Class: Cassandra

Inherits:
Object
  • Object
show all
Includes:
Columns, Helpers, Protocol
Defined in:
lib/cassandra/cassandra.rb,
lib/cassandra.rb,
lib/cassandra/0.6.rb,
lib/cassandra/0.7.rb,
lib/cassandra/0.8.rb,
lib/cassandra/long.rb,
lib/cassandra/columns.rb,
lib/cassandra/helpers.rb,
lib/cassandra/version.rb,
lib/cassandra/keyspace.rb,
lib/cassandra/protocol.rb,
lib/cassandra/constants.rb,
lib/cassandra/comparable.rb,
lib/cassandra/0.6/columns.rb,
lib/cassandra/0.7/columns.rb,
lib/cassandra/0.8/columns.rb,
lib/cassandra/0.6/protocol.rb,
lib/cassandra/0.7/protocol.rb,
lib/cassandra/0.8/protocol.rb,
lib/cassandra/ordered_hash.rb,
lib/cassandra/0.6/cassandra.rb,
lib/cassandra/0.7/cassandra.rb,
lib/cassandra/0.8/cassandra.rb,
lib/cassandra/column_family.rb,
lib/cassandra/mock.rb

Overview

OrderedHash is namespaced to prevent conflicts with other implementations

Defined Under Namespace

Modules: Columns, Consistency, Constants, Helpers, Protocol Classes: AccessError, ColumnFamily, Comparable, Keyspace, Long, Mock, OrderedHash, OrderedHashInt

Constant Summary collapse

VERSION =
'0.12.6'
WRITE_DEFAULTS =
{
  :count => 1000,
  :timestamp => nil,
  :consistency => Consistency::ONE,
  :ttl => nil
}
READ_DEFAULTS =
{
  :count => 100,
  :start => nil,
  :finish => nil,
  :reversed => false,
  :consistency => Consistency::ONE
}
THRIFT_DEFAULTS =
{
  :transport_wrapper    => Thrift::FramedTransport,
  :thrift_client_class  => ThriftClient
}

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Methods included from Helpers

#extract_and_validate_params, #s_map

Constructor Details

#initialize(keyspace, servers = "127.0.0.1:9160", thrift_client_options = {}) ⇒ Cassandra

Create a new Cassandra instance and open the connection.


74
75
76
77
78
79
80
81
82
83
84
# File 'lib/cassandra/cassandra.rb', line 74

def initialize(keyspace, servers = "127.0.0.1:9160", thrift_client_options = {})
  @is_super = {}
  @column_name_class = {}
  @sub_column_name_class = {}
  @auto_discover_nodes = true
  thrift_client_options[:transport_wrapper] ||= Cassandra.DEFAULT_TRANSPORT_WRAPPER
  @thrift_client_options = THRIFT_DEFAULTS.merge(thrift_client_options)
  @thrift_client_class = @thrift_client_options[:thrift_client_class]
  @keyspace = keyspace
  @servers = Array(servers)
end

Instance Attribute Details

#auth_requestObject (readonly)

Returns the value of attribute auth_request


67
68
69
# File 'lib/cassandra/cassandra.rb', line 67

def auth_request
  @auth_request
end

#keyspaceObject

Returns the value of attribute keyspace


67
68
69
# File 'lib/cassandra/cassandra.rb', line 67

def keyspace
  @keyspace
end

#serversObject (readonly)

Returns the value of attribute servers


67
68
69
# File 'lib/cassandra/cassandra.rb', line 67

def servers
  @servers
end

#thrift_client_classObject (readonly)

Returns the value of attribute thrift_client_class


67
68
69
# File 'lib/cassandra/cassandra.rb', line 67

def thrift_client_class
  @thrift_client_class
end

#thrift_client_optionsObject (readonly)

Returns the value of attribute thrift_client_options


67
68
69
# File 'lib/cassandra/cassandra.rb', line 67

def thrift_client_options
  @thrift_client_options
end

Class Method Details

.DEFAULT_TRANSPORT_WRAPPERObject


69
70
71
# File 'lib/cassandra/cassandra.rb', line 69

def self.DEFAULT_TRANSPORT_WRAPPER
  Thrift::FramedTransport
end

.VERSIONObject


2
3
4
# File 'lib/cassandra/0.6.rb', line 2

def self.VERSION
  "0.6"
end

Instance Method Details

#add(column_family, key, value, *columns_and_options) ⇒ Object

Add a value to the counter in cf:key:super column:column


6
7
8
9
# File 'lib/cassandra/0.8/cassandra.rb', line 6

def add(column_family, key, value, *columns_and_options)
  column_family, column, sub_column, options = extract_and_validate_params(column_family, key, columns_and_options, WRITE_DEFAULTS)
  _add(column_family, key, column, sub_column, value, options[:consistency])
end

#add_column_family(cf_def) ⇒ Object

Creates a new column family from the passed in Cassandra::ColumnFamily instance, and returns the schema id.


