unit_validator 0.1.0

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.
data/.autotest ADDED
@@ -0,0 +1,2 @@
1
+ require 'autotest/growl'
2
+ require 'autotest/fsevent'
data/.gitignore ADDED
@@ -0,0 +1,43 @@
1
+ # rcov generated
2
+ coverage
3
+
4
+ # rdoc generated
5
+ rdoc
6
+
7
+ # yard generated
8
+ doc
9
+ .yardoc
10
+
11
+ # bundler
12
+ .bundle
13
+
14
+ # jeweler generated
15
+ pkg
16
+
17
+ # Have editor/IDE/OS specific files you need to ignore? Consider using a global gitignore:
18
+ #
19
+ # * Create a file at ~/.gitignore
20
+ # * Include files you want ignored
21
+ # * Run: git config --global core.excludesfile ~/.gitignore
22
+ #
23
+ # After doing this, these files will be ignored in all your git projects,
24
+ # saving you from having to 'pollute' every project you touch with them
25
+ #
26
+ # Not sure what to needs to be ignored for particular editors/OSes? Here's some ideas to get you started. (Remember, remove the leading # of the line)
27
+ #
28
+ # For MacOS:
29
+ #
30
+ .DS_Store
31
+ #
32
+ # For TextMate
33
+ *.tmproj
34
+ tmtags
35
+ #
36
+ # For emacs:
37
+ #*~
38
+ #\#*
39
+ #.\#*
40
+ #
41
+ # For vim:
42
+ *.swp
43
+ .~*
data/Gemfile ADDED
@@ -0,0 +1,19 @@
1
+ source "http://rubygems.org"
2
+
3
+ group :development do
4
+ gem 'roo'
5
+ gem 'zip'
6
+ gem 'spreadsheet'
7
+ gem 'nokogiri'
8
+ gem 'google-spreadsheet-ruby'
9
+ gem 'activesupport'
10
+ gem 'fastercsv'
11
+
12
+ gem 'autotest-fsevent', '>=0.2.2'
13
+ gem 'autotest-growl', '>=0.2.4'
14
+ gem 'builder'
15
+ gem "rspec", ">= 2.0.0.rc"
16
+ gem "bundler", "~> 1.0.0"
17
+ gem "jeweler", "~> 1.5.0.pre3"
18
+ gem "rcov"
19
+ end
data/Gemfile.lock ADDED
@@ -0,0 +1,57 @@
1
+ GEM
2
+ remote: http://rubygems.org/
3
+ specs:
4
+ activesupport (3.0.1)
5
+ autotest-fsevent (0.2.3)
6
+ sys-uname
7
+ autotest-growl (0.2.6)
8
+ builder (2.1.2)
9
+ diff-lcs (1.1.2)
10
+ fastercsv (1.5.3)
11
+ git (1.2.5)
12
+ google-spreadsheet-ruby (0.1.2)
13
+ nokogiri (>= 1.4.3.1)
14
+ oauth (>= 0.3.6)
15
+ jeweler (1.5.0.pre3)
16
+ bundler (~> 1.0.0)
17
+ git (>= 1.2.5)
18
+ rake
19
+ nokogiri (1.4.3.1)
20
+ oauth (0.4.3)
21
+ rake (0.8.7)
22
+ rcov (0.9.9)
23
+ roo (1.9.3)
24
+ rspec (2.0.0.rc)
25
+ rspec-core (= 2.0.0.rc)
26
+ rspec-expectations (= 2.0.0.rc)
27
+ rspec-mocks (= 2.0.0.rc)
28
+ rspec-core (2.0.0.rc)
29
+ rspec-expectations (2.0.0.rc)
30
+ diff-lcs (>= 1.1.2)
31
+ rspec-mocks (2.0.0.rc)
32
+ rspec-core (= 2.0.0.rc)
33
+ rspec-expectations (= 2.0.0.rc)
34
+ ruby-ole (1.2.11)
35
+ spreadsheet (0.6.4.1)
36
+ ruby-ole
37
+ sys-uname (0.8.4)
38
+ zip (2.0.2)
39
+
40
+ PLATFORMS
41
+ ruby
42
+
43
+ DEPENDENCIES
44
+ activesupport
45
+ autotest-fsevent (>= 0.2.2)
46
+ autotest-growl (>= 0.2.4)
47
+ builder
48
+ bundler (~> 1.0.0)
49
+ fastercsv
50
+ google-spreadsheet-ruby
51
+ jeweler (~> 1.5.0.pre3)
52
+ nokogiri
53
+ rcov
54
+ roo
55
+ rspec (>= 2.0.0.rc)
56
+ spreadsheet
57
+ zip
data/LICENSE ADDED
@@ -0,0 +1,20 @@
1
+ Copyright© Sprout Technology International Limited
2
+
3
+ Permission is hereby granted, free of charge, to any person obtaining
4
+ a copy of this software and associated documentation files (the
5
+ "Software"), to deal in the Software without restriction, including
6
+ without limitation the rights to use, copy, modify, merge, publish,
7
+ distribute, sublicense, and/or sell copies of the Software, and to
8
+ permit persons to whom the Software is furnished to do so, subject to
9
+ the following conditions:
10
+
11
+ The above copyright notice and this permission notice shall be
12
+ included in all copies or substantial portions of the Software.
