csv-check 0.0.1

data/.gitignore

@@ -0,0 +1,18 @@
+*.gem
+*.rbc
+.bundle
+.config
+coverage
+InstalledFiles
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+
+# YARD artifacts
+.yardoc
+_yardoc
+doc/

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in csv-check.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,45 @@
+PATH
+  remote: .
+  specs:
+    csv-check (0.0.1)
+      fastercsv
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    aruba (0.4.11)
+      childprocess (>= 0.2.3)
+      cucumber (>= 1.1.1)
+      ffi (>= 1.0.11)
+      rspec (>= 2.7.0)
+    builder (3.1.3)
+    childprocess (0.3.5)
+      ffi (~> 1.0, >= 1.0.6)
+    cucumber (1.2.1)
+      builder (>= 2.1.2)
+      diff-lcs (>= 1.1.3)
+      gherkin (~> 2.11.0)
+      json (>= 1.4.6)
+    diff-lcs (1.1.3)
+    fastercsv (1.5.5)
+    ffi (1.1.5)
+    gherkin (2.11.2)
+      json (>= 1.4.6)
+    json (1.7.5)
+    rspec (2.11.0)
+      rspec-core (~> 2.11.0)
+      rspec-expectations (~> 2.11.0)
+      rspec-mocks (~> 2.11.0)
+    rspec-core (2.11.1)
+    rspec-expectations (2.11.3)
+      diff-lcs (~> 1.1.3)
+    rspec-mocks (2.11.3)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  aruba
+  csv-check!
+  cucumber
+  rspec (~> 2.6)

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2012 rory
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,29 @@
+# CsvCheck
+
+Format checker for CSV files
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'csv-check'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install csv-check
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/bin/csv-check

@@ -0,0 +1,89 @@
+#!/usr/bin/env ruby
+
+require "rubygems"
+require 'optparse'
+require 'ostruct'
+require  File.join(File.expand_path(File.dirname(__FILE__)), '..', 'lib', 'csvchecker.rb')
+require  File.join(File.expand_path(File.dirname(__FILE__)), '..', 'lib', 'typemapper.rb')
+
+module CsvCheckRunner
+
+    # command-line parsing
+    COMMAND = File.basename($0)
+    USAGE = "Usage: #{COMMAND} [INPUT] [OPTIONS]"
+
+    options = OpenStruct.new
+    options.output = "-"
+    options.separator = ","
+    options.pretty = false
+    options.headers = nil
+    options.skip_first_row = false
+
+    opts = OptionParser.new do |o|
+        o.banner = USAGE
+        o.separator ""
+        o.separator "Specific options:"
+
+        o.on("-k", "--skip-headers-from-file", "Ignore the headers (first line) in the file; use with --headers to set your own") do |headers|
+            options.skip_first_row = true
+        end
+
+        o.on("-s", "--separator SEP", "Set separator character surrounded by single quotes (default is ',')") do |sep|
+            options.separator = sep
+        end
+
+        o.on("-m", "--map \"<type map>\"", "Set separator character surrounded by single quotes (default is ',')") do |sep|
+            options.mappings = sep
+        end
+
+        o.on("-o", "--output FILE", "Write output to a file") do |fn|
+            options.output = fn
+        end
+     
+        o.on_tail("-h", "--help", "Show this message") do
+            puts o
+            exit
+        end
+
+        o.on_tail("-v", "--version", "Show version") do
+            puts CsvCheck::VERSION
+            exit
+        end
+    end
+
+    begin
+        opts.parse!(ARGV)
+    rescue
+        raise "Unable to parse options: #{$!}"
+    end
+
+    # initialize output handle
+    if options.output == "-"
+        OUT = $stdout.clone
+    else
+        OUT = File.open(options.output, "w")
+    end
+
+    if ARGV.size > 0
+        begin
+            IN = File.open(ARGV[0], "r")
+        rescue
+            print "Unable to open input file #{ARGV[0]}\n"
+            exit 1
+        end
+    else
+        IN = StringIO.new($stdin.read)
+    end
+
+    if options.mappings then
+        typeMappings = TypeMapper.new.to_map(options.mappings)
+    else
+        typeMappingd = {}
+    end
+
+    # run the command
+    CsvChecker.check(IN, OUT, typeMappings, {:col_sep => options.separator}, options.skip_first_row)
+    
+    # leave in peace
+    OUT.flush
+end