266
267
268
269
270
271
272
273
274
275
276
# File 'lib/cassandra/cassandra.rb', line 266

def add_column_family(cf_def)
  return false if Cassandra.VERSION.to_f < 0.7

  begin
    res = client.system_add_column_family(cf_def)
  rescue CassandraThrift::TimedOutException => te
    puts "Timed out: #{te.inspect}"
  end
  @schema = nil
  res
end

#add_keyspace(ks_def) ⇒ Object

Add keyspace using the passed in keyspace definition.

Returns the new schema id.


333
334
335
336
337
338
339
340
341
342
343
344
345
# File 'lib/cassandra/cassandra.rb', line 333

def add_keyspace(ks_def)
  return false if Cassandra.VERSION.to_f < 0.7

  begin
    res = client.system_add_keyspace(ks_def)
  rescue CassandraThrift::TimedOutException => toe
    puts "Timed out: #{toe.inspect}"
  rescue Thrift::TransportException => te
    puts "Timed out: #{te.inspect}"
  end
  @keyspaces = nil
  res
end

#batch(options = {}) ⇒ Object

Open a batch operation and yield self. Inserts and deletes will be queued until the block closes, and then sent atomically to the server. Supports the :consistency option, which overrides the consistency set in the individual commands.


847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
# File 'lib/cassandra/cassandra.rb', line 847

def batch(options = {})
  _, _, _, options =
    extract_and_validate_params(schema.cf_defs.first.name, "", [options], WRITE_DEFAULTS)

    @batch = []
    yield(self)
    compacted_map,seen_clevels = compact_mutations!
    clevel = if options[:consistency] != nil # Override any clevel from individual mutations if 
               options[:consistency]
             elsif seen_clevels.length > 1 # Cannot choose which CLevel to use if there are several ones
               raise "Multiple consistency levels used in the batch, and no override...cannot pick one" 
             else # if no consistency override has been provided but all the clevels in the batch are the same: use that one
               seen_clevels.first
             end

    _mutate(compacted_map,clevel)
ensure
  @batch = nil
end

#clear_keyspace!(options = {}) ⇒ Object

Remove all rows in the keyspace. Supports options :consistency and :timestamp. FIXME May not currently delete all records without multiple calls. Waiting for ranged remove support in Cassandra.


256
257
258
259
260
# File 'lib/cassandra/cassandra.rb', line 256

def clear_keyspace!
  return false if Cassandra.VERSION.to_f < 0.7

  schema.cf_defs.each { |cfdef| truncate!(cfdef.name) }
end

#cluster_nameObject

Returns the string name specified for the cluster.

Please note that this only works on version 0.7.0 and higher.


205
206
207
208
209
# File 'lib/cassandra/cassandra.rb', line 205

def cluster_name
  return false if Cassandra.VERSION.to_f < 0.7

  @cluster_name ||= client.describe_cluster_name()
end

#column_familiesObject

Return a hash of column_family definitions indexed by their names


160
161
162
163
164
# File 'lib/cassandra/cassandra.rb', line 160

def column_families
  return false if Cassandra.VERSION.to_f < 0.7

  schema.cf_defs.inject(Hash.new){|memo, cf_def| memo[cf_def.name] = cf_def; memo;}
end

#count_columns(column_family, key, *columns_and_options) ⇒ Object

Count the columns for the provided parameters.

  • column_family - The column_family that you are inserting into.

  • key - The row key to insert.

  • columns - Either a single super_column or a list of columns.

  • sub_columns - The list of sub_columns to select.

  • options - Valid options are:

    • :start - The column name to start from.

    • :stop - The column name to stop at.

    • :count - The maximum count of columns to return. (By default cassandra will count up to 100 columns)

    • :consistency - Uses the default read consistency if none specified.


516
517
518
519
520
# File 'lib/cassandra/cassandra.rb', line 516

def count_columns(column_family, key, *columns_and_options)
  column_family, super_column, _, options = 
    extract_and_validate_params(column_family, key, columns_and_options, READ_DEFAULTS)      
  _count_columns(column_family, key, super_column, options[:start], options[:stop], options[:count], options[:consistency])
end

#count_range(column_family, options = {}) ⇒ Object

Count all rows in the column_family you request.

This method just calls Cassandra#get_range_keys and returns the number of records returned.

See Cassandra#get_range for options.


