csvlint 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: a5c033caad4d4ee2536ecf2af837461a946151e1
+  data.tar.gz: 1c9d644f1295bbbeb2c160828d3a520f6b35999c
+SHA512:
+  metadata.gz: cf5029278e55511925b7abad559489810d8e56555ea46afd68960af2d18db786a6f0df2afa30ba4bcd99c1ea9d149d570536e94b84d45ce9bdae837d395dc1f2
+  data.tar.gz: 56f23ba6e7b701af2e7ec575519d46e7b4c29bfa6403f123359b89d58c1191df65166b3739a663b1febc66d8c54f9a339394ca74a890e42ccba2fb6cb03fc4d3

data/.coveralls.yml

@@ -0,0 +1 @@
+service_name: travis-ci

data/.gitignore

@@ -0,0 +1,22 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+coverage/
+/.rspec
+
+.idea
+.DS_Store

data/.travis.yml

@@ -0,0 +1,10 @@
+rvm:
+- 2.0.0
+notifications:
+  irc:
+    channels:
+      - "irc.freenode.net#theodi"
+    template:
+      - "%{repository} %{branch} - %{message} %{build_url}"
+    on_success: change
+    on_failure: always

data/Gemfile

@@ -0,0 +1,7 @@
+#ruby=ruby-2.0.0
+#ruby-gemset=csvlintrb
+
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in csvlint.rb.gemspec
+gemspec

