Class: RedshiftConnector::S3DataFileBundle

Inherits:
AbstractDataFileBundle
  • Object
show all
Defined in:
lib/redshift-connector/s3_data_file_bundle.rb

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(bucket, prefix, format: :csv, filter: nil, batch_size: 1000, logger: RedshiftConnector.logger) ⇒ S3DataFileBundle



19
20
21
22
23
24
25
26
27
# File 'lib/redshift-connector/s3_data_file_bundle.rb', line 19

def initialize(bucket, prefix, format: :csv, filter: nil, batch_size: 1000, logger: RedshiftConnector.logger)
  @bucket = bucket
  @prefix = prefix
  @format = format
  @filter = filter || lambda {|*row| row }
  @batch_size = batch_size
  @logger = logger
  @reader_class = Reader.get(format)
end

Instance Attribute Details

#bucketObject (readonly)

Returns the value of attribute bucket.



29
30
31
# File 'lib/redshift-connector/s3_data_file_bundle.rb', line 29

def bucket
  @bucket
end

#prefixObject (readonly)

Returns the value of attribute prefix.



30
31
32
# File 'lib/redshift-connector/s3_data_file_bundle.rb', line 30

def prefix
  @prefix
end

Class Method Details

.for_prefix(bucket: S3Bucket.default, prefix:, format:, filter: nil, batch_size: 1000, logger: RedshiftConnector.logger) ⇒ Object



9
10
11
12
# File 'lib/redshift-connector/s3_data_file_bundle.rb', line 9

def self.for_prefix(bucket: S3Bucket.default, prefix:, format:, filter: nil, batch_size: 1000, logger: RedshiftConnector.logger)
  real_prefix = "#{bucket.prefix}/#{prefix}"
  new(bucket, real_prefix, format: format, filter: filter, batch_size: batch_size, logger: logger)
end

.for_table(bucket: S3Bucket.default, schema:, table:, txn_id:, filter: nil, batch_size: 1000, logger: RedshiftConnector.logger) ⇒ Object



14
15
16
17
# File 'lib/redshift-connector/s3_data_file_bundle.rb', line 14

def self.for_table(bucket: S3Bucket.default, schema:, table:, txn_id:, filter: nil, batch_size: 1000, logger: RedshiftConnector.logger)
  prefix = "#{bucket.prefix}/#{schema}_export/#{table}/#{txn_id}/#{table}.csv."
  new(bucket, prefix, format: :redshift_csv, filter: filter, batch_size: batch_size, logger: logger)
end

Instance Method Details

#clearObject



45
46
47
48
49
50
51
52
# File 'lib/redshift-connector/s3_data_file_bundle.rb', line 45

def clear
  pref = File.dirname(@prefix) + '/'
  keys = @bucket.objects(prefix: pref).map(&:key)
  unless keys.empty?
    @logger.info "DELETE #{pref}*"
    @bucket.delete_objects(keys)
  end
end

#credential_stringObject



36
37
38
# File 'lib/redshift-connector/s3_data_file_bundle.rb', line 36

def credential_string
  @bucket.credential_string
end

#data_filesObject



40
41
42
43
# File 'lib/redshift-connector/s3_data_file_bundle.rb', line 40

def data_files
  @bucket.objects(prefix: @prefix)
    .map {|obj| S3DataFile.new(obj, reader_class: @reader_class) }
end

#urlObject



32
33
34
# File 'lib/redshift-connector/s3_data_file_bundle.rb', line 32

def url
  "s3://#{@bucket.name}/#{@prefix}"
end