2008-12-17 16:49:06 +00:00
|
|
|
# --
|
2009-01-06 15:51:01 +00:00
|
|
|
# Copyright (C) 2008-2009 10gen Inc.
|
2008-11-22 01:00:51 +00:00
|
|
|
#
|
2009-02-15 13:24:14 +00:00
|
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
|
|
# you may not use this file except in compliance with the License.
|
|
|
|
# You may obtain a copy of the License at
|
2008-11-22 01:00:51 +00:00
|
|
|
#
|
2009-02-15 13:24:14 +00:00
|
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
2008-11-22 01:00:51 +00:00
|
|
|
#
|
2009-02-15 13:24:14 +00:00
|
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
# See the License for the specific language governing permissions and
|
|
|
|
# limitations under the License.
|
2008-12-17 16:49:06 +00:00
|
|
|
# ++
|
2008-11-22 01:00:51 +00:00
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
module Mongo
|
2008-11-22 01:00:51 +00:00
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# A named collection of documents in a database.
|
2009-08-20 14:50:48 +00:00
|
|
|
class Collection
|
2009-08-17 15:11:03 +00:00
|
|
|
|
2009-10-19 21:14:41 +00:00
|
|
|
attr_reader :db, :name, :pk_factory, :hint
|
2009-01-13 20:51:41 +00:00
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Initialize a collection object.
|
|
|
|
#
|
|
|
|
# @param [DB] db a MongoDB database instance.
|
|
|
|
# @param [String, Symbol] name the name of the collection.
|
|
|
|
#
|
|
|
|
# @raise [InvalidName]
|
|
|
|
# if collection name is empty, contains '$', or starts or ends with '.'
|
|
|
|
#
|
|
|
|
# @raise [TypeError]
|
|
|
|
# if collection name is not a string or symbol
|
|
|
|
#
|
|
|
|
# @return [Collection]
|
2009-10-19 21:14:41 +00:00
|
|
|
def initialize(db, name, pk_factory=nil)
|
2009-08-20 14:50:48 +00:00
|
|
|
case name
|
|
|
|
when Symbol, String
|
|
|
|
else
|
|
|
|
raise TypeError, "new_name must be a string or symbol"
|
|
|
|
end
|
2008-11-22 01:00:51 +00:00
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
name = name.to_s
|
2009-08-14 19:39:49 +00:00
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
if name.empty? or name.include? ".."
|
|
|
|
raise InvalidName, "collection names cannot be empty"
|
|
|
|
end
|
2009-12-04 21:35:12 +00:00
|
|
|
if name.include? "$"
|
|
|
|
raise InvalidName, "collection names must not contain '$'" unless name =~ /((^\$cmd)|(oplog\.\$main))/
|
2009-08-20 14:50:48 +00:00
|
|
|
end
|
|
|
|
if name.match(/^\./) or name.match(/\.$/)
|
|
|
|
raise InvalidName, "collection names must not start or end with '.'"
|
|
|
|
end
|
2009-06-02 18:37:58 +00:00
|
|
|
|
2009-10-19 21:14:41 +00:00
|
|
|
@db, @name = db, name
|
2009-11-23 20:20:05 +00:00
|
|
|
@connection = @db.connection
|
2009-10-19 21:14:41 +00:00
|
|
|
@pk_factory = pk_factory || ObjectID
|
2009-08-20 14:50:48 +00:00
|
|
|
@hint = nil
|
|
|
|
end
|
2009-02-09 14:46:30 +00:00
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Return a sub-collection of this collection by name. If 'users' is a collection, then
|
|
|
|
# 'users.comments' is a sub-collection of users.
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @param [String] name
|
|
|
|
# the collection to return
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @raise [InvalidName]
|
|
|
|
# if passed an invalid collection name
|
|
|
|
#
|
|
|
|
# @return [Collection]
|
|
|
|
# the specified sub-collection
|
2009-08-20 14:50:48 +00:00
|
|
|
def [](name)
|
|
|
|
name = "#{self.name}.#{name}"
|
2009-09-14 14:03:26 +00:00
|
|
|
return Collection.new(db, name) if !db.strict? || db.collection_names.include?(name)
|
2009-08-20 14:50:48 +00:00
|
|
|
raise "Collection #{name} doesn't exist. Currently in strict mode."