13
+
14
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
15
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
16
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
17
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
18
+ LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
19
+ OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
20
+ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
data/README.md ADDED
@@ -0,0 +1,93 @@
1
+ # Cloud Factory Validatior (CFValidator)
2
+
3
+ The CFInputValidator - Cloud Factory Input Validator is a simple gem to **validate** the *spreadsheet data* inputs as per the given rules.
4
+
5
+ This gem is being developed for Project **Cloud Factory** Copyright© [Sprout Technology International Limited](http://sprout-technology.com)
6
+
7
+ ![Sprout logo](http://sprout-technology.com/images/logo.png)
8
+
9
+ ## Installation
10
+
11
+ In Gemfile
12
+ source 'http://rubygems.org'
13
+ gem 'unit_validator'
14
+
15
+ bundle install
16
+
17
+ OR
18
+ gem install unit_validator
19
+
20
+ require 'rubygems'
21
+ require 'unit_validator'
22
+
23
+ ## Usage
24
+
25
+ The CFInputValidator checks if the **headers** of the provided spreadsheet matches with the corresponding **rules** *(checked by label)* and gives error message if it doesn't match.
26
+
27
+ The individual row of the spreadsheet undergoes the validation process and gives the final output as an array of **valid and invalid units**.
28
+ Later the valid and invalid units can be processed separately as required.
29
+
30
+ You can even check if a **file format** is supported by the gem.
31
+
32
+ The gem currently supports `validation_format` of `email`, `number`, `url`, `date` and `time` only.
33
+ It also checks if value is present if required is true.
34
+
35
+ ## Example
36
+
37
+ 1. Specify the rules, i.e `:label` `:required` `:validation_format`
38
+ rules = [{:label => "company name",:required => true, :validation_format => "general"},
39
+ {:label => "email", :required => false, :validation_format => "email"}]
40
+
41
+ 2. Provide data for validation:
42
+ inputs = "company name,email\nSprout,info@sproutify.com\nApple,saroj@apple"
43
+
44
+ **You can also give the file location as input**
45
+ inputs = File.read("fixtures/gdoc.csv")
46
+
47
+ * Check the file format with `check_extension(path)` method which gives you a 'boolean' value `:check`
48
+
49
+ `file_location = "fixtures/gdoc.xlsxsfdsf"`
50
+
51
+ `CFInputValidator.check_extension(file_location)[:check]`
52
+
53
+ * This gem currently supports the following formats and 'must be converted into csv' before validation.
54
+ * `inputs = File.read("fixtures/gdoc.csv")`
55
+ * `inputs = Excel.new("fixtures/gdoc.xls").to_csv`
56
+ * `inputs = Excelx.new("fixtures/gdoc.xlsx").to_csv`
57
+ * `inputs = Openoffice.new("fixtures/gdoc.ods").to_csv`
58
+
59
+ 3. Create a new constructor of *CF::InputValidator* class passing the above **rules** as argument.
60
+
61
+ cloud_validator = CF::InputValidator.new(rules)
62
+
63
+ 4. Call `parse_and_validate(data)` method passing the above inputs as arguments.
64
+ val = cloud_validator.parse_and_validate(inputs)
65
+
66
+ 5. Now you'll get both valid and invalid data in `:valid_units` and `:invalid_units` arrays respectively.
67
+ * `val[:valid_units]`
68
+ * `val[:invalid_units]`
69
+
70
+ 6. It will give a `.errors` instance variable as error if the *headers* of spreadsheet data doesn't match with the *rules* or vice-versa saying *"Headers doesnot match the column counts"*.
