gotime-cassandra_object 0.6.1

data/test/config/cassandra.in.sh

@@ -0,0 +1,53 @@
+# 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.
+
+
+cassandra_home=`dirname $0`/..
+
+# The directory where Cassandra's configs live (required)
+CASSANDRA_CONF=`pwd`/../test/config
+
+# This can be the path to a jar file, or a directory containing the 
+# compiled classes. NOTE: This isn't needed by the startup script,
+# it's just used here in constructing the classpath.
+cassandra_bin=$cassandra_home/build/classes
+#cassandra_bin=$cassandra_home/build/cassandra.jar
+
+# The java classpath (required)
+CLASSPATH=$CASSANDRA_CONF:$cassandra_bin
+
+for jar in $cassandra_home/lib/*.jar; do
+    CLASSPATH=$CLASSPATH:$jar
+done
+
+# Arguments to pass to the JVM
+JVM_OPTS=" \
+        -ea \
+        -Xdebug \
+        -Xrunjdwp:transport=dt_socket,server=y,address=8888,suspend=n \
+        -Xms128M \
+        -Xmx1G \
+        -XX:SurvivorRatio=8 \
+        -XX:TargetSurvivorRatio=90 \
+        -XX:+AggressiveOpts \
+        -XX:+UseParNewGC \
+        -XX:+UseConcMarkSweepGC \
+        -XX:CMSInitiatingOccupancyFraction=1 \
+        -XX:+CMSParallelRemarkEnabled \
+        -XX:+HeapDumpOnOutOfMemoryError \
+        -Dcom.sun.management.jmxremote.port=8080 \
+        -Dcom.sun.management.jmxremote.ssl=false \
+        -Dcom.sun.management.jmxremote.authenticate=false"

data/test/config/log4j.properties

@@ -0,0 +1,38 @@
+# 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.
+
+# for production, you should probably set the root to INFO
+# and the pattern to %c instead of %l.  (%l is slower.)
+
+# output messages into a rolling log file as well as stdout
+log4j.rootLogger=DEBUG,stdout,R
+
+# stdout
+log4j.appender.stdout=org.apache.log4j.ConsoleAppender
+log4j.appender.stdout.layout=org.apache.log4j.SimpleLayout
+
+# rolling log file ("system.log
+log4j.appender.R=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.R.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.R.layout=org.apache.log4j.PatternLayout
+log4j.appender.R.layout.ConversionPattern=%5p [%t] %d{ISO8601} %F (line %L) %m%n
+# Edit the next line to point to your logs directory
+log4j.appender.R.File=data/logs/system.log
+
+# Application logging options
+#log4j.logger.com.facebook=DEBUG
+#log4j.logger.com.facebook.infrastructure.gms=DEBUG
+#log4j.logger.com.facebook.infrastructure.db=DEBUG