|
|
|
|
end
|
2008-11-22 01:00:51 +00:00
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Set a hint field for query optimizer. Hint may be a single field
|
|
|
|
# name, array of field names, or a hash (preferably an [OrderedHash]).
|
|
|
|
# If using MongoDB > 1.1, you probably don't ever need to set a hint.
|
|
|
|
#
|
|
|
|
# @param [String, Array, OrderedHash] hint a single field, an array of
|
|
|
|
# fields, or a hash specifying fields
|
|
|
|
def hint=(hint=nil)
|
2009-08-20 14:50:48 +00:00
|
|
|
@hint = normalize_hint_fields(hint)
|
|
|
|
self
|
|
|
|
end
|
2008-11-22 01:00:51 +00:00
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
# Query the database.
|
|
|
|
#
|
|
|
|
# The +selector+ argument is a prototype document that all results must
|
|
|
|
# match. For example:
|
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# collection.find({"hello" => "world"})
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
|
|
|
# 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.
|
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @param [Hash] selector
|
|
|
|
# a document specifying elements which must be present for a
|
|
|
|
# document to be included in the result set.
|
|
|
|
#
|
|
|
|
# @option opts [Array] :fields field names that should be returned in the result
|
|
|
|
# set ("_id" will always be included). By limiting results to a certain subset of fields,
|
|
|
|
# you can cut down on network traffic and decoding time.
|
|
|
|
# @option opts [Integer] :skip number of documents to skip from the beginning of the result set
|
|
|
|
# @option opts [Integer] :limit maximum number of documents to return
|
|
|
|
# @option opts [Array] :sort 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)
|
|
|
|
# @option opts [String, Array, OrderedHash] :hint hint for query optimizer, usually not necessary if using MongoDB > 1.1
|
|
|
|
# @option opts [Boolean] :snapshot ('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 http://www.mongodb.org/display/DOCS/How+to+do+Snapshotting+in+the+Mongo+Database
|
|
|
|
# @option opts [Boolean] :timeout ('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 inadvertant failure to
|
|
|
|
# close the cursor, as the cursor is explicitly closed when block code finishes.
|
|
|
|
#
|
|
|
|
# @raise [ArgumentError]
|
|
|
|
# if timeout is set to false and find is not invoked in a block
|
|
|
|
#
|
|
|
|
# @raise [RuntimeError]
|
|
|
|
# if given unknown options
|
|
|
|
def find(selector={}, opts={})
|
|
|
|
fields = opts.delete(:fields)
|
2009-08-20 14:50:48 +00:00
|
|
|
fields = ["_id"] if fields && fields.empty?
|
2010-01-05 22:42:52 +00:00
|
|
|
skip = opts.delete(:skip) || skip || 0
|
|
|
|
limit = opts.delete(:limit) || 0
|
|
|
|
sort = opts.delete(:sort)
|
|
|
|
hint = opts.delete(:hint)
|
|
|
|
snapshot = opts.delete(:snapshot)
|
|
|
|
if opts[:timeout] == false && !block_given?
|
2009-12-08 22:52:07 +00:00
|
|
|
raise ArgumentError, "Timeout can be set to false only when #find is invoked with a block."
|
2009-10-14 18:38:44 +00:00
|
|
|
end
|
2010-01-05 22:42:52 +00:00
|
|
|
timeout = block_given? ? (opts.delete(:timeout) || true) : true
|
2009-08-20 14:50:48 +00:00
|
|
|
if hint
|
|
|
|
hint = normalize_hint_fields(hint)
|
|
|
|
else
|
|
|
|
hint = @hint # assumed to be normalized already
|
|
|
|
end
|
2010-01-05 22:42:52 +00:00
|
|
|
raise RuntimeError, "Unknown options [#{opts.inspect}]" unless opts.empty?
|
2009-08-20 14:50:48 +00:00
|
|
|
|
2009-12-08 22:52:07 +00:00
|
|
|
cursor = Cursor.new(self, :selector => selector, :fields => fields, :skip => skip, :limit => limit,
|
2009-10-22 18:10:12 +00:00
|
|
|
:order => sort, :hint => hint, :snapshot => snapshot, :timeout => timeout)
|
2009-08-20 14:50:48 +00:00
|
|
|
if block_given?
|
|
|
|
yield cursor
|
|
|
|
cursor.close()
|
|
|
|
nil
|
|
|
|
else
|
|
|
|
cursor
|
|
|
|
end
|
|
|
|
end
|
2008-11-22 01:00:51 +00:00
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Return a single object from the database.