data/LICENSE.md

@@ -0,0 +1,22 @@
+##Copyright (c) 2014 The Open Data Institute
+
+#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 +1,214 @@
+[![Build Status](http://img.shields.io/travis/theodi/csvlint.rb.svg)](https://travis-ci.org/theodi/csvlint.rb)
+[![Dependency Status](http://img.shields.io/gemnasium/theodi/csvlint.rb.svg)](https://gemnasium.com/theodi/csvlint.rb)
+[![Coverage Status](http://img.shields.io/coveralls/theodi/csvlint.rb.svg)](https://coveralls.io/r/theodi/csvlint.rb)
+[![License](http://img.shields.io/:license-mit-blue.svg)](http://theodi.mit-license.org)
+[![Badges](http://img.shields.io/:badges-5/5-ff6799.svg)](https://github.com/pikesley/badger)
+
+# CSV Lint
+
+A ruby gem to support validating CSV files to check their syntax and contents.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'csvlint'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install csvlint
+
+## Usage
+
+Currently the gem supports retrieving a CSV accessible from a URL, File, or an IO-style object (e.g. StringIO)
+
+	require 'csvlint'
+	
+	validator = Csvlint::Validator.new( "http://example.org/data.csv" )
+	validator = Csvlint::Validator.new( File.new("/path/to/my/data.csv" )
+	validator = Csvlint::Validator.new( StringIO.new( my_data_in_a_string ) )
+
+When validating from a URL the range of errors and warnings is wider as the library will also check HTTP headers for 
+best practices
+	
+	#invoke the validation	
+	validator.validate
+	
+	#check validation status
+	validator.valid?
+	
+	#access array of errors, each is an Csvlint::ErrorMessage object
+	validator.errors
+	
+	#access array of warnings
+	validator.warnings
+	
+	#access array of information messages
+	validator.info_messages
+	
+	#get some information about the CSV file that was validated
+	validator.encoding
+	validator.content_type
+	validator.extension
+	
+	#retrieve HTTP headers from request
+	validator.headers
+
+## Controlling CSV Parsing
+
+The validator supports configuration of the [CSV Dialect](http://dataprotocols.org/csv-dialect/) used in a data file. This is specified by 
+passing an options hash to the constructor:
+
+    opts = {
+    	"header" => true,
+    	"delimiter" => ","
+    }
+	validator = Csvlint::Validator.new( "http://example.org/data.csv", opts )
+
+The options should be a Hash that conforms to the [CSV Dialect](http://dataprotocols.org/csv-dialect/) JSON structure.
+
+While these options configure the parser to correctly process the file, the validator will still raise errors or warnings for CSV 
+structure that it considers to be invalid, e.g. a missing header or different delimiters.
+
+Note that the parser will also check for a `header` parameter on the `Content-Type` header returned when fetching a remote CSV file. As 
+specified in [RFC 4180](http://www.ietf.org/rfc/rfc4180.txt) the values for this can be `present` and `absent`, e.g:
+
+	Content-Type: text/csv; header=present
+
+## Error Reporting
+
+The validator provides feedback on a validation result using instances of `Csvlint::ErrorMessage`. Errors are divided into errors, warnings and information 
+messages. A validation attempt is successful if there are no errors.
+
+Messages provide context including:
+
+* `category` has a symbol that indicates the category or error/warning: `:structure` (well-formedness issues), `:schema` (schema validation), `:context` (publishing metadata, e.g. content type)
+* `type` has a symbol that indicates the type of error or warning being reported
+* `row` holds the line number of the problem
+* `column` holds the column number of the issue
+* `content` holds the contents of the row that generated the error or warning
+
+## Errors
+
+The following types of error can be reported:
+
+* `:wrong_content_type` -- content type is not `text/csv`
+* `:ragged_rows` -- row has a different number of columns (than the first row in the file)
+* `:blank_rows` -- completely empty row, e.g. blank line or a line where all column values are empty
+* `:invalid_encoding` -- encoding error when parsing row, e.g. because of invalid characters 
+* `:not_found` -- HTTP 404 error when retrieving the data
+* `:stray_quote` -- missing or stray quote
+* `:unclosed_quote` -- unclosed quoted field
+* `:whitespace` -- a quoted column has leading or trailing whitespace
+* `:line_breaks` -- line breaks were inconsistent or incorrectly specified
+* `:undeclared_header` -- if there is no machine-readable description of whether a header is present (e.g. in a dialect or `Content-Type` header)
+
+## Warnings
+
+The following types of warning can be reported:
+
+* `:no_encoding` -- the `Content-Type` header returned in the HTTP request does not have a `charset` parameter
+* `:encoding` -- the character set is not UTF-8
+* `:no_content_type` -- file is being served without a `Content-Type` header
+* `:excel` -- no `Content-Type` header and the file extension is `.xls`
+* `:check_options` -- CSV file appears to contain only a single column
