Class: Mongo::Collection

Inherits:
Object show all
Includes:
Logging, WriteConcern
Defined in:
lib/mongo/collection.rb

Overview

A named collection of documents in a database.

Instance Attribute Summary collapse

Attributes included from WriteConcern

#legacy_write_concern

Instance Method Summary collapse

Methods included from WriteConcern

#get_write_concern, gle?, #write_concern_from_legacy

Methods included from Logging

#instrument, instrumenter, instrumenter=, #log, #write_logging_startup_message

Constructor Details

#initialize(name, db, opts = {}) ⇒ Collection

Initialize a collection object.

Parameters:

  • name (String, Symbol) —

    the name of the collection.

  • db (DB) —

    a MongoDB database instance.

  • opts (Hash) (defaults to: {}) —

    a customizable set of options

Options Hash (opts):

  • :w (String, Integer, Symbol) — default: 1 —

    Set default number of nodes to which a write should be acknowledged

  • :j (Boolean) — default: false —

    Set journal acknowledgement

  • :wtimeout (Integer) — default: nil —

    Set replica set acknowledgement timeout

  • :fsync (Boolean) — default: false —

    Set fsync acknowledgement.

    Notes about write concern:

    These write concern options will be used for insert, update, and remove methods called on this
Collection instance. If no value is provided, the default values set on this instance's DB will be used.
These option values can be overridden for any invocation of insert, update, or remove.
  • :pk (:create_pk) — default: BSON::ObjectId —

    A primary key factory to use other than the default BSON::ObjectId.

  • :read (:primary, :secondary) —

    The default read preference for queries initiates from this connection object. If :secondary is chosen, reads will be sent to one of the closest available secondary nodes. If a secondary node cannot be located, the read will be sent to the primary. If this option is left unspecified, the value of the read preference for this collection’s associated Mongo::DB object will be used.

Raises:

  • (InvalidNSName) —

    if collection name is empty, contains ‘$’, or starts or ends with ‘.’

  • (TypeError) —

    if collection name is not a string or symbol



53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
 
# File 'lib/mongo/collection.rb', line 53

def initialize(name, db, opts={})
  if db.is_a?(String) && name.is_a?(Mongo::DB)
    warn "Warning: the order of parameters to initialize a collection have changed. " +
         "Please specify the collection name first, followed by the db. This will be made permanent" +
         "in v2.0."
    db, name = name, db
  end

  raise TypeError,
    "Collection name must be a String or Symbol." unless [String, Symbol].include?(name.class)
  name = name.to_s

  raise Mongo::InvalidNSName,
    "Collection names cannot be empty." if name.empty? || name.include?("..")

  if name.include?("$")
    raise Mongo::InvalidNSName,
      "Collection names must not contain '$'" unless name =~ /((^\$cmd)|(oplog\.\$main))/
  end

  raise Mongo::InvalidNSName,
    "Collection names must not start or end with '.'" if name.match(/^\./) || name.match(/\.$/)

  pk_factory = nil
  if opts.respond_to?(:create_pk) || !opts.is_a?(Hash)
    warn "The method for specifying a primary key factory on a Collection has changed.\n" +
         "Please specify it as an option (e.g., :pk => PkFactory)."
    pk_factory = opts
  end

  @db, @name  = db, name
  @connection = @db.connection
  @logger     = @connection.logger
  @cache_time = @db.cache_time
  @cache      = Hash.new(0)
  unless pk_factory
    @write_concern = get_write_concern(opts, db)
    @read =  opts[:read] || @db.read
    Mongo::ReadPreference::validate(@read)
    @capped             = opts[:capped]
    @tag_sets           = opts.fetch(:tag_sets, @db.tag_sets)
    @acceptable_latency = opts.fetch(:acceptable_latency, @db.acceptable_latency)
  end
  @pk_factory = pk_factory || opts[:pk] || BSON::ObjectId
  @hint = nil
end

Instance Attribute Details

#acceptable_latency ⇒ Object

Read Preference



16
17
18
 
# File 'lib/mongo/collection.rb', line 16

def acceptable_latency
  @acceptable_latency
end

#capped ⇒ Object (readonly)

Returns the value of attribute capped.



8
9
10
 
# File 'lib/mongo/collection.rb', line 8

def capped
  @capped
end

#db ⇒ Object (readonly)

Returns the value of attribute db.



8
9
10
 
# File 'lib/mongo/collection.rb', line 8

def db
  @db
end

#hint ⇒ Object

Returns the value of attribute hint.



8
9
10
 
# File 'lib/mongo/collection.rb', line 8

def hint
  @hint
end

#name ⇒ Object (readonly)

Returns the value of attribute name.



8
9
10
 
# File 'lib/mongo/collection.rb', line 8

def name
  @name
end

#pk_factory ⇒ Object (readonly)

Returns the value of attribute pk_factory.



8
9
10
 
# File 'lib/mongo/collection.rb', line 8

def pk_factory
  @pk_factory
end

#read ⇒ Object

Read Preference



16
17
18
 
# File 'lib/mongo/collection.rb', line 16

def read
  @read
end

#tag_sets ⇒ Object

Read Preference



16
17
18
 
# File 'lib/mongo/collection.rb', line 16

def tag_sets
  @tag_sets
end

#write_concern ⇒ Object (readonly)

Returns the value of attribute write_concern.