796
797
798
# File 'lib/cassandra/cassandra.rb', line 796

def count_range(column_family, options = {})
  get_range_keys(column_family, options).length
end

#create_index(keyspace, column_family, column_name, validation_class) ⇒ Object

Create secondary index.

  • keyspace

  • column_family

  • column_name

  • validation_class


875
876
877
878
879
880
881
882
883
884
885
886
887
888
# File 'lib/cassandra/cassandra.rb', line 875

def create_index(keyspace, column_family, column_name, validation_class)
  return false if Cassandra.VERSION.to_f < 0.7

  cf_def = client.describe_keyspace(keyspace).cf_defs.find{|x| x.name == column_family}
  if !cf_def.nil? and !cf_def..find{|x| x.name == column_name}
    c_def  = CassandraThrift::ColumnDef.new do |cd|
      cd.name             = column_name
      cd.validation_class = "org.apache.cassandra.db.marshal."+validation_class
      cd.index_type       = CassandraThrift::IndexType::KEYS
    end
    cf_def..push(c_def)
    update_column_family(cf_def)
  end
end

#create_index_clause(index_expressions, start = "", count = 100) ⇒ Object Also known as: create_idx_clause

This method takes an array if CassandraThrift::IndexExpression objects and creates a CassandraThrift::IndexClause for use in the Cassandra#get_index_slices

  • index_expressions - Array of CassandraThrift::IndexExpressions.

  • start - The starting row key.

  • count - The count of items to be returned


945
946
947
948
949
950
951
952
# File 'lib/cassandra/cassandra.rb', line 945

def create_index_clause(index_expressions, start = "", count = 100)
  return false if Cassandra.VERSION.to_f < 0.7

  CassandraThrift::IndexClause.new(
    :start_key    => start,
    :expressions  => index_expressions,
    :count        => count)
end

#create_index_expression(column_name, value, comparison) ⇒ Object Also known as: create_idx_expr

This method is mostly used internally by get_index_slices to create a CassandraThrift::IndexExpression for the given options.

  • column_name - Column to be compared

  • value - Value to compare against

  • comparison - Type of comparison to do.


915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
# File 'lib/cassandra/cassandra.rb', line 915

def create_index_expression(column_name, value, comparison)
  return false if Cassandra.VERSION.to_f < 0.7

  CassandraThrift::IndexExpression.new(
    :column_name => column_name,
    :value => value,
    :op => (case comparison
              when nil, "EQ", "eq", "=="
                CassandraThrift::IndexOperator::EQ
              when "GTE", "gte", ">="
                CassandraThrift::IndexOperator::GTE
              when "GT", "gt", ">"
                CassandraThrift::IndexOperator::GT
              when "LTE", "lte", "<="
                CassandraThrift::IndexOperator::LTE
              when "LT", "lt", "<"
                CassandraThrift::IndexOperator::LT
            end ))
end

#default_read_consistency=(value) ⇒ Object

The initial default consistency is set to ONE, but you can use this method to override the normal default with your specified value. Use this if you do not want to specify a read consistency for each query.


419
420
421
# File 'lib/cassandra/cassandra.rb', line 419

def default_read_consistency=(value)
  READ_DEFAULTS[:consistency] = value
end

#default_write_consistency=(value) ⇒ Object

The initial default consistency is set to ONE, but you can use this method to override the normal default with your specified value. Use this if you do not want to specify a write consistency for each insert statement.


410
411
412
# File 'lib/cassandra/cassandra.rb', line 410

def default_write_consistency=(value)
  WRITE_DEFAULTS[:consistency] = value
end

#disable_node_auto_discovery!Object

This is primarily helpful when the cassandra cluster is communicating internally on a different ip address than what you are using to connect. A prime example of this would be when using EC2 to host a cluster. Typically, the cluster would be communicating over the local ip addresses issued by Amazon, but any clients connecting from outside EC2 would need to use the public ip.


98
99
100
# File 'lib/cassandra/cassandra.rb', line 98

def disable_node_auto_discovery!
  @auto_discover_nodes = false
end

#disconnect!Object

Disconnect the current client connection.


105
106
107
108
109
110
# File 'lib/cassandra/cassandra.rb', line 105

def disconnect!
  if @client
    @client.disconnect!
    @client = nil
  end
end

#drop_column_family(column_family) ⇒ Object

Delete the specified column family. Return the new schema id.

  • column_family - The column_family name to drop.