+* `:inconsistent_values` -- inconsistent values in the same column. Reported if <90% of values seem to have same data type (either numeric or alphanumeric including punctuation)
+* `:empty_column_name` -- a column in the CSV header has an empty name
+* `:duplicate_column_name` -- a column in the CSV header has a duplicate name
+* `:title_row` -- if there appears to be a title field in the first row of the CSV
+
+## Information Messages
+
+There are also information messages available:
+
+* `:nonrfc_line_breaks` -- uses non-CRLF line breaks, so doesn't conform to RFC4180.
+* `:assumed_header` -- the validator has assumed that a header is present
+
+## Schema Validation
+
+The library supports validating data against a schema. A schema configuration can be provided as a Hash or parsed from JSON. The structure currently 
+follows JSON Table Schema with some extensions.
+
+An example schema file is:
+
+	{
+		"fields": [
+			{ 
+				"name": "id", 
+			  	"constraints": { "required": true } 
+			},
+            { 
+               	"name": "price", 
+               	"constraints": { "required": true, "minLength": 1 } 
+            },
+            { 
+            	"name": "postcode", 
+            	"constraints": { 
+            		"required": true, 
+            		"pattern": "[A-Z]{1,2}[0-9][0-9A-Z]? ?[0-9][A-Z]{2}" 
+            	} 
+            }
+        ]
+	}
+
+Parsing and validating with a schema:
+
+	schema = Schema.load_from_json_table(uri)
+	validator = Csvlint::Validator.new( "http://example.org/data.csv", nil, schema )
+
+Supported constraints:
+
+* `required` -- there must be a value for this field in every row
+* `unique` -- the values in every row should be unique
+* `minLength` -- minimum number of characters in the value
+* `maxLength` -- maximum number of characters in the value
+* `pattern` -- values must match the provided regular expression
+* `type` -- specifies an XML Schema data type. Values of the column must be a valid value for that type
+* `minimum` -- specify a minimum range for values, the value will be parsed as specified by `type`
+* `maximum` -- specify a maximum range for values, the value will be parsed as specified by `type` 
+* `datePattern` -- specify a `strftime` compatible date pattern to be used when parsing date values and min/max constraints
+
+Supported data types (this is still a work in progress):
+
+* String -- `http://www.w3.org/2001/XMLSchema#string` (effectively a no-op)
+* Integer -- `http://www.w3.org/2001/XMLSchema#integer` or `http://www.w3.org/2001/XMLSchema#int`
+* Float -- `http://www.w3.org/2001/XMLSchema#float`
+* Double -- `http://www.w3.org/2001/XMLSchema#double`
+* URI -- `http://www.w3.org/2001/XMLSchema#anyURI`
+* Boolean -- `http://www.w3.org/2001/XMLSchema#boolean`
+* Non Positive Integer -- `http://www.w3.org/2001/XMLSchema#nonPositiveInteger`
+* Positive Integer -- `http://www.w3.org/2001/XMLSchema#positiveInteger`
+* Non Negative Integer -- `http://www.w3.org/2001/XMLSchema#nonNegativeInteger`
+* Negative Integer -- `http://www.w3.org/2001/XMLSchema#negativeInteger`
+* Date -- `http://www.w3.org/2001/XMLSchema#date`
+* Date Time -- `http://www.w3.org/2001/XMLSchema#dateTime`
+* Year -- `http://www.w3.org/2001/XMLSchema#gYear`
+* Year Month -- `http://www.w3.org/2001/XMLSchema#gYearMonth`
+* Time -- `http://www.w3.org/2001/XMLSchema#time`
+
+Use of an unknown data type will result in the column failing to validate.
+	
+Schema validation provides some additional types of error and warning messages:
+
+* `:missing_value` (error) -- a column marked as `required` in the schema has no value
+* `:min_length` (error) -- a column with a `minLength` constraint has a value that is too short
+* `:max_length` (error) -- a column with a `maxLength` constraint has a value that is too long
+* `:pattern` (error) --  a column with a `pattern` constraint has a value that doesn't match the regular expression
+* `:header_name` (warning) -- the header in the CSV has a column name that doesn't match the schema
+* `:missing_column` (warning) -- a row in the CSV file has a missing column, that is specified in the schema. This is a warning only, as it may be legitimate
+* `:extra_column` (warning) -- a row in the CSV file has extra column.
+* `:unique` (error) -- a column with a `unique` constraint contains non-unique values
+* `:below_minimum` (error) -- a column with a `minimum` constraint contains a value that is below the minimum
+* `:above_maximum` (error) -- a column with a `maximum` constraint contains a value that is above the maximum
+
+## 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 +1,17 @@
+require "bundler/gem_tasks"
+
+$:.unshift File.join( File.dirname(__FILE__), "lib")
+
+require 'rubygems'
+require 'cucumber'
+require 'cucumber/rake/task'
+require 'coveralls/rake/task'
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+Coveralls::RakeTask.new
+Cucumber::Rake::Task.new(:features) do |t|
+  t.cucumber_opts = "features --format pretty"
+end
+
+task :default => [:spec, :features, 'coveralls:push']

