cassandra 0.8.2 → 0.9.0

data/CHANGELOG

@@ -1,3 +1,5 @@
+v0.9.0 cassandra 0.7 compat
+
 v0.8.2 Renamed :thrift_client_class option, UUID fix, 0.6 update, fixing cassanda install, much Mock fixes
 
 v0.8.1 Adding the ability to compose ThriftClient classes.

data/Manifest

@@ -5,9 +5,20 @@ README.rdoc
 Rakefile
 bin/cassandra_helper
 conf/cassandra.in.sh
+conf/cassandra.yaml
 conf/log4j.properties
 conf/storage-conf.xml
 lib/cassandra.rb
+lib/cassandra/0.6.rb
+lib/cassandra/0.6/cassandra.rb
+lib/cassandra/0.6/columns.rb
+lib/cassandra/0.6/protocol.rb
+lib/cassandra/0.7.rb
+lib/cassandra/0.7/cassandra.rb
+lib/cassandra/0.7/column_family.rb
+lib/cassandra/0.7/columns.rb
+lib/cassandra/0.7/keyspace.rb
+lib/cassandra/0.7/protocol.rb
 lib/cassandra/array.rb
 lib/cassandra/cassandra.rb
 lib/cassandra/columns.rb
@@ -18,14 +29,17 @@ lib/cassandra/helpers.rb
 lib/cassandra/long.rb
 lib/cassandra/mock.rb
 lib/cassandra/ordered_hash.rb
-lib/cassandra/protocol.rb
 lib/cassandra/time.rb
 test/cassandra_client_test.rb
 test/cassandra_mock_test.rb
 test/cassandra_test.rb
 test/comparable_types_test.rb
+test/eventmachine_test.rb
 test/ordered_hash_test.rb
 test/test_helper.rb
-vendor/gen-rb/cassandra.rb
-vendor/gen-rb/cassandra_constants.rb
-vendor/gen-rb/cassandra_types.rb
+vendor/0.6/gen-rb/cassandra.rb
+vendor/0.6/gen-rb/cassandra_constants.rb
+vendor/0.6/gen-rb/cassandra_types.rb
+vendor/0.7/gen-rb/cassandra.rb
+vendor/0.7/gen-rb/cassandra_constants.rb
+vendor/0.7/gen-rb/cassandra_types.rb

data/README.rdoc

@@ -4,7 +4,7 @@ A Ruby client for the Cassandra distributed database.
 
 == License
 
-Copyright 2009 Twitter, Inc. See included LICENSE file. Portions copyright 2004-2009 David Heinemeier Hansson, and used with permission.
+Copyright 2009, 2010 Twitter, Inc. See included LICENSE file. Portions copyright 2004-2009 David Heinemeier Hansson, and used with permission.
 
 == Features
 
@@ -30,14 +30,26 @@ WARNING: Don't use the test folder for your data, as it will get overwritten whe
 
 == Usage
 
-Now, start IRb and require the library:
+Now, start IRb and require the library, which defaults to version 0.6 of the Cassandra API:
 
   require 'cassandra'
 
+Alternatively, you can specify a version of the Cassandra API to use:
+
+  require 'cassandra/0.6'
+
+or
+
+  require 'cassandra/0.7'
+
 Connect to a server and keyspace:
 
   client = Cassandra.new('Twitter', '127.0.0.1:9160')
 
+Login on server if the keyspace require authentication:
+
+  client.login!('username','password')
+
 Insert into a column family. You can insert a `Cassandra::OrderedHash`, or a regular Hash, if order doesn't matter:
 
   client.insert(:Users, "5", {'screen_name' => "buttonscat"})

