fencer 0.4.2
Sign up to get free protection for your applications and to get access to all the features.
- data/.rspec +1 -0
- data/LICENSE +22 -0
- data/README.md +66 -0
- data/Rakefile +2 -0
- data/fencer.gemspec +22 -0
- data/lib/fencer.rb +89 -0
- data/lib/fencer/version.rb +3 -0
- data/spec/fencer_spec.rb +142 -0
- metadata +83 -0
data/.rspec
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--color --format documentation
|
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Dan Cheail
|
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 +1,66 @@
|
|
1
|
+
# Fencer
|
2
|
+
Fencer is designed to process rows of fixed-length and delimited text
|
3
|
+
data, splitting at designated termination points, converting field values
|
4
|
+
where required and making fields available through named object accessors.
|
5
|
+
|
6
|
+
Row formats are defined by subclassing Fencer::Base and using the DSL
|
7
|
+
provided.
|
8
|
+
|
9
|
+
## Example
|
10
|
+
class EmployeeRecord < Fencer::Base
|
11
|
+
field :department, 50, :string
|
12
|
+
field :name, 20, -> s { s.split }
|
13
|
+
space 2
|
14
|
+
field :age, 4, :integer
|
15
|
+
end
|
16
|
+
|
17
|
+
`field` takes 3 arguments: a field name, the field length and an (optional)
|
18
|
+
converter.
|
19
|
+
|
20
|
+
## Field Conversion
|
21
|
+
`Fencer::Base::Converters` is a `Hash<` defines some commonly-used converters.
|
22
|
+
It's left un-frozen, so it can be extended as required.
|
23
|
+
|
24
|
+
Short-cut methods for the default field types are also available:
|
25
|
+
|
26
|
+
class EmployeeRecord < Fencer::Base
|
27
|
+
string :department, 20 => String
|
28
|
+
integer :age, 2 => Integer
|
29
|
+
decimal :salary, 10 => BigDecimal
|
30
|
+
end
|
31
|
+
|
32
|
+
Additionally, custom conversions can be defined by passing a `lambda`
|
33
|
+
as the final argument.
|
34
|
+
|
35
|
+
## Usage
|
36
|
+
|
37
|
+
Records are extracted on initialisation:
|
38
|
+
|
39
|
+
raw_string = "EXAMPLE FORMAT 10 300.04"
|
40
|
+
fields = EmployeeRecord.new(raw_string)
|
41
|
+
|
42
|
+
And are directly accessible thereafter:
|
43
|
+
|
44
|
+
fields.department # => "EXAMPLE FORMAT"
|
45
|
+
fields.age # => 2
|
46
|
+
fields.salary # => BigDecimal("300.04")
|
47
|
+
|
48
|
+
In the case of importing delimiter-separated data, passing the delimiting
|
49
|
+
character as the second argument to `new` will yield the desired result
|
50
|
+
without any change of layout:
|
51
|
+
|
52
|
+
raw_string = "EXAMPLE FORMAT|10|300.04"
|
53
|
+
fields = EmployeeRecord.new(raw_string, "|")
|
54
|
+
|
55
|
+
fields.department # => "EXAMPLE FORMAT"
|
56
|
+
fields.age # => 2
|
57
|
+
fields.salary # => BigDecimal("300.04")
|
58
|
+
|
59
|
+
|
60
|
+
## Known Deficiencies
|
61
|
+
|
62
|
+
Currently, Fencer works with Ruby 1.9 only. Sorry. I wanted Hashes that
|
63
|
+
preserve field-order. P;us, the newer syntax is pretty.
|
64
|
+
|
65
|
+
Fencer is also blissfully unaware of any sort of encoding. This is a planned
|
66
|
+
feature for the 1.0 release.