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @return [OrderedHash, Nil]
|
|
|
|
# a single document or nil if no result is found.
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @param [Hash, ObjectID, Nil] spec_or_object_id a hash specifying elements
|
|
|
|
# which must be present for a document to be included in the result set or an
|
2009-08-20 14:50:48 +00:00
|
|
|
# instance of ObjectID to be used as the value for an _id query.
|
2010-01-05 22:42:52 +00:00
|
|
|
# If nil, an empty selector, {}, will be used.
|
|
|
|
#
|
|
|
|
# @option opts [Hash]
|
|
|
|
# any valid options that can be send to Collection#find
|
|
|
|
#
|
|
|
|
# @raise [TypeError]
|
|
|
|
# if the argument is of an improper type.
|
|
|
|
def find_one(spec_or_object_id=nil, opts={})
|
2009-08-20 14:50:48 +00:00
|
|
|
spec = case spec_or_object_id
|
|
|
|
when nil
|
|
|
|
{}
|
|
|
|
when 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
|
2010-01-05 22:42:52 +00:00
|
|
|
find(spec, opts.merge(:limit => -1)).next_document
|
2009-08-20 14:50:48 +00:00
|
|
|
end
|
2008-11-22 01:00:51 +00:00
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Save a document to this collection.
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @param [Hash] doc
|
|
|
|
# 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.
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @return [ObjectID] the _id of the saved document.
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @option opts [Boolean] :safe (+false+)
|
|
|
|
# If true, check that the save succeeded. OperationFailure
|
|
|
|
# will be raised on an error. Note that a safe check requires an extra
|
|
|
|
# round-trip to the database.
|
|
|
|
def save(doc, options={})
|
|
|
|
if doc.has_key?(:_id) || doc.has_key?('_id')
|
|
|
|
id = doc[:_id] || doc['_id']
|
|
|
|
update({:_id => id}, doc, :upsert => true, :safe => options.delete(:safe))
|
2009-08-20 14:50:48 +00:00
|
|
|
id
|
|
|
|
else
|
2010-01-05 22:42:52 +00:00
|
|
|
insert(doc, :safe => options.delete(:safe))
|
2009-08-20 14:50:48 +00:00
|
|
|
end
|
|
|
|
end
|
2009-08-13 19:18:53 +00:00
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Insert one or more documents into the collection.
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @param [Hash, Array] doc_or_docs
|
|
|
|
# a document (as a hash) or array of documents to be inserted.
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @return [ObjectID, Array]
|
|
|
|
# the _id of the inserted document or a list of _ids of all inserted documents.
|
|
|
|
# Note: the object may have been modified by the database's PK factory, if it has one.
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @option opts [Boolean] :safe (+false+)
|
|
|
|
# If true, check that the save succeeded. OperationFailure
|
|
|
|
# will be raised on an error. Note that a safe check requires an extra
|
|
|
|
# round-trip to the database.
|
2009-08-20 14:50:48 +00:00
|
|
|
def insert(doc_or_docs, options={})
|
2009-10-19 21:14:41 +00:00
|
|
|
doc_or_docs = [doc_or_docs] unless doc_or_docs.is_a?(Array)
|
|
|
|
doc_or_docs.collect! { |doc| @pk_factory.create_pk(doc) }
|
2009-11-05 20:14:48 +00:00
|
|
|
result = insert_documents(doc_or_docs, @name, true, options[:safe])
|
2009-10-19 21:14:41 +00:00
|
|
|
result.size > 1 ? result : result.first
|
2009-08-20 14:50:48 +00:00
|
|
|
end
|
|
|
|
alias_method :<<, :insert
|
2008-11-22 01:00:51 +00:00
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Remove all documents from this collection.