data/csv-check.gemspec

@@ -0,0 +1,25 @@
+# -*- encoding: utf-8 -*-
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'csv-check/version'
+
+Gem::Specification.new do |gem|
+  gem.name          = "csv-check"
+  gem.version       = CsvCheck::VERSION
+  gem.authors       = ["rory"]
+  gem.email         = ["rory@deadcrow.net"]
+  gem.description   = %q{Lets you verify that cells in a CSV files match formats you expect}
+  gem.summary       = %q{Allows you to specify formats (integer, float, string, date (with checking aginst date format strings) for columns in CSV data, both std in and files)}
+  gem.homepage      = "http://github.com/rorygibson/csv-check"
+
+  gem.files         = `git ls-files`.split($/)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.require_paths = ["lib"]
+
+  gem.add_dependency "fastercsv", ">= 0"
+
+  gem.add_development_dependency "rspec", "~> 2.6"
+  gem.add_development_dependency "cucumber"
+  gem.add_development_dependency "aruba"
+end

data/features/any.feature

@@ -0,0 +1,47 @@
+@any
+Feature: Checking that a column can contain any type of value
+
+  Scenario: Any can substiture for integer
+  	Given a file named "test.csv" with:
+  	"""
+  	a,b,c,d
+  	1,2,3,4
+  	"""
+    When I run `csv-check -k --map "0:any" test.csv`
+    Then the output should contain "Found 0 errors"
+    And the exit status should be 0
+
+
+  Scenario: Any can substiture for float
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    1.0, 2, 3, 4
+    """
+    When I run `csv-check -k --map "0:any" test.csv`
+    Then the output should contain "Found 0 errors"
+    And the exit status should be 0
+
+
+  Scenario: Any can substiture for string
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    x, 2, 3, 4
+    """
+    When I run `csv-check -k --map "0:any" test.csv`
+    Then the output should contain "Found 0 errors"
+    And the exit status should be 0
+
+
+  Scenario: Any doesn't substitute for nil
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    , 2, 3, 4
+    """
+    When I run `csv-check -k --map "0:any" test.csv`
+    Then the output should contain "Found 1 errors"
+    And the exit status should be 1
+
+

data/features/cli.feature

@@ -0,0 +1,22 @@
+Feature: Skip first row
+  In order to work with files with or without headers
+  As a CLI
+  I want to be able to skip the first row of input
+
+  Scenario: Skip first row
+  	Given a file named "test.csv" with:
+  	"""
+  	a,b,c,d
+  	1,2,3,4 
+  	"""
+    When I run `csv-check -k -m "0:integer" test.csv`
+    Then the output should contain "Total number of lines checked: 1"
+
+  Scenario: Don't skip first row  
+  	Given a file named "test.csv" with:
+  	"""
+  	a,b,c,d
+  	1,2,3,4 
+  	"""
+    When I run `csv-check -m "0:integer" test.csv`
+    Then the output should contain "Total number of lines checked: 2"

data/features/date.feature

@@ -0,0 +1,46 @@
+@date
+Feature: Checking that a column can contain only date values
+
+  Scenario: Check for presence of date in a column - successful - one row
+  	Given a file named "test.csv" with:
+  	"""
+  	a,b,c,d
+  	01/01/1980,2,3,4
+  	"""
+    When I run `csv-check -k --map "0:date" test.csv`
+    Then the output should contain "Found 0 errors"
+    And the exit status should be 0
+
+
+  Scenario: Specifying date format - success
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    01/01/1980 12:50,2,3,4
+    """
+    When I run `csv-check -k --map "0:date('%d/%m/%Y %H:%M')" test.csv`
+    Then the output should contain "Found 0 errors"
+    And the exit status should be 0   
+
+
+  Scenario: Specifying date format - failure
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    01/01/1980 12:50,2,3,4
+    """
+    When I run `csv-check -k --map "0:date('%d/%m/%Y')" test.csv`
+    Then the output should contain "Found 1 errors"
+    And the exit status should be 1    
+
+
+  Scenario: Check for presence of date in a column - failure - one row
+  	Given a file named "test.csv" with:
+  	"""
+  	a,b,c,d
+  	1,2,x,4
+  	"""
+    When I run `csv-check -k --map "2:date" test.csv`
+    Then the output should contain "Found 1 errors"   
+    And the exit status should be 1
+

