ruby-druid 0.1.9 → 0.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d0e676ac15efc4d9777fa182d8c8855bc1ebf386
-  data.tar.gz: e54d2ec80e3bb5efdf02d3b5b127c565c5cfce86
+  metadata.gz: 804e71f527f98f4bc082a2967da5ce7065fa2c01
+  data.tar.gz: ada587e143c21e913df7386ebb3020155d82ff5d
 SHA512:
-  metadata.gz: 884a621b0fb481490d114248bfff0207bc2fd54e889832cf86318c6d26fb53c73c535d97d4d832fc9872a4f6b76b0d426a7050190e41639abfad2d728a36dd7a
-  data.tar.gz: b46976c63af7169c6581d092522f5ac97098320efe903bd6d5a6e58c9c2792aab34d0e17c474de174fc44e74d91a0fc6594a89d39beaf3c8f7fabe3f432af21e
+  metadata.gz: be6eb7e1e566340d22c70b7bc693e3849260b9994886249b501d90db10fcbfac1b0074928e7e5118cc704b5b8eaeda5c02e8e24b3a6b05b0a03e31137090929e
+  data.tar.gz: 08d4a836a5ebc98cbd8c923a1ab718b9c67cceaa66be5e2ab218e85c2928564f47ed05ad2648a977b079f1691c96c35e273bf70494a5c50d9944636218e668fd

data/LICENSE

@@ -1,20 +1,22 @@
-Copyright (c) 2013 madvertise Mobile Advertising GmbH
+Copyright (c) 2016 Ruby Druid Community
 
-Permission is hereby granted, free of charge, to any person obtaining
-a copy of this software and associated documentation files (the
-"Software"), to deal in the Software without restriction, including
-without limitation the rights to use, copy, modify, merge, publish,
-distribute, sublicense, and/or sell copies of the Software, and to
-permit persons to whom the Software is furnished to do so, subject to
-the following conditions:
+Permission is hereby granted, free of charge, to any person
+obtaining a copy of this software and associated documentation
+files (the "Software"), to deal in the Software without
+restriction, including without limitation the rights to use,
+copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the following
+conditions:
 
-The above copyright notice and this permission notice shall be included
-in all copies or substantial portions of the Software.
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
 
 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
-IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
-CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
-TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
-SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -1,29 +1,31 @@
 # ruby-druid
 
-A ruby client for [druid](http://druid.io).
-
-ruby-druid features a [Squeel](https://github.com/ernie/squeel)-like query DSL
-and generates a JSON query that can be sent to druid directly. A console for
-testing is also provided.
+A Ruby client for [Druid](http://druid.io). Includes a [Squeel](https://github.com/ernie/squeel)-like query DSL and generates a JSON query that can be sent to Druid directly.
 
 [![Gem Version](https://badge.fury.io/rb/ruby-druid.png)](http://badge.fury.io/rb/ruby-druid)
-[![Build Status](https://travis-ci.org/liquidm/ruby-druid.png)](https://travis-ci.org/liquidm/ruby-druid)
-[![Code Climate](https://codeclimate.com/github/liquidm/ruby-druid.png)](https://codeclimate.com/github/liquidm/ruby-druid)
-[![Dependency Status](https://gemnasium.com/liquidm/ruby-druid.png)](https://gemnasium.com/liquidm/ruby-druid)
+[![Build Status](https://travis-ci.org/ruby-druid/ruby-druid.png)](https://travis-ci.org/ruby-druid/ruby-druid)
+[![Code Climate](https://codeclimate.com/github/ruby-druid/ruby-druid.png)](https://codeclimate.com/github/ruby-druid/ruby-druid)
+[![Dependency Status](https://gemnasium.com/ruby-druid/ruby-druid.png)](https://gemnasium.com/ruby-druid/ruby-druid)
 
 ## Installation
 
 Add this line to your application's Gemfile:
 
