dm-cassandra-adapter 0.0.1

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2010 Michael Rykov
+
+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 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.

data/Rakefile

@@ -0,0 +1,32 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  gem 'jeweler', '~> 1.4'
+  require 'jeweler'
+
+  Jeweler::Tasks.new do |gem|
+    gem.name        = 'dm-cassandra-adapter'
+    gem.summary     = 'Cassandra Adapter for DataMapper'
+    gem.description = gem.summary
+    gem.email       = 'mrykov [a] gmail [d] com'
+    gem.homepage    = 'http://github.com/rykov/%s' % gem.name
+    gem.authors     = [ 'Michael Rykov' ]
+    gem.has_rdoc    = 'yard'
+
+    gem.rubyforge_project = 'datamapper'
+
+    gem.add_dependency 'dm-core',       '~> 1.0.2'
+    gem.add_dependency 'dm-serializer', '~> 1.0.2'
+
+    gem.add_development_dependency 'rspec',          '~> 1.3'
+    gem.add_development_dependency 'dm-validations', '~> 1.0.2'
+    gem.add_development_dependency 'fakeweb',        '~> 1.3'
+  end
+
+  Jeweler::GemcutterTasks.new
+
+  FileList['tasks/**/*.rake'].each { |task| import task }
+rescue LoadError
+  puts 'Jeweler (or a dependency) not available. Install it with: gem install jeweler'
+end