283
284
285
286
287
288
289
290
291
292
293
# File 'lib/cassandra/cassandra.rb', line 283

def drop_column_family(column_family)
  return false if Cassandra.VERSION.to_f < 0.7

  begin
    res = client.system_drop_column_family(column_family)
  rescue CassandraThrift::TimedOutException => te
    puts "Timed out: #{te.inspect}"
  end
  @schema = nil
  res
end

#drop_index(keyspace, column_family, column_name) ⇒ Object

Delete secondary index.

  • keyspace

  • column_family

  • column_name


897
898
899
900
901
902
903
904
905
# File 'lib/cassandra/cassandra.rb', line 897

def drop_index(keyspace, column_family, column_name)
  return false if Cassandra.VERSION.to_f < 0.7

  cf_def = client.describe_keyspace(keyspace).cf_defs.find{|x| x.name == column_family}
  if !cf_def.nil? and cf_def..find{|x| x.name == column_name}
    cf_def..delete_if{|x| x.name == column_name}
    update_column_family(cf_def)
  end
end

#drop_keyspace(keyspace) ⇒ Object

Deletes keyspace using the passed in keyspace name.

Returns the new schema id.


352
353
354
355
356
357
358
359
360
361
362
363
364
365
# File 'lib/cassandra/cassandra.rb', line 352

def drop_keyspace(keyspace)
  return false if Cassandra.VERSION.to_f < 0.7

  begin
    res = client.system_drop_keyspace(keyspace)
  rescue CassandraThrift::TimedOutException => toe
    puts "Timed out: #{toe.inspect}"
  rescue Thrift::TransportException => te
    puts "Timed out: #{te.inspect}"
  end
  keyspace = "system" if keyspace.eql?(@keyspace)
  @keyspaces = nil
  res
end

#each(column_family, options = {}) ⇒ Object

Iterate through each row in the given column family

This method just calls Cassandra#get_range and yields the key and columns.

See Cassandra#get_range for options.


834
835
836
837
838
# File 'lib/cassandra/cassandra.rb', line 834

def each(column_family, options = {})
  get_range_batch(column_family, options) do |key, columns|
    yield key, columns
  end
end

#each_key(column_family, options = {}) ⇒ Object

Iterate through each key within the given parameters. This function can be used to iterate over each key in the given column family.

This method just calls Cassandra#get_range and yields each row key.

See Cassandra#get_range for options.


820
821
822
823
824
# File 'lib/cassandra/cassandra.rb', line 820

def each_key(column_family, options = {})
  get_range_batch(column_family, options) do |key, columns|
    yield key
  end
end

#exists?(column_family, key, *columns_and_options) ⇒ Boolean

Return true if the column_family:key::[sub_column] path you request exists.

If passed in only a row key it will query for any columns (limiting to 1) for that row key. If a column is passed in it will query for that specific column/super column.

This method will return true or false.

  • column_family - The column_family that you are inserting into.

  • key - The row key to insert.

  • columns - Either a single super_column or a list of columns.

  • sub_columns - The list of sub_columns to select.

  • options - Valid options are:

    • :consistency - Uses the default read consistency if none specified.

Returns:

  • (Boolean)

652
653
654
655
656
657
658
659
660
661
662
# File 'lib/cassandra/cassandra.rb', line 652

def exists?(column_family, key, *columns_and_options)
  column_family, column, sub_column, options = 
    extract_and_validate_params(column_family, key, columns_and_options, READ_DEFAULTS)
  result = if column
             _multiget(column_family, [key], column, sub_column, '', '', 1, false, options[:consistency])[key]
           else
             _multiget(column_family, [key], nil, nil, '', '', 1, false, options[:consistency])[key]
           end

  ![{}, nil].include?(result)
end

#get(column_family, key, *columns_and_options) ⇒ Object

Return a hash (actually, a Cassandra::OrderedHash) or a single value representing the element at the column_family:key::[sub_column] path you request.

  • column_family - The column_family that you are inserting into.

  • key - The row key to insert.

  • columns - Either a single super_column or a list of columns.

  • sub_columns - The list of sub_columns to select.

  • options - Valid options are:

    • :count - The number of columns requested to be returned.

    • :start - The starting value for selecting a range of columns.

    • :finish - The final value for selecting a range of columns.

    • :reversed - If set to true the results will be returned in

      reverse order.
      
    • :consistency - Uses the default read consistency if none specified.


598
599
600
# File 'lib/cassandra/cassandra.rb', line 598

def get(column_family, key, *columns_and_options)
  multi_get(column_family, [key], *columns_and_options)[key]
end

#get_columns(column_family, key, *columns_and_options) ⇒ Object

Return a hash of column value pairs for the path you request.

  • column_family - The column_family that you are inserting into.

  • key - The row key to insert.

  • columns - Either a single super_column or a list of columns.

  • sub_columns - The list of sub_columns to select.