|
|
|
|
#
|
|
|
|
# @param [Hash] selector
|
|
|
|
# If specified, only matching documents will be removed.
|
2009-12-08 22:52:07 +00:00
|
|
|
#
|
2010-01-08 20:43:13 +00:00
|
|
|
# @example remove all documents from the 'users' collection:
|
|
|
|
# users.remove
|
|
|
|
# users.remove({})
|
2009-10-20 15:31:07 +00:00
|
|
|
#
|
2010-01-08 20:43:13 +00:00
|
|
|
# @example remove only documents that have expired:
|
|
|
|
# users.remove({:expire => {"$lte" => Time.now}})
|
2009-10-19 21:48:20 +00:00
|
|
|
def remove(selector={})
|
2009-10-19 21:14:41 +00:00
|
|
|
message = ByteBuffer.new
|
|
|
|
message.put_int(0)
|
2009-12-01 22:23:24 +00:00
|
|
|
BSON_RUBY.serialize_cstr(message, "#{@db.name}.#{@name}")
|
2009-10-19 21:14:41 +00:00
|
|
|
message.put_int(0)
|
2009-12-02 16:56:58 +00:00
|
|
|
message.put_array(BSON.serialize(selector, false).unpack("C*"))
|
2009-11-24 19:23:43 +00:00
|
|
|
@connection.send_message(Mongo::Constants::OP_DELETE, message,
|
2009-11-02 20:04:06 +00:00
|
|
|
"db.#{@db.name}.remove(#{selector.inspect})")
|
2009-08-20 14:50:48 +00:00
|
|
|
end
|
2008-11-22 01:00:51 +00:00
|
|
|
|
2009-09-06 20:28:46 +00:00
|
|
|
# Update a single document in this collection.
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @param [Hash] selector
|
|
|
|
# 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.
|
|
|
|
# @param [Hash] document
|
|
|
|
# a hash specifying the fields to be changed in the selected document,
|
|
|
|
# or (in the case of an upsert) the document to be inserted
|
|
|
|
#
|
|
|
|
# @option [Boolean] :upsert (+false+) if true, performs an upsert (update or insert)
|
|
|
|
# @option [Boolean] :multi (+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.
|
|
|
|
# @option opts [Boolean] :safe (+false+)
|
|
|
|
# If true, check that the save succeeded. OperationFailure
|
|
|
|
# will be raised on an error. Note that a safe check requires an extra
|
|
|
|
# round-trip to the database.
|
2009-11-05 21:08:54 +00:00
|
|
|
def update(selector, document, options={})
|
2009-10-19 21:14:41 +00:00
|
|
|
message = ByteBuffer.new
|
|
|
|
message.put_int(0)
|
2009-12-01 22:23:24 +00:00
|
|
|
BSON_RUBY.serialize_cstr(message, "#{@db.name}.#{@name}")
|
2009-11-05 21:08:54 +00:00
|
|
|
update_options = 0
|
|
|
|
update_options += 1 if options[:upsert]
|
|
|
|
update_options += 2 if options[:multi]
|
|
|
|
message.put_int(update_options)
|
2009-12-02 16:56:58 +00:00
|
|
|
message.put_array(BSON.serialize(selector, false).unpack("C*"))
|
|
|
|
message.put_array(BSON.serialize(document, false).unpack("C*"))
|
2009-11-05 20:14:48 +00:00
|
|
|
if options[:safe]
|
2009-11-23 20:20:05 +00:00
|
|
|
@connection.send_message_with_safe_check(Mongo::Constants::OP_UPDATE, message, @db.name,
|
2009-11-05 21:08:54 +00:00
|
|
|
"db.#{@name}.update(#{selector.inspect}, #{document.inspect})")
|
2009-11-05 20:14:48 +00:00
|
|
|
else
|
2009-12-08 22:52:07 +00:00
|
|
|
@connection.send_message(Mongo::Constants::OP_UPDATE, message,
|
2009-11-05 21:08:54 +00:00
|
|
|
"db.#{@name}.update(#{selector.inspect}, #{document.inspect})")
|
2009-08-20 14:50:48 +00:00
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Create a new index.
|
|
|
|
#
|
|
|
|
# @param [String, Array] field_or_spec
|
|
|
|
# should be either a single field name or an array of
|
|
|
|
# [field name, direction] pairs. Directions should be specified as Mongo::ASCENDING or Mongo::DESCENDING.
|
|
|
|
#
|
|
|
|
# @param [Boolean] unique if true, this index will enforce a uniqueness constraint.
|
2010-01-11 23:11:38 +00:00
|
|
|
#
|
|
|
|
# @return [String] the name of the index created.
|
2009-08-20 14:50:48 +00:00
|
|
|
def create_index(field_or_spec, unique=false)
|
2009-10-19 21:14:41 +00:00
|
|
|
field_h = OrderedHash.new
|
|
|
|
if field_or_spec.is_a?(String) || field_or_spec.is_a?(Symbol)
|
|
|
|
field_h[field_or_spec.to_s] = 1
|
|
|
|
else
|
|
|
|
field_or_spec.each { |f| field_h[f[0].to_s] = f[1] }
|
|
|
|
end
|
|
|
|
name = generate_index_names(field_h)
|
|
|
|
sel = {
|
|
|
|
:name => name,
|
|
|
|
:ns => "#{@db.name}.#{@name}",
|
|
|
|
:key => field_h,
|
|
|
|
:unique => unique }
|
|
|
|
insert_documents([sel], Mongo::DB::SYSTEM_INDEX_COLLECTION, false)
|
|
|
|
name
|
2009-08-20 14:50:48 +00:00
|
|
|
end
|
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Drop a specified index.
