Class: ETL::Processor::CheckExistProcessor

Inherits:
RowProcessor show all
Defined in:
lib/etl/processor/check_exist_processor.rb

Overview

A row-level processor that checks if the row already exists in the target table

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(control, configuration) ⇒ CheckExistProcessor

Initialize the processor Configuration options:

  • :skip: A symbol or array of column names that should not be checked

  • :table: The table name

  • :columns: An array of columns which represent the natural key



26
27
28
29
30
31
32
33
34
 
# File 'lib/etl/processor/check_exist_processor.rb', line 26

def initialize(control, configuration)
  super
  @skip = configuration[:skip] || []
  @table = configuration[:table]
  @columns = configuration[:columns]
  
  q = "SELECT COUNT(*) FROM #{table}"
  @should_check = ETL::ActiveRecord::Base.connection.select_value(q).to_i > 0 
end

Instance Attribute Details

#columns ⇒ Object

An array of columns representing the natural key



13
14
15
 
# File 'lib/etl/processor/check_exist_processor.rb', line 13

def columns
  @columns
end

#should_check ⇒ Object

Is set to true if the processor should execute the check. If there are no rows in the target table then this should return false.



17
18
19
 
# File 'lib/etl/processor/check_exist_processor.rb', line 17

def should_check
  @should_check
end

#skip ⇒ Object

A symbol or array of symbols representing keys that should be skipped



7
8
9
 
# File 'lib/etl/processor/check_exist_processor.rb', line 7

def skip
  @skip
end

#table ⇒ Object

The name of the table to check against



10
11
12
 
# File 'lib/etl/processor/check_exist_processor.rb', line 10

def table
  @table
end

Instance Method Details

#process(row) ⇒ Object

Process the row



52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
 
# File 'lib/etl/processor/check_exist_processor.rb', line 52

def process(row)
  return row unless should_check?
  connection = ETL::ActiveRecord::Base.connection
  q = "SELECT * FROM #{table} WHERE "
  conditions = []
  row.each do |k,v| 
    if columns.nil? || columns.include?(k.to_sym)
      conditions << "#{k} = #{connection.quote(v)}" unless skip?(k.to_sym)
    end
  end
  q << conditions.join(" AND ")

  #puts "query: #{q}"
  result = connection.select_one(q)
  return row if result.nil?
end

#should_check? ⇒ Boolean

Return true if the row should be checked

Returns:

  • (Boolean) 


47
48
49
 
# File 'lib/etl/processor/check_exist_processor.rb', line 47

def should_check?
  @should_check ? true : false
end

#skip?(key) ⇒ Boolean

Return true if the given key should be skipped

Returns:

  • (Boolean) 


37
38
39
40
41
42
43
44
 
# File 'lib/etl/processor/check_exist_processor.rb', line 37

def skip?(key)
  case skip
  when Array
    skip.include?(key)
  else
    skip.to_sym == key.to_sym
  end
end