-    gem 'ruby-druid'
+```
+gem 'ruby-druid'
+```
 
 And then execute:
 
-    $ bundle
+```
+bundle
+```
 
 Or install it yourself as:
 
-    $ gem install ruby-druid
+```
+gem install ruby-druid
+```
 
 ## Usage
 
@@ -31,8 +33,7 @@ Or install it yourself as:
 Druid::Client.new('zk1:2181,zk2:2181/druid').query('service/source')
 ```
 
-returns a query object on which all other methods can be called to create a
-full and valid druid query.
+returns a query object on which all other methods can be called to create a full and valid Druid query.
 
 A query object can be sent like this:
 
@@ -42,11 +43,7 @@ query = Druid::Query.new('service/source')
 client.send(query)
 ```
 
-The `send` method returns the parsed response from the druid server as an
-array.  If the response is not empty it contains one `ResponseRow` object for
-each row.  The timestamp by can be received by a method with the same name
-(i.e. `row.timestamp`), all row values by hashlike syntax (i.e.
-`row['dimension'])
+The `send` method returns the parsed response from the druid server as an array.  If the response is not empty it contains one `ResponseRow` object for each row.  The timestamp by can be received by a method with the same name (i.e. `row.timestamp`), all row values by hashlike syntax (i.e. `row['dimension'])
 
 An options hash can be passed when creating `Druid::Client` instance:
 
@@ -60,7 +57,7 @@ Supported options are:
 
 ### GroupBy
 
-A [GroupByQuery](https://github.com/metamx/druid/wiki/GroupByQuery) sets the
+A [GroupByQuery](http://druid.io/docs/latest/querying/groupbyquery.html) sets the
 dimensions to group the data.
 
 `queryType` is set automatically to `groupBy`.
@@ -71,9 +68,7 @@ Druid::Query.new('service/source').group_by([:dimension1, :dimension2])
 
 ### TimeSeries
 
-A [TimeSeriesQuery](https://github.com/metamx/druid/wiki/TimeseriesQuery)
-returns an array of JSON objects where each object represents a value asked for
-by the timeseries query.
+A [TimeSeriesQuery](http://druid.io/docs/latest/querying/timeseriesquery.html) returns an array of JSON objects where each object represents a value asked for by the timeseries query.
 
 ```ruby
 Druid::Query.new('service/source').time_series([:aggregate1, :aggregate2])
@@ -81,10 +76,32 @@ Druid::Query.new('service/source').time_series([:aggregate1, :aggregate2])
 
 ### Aggregations
 
+#### longSum, doubleSum, count, min, max, hyperUnique
+
 ```ruby
 Druid::Query.new('service/source').long_sum([:aggregate1, :aggregate2])
 ```
 
+In the same way could be used the following methods for [aggregations](http://druid.io/docs/latest/querying/aggregations.html) adding: `double_sum, count, min, max, hyper_unique`
+
+#### cardinality
+
+```ruby
+Druid::Query.new('service/source').cardinality(:aggregate, [:dimension1, dimension2], <by_row: true | false>)
+```
+
+#### javascript
+
+For example calculation for `sum(log(x)/y) + 10`:
+
+```ruby
+Druid::Query.new('service/source').js_aggregation(:aggregate, [:x, :y],
+  aggregate: "function(current, a, b)      { return current + (Math.log(a) * b); }",
+  combine:   "function(partialA, partialB) { return partialA + partialB; }",
+  reset:     "function()                   { return 10; }"
+)
+```
+
 ### Post Aggregations
 
 A simple syntax for post aggregations with +,-,/,* can be used like:
@@ -94,8 +111,7 @@ query = Druid::Query.new('service/source').long_sum([:aggregate1, :aggregate2])
 query.postagg { (aggregate2 + aggregate2).as output_field_name }
 ```
 
-Required fields for the postaggregation are fetched automatically by the
-library.
+Required fields for the postaggregation are fetched automatically by the library.
 
