6921e4201e66
+  data.tar.gz: 0ccaf8bbb67bceb9136806a93da4447ace996ab9709e82d8f6861249e6a62246680c3a618a1479481b931127e568e966038569da2d1814540ef64b7ab3dd155e

data/CHANGELOG.md

@@ -1,3 +1,26 @@
+## 0.3.3 / 2021-01-12
+
+* Added support for Ruby 3.0 (thanks [blackjiro](https://github.com/blackjiro))
+
+## 0.3.2 / 2020-11-24
+
+* Added optional `request_token` and `work_group` parameters to the query execute method (thanks [mediafinger](https://github.com/mediafinger))
+
+## 0.3.1 / 2020-07-20
+
+* Bumped development rake version from 0.10 to 0.13 for security fixes
+* Fixed warning about string defaulting to string (#2)
+
+## 0.3.0 / 2019-07-02
+
+* Added enumerator-based result access methods: `#rows` and `#records`
+* Fixed bug dropping headers from memoized rows across `#to_h` and `#to_a(header_row: true)`
+
+## 0.2.0 / 2019-03-20
+
+* Added support for NULL values.  Columns with a nullable status of "NULLABLE" or "UNKNOWN" will return nil for NULL values
+* If a NOT_NULL column returns a nil value an InvalidNullError will be raised
+
 ## 0.1.0 / 2019-03-01
 
 * Initial release!

data/Gemfile.lock

@@ -1,33 +1,36 @@
 PATH
   remote: .
   specs:
-    athens (0.1.0)
+    athens (0.3.3)
       aws-sdk-athena (~> 1)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    aws-eventstream (1.0.1)
-    aws-partitions (1.136.0)
-    aws-sdk-athena (1.7.0)
-      aws-sdk-core (~> 3, >= 3.39.0)
-      aws-sigv4 (~> 1.0)
-    aws-sdk-core (3.46.0)
-      aws-eventstream (~> 1.0)
-      aws-partitions (~> 1.0)
-      aws-sigv4 (~> 1.0)
+    aws-eventstream (1.1.0)
+    aws-partitions (1.416.0)
+    aws-sdk-athena (1.33.0)
+      aws-sdk-core (~> 3, >= 3.109.0)
+      aws-sigv4 (~> 1.1)
+    aws-sdk-core (3.111.0)
+      aws-eventstream (~> 1, >= 1.0.2)
+      aws-partitions (~> 1, >= 1.239.0)
+      aws-sigv4 (~> 1.1)
       jmespath (~> 1.0)
-    aws-sigv4 (1.0.3)
+    aws-sigv4 (1.2.2)
+      aws-eventstream (~> 1, >= 1.0.2)
     jmespath (1.4.0)
-    rake (10.5.0)
+    rake (13.0.1)
+    rexml (3.2.4)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
   athens!
-  bundler (~> 1.17)
-  rake (~> 10.0)
+  bundler (>= 1.17)
+  rake (~> 13.0)
+  rexml (~> 3.2)
 
 BUNDLED WITH
-   1.17.2
+   2.2.5

data/README.md

@@ -61,6 +61,23 @@ results = query.to_h
 # ]
 ```
 
+Results are also available as unbuffered enumerators of row arrays:
+```ruby
+query.rows.each {|row| ...}
+# ['column_1', 'column_2', 'column_3']
+# [15, 'data', true]
+# [20, 'foo', false],
+# ...
+```
+
+Or hashes:
+```ruby
+query.records.each {|record| ...}
+# {'column_1': 15, 'column_2': 'data', 'column_3': true}
+# {'column_1': 20, 'column_2': 'foo', 'column_3': false}
+# ...
+```
+
 Athens attempts to parse the sql data types into their ruby equivalents, although there's currently no support for the more complex Array/Map types.
 
 ### Configuration
@@ -129,6 +146,13 @@ query.cancel   # Attempts to cancel an in-progress query, returns true or false
 query.to_a(header_row: false)  # If you want your query results returned without a header row of column names
 ```
 