|
|
|
|
#
|
|
|
|
# @param [String] name
|
2009-08-20 14:50:48 +00:00
|
|
|
def drop_index(name)
|
|
|
|
@db.drop_index(@name, name)
|
|
|
|
end
|
2009-01-15 16:25:23 +00:00
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
# Drop all indexes.
|
|
|
|
def drop_indexes
|
2010-01-05 22:42:52 +00:00
|
|
|
|
|
|
|
# Note: calling drop_indexes with no args will drop them all.
|
2009-08-20 14:50:48 +00:00
|
|
|
@db.drop_index(@name, '*')
|
2010-01-05 22:42:52 +00:00
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
end
|
|
|
|
|
|
|
|
# Drop the entire collection. USE WITH CAUTION.
|
|
|
|
def drop
|
|
|
|
@db.drop_collection(@name)
|
|
|
|
end
|
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Perform a map/reduce operation on the current collection.
|
|
|
|
#
|
|
|
|
# @param [String, Code] map a map function, written in JavaScript.
|
|
|
|
# @param [String, Code] reduce a reduce function, written in JavaScript.
|
|
|
|
#
|
|
|
|
# @option opts [Hash] :query ({}) a query selector document, like what's passed to #find, to limit
|
|
|
|
# the operation to a subset of the collection.
|
|
|
|
# @option opts [Array] :sort ([]) 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)
|
|
|
|
# @option opts [Integer] :limit (nil) if passing a query, number of objects to return from the collection.
|
|
|
|
# @option opts [String, Code] :finalize (nil) a javascript function to apply to the result set after the
|
|
|
|
# map/reduce operation has finished.
|
|
|
|
# @option opts [String] :out (nil) the name of the output collection. If specified, the collection will not be treated as temporary.
|
|
|
|
# @option opts [Boolean] :keeptemp (false) if true, the generated collection will be persisted. default is false.
|
|
|
|
# @option opts [Boolean ] :verbose (false) if true, provides statistics on job execution time.
|
|
|
|
#
|
|
|
|
# @return [Collection] a collection containing the results of the operation.
|
|
|
|
#
|
|
|
|
# @see http://www.mongodb.org/display/DOCS/MapReduce Offical MongoDB map/reduce documentation.
|
|
|
|
def map_reduce(map, reduce, opts={})
|
2009-11-25 16:25:50 +00:00
|
|
|
map = Code.new(map) unless map.is_a?(Code)
|
|
|
|
reduce = Code.new(reduce) unless reduce.is_a?(Code)
|
2009-11-23 08:04:48 +00:00
|
|
|
|
|
|
|
hash = OrderedHash.new
|
|
|
|
hash['mapreduce'] = self.name
|
|
|
|
hash['map'] = map
|
|
|
|
hash['reduce'] = reduce
|
2010-01-05 22:42:52 +00:00
|
|
|
hash.merge! opts
|
2009-11-23 08:04:48 +00:00
|
|
|
|
2009-11-25 16:25:50 +00:00
|
|
|
result = @db.command(hash)
|
|
|
|
unless result["ok"] == 1
|
2009-12-08 22:52:07 +00:00
|
|
|
raise Mongo::OperationFailure, "map-reduce failed: #{result['errmsg']}"
|
2009-11-23 08:04:48 +00:00
|
|
|
end
|
2009-11-25 16:25:50 +00:00
|
|
|
@db[result["result"]]
|
2009-11-23 08:04:48 +00:00
|
|
|
end
|
2009-11-25 16:25:50 +00:00
|
|
|
alias :mapreduce :map_reduce
|
2009-11-23 08:04:48 +00:00
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Perform a group aggregation.