data/Rakefile

@@ -7,7 +7,7 @@ unless ENV['FROM_BIN_CASSANDRA_HELPER']
     p.project = "fauna"
     p.summary = "A Ruby client for the Cassandra distributed database."
     p.rubygems_version = ">= 0.8"
-    p.dependencies = ['thrift_client >=0.4.0', 'json', 'rake', 'simple_uuid >=0.1.0']
+    p.dependencies = ['thrift_client >=0.6.0', 'json', 'rake', 'simple_uuid >=0.1.0']
     p.ignore_pattern = /^(data|vendor\/cassandra|cassandra|vendor\/thrift)/
     p.rdoc_pattern = /^(lib|bin|tasks|ext)|^README|^CHANGELOG|^TODO|^LICENSE|^COPYING$/
     p.url = "http://blog.evanweaver.com/files/doc/fauna/cassandra/"
@@ -17,7 +17,7 @@ end
 
 CASSANDRA_HOME = ENV['CASSANDRA_HOME'] || "#{ENV['HOME']}/cassandra"
 DOWNLOAD_DIR = "/tmp"
-DIST_URL = "http://mirrors.kahuki.com/apache/cassandra/0.6.0/apache-cassandra-0.6.0-rc1-bin.tar.gz"
+DIST_URL = "http://www.takeyellow.com/apachemirror//cassandra/0.6.8/apache-cassandra-0.6.8-bin.tar.gz"
 DIST_FILE = DIST_URL.split('/').last
 
 directory CASSANDRA_HOME
@@ -30,6 +30,10 @@ task :cassandra => [:java, File.join(CASSANDRA_HOME, 'server'), File.join(CASSAN
     env << "CASSANDRA_INCLUDE=#{File.expand_path(Dir.pwd)}/conf/cassandra.in.sh "
     env << "CASSANDRA_HOME=#{CASSANDRA_HOME}/server "
     env << "CASSANDRA_CONF=#{File.expand_path(Dir.pwd)}/conf"
+  else
+    env << "CASSANDRA_INCLUDE=#{ENV['CASSANDRA_INCLUDE']} "
+    env << "CASSANDRA_HOME=#{ENV['CASSANDRA_HOME']} "
+    env << "CASSANDRA_CONF=#{ENV['CASSANDRA_CONF']}"
   end
 
   Dir.chdir(File.join(CASSANDRA_HOME, 'server')) do
@@ -65,7 +69,7 @@ namespace :data do
   desc "Reset test data"
   task :reset do
     puts "Resetting test data"
-    system("rm -rf #{File.join(CASSANDRA_HOME, 'test', 'data')}")
+    sh("rm -rf #{File.join(CASSANDRA_HOME, 'server', 'data')}")
   end
 end
 
@@ -75,5 +79,5 @@ task :thrift do
   system(
     "cd vendor &&
     rm -rf gen-rb &&
-    thrift -gen rb #{CASSANDRA_HOME}/server/interface/cassandra.thrift")
+    thrift -gen rb #{CASSANDRA_HOME}/interface/cassandra.thrift")
 end

