fnb_pdf_to_csv 0.0.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +55 -0
- data/Rakefile +1 -0
- data/fnb_pdf_to_csv.gemspec +26 -0
- data/lib/fnb_pdf_to_csv.rb +108 -0
- data/lib/fnb_pdf_to_csv/version.rb +3 -0
- metadata +108 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 183a2744177796522f8d2cb8fc99bf5edff5358e
|
4
|
+
data.tar.gz: 56f3cb527da92c169b6e5bb44690a4e4328aaa23
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 9a5cfa42da23d78bec0bd6abf01122402e0bb5054fb20d08e1942f8b7b69aca9988bb618eb7dc19a0c51f4af2482a8e17c9fc4cdf143742c4c896193ba07105b
|
7
|
+
data.tar.gz: 2a4eda17fb67e874d2883f8d6f4ae1bc03f41f41f2bb4d3cbf12a65de1a4d5d0cb12cd9c1c2807b9d2bdd561eb122a3522e986f175eef727be5e93262498b78d
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Jurgens du Toit
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
# FNB PDF Convert to CSV
|
2
|
+
|
3
|
+
This gem provides the ability to convert a PDF FNB statement to a CSV file or statement.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'fnb_pdf_to_csv'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install fnb_pdf_to_csv
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
```ruby
|
22
|
+
#!/usr/bin/env ruby
|
23
|
+
require 'thor'
|
24
|
+
require 'fnb_pdf_to_csv'
|
25
|
+
|
26
|
+
class Converter < Thor
|
27
|
+
desc 'csvfile source destination', 'Convert the PDF from source to destination. Destination will be a plain CSV file'
|
28
|
+
def csvfile(from, to)
|
29
|
+
parser = FnbPdfToCsv.parse from
|
30
|
+
parser.output to
|
31
|
+
end
|
32
|
+
|
33
|
+
desc 'file source destination', 'Convert the PDF from source to destination. Destination will be a tabbed CSV file'
|
34
|
+
def file(from, to)
|
35
|
+
parser = FnbPdfToCsv.parse from
|
36
|
+
parser.output to, "\t"
|
37
|
+
end
|
38
|
+
|
39
|
+
desc 'statement source destination', 'Convert the PDF from source to destination. Destination will mimick a FNB statement'
|
40
|
+
def statement(from, to)
|
41
|
+
parser = FnbPdfToCsv.parse from
|
42
|
+
parser.statement to
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
Converter.start(ARGV)
|
47
|
+
```
|
48
|
+
|
49
|
+
## Contributing
|
50
|
+
|
51
|
+
1. Fork it
|
52
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
53
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
54
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
55
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
@@ -0,0 +1,26 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'fnb_pdf_to_csv/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = 'fnb_pdf_to_csv'
|
8
|
+
spec.version = FnbPdfToCsv::VERSION
|
9
|
+
spec.authors = ['Jurgens du Toit']
|
10
|
+
spec.email = ['jrgns@jrgns.net']
|
11
|
+
spec.description = %(Convert account statements from FNB in PDF to CSV)
|
12
|
+
spec.summary = %(Convert account statements from FNB in PDF to CSV)
|
13
|
+
spec.homepage = 'https://github.com/jrgns/fnb_pdf_to_csv'
|
14
|
+
spec.license = 'MIT'
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(/^bin\//) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(/^(test|spec|features)\//)
|
19
|
+
spec.require_paths = ['lib']
|
20
|
+
|
21
|
+
spec.add_runtime_dependency 'pdf-reader', '~> 1.3'
|
22
|
+
|
23
|
+
spec.add_development_dependency 'bundler', '~> 1.3'
|
24
|
+
spec.add_development_dependency 'rake', '~> 10.4'
|
25
|
+
spec.add_development_dependency 'rubocop', '~> 0.33'
|
26
|
+
end
|
@@ -0,0 +1,108 @@
|
|
1
|
+
require 'fnb_pdf_to_csv/version'
|
2
|
+
require 'pdf-reader'
|
3
|
+
require 'csv'
|
4
|
+
|
5
|
+
class FnbPdfToCsv
|
6
|
+
attr_reader :lines
|
7
|
+
|
8
|
+
AMOUNT = '\(?[0-9][0-9,]*\.[0-9]{2}\)?(Cr)?'