data/features/float.feature

@@ -0,0 +1,34 @@
+@float
+Feature: Checking that a column can contain only float values
+
+  Scenario: Check for presence of float in a column - successful - one row
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    1.0, 2, 3, 4
+    """
+    When I run `csv-check -k --map "0:float" test.csv`
+    Then the output should contain "Found 0 errors"
+    And the exit status should be 0
+
+  Scenario: Check for presence of float in a column - failure - one row
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    1.0, 2.0, x, 4.0
+    """
+    When I run `csv-check -k --map "2:float" test.csv`
+    Then the output should contain "Found 1 errors"   
+    And the exit status should be 1
+
+  Scenario: Check for presence of float in a column - multiple rows and mapping elements
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    1.0, 2.0, 3.0, 4.0
+    5.0, 6.0, 7.0, 8.0
+    4.0, 3.0, 2.0, 1.0
+    """
+    When I run `csv-check -k --map "0:float,1:float,2:float,3:float" test.csv`
+    Then the output should contain "Found 0 errors"   
+    And the exit status should be 0

data/features/integer.feature

@@ -0,0 +1,54 @@
+@integer
+Feature: Checking that a column can contain only integer values
+
+  Scenario: Check for presence of integer in a column - successful - one row
+  	Given a file named "test.csv" with:
+  	"""
+  	a,b,c,d
+  	1,2,3,4
+  	"""
+    When I run `csv-check -k --map "0:integer" test.csv`
+    Then the output should contain "Found 0 errors"
+    And the exit status should be 0
+
+  Scenario: Check for presence of integer in a column - failure - one row
+  	Given a file named "test.csv" with:
+  	"""
+  	a,b,c,d
+  	1,2,x,4
+  	"""
+    When I run `csv-check -k --map "2:integer" test.csv`
+    Then the output should contain "Found 1 errors"   
+    And the exit status should be 1
+
+  Scenario: Quoted integers are allowed
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    "1000","2000","1000","4000"
+    """
+    When I run `csv-check -k --map "2:integer" test.csv`
+    Then the output should contain "Found 0 errors"   
+    And the exit status should be 0
+
+  Scenario: Comma-separated numbers aren't allowed
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    "1000","2000","1,000","4000"
+    """
+    When I run `csv-check -k --map "2:integer" test.csv`
+    Then the output should contain "Found 1 errors"   
+    And the exit status should be 1
+
+  Scenario: Check for presence of integer in a column - multiple rows and mapping elements
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    1,2,3,4
+    5,6,7,8
+    4,3,2,1
+    """
+    When I run `csv-check -k --map "0:integer,1:integer,2:integer,3:integer" test.csv`
+    Then the output should contain "Found 0 errors"   
+    And the exit status should be 0

data/features/parsing-tolerance.feature

@@ -0,0 +1,13 @@
+Feature: Parsing is tolerant of spaces in cells and at the end of lines
+
+  Scenario: End of line has spaces
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    1,2,3,4   
+    5,6,7,8    
+    4,3,2,1 
+    """
+    When I run `csv-check -k --map "0:integer,1:integer,2:integer,3:integer" test.csv`
+    Then the output should contain "Found 0 errors"   
+    And the exit status should be 0  

data/features/real-example.feature

@@ -0,0 +1,42 @@
+@real
+Feature: Test against a real example
+
+  Scenario: Test against a real example, row is OK
+    Given a file named "test.csv" with:
+    """
+    1359515,7102,129,11/09/2012 00:00,IP12 7QN,X21356,RM,16 Long Road,2000,200000,7831060
+    1359524,7158,129,11/09/2012 00:00,E14 3NU,X22366,SS,57 Wide Road,34000,0,734820
+    1359534,8073,136,11/09/2012 00:00,S11 3XX,X22373,DP,27 Sally Road,8000,85000,559974/1
+    1359590,7073,240,11/09/2012 00:00,RM5 5UB,X22419,IL,9 Green Green,130000,144000,A6229012190-1
+    1359647,6937,353,11/09/2012 00:00,GU4 0SN,X22474,S2,50 Owls'n'Blades Road,250000,250000,9455066180 040305
+    1359670,20,301,11/09/2012 00:00,DN17 5AD,X22898,FA,19 Olive Oyl,200000,200000,70727669
+    1359682,3228,6,11/09/2012 00:00,AB1 8FD,X22811,RM,7 Middleearth Crescent,225000,500000,9453390 036541705
+    """
+    When I run `csv-check -k --map "0:integer,1:integer,2:integer,3:string,4:string,5:string,6:string,7:string,8:integer,9:integer,10:any" test.csv`
+    Then the output should contain "Found 0 errors"
+    And the exit status should be 0
+
+
+  Scenario: Test against a real example, row has errors
+    Given a file named "test.csv" with:
+    """
+    6856,Mr,"Christie, Stephen",1985,0072613
+    6857,Ms,"Parkes, Sirah",2001,0854757
+    6859,Mr,"Dyce, John",Barr Brady,0096518
+    """
+    When I run `csv-check -k --map "0:integer,1:string,2:string,3:integer,4:integer" test.csv`
+    Then the output should contain "Found 1 errors"   
+    And the exit status should be 1
+
+
+  Scenario: Check for presence of string in a column - multiple rows and mapping elements
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    e,f,g,h
+    i,j,k,l
+    m,n,o,p
+    """
+    When I run `csv-check -k --map "0:string,1:string,2:string,3:string" test.csv`
+    Then the output should contain "Found 0 errors"   
+    And the exit status should be 0