+The execute method also optionally supports the `request_token` and `work_group` [parameters](https://docs.aws.amazon.com/athena/latest/APIReference/API_StartQueryExecution.html#API_StartQueryExecution_RequestSyntax):
+
+```ruby
+conn = Athens::Connection.new(database: 'sample')
+query = conn.execute("SELECT * FROM mytable", request_token: single_use_token, work_group: my_work_group)
+```
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.

data/Rakefile

@@ -1,2 +1 @@
 require "bundler/gem_tasks"
-task :default => :spec

data/athens.gemspec

@@ -32,10 +32,11 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
-  spec.required_ruby_version = '~> 2.4'
+  spec.required_ruby_version = '>= 2.4'
 
   spec.add_dependency "aws-sdk-athena", "~> 1"
 
-  spec.add_development_dependency "bundler", "~> 1.17"
-  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "bundler", ">= 1.17"
+  spec.add_development_dependency "rake", "~> 13.0"
+  spec.add_development_dependency "rexml", "~> 3.2"
 end

data/lib/athens/connection.rb

@@ -8,7 +8,7 @@ module Athens
     def initialize(database: nil, aws_client_override: {})
       @database_name = database
 
-      client_config = { 
+      client_config = {
         access_key_id: Athens.configuration.aws_access_key,
         secret_access_key: Athens.configuration.aws_secret_key,
         region: Athens.configuration.aws_region
@@ -19,26 +19,28 @@ module Athens
 
     # Runs a query against Athena, returning an Athens::Query object
     # that you can use to wait for it to finish or get the results
-    def execute(query)
+    def execute(query, request_token: nil, work_group: nil)
       if @database_name
         resp = @client.start_query_execution(
           query_string: query,
           query_execution_context: context,
-          result_configuration: result_config
+          result_configuration: result_config,
+          client_request_token: request_token,
+          work_group: work_group
         )
       else
         resp = @client.start_query_execution(
           query_string: query,
           result_configuration: result_config
         )
-      end        
+      end
 
       return Athens::Query.new(self, resp.query_execution_id)
     end
 
     private
 
-      def context 
+      def context
         Aws::Athena::Types::QueryExecutionContext.new(database: @database_name)
       end
 

data/lib/athens/error.rb

@@ -4,5 +4,6 @@ module Athens
   class QueryFailedError < Error; end
   class QueryCancelledError < Error; end
   class InvalidRequestError < Error; end
+  class InvalidNullError < Error; end
 
 end

data/lib/athens/query.rb

@@ -69,12 +69,10 @@ module Athens
       end
     end
 
-    def to_a(header_row: true)
+    def rows
       raise InvalidRequestError.new("Query must be in SUCCEEDED state to return results") unless @state == 'SUCCEEDED'
 
-      if @results.nil?
-        # Need to load and map all of the rows from the original result
-        @results = []
+      Enumerator.new do |y|
         result = @connection.client.get_query_results({query_execution_id: @query_execution_id})
 
         metadata = result.result_set.result_set_metadata
@@ -85,53 +83,43 @@ module Athens
           break if rows.empty?
 
           if first
-            @results << rows.shift.data.map {|col| col.var_char_value}
+            y << rows.shift.data.map {|col| col.var_char_value}
             first = false
           end
 
-          rows.each do |row|
-            @results << map_types(metadata, row)
-          end
+          rows.each {|row| y << map_types(metadata, row)}
 
-          if result.next_token
-            result = @connection.client.get_query_results({
-              query_execution_id: @query_execution_id,
-              next_token: result.next_token
-            })
-          else
-            # No more rows, break out and return our mapped data
-            break
-          end
-        end
-      end
+          break unless result.next_token
 
-      if header_row
-        return @results
-      else
-        return @results[1, @results.size]
+          result = @connection.client.get_query_results({
+            query_execution_id: @query_execution_id,
+            next_token: result.next_token
+          })
+        end
       end
     end
 