  • options - Valid options are:

    • :consistency - Uses the default read consistency if none specified.


550
551
552
553
554
# File 'lib/cassandra/cassandra.rb', line 550

def get_columns(column_family, key, *columns_and_options)
  column_family, columns, sub_columns, options = 
    extract_and_validate_params(column_family, key, columns_and_options, READ_DEFAULTS)      
  _get_columns(column_family, key, columns, sub_columns, options[:consistency])
end

#get_indexed_slices(column_family, index_clause, *columns_and_options) ⇒ Object

This method is used to query a secondary index with a set of provided search parameters

Please note that you can either specify a CassandraThrift::IndexClause or an array of hashes with the format as below.

  • column_family - The Column Family this operation will be run on.

  • index_clause - This can either be a CassandraThrift::IndexClause or an array of hashes with the following keys:

    • :column_name - Column to be compared

    • :value - Value to compare against

    • :comparison - Type of comparison to do.

  • options

    • :key_count - Set maximum number of rows to return. (Only works if CassandraThrift::IndexClause is not passed in.)

    • :key_start - Set starting row key for search. (Only works if CassandraThrift::IndexClause is not passed in.)

    • :consistency

TODO: Supercolumn support.


974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
# File 'lib/cassandra/cassandra.rb', line 974

def get_indexed_slices(column_family, index_clause, *columns_and_options)
  return false if Cassandra.VERSION.to_f < 0.7

  column_family, columns, _, options =
    extract_and_validate_params(column_family, [], columns_and_options, READ_DEFAULTS.merge(:key_count => 100, :key_start => ""))

  if index_clause.class != CassandraThrift::IndexClause
    index_expressions = index_clause.collect do |expression|
      create_index_expression(expression[:column_name], expression[:value], expression[:comparison])
    end

    index_clause = create_index_clause(index_expressions, options[:key_start], options[:key_count])
  end

  key_slices = _get_indexed_slices(column_family, index_clause, columns, options[:count], options[:start],
    options[:finish], options[:reversed], options[:consistency])

  key_slices.inject({}){|h, key_slice| h[key_slice.key] = key_slice.columns; h}
end

#get_range(column_family, options = {}, &blk) ⇒ Object

Return an Cassandra::OrderedHash containing the columns specified for the given range of keys in the column_family you request.

This method is just a convenience wrapper around Cassandra#get_range_single and Cassandra#get_range_batch. If :key_size, :batch_size, or a block is passed in Cassandra#get_range_batch will be called. Otherwise Cassandra#get_range_single will be used.

The start_key and finish_key parameters are only useful for iterating of all records as is done in the Cassandra#each and Cassandra#each_key methods if you are using the RandomPartitioner.

If the table is partitioned with OrderPreservingPartitioner you may use the start_key and finish_key params to select all records with the same prefix value.

If a block is passed in we will yield the row key and columns for each record returned.

Please note that Cassandra returns a row for each row that has existed in the system since gc_grace_seconds. This is because deleted row keys are marked as deleted, but left in the system until the cluster has had resonable time to replicate the deletion. This function attempts to suppress deleted rows (actually any row returned without columns is suppressed).

Please note that when enabling the :reversed option, :start and :finish should be swapped (e.g. reversal happens before selecting the range).

  • column_family - The column_family that you are inserting into.

  • options - Valid options are:

    • :start_key - The starting value for selecting a range of keys (only useful with OPP).

    • :finish_key - The final value for selecting a range of keys (only useful with OPP).

    • :key_count - The total number of keys to return from the query. (see note regarding deleted records)

    • :batch_size - The maximum number of keys to return per query. If specified will loop until :key_count is obtained or all records have been returned.

    • :columns - A list of columns to return.

    • :count - The number of columns requested to be returned.

    • :start - The starting value for selecting a range of columns.

    • :finish - The final value for selecting a range of columns.

    • :reversed - If set to true the results will be returned in reverse order.

    • :consistency - Uses the default read consistency if none specified.


706
707
708
709
710
711
712
# File 'lib/cassandra/cassandra.rb', line 706

def get_range(column_family, options = {}, &blk)
  if block_given? || options[:key_count] || options[:batch_size]
    get_range_batch(column_family, options, &blk)
  else
    get_range_single(column_family, options, &blk)
  end
end

#get_range_batch(column_family, options = {}) ⇒ Object

Return an Cassandra::OrderedHash containing the columns specified for the given range of keys in the column_family you request.

If a block is passed in we will yield the row key and columns for each record returned.

See Cassandra#get_range for more details.