data/VERSION

@@ -0,0 +1 @@
+0.0.1

data/conf/storage-conf.xml

@@ -0,0 +1,354 @@
+<!--
+ ~ Licensed to the Apache Software Foundation (ASF) under one
+ ~ or more contributor license agreements.  See the NOTICE file
+ ~ distributed with this work for additional information
+ ~ regarding copyright ownership.  The ASF licenses this file
+ ~ to you under the Apache License, Version 2.0 (the
+ ~ "License"); you may not use this file except in compliance
+ ~ with the License.  You may obtain a copy of the License at
+ ~
+ ~    http://www.apache.org/licenses/LICENSE-2.0
+ ~
+ ~ Unless required by applicable law or agreed to in writing,
+ ~ software distributed under the License is distributed on an
+ ~ "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ ~ KIND, either express or implied.  See the License for the
+ ~ specific language governing permissions and limitations
+ ~ under the License.
+-->
+<Storage>
+  <!--======================================================================-->
+  <!-- Basic Configuration                                                  -->
+  <!--======================================================================-->
+
+  <!--
+   ~ The name of this cluster.  This is mainly used to prevent machines in
+   ~ one logical cluster from joining another.
+  -->
+  <ClusterName>Test</ClusterName>
+
+  <!--
+   ~ Turn on to make new [non-seed] nodes automatically migrate the right data
+   ~ to themselves.  (If no InitialToken is specified, they will pick one
+   ~ such that they will get half the range of the most-loaded node.)
+   ~ If a node starts up without bootstrapping, it will mark itself bootstrapped
+   ~ so that you can't subsequently accidently bootstrap a node with
+   ~ data on it.  (You can reset this by wiping your data and commitlog
+   ~ directories.)
+   ~
+   ~ Off by default so that new clusters and upgraders from 0.4 don't
+   ~ bootstrap immediately.  You should turn this on when you start adding
+   ~ new nodes to a cluster that already has data on it.  (If you are upgrading
+   ~ from 0.4, start your cluster with it off once before changing it to true.
+   ~ Otherwise, no data will be lost but you will incur a lot of unnecessary
+   ~ I/O before your cluster starts up.)
+  -->
+  <AutoBootstrap>false</AutoBootstrap>
+
+  <!--
+   ~ Keyspaces and ColumnFamilies:
+   ~ A ColumnFamily is the Cassandra concept closest to a relational
+   ~ table.  Keyspaces are separate groups of ColumnFamilies.  Except in
+   ~ very unusual circumstances you will have one Keyspace per application.
+
+   ~ There is an implicit keyspace named 'system' for Cassandra internals.
+  -->
+  <Keyspaces>
+    <Keyspace Name="AdapterTest">
+        <KeysCachedFraction>0.01</KeysCachedFraction>
+
+        <!-- 'Books' is for my our own tests -->
+        <ColumnFamily CompareWith="UTF8Type" Name="Books" />
+        <!-- 'Heffalumps' is for shared DataMapper adapter tests -->
+        <ColumnFamily CompareWith="UTF8Type" Name="Heffalumps" />
+
+        <ReplicaPlacementStrategy>org.apache.cassandra.locator.RackUnawareStrategy</ReplicaPlacementStrategy>
+        <ReplicationFactor>1</ReplicationFactor>
+        <EndPointSnitch>org.apache.cassandra.locator.EndPointSnitch</EndPointSnitch>
+    </Keyspace>
+
+    <Keyspace Name="Twitter">
+        <KeysCachedFraction>0.01</KeysCachedFraction>
+        <ColumnFamily CompareWith="UTF8Type" Name="Users" />
+        <ColumnFamily CompareWith="UTF8Type" Name="UserAudits" />
+        <ColumnFamily CompareWith="UTF8Type" CompareSubcolumnsWith="TimeUUIDType" ColumnType="Super" Name="UserRelationships" />
+        <ColumnFamily CompareWith="UTF8Type" Name="Usernames" />
+        <ColumnFamily CompareWith="UTF8Type" Name="Statuses" />
+        <ColumnFamily CompareWith="UTF8Type" Name="StatusAudits" />
+        <ColumnFamily CompareWith="UTF8Type" CompareSubcolumnsWith="TimeUUIDType" ColumnType="Super" Name="StatusRelationships" />
+        <ColumnFamily CompareWith="UTF8Type" ColumnType="Super" Name="Index" />
+        <ColumnFamily CompareWith="BytesType" ColumnType="Standard" Name="TimelinishThings" />
+
+        <ReplicaPlacementStrategy>org.apache.cassandra.locator.RackUnawareStrategy</ReplicaPlacementStrategy>