data/features/string.feature

@@ -0,0 +1,36 @@
+@string
+Feature: Checking that a column can contain only string values
+
+  Scenario: Check for presence of string in a column - successful - one row
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    w,x,y,z
+    """
+    When I run `csv-check -k --map "0:string" test.csv`
+    Then the output should contain "Found 0 errors"
+    And the exit status should be 0
+
+
+  Scenario: Check for presence of string in a column - failure - one row
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    w,x,1,z
+    """
+    When I run `csv-check -k --map "2:string" test.csv`
+    Then the output should contain "Found 1 errors"   
+    And the exit status should be 1
+
+
+  Scenario: Check for presence of string in a column - multiple rows and mapping elements
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    e,f,g,h
+    i,j,k,l
+    m,n,o,p
+    """
+    When I run `csv-check -k --map "0:string,1:string,2:string,3:string" test.csv`
+    Then the output should contain "Found 0 errors"   
+    And the exit status should be 0

data/features/support/setup.rb

@@ -0,0 +1 @@
+require 'aruba/cucumber'

data/features/works-one-one-row-or-many.feature

@@ -0,0 +1,24 @@
+@integer
+Feature: Should work the same regardless of number of rows
+
+  Scenario: Works for header + one row
+  	Given a file named "test.csv" with:
+  	"""
+  	a,b,c,d
+  	1,2,3,4
+  	"""
+    When I run `csv-check -k --map "0:integer" test.csv`
+    Then the output should contain "Found 0 errors"
+    And the exit status should be 0
+
+  Scenario: Works for header + many rows
+    Given a file named "test.csv" with:
+    """
+    a,b,c,d
+    1,2,3,4
+    5,6,7,8
+    4,3,2,1
+    """
+    When I run `csv-check -k --map "0:integer,1:integer,2:integer,3:integer" test.csv`
+    Then the output should contain "Found 0 errors"   
+    And the exit status should be 0