 Javascript post aggregations are also supported:
 
@@ -105,8 +121,7 @@ query.postagg { js('function(aggregate1, aggregate2) { return aggregate1 + aggre
 
 ### Query Interval
 
-The interval for the query takes a string with date and time or objects that
-provide an `iso8601` method.
+The interval for the query takes a string with date and time or objects that provide an `iso8601` method.
 
 ```ruby
 query = Druid::Query.new('service/source').long_sum(:aggregate1)
@@ -115,16 +130,13 @@ query.interval("2013-01-01T00", Time.now)
 
 ### Result Granularity
 
-The granularity can be `:all`, `:none`, `:minute`, `:fifteen_minute`,
-`:thirthy_minute`, `:hour` or `:day`.
+The granularity can be `:all`, `:none`, `:minute`, `:fifteen_minute`, `:thirthy_minute`, `:hour` or `:day`.
 
-It can also be a period granularity as described in the [druid
-wiki](https://github.com/metamx/druid/wiki/Granularities).
+It can also be a period granularity as described in the [Druid documentation](http://druid.io/docs/latest/querying/granularities.html).
 
 The period `'day'` or `:day` will be interpreted as `'P1D'`.
 
-If a period granularity is specifed, the (optional) second parameter is a time
-zone. It defaults to the machines local time zone. i.e.
+If a period granularity is specifed, the (optional) second parameter is a time zone. It defaults to the machines local time zone. i.e.
 
 ```ruby
 query = Druid::Query.new('service/source').long_sum(:aggregate1)
@@ -138,20 +150,46 @@ query = Druid::Query.new('service/source').long_sum(:aggregate1)
 query.granularity('P1D', 'Europe/Berlin')
 ```
 
-### Having
+### Having filters
 
 ```ruby
-Druid::Query.new('service/source').having{metric > 10}
+# equality
+Druid::Query.new('service/source').having { metric == 10 }
 ```
 
 ```ruby
-Druid::Query.new('service/source').having{metric < 10}
+# inequality
+Druid::Query.new('service/source').having { metric != 10 }
+```
+
+```ruby
+# greater, less
+Druid::Query.new('service/source').having { metric > 10 }
+Druid::Query.new('service/source').having { metric < 10 }
+```
+
+#### Compound having filters
+
+Having filters can be combined with boolean logic.
+
+```ruby
+# and
+Druid::Query.new('service/source').having { (metric != 1) & (metric2 != 2) }
+```
+
+```ruby
+# or
+Druid::Query.new('service/source').having { (metric == 1) | (metric2 == 2) }
+```
+
+```ruby
+# not
+Druid::Query.new('service/source').having{ !metric.eq(1) }
 ```
 
 ### Filters
 
-Filters are set by the `filter` method. It takes a block or a hash as
-parameter.
+Filters are set by the `filter` method. It takes a block or a hash as parameter.
 
 Filters can be chained `filter{...}.filter{...}`
 
@@ -210,7 +248,7 @@ Druid::Query.new('service/source').filter{dimension.in(1,2,3)}
 ```
 #### Geographic filter
 
-These filters have to be combined with time_series and do only work when coordinates is a spatial dimension [GeographicQueries](http://druid.io/docs/0.6.73/GeographicQueries.html)
+These filters have to be combined with time_series and do only work when coordinates is a spatial dimension [GeographicQueries](http://druid.io/docs/latest/development/geo.html)
 
 ```ruby
 Druid::Query.new('service/source').time_series().long_sum([:aggregate1]).filter{coordinates.in_rec [[50.0,13.0],[54.0,15.0]]}
@@ -230,85 +268,14 @@ Druid::Query.new('service/source').filter{dimension.nin(1,2,3)}
 
 #### Hash syntax
 
-Sometimes it can be useful to use a hash syntax for filtering
-for example if you already get them from a list or parameter hash.
+Sometimes it can be useful to use a hash syntax for filtering for example if you already get them from a list or parameter hash.
 