data/cassandra.gemspec

@@ -2,22 +2,22 @@
 
 Gem::Specification.new do |s|
   s.name = %q{cassandra}
-  s.version = "0.8.2"
+  s.version = "0.9.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0.8") if s.respond_to? :required_rubygems_version=
   s.authors = ["Evan Weaver, Ryan King"]
-  s.date = %q{2010-04-13}
+  s.date = %q{2010-12-08}
   s.default_executable = %q{cassandra_helper}
   s.description = %q{A Ruby client for the Cassandra distributed database.}
   s.email = %q{}
   s.executables = ["cassandra_helper"]
-  s.extra_rdoc_files = ["CHANGELOG", "LICENSE", "README.rdoc", "bin/cassandra_helper", "lib/cassandra.rb", "lib/cassandra/array.rb", "lib/cassandra/cassandra.rb", "lib/cassandra/columns.rb", "lib/cassandra/comparable.rb", "lib/cassandra/constants.rb", "lib/cassandra/debug.rb", "lib/cassandra/helpers.rb", "lib/cassandra/long.rb", "lib/cassandra/mock.rb", "lib/cassandra/ordered_hash.rb", "lib/cassandra/protocol.rb", "lib/cassandra/time.rb"]
-  s.files = ["CHANGELOG", "LICENSE", "Manifest", "README.rdoc", "Rakefile", "bin/cassandra_helper", "conf/cassandra.in.sh", "conf/log4j.properties", "conf/storage-conf.xml", "lib/cassandra.rb", "lib/cassandra/array.rb", "lib/cassandra/cassandra.rb", "lib/cassandra/columns.rb", "lib/cassandra/comparable.rb", "lib/cassandra/constants.rb", "lib/cassandra/debug.rb", "lib/cassandra/helpers.rb", "lib/cassandra/long.rb", "lib/cassandra/mock.rb", "lib/cassandra/ordered_hash.rb", "lib/cassandra/protocol.rb", "lib/cassandra/time.rb", "test/cassandra_client_test.rb", "test/cassandra_mock_test.rb", "test/cassandra_test.rb", "test/comparable_types_test.rb", "test/ordered_hash_test.rb", "test/test_helper.rb", "vendor/gen-rb/cassandra.rb", "vendor/gen-rb/cassandra_constants.rb", "vendor/gen-rb/cassandra_types.rb", "cassandra.gemspec", "test/eventmachine_test.rb"]
+  s.extra_rdoc_files = ["CHANGELOG", "LICENSE", "README.rdoc", "bin/cassandra_helper", "lib/cassandra.rb", "lib/cassandra/0.6.rb", "lib/cassandra/0.6/cassandra.rb", "lib/cassandra/0.6/columns.rb", "lib/cassandra/0.6/protocol.rb", "lib/cassandra/0.7.rb", "lib/cassandra/0.7/cassandra.rb", "lib/cassandra/0.7/column_family.rb", "lib/cassandra/0.7/columns.rb", "lib/cassandra/0.7/keyspace.rb", "lib/cassandra/0.7/protocol.rb", "lib/cassandra/array.rb", "lib/cassandra/cassandra.rb", "lib/cassandra/columns.rb", "lib/cassandra/comparable.rb", "lib/cassandra/constants.rb", "lib/cassandra/debug.rb", "lib/cassandra/helpers.rb", "lib/cassandra/long.rb", "lib/cassandra/mock.rb", "lib/cassandra/ordered_hash.rb", "lib/cassandra/time.rb"]
+  s.files = ["CHANGELOG", "LICENSE", "Manifest", "README.rdoc", "Rakefile", "bin/cassandra_helper", "conf/cassandra.in.sh", "conf/cassandra.yaml", "conf/log4j.properties", "conf/storage-conf.xml", "lib/cassandra.rb", "lib/cassandra/0.6.rb", "lib/cassandra/0.6/cassandra.rb", "lib/cassandra/0.6/columns.rb", "lib/cassandra/0.6/protocol.rb", "lib/cassandra/0.7.rb", "lib/cassandra/0.7/cassandra.rb", "lib/cassandra/0.7/column_family.rb", "lib/cassandra/0.7/columns.rb", "lib/cassandra/0.7/keyspace.rb", "lib/cassandra/0.7/protocol.rb", "lib/cassandra/array.rb", "lib/cassandra/cassandra.rb", "lib/cassandra/columns.rb", "lib/cassandra/comparable.rb", "lib/cassandra/constants.rb", "lib/cassandra/debug.rb", "lib/cassandra/helpers.rb", "lib/cassandra/long.rb", "lib/cassandra/mock.rb", "lib/cassandra/ordered_hash.rb", "lib/cassandra/time.rb", "test/cassandra_client_test.rb", "test/cassandra_mock_test.rb", "test/cassandra_test.rb", "test/comparable_types_test.rb", "test/eventmachine_test.rb", "test/ordered_hash_test.rb", "test/test_helper.rb", "vendor/0.6/gen-rb/cassandra.rb", "vendor/0.6/gen-rb/cassandra_constants.rb", "vendor/0.6/gen-rb/cassandra_types.rb", "vendor/0.7/gen-rb/cassandra.rb", "vendor/0.7/gen-rb/cassandra_constants.rb", "vendor/0.7/gen-rb/cassandra_types.rb", "cassandra.gemspec"]
   s.homepage = %q{http://blog.evanweaver.com/files/doc/fauna/cassandra/}
   s.rdoc_options = ["--line-numbers", "--inline-source", "--title", "Cassandra", "--main", "README.rdoc"]
   s.require_paths = ["lib"]
   s.rubyforge_project = %q{fauna}
-  s.rubygems_version = %q{1.3.6}
+  s.rubygems_version = %q{1.3.7}
   s.summary = %q{A Ruby client for the Cassandra distributed database.}
   s.test_files = ["test/cassandra_client_test.rb", "test/cassandra_mock_test.rb", "test/cassandra_test.rb", "test/comparable_types_test.rb", "test/eventmachine_test.rb", "test/ordered_hash_test.rb", "test/test_helper.rb"]
 