|
9
|
+
DATE = '\d{2} \w{3}'
|
10
|
+
|
11
|
+
def initialize file
|
12
|
+
@reader = ::PDF::Reader.new file
|
13
|
+
@lines = []
|
14
|
+
end
|
15
|
+
|
16
|
+
def self.parse file
|
17
|
+
parser = self.new(file)
|
18
|
+
parser.parse
|
19
|
+
parser
|
20
|
+
end
|
21
|
+
|
22
|
+
def parse
|
23
|
+
@reader.pages.each { |page| parse_page page }
|
24
|
+
end
|
25
|
+
|
26
|
+
def output file, separator = ','
|
27
|
+
f = File.new file, 'w'
|
28
|
+
f.write [
|
29
|
+
'Date','Description1','Description2','Description3','Amount','Balance','Accrued Charges'
|
30
|
+
].to_csv(col_sep: separator)
|
31
|
+
|
32
|
+
lines.each { |line| f.write clean_line(line).to_csv(col_sep: separator) }
|
33
|
+
end
|
34
|
+
|
35
|
+
def statement file
|
36
|
+
f = File.new file, 'w'
|
37
|
+
f.write "5,'Number','Date','Description1','Description2','Description3','Amount','Balance','Accrued Charges'\n"
|
38
|
+
|
39
|
+
count = 1
|
40
|
+
lines.each do |line|
|
41
|
+
f.write statement_line(line, count).join(',') + "\n"
|
42
|
+
count = count + 1
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
def statement_line line, count
|
47
|
+
sline = line.dup
|
48
|
+
sline.insert(0, 5)
|
49
|
+
sline.insert(1, count)
|
50
|
+
sline[2] = "'#{sline[2]}'"
|
51
|
+
sline[3] = '"' + sline[3] + '"' unless (sline[3].nil? or sline[3] == '')
|
52
|
+
sline[4] = '"' + sline[4] + '"' unless (sline[4].nil? or sline[4] == '')
|
53
|
+
sline[5] = '"' + sline[5] + '"' unless (sline[5].nil? or sline[5] == '')
|
54
|
+
sline[6] = clean_amount(sline[6])
|
55
|
+
sline[7] = clean_amount(sline[7])
|
56
|
+
|
57
|
+
sline
|
58
|
+
end
|
59
|
+
|
60
|
+
def parse_page page
|
61
|
+
page.text.each_line { |line| parse_line line }
|
62
|
+
end
|
63
|
+
|
64
|
+
def parse_line line
|
65
|
+
line.match(/^\s*(#{DATE})(.*?)(#{AMOUNT})\s+(#{AMOUNT})(\s+#{AMOUNT})?$/) do |m|
|
66
|
+
@lines.push mangle_line!(m.to_a)
|
67
|
+
end
|
68
|
+
end
|
69
|
+
|
70
|
+
def clean_date(date)
|
71
|
+
day, month = date.split(/\s/)
|
72
|
+
Time.new(Time.new.year, month, day.to_i).strftime("%Y-%m-%d")
|
73
|
+
end
|
74
|
+
|
75
|
+
def clean_amount(amount)
|
76
|
+
return amount if amount.nil?
|
77
|
+
return 0 - amount[1..-2].to_f if amount[0] == '(' and amount[-1] == ')'
|
78
|
+
if amount[-2..-1] == 'Cr'
|
79
|
+
return amount[0..-3].tr(',', '').to_f
|
80
|
+
else
|
81
|
+
return 0 - amount.tr(',', '').to_f
|
82
|
+
end
|
83
|
+
end
|
84
|
+
|
85
|
+
def clean_line(line)
|
86
|
+
sline = line.dup
|
87
|
+
sline[0] = clean_date sline[0]
|
88
|
+
sline[4] = clean_amount sline[4]
|
89
|
+
sline[5] = clean_amount sline[5]
|
90
|
+
sline[6] = clean_amount sline[6]
|
91
|
+
|
92
|
+
sline
|
93
|
+
end
|
94
|
+
|
95
|
+
def mangle_line! arr
|
96
|
+
arr.delete_at 0
|
97
|
+
arr.map! { |elm| elm.strip unless elm.nil? } # Cleanup
|
98
|
+
|
99
|
+
arr.delete_at 3
|
100
|
+
arr.delete_at 4
|
101
|
+
arr.delete_at 5
|
102
|
+
arr[1] = arr[1].split(/\s{2,}/) # We get the three descriptions as one string
|
103
|
+
arr.insert(2, arr[1][1]) # So split them up and add them back
|
104
|
+
arr.insert(3, arr[1][2])
|
105
|
+
arr[1] = arr[1][0]
|
106
|
+
arr
|
107
|
+
end
|
108
|
+
end
|
metadata
ADDED
@@ -0,0 +1,108 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: fnb_pdf_to_csv
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Jurgens du Toit
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-08-23 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: pdf-reader
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.3'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.3'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.3'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.4'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.4'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rubocop
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0.33'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0.33'
|
69
|
+
description: Convert account statements from FNB in PDF to CSV
|
70
|
+
email:
|
71
|
+
- jrgns@jrgns.net
|
72
|
+
executables: []
|
73
|
+
extensions: []
|
74
|
+
extra_rdoc_files: []
|
75
|
+
files:
|
76
|
+
- ".gitignore"
|
77
|
+
- Gemfile
|
78
|
+
- LICENSE.txt
|
79
|
+
- README.md
|
80
|
+
- Rakefile
|
81
|
+
- fnb_pdf_to_csv.gemspec
|
82
|
+
- lib/fnb_pdf_to_csv.rb
|
83
|
+
- lib/fnb_pdf_to_csv/version.rb
|
84
|
+
homepage: https://github.com/jrgns/fnb_pdf_to_csv
|
85
|
+
licenses:
|
86
|
+
- MIT
|
87
|
+
metadata: {}
|
88
|
+
post_install_message:
|
89
|
+
rdoc_options: []
|
90
|
+
require_paths:
|
91
|
+
- lib
|
92
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
98
|
+
requirements:
|
99
|
+
- - ">="
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '0'
|
102
|
+
requirements: []
|
103
|
+
rubyforge_project:
|
104
|
+
rubygems_version: 2.4.6
|
105
|
+
signing_key:
|
106
|
+
specification_version: 4
|
107
|
+
summary: Convert account statements from FNB in PDF to CSV
|
108
|
+
test_files: []
|