|
data/Rakefile
ADDED
data/fencer.gemspec
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/fencer/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Dan Cheail"]
|
6
|
+
gem.email = ["dan@undumb.com"]
|
7
|
+
gem.description = %q{Fixed-length/delimited record parser DSL}
|
8
|
+
gem.summary = %q{Fencer makes working with fixed-length and delimited
|
9
|
+
text-based records simpler by providing a flexible DSL
|
10
|
+
for defining field lengths and transformations}
|
11
|
+
|
12
|
+
gem.homepage = "https://github.com/undumb/fencer"
|
13
|
+
gem.files = `git ls-files`.split($\) - %w(Gemfile .gitignore)
|
14
|
+
# gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
15
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
16
|
+
gem.name = "fencer"
|
17
|
+
gem.require_paths = ["lib"]
|
18
|
+
gem.version = Fencer::VERSION
|
19
|
+
|
20
|
+
gem.add_development_dependency "rspec", "~> 2.10"
|
21
|
+
gem.add_development_dependency "rake"
|
22
|
+
end
|
data/lib/fencer.rb
ADDED
@@ -0,0 +1,89 @@
|
|
1
|
+
require "bigdecimal"
|
2
|
+
require "fencer/version"
|
3
|
+
|
4
|
+
module Fencer
|
5
|
+
|
6
|
+
class Base
|
7
|
+
Converters = {
|
8
|
+
string: -> s { s.strip },
|
9
|
+
integer: -> s { s.to_i },
|
10
|
+
decimal: -> s { BigDecimal(s) },
|
11
|
+
}
|
12
|
+
|
13
|
+
class << self
|
14
|
+
attr_reader :fields
|
15
|
+
|
16
|
+
def inherited(subclass)
|
17
|
+
subclass.instance_variable_set(:@fields, {})
|
18
|
+
end
|
19
|
+
|
20
|
+
def field(name, size, convert = nil)
|
21
|
+
# error handling, ahoy!
|
22
|
+
raise "#{name} already defined as a field on #{self.name}" if fields.has_key?(name)
|
23
|
+
|
24
|
+
unless convert.nil? || Converters.has_key?(convert) || convert.is_a?(Proc)
|
25
|
+
raise "Invalid converter"
|
26
|
+
end
|
27
|
+
|
28
|
+
fields[name] = { size: size, convert: convert }
|
29
|
+
|
30
|
+
# create our attr method
|
31
|
+
define_method(name) { @values[name] }
|
32
|
+
end
|
33
|
+
|
34
|
+
def space(size)
|
35
|
+
fields[:"_#{fields.length.succ}"] = { size: size, space: true }
|
36
|
+
end
|
37
|
+
|
38
|
+
def string(name, size)
|
39
|
+
field(name, size, :string)
|
40
|
+
end
|
41
|
+
|
42
|
+
def integer(name, size)
|
43
|
+
field(name, size, :integer)
|
44
|
+
end
|
45
|
+
|
46
|
+
def decimal(name, size)
|
47
|
+
field(name, size, :decimal)
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
def initialize(str, delimiter = nil)
|
52
|
+
@values = {}
|
53
|
+
@delimiter = delimiter
|
54
|
+
@str = str
|
55
|
+
|
56
|
+
parse!
|
57
|
+
end
|
58
|
+
|
59
|
+
def to_hash
|
60
|
+
@values
|
61
|
+
end
|
62
|
+
|
63
|
+
private
|
64
|
+
|
65
|
+
def parse!
|
66
|
+
if @delimiter
|
67
|
+
raw_values = @str.split(@delimiter)
|
68
|
+
else
|
69
|
+
unpack_phrase = self.class.fields.values.map { |s| "A#{s[:size]}" }.join
|
70
|
+
raw_values = @str.unpack(unpack_phrase)
|
71
|
+
end
|
72
|
+
|
73
|
+
_index = 0
|
74
|
+
self.class.fields.each do |name, opts|
|
75
|
+
unless opts[:space]
|
76
|
+
_conversion_proc = case opts[:convert]
|
77
|
+
when Symbol then Converters[opts[:convert]]
|
78
|
+