8
9
10
 
# File 'lib/mongo/collection.rb', line 8

def write_concern
  @write_concern
end

Instance Method Details

#[](name) ⇒ Collection

Return a sub-collection of this collection by name. If ‘users’ is a collection, then ‘users.comments’ is a sub-collection of users.

Parameters:

  • name (String, Symbol) —

    the collection to return

Returns:

Raises:



121
122
123
124
125
126
 
# File 'lib/mongo/collection.rb', line 121

def [](name)
  name = "#{self.name}.#{name}"
  return Collection.new(name, db) if !db.strict? ||
    db.collection_names.include?(name.to_s)
  raise "Collection #{name} doesn't exist. Currently in strict mode."
end

#aggregate(pipeline = nil, opts = {}) ⇒ Array

Note:

Aggregate requires server version >= 2.1.1

Note:

Field References: Within an expression, field names must be quoted and prefixed by a dollar sign ($).

Perform an aggregation using the aggregation framework on the current collection.

Examples:

Define the pipeline as an array of operator hashes:

coll.aggregate([ {"$project" => {"last_name" => 1, "first_name" => 1 }}, {"$match" => {"last_name" => "Jones"}} ])

Parameters:

  • pipeline (Array) (defaults to: nil) —

    Should be a single array of pipeline operator hashes.

    ‘$project’ Reshapes a document stream by including fields, excluding fields, inserting computed fields, renaming fields,or creating/populating fields that hold sub-documents.

    ‘$match’ Query-like interface for filtering documents out of the aggregation pipeline.

    ‘$limit’ Restricts the number of documents that pass through the pipeline.

    ‘$skip’ Skips over the specified number of documents and passes the rest along the pipeline.

    ‘$unwind’ Peels off elements of an array individually, returning one document for each member.

    ‘$group’ Groups documents for calculating aggregate values.

    ‘$sort’ Sorts all input documents and returns them to the pipeline in sorted order.

  • opts (Hash) (defaults to: {}) —

    a customizable set of options

Options Hash (opts):

  • :read (:primary, :secondary) —

    Read preference indicating which server to perform this query on. See Collection#find for more details.

  • :comment (String) — default: nil —

    a comment to include in profiling logs

Returns:

  • (Array) —

    An Array with the aggregate command’s results.

Raises:

  • MongoArgumentError if operators either aren’t supplied or aren’t in the correct format.

  • MongoOperationFailure if the aggregate command fails.



656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
 
# File 'lib/mongo/collection.rb', line 656

def aggregate(pipeline=nil, opts={})
  raise MongoArgumentError, "pipeline must be an array of operators" unless pipeline.class == Array
  raise MongoArgumentError, "pipeline operators must be hashes" unless pipeline.all? { |op| op.class == Hash }

  hash = BSON::OrderedHash.new
  hash['aggregate'] = self.name
  hash['pipeline'] = pipeline

  result = @db.command(hash, command_options(opts))
  unless Mongo::Support.ok?(result)
    raise Mongo::OperationFailure, "aggregate failed: #{result['errmsg']}"
  end

  return result["result"]
end

#capped? ⇒ Boolean

Indicate whether this is a capped collection.

Returns:

  • (Boolean)

Raises:



106
107
108
 
# File 'lib/mongo/collection.rb', line 106

def capped?
  @capped ||= [1, true].include?(@db.command({:collstats => @name})['capped'])
end

#count(opts = {}) ⇒ Integer Also known as: size

Get the number of documents in this collection.

Parameters:

  • opts (Hash) (defaults to: {}) —

    a customizable set of options

Options Hash (opts):

  • :query (Hash) — default: {} —

    A query selector for filtering the documents counted.

  • :skip (Integer) — default: nil —

    The number of documents to skip.

  • :limit (Integer) — default: nil —

    The number of documents to limit.

  • :read (:primary, :secondary) —

    Read preference for this command. See Collection#find for more details.

  • :comment (String) — default: nil —

    a comment to include in profiling logs

Returns:

  • (Integer) 


959
960
961
962
963
964
965
 
# File 'lib/mongo/collection.rb', line 959

def count(opts={})
  find(opts[:query],
       :skip  => opts[:skip],
       :limit => opts[:limit],
       :read  => opts[:read],
       :comment => opts[:comment]).count(true)
end

#create_index(spec, opts = {}) ⇒ String

Create a new index.

Examples:

Creating a compound index using a hash: (Ruby 1.9 and above)

@posts.create_index({'subject' => Mongo::ASCENDING, 'created_at' => Mongo::DESCENDING})

Creating a compound index:

@posts.create_index([['subject', Mongo::ASCENDING], ['created_at', Mongo::DESCENDING]])

Creating a geospatial index:

@restaurants.create_index([['location', Mongo::GEO2D]])

# Note that this will work only if 'location' represents x,y coordinates:
{'location': [0, 50]}
{'location': {'x' => 0, 'y' => 50}}
{'location': {'latitude' => 0, 'longitude' => 50}}

A geospatial index with alternate longitude and latitude:

@restaurants.create_index([['location', Mongo::GEO2D]], :min => 500, :max => 500)

Parameters:

  • spec (String, Array) —

    should be either a single field name or an array of

    field name, type

    pairs. Index types should be specified

    as Mongo::ASCENDING, Mongo::DESCENDING, Mongo::GEO2D, Mongo::GEO2DSPHERE, Mongo::GEOHAYSTACK, Mongo::TEXT or Mongo::HASHED.