756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
# File 'lib/cassandra/cassandra.rb', line 756

def get_range_batch(column_family, options = {})
  batch_size    = options.delete(:batch_size) || 100
  count         = options.delete(:key_count)
  result        = {}

  options[:start_key] ||= ''
  last_key  = nil

  while options[:start_key] != last_key && (count.nil? || count > result.length)
    options[:start_key] = last_key
    res = get_range_single(column_family, options.merge!(:start_key => last_key,
                                                         :key_count => batch_size,
                                                         :return_empty_rows => true
                                                        ))
    res.each do |key, columns|
      next if options[:start_key] == key
      next if result.length == count

      unless columns == {}
        if block_given?
          yield key, columns
        else
          result[key] = columns
        end
      end
      last_key = key
    end
  end

  result if !block_given?
end

#get_range_keys(column_family, options = {}) ⇒ Object

Return an Array containing all of the keys within a given range.

This method just calls Cassandra#get_range and returns the row keys for the records returned.

See Cassandra#get_range for options.


808
809
810
# File 'lib/cassandra/cassandra.rb', line 808

def get_range_keys(column_family, options = {})
  get_range(column_family,options.merge!(:count => 1)).keys
end

#get_range_single(column_family, options = {}) ⇒ Object

Return an Cassandra::OrderedHash containing the columns specified for the given range of keys in the column_family you request.

See Cassandra#get_range for more details.


720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
# File 'lib/cassandra/cassandra.rb', line 720

def get_range_single(column_family, options = {})
  return_empty_rows = options.delete(:return_empty_rows) || false

  column_family, _, _, options = 
    extract_and_validate_params(column_family, "", [options], 
                                READ_DEFAULTS.merge(:start_key  => '',
                                                    :finish_key => '',
                                                    :key_count  => 100,
                                                    :columns    => nil,
                                                    :reversed   => false
                                                   )
                               )

  results = _get_range( column_family,
                        options[:start_key].to_s,
                        options[:finish_key].to_s,
                        options[:key_count],
                        options[:columns],
                        options[:start].to_s,
                        options[:finish].to_s,
                        options[:count],
                        options[:consistency],
                        options[:reversed] )

  multi_key_slices_to_hash(column_family, results, return_empty_rows)
end

#insert(column_family, key, hash, options = {}) ⇒ Object

This is the main method used to insert rows into cassandra. If the column_family that you are inserting into is a SuperColumnFamily then the hash passed in should be a nested hash, otherwise it should be a flat hash.

This method can also be called while in batch mode. If in batch mode then we queue up the mutations (an insert in this case) and pass them to cassandra in a single batch at the end of the block.

  • column_family - The column_family that you are inserting into.

  • key - The row key to insert.

  • hash - The columns or super columns to insert.

  • options - Valid options are:

    • :timestamp - Uses the current time if none specified.

    • :consistency - Uses the default write consistency if none specified.

    • :ttl - If specified this is the number of seconds after the insert that this value will be available.


441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
# File 'lib/cassandra/cassandra.rb', line 441

def insert(column_family, key, hash, options = {})
  column_family, _, _, options = extract_and_validate_params(column_family, key, [options], WRITE_DEFAULTS)

  timestamp = options[:timestamp] || Time.stamp
  mutation_map = if is_super(column_family)
    {
      key => {
        column_family => hash.collect{|k,v| _super_insert_mutation(column_family, k, v, timestamp, options[:ttl]) }
      }
    }
  else
    {
      key => {
        column_family => hash.collect{|k,v| _standard_insert_mutation(column_family, k, v, timestamp, options[:ttl])}
      }
    }
  end

  @batch ? @batch << [mutation_map, options[:consistency]] : _mutate(mutation_map, options[:consistency])
end

#inspectObject


130
131
132
133
134
# File 'lib/cassandra/cassandra.rb', line 130

def inspect
  "#<Cassandra:#{object_id}, @keyspace=#{keyspace.inspect}, @schema={#{
    Array(schema(false).cf_defs).map {|cfdef| ":#{cfdef.name} => #{cfdef.column_type}"}.join(', ')
  }}, @servers=#{servers.inspect}>"
end

#keyspacesObject

Returns an array of available keyspaces.


151
152
153
154
155
# File 'lib/cassandra/cassandra.rb', line 151

def keyspaces
  return false if Cassandra.VERSION.to_f < 0.7

  client.describe_keyspaces.to_a.collect {|ksdef| ksdef.name }
end

#login!(username, password) ⇒ Object

Issues a login attempt using the username and password specified.