data/test/config/storage-conf.xml

@@ -0,0 +1,221 @@
+<!--
+ ~ 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                                                  -->
+    <!--======================================================================-->
+    <ClusterName>Test</ClusterName>
+
+    <!-- Tables and ColumnFamilies                                            
+         Think of a table as a namespace, not a relational table.
+         (ColumnFamilies are closer in meaning to those.)
+
+         There is an implicit table named 'system' for Cassandra internals.
+    -->
+    <Keyspaces>
+      <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" />  
+      </Keyspace>
+
+      <Keyspace Name="Multiblog">      
+        <KeysCachedFraction>0.01</KeysCachedFraction>
+        <ColumnFamily CompareWith="UTF8Type" Name="Blogs"/>
+        <ColumnFamily CompareWith="UTF8Type" Name="Comments"/>
+      </Keyspace>
+
+      <Keyspace Name="CassandraObject">
+        <KeysCachedFraction>0.01</KeysCachedFraction>
+        <ColumnFamily CompareWith="UTF8Type" Name="Customers" />
+        <ColumnFamily CompareWith="UTF8Type" CompareSubcolumnsWith="TimeUUIDType" ColumnType="Super" Name="CustomerRelationships" />
+        <ColumnFamily CompareWith="UTF8Type" CompareSubcolumnsWith="TimeUUIDType" ColumnType="Super" 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" />
+      </Keyspace>
+    </Keyspaces>
+
+    <!-- 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 and
+         org.apache.cassandra.dht.OrderPreservingPartitioner.
+         Range queries require using OrderPreservingPartitioner or a subclass.
+
+         Achtung!  Changing this parameter requires wiping your data directories,
+         since the partitioner can modify the sstable on-disk format.
+    -->
+    <Partitioner>org.apache.cassandra.dht.OrderPreservingPartitioner</Partitioner>
+
+    <!-- If you are using the OrderPreservingPartitioner 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>
+
+	
+    <!-- EndPointSnitch: Setting this to the class that implements IEndPointSnitch
+	     which will see if two endpoints are in the same data center or on the same rack.
+         Out of the box, Cassandra provides
+         org.apache.cassandra.locator.EndPointSnitch
+    -->
+    <EndPointSnitch>org.apache.cassandra.locator.EndPointSnitch</EndPointSnitch>
+
+    <!-- Strategy: Setting this to the class that implements IReplicaPlacementStrategy
+	     will change the way the node picker works.
+         Out of the box, Cassandra provides
+         org.apache.cassandra.locator.RackUnawareStrategy
+         org.apache.cassandra.locator.RackAwareStrategy 
+		 (place one replica in a different datacenter, and the
+         others on different racks in the same one.)
+    -->
+    <ReplicaPlacementStrategy>org.apache.cassandra.locator.RackUnawareStrategy</ReplicaPlacementStrategy>
+    
+    <!-- Number of replicas of the data-->
+    <ReplicationFactor>1</ReplicationFactor>
+
+    <!-- Directories: Specify where Cassandra should store different data on disk
+         Keep the data disks and the CommitLog disks separate for best performance
+    -->
+    <CommitLogDirectory>data/commitlog</CommitLogDirectory>
+    <DataFileDirectories>
+        <DataFileDirectory>data/data</DataFileDirectory>
+    </DataFileDirectories>
+    <CalloutLocation>data/callouts</CalloutLocation>
+    <BootstrapFileDirectory>data/bootstrap</BootstrapFileDirectory>
+    <StagingFileDirectory>data/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>
+    <!-- TCP port, for commands and data -->
+    <StoragePort>7000</StoragePort>
+    <!-- UDP port, for membership communications (gossip) -->
+    <ControlPort>7001</ControlPort>
+
+    <!-- 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>
+
+
+    <!--======================================================================-->
+    <!-- Memory, Disk, and Performance                                        -->
+    <!--======================================================================-->
+
+    <!-- Add column indexes to a row after its contents reach this size -->
+    <ColumnIndexSizeInKB>256</ColumnIndexSizeInKB>
+
+    <!--
+      The maximum amount of data to store in memory before flushing to
+      disk. Note: 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).
+    -->
+    <MemtableSizeInMB>32</MemtableSizeInMB>
+
+    <!--
+      The maximum number of columns in millions to store in memory
+      before flushing to disk.  This is also a per-memtable setting.
+      Use with MemtableSizeInMB to tune memory usage.
+    -->
+    <MemtableObjectCountInMillions>0.01</MemtableObjectCountInMillions>
+
+    <!-- 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.
+         You especially want more concurrentwrites if you are using
+         CommitLogSync + CommitLogSyncDelay. -->
+    <ConcurrentReads>8</ConcurrentReads>
+    <ConcurrentWrites>32</ConcurrentWrites>
+
+    <!-- Turn on CommitLogSync to improve durability.
+         When enabled, Cassandra won't ack writes until the commit log
+         has been synced to disk.  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.
+    -->
+    <CommitLogSync>false</CommitLogSync>
+    <!-- Delay (in microseconds) during which additional commit log
+         entries may be written before fsync.  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 100 to even 10000
+         if throughput matters more than latency.  (10000us = 10ms
+         write latency isn't even that bad by traditional db
+         standards.)
+    -->
+    <CommitLogSyncDelay>1000</CommitLogSyncDelay>
+         
+
+    <!-- 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/test/connection.rb

@@ -0,0 +1,25 @@
+ENV['CASSANDRA'] ||= "/usr/local/cassandra/bin/cassandra"
+
+if ENV['CASSANDRA_REQUIRED']
+  tmp = File.expand_path(File.join(File.dirname(__FILE__), '..', 'tmp'))
+  config = File.expand_path(File.join(File.dirname(__FILE__), 'config'))
+
+  $pid = fork {
+    Dir.chdir(tmp)
+    puts "CASSANDRA_INCLUDE=#{config}/cassandra.in.sh #{ENV['CASSANDRA']} -f"
+  }
+
+  # Wait for cassandra to boot
+  sleep 3
+end
+
+puts "Connecting..."
+CassandraObject::Base.establish_connection "CassandraObject"
+
+if defined?($pid)
+  at_exit do
+    puts "Shutting down Cassandra..."
+    Process.kill('INT', $pid)
+    Process.wait($pid)
+  end
+end