    Note that geospatial indexing only works with versions of MongoDB >= 1.3.3+. Keep in mind, too, that in order to geo-index a given field, that field must reference either an array or a sub-object where the first two values represent x- and y-coordinates. Examples can be seen below.

    Also note that it is permissible to create compound indexes that include a geospatial index as long as the geospatial index comes first.

    If your code calls create_index frequently, you can use Collection#ensure_index to cache these calls and thereby prevent excessive round trips to the database.

  • opts (Hash) (defaults to: {}) —

    a customizable set of options

Options Hash (opts):

  • :unique (Boolean) — default: false —

    if true, this index will enforce a uniqueness constraint.

  • :background (Boolean) — default: false —

    indicate that the index should be built in the background. This feature is only available in MongoDB >= 1.3.2.

  • :drop_dups (Boolean) — default: nil —

    If creating a unique index on a collection with pre-existing records, this option will keep the first document the database indexes and drop all subsequent with duplicate values.

  • :bucket_size (Integer) — default: nil —

    For use with geoHaystack indexes. Number of documents to group together within a certain proximity to a given longitude and latitude.

  • :min (Integer) — default: nil —

    specify the minimum longitude and latitude for a geo index.

  • :max (Integer) — default: nil —

    specify the maximum longitude and latitude for a geo index.

Returns:

  • (String) —

    the name of the index created.



528
529
530
531
532
533
534
535
536
537
 
# File 'lib/mongo/collection.rb', line 528

def create_index(spec, opts={})
  opts[:dropDups]   = opts[:drop_dups] if opts[:drop_dups]
  opts[:bucketSize] = opts[:bucket_size] if opts[:bucket_size]
  field_spec        = parse_index_spec(spec)
  opts              = opts.dup
  name              = opts.delete(:name) || generate_index_name(field_spec)
  name              = name.to_s if name
  generate_indexes(field_spec, name, opts)
  name
end

#distinct(key, query = nil, opts = {}) ⇒ Array

Return a list of distinct values for key across all documents in the collection. The key may use dot notation to reach into an embedded object.

Examples:

Saving zip codes and ages and returning distinct results.

@collection.save({:zip => 10010, :name => {:age => 27}})
@collection.save({:zip => 94108, :name => {:age => 24}})
@collection.save({:zip => 10010, :name => {:age => 27}})
@collection.save({:zip => 99701, :name => {:age => 24}})
@collection.save({:zip => 94108, :name => {:age => 27}})

@collection.distinct(:zip)
  [10010, 94108, 99701]
@collection.distinct("name.age")
  [27, 24]

# You may also pass a document selector as the second parameter
# to limit the documents over which distinct is run:
@collection.distinct("name.age", {"name.age" => {"$gt" => 24}})
  [27]

Parameters:

  • key (String, Symbol, OrderedHash) —

    or hash to group by.

  • query (Hash) (defaults to: nil) —

    a selector for limiting the result set over which to group.

  • opts (Hash) (defaults to: {}) —

    the options for this distinct operation.

Options Hash (opts):

  • :read (:primary, :secondary) —

    Read preference indicating which server to perform this query on. See Collection#find for more details.

  • :comment (String) — default: nil —

    a comment to include in profiling logs

Returns:

  • (Array) —

    an array of distinct values.

Raises:



882
883
884
885
886
887
888
889
890
 
# File 'lib/mongo/collection.rb', line 882

def distinct(key, query=nil, opts={})
  raise MongoArgumentError unless [String, Symbol].include?(key.class)
  command            = BSON::OrderedHash.new
  command[:distinct] = @name
  command[:key]      = key.to_s
  command[:query]    = query

  @db.command(command, command_options(opts))["values"]
end

#drop ⇒ Object

Drop the entire collection. USE WITH CAUTION.



596
597
598
 
# File 'lib/mongo/collection.rb', line 596

def drop
  @db.drop_collection(@name)
end

#drop_index(name) ⇒ Object

Drop a specified index.

Parameters:



577
578
579
580
581
582
583
 
# File 'lib/mongo/collection.rb', line 577

def drop_index(name)
  if name.is_a?(Array)
    return drop_index(index_name(name))
  end
  @cache[name.to_s] = nil
  @db.drop_index(@name, name)
end

#drop_indexes ⇒ Object

Drop all indexes.



588
589
590
591
592
593
 
# File 'lib/mongo/collection.rb', line 588

def drop_indexes
  @cache = {}

  # Note: calling drop_indexes with no args will drop them all.
  @db.drop_index(@name, '*')
end

#ensure_index(spec, opts = {}) ⇒ String

Calls create_index and sets a flag to not do so again for another X minutes. this time can be specified as an option when initializing a Mongo::DB object as options Any changes to an index will be propagated through regardless of cache time (e.g., a change of index direction)

The parameters and options for this methods are the same as those for Collection#create_index.