71
+ rules = [{:field_id => "field_1", :label => "company name", :field_type => "text_data",
72
+ :value => "Sprout", :required => true, :validation_format => "general"
73
+ }]
74
+ inputs = "company name,email\nSprout,info@sproutify.com"
75
+
76
+ cloud_validator = CF::InputValidator.new(rules)
77
+ val = cloud_validator.parse_and_validate(inputs)
78
+ err = val.errors
79
+
80
+
81
+ ## Note on Patches/Pull Requests
82
+
83
+ * Fork the project.
84
+ * Make your feature addition or bug fix.
85
+ * Add tests for it. This is important so I don't break it in a
86
+ future version unintentionally.
87
+ * Commit, do not mess with rakefile, version, or history.
88
+ (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
89
+ * Send me a pull request. Bonus points for topic branches.
90
+
91
+ ### Copyright
92
+
93
+ Copyright© Sprout Technology International Limited. See LICENSE for details.
data/Rakefile ADDED
@@ -0,0 +1,61 @@
1
+ require 'rubygems'
2
+ require 'bundler'
3
+ begin
4
+ Bundler.setup(:default, :development)
5
+ rescue Bundler::BundlerError => e
6
+ $stderr.puts e.message
7
+ $stderr.puts "Run `bundle install` to install missing gems"
8
+ exit e.status_code
9
+ end
10
+ require 'rake'
11
+
12
+ require 'jeweler'
13
+ Jeweler::Tasks.new do |gem|
14
+ # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
15
+ gem.name = "unit_validator"
16
+ gem.summary = %Q{Takes the Instruction Input as Rule, parse the CSV files and does the validation}
17
+ gem.description = %Q{Takes the Instruction Input as Rule, parse the CSV files and applies the validation and returns valid and invalid units}
18
+ gem.email = "saroj@sprout-technology.com"
19
+ gem.homepage = "http://github.com/sprout/unit_validator"
20
+ gem.authors = ["millisami", "zoras"]
21
+ # Include your dependencies below. Runtime dependencies are required when using your gem,
22
+ # and development dependencies are only needed for development (ie running rake tasks, tests, etc)
23
+ gem.add_runtime_dependency 'roo'
24
+ gem.add_runtime_dependency 'zip'
25
+ gem.add_runtime_dependency 'spreadsheet'
26
+ gem.add_runtime_dependency 'nokogiri'
27
+ gem.add_runtime_dependency 'google-spreadsheet-ruby'
28
+ gem.add_runtime_dependency 'activesupport'
29
+ gem.add_runtime_dependency 'builder'
30
+
31
+ gem.add_development_dependency "rspec", ">= 2.0.0.rc"
32
+ gem.add_development_dependency "bundler", "~> 1.0.0"
33
+ gem.add_development_dependency "jeweler", "~> 1.5.0.pre3"
34
+ gem.add_development_dependency "rcov", ">= 0"
35
+ end
36
+ Jeweler::RubygemsDotOrgTasks.new
37
+
38
+ require 'rspec/core'
39
+ require 'rspec/core/rake_task'
40
+ # custom rcov
41
+ require File.expand_path(File.dirname(__FILE__) + '/lib/tasks/rcov_custom')
42
+ RSpec::Core::RakeTask.new(:spec) do |spec|
43
+ spec.pattern = FileList['spec/**/*_spec.rb']
44
+ end
45
+
46
+ RSpec::Core::RakeTask.new(:rcov) do |spec|
47
+ spec.pattern = 'spec/**/*_spec.rb'
48
+ spec.rcov = true
49
+ end
50
+
51
+ task :default => :spec
52
+
53
+ require 'rake/rdoctask'
54
+ Rake::RDocTask.new do |rdoc|
55
+ version = File.exist?('VERSION') ? File.read('VERSION') : ""
56
+
57
+ rdoc.rdoc_dir = 'rdoc'
58
+ rdoc.title = "unit_validator #{version}"
59
+ rdoc.rdoc_files.include('README*')
60
+ rdoc.rdoc_files.include('lib/**/*.rb')
61
+ end
data/VERSION ADDED
@@ -0,0 +1 @@
1
+ 0.1.0
@@ -0,0 +1,3 @@
1
+ Autotest.add_discovery do
2
+ "rspec2"
3
+ end
data/fixtures/gdoc.csv ADDED
@@ -0,0 +1,10 @@
1
+ company name,email
2
+ "Apple, Inc.",
3
+ Sprout,info@sproutify.com
4
+ ,inf o@ab c.com
5
+
6
+
7
+ DEF, info@def.com
