Class: CSVUtils::CSVCompare

Inherits:
Object
  • Object
show all
Defined in:
lib/csv_utils/csv_compare.rb

Overview

CSVUtils::CSVCompare purpose is to determine which rows in the secondary_data_file need to be created, deleted or updated **requires both CSV files to be sorted on the same columns, CSVUtils::CSVSort can accomplish this In order to receive updates, update_comparison_columns must configured or use inheritance and change the update_row? method

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(primary_data_file, update_comparison_columns = nil, &block) ⇒ CSVCompare

Returns a new instance of CSVCompare.



13
14
15
16
17
 
# File 'lib/csv_utils/csv_compare.rb', line 13

def initialize(primary_data_file, update_comparison_columns=nil, &block)
  @primary_data_file = primary_data_file
  @update_comparison_columns = update_comparison_columns
  @compare_proc = block
end

Instance Attribute Details

#compare_proc ⇒ Object (readonly)

primary_data_file is the source of truth compare_proc used to compare the id column(s) update_comparison_columns column(s) to compare for equality, ex: updated_at, timestamp, hash

caveat: update_comparison_columns need to be in both csv files



9
10
11
 
# File 'lib/csv_utils/csv_compare.rb', line 9

def compare_proc
  @compare_proc
end

#primary_data_file ⇒ Object (readonly)

primary_data_file is the source of truth compare_proc used to compare the id column(s) update_comparison_columns column(s) to compare for equality, ex: updated_at, timestamp, hash

caveat: update_comparison_columns need to be in both csv files



9
10
11
 
# File 'lib/csv_utils/csv_compare.rb', line 9

def primary_data_file
  @primary_data_file
end

#update_comparison_columns ⇒ Object (readonly)

primary_data_file is the source of truth compare_proc used to compare the id column(s) update_comparison_columns column(s) to compare for equality, ex: updated_at, timestamp, hash

caveat: update_comparison_columns need to be in both csv files



9
10
11
 
# File 'lib/csv_utils/csv_compare.rb', line 9

def update_comparison_columns
  @update_comparison_columns
end

Instance Method Details

#compare(secondary_data_file) ⇒ Object 



19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
 
# File 'lib/csv_utils/csv_compare.rb', line 19

def compare(secondary_data_file)
  src = CSV.open(primary_data_file, 'rb')
  src_headers = src.shift
  strip_bom!(src_headers[0])
  dest = CSV.open(secondary_data_file, 'rb')
  dest_headers = dest.shift
  strip_bom!(dest_headers[0])

  read_next_src = true
  read_next_dest = true

  while(!src.eof? || !dest.eof?)
    src_record = next_record_from_file(src_headers, src) if read_next_src
    dest_record = next_record_from_file(dest_headers, dest) if read_next_dest

    if ! src_record
      read_next_src = false
      read_next_dest = true

      yield :delete, dest_record
    elsif ! dest_record
      read_next_src = true
      read_next_dest = false

      yield :create, src_record
    elsif compare_proc.call(src_record, dest_record) == 0
      read_next_src = true
      read_next_dest = true

      yield(:update, src_record) if update_row?(src_record, dest_record)
    elsif compare_proc.call(src_record, dest_record) > 0
      read_next_src = false
      read_next_dest = true

      yield :delete, dest_record
    else
      read_next_src = true
      read_next_dest = false

      yield :create, src_record
    end
  end

  src.close
  dest.close
end