Examples:

Call sequence:

Time t: @posts.ensure_index([['subject', Mongo::ASCENDING])  -- calls create_index and
  sets the 5 minute cache
Time t+2min : @posts.ensure_index([['subject', Mongo::ASCENDING])  -- doesn't do anything
Time t+3min : @posts.ensure_index([['something_else', Mongo::ASCENDING])  -- calls create_index
  and sets 5 minute cache
Time t+10min : @posts.ensure_index([['subject', Mongo::ASCENDING])  -- calls create_index and
  resets the 5 minute counter

Returns:

  • (String) —

    the name of the index.



555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
 
# File 'lib/mongo/collection.rb', line 555

def ensure_index(spec, opts={})
  now               = Time.now.utc.to_i
  opts[:dropDups]   = opts[:drop_dups] if opts[:drop_dups]
  opts[:bucketSize] = opts[:bucket_size] if opts[:bucket_size]
  field_spec        = parse_index_spec(spec)
  name              = opts[:name] || generate_index_name(field_spec)
  name              = name.to_s if name

  if !@cache[name] || @cache[name] <= now
    generate_indexes(field_spec, name, opts)
  end

  # Reset the cache here in case there are any errors inserting. Best to be safe.
  @cache[name] = now + @cache_time
  name
end

#find(selector = {}, opts = {}) ⇒ Object

Query the database.

The selector argument is a prototype document that all results must match. For example:

collection.find({"hello" => "world"})

only matches documents that have a key “hello” with value “world”. Matches can have other keys *in addition* to “hello”.

If given an optional block find will yield a Cursor to that block, close the cursor, and then return nil. This guarantees that partially evaluated cursors will be closed. If given no block find returns a cursor.

Parameters:

  • selector (Hash) (defaults to: {}) —

    a document specifying elements which must be present for a document to be included in the result set. Note that in rare cases, (e.g., with $near queries), the order of keys will matter. To preserve key order on a selector, use an instance of BSON::OrderedHash (only applies to Ruby 1.8).

  • opts (Hash) (defaults to: {}) —

    a customizable set of options

Options Hash (opts):

  • :fields (Array, Hash) —

    field names that should be returned in the result set (“_id” will be included unless explicitly excluded). By limiting results to a certain subset of fields, you can cut down on network traffic and decoding time. If using a Hash, keys should be field names and values should be either 1 or 0, depending on whether you want to include or exclude the given field.

  • :read (:primary, :secondary) —

    The default read preference for queries initiates from this connection object. If :secondary is chosen, reads will be sent to one of the closest available secondary nodes. If a secondary node cannot be located, the read will be sent to the primary. If this option is left unspecified, the value of the read preference for this Collection object will be used.

  • :skip (Integer) —

    number of documents to skip from the beginning of the result set

  • :limit (Integer) —

    maximum number of documents to return

  • :sort (Array) —

    an array of [key, direction] pairs to sort by. Direction should be specified as Mongo::ASCENDING (or :ascending / :asc) or Mongo::DESCENDING (or :descending / :desc)

  • :hint (String, Array, OrderedHash) —

    hint for query optimizer, usually not necessary if using MongoDB > 1.1

  • :named_hint (String) —

    for specifying a named index as a hint, will be overriden by :hint if :hint is also provided.

  • :snapshot (Boolean) — default: false —

    if true, snapshot mode will be used for this query. Snapshot mode assures no duplicates are returned, or objects missed, which were preset at both the start and end of the query’s execution. For details see www.mongodb.org/display/DOCS/How+to+do+Snapshotting+in+the+Mongo+Database

  • :batch_size (Boolean) — default: 100 —

    the number of documents to returned by the database per GETMORE operation. A value of 0 will let the database server decide how many results to return. This option can be ignored for most use cases.

  • :timeout (Boolean) — default: true —

    when true, the returned cursor will be subject to the normal cursor timeout behavior of the mongod process. When false, the returned cursor will never timeout. Note that disabling timeout will only work when #find is invoked with a block. This is to prevent any inadvertent failure to close the cursor, as the cursor is explicitly closed when block code finishes.

  • :max_scan (Integer) — default: nil —

    Limit the number of items to scan on both collection scans and indexed queries..

  • :show_disk_loc (Boolean) — default: false —

    Return the disk location of each query result (for debugging).

  • :return_key (Boolean) — default: false —

    Return the index key used to obtain the result (for debugging).

  • :transformer (Block) — default: nil —

    a block for transforming returned documents. This is normally used by object mappers to convert each returned document to an instance of a class.