 ```ruby
 Druid::Query.new('service/source').filter{dimension => 1, dimension1 =>2, dimension2 => 3}
-
-#this is the same as
-
+# which is equivalent to
 Druid::Query.new('service/source').filter{dimension.eq(1) & dimension1.eq(2) & dimension2.eq(3)}
 ```
 
-### DRIPL
-
-ruby-druid now includes a [REPL](https://github.com/cldwalker/ripl):
-
-```ruby
-$ bin/dripl
->> metrics
-[
-    [0] "actions"
-    [1] "words"
-]
-
->> dimensions
-[
-    [0] "type"
-]
-
->> long_sum(:actions)
-+---------+
-| actions |
-+---------+
-|   98575 |
-+---------+
-
->> long_sum(:actions, :words)[-3.days].granularity(:day)
-+---------------+---------------+
-| actions       | words         |
-+---------------+---------------+
-| 2013-12-11T00:00:00.000+01:00 |
-+---------------+---------------+
-| 537345        | 68974         |
-+---------------+---------------+
-| 2013-12-12T00:00:00.000+01:00 |
-+---------------+---------------+
-| 675431        | 49253         |
-+---------------+---------------+
-| 2013-12-13T00:00:00.000+01:00 |
-+---------------+---------------+
-| 749034        | 87542         |
-+---------------+---------------+
-
->> long_sum(:actions, :words)[-3.days].granularity(:day).properties
-{
-      :dataSource => "events",
-     :granularity => {
-            :type => "period",
-          :period => "P1D",
-        :timeZone => "Europe/Berlin"
-    },
-       :intervals => [
-        [0] "2013-12-11T00:00:00+01:00/2013-12-13T09:41:10+01:00"
-    ],
-       :queryType => :groupBy,
-    :aggregations => [
-        [0] {
-                 :type => "longSum",
-                 :name => :actions,
-            :fieldName => :actions
-        },
-        [1] {
-                 :type => "longSum",
-                 :name => :words,
-            :fieldName => :words
-        }
-    ]
-}
-```
-
 ## Contributing
 
 1. Fork it

data/lib/druid.rb

@@ -1,8 +1,2 @@
 require 'druid/client'
 require 'druid/query'
-require 'druid/response_row'
-require 'druid/zoo_handler'
-
-module Druid
-
-end

data/lib/druid/aggregation.rb

@@ -0,0 +1,66 @@
+module Druid
+  class Aggregation
+    include ActiveModel::Model
+
+    attr_accessor :type
+    validates :type, inclusion: { in: %w(count longSum doubleSum min max javascript cardinality hyperUnique) }
+
+    attr_accessor :name
+    validates :name, presence: true
+
+    class FieldnameValidator < ActiveModel::EachValidator
+      TYPES = %w(count longSum doubleSum min max hyperUnique)
+      def validate_each(record, attribute, value)
+        if TYPES.include?(record.type)
+          record.errors.add(attribute, 'may not be blank') if value.blank?
+        else
+          record.errors.add(attribute, "is not supported by type=#{record.type}") if value
+        end
+      end
+    end
+
+    attr_accessor :fieldName
+    validates :fieldName, fieldname: true
+
+    class FieldnamesValidator < ActiveModel::EachValidator
+      TYPES = %w(javascript cardinality)
+      def validate_each(record, attribute, value)
+        if TYPES.include?(record.type)
+          record.errors.add(attribute, 'must be a list of field names') if !value.is_a?(Array) || value.blank?
+        else
+          record.errors.add(attribute, "is not supported by type=#{record.type}") if value
+        end
+      end
+    end
+
+    attr_accessor :fieldNames
+    validates :fieldNames, fieldnames: true
+
+    class FnValidator < ActiveModel::EachValidator
+      TYPES = %w(javascript)
+      def validate_each(record, attribute, value)
+        if TYPES.include?(record.type)