when Proc then opts[:convert]
|
79
|
+
else nil
|
80
|
+
end
|
81
|
+
|
82
|
+
@values[name] = _conversion_proc ? _conversion_proc.call(raw_values[_index]) : raw_values[_index]
|
83
|
+
end
|
84
|
+
|
85
|
+
_index += 1 unless opts[:space] && @delimiter
|
86
|
+
end
|
87
|
+
end
|
88
|
+
end
|
89
|
+
end
|
data/spec/fencer_spec.rb
ADDED
@@ -0,0 +1,142 @@
|
|
1
|
+
# require 'rubygems'
|
2
|
+
|
3
|
+
Bundler.require(:default, :development)
|
4
|
+
|
5
|
+
require 'rspec'
|
6
|
+
require 'fencer'
|
7
|
+
|
8
|
+
describe Fencer do
|
9
|
+
|
10
|
+
class EmployeeRecord < Fencer::Base
|
11
|
+
string :name, 20
|
12
|
+
string :department, 20
|
13
|
+
space 2
|
14
|
+
field :employment_date, 8, -> s { dasherise_ymd(s) }
|
15
|
+
integer :id_number, 6
|
16
|
+
decimal :leave_accrued, 11
|
17
|
+
|
18
|
+
class << self
|
19
|
+
def dasherise_ymd(str)
|
20
|
+
str.gsub(/([0-9]{4})([0-9]{2})([0-9]{2})/) { "#{$1}-#{$2}-#{$3}" }
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
let(:name) { "Ford Prefect" }
|
26
|
+
let(:department) { "Publication" }
|
27
|
+
let(:employment_date) { "20120525" }
|
28
|
+
let(:id_number) { "42" }
|
29
|
+
let(:leave_accrued) { "1484.33" }
|
30
|
+
|
31
|
+
it "has many wonderful features" do
|
32
|
+
|
33
|
+
compiled_record = name.ljust(20)
|
34
|
+
compiled_record << department.ljust(20)
|
35
|
+
compiled_record << " "
|
36
|
+
compiled_record << employment_date
|
37
|
+
compiled_record << id_number.rjust(6, '0')
|
38
|
+
compiled_record << leave_accrued.rjust(11, '0')
|
39
|
+
|
40
|
+
# auto parsing
|
41
|
+
values = EmployeeRecord.new(compiled_record)
|
42
|
+
|
43
|
+
# individual accessors for each field
|
44
|
+
values.name.should eq(name)
|
45
|
+
values.department.should eq(department)
|
46
|
+
values.employment_date.should eq("2012-05-25")
|
47
|
+
values.id_number.should eq(id_number.to_i)
|
48
|
+
values.leave_accrued.should eq(BigDecimal(leave_accrued))
|
49
|
+
|
50
|
+
# export our values to a hash
|
51
|
+
values.to_hash.should eq({
|
52
|
+
name: name,
|
53
|
+
department: department,
|
54
|
+
employment_date: "2012-05-25",
|
55
|
+
id_number: id_number.to_i,
|
56
|
+
leave_accrued: BigDecimal(leave_accrued),
|
57
|
+
})
|
58
|
+
end
|
59
|
+
|
60
|
+
it "also works when parsing arbitrarily delimited fields!" do
|
61
|
+
compiled_record = [
|
62
|
+
name, department, employment_date, id_number, leave_accrued
|
63
|
+
].join("|")
|
64
|
+
|
65
|
+
values = EmployeeRecord.new(compiled_record, "|")
|
66
|
+
|
67
|
+
values.name.should eq(name)
|
68
|
+
values.department.should eq(department)
|
69
|
+
values.employment_date.should eq("2012-05-25")
|
70
|
+
values.id_number.should eq(id_number.to_i)
|
71
|
+
values.leave_accrued.should eq(BigDecimal(leave_accrued))
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
|
76
|
+
class FencerBaseTest < Fencer::Base
|
77
|
+
class << self
|
78
|
+
def reset_fields!
|
79
|
+
@fields = {}
|
80
|
+
end
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
84
|
+
describe Fencer::Base do
|
85
|
+
before(:each) do
|
86
|
+
subject.reset_fields!