  • :comment (String) — default: nil —

    a comment to include in profiling logs

Raises:

  • (ArgumentError) —

    if timeout is set to false and find is not invoked in a block

  • (RuntimeError) —

    if given unknown options



212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
 
# File 'lib/mongo/collection.rb', line 212

def find(selector={}, opts={})
  opts               = opts.dup
  fields             = opts.delete(:fields)
  fields             = ["_id"] if fields && fields.empty?
  skip               = opts.delete(:skip) || skip || 0
  limit              = opts.delete(:limit) || 0
  sort               = opts.delete(:sort)
  hint               = opts.delete(:hint)
  named_hint         = opts.delete(:named_hint)
  snapshot           = opts.delete(:snapshot)
  batch_size         = opts.delete(:batch_size)
  timeout            = (opts.delete(:timeout) == false) ? false : true
  max_scan           = opts.delete(:max_scan)
  return_key         = opts.delete(:return_key)
  transformer        = opts.delete(:transformer)
  show_disk_loc      = opts.delete(:show_disk_loc)
  comment            = opts.delete(:comment)
  read               = opts.delete(:read) || @read
  tag_sets           = opts.delete(:tag_sets) || @tag_sets
  acceptable_latency = opts.delete(:acceptable_latency) || @acceptable_latency

  if timeout == false && !block_given?
    raise ArgumentError, "Collection#find must be invoked with a block when timeout is disabled."
  end

  if hint
    hint = normalize_hint_fields(hint)
  else
    hint = @hint        # assumed to be normalized already
  end

  raise RuntimeError, "Unknown options [#{opts.inspect}]" unless opts.empty?

  cursor = Cursor.new(self, {
    :selector           => selector,
    :fields             => fields,
    :skip               => skip,
    :limit              => limit,
    :order              => sort,
    :hint               => hint || named_hint,
    :snapshot           => snapshot,
    :timeout            => timeout,
    :batch_size         => batch_size,
    :transformer        => transformer,
    :max_scan           => max_scan,
    :show_disk_loc      => show_disk_loc,
    :return_key         => return_key,
    :read               => read,
    :tag_sets           => tag_sets,
    :comment            => comment,
    :acceptable_latency => acceptable_latency
  })

  if block_given?
    begin
      yield cursor
    ensure
      cursor.close
    end
    nil
  else
    cursor
  end
end

#find_and_modify(opts = {}) ⇒ Hash

Atomically update and return a document using MongoDB’s findAndModify command. (MongoDB > 1.3.0)

Parameters:

  • opts (Hash) (defaults to: {}) —

    a customizable set of options

Options Hash (opts):

  • :query (Hash) — default: {} —

    a query selector document for matching the desired document.

  • :update (Hash) — default: nil —

    the update operation to perform on the matched document.

  • :sort (Array, String, OrderedHash) — default: {} —

    specify a sort option for the query using any of the sort options available for Cursor#sort. Sort order is important if the query will be matching multiple documents since only the first matching document will be updated and returned.

  • :remove (Boolean) — default: false —

    If true, removes the the returned document from the collection.

  • :new (Boolean) — default: false —

    If true, returns the updated document; otherwise, returns the document prior to update.

Returns:

  • (Hash) —

    the matched document.



614
615
616
617
618
619
620
621
 
# File 'lib/mongo/collection.rb', line 614

def find_and_modify(opts={})
  cmd = BSON::OrderedHash.new
  cmd[:findandmodify] = @name
  cmd.merge!(opts)
  cmd[:sort] = Mongo::Support.format_order_clause(opts[:sort]) if opts[:sort]

  @db.command(cmd)['value']
end

#find_one(spec_or_object_id = nil, opts = {}) ⇒ OrderedHash, Nil

Return a single object from the database.

Parameters:

  • spec_or_object_id (Hash, ObjectId, Nil) (defaults to: nil) —

    a hash specifying elements which must be present for a document to be included in the result set or an instance of ObjectId to be used as the value for an _id query. If nil, an empty selector, {}, will be used.

  • opts (Hash) (defaults to: {}) —

    a customizable set of options

Options Hash (opts):

  • any (Hash) —

    valid options that can be send to Collection#find

Returns:

  • (OrderedHash, Nil) —

    a single document or nil if no result is found.

Raises:

  • (TypeError) —

    if the argument is of an improper type.



292
293
294
295
296
297
298
299
300
301
302
303
304
 
# File 'lib/mongo/collection.rb', line 292

def find_one(spec_or_object_id=nil, opts={})
  spec = case spec_or_object_id
         when nil
           {}
         when BSON::ObjectId
           {:_id => spec_or_object_id}
         when Hash
           spec_or_object_id
         else
           raise TypeError, "spec_or_object_id must be an instance of ObjectId or Hash, or nil"
         end
  find(spec, opts.merge(:limit => -1)).next_document
end

#group(opts, condition = {}, initial = {}, reduce = nil, finalize = nil) ⇒ Array

Perform a group aggregation.

Parameters:

  • opts (Hash) —

    the options for this group operation. The minimum required are :initial and :reduce.

Options Hash (opts):

  • :key (Array, String, Symbol) — default: nil —

    Either the name of a field or a list of fields to group by (optional).

  • :keyf (String, BSON::Code) — default: nil —

    A JavaScript function to be used to generate the grouping keys (optional).

  • :cond (String, BSON::Code) — default: {} —

    A document specifying a query for filtering the documents over which the aggregation is run (optional).

  • :initial (Hash) —

    the initial value of the aggregation counter object (required).

  • :reduce (String, BSON::Code) — default: nil —

    a JavaScript aggregation function (required).