+          record.errors.add(attribute, 'may not be blank') if value.blank?
+        else
+          record.errors.add(attribute, "is not supported by type=#{record.type}") if value
+        end
+      end
+    end
+
+    attr_accessor :fnAggregate
+    validates :fnAggregate, fn: true
+
+    attr_accessor :fnCombine
+    validates :fnCombine, fn: true
+
+    attr_accessor :fnReset
+    validates :fnReset, fn: true
+
+    attr_accessor :byRow
+    validates :byRow, allow_nil: true, inclusion: { in: [true, false] }
+
+    def as_json(options = {})
+      super(options.merge(except: %w(errors validation_context)))
+    end
+  end
+end

data/lib/druid/client.rb

@@ -1,95 +1,23 @@
+require 'druid/zk'
+require 'druid/data_source'
+
 module Druid
   class Client
 
-    def initialize(zookeeper_uri, opts = nil)
-      opts ||= {}
-
-      if opts[:static_setup] && !opts[:fallback]
-        @static = opts[:static_setup]
-      else
-        @backup = opts[:static_setup] if opts[:fallback]
-        zookeeper_caching_management!(zookeeper_uri, opts)
-      end
-
-      @http_timeout = opts[:http_timeout] || 2 * 60
-    end
-
-    def send(query)
-      uri = data_source_uri(query.source)
-      raise "data source #{query.source} (currently) not available" unless uri
-
-      req = Net::HTTP::Post.new(uri.path, {'Content-Type' =>'application/json'})
-      req.body = query.to_json
+    attr_reader :zk
 
-      response = Net::HTTP.new(uri.host, uri.port).start do |http|
-        http.read_timeout = @http_timeout
-        http.request(req)
-      end
-
-      if response.code == "200"
-        JSON.parse(response.body).map{ |row| ResponseRow.new(row) }
-      else
-        raise "Request failed: #{response.code}: #{response.body}"
-      end
-    end
-
-    def query(id, &block)
-      uri = data_source_uri(id)
-      raise "data source #{id} (currently) not available" unless uri
-      query = Query.new(id, self)
-      return query unless block
-
-      send query
+    def initialize(zookeeper, opts = {})
+      @zk = ZK.new(zookeeper, opts)
     end
 
-    def zookeeper_caching_management!(zookeeper_uri, opts)
-      @zk = ZooHandler.new(zookeeper_uri, opts)
-
-      unless opts[:zk_keepalive]
-        @cached_data_sources = @zk.data_sources unless @zk.nil?
-
-        @zk.close!
-      end
-    end
-
-    def ds
-      @cached_data_sources || (@zk.data_sources unless @zk.nil?)
+    def data_source(source)
+      uri = @zk.data_sources[source]
+      Druid::DataSource.new(source, uri)
     end
 
     def data_sources
-      (ds.nil? ? @static : ds).keys
+      @zk.data_sources
     end
 
-    def data_source_uri(source)
-      uri = (ds.nil? ? @static : ds)[source]
-      begin
-        return URI(uri) if uri
-      rescue
-         return URI(@backup) if @backup
-      end
-    end
-
-    def data_source(source)
-      uri = data_source_uri(source)
-      raise "data source #{source} (currently) not available" unless uri
-
-      meta_path = "#{uri.path}datasources/#{source.split('/').last}"
-
-      req = Net::HTTP::Get.new(meta_path)
-
-      response = Net::HTTP.new(uri.host, uri.port).start do |http|
-        http.read_timeout = @http_timeout
-        http.request(req)
-      end
-
-      if response.code == "200"
-        meta = JSON.parse(response.body)
-        meta.define_singleton_method(:dimensions) { self['dimensions'] }
-        meta.define_singleton_method(:metrics) { self['metrics'] }
-        meta
-      else
-        raise "Request failed: #{response.code}: #{response.body}"
-      end
-    end
   end
 end