8
+ GHI
9
+
10
+
data/fixtures/gdoc.ods ADDED
Binary file
data/fixtures/gdoc.xls ADDED
Binary file
Binary file
@@ -0,0 +1,72 @@
1
+ require 'fastercsv'
2
+ require 'roo'
3
+ require 'active_support/core_ext/object/blank'
4
+ require 'generic_spreadsheet'
5
+ require 'validator_helpers'
6
+
7
+ module CF
8
+ class InputValidator
9
+ include ValidatorHelpers
10
+
11
+ attr_accessor :errors, :rules
12
+
13
+ def initialize(rules)
14
+ @errors = []
15
+ @rules = rules
16
+ @invalid_units, @temp_units, @valid_units = [], [], []
17
+ end
18
+
19
+ def self.check_extension(file_location)
20
+ @error = []
21
+ ext = File.extname(file_location).sub(/./,"")
22
+ formats = %w[csv xls xlsx ods]
23
+ check = formats.include?(ext)
24
+
25
+ @error << "Invalid file! The specified format is not supported." unless check
26
+ {:check => check, :error => @error}
27
+ end
28
+
29
+ # returns a hash of arrays with two keys :valid_units and :invalid_units
30
+ # {:valid_units => @valid_units, :invalid_units => @invalid_units}
31
+ def parse_and_validate(inputs)
32
+ csv_contents = FasterCSV.parse(inputs)
33
+ csv_header = csv_contents[0].map{|a| a.strip unless a.nil? }
34
+
35
+ # Initialize rule_labels array and store labels of RULE_HEADERS into it
36
+ rule_labels = Array.new
37
+ rules.each do |rule|
38
+ rule_labels << rule[:label]
39
+ end
40
+
41
+ if rule_labels == csv_header
42
+ csv_contents[1..-1].each do |item|
43
+ # Validation.
44
+ rules.each_with_index do |header, index|
45
+ next unless item # Escape nil items. This may result while reading csv file with blank line
46
+
47
+ unless (item = item.select{|x| !x.blank? }).empty?
48
+ item[index].strip! if !item[index].nil?
49
+
50
+ if required(header[:required], item[index]) and valid(header[:validation_format], item[index])
51
+ # temporarily store valid units into temp_units array
52
+ @temp_units << item unless @temp_units.include?(item)
53
+ else
54
+ # Note:: While validating input data, collect invalid row(data) and process the others.
55
+ # Display invalid data to user later
56
+ @invalid_units << item unless @invalid_units.include?(item)
57
+ end
58
+ end
59
+ end
60
+
61
+ end
62
+ else
63
+ @errors << "Headers doesnot match the column counts"
64
+ end
65
+
66
+ # calculate valid_units
67
+ @valid_units = @temp_units - @invalid_units
68
+
69
+ {:valid_units => @valid_units, :invalid_units => @invalid_units}
70
+ end
71
+ end
72
+ end
@@ -0,0 +1,52 @@
1
+ module CF
2
+ class ResultValidator
3
+ include ValidatorHelpers
4
+ attr_accessor :errors
5
+
6
+ def initialize
7
+ @errors = []
8
+ end
9
+
10
+ def valid?(rules, result)
11
+ csv_contents = FasterCSV.parse(result)
12
+ csv_header = csv_contents[0].map{|a| a.strip unless a.nil? }
13
+
14
+ rule_labels = Array.new
15
+ rules.each do |rule|
16
+ rule_labels << rule[:label]
17
+ end
18
+
19
+ bool = false
20
+ case (rule_labels <=> csv_header)
21
+ when 1
22
+ # when input header is less than rule label
23
+ @errors << "#{rule_labels - csv_header} is/are required"
24
+ when -1
25
+ # when input header is more than rule label
26
+ @errors << "cannot process as the input data consists extra headers"
27
+ when 0
28
+ # if rule_labels == csv_header
29
+ csv_contents[1..-1].each do |item|
30
+ rules.each_with_index do |header, index|
31
+ next unless item
32
+ unless item.compact.empty?
33
+ item[index].strip! if !item[index].nil?
34
+ if required(header[:required], item[index]) and valid(header[:validation_format], item[index])
35
+ bool = true
36
+ else
37
+ bool = false
38
+ if header[:required] && item[index].blank?