data/lib/csv-check/version.rb

@@ -0,0 +1,3 @@
+module CsvCheck
+  VERSION = "0.0.1"
+end

data/lib/csvchecker.rb

@@ -0,0 +1,111 @@
+require 'rubygems'
+require 'fastercsv'
+require  File.join(File.expand_path(File.dirname(__FILE__)), '..', 'lib', 'typechecker.rb')
+
+module CsvChecker
+
+    DEFAULT_DATE_FORMAT = "%d/%m/%Y"
+
+	def check input, output, mappings={}, csv_options={}, skip_first=false
+		line_no = 1
+		lines_scanned = 0
+        num_errors = 0
+
+        i = 0
+        FasterCSV.new(input, csv_options).each do |row|
+            if skip_first then
+            	line_no = line_no + 1
+            	skip_first = false
+                next
+            end
+
+			lines_scanned = lines_scanned + 1 
+            
+            num_errors = num_errors + check_row(i, row, mappings) unless row.empty?
+            i = i + 1
+        end
+
+        print "Total number of lines checked: #{lines_scanned}\n"
+        print "Found #{num_errors} errors"
+        print "\n"
+
+        if num_errors > 0 then
+            exit 1
+        else
+            exit 0
+        end
+	end
+
+
+    def check_row row_num, row, mappings
+        raise "Nil mappings" if mappings.nil? 
+        raise "Nil row" if row.nil?
+
+        errors = 0
+        i = 0
+        row.each { |item|
+            type = mappings[i.to_s]
+
+            if type then
+                puts "Checking [#{item}] against [#{type}]\n"
+                valid = is_valid item, type
+                if !valid then
+                    print "Error at row #{row_num} column #{i}\n"
+                    errors = errors + 1 
+                end
+            end
+
+            i = i + 1
+        } 
+
+        return errors
+    end
+
+
+    def is_valid cell, type
+        raise 'Nil type' unless type
+        raise 'Empty type' unless type.size > 0
+
+        type_selector = type.downcase
+        type_selector = "date" if type.match /^date/ 
+
+        case type_selector
+        when 'integer'
+            return TypeChecker.new.is_integer?(cell)
+
+        when 'float'
+            return TypeChecker.new.is_float?(cell)
+
+        when 'string'
+            return TypeChecker.new.is_string?(cell)
+
+        when 'date'
+            format = dateFormatFrom(type)
+            return TypeChecker.new.is_date?(cell, format)
+
+        when 'any'
+            return TypeChecker.new.is_any?(cell)
+
+        else
+            raise "Unrecognised column type [#{type_selector}]"
+        end
+    end
+
+    def dateFormatFrom str
+        return DEFAULT_DATE_FORMAT if str == "date" 
+
+        puts "[#{str}]\n"
+
+        if str.match /^date.*/ then
+            type = str[ /'(.*)'/ , 1 ]
+            return type
+        end
+
+        return DEFAULT_DATE_FORMAT
+    end
+
+    module_function :check
+    module_function :is_valid
+    module_function :check_row
+    module_function :dateFormatFrom
+end

data/lib/typechecker.rb

@@ -0,0 +1,55 @@
+class TypeChecker
+	
+    def is_integer?(str)
+      str = str.to_s
+      str.strip!
+
+      match_pattern = /^[-+]?[0-9][0-9]*?$/
+      return !str.match(match_pattern).nil?
+    end
+
+    def is_float?(str)
+      str = str.to_s
+      str.strip!
+
+      match_pattern = /^[-+]?[0-9]*\.[0-9]+?$/
+      return !str.match(match_pattern).nil?
+    end
+
+    def is_date?(data, format)
+      parsed = nil
+      begin
+        parsed = DateTime.parse(data)
+      rescue
+      end
+      output = parsed.strftime(format) if parsed
+      matches = (output == data)
+
+      return matches
+    end
+
+    def is_space?(thing)
+      return thing.to_s == " "
+    end
+
+    def is_nil?(thing) 
+      return thing.nil?
+    end
+
+    def is_string?(thing) 
+      return false if is_nil?(thing)      
+      return false if is_integer?(thing) 
+      return false if is_float?(thing)
+      return true if is_space?(thing)
+      true if thing.is_a? String
+    end
+
+    def is_any?(thing) 
+      return false if is_nil?(thing)      
+      return true if is_integer?(thing) 
+      return true if is_float?(thing)
+      return true if is_space?(thing)
+      true if thing.is_a? String
+    end
+
+end

data/lib/typemapper.rb

@@ -0,0 +1,17 @@
+class TypeMapper 
+
+	def to_map str
+		raise 'Nil map string' unless str
+		raise 'Empty map string' if str.length == 0
+
+		map = Hash.new
+		str.split(",").each {|pair|
+			split_pair = pair.split(":", 2)
+			k = split_pair[0]
+			v = split_pair[1]
+			map[k] = v
+		}
+		map
+	end
+
+end

data/spec/csvchecker_date_format_extraction.rb

@@ -0,0 +1,17 @@
+require  File.join(File.expand_path(File.dirname(__FILE__)), '..', 'lib', 'csvchecker.rb')
+
+describe CsvChecker, "#dateFormatFrom" do
+
+  it "should extract a simple format" do
+  	CsvChecker.dateFormatFrom("date('%d-%m-%Y')").should eq("%d-%m-%Y")
+  end
+
+  it "should extract a timestamp format" do
+  	CsvChecker.dateFormatFrom("date('%d-%m-%Y %H:%M')").should eq("%d-%m-%Y %H:%M")
+  end
+
+  it "should supply the default format if no format is supplied" do
+  	CsvChecker.dateFormatFrom("date").should eq("%d/%m/%Y")
+  end
+
+end