-    def to_h
-      if @hash_results.nil?
-        all_rows = self.to_a(header_row: true)
-
-        headers = all_rows.shift
-
-        @hash_results = []
+    def records
+      Enumerator.new do |y|
+        headers = nil
 
-        unless headers.nil?
-          all_rows.each do |row|
-            map = {}
-            headers.each_with_index do |header, index|
-              map[header] = row[index]
-            end
-            @hash_results << map
+        rows.each_with_index do |row|
+          if headers.nil?
+            headers = row
+            next
           end
+
+          y << Hash[headers.zip(row)]
         end
       end
+    end
+
+    def to_a(header_row: true)
+      (@results ||= rows.to_a).drop(header_row ? 0 : 1)
+    end
 
-      return @hash_results
+    def to_h
+      @hash_results ||= records.to_a
     end
 
     private
@@ -151,29 +139,36 @@ module Athens
 
         metadata.column_info.each_with_index do |col, index|
           data = row.data[index].var_char_value
+          nullable = ["UNKNOWN", "NULLABLE"].include?(col.nullable)
 
-          case col.type
-          when 'tinyint', 'smallint', 'int', 'integer', 'bigint'
-            mapped << data.to_i
-          when 'timestamp'
-            mapped << Time.parse(data)
-          when 'varchar'
+          if nullable && data.nil?
             mapped << data
-          when 'float', 'double'
-            mapped << data.to_f
-          when 'decimal'
-            if @decimal_without_new
-              mapped << BigDecimal(data)
+          elsif !nullable && data.nil?
+            raise InvalidNullError.new("Got null data from a non-null field (#{col.name})")
+          else
+            case col.type
+            when 'tinyint', 'smallint', 'int', 'integer', 'bigint'
+              mapped << data.to_i
+            when 'timestamp'
+              mapped << Time.parse(data)
+            when 'varchar', 'string'
+              mapped << data
+            when 'float', 'double'
+              mapped << data.to_f
+            when 'decimal'
+              if @decimal_without_new
+                mapped << BigDecimal(data)
+              else
+                mapped << BigDecimal.new(data)
+              end
+            when 'date'
+              mapped << Date.parse(data)
+            when 'boolean'
+              mapped << (data == "true")
             else
-              mapped << BigDecimal.new(data)
+              puts "WARNING: Unsupported type: #{col.type}, defaulting to string"
+              mapped << data
             end
-          when 'date'
-            mapped << Date.parse(data)
-          when 'boolean'
-            mapped << (data == "true")
-          else
-            puts "WARNING: Unsupported type: #{col.type}, defaulting to string"
-            mapped << data
           end
         end
 

data/lib/athens/version.rb

@@ -1,3 +1,3 @@
 module Athens
-  VERSION = "0.1.0"
+  VERSION = "0.3.3"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: athens
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.3.3
 platform: ruby
 authors:
 - Chris Schulte
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2019-03-01 00:00:00.000000000 Z
+date: 2021-01-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: aws-sdk-athena
@@ -28,14 +28,14 @@ dependencies:
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: '1.17'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: '1.17'
 - !ruby/object:Gem::Dependency
@@ -44,14 +44,28 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '13.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+- !ruby/object:Gem::Dependency
+  name: rexml
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '3.2'
 description: Allows you to easily access AWS Athena databases and run queries
 email:
 - chris@oceanbreezesoftware.com
@@ -84,13 +98,13 @@ metadata:
   homepage_uri: https://github.com/getletterpress/athens
   source_code_uri: https://github.com/getletterpress/athens
   changelog_uri: https://github.com/getletterpress/athens/CHANGELOG.md
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - "~>"
+  - - ">="
     - !ruby/object:Gem::Version
       version: '2.4'
 required_rubygems_version: !ruby/object:Gem::Requirement
@@ -99,9 +113,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.8
-signing_key: 
+rubygems_version: 3.1.4
+signing_key:
 specification_version: 4
 summary: Run simple SQL queries in AWS Athena
 test_files: []