39
+ @errors << "#{header[:label]} is required"
40
+ else
41
+ @errors << "#{item[index]} is not valid"
42
+ end
43
+ end
44
+ end
45
+ end
46
+ end
47
+ end
48
+ # finally return boolean for .valid?
49
+ return bool
50
+ end
51
+ end
52
+ end
@@ -0,0 +1,23 @@
1
+ class GenericSpreadsheet
2
+
3
+ # write the current spreadsheet to csv_string
4
+ def to_csv(filename=nil,sheet=nil)
5
+ csv_string = write_csv_content(STDOUT,sheet)
6
+ end
7
+
8
+ def write_csv_content(file=nil,sheet=nil)
9
+ csv_string = ""
10
+ if first_row(sheet) # sheet is not empty
11
+ 1.upto(last_row(sheet)) do |row|
12
+ 1.upto(last_column(sheet)) do |col|
13
+ csv_string += "," if col > 1
14
+ onecell = cell(row,col,sheet)
15
+ onecelltype = celltype(row,col,sheet)
16
+ csv_string += one_cell_output(onecelltype,onecell,empty?(row,col,sheet))
17
+ end
18
+ csv_string += "\n"
19
+ end # sheet not empty
20
+ end
21
+ csv_string
22
+ end
23
+ end
@@ -0,0 +1,5 @@
1
+ desc "Custom rcov"
2
+ RSpec::Core::RakeTask.new(:rcov_custom) do |t|
3
+ t.rcov = true
4
+ t.rcov_opts = %w{--exclude gems\/,spec\/ -T}
5
+ end
@@ -0,0 +1,56 @@
1
+ module ValidatorHelpers
2
+
3
+ private
4
+
5
+ def required(rule, value)
6
+ # returns true unless value is blank when required rule is true
7
+ (rule && value.blank?) ? false : true
8
+ end
9
+
10
+ def valid(format, value)
11
+ case format
12
+ when "email"
13
+ regex = /\A([^@\s]+)@((?:[-a-z0-9]+\.)+[a-z]{2,})\Z/i
14
+ when "url" # image_data => url, path
15
+ regex = /^(http:\/\/|https:\/\/)?(www.)?[a-zA-Z0-9\-\.]+\.([a-zA-Z]{2,3})([.]?[a-zA-Z]{2})?(\/\S*)?$/i
16
+ msg = "Start with http:// or https://"
17
+ when "number"
18
+ regex = /^\d{1,3}(\,?\d{3})*$/
19
+ when "date"
20
+ # Check if date (dd.mm.yyyy) is valid date or not
21
+ #regex = /\d{1,2}(\/|-|\.|\s)\d{1,2}(\/|-|\.|\s)\d{2,4}/
22
+ test = check_date(value)
23
+ return test
24
+ when "time"
25
+ regex = /^(([0-1]?[0-9])|([2][0-3])):([0-5]?[0-9])(:([0-5]?[0-9]))?$/
26
+ when "datetime"
27
+ regex = /^(1[0-2]|0?[1-9])\/(3[01]|[12][0-9]|0?[1-9])\/(?:[0-9]{2})?[0-9]{2}|(([0-1]?[0-9])|([2][0-3])):([0-5]?[0-9])(:([0-5]?[0-9]))?$/
28
+ when "currency" #=> for USD
29
+ regex = /^\$?(?:\d+|\d{1,3}(?:,\d{3})*)(?:\.\d{1,2}){0,1}$/
30
+ # when "boolean"
31
+ # when "rating"
32
+ # when "radio"
33
+ # when "checkbox" => multiple choice
34
+ when "general"
35
+ return true
36
+ else
37
+ @errors << "Validation format not supported:: #{format}"
38
+ # puts "error message:: #{@errors.inspect}"
39
+ return false
40
+ end
41
+
42
+ if !value.blank?
43
+ !value.match(regex).nil? ? true : false
44
+ end
45
+ end
46
+
47
+ def check_date(value)
48
+ begin
49
+ val = value.scan(/^(\d{1,2})[\/|-|\.|\s](\d{1,2})[\/|-|\.|\s](\d{2,4})$/) # dd.mm.yyyy
50
+ Date.civil(val[0][2].to_i,val[0][1].to_i,val[0][0].to_i) # civil check julian date in yyyy.mm.dd
51
+ !val.blank? ? true : false
52
+ rescue
53
+ return false
54
+ end
55
+ end
56
+ end
data/spec/.rspec ADDED
@@ -0,0 +1 @@
1
+ --color