data/spec/csvchecker_is_valid.rb

@@ -0,0 +1,25 @@
+require 'csvchecker'
+
+describe CsvChecker, "#is_valid" do
+
+  it "should raise an error for an unknown type" do
+    expect { CsvChecker.is_valid(1, 'SOMETHING_ELSE')}.to raise_error
+  end
+
+  it "should pass when an integer is found" do
+    CsvChecker.is_valid(1, 'integer').should eq(true)
+  end
+
+  it "should allow types to be specific case-insensitively" do
+    CsvChecker.is_valid(1, 'InTeGeR').should eq(true)
+  end
+
+  it "should allow cells to have spaces at the end" do
+    CsvChecker.is_valid("1 ", 'integer').should eq(true)
+  end
+
+  it "should allow cells to have spaces at the start" do
+    CsvChecker.is_valid(" 1 ", 'integer').should eq(true)
+  end
+
+end

data/spec/typechecker_is_any.rb

@@ -0,0 +1,25 @@
+require  File.join(File.expand_path(File.dirname(__FILE__)), '..', 'lib', 'typechecker.rb')
+
+describe TypeChecker, "#is_string" do
+
+  it "should allow a float" do
+    TypeChecker.new.is_any?("1.0").should eq(true)
+  end
+
+  it "should allow an integer" do
+    TypeChecker.new.is_any?("1").should eq(true)
+  end
+
+  it "should allow a string" do
+    TypeChecker.new.is_any?("x").should eq(true)
+  end
+
+  it "should allow a space" do
+    TypeChecker.new.is_any?(" ").should eq(true)
+  end
+
+  it "should not allow a nil" do
+    TypeChecker.new.is_any?(nil).should eq(false)
+  end
+
+end

data/spec/typechecker_is_date.rb

@@ -0,0 +1,17 @@
+require  File.join(File.expand_path(File.dirname(__FILE__)), '..', 'lib', 'typechecker.rb')
+
+describe TypeChecker, "#is_date" do
+
+  it "should allow a date that matches the date format" do
+    TypeChecker.new.is_date?("01/01/2012", "%d/%m/%Y").should eq(true)
+  end
+
+  it "should work with custom formats" do
+    TypeChecker.new.is_date?("01-01-2012", "%d/%m/%Y").should eq(false)
+  end
+
+  it "should allow timestamps if used with custom format" do
+    TypeChecker.new.is_date?("01-01-2012 12:50", "%d-%m-%Y %H:%M").should eq(true)
+  end
+
+end

data/spec/typechecker_is_float.rb

@@ -0,0 +1,29 @@
+require  File.join(File.expand_path(File.dirname(__FILE__)), '..', 'lib', 'typechecker.rb')
+
+describe TypeChecker, "#is_string" do
+
+  it "should allow a negative float" do
+    TypeChecker.new.is_float?("-1.0").should eq(true)
+  end
+
+  it "should allow a positive signed float" do
+    TypeChecker.new.is_float?("+1.0").should eq(true)
+  end
+
+  it "should allow a zero-padded float" do
+    TypeChecker.new.is_float?("001.0").should eq(true)
+  end
+
+  it "should allow more than one digit after the decimal point" do
+    TypeChecker.new.is_float?("2.000").should eq(true)
+  end
+
+  it "should require numbers after the decimal point" do
+    TypeChecker.new.is_float?("1.").should eq(false)
+  end
+
+  it "should not require numbers before the decimal point" do
+    TypeChecker.new.is_float?(".22").should eq(true)
+  end
+
+end

data/spec/typechecker_is_integer.rb

@@ -0,0 +1,21 @@
+require  File.join(File.expand_path(File.dirname(__FILE__)), '..', 'lib', 'typechecker.rb')
+
+describe TypeChecker, "#is_integer" do
+
+  it "should be true for an Integer" do
+    TypeChecker.new.is_integer?("1").should eq(true)
+  end
+
+  it "should be false for a string" do
+    TypeChecker.new.is_integer?("a string").should eq(false)
+  end
+
+  it "should be false for a space" do
+    TypeChecker.new.is_integer?(" ").should eq(false)
+  end
+
+  it "should be false for a float" do
+    TypeChecker.new.is_integer?("1.0").should eq(false)
+  end
+
+end