+        <ReplicationFactor>1</ReplicationFactor>
+        <EndPointSnitch>org.apache.cassandra.locator.EndPointSnitch</EndPointSnitch>
+    </Keyspace>
+
+    <Keyspace Name="Multiblog">
+      <KeysCachedFraction>0.01</KeysCachedFraction>
+      <ColumnFamily CompareWith="TimeUUIDType" Name="Blogs"/>
+      <ColumnFamily CompareWith="TimeUUIDType" Name="Comments"/>
+
+      <ReplicaPlacementStrategy>org.apache.cassandra.locator.RackUnawareStrategy</ReplicaPlacementStrategy>
+      <ReplicationFactor>1</ReplicationFactor>
+      <EndPointSnitch>org.apache.cassandra.locator.EndPointSnitch</EndPointSnitch>
+    </Keyspace>
+
+    <Keyspace Name="MultiblogLong">
+      <KeysCachedFraction>0.01</KeysCachedFraction>
+      <ColumnFamily CompareWith="LongType" Name="Blogs"/>
+      <ColumnFamily CompareWith="LongType" Name="Comments"/>
+
+      <ReplicaPlacementStrategy>org.apache.cassandra.locator.RackUnawareStrategy</ReplicaPlacementStrategy>
+      <ReplicationFactor>1</ReplicationFactor>
+      <EndPointSnitch>org.apache.cassandra.locator.EndPointSnitch</EndPointSnitch>
+    </Keyspace>
+
+    <Keyspace Name="CassandraObject">
+      <KeysCachedFraction>0.01</KeysCachedFraction>
+      <ColumnFamily CompareWith="UTF8Type" Name="Customers" />
+      <ColumnFamily CompareWith="UTF8Type" CompareSubcolumnsWith="TimeUUIDType" ColumnType="Super" Name="CustomerRelationships" />
+      <ColumnFamily CompareWith="TimeUUIDType" Name="CustomersByLastName" />
+      <ColumnFamily CompareWith="UTF8Type" Name="Invoices" />
+      <ColumnFamily CompareWith="UTF8Type" CompareSubcolumnsWith="TimeUUIDType" ColumnType="Super" Name="InvoiceRelationships" />
+      <ColumnFamily CompareWith="UTF8Type" Name="InvoicesByNumber" />
+      <ColumnFamily CompareWith="UTF8Type" Name="Payments" />
+      <ColumnFamily CompareWith="UTF8Type" Name="Appointments" />
+      <!-- <ColumnFamily CompareWith="UTF8Type" Name="FirstNames" /> -->
+
+      <ReplicaPlacementStrategy>org.apache.cassandra.locator.RackUnawareStrategy</ReplicaPlacementStrategy>
+      <ReplicationFactor>1</ReplicationFactor>
+      <EndPointSnitch>org.apache.cassandra.locator.EndPointSnitch</EndPointSnitch>
+    </Keyspace>
+  </Keyspaces>
+
+  <!--
+   ~ Authenticator: any IAuthenticator may be used, including your own as long
+   ~ as it is on the classpath.  Out of the box, Cassandra provides
+   ~ org.apache.cassandra.auth.AllowAllAuthenticator and,
+   ~ org.apache.cassandra.auth.SimpleAuthenticator
+   ~ (SimpleAuthenticator uses access.properties and passwd.properties by
+   ~ default).
+   ~
+   ~ If you don't specify an authenticator, AllowAllAuthenticator is used.
+  -->
+  <Authenticator>org.apache.cassandra.auth.AllowAllAuthenticator</Authenticator>
+
+  <!--
+   ~ Partitioner: any IPartitioner may be used, including your own as long
+   ~ as it is on the classpath.  Out of the box, Cassandra provides
+   ~ org.apache.cassandra.dht.RandomPartitioner,
+   ~ org.apache.cassandra.dht.OrderPreservingPartitioner, and
+   ~ org.apache.cassandra.dht.CollatingOrderPreservingPartitioner.
+   ~ (CollatingOPP colates according to EN,US rules, not naive byte
+   ~ ordering.  Use this as an example if you need locale-aware collation.)
+   ~ Range queries require using an order-preserving partitioner.
+   ~
+   ~ Achtung!  Changing this parameter requires wiping your data
+   ~ directories, since the partitioner can modify the sstable on-disk
+   ~ format.
+  -->
+  <Partitioner>org.apache.cassandra.dht.RandomPartitioner</Partitioner>
+
+  <!--
+   ~ If you are using an order-preserving partitioner and you know your key
+   ~ distribution, you can specify the token for this node to use. (Keys
+   ~ are sent to the node with the "closest" token, so distributing your
+   ~ tokens equally along the key distribution space will spread keys
+   ~ evenly across your cluster.)  This setting is only checked the first
+   ~ time a node is started.
+
+   ~ This can also be useful with RandomPartitioner to force equal spacing
+   ~ of tokens around the hash space, especially for clusters with a small
+   ~ number of nodes.
+  -->
+  <InitialToken></InitialToken>