@@ -25,19 +25,19 @@ Gem::Specification.new do |s|
     current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
     s.specification_version = 3
 
-    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
-      s.add_runtime_dependency(%q<thrift_client>, [">= 0.4.0"])
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<thrift_client>, [">= 0.6.0"])
       s.add_runtime_dependency(%q<json>, [">= 0"])
       s.add_runtime_dependency(%q<rake>, [">= 0"])
       s.add_runtime_dependency(%q<simple_uuid>, [">= 0.1.0"])
     else
-      s.add_dependency(%q<thrift_client>, [">= 0.4.0"])
+      s.add_dependency(%q<thrift_client>, [">= 0.6.0"])
       s.add_dependency(%q<json>, [">= 0"])
       s.add_dependency(%q<rake>, [">= 0"])
       s.add_dependency(%q<simple_uuid>, [">= 0.1.0"])
     end
   else
-    s.add_dependency(%q<thrift_client>, [">= 0.4.0"])
+    s.add_dependency(%q<thrift_client>, [">= 0.6.0"])
     s.add_dependency(%q<json>, [">= 0"])
     s.add_dependency(%q<rake>, [">= 0"])
     s.add_dependency(%q<simple_uuid>, [">= 0.1.0"])

data/conf/cassandra.yaml

@@ -0,0 +1,113 @@
+# Cassandra YAML generated from previous config
+# Configuration wiki: http://wiki.apache.org/cassandra/StorageConfiguration
+
+cluster_name:                        Test
+
+listen_address:                      localhost
+storage_port:                        7000
+rpc_port:                            9160
+seeds:
+  - 127.0.0.1
+data_file_directories:
+  - data/cassandra/data
+commitlog_directory:                 data/cassandra/commitlog
+auto_bootstrap:                      false
+partitioner:                         org.apache.cassandra.dht.RandomPartitioner
+authenticator:                       org.apache.cassandra.auth.AllowAllAuthenticator
+
+binary_memtable_throughput_in_mb:    256
+column_index_size_in_kb:             64
+commitlog_rotation_threshold_in_mb:  128
+commitlog_sync:                      periodic
+commitlog_sync_period_in_ms:         10000
+concurrent_reads:                    8
+concurrent_writes:                   32
+disk_access_mode:                    auto
+dynamic_snitch:                      false
+hinted_handoff_enabled:              true
+in_memory_compaction_limit_in_mb:    256
+memtable_flush_after_mins:           60
+memtable_operations_in_millions:     0.3
+memtable_throughput_in_mb:           64
+phi_convict_threshold:               8
+rpc_timeout_in_ms:                   5000
+sliced_buffer_size_in_kb:            64
+snapshot_before_compaction:          false
+thrift_framed_transport_size_in_mb:  15
+thrift_max_message_length_in_mb:     16
+
+
+keyspaces:
+
+    - name: Twitter
+      replication_factor: 1
+      replica_placement_strategy: org.apache.cassandra.locator.RackUnawareStrategy
+      column_families:
+      - name:                    Users
+        compare_with:            UTF8Type
+      - name:                    UserAudits
+        compare_with:            UTF8Type
+      - name:                    UserRelationships
+        compare_with:            UTF8Type
+        column_type:             Super
+        compare_subcolumns_with: TimeUUIDType
+      - name:                    Usernames
+        compare_with:            UTF8Type