|
87
|
+
end
|
88
|
+
|
89
|
+
subject { FencerBaseTest }
|
90
|
+
|
91
|
+
it "#field adds fields to the internal register" do
|
92
|
+
subject.field(:derp, 1)
|
93
|
+
subject.fields.should have_key(:derp)
|
94
|
+
end
|
95
|
+
|
96
|
+
it "#field adds an instance access method" do
|
97
|
+
subject.field(:derp, 1)
|
98
|
+
|
99
|
+
instance = subject.new("")
|
100
|
+
instance.should respond_to(:derp)
|
101
|
+
instance.should_not respond_to(:herp)
|
102
|
+
end
|
103
|
+
|
104
|
+
it "raises an error when the size attribute is omitted" do
|
105
|
+
expect { subject.field(:derp) }.to raise_error
|
106
|
+
end
|
107
|
+
|
108
|
+
it "raises an error when duplicate keys are defined" do
|
109
|
+
subject.field(:derp, 1)
|
110
|
+
expect { subject.field(:derp, 1) }.to raise_error
|
111
|
+
end
|
112
|
+
|
113
|
+
context "when using shortcut methods" do
|
114
|
+
it "has a shortcut for string fields" do
|
115
|
+
subject.string(:derp, 1)
|
116
|
+
subject.fields.should have_key(:derp)
|
117
|
+
subject.fields[:derp][:convert].should be :string
|
118
|
+
end
|
119
|
+
|
120
|
+
it "has a shortcut for integer fields" do
|
121
|
+
subject.integer(:derp, 1)
|
122
|
+
subject.fields.should have_key(:derp)
|
123
|
+
subject.fields[:derp][:convert].should be :integer
|
124
|
+
end
|
125
|
+
|
126
|
+
it "has a shortcut for decimal fields" do
|
127
|
+
subject.decimal(:derp, 1)
|
128
|
+
subject.fields.should have_key(:derp)
|
129
|
+
subject.fields[:derp][:convert].should be :decimal
|
130
|
+
end
|
131
|
+
end
|
132
|
+
|
133
|
+
context "when setting an invalid conversion argument" do
|
134
|
+
it "raises an error if the symbol is not registered" do
|
135
|
+
expect { subject.field(:derp, 1, :to_date) }.to raise_error
|
136
|
+
end
|
137
|
+
|
138
|
+
it "raises an error if the argument is not a lambda" do
|
139
|
+
expect { subject.field(:derp, 1, "") }.to raise_error
|
140
|
+
end
|
141
|
+
end
|
142
|
+
end
|
metadata
ADDED
@@ -0,0 +1,83 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: fencer
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.4.2
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Dan Cheail
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-05-31 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rspec
|
16
|
+
requirement: &70270773693060 !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '2.10'
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *70270773693060
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: rake
|
27
|
+
requirement: &70270773692560 !ruby/object:Gem::Requirement
|
28
|
+
none: false
|
29
|
+
requirements:
|
30
|
+
- - ! '>='
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0'
|
33
|
+
type: :development
|
34
|
+
prerelease: false
|
35
|
+
version_requirements: *70270773692560
|
36
|
+
description: Fixed-length/delimited record parser DSL
|
37
|
+
email:
|
38
|
+
- dan@undumb.com
|
39
|
+
executables: []
|
40
|
+
extensions: []
|
41
|
+
extra_rdoc_files: []
|
42
|
+
files:
|
43
|
+
- .rspec
|
44
|
+
- LICENSE
|
45
|
+
- README.md
|
46
|
+
- Rakefile
|
47
|
+
- fencer.gemspec
|
48
|
+
- lib/fencer.rb
|
49
|
+
- lib/fencer/version.rb
|
50
|
+
- spec/fencer_spec.rb
|
51
|
+
homepage: https://github.com/undumb/fencer
|
52
|
+
licenses: []
|
53
|
+
post_install_message:
|
54
|
+
rdoc_options: []
|
55
|
+
require_paths:
|
56
|
+
- lib
|
57
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
58
|
+
none: false
|
59
|
+
requirements:
|
60
|
+
- - ! '>='
|
61
|
+
- !ruby/object:Gem::Version
|
62
|
+
version: '0'
|
63
|
+
segments:
|
64
|
+
- 0
|
65
|
+
hash: 1981968692186319614
|
66
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
67
|
+
none: false
|
68
|
+
requirements:
|
69
|
+
- - ! '>='
|
70
|
+
- !ruby/object:Gem::Version
|
71
|
+
version: '0'
|
72
|
+
segments:
|
73
|
+
- 0
|
74
|
+
hash: 1981968692186319614
|
75
|
+
requirements: []
|
76
|
+
rubyforge_project:
|
77
|
+
rubygems_version: 1.8.17
|
78
|
+
signing_key:
|
79
|
+
specification_version: 3
|
80
|
+
summary: Fencer makes working with fixed-length and delimited text-based records simpler
|
81
|
+
by providing a flexible DSL for defining field lengths and transformations
|
82
|
+
test_files:
|
83
|
+
- spec/fencer_spec.rb
|