+
+  <!--
+   ~ Directories: Specify where Cassandra should store different data on
+   ~ disk.  Keep the data disks and the CommitLog disks separate for best
+   ~ performance
+  -->
+  <CommitLogDirectory>data/cassandra/commitlog</CommitLogDirectory>
+  <DataFileDirectories>
+      <DataFileDirectory>data/cassandra/data</DataFileDirectory>
+  </DataFileDirectories>
+  <CalloutLocation>data/cassandra/callouts</CalloutLocation>
+  <StagingFileDirectory>data/cassandra/staging</StagingFileDirectory>
+
+
+  <!--
+   ~ Addresses of hosts that are deemed contact points. Cassandra nodes
+   ~ use this list of hosts to find each other and learn the topology of
+   ~ the ring. You must change this if you are running multiple nodes!
+  -->
+  <Seeds>
+      <Seed>127.0.0.1</Seed>
+  </Seeds>
+
+
+  <!-- Miscellaneous -->
+
+  <!-- Time to wait for a reply from other nodes before failing the command -->
+  <RpcTimeoutInMillis>5000</RpcTimeoutInMillis>
+  <!-- Size to allow commitlog to grow to before creating a new segment -->
+  <CommitLogRotationThresholdInMB>128</CommitLogRotationThresholdInMB>
+
+
+  <!-- Local hosts and ports -->
+
+  <!--
+   ~ Address to bind to and tell other nodes to connect to.  You _must_
+   ~ change this if you want multiple nodes to be able to communicate!
+   ~
+   ~ Leaving it blank leaves it up to InetAddress.getLocalHost(). This
+   ~ will always do the Right Thing *if* the node is properly configured
+   ~ (hostname, name resolution, etc), and the Right Thing is to use the
+   ~ address associated with the hostname (it might not be).
+  -->
+  <ListenAddress>localhost</ListenAddress>
+  <!-- internal communications port -->
+  <StoragePort>7000</StoragePort>
+
+  <!--
+   ~ The address to bind the Thrift RPC service to. Unlike ListenAddress
+   ~ above, you *can* specify 0.0.0.0 here if you want Thrift to listen on
+   ~ all interfaces.
+   ~
+   ~ Leaving this blank has the same effect it does for ListenAddress,
+   ~ (i.e. it will be based on the configured hostname of the node).
+  -->
+  <ThriftAddress>localhost</ThriftAddress>
+  <!-- Thrift RPC port (the port clients connect to). -->
+  <ThriftPort>9160</ThriftPort>
+  <!--
+   ~ Whether or not to use a framed transport for Thrift. If this option
+   ~ is set to true then you must also use a framed transport on the
+   ~ client-side, (framed and non-framed transports are not compatible).
+  -->
+  <ThriftFramedTransport>false</ThriftFramedTransport>
+
+
+  <!--======================================================================-->
+  <!-- Memory, Disk, and Performance                                        -->
+  <!--======================================================================-->
+
+  <!--
+   ~ Access mode.  mmapped i/o is substantially faster, but only practical on
+   ~ a 64bit machine (which notably does not include EC2 "small" instances)
+   ~ or relatively small datasets.  "auto", the safe choice, will enable
+   ~ mmapping on a 64bit JVM.  Other values are "mmap", "mmap_index_only"
+   ~ (which may allow you to get part of the benefits of mmap on a 32bit
+   ~ machine by mmapping only index files) and "standard".
+   ~ (The buffer size settings that follow only apply to standard,
+   ~ non-mmapped i/o.)
+   -->
+  <DiskAccessMode>auto</DiskAccessMode>
+
+  <!--
+   ~ Buffer size to use when performing contiguous column slices. Increase
+   ~ this to the size of the column slices you typically perform.
+   ~ (Name-based queries are performed with a buffer size of
+   ~ ColumnIndexSizeInKB.)
+  -->
+  <SlicedBufferSizeInKB>64</SlicedBufferSizeInKB>
+
+  <!--
+   ~ Buffer size to use when flushing memtables to disk. (Only one
+   ~ memtable is ever flushed at a time.) Increase (decrease) the index
+   ~ buffer size relative to the data buffer if you have few (many)
+   ~ columns per key.  Bigger is only better _if_ your memtables get large
+   ~ enough to use the space. (Check in your data directory after your
+   ~ app has been running long enough.) -->
+  <FlushDataBufferSizeInMB>32</FlushDataBufferSizeInMB>
+  <FlushIndexBufferSizeInMB>8</FlushIndexBufferSizeInMB>
+
+  <!--
+   ~ Add column indexes to a row after its contents reach this size.