+      - name:                    Statuses
+        compare_with:            UTF8Type
+      - name:                    StatusAudits
+        compare_with:            UTF8Type
+      - name:                    StatusRelationships
+        compare_with:            UTF8Type
+        column_type:             Super
+        compare_subcolumns_with: TimeUUIDType
+      - name:                    Index
+        compare_with:            UTF8Type
+        column_type:             Super
+      - name:                    TimelinishThings
+        compare_with:            BytesType
+        column_type:             Standard
+
+    - name: Multiblog
+      replication_factor: 1
+      replica_placement_strategy: org.apache.cassandra.locator.RackUnawareStrategy
+      column_families:
+      - name:                    Blogs
+        compare_with:            TimeUUIDType
+      - name:                    Comments
+        compare_with:            TimeUUIDType
+
+    - name: MultiblogLong
+      replication_factor: 1
+      replica_placement_strategy: org.apache.cassandra.locator.RackUnawareStrategy
+      column_families:
+      - name:                    Blogs
+        compare_with:            LongType
+      - name:                    Comments
+        compare_with:            LongType
+
+    - name: CassandraObject
+      replication_factor: 1
+      replica_placement_strategy: org.apache.cassandra.locator.RackUnawareStrategy
+      column_families:
+      - name:                    Customers
+        compare_with:            UTF8Type
+      - name:                    CustomerRelationships
+        compare_with:            UTF8Type
+        column_type:             Super
+        compare_subcolumns_with: TimeUUIDType
+      - name:                    CustomersByLastName
+        compare_with:            TimeUUIDType
+      - name:                    Invoices
+        compare_with:            UTF8Type
+      - name:                    InvoiceRelationships
+        compare_with:            UTF8Type
+        column_type:             Super
+        compare_subcolumns_with: TimeUUIDType
+      - name:                    InvoicesByNumber
+        compare_with:            UTF8Type
+      - name:                    Payments
+        compare_with:            UTF8Type
+      - name:                    Appointments
+        compare_with:            UTF8Type
+  

data/conf/storage-conf.xml

@@ -95,12 +95,13 @@
       <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="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>

data/lib/cassandra.rb

@@ -1,11 +1,22 @@
 require 'rubygems'
+gem 'thrift', '~> 0.5.0'
+require 'thrift'
+gem 'thrift_client', '~> 0.6.0'
 require 'thrift_client'
-require 'json' unless defined?(JSON)
+gem 'simple_uuid' , '~> 0.1.0'
 require 'simple_uuid'
+
+require 'json' unless defined?(JSON)
+
 here = File.expand_path(File.dirname(__FILE__))
 
-$LOAD_PATH << "#{here}/../vendor/gen-rb"
-require "#{here}/../vendor/gen-rb/cassandra"
+class Cassandra ; end
+unless Cassandra.respond_to?(:VERSION)
+  require "#{here}/cassandra/0.6"
+end
+
+$LOAD_PATH << "#{here}/../vendor/#{Cassandra.VERSION}/gen-rb"
+require "#{here}/../vendor/#{Cassandra.VERSION}/gen-rb/cassandra"
 
 $LOAD_PATH << "#{here}"
 