data/spec/typechecker_is_string.rb

@@ -0,0 +1,25 @@
+require  File.join(File.expand_path(File.dirname(__FILE__)), '..', 'lib', 'typechecker.rb')
+
+describe TypeChecker, "#is_string" do
+
+  it "should be true for a string" do
+    TypeChecker.new.is_string?("some string").should eq(true)
+  end
+
+  it "should be false for an integer" do
+    TypeChecker.new.is_string?("1").should eq(false)
+  end
+
+  it "should be true for a string with an integer in it" do
+    TypeChecker.new.is_string?("abc1def").should eq(true)
+  end
+
+  it "should be true for a space" do
+    TypeChecker.new.is_string?(" ").should eq(true)
+  end
+
+  it "should be false for a float" do
+    TypeChecker.new.is_string?("1.0").should eq(false)
+  end
+
+end

data/spec/typechecker_misc.rb

@@ -0,0 +1,9 @@
+require  File.join(File.expand_path(File.dirname(__FILE__)), '..', 'lib', 'typechecker.rb')
+
+describe TypeChecker, "#misc" do
+
+  it "should be false for nil" do
+    TypeChecker.new.is_nil?(nil).should eq(true)
+  end
+
+end

data/spec/typemapper.rb

@@ -0,0 +1,21 @@
+require  File.join(File.expand_path(File.dirname(__FILE__)), '..', 'lib', 'typemapper.rb')
+
+describe TypeMapper, "#to_map" do
+
+  it "should create the map" do
+    TypeMapper.new.to_map("0:integer,1:string").should == {"1"=>"string", "0"=>"integer"}
+  end
+
+  it "should raise error for a nil string" do
+    expect { TypeMapper.new.to_map(nil) }.to raise_error
+  end
+
+  it "should raise error for an empty string" do
+    expect { TypeMapper.new.to_map("") }.to raise_error
+  end
+
+  it "should allow type names with colons in (for date format)" do
+  	TypeMapper.new.to_map("0:integer,1:date('%d/%m/%Y %H:%M')").should == { "0"=>"integer", "1"=>"date('%d/%m/%Y %H:%M')" }	
+  end
+
+end

data/test.csv

@@ -0,0 +1,2 @@
+a,b,c,d
+1,2,3,4

metadata

@@ -0,0 +1,171 @@
+--- !ruby/object:Gem::Specification 
+name: csv-check
+version: !ruby/object:Gem::Version 
+  hash: 29
+  prerelease: 
+  segments: 
+  - 0
+  - 0
+  - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+- rory
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2012-10-09 00:00:00 Z
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: fastercsv
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 15
+        segments: 
+        - 2
+        - 6
+        version: "2.6"
+  type: :development
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: cucumber
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: aruba
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id004
+description: Lets you verify that cells in a CSV files match formats you expect
+email: 
+- rory@deadcrow.net
+executables: 
+- csv-check
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- .gitignore
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/csv-check
+- csv-check.gemspec
+- features/any.feature
+- features/cli.feature
+- features/date.feature
+- features/float.feature
+- features/integer.feature
+- features/parsing-tolerance.feature
+- features/real-example.feature
+- features/string.feature
+- features/support/setup.rb
+- features/works-one-one-row-or-many.feature
+- lib/csv-check/version.rb
+- lib/csvchecker.rb
+- lib/typechecker.rb
+- lib/typemapper.rb
+- spec/csvchecker_date_format_extraction.rb
+- spec/csvchecker_is_valid.rb
+- spec/typechecker_is_any.rb
+- spec/typechecker_is_date.rb
+- spec/typechecker_is_float.rb
+- spec/typechecker_is_integer.rb
+- spec/typechecker_is_string.rb
+- spec/typechecker_misc.rb
+- spec/typemapper.rb
+- test.csv
+homepage: http://github.com/rorygibson/csv-check
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: Allows you to specify formats (integer, float, string, date (with checking aginst date format strings) for columns in CSV data, both std in and files)
+test_files: 
+- features/any.feature
+- features/cli.feature
+- features/date.feature
+- features/float.feature
+- features/integer.feature
+- features/parsing-tolerance.feature
+- features/real-example.feature
+- features/string.feature
+- features/support/setup.rb
+- features/works-one-one-row-or-many.feature
+- spec/csvchecker_date_format_extraction.rb
+- spec/csvchecker_is_valid.rb
+- spec/typechecker_is_any.rb
+- spec/typechecker_is_date.rb
+- spec/typechecker_is_float.rb
+- spec/typechecker_is_integer.rb
+- spec/typechecker_is_string.rb
+- spec/typechecker_misc.rb
+- spec/typemapper.rb