  • username

  • password


118
119
120
121
122
123
124
125
126
127
128
# File 'lib/cassandra/cassandra.rb', line 118

def login!(username, password)
  request = CassandraThrift::AuthenticationRequest.new
  request.credentials = {'username' => username, 'password' => password}
  ret = client.(request)

  # To avoid a double login on the initial connect, we set
  # @auth_request after the first successful login.
  #
  @auth_request = request
  ret
end

#multi_count_columns(column_family, keys, *options) ⇒ Object

Multi-key version of Cassandra#count_columns. Please note that this queries the server for each key passed in.

Supports same parameters as Cassandra#count_columns.

  • column_family - The column_family that you are inserting into.

  • key - The row key to insert.

  • columns - Either a single super_column or a list of columns.

  • sub_columns - The list of sub_columns to select.

  • options - Valid options are:

    • :consistency - Uses the default read consistency if none specified.

FIXME: Not real multi; needs server support


536
537
538
# File 'lib/cassandra/cassandra.rb', line 536

def multi_count_columns(column_family, keys, *options)
  OrderedHash[*keys.map { |key| [key, count_columns(column_family, key, *options)] }._flatten_once]
end

#multi_get(column_family, keys, *columns_and_options) ⇒ Object

Multi-key version of Cassandra#get.

This method allows you to select multiple rows with a single query. If a key that is passed in doesn't exist an empty hash will be returned.

Supports the same parameters as Cassandra#get.

  • column_family - The column_family that you are inserting into.

  • keys - An array of keys to select.

  • columns - Either a single super_column or a list of columns.

  • sub_columns - The list of sub_columns to select.

  • options - Valid options are:

    • :count - The number of columns requested to be returned.

    • :start - The starting value for selecting a range of columns.

    • :finish - The final value for selecting a range of columns.

    • :reversed - If set to true the results will be returned in reverse order.

    • :consistency - Uses the default read consistency if none specified.


622
623
624
625
626
627
628
629
630
631
632
633
# File 'lib/cassandra/cassandra.rb', line 622

def multi_get(column_family, keys, *columns_and_options)
  column_family, column, sub_column, options = 
    extract_and_validate_params(column_family, keys, columns_and_options, READ_DEFAULTS)

  hash = _multiget(column_family, keys, column, sub_column, 
    options[:start], options[:finish], options[:count], options[:reversed],
    options[:consistency])
  # Restore order
  ordered_hash = OrderedHash.new
  keys.each { |key| ordered_hash[key] = hash[key] || (OrderedHash.new if is_super(column_family) and !sub_column) }
  ordered_hash
end

#multi_get_columns(column_family, keys, *columns_and_options) ⇒ Object

Multi-key version of Cassandra#get_columns. Please note that this queries the server for each key passed in.

Supports same parameters as Cassandra#get_columns

  • column_family - The column_family that you are inserting into.

  • key - The row key to insert.

  • columns - Either a single super_column or a list of columns.

  • sub_columns - The list of sub_columns to select.

  • options - Valid options are:

    • :consistency - Uses the default read consistency if none specified.


569
570
571
572
573
574
575
576
577
578
579
# File 'lib/cassandra/cassandra.rb', line 569

def multi_get_columns(column_family, keys, *columns_and_options)
  column_family, columns, sub_columns, options = 
    extract_and_validate_params(column_family, keys, columns_and_options, READ_DEFAULTS)

  hash = _multiget(column_family, keys, columns, sub_columns, 
    nil, nil, nil, nil, options[:consistency])
  # Restore order
  ordered_hash = OrderedHash.new
  keys.each { |key| ordered_hash[key] = hash[key] || (OrderedHash.new if is_super(column_family) and !sub_columns) }
  ordered_hash
end

#partitionerObject

Returns a string identifying which partitioner is in use by the current cluster. Typically, this will be RandomPartitioner, but it could be OrderPreservingPartioner as well.

Please note that this only works on version 0.7.0 and higher.


229
230
231
232
233
# File 'lib/cassandra/cassandra.rb', line 229

def partitioner
  return false if Cassandra.VERSION.to_f < 0.7

  client.describe_partitioner()
end

#remove(column_family, key, *columns_and_options) ⇒ Object

This method is used to delete (actually marking them as deleted with a tombstone) rows, columns, or super columns depending on the parameters passed. If only a key is passed the entire row will be marked as deleted. If a column name is passed in that column will be deleted.

This method can also be used in batch mode. If in batch mode then we queue up the mutations (a deletion in this case)

  • column_family - The column_family that you are inserting into.

  • key - The row key to insert.

  • columns - Either a single super_column or a list of columns.

  • sub_columns - The list of sub_columns to select.

  • options - Valid options are:

    • :timestamp - Uses the current time if none specified.

    • :consistency - Uses the default write consistency if none specified.