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @param [Array, String, Code, Nil] :key either 1) an array of fields to group by,
|
|
|
|
# 2) a javascript function to generate the key object, or 3) nil.
|
|
|
|
# @param [Hash] condition an optional document specifying a query to limit the documents over which group is run.
|
|
|
|
# @param [Hash] initial initial value of the aggregation counter object
|
|
|
|
# @param [String, Code] reduce aggregation function, in JavaScript
|
|
|
|
# @param [String, Code] finalize :: optional. a JavaScript function that receives and modifies
|
2009-12-07 20:46:39 +00:00
|
|
|
# each of the resultant grouped objects. Available only when group is run
|
|
|
|
# with command set to true.
|
2010-01-05 22:42:52 +00:00
|
|
|
# @param [Boolean] command if true, run the group as a command instead of in an
|
|
|
|
# eval. Note: Running group as eval has been DEPRECATED.
|
|
|
|
#
|
|
|
|
# @return [Array] the grouped items.
|
2009-12-18 19:48:44 +00:00
|
|
|
def group(key, condition, initial, reduce, command=false, finalize=nil)
|
2009-12-06 23:45:42 +00:00
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
if command
|
2009-08-26 15:13:40 +00:00
|
|
|
|
2009-12-18 19:48:44 +00:00
|
|
|
reduce = Code.new(reduce) unless reduce.is_a?(Code)
|
2009-12-06 23:45:42 +00:00
|
|
|
|
|
|
|
group_command = {
|
|
|
|
"group" => {
|
|
|
|
"ns" => @name,
|
|
|
|
"$reduce" => reduce,
|
|
|
|
"cond" => condition,
|
|
|
|
"initial" => initial
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2009-12-18 19:48:44 +00:00
|
|
|
unless key.nil?
|
|
|
|
if key.is_a? Array
|
|
|
|
key_type = "key"
|
|
|
|
key_value = {}
|
|
|
|
key.each { |k| key_value[k] = 1 }
|
|
|
|
else
|
|
|
|
key_type = "$keyf"
|
|
|
|
key_value = key.is_a?(Code) ? key : Code.new(key)
|
|
|
|
end
|
|
|
|
|
|
|
|
group_command["group"][key_type] = key_value
|
|
|
|
end
|
|
|
|
|
2009-12-06 23:45:42 +00:00
|
|
|
# only add finalize if specified
|
|
|
|
if finalize
|
|
|
|
finalize = Code.new(finalize) unless finalize.is_a?(Code)
|
|
|
|
group_command['group']['finalize'] = finalize
|
|
|
|
end
|
|
|
|
|
|
|
|
result = @db.command group_command
|
2009-08-26 15:13:40 +00:00
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
if result["ok"] == 1
|
|
|
|
return result["retval"]
|
|
|
|
else
|
|
|
|
raise OperationFailure, "group command failed: #{result['errmsg']}"
|
|
|
|
end
|
2009-08-26 15:13:40 +00:00
|
|
|
|
|
|
|
else
|
2009-12-18 19:48:44 +00:00
|
|
|
|
|
|
|
warn "Collection#group must now be run as a command; you can do this by passing 'true' as the command argument."
|
|
|
|
|
|
|
|
raise OperationFailure, ":finalize can be specified only when " +
|
|
|
|
"group is run as a command (set command param to true)" if finalize
|
|
|
|
|
|
|
|
raise OperationFailure, "key must be an array of fields to group by. If you want to pass a key function,
|
|
|
|
run group as a command by passing 'true' as the command argument." unless key.is_a? Array || key.nil?