@@ -16,7 +27,13 @@ require 'cassandra/comparable'
 require 'cassandra/long'
 require 'cassandra/ordered_hash'
 require 'cassandra/columns'
-require 'cassandra/protocol'
-require 'cassandra/cassandra'
+require "cassandra/#{Cassandra.VERSION}/columns"
+require "cassandra/#{Cassandra.VERSION}/protocol"
+require "cassandra/cassandra"
+require "cassandra/#{Cassandra.VERSION}/cassandra"
+unless Cassandra.VERSION.eql?("0.6")
+  require "cassandra/#{Cassandra.VERSION}/column_family"
+  require "cassandra/#{Cassandra.VERSION}/keyspace"
+end
 require 'cassandra/constants'
 require 'cassandra/debug' if ENV['DEBUG']

data/lib/cassandra/0.6.rb

@@ -0,0 +1,7 @@
+class Cassandra
+  def self.VERSION
+    "0.6"
+  end
+end
+
+require "#{File.expand_path(File.dirname(__FILE__))}/../cassandra"

data/lib/cassandra/0.6/cassandra.rb

@@ -0,0 +1,63 @@
+class Cassandra
+  def self.DEFAULT_TRANSPORT_WRAPPER
+    Thrift::BufferedTransport
+  end
+  
+  ## Delete
+
+  # Remove all rows in the column family you request. Supports options
+  # <tt>:consistency</tt> and <tt>:timestamp</tt>.
+  # FIXME May not currently delete all records without multiple calls. Waiting
+  # for ranged remove support in Cassandra.
+  def clear_column_family!(column_family, options = {})
+    each_key(column_family) do |key|
+      remove(column_family, key, options)
+    end
+  end
+
+  # Remove all rows in the keyspace. Supports options <tt>:consistency</tt> and
+  # <tt>:timestamp</tt>.
+  # FIXME May not currently delete all records without multiple calls. Waiting
+  # for ranged remove support in Cassandra.
+  def clear_keyspace!(options = {})
+    schema.keys.each { |column_family| clear_column_family!(column_family, options) }
+  end
+
+  protected
+
+  def schema(load=true)
+    if !load && !@schema
+      []
+    else
+      @schema ||= client.describe_keyspace(@keyspace)
+    end
+  end
+
+  def client
+    reconnect! if @client.nil?
+    @client
+  end
+
+  def reconnect!
+    @servers = all_nodes
+    @client = new_client
+    check_keyspace
+  end
+
+  def check_keyspace
+    unless (keyspaces = client.get_string_list_property("keyspaces")).include?(@keyspace)
+      raise AccessError, "Keyspace #{@keyspace.inspect} not found. Available: #{keyspaces.inspect}"
+    end
+  end
+
+  def all_nodes
+    if @auto_discover_nodes
+      ips = ::JSON.parse(new_client.get_string_property('token map')).values
+      port = @servers.first.split(':').last
+      ips.map{|ip| "#{ip}:#{port}" }
+    else
+      @servers
+    end
+  end
+
+end

data/lib/cassandra/0.6/columns.rb

@@ -0,0 +1,35 @@
+class Cassandra
+  # A bunch of crap, mostly related to introspecting on column types
+  module Columns #:nodoc:
+    private
+
+    def _standard_insert_mutation(column_family, column_name, value, timestamp, _=nil)
+      CassandraThrift::Mutation.new(
+        :column_or_supercolumn => CassandraThrift::ColumnOrSuperColumn.new(
+          :column => CassandraThrift::Column.new(
+            :name      => column_name_class(column_family).new(column_name).to_s,
+            :value     => value,
+            :timestamp => timestamp
+          )
+        )
+      )
+    end
+
+    def _super_insert_mutation(column_family, super_column_name, sub_columns, timestamp, _=nil)
+      CassandraThrift::Mutation.new(:column_or_supercolumn => 
+        CassandraThrift::ColumnOrSuperColumn.new(
+          :super_column => CassandraThrift::SuperColumn.new(
+            :name => column_name_class(column_family).new(super_column_name).to_s,
+            :columns => sub_columns.collect { |sub_column_name, sub_column_value|
+              CassandraThrift::Column.new(
+                :name      => sub_column_name_class(column_family).new(sub_column_name).to_s,
+                :value     => sub_column_value.to_s,
+                :timestamp => timestamp
+              )
+            }
+          )
+        )
+      )
+    end
+  end
+end