+   ~ Increase if your column values are large, or if you have a very large
+   ~ number of columns.  The competing causes are, Cassandra has to
+   ~ deserialize this much of the row to read a single column, so you want
+   ~ it to be small - at least if you do many partial-row reads - but all
+   ~ the index data is read for each access, so you don't want to generate
+   ~ that wastefully either.
+  -->
+  <ColumnIndexSizeInKB>64</ColumnIndexSizeInKB>
+
+  <!--
+   ~ Flush memtable after this much data has been inserted, including
+   ~ overwritten data.  There is one memtable per column family, and
+   ~ this threshold is based solely on the amount of data stored, not
+   ~ actual heap memory usage (there is some overhead in indexing the
+   ~ columns).
+  -->
+  <MemtableThroughputInMB>64</MemtableThroughputInMB>
+  <!--
+   ~ Throughput setting for Binary Memtables.  Typically these are
+   ~ used for bulk load so you want them to be larger.
+  -->
+  <BinaryMemtableThroughputInMB>256</BinaryMemtableThroughputInMB>
+  <!--
+   ~ The maximum number of columns in millions to store in memory per
+   ~ ColumnFamily before flushing to disk.  This is also a per-memtable
+   ~ setting.  Use with MemtableThroughputInMB to tune memory usage.
+  -->
+  <MemtableOperationsInMillions>0.3</MemtableOperationsInMillions>
+  <!--
+   ~ The maximum time to leave a dirty memtable unflushed.
+   ~ (While any affected columnfamilies have unflushed data from a
+   ~ commit log segment, that segment cannot be deleted.)
+   ~ This needs to be large enough that it won't cause a flush storm
+   ~ of all your memtables flushing at once because none has hit
+   ~ the size or count thresholds yet.  For production, a larger
+   ~ value such as 1440 is recommended.
+  -->
+  <MemtableFlushAfterMinutes>60</MemtableFlushAfterMinutes>
+
+  <!--
+   ~ Unlike most systems, in Cassandra writes are faster than reads, so
+   ~ you can afford more of those in parallel.  A good rule of thumb is 2
+   ~ concurrent reads per processor core.  Increase ConcurrentWrites to
+   ~ the number of clients writing at once if you enable CommitLogSync +
+   ~ CommitLogSyncDelay. -->
+  <ConcurrentReads>8</ConcurrentReads>
+  <ConcurrentWrites>32</ConcurrentWrites>
+
+  <!--
+   ~ CommitLogSync may be either "periodic" or "batch."  When in batch
+   ~ mode, Cassandra won't ack writes until the commit log has been
+   ~ fsynced to disk.  It will wait up to CommitLogSyncBatchWindowInMS
+   ~ milliseconds for other writes, before performing the sync.
+
+   ~ This is less necessary in Cassandra than in traditional databases
+   ~ since replication reduces the odds of losing data from a failure
+   ~ after writing the log entry but before it actually reaches the disk.
+   ~ So the other option is "timed," where writes may be acked immediately
+   ~ and the CommitLog is simply synced every CommitLogSyncPeriodInMS
+   ~ milliseconds.
+  -->
+  <CommitLogSync>periodic</CommitLogSync>
+  <!--
+   ~ Interval at which to perform syncs of the CommitLog in periodic mode.
+   ~ Usually the default of 10000ms is fine; increase it if your i/o
+   ~ load is such that syncs are taking excessively long times.
+  -->
+  <CommitLogSyncPeriodInMS>10000</CommitLogSyncPeriodInMS>
+  <!--
+   ~ Delay (in milliseconds) during which additional commit log entries
+   ~ may be written before fsync in batch mode.  This will increase
+   ~ latency slightly, but can vastly improve throughput where there are
+   ~ many writers.  Set to zero to disable (each entry will be synced
+   ~ individually).  Reasonable values range from a minimal 0.1 to 10 or
+   ~ even more if throughput matters more than latency.
+  -->
+  <!-- <CommitLogSyncBatchWindowInMS>1</CommitLogSyncBatchWindowInMS> -->
+
+  <!--
+   ~ Time to wait before garbage-collection deletion markers.  Set this to
+   ~ a large enough value that you are confident that the deletion marker
+   ~ will be propagated to all replicas by the time this many seconds has
+   ~ elapsed, even in the face of hardware failures.  The default value is
+   ~ ten days.
+  -->
+  <GCGraceSeconds>864000</GCGraceSeconds>
+</Storage>