  • :finalize (String, BSON::Code) — default: nil —

    a JavaScript function that receives and modifies each of the resultant grouped objects. Available only when group is run with command set to true.

  • :read (:primary, :secondary) —

    Read preference indicating which server to perform this group on. See Collection#find for more details.

  • :comment (String) — default: nil —

    a comment to include in profiling logs

Returns:

  • (Array) —

    the command response consisting of grouped items.



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
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
 
# File 'lib/mongo/collection.rb', line 759

def group(opts, condition={}, initial={}, reduce=nil, finalize=nil)
  if opts.is_a?(Hash)
    return new_group(opts)
  else
    warn "Collection#group no longer take a list of parameters. This usage is deprecated and will be remove in v2.0." +
         "Check out the new API at http://api.mongodb.org/ruby/current/Mongo/Collection.html#group-instance_method"
  end

  reduce = BSON::Code.new(reduce) unless reduce.is_a?(BSON::Code)

  group_command = {
    "group" => {
      "ns"      => @name,
      "$reduce" => reduce,
      "cond"    => condition,
      "initial" => initial
    }
  }

  if opts.is_a?(Symbol)
    raise MongoArgumentError, "Group takes either an array of fields to group by or a JavaScript function" +
      "in the form of a String or BSON::Code."
  end

  unless opts.nil?
    if opts.is_a? Array
      key_type = "key"
      key_value = {}
      opts.each { |k| key_value[k] = 1 }
    else
      key_type  = "$keyf"
      key_value = opts.is_a?(BSON::Code) ? opts : BSON::Code.new(opts)
    end

    group_command["group"][key_type] = key_value
  end

  finalize = BSON::Code.new(finalize) if finalize.is_a?(String)
  if finalize.is_a?(BSON::Code)
    group_command['group']['finalize'] = finalize
  end

  result = @db.command(group_command)

  if Mongo::Support.ok?(result)
    result["retval"]
  else
    raise OperationFailure, "group command failed: #{result['errmsg']}"
  end
end

#index_information ⇒ Hash

Get information on the indexes for this collection.

Returns:

  • (Hash) —

    a hash where the keys are index names.



930
931
932
 
# File 'lib/mongo/collection.rb', line 930

def index_information
  @db.index_information(@name)
end

#insert(doc_or_docs, opts = {}) ⇒ ObjectId, ... Also known as: <<

Insert one or more documents into the collection.

Parameters:

  • doc_or_docs (Hash, Array) —

    a document (as a hash) or array of documents to be inserted.

  • opts (Hash) (defaults to: {}) —

    a customizable set of options

Options Hash (opts):

  • :w (String, Integer, Symbol) — default: 1 —

    Set default number of nodes to which a write should be acknowledged

  • :j (Boolean) — default: false —

    Set journal acknowledgement

  • :wtimeout (Integer) — default: nil —

    Set replica set acknowledgement timeout

  • :fsync (Boolean) — default: false —

    Set fsync acknowledgement.

    Notes on write concern:

    Options provided here will override any write concern options set on this collection,
its database object, or the current connection. See the options for +DB#get_last_error+.
  • :continue_on_error (Boolean) — default: +false+ —

    If true, then continue a bulk insert even if one of the documents inserted triggers a database assertion (as in a duplicate insert, for instance). If not acknowledging writes, the list of ids returned will include the object ids of all documents attempted on insert, even if some are rejected on error. When acknowledging writes, any error will raise an OperationFailure exception. MongoDB v2.0+.

  • :collect_on_error (Boolean) — default: +false+ —

    if true, then collects invalid documents as an array. Note that this option changes the result format.

Returns:

  • (ObjectId, Array) —

    The _id of the inserted document or a list of _ids of all inserted documents.

  • ([ObjectId, Array], [Hash, Array]) —

    1st, the _id of the inserted document or a list of _ids of all inserted documents. 2nd, a list of invalid documents. Return this result format only when :collect_on_error is true.

Raises:



371
372
373
374
375
376
377
 
# File 'lib/mongo/collection.rb', line 371

def insert(doc_or_docs, opts={})
  doc_or_docs = [doc_or_docs] unless doc_or_docs.is_a?(Array)
  doc_or_docs.collect! { |doc| @pk_factory.create_pk(doc) }
  write_concern = get_write_concern(opts, self)
  result = insert_documents(doc_or_docs, @name, true, write_concern, opts)
  result.size > 1 ? result : result.first
end

#map_reduce(map, reduce, opts = {}) ⇒ Collection, Hash Also known as: mapreduce

Perform a map-reduce operation on the current collection.

Parameters:

  • map (String, BSON::Code) —

    a map function, written in JavaScript.

  • reduce (String, BSON::Code) —

    a reduce function, written in JavaScript.

  • opts (Hash) (defaults to: {}) —

    a customizable set of options

Options Hash (opts):

  • :query (Hash) — default: {} —

    a query selector document, like what’s passed to #find, to limit the operation to a subset of the collection.

  • :sort (Array) — default: [] —

    an array of [key, direction] pairs to sort by. Direction should be specified as Mongo::ASCENDING (or :ascending / :asc) or Mongo::DESCENDING (or :descending / :desc)

  • :limit (Integer) — default: nil —

    if passing a query, number of objects to return from the collection.

