Class: HsbcPdfStatementParser::Parser

Inherits:
Object
  • Object
show all
Defined in:
lib/hsbc_pdf_statement_parser/parser.rb

Instance Method Summary collapse

Constructor Details

#initialize(filename) ⇒ Parser

Creates a new parser from a PDF file.

Parameters

filename

the filename to parse



8
9
10
11
12
 
# File 'lib/hsbc_pdf_statement_parser/parser.rb', line 8

def initialize( filename )
  
  @reader = PDF::Reader.new( filename )
  
end

Instance Method Details

#closing_balance ⇒ Object

Returns the closing balance of the statement read from the table on the first page.



68
69
70
71
72
 
# File 'lib/hsbc_pdf_statement_parser/parser.rb', line 68

def closing_balance
  
  @_closing_balance ||= scan_figure( 'Closing Balance' )
  
end

#opening_balance ⇒ Object

Returns the opening balance of the statement read from the table on the first page.



61
62
63
64
65
 
# File 'lib/hsbc_pdf_statement_parser/parser.rb', line 61

def opening_balance
  
  @_opening_balance ||= scan_figure( 'Opening Balance' )
  
end

#payments_in ⇒ Object

Returns the total value of payments in during the statement read from the table on the first page (ie: not calculated)



75
76
77
78
79
 
# File 'lib/hsbc_pdf_statement_parser/parser.rb', line 75

def payments_in
  
  @_payments_in ||= scan_figure( 'Payments In' )
  
end

#payments_out ⇒ Object

Returns the total value of payments out during the statement read from the table on the first page (ie: not calculated)



82
83
84
85
86
 
# File 'lib/hsbc_pdf_statement_parser/parser.rb', line 82

def payments_out
  
  @_payments_out ||= scan_figure( 'Payments Out' )
  
end

#transactions ⇒ Object

Returns an array of the transactions in the document as hashes.

Hash keys

:date

the date of the transaction _(Date)_

:type

the type of the transaction, eg ‘VISA’, ‘DD’, ‘ATM’, etc _(String)_

:details

the details of the transaction. This can span multiple lines _(String)_

:out

the amount of the transaction, if a debit _(Float, nil)_

:in

the amount of the transaction, if a credit _(Float, nil)_

:change

the amount of the transacation: negative if a debit, positive if a credit _(Float)_



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
 
# File 'lib/hsbc_pdf_statement_parser/parser.rb', line 24

def transactions
  
  @_transactions ||= begin
    
    current_transaction = nil
    current_date = nil
    transactions = []
    
    document_text
      .scan( /BALANCE\s?BROUGHT\s?FORWARD(?:.*?)\n(.*?)BALANCE\s?CARRIED\s?FORWARD/im )
      .map{ |text| parse_page( text[0] )}
      .flatten
      .each do |line|
      
        # store the current date
        current_date = line[:date] unless line[:date].nil?
      
        # if we have a type, start a new transaction
        unless line[:type].nil?
          transactions << current_transaction unless current_transaction.nil?
          current_transaction = line.merge( date: current_date )
          next
        end
      
        # merge things in
        current_transaction.merge!( line.select{ |k,v| v }, { details: "#{current_transaction[:details]}\n#{line[:details]}" })
      
      end
    
    # dump the final transaction + return
    transactions << current_transaction unless current_transaction.nil?
    transactions
  end
  
end