data/lib/dm-cassandra-adapter.rb

@@ -0,0 +1,9 @@
+require 'extlib'
+require 'dm-core'
+require 'dm-serializer'
+require 'cassandra'
+
+require 'dm-cassandra-adapter/adapter'
+
+DataMapper::Adapters::CassandraAdapter = DataMapperCassandra::Adapter
+DataMapper::Adapters.const_added(:CassandraAdapter)

data/lib/dm-cassandra-adapter/adapter.rb

@@ -0,0 +1,169 @@
+module DataMapperCassandra
+  # TODO: Do not store IDs in the object hash ????
+
+  class Adapter < DataMapper::Adapters::AbstractAdapter
+    def create(resources)
+      client.batch do
+        resources.each do |resource|
+          repository = resource.repository
+          model = resource.model
+          attributes = resource.attributes
+          properties = model.properties(repository.name)
+
+          ## Figure out or generate the key
+          kind = self.column_family(model)
+          keys = properties.key
+          raise "Multiple keys in #{resource.inspect}" if keys.size > 1
+          if keys.size == 1
+            name = keys.first.name
+            property = properties[name]
+            key = convert_value(property, attributes[name])
+          end
+          if keys.first.serial? && (key.nil? || key == 0 || key == '')
+            name = keys.first.name
+            property = properties[name]
+            key = if property.primitive == Integer
+              # BAD: for Serial
+              Time.stamp & 0x7FFFFFFF
+            else
+              # GOOD: for UUID/:key => true
+              SimpleUUID::UUID.new.to_guid
+            end
+          end
+
+          initialize_serial(resource, key)
+          attributes = resource.attributes
+
+          #puts "#{key} => #{attributes.inspect}"
+
+          ## Convert to serialized data ##
+          data = {}
+          attributes.each do |name, value|
+            property = properties[name]
+            data[property.field] = convert_value(property, value)
+          end
+
+          # Insert this resource into Cassandra
+          client.insert(kind, key.to_s, data);
+        end
+      end
+      resources
+    end
+
+    def column_family(model)
+      model.storage_name(self.name)
+    end
+
+    def convert_value(property, value)
+      property.dump(value)
+    end
+
+    def read(query)
+      model = query.model
+      kind = self.column_family(model)
+
+      records = if id = extract_id_from_query(query)
+        data = client.get(kind, id.to_s)
+        [ load_resource(data, model) ]
+      else
+        # raise NotImplementedError.new("SimpleDB supports only a single order clause")
+        # FIXME - This is terrible, we should not get all keys
+        all_keys = client.get_range(kind)
+        data_hash = client.multi_get(kind, all_keys)
+        data_hash.map do |id, data|
+          load_resource(data, model)
+        end
+      end
+
+      query.filter_records(records)
+    end
+
+    def update(dirty_attributes, collection)
+      client.batch do
+        count = collection.select do |resource|
+          model = resource.model
+          kind  = self.column_family(model)
+          key   = model.key
+          id    = key.get(resource).join
+
+          data = {}
+          dirty_attributes.each do |property, value|
+            property.set!(resource, value)
+            data[property.field] = convert_value(property, value)
+          end
+
+          client.insert(kind, id, data);
+        end
+      end.size
+    end
+
+    def delete(collection)
+      client.batch do
+        count = collection.select do |resource|
+          model = resource.model
+          kind  = self.column_family(model)
+          key   = model.key
+          id    = key.get(resource).join
+
+          client.remove(kind, id)
+        end
+      end.size
+    end
+
+    private
+
+    def initialize(*)
+      super
+      @resource_naming_convention = lambda do |value|
+        Extlib::Inflection.pluralize(Extlib::Inflection.camelize(value))
+      end
+    end
+
+    def client
+      @client ||= begin
+        keyspace = @options[:path][1..-1] # Without leading slash
+        if @options[:host] == 'memory'
+          require 'cassandra/mock'
+          this_dir = File.dirname(__FILE__)
+          conf_xml = File.expand_path('../../conf/storage-conf.xml', this_dir)
+          Cassandra::Mock.new(keyspace, conf_xml)
+        else
+          server = "#{@options[:host]}:#{@options[:port] || 9160}"
+          Cassandra.new(keyspace, server)
+        end
+      end
+    end
+
+    def extract_id_from_query(query)
+      return nil unless query.limit == 1
+
+      conditions = query.conditions
+
+      return nil unless conditions.kind_of?(DataMapper::Query::Conditions::AndOperation)
+      return nil unless (key_condition = conditions.select { |o| o.subject.key? }).size == 1
+
+      key_condition.first.value
+    end
+
+    def extract_params_from_query(query)
+      conditions = query.conditions
+
+      return {} unless conditions.kind_of?(DataMapper::Query::Conditions::AndOperation)
+      return {} if conditions.any? { |o| o.subject.key? }
+
+      query.options
+    end
+
+    ## CASSANDRA ###
+    def load_resource(data, model)
+      field_to_property = model.properties(name).map { |p| [ p.field, p ] }.to_hash
+
+      record = {}
+      data.each do |key, value|
+        next unless property = field_to_property[key]
+        record[key] = property.load(value)
+      end
+      record
+    end
+  end
+end

data/lib/dm-cassandra-adapter/spec/setup.rb

@@ -0,0 +1,15 @@
+require 'dm-cassandra-adapter'
+require 'dm-core/spec/setup'
+
+module DataMapper
+  module Spec
+    module Adapters
+
+      class CassandraAdapter < Adapter
+      end
+
+      use CassandraAdapter
+
+    end
+  end
+end

data/spec/fixtures/book.rb

@@ -0,0 +1,8 @@
+class Book
+  include DataMapper::Resource
+
+  property :id,         Serial
+  property :created_at, DateTime
+  property :title,      String
+  property :author,     String
+end

data/spec/fixtures/difficult_book.rb

@@ -0,0 +1,10 @@
+class DifficultBook
+  include DataMapper::Resource
+
+  storage_names[:default] = 'Books'
+
+  property :id,         Serial
+  property :created_at, DateTime
+  property :title,      String
+  property :author,     String
+end

data/spec/rcov.opts

@@ -0,0 +1,6 @@
+--exclude "spec,^/"
+--sort coverage
+--callsites
+--xrefs
+--profile
+--text-summary