|
|
|
|
|
|
|
|
case reduce
|
|
|
|
when Code
|
|
|
|
scope = reduce.scope
|
|
|
|
else
|
|
|
|
scope = {}
|
|
|
|
end
|
|
|
|
scope.merge!({
|
|
|
|
"ns" => @name,
|
|
|
|
"keys" => key,
|
|
|
|
"condition" => condition,
|
|
|
|
"initial" => initial })
|
2009-08-26 15:13:40 +00:00
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
group_function = <<EOS
|
2009-04-27 18:19:38 +00:00
|
|
|
function () {
|
|
|
|
var c = db[ns].find(condition);
|
|
|
|
var map = new Map();
|
|
|
|
var reduce_function = #{reduce};
|
|
|
|
while (c.hasNext()) {
|
|
|
|
var obj = c.next();
|
|
|
|
|
|
|
|
var key = {};
|
2009-08-19 19:18:42 +00:00
|
|
|
for (var i = 0; i < keys.length; i++) {
|
|
|
|
var k = keys[i];
|
|
|
|
key[k] = obj[k];
|
2009-04-27 18:19:38 +00:00
|
|
|
}
|
|
|
|
|
2009-06-08 15:08:59 +00:00
|
|
|
var aggObj = map.get(key);
|
2009-04-27 18:19:38 +00:00
|
|
|
if (aggObj == null) {
|
|
|
|
var newObj = Object.extend({}, key);
|
2009-06-08 15:08:59 +00:00
|
|
|
aggObj = Object.extend(newObj, initial);
|
|
|
|
map.put(key, aggObj);
|
2009-04-27 18:19:38 +00:00
|
|
|
}
|
|
|
|
reduce_function(obj, aggObj);
|
|
|
|
}
|
|
|
|
return {"result": map.values()};
|
|
|
|
}
|
|
|
|
EOS
|
2009-12-18 19:48:44 +00:00
|
|
|
@db.eval(Code.new(group_function, scope))["result"]
|
|
|
|
end
|
2009-08-20 14:50:48 +00:00
|
|
|
end
|
2009-04-27 18:19:38 +00:00
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Return a list of distinct values for +key+ across all
|
2009-10-27 18:05:45 +00:00
|
|
|
# documents in the collection. The key may use dot notation
|
|
|
|
# to reach into an embedded object.
|
2010-01-05 22:42:52 +00:00
|
|
|
#
|
|
|
|
# @param [String, Symbol, OrderedHash] key or hash to group by.
|
|
|
|
# @param [Hash] query a selector for limiting the result set over which to group.
|
|
|
|
#
|
|
|
|
# @example Saving zip codes and ages and returning distinct results.
|
2009-10-27 18:05:45 +00:00
|
|
|
# @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]
|
2009-12-14 18:57:22 +00:00
|
|
|
#
|
2010-01-08 20:43:13 +00:00
|
|
|
# # You may also pass a document selector as the second parameter
|
|
|
|
# # to limit the documents over which distinct is run:
|
2009-12-14 18:57:22 +00:00
|
|
|
# @collection.distinct("name.age", {"name.age" => {"$gt" => 24}})
|
|
|
|
# [27]
|
2010-01-05 22:42:52 +00:00
|
|
|
#
|
|
|
|
# @return [Array] an array of distinct values.
|
2009-12-14 18:57:22 +00:00
|
|
|
def distinct(key, query=nil)
|
2009-10-27 18:05:45 +00:00
|
|
|
raise MongoArgumentError unless [String, Symbol].include?(key.class)
|
|
|
|
command = OrderedHash.new
|
|
|
|
command[:distinct] = @name
|
2009-12-14 18:57:22 +00:00
|
|
|
command[:key] = key.to_s
|
|
|
|
command[:query] = query
|
2009-10-27 18:05:45 +00:00
|
|
|
|
2009-11-23 20:20:05 +00:00
|
|
|
@db.command(command)["values"]
|
2009-10-27 18:05:45 +00:00
|
|
|
end
|
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
# Rename this collection.
|
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# Note: If operating in auth mode, the client must be authorized as an admin to
|
|
|
|
# perform this operation.
|
|
|
|
#
|
|
|
|
# @param [String ] new_name the new name for this collection
|
2009-08-20 14:50:48 +00:00
|
|
|
#
|
2010-01-05 22:42:52 +00:00
|
|
|
# @raise [InvalidName] if +new_name+ is an invalid collection name.
|
2009-08-20 14:50:48 +00:00
|
|
|
def rename(new_name)
|
|
|
|
case new_name
|
|
|
|
when Symbol, String
|
|
|
|
else
|
|
|
|
raise TypeError, "new_name must be a string or symbol"
|
|
|
|
end
|
2009-08-04 18:16:02 +00:00
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
new_name = new_name.to_s
|
2008-11-22 01:00:51 +00:00
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
if new_name.empty? or new_name.include? ".."
|
|
|
|
raise InvalidName, "collection names cannot be empty"
|
|
|
|
end
|
|
|
|
if new_name.include? "$"
|
|
|
|
raise InvalidName, "collection names must not contain '$'"
|
|
|
|
end
|
|
|
|
if new_name.match(/^\./) or new_name.match(/\.$/)
|
|
|
|
raise InvalidName, "collection names must not start or end with '.'"