  • :finalize (String, BSON::Code) — default: nil —

    a javascript function to apply to the result set after the map/reduce operation has finished.

  • :out (String) — default: nil —

    a valid output type. In versions of MongoDB prior to v1.7.6, this option takes the name of a collection for the output results. In versions 1.7.6 and later, this option specifies the output type. See the core docs for available output types.

  • :keeptemp (Boolean) — default: false —

    if true, the generated collection will be persisted. The default is false. Note that this option has no effect is versions of MongoDB > v1.7.6.

  • :verbose (Boolean) — default: false —

    if true, provides statistics on job execution time.

  • :raw (Boolean) — default: false —

    if true, return the raw result object from the map_reduce command, and not the instantiated collection that’s returned by default. Note if a collection name isn’t returned in the map-reduce output (as, for example, when using :out => { :inline => 1 }), then you must specify this option or an ArgumentError will be raised.

  • :read (:primary, :secondary) —

    Read preference indicating which server to run this map-reduce on. See Collection#find for more details.

  • :comment (String) — default: nil —

    a comment to include in profiling logs

Returns:

  • (Collection, Hash) —

    a Mongo::Collection object or a Hash with the map-reduce command’s results.

Raises:

  • ArgumentError if you specify { :out => { :inline => true }} but don’t specify :raw => true.

See Also:



705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
 
# File 'lib/mongo/collection.rb', line 705

def map_reduce(map, reduce, opts={})
  map    = BSON::Code.new(map) unless map.is_a?(BSON::Code)
  reduce = BSON::Code.new(reduce) unless reduce.is_a?(BSON::Code)
  raw    = opts.delete(:raw)

  hash = BSON::OrderedHash.new
  hash['mapreduce'] = self.name
  hash['map'] = map
  hash['reduce'] = reduce
  hash.merge! opts
  if hash[:sort]
    hash[:sort] = Mongo::Support.format_order_clause(hash[:sort])
  end

  result = @db.command(hash, command_options(opts))
  unless Mongo::Support.ok?(result)
    raise Mongo::OperationFailure, "map-reduce failed: #{result['errmsg']}"
  end

  if raw
    result
  elsif result["result"]
    if result['result'].is_a? BSON::OrderedHash and result['result'].has_key? 'db' and result['result'].has_key? 'collection'
      otherdb = @db.connection[result['result']['db']]
      otherdb[result['result']['collection']]
    else
      @db[result["result"]]
    end
  else
    raise ArgumentError, "Could not instantiate collection from result. If you specified " +
      "{:out => {:inline => true}}, then you must also specify :raw => true to get the results."
  end
end

#named_hint=(hint = nil) ⇒ Object

Set a hint field using a named index.

Parameters:

  • hinted (String) —

    index name



141
142
143
144
 
# File 'lib/mongo/collection.rb', line 141

def named_hint=(hint=nil)
  @hint = hint
  self
end

#options ⇒ Hash

Return a hash containing options that apply to this collection. For all possible keys and values, see DB#create_collection.

Returns:

  • (Hash) —

    options that apply to this collection.



938
939
940
 
# File 'lib/mongo/collection.rb', line 938

def options
  @db.collections_info(@name).next_document['options']
end

#remove(selector = {}, opts = {}) ⇒ Hash, true

Remove all documents from this collection.

Examples:

remove all documents from the ‘users’ collection:

users.remove
users.remove({})

remove only documents that have expired:

users.remove({:expire => {"$lte" => Time.now}})

Parameters:

  • selector (Hash) (defaults to: {}) —

    If specified, only matching documents will be removed.

  • opts (Hash) (defaults to: {}) —

    a customizable set of options

Options Hash (opts):

  • :w (String, Integer, Symbol) — default: 1 —

    Set default number of nodes to which a write should be acknowledged

  • :j (Boolean) — default: false —

    Set journal acknowledgement

  • :wtimeout (Integer) — default: nil —

    Set replica set acknowledgement timeout

  • :fsync (Boolean) — default: false —

    Set fsync acknowledgement.

    Notes on write concern:

    Options provided here will override any write concern options set on this collection,
its database object, or the current connection. See the options for +DB#get_last_error+.

Returns:

  • (Hash, true) —

    Returns a Hash containing the last error object if acknowledging writes Otherwise, returns true.

Raises:



408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
 
# File 'lib/mongo/collection.rb', line 408

def remove(selector={}, opts={})
  write_concern = get_write_concern(opts, self)
  message = BSON::ByteBuffer.new("\0\0\0\0", @connection.max_message_size)
  BSON::BSON_RUBY.serialize_cstr(message, "#{@db.name}.#{@name}")
  message.put_int(0)
  message.put_binary(BSON::BSON_CODER.serialize(selector, false, true, @connection.max_bson_size).to_s)

  instrument(:remove, :database => @db.name, :collection => @name, :selector => selector) do
    if Mongo::WriteConcern.gle?(write_concern)
      @connection.send_message_with_gle(Mongo::Constants::OP_DELETE, message, @db.name, nil, write_concern)
    else
      @connection.send_message(Mongo::Constants::OP_DELETE, message)
      true
    end
  end
end

#rename(new_name) ⇒ String

Rename this collection.