data/spec/semipublic/cassandra_adapter_spec.rb

@@ -0,0 +1,116 @@
+require 'spec_helper'
+require DataMapper.root / 'lib' / 'dm-core' / 'spec' / 'shared' / 'adapter_spec'
+
+describe DataMapper::Adapters::CassandraAdapter do
+  before :all do
+    @adapter = DataMapper::Repository.adapters[:default]
+    @adapter.send(:client).clear_keyspace!
+  end
+  
+  # Shared DataMapper::Adapter specs
+  it_should_behave_like 'An Adapter'
+
+
+  describe 'with one created resource' do
+    before :all do
+      @input_hash = {
+        :created_at => DateTime.parse('2009-05-17T22:38:42-07:00'),
+        :title => 'DataMapper',
+        :author => 'Dan Kubb'
+      }
+
+      # Create resource
+      @resource  = Book.new(@input_hash)
+      @resources = [ @resource ]
+      @response = @adapter.create(@resources)
+      @generated_id = @resource.id
+
+      # Stringify keys and add the Generated ID
+      @output_hash = @input_hash.inject('id' => @generated_id) do |s, kv|
+        s[kv[0].to_s] = kv[1]
+        s
+      end
+    end
+
+    it 'should return an Array containing the Resource' do
+      @response.should equal(@resources)
+    end
+
+    it 'should set the identity field' do
+      @generated_id.should be_present
+    end
+
+    describe '#read' do
+      describe 'with unscoped query' do
+        before :all do
+          @query = Book.all.query
+          @response = @adapter.read(@query)
+        end
+
+        it 'should return an Array with the matching Records' do
+          @response.should == [ @output_hash ]
+        end
+      end
+    end
+
+    describe 'with query scoped by a key' do
+      before :all do
+        @query = Book.all(:id => @generated_id, :limit => 1).query
+        @response = @adapter.read(@query)
+      end
+
+      it 'should return an Array with the matching Records' do
+        @response.should == [ @output_hash ]
+      end
+    end
+
+
+    describe 'with query scoped by a non-key' do
+      before :all do
+        @query = Book.all(:author => 'Dan Kubb').query
+        @response = @adapter.read(@query)
+      end
+
+      it 'should return an Array with the matching Records' do
+        @response.should == [  @output_hash ]
+      end
+    end
+
+    describe 'with a non-standard model <=> storage_name relationship' do
+      before :all do
+        @query = DifficultBook.all.query
+        @response = @adapter.read(@query)
+      end
+
+      it 'should return an Array with the matching Records' do
+        @response.should == [ @output_hash  ]
+      end
+    end
+
+    describe '#update' do
+      before :all do
+        @resources = Book.all
+        @response = @adapter.update({ Book.properties[:author] => 'John Doe' }, @resources)
+      end
+
+      it 'should return the number of updated Resources' do
+        @response.should == 1
+      end
+
+      it 'should modify the Resource' do
+        @resources.first.author.should == 'John Doe'
+      end
+    end
+
+    describe '#delete' do
+      before :all do
+        @resources = Book.all
+        @response = @adapter.delete(@resources)
+      end
+
+      it 'should return the number of updated Resources' do
+        @response.should == 1
+      end
+    end
+  end
+end

data/spec/spec.opts

@@ -0,0 +1,4 @@
+--colour
+--loadby random
+--format profile
+--backtrace

data/spec/spec_helper.rb

@@ -0,0 +1,30 @@
+require 'rubygems'
+require 'pathname'
+require 'simple_uuid'
+
+# use local dm-core if running from a typical dev checkout.
+lib = File.join('..', '..', '..', 'dm-core', 'lib')
+$LOAD_PATH.unshift(lib) if File.directory?(lib)
+
+# use local dm-validations if running from a typical dev checkout.
+lib = File.join('..', '..', 'dm-validations', 'lib')
+$LOAD_PATH.unshift(lib) if File.directory?(lib)
+require 'dm-validations'
+
+# use local dm-serializer if running from a typical dev checkout.
+lib = File.join('..', '..', 'dm-serializer', 'lib')
+$LOAD_PATH.unshift(lib) if File.directory?(lib)
+
+# Support running specs with 'rake spec' and 'spec'
+$LOAD_PATH.unshift('lib') unless $LOAD_PATH.include?('lib')
+
+require 'simple_uuid'
+require 'dm-cassandra-adapter'
+
+ROOT = Pathname(__FILE__).dirname.parent
+
+DataMapper.setup(:default, 'cassandra://memory/AdapterTest')
+
+Dir[ROOT / 'spec' / 'fixtures' / '**' / '*.rb'].each { |rb| require rb }
+
+####FakeWeb.allow_net_connect = false