TODO: we could change this function or add another that support multi-column removal (by list or predicate)


482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
# File 'lib/cassandra/cassandra.rb', line 482

def remove(column_family, key, *columns_and_options)
  column_family, column, sub_column, options = extract_and_validate_params(column_family, key, columns_and_options, WRITE_DEFAULTS)

  if @batch
    mutation_map = 
      {
        key => {
          column_family => [ _delete_mutation(column_family, column, sub_column, options[:timestamp]|| Time.stamp) ]
        }
      }
    @batch << [mutation_map, options[:consistency]]
  else 
    # Let's continue using the 'remove' thrift method...not sure about the implications/performance of using the mutate instead
    # Otherwise we coul get use the mutation_map above, and do _mutate(mutation_map, options[:consistency])
    args = {:column_family => column_family}
    columns = is_super(column_family) ? {:super_column => column, :column => sub_column} : {:column => column}
    column_path = CassandraThrift::ColumnPath.new(args.merge(columns))
    _remove(key, column_path, options[:timestamp] || Time.stamp, options[:consistency])
  end
end

#rename_column_family(old_name, new_name) ⇒ Object

Rename a column family. Returns the new schema id.

  • old_name - The current column_family name.

  • new_name - The desired column_family name.


301
302
303
304
305
306
307
308
309
310
311
# File 'lib/cassandra/cassandra.rb', line 301

def rename_column_family(old_name, new_name)
  return false if Cassandra.VERSION.to_f != 0.7

  begin
    res = client.system_rename_column_family(old_name, new_name)
  rescue CassandraThrift::TimedOutException => te
    puts "Timed out: #{te.inspect}"
  end
  @schema = nil
  res
end

#rename_keyspace(old_name, new_name) ⇒ Object

Renames keyspace.

  • old_name - Current keyspace name.

  • new_name - Desired keyspace name.

Returns the new schema id


374
375
376
377
378
379
380
381
382
383
384
385
386
387
# File 'lib/cassandra/cassandra.rb', line 374

def rename_keyspace(old_name, new_name)
  return false if Cassandra.VERSION.to_f < 0.7

  begin
    res = client.system_rename_keyspace(old_name, new_name)
  rescue CassandraThrift::TimedOutException => toe
    puts "Timed out: #{toe.inspect}"
  rescue Thrift::TransportException => te
    puts "Timed out: #{te.inspect}"
  end
  keyspace = new_name if old_name.eql?(@keyspace)
  @keyspaces = nil
  res
end

#ringObject

Returns an array of CassandraThrift::TokenRange objects indicating which servers make up the current ring. What their start and end tokens are, and their list of endpoints.

Please note that this only works on version 0.7.0 and higher.


217
218
219
220
221
# File 'lib/cassandra/cassandra.rb', line 217

def ring
  return false if Cassandra.VERSION.to_f < 0.7

  client.describe_ring(@keyspace)
end

#schema_agreement?Boolean

This returns true if all servers are in agreement on the schema.

Please note that this only works on version 0.7.0 and higher.

Returns:

  • (Boolean)

185
186
187
188
189
# File 'lib/cassandra/cassandra.rb', line 185

def schema_agreement?
  return false if Cassandra.VERSION.to_f < 0.7

  client.describe_schema_versions().length == 1
end

#update_column_family(cf_def) ⇒ Object

Update the column family based on the passed in definition.


316
317
318
319
320
321
322
323
324
325
326
# File 'lib/cassandra/cassandra.rb', line 316

def update_column_family(cf_def)
  return false if Cassandra.VERSION.to_f < 0.7

  begin
    res = client.system_update_column_family(cf_def)
  rescue CassandraThrift::TimedOutException => te
    puts "Timed out: #{te.inspect}"
  end
  @schema = nil
  res
end

#update_keyspace(ks_def) ⇒ Object

Update the keyspace using the passed in keyspace definition.


392
393
394
395
396
397
398
399
400
401
402
403
404
# File 'lib/cassandra/cassandra.rb', line 392

def update_keyspace(ks_def)
  return false if Cassandra.VERSION.to_f < 0.7

  begin
    res = client.system_update_keyspace(ks_def)
  rescue CassandraThrift::TimedOutException => toe
    puts "Timed out: #{toe.inspect}"
  rescue Thrift::TransportException => te
    puts "Timed out: #{te.inspect}"
  end
  @keyspaces = nil
  res
end

#versionObject

Lists the current cassandra.thrift version.

Please note that this only works on version 0.7.0 and higher.


195
196
197
198
199
# File 'lib/cassandra/cassandra.rb', line 195

def version
  return false if Cassandra.VERSION.to_f < 0.7

  client.describe_version()
end