Note: If operating in auth mode, the client must be authorized as an admin to perform this operation.

Parameters:

  • new_name (String) —

    the new name for this collection

Returns:

  • (String) —

    the name of the new collection.

Raises:



902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
 
# File 'lib/mongo/collection.rb', line 902

def rename(new_name)
  case new_name
  when Symbol, String
  else
    raise TypeError, "new_name must be a string or symbol"
  end

  new_name = new_name.to_s

  if new_name.empty? or new_name.include? ".."
    raise Mongo::InvalidNSName, "collection names cannot be empty"
  end
  if new_name.include? "$"
    raise Mongo::InvalidNSName, "collection names must not contain '$'"
  end
  if new_name.match(/^\./) or new_name.match(/\.$/)
    raise Mongo::InvalidNSName, "collection names must not start or end with '.'"
  end

  @db.rename_collection(@name, new_name)
  @name = new_name
end

#save(doc, opts = {}) ⇒ ObjectId

Save a document to this collection.

Parameters:

  • doc (Hash) —

    the document to be saved. If the document already has an ‘_id’ key, then an update (upsert) operation will be performed, and any existing document with that _id is overwritten. Otherwise an insert operation is performed.

  • opts (Hash) (defaults to: {}) —

    a customizable set of options

Options Hash (opts):

  • :w, (Hash) —

    :j, :wtimeout, :fsync Set the write concern for this operation. :w > 0 will run a getlasterror command on the database to report any assertion. :j will confirm a write has been committed to the journal, :wtimeout specifies how long to wait for write confirmation, :fsync will confirm that a write has been fsynced. Options provided here will override any write concern options set on this collection, its database object, or the current connection. See the options for DB#get_last_error.

Returns:

  • (ObjectId) —

    the _id of the saved document.

Raises:



325
326
327
328
329
330
331
332
333
 
# File 'lib/mongo/collection.rb', line 325

def save(doc, opts={})
  if doc.has_key?(:_id) || doc.has_key?('_id')
    id = doc[:_id] || doc['_id']
    update({:_id => id}, doc, opts.merge!({:upsert => true}))
    id
  else
    insert(doc, opts)
  end
end

#stats ⇒ Hash

Return stats on the collection. Uses MongoDB’s collstats command.

Returns:



945
946
947
 
# File 'lib/mongo/collection.rb', line 945

def stats
  @db.command({:collstats => @name})
end

#update(selector, document, opts = {}) ⇒ Hash, true

Update one or more documents in this collection.

Parameters:

  • selector (Hash) —

    a hash specifying elements which must be present for a document to be updated. Note: the update command currently updates only the first document matching the given selector. If you want all matching documents to be updated, be sure to specify :multi => true.

  • document (Hash) —

    a hash specifying the fields to be changed in the selected document, or (in the case of an upsert) the document to be inserted

  • opts (Hash) (defaults to: {}) —

    a customizable set of options

Options Hash (opts):

  • :upsert (Boolean) — default: +false+ —

    if true, performs an upsert (update or insert)

  • :multi (Boolean) — default: +false+ —

    update all documents matching the selector, as opposed to just the first matching document. Note: only works in MongoDB 1.1.3 or later.

  • :w (String, Integer, Symbol) — default: 1 —

    Set default number of nodes to which a write should be acknowledged

  • :j (Boolean) — default: false —

    Set journal acknowledgement

  • :wtimeout (Integer) — default: nil —

    Set replica set acknowledgement timeout

  • :fsync (Boolean) — default: false —

    Set fsync acknowledgement.

    Notes on write concern:

    Options provided here will override any write concern options set on this collection,
its database object, or the current connection. See the options for DB#get_last_error.

Returns:

  • (Hash, true) —

    Returns a Hash containing the last error object if acknowledging writes. Otherwise, returns true.

Raises:



455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
 
# File 'lib/mongo/collection.rb', line 455

def update(selector, document, opts={})
  # Initial byte is 0.
  write_concern = get_write_concern(opts, self)
  message = BSON::ByteBuffer.new("\0\0\0\0", @connection.max_message_size)
  BSON::BSON_RUBY.serialize_cstr(message, "#{@db.name}.#{@name}")
  update_options  = 0
  update_options += 1 if opts[:upsert]
  update_options += 2 if opts[:multi]

  # Determine if update document has modifiers and check keys if so
  check_keys = document.keys.first.to_s.start_with?("$") ? false : true

  message.put_int(update_options)
  message.put_binary(BSON::BSON_CODER.serialize(selector, false, true, @connection.max_bson_size).to_s)
  message.put_binary(BSON::BSON_CODER.serialize(document, check_keys, true, @connection.max_bson_size).to_s)

  instrument(:update, :database => @db.name, :collection => @name, :selector => selector, :document => document) do
    if Mongo::WriteConcern.gle?(write_concern)
      @connection.send_message_with_gle(Mongo::Constants::OP_UPDATE, message, @db.name, nil, write_concern)
    else
      @connection.send_message(Mongo::Constants::OP_UPDATE, message)
    end
  end
end