data/tasks/spec.rake

@@ -0,0 +1,41 @@
+spec_defaults = lambda do |spec|
+  spec.pattern    = 'spec/**/*_spec.rb'
+  spec.libs      << 'lib' << 'spec'
+  spec.spec_opts << '--options' << 'spec/spec.opts'
+end
+
+begin
+  require 'spec/rake/spectask'
+
+  Spec::Rake::SpecTask.new(:spec, &spec_defaults)
+rescue LoadError
+  task :spec do
+    abort 'rspec is not available. In order to run spec, you must: gem install rspec'
+  end
+end
+
+begin
+  require 'rcov'
+  require 'spec/rake/verify_rcov'
+
+  Spec::Rake::SpecTask.new(:rcov) do |rcov|
+    spec_defaults.call(rcov)
+    rcov.rcov      = true
+    rcov.rcov_opts = File.read('spec/rcov.opts').split(/\s+/)
+  end
+
+  RCov::VerifyTask.new(:verify_rcov => :rcov) do |rcov|
+    rcov.threshold = 100
+  end
+rescue LoadError
+  %w[ rcov verify_rcov ].each do |name|
+    task name do
+      abort "rcov is not available. In order to run #{name}, you must: gem install rcov"
+    end
+  end
+end
+
+#task :spec => :check_dependencies
+#task :rcov => :check_dependencies
+
+task :default => :spec

metadata

@@ -0,0 +1,145 @@
+--- !ruby/object:Gem::Specification 
+name: dm-cassandra-adapter
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+    - 0
+    - 0
+    - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+  - Michael Rykov
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-12-19 00:00:00 -08:00
+default_executable: 
+dependencies: 
+  - !ruby/object:Gem::Dependency 
+    name: dm-core
+    prerelease: false
+    requirement: &id001 !ruby/object:Gem::Requirement 
+      requirements: 
+        - - ~>
+          - !ruby/object:Gem::Version 
+            segments: 
+              - 1
+              - 0
+              - 2
+            version: 1.0.2
+    type: :runtime
+    version_requirements: *id001
+  - !ruby/object:Gem::Dependency 
+    name: dm-serializer
+    prerelease: false
+    requirement: &id002 !ruby/object:Gem::Requirement 
+      requirements: 
+        - - ~>
+          - !ruby/object:Gem::Version 
+            segments: 
+              - 1
+              - 0
+              - 2
+            version: 1.0.2
+    type: :runtime
+    version_requirements: *id002
+  - !ruby/object:Gem::Dependency 
+    name: rspec
+    prerelease: false
+    requirement: &id003 !ruby/object:Gem::Requirement 
+      requirements: 
+        - - ~>
+          - !ruby/object:Gem::Version 
+            segments: 
+              - 1
+              - 3
+            version: "1.3"
+    type: :development
+    version_requirements: *id003
+  - !ruby/object:Gem::Dependency 
+    name: dm-validations
+    prerelease: false
+    requirement: &id004 !ruby/object:Gem::Requirement 
+      requirements: 
+        - - ~>
+          - !ruby/object:Gem::Version 
+            segments: 
+              - 1
+              - 0
+              - 2
+            version: 1.0.2
+    type: :development
+    version_requirements: *id004
+  - !ruby/object:Gem::Dependency 
+    name: fakeweb
+    prerelease: false
+    requirement: &id005 !ruby/object:Gem::Requirement 
+      requirements: 
+        - - ~>
+          - !ruby/object:Gem::Version 
+            segments: 
+              - 1
+              - 3
+            version: "1.3"
+    type: :development
+    version_requirements: *id005
+description: Cassandra Adapter for DataMapper
+email: mrykov [a] gmail [d] com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+  - LICENSE
+files: 
+  - LICENSE
+  - Rakefile
+  - VERSION
+  - conf/storage-conf.xml
+  - lib/dm-cassandra-adapter.rb
+  - lib/dm-cassandra-adapter/adapter.rb
+  - lib/dm-cassandra-adapter/spec/setup.rb
+  - spec/fixtures/book.rb
+  - spec/fixtures/difficult_book.rb
+  - spec/rcov.opts
+  - spec/semipublic/cassandra_adapter_spec.rb
+  - spec/spec.opts
+  - spec/spec_helper.rb
+  - tasks/spec.rake
+has_rdoc: true
+homepage: http://github.com/rykov/dm-cassandra-adapter
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+  - lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+          - 0
+        version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+          - 0
+        version: "0"
+requirements: []
+
+rubyforge_project: datamapper
+rubygems_version: 1.3.6
+signing_key: 
+specification_version: 3
+summary: Cassandra Adapter for DataMapper
+test_files: 
+  - spec/fixtures/book.rb
+  - spec/fixtures/difficult_book.rb
+  - spec/semipublic/cassandra_adapter_spec.rb
+  - spec/spec_helper.rb