data/test/cursor_test.rb

@@ -0,0 +1,66 @@
+require 'test_helper'
+
+class CursorTest < CassandraObjectTestCase
+  
+  context "A Cursor working with a Super Column with mixed valid / invalid keys" do
+    setup do
+      @customer = Customer.create :first_name    => "Michael",
+                                  :last_name     => "Koziarski",
+                                  :date_of_birth => Date.parse("1980/08/15")
+                                  
+      @old = mock_invoice.tap {|i| @customer.invoices << i }
+      
+      @to_die = mock_invoice.tap {|i| @customer.invoices << i }
+      
+      @new = mock_invoice.tap {|i| @customer.invoices << i }
+      
+      assert_ordered [@new.key, @to_die.key, @old.key],
+                   association_keys_in_cassandra
+      
+      Invoice.remove(@to_die.key)
+    end
+    
+    context "starting at the beginning" do
+      setup do
+        @cursor = invoices_cursor(:reversed=>true)
+      end
+
+      should "leave values alone it doesn't scroll past" do
+        assert_equal [@new], @cursor.find(1)
+
+        assert_ordered [@new.key, @to_die.key, @old.key],
+                     association_keys_in_cassandra
+      end
+
+      should "clean up when it hits a missing record" do
+        assert_equal [@new, @old], @cursor.find(2)
+        assert_ordered [@new.key, @old.key],
+                     association_keys_in_cassandra
+      end
+    end
+    
+    context "starting at an offset" do
+      setup do
+        start_after = invoices_cursor(:reversed=>true).find(1).last_column_name
+        @cursor = invoices_cursor(:start_after=>start_after, :reversed=>true)
+      end
+      
+      should "clean up when it hits a missing record" do
+        assert_equal [@old.key], @cursor.find(1).map(&:key), "Wasn't expecting #{@new.key.inspect}"
+        assert_ordered [@new.key, @old.key],
+                     association_keys_in_cassandra
+      end
+    end
+    
+  end
+  
+  
+  def association_keys_in_cassandra
+    res = Customer.connection.get(Customer.associations[:invoices].column_family, @customer.key.to_s, "invoices", :reversed=>true)
+    res.values
+  end
+  
+  def invoices_cursor(options = {})
+    CassandraObject::Cursor.new(Invoice, Customer.associations[:invoices].column_family, @customer.key, "invoices", options)
+  end
+end

data/test/dirty_test.rb

@@ -0,0 +1,34 @@
+require 'test_helper'
+
+class DirtyTest < CassandraObjectTestCase
+  def setup
+    super
+
+    @customer = Customer.create :first_name    => "Michael",
+                                :last_name     => "Koziarski",
+                                :date_of_birth => Date.parse("1980/08/15")
+    @customer_key = @customer.key
+    assert @customer.valid?, @customer.errors.full_messages.to_sentence
+  end
+
+  test "a new object can be retrieved by key" do
+    assert_equal "Michael", @customer.first_name
+    assert !@customer.changed?
+    assert_equal [], @customer.changed
+    assert_equal({}, @customer.changes)
+
+    @customer.first_name = "Josh"
+    assert_equal "Josh", @customer.first_name
+
+    assert @customer.changed?
+    assert_equal ["first_name"], @customer.changed
+    assert_equal({"first_name" => ["Michael", "Josh"]}, @customer.changes)
+
+    assert @customer.first_name_changed?
+    assert_equal ["Michael", "Josh"], @customer.first_name_change
+    assert_equal "Michael", @customer.first_name_was
+
+    @customer.reset_first_name!
+    assert_equal "Michael", @customer.first_name
+  end
+end

data/test/fixture_models.rb

@@ -0,0 +1,90 @@
+module ReverseStorage
+  def encode(str)
+    str.reverse
+  end
+  module_function :encode
+
+  def decode(str)
+    str.reverse
+  end
+  module_function :decode
+end
+
+
+class Customer < CassandraObject::Base
+  attribute :first_name,     :type => :string
+  attribute :last_name,      :type => :string
+  attribute :date_of_birth,  :type => :date
+  attribute :preferences,    :type => :hash
+  attribute :custom_storage, :type => String, :converter=>ReverseStorage
+
+  validate :should_be_cool
+  validates_presence_of :last_name
+
+  after_create :set_after_create_called
+
+  key :uuid
+
+  index :last_name, :reversed=>true
+
+  association :invoices, :unique=>false, :inverse_of=>:customer, :reversed=>true
+  association :paid_invoices, :unique=>false, :class_name=>'Invoice'
+
+  def after_create_called?
+    @after_create_called
+  end
+
+  def set_after_create_called
+    @after_create_called = true
+  end
+
+  private
+
+  def should_be_cool
+    unless ["Michael", "Anika", "Evan", "Tom"].include?(first_name)
+      errors.add(:first_name, "must be that of a cool person")
+    end
+  end
+end
+
+class Invoice < CassandraObject::Base
+  attribute :number,     :type=>:integer
+  attribute :total,      :type=>:float
+  attribute :gst_number, :type=>:string
+
+  index :number, :unique=>true
+
+  association :customer, :unique=>true, :inverse_of=>:invoices
+
+  migrate 1 do |attrs|
+    attrs["total"] ||= (rand(2000) / 100.0).to_s
+  end
+
+  migrate 2 do |attrs|
+    attrs["gst_number"] = "66-666-666"
+  end
+
+  key :uuid
+end
+
+class Payment < CassandraObject::Base
+  attribute :reference_number, :type => :string
+  attribute :amount,           :type => :integer
+
+  key :natural, :attributes => :reference_number
+end
+
+MockRecord = Struct.new(:key)
+
+class Person < CassandraObject::Base
+  attribute :name, :type => :string
+  attribute :age,  :type => :integer
+end
+
+class Appointment < CassandraObject::Base
+  attribute :title,      :type => :string
+  attribute :start_time, :type => :time
+  attribute :end_time,   :type => :time_with_zone, :allow_nil => true
+
+  key :natural, :attributes => :title
+end