|
|
|
|
end
|
2008-12-17 18:52:10 +00:00
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
@db.rename_collection(@name, new_name)
|
|
|
|
end
|
2008-11-22 01:00:51 +00:00
|
|
|
|
2010-01-05 22:42:52 +00:00
|
|
|
# Get information on the indexes for this collection.
|
|
|
|
#
|
|
|
|
# @return [Hash] a hash where the keys are index names.
|
2009-08-20 14:50:48 +00:00
|
|
|
def index_information
|
|
|
|
@db.index_information(@name)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Return a hash containing options that apply to this collection.
|
2010-01-05 22:42:52 +00:00
|
|
|
# For all possible keys and values, see DB#create_collection.
|
|
|
|
#
|
|
|
|
# @return [Hash] options that apply to this collection.
|
2009-08-20 14:50:48 +00:00
|
|
|
def options
|
2009-12-16 19:03:15 +00:00
|
|
|
@db.collections_info(@name).next_document['options']
|
2009-08-20 14:50:48 +00:00
|
|
|
end
|
|
|
|
|
|
|
|
# Get the number of documents in this collection.
|
2010-01-05 22:42:52 +00:00
|
|
|
#
|
|
|
|
# @return [Integer]
|
|
|
|
def count
|
2009-09-17 19:28:45 +00:00
|
|
|
find().count()
|
2009-08-20 14:50:48 +00:00
|
|
|
end
|
|
|
|
|
2009-10-13 20:20:41 +00:00
|
|
|
alias :size :count
|
|
|
|
|
2009-08-20 14:50:48 +00:00
|
|
|
protected
|
|
|
|
|
|
|
|
def normalize_hint_fields(hint)
|
|
|
|
case hint
|
|
|
|
when String
|
|
|
|
{hint => 1}
|
|
|
|
when Hash
|
|
|
|
hint
|
|
|
|
when nil
|
|
|
|
nil
|
|
|
|
else
|
|
|
|
h = OrderedHash.new
|
|
|
|
hint.to_a.each { |k| h[k] = 1 }
|
|
|
|
h
|
2008-11-22 01:00:51 +00:00
|
|
|
end
|
|
|
|
end
|
2009-10-19 21:14:41 +00:00
|
|
|
|
|
|
|
private
|
|
|
|
|
2009-12-16 19:03:15 +00:00
|
|
|
# Sends a Mongo::Constants::OP_INSERT message to the database.
|
2009-10-19 21:14:41 +00:00
|
|
|
# Takes an array of +documents+, an optional +collection_name+, and a
|
|
|
|
# +check_keys+ setting.
|
2009-11-05 20:14:48 +00:00
|
|
|
def insert_documents(documents, collection_name=@name, check_keys=true, safe=false)
|
2009-10-19 21:14:41 +00:00
|
|
|
message = ByteBuffer.new
|
|
|
|
message.put_int(0)
|
2009-12-01 22:23:24 +00:00
|
|
|
BSON_RUBY.serialize_cstr(message, "#{@db.name}.#{collection_name}")
|
2009-12-02 16:56:58 +00:00
|
|
|
documents.each { |doc| message.put_array(BSON.serialize(doc, check_keys).unpack("C*")) }
|
2009-11-05 20:14:48 +00:00
|
|
|
if safe
|
2009-11-23 20:20:05 +00:00
|
|
|
@connection.send_message_with_safe_check(Mongo::Constants::OP_INSERT, message, @db.name,
|
2009-11-05 20:14:48 +00:00
|
|
|
"db.#{collection_name}.insert(#{documents.inspect})")
|
|
|
|
else
|
2009-11-24 19:23:43 +00:00
|
|
|
@connection.send_message(Mongo::Constants::OP_INSERT, message,
|
2009-11-05 20:14:48 +00:00
|
|
|
"db.#{collection_name}.insert(#{documents.inspect})")
|
|
|
|
end
|
2009-10-19 21:14:41 +00:00
|
|
|
documents.collect { |o| o[:_id] || o['_id'] }
|
|
|
|
end
|
|
|
|
|
|
|
|
def generate_index_names(spec)
|
|
|
|
indexes = []
|
|
|
|
spec.each_pair do |field, direction|
|
|
|
|
indexes.push("#{field}_#{direction}")
|
2009-12-08 22:52:07 +00:00
|
|
|
end
|
2009-10-19 21:14:41 +00:00
|
|
|
indexes.join("_")
|
|
|
|
end
|
2008-11-22 01:00:51 +00:00
|
|
|
end
|
2009-11-17 18:20:57 +00:00
|
|
|
|
2008-11-22 01:00:51 +00:00
|
|
|
end
|