data/bin/create_schema

@@ -0,0 +1,32 @@
+#!/usr/bin/env ruby
+$:.unshift File.join( File.dirname(__FILE__), "..", "lib")
+
+require 'csvlint'
+
+begin
+  puts ARGV[0]
+	csv = CSV.new( open(ARGV[0]) )
+	headers = csv.shift
+	
+	name = File.basename( ARGV[0] )
+	schema = {
+	  "title" => name,
+	  "description" => "Auto generated schema for #{name}",
+	  "fields" => []
+	}
+	
+	headers.each do |name|
+	  schema["fields"] << {
+	    "name" => name,
+	    "title" => "",
+	    "description" => "",
+	    "constraints" => {}
+	  }
+	end
+	
+	$stdout.puts JSON.pretty_generate(schema)
+rescue => e
+  puts e
+  puts e.backtrace
+	puts "Unable to parse CSV file"
+end

data/bin/csvlint

@@ -0,0 +1,52 @@
+#!/usr/bin/env ruby
+$:.unshift File.join( File.dirname(__FILE__), "..", "lib")
+
+require 'csvlint'
+require 'colorize'
+
+def print_error(index, error, color=:red)
+  location = ""
+  location += error.row.to_s if error.row
+  location += "#{error.row ? "," : ""}#{error.column.to_s}" if error.column
+  if error.row || error.column
+    location = "#{error.row ? "Row" : "Column"}: #{location}"
+  end
+  puts "#{index+1}. #{error.type}. #{location}".colorize(color)
+end
+
+if ARGV.length == 0 && !$stdin.tty?
+  source = StringIO.new(ARGF.read)
+else
+  if ARGV[0]
+    source = ARGV[0]
+    unless source =~ /^http(s)?/
+      begin
+        source = File.new( source ) unless source =~ /^http(s)?/ 
+      rescue Errno::ENOENT
+        puts "File not found"
+        exit 1
+      end
+    end
+  else
+    puts "Usage: csvlint {file or URL} or {input} | csvlint"
+    exit 1
+  end
+end
+
+validator = Csvlint::Validator.new( source )
+
+puts "#{ARGV[0] || "CSV"} is #{validator.valid? ? "VALID".green : "INVALID".red}"
+
+if validator.errors.size > 0
+  validator.errors.each_with_index do |error, i|
+    print_error(i, error)
+  end
+end
+
+if validator.warnings.size > 0
+  validator.warnings.each_with_index do |error, i|
+    print_error(i, error, :yellow)
+  end
+end
+
+exit 1 unless validator.valid?

data/csvlint.gemspec

@@ -0,0 +1,39 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'csvlint/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "csvlint"
+  spec.version       = Csvlint::VERSION
+  spec.authors       = ["pezholio"]
+  spec.email         = ["pezholio@gmail.com"]
+  spec.description   = %q{CSV Validator}
+  spec.summary       = %q{CSV Validator}
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "mime-types"
+  spec.add_dependency "colorize"
+  spec.add_dependency "open_uri_redirections"
+  spec.add_dependency "activesupport"
+  spec.add_dependency "addressable"
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "cucumber"
+  spec.add_development_dependency "simplecov"
+  spec.add_development_dependency "simplecov-rcov"
+  spec.add_development_dependency "spork"
+  spec.add_development_dependency "webmock"
+  spec.add_development_dependency "rspec"
+  spec.add_development_dependency "rspec-pride"
+  spec.add_development_dependency "rspec-expectations"
+  spec.add_development_dependency "coveralls"
+  spec.add_development_dependency "pry"
+end

data/features/check_format.feature

@@ -0,0 +1,46 @@
+Feature: Check inconsistent formatting
+
+  Scenario: Inconsistent formatting for integers
+    Given I have a CSV with the following content:
+    """
+"1","2","3"
+"Foo","5","6"
+"3","2","1"
+"3","2","1"
+    """
+    And it is stored at the url "http://example.com/example1.csv"
+    And I ask if there are warnings
+    Then there should be 1 warnings
+    And that warning should have the type "inconsistent_values"
+    And that warning should have the column "1"
+    
+  Scenario: Inconsistent formatting for alpha fields
+    Given I have a CSV with the following content:
+    """
+"Foo","Bar","Baz"
+"Biz","1","Baff"
+"Boff","Giff","Goff"
+"Boff","Giff","Goff"
+    """
+    And it is stored at the url "http://example.com/example1.csv"
+    And I ask if there are warnings
+    Then there should be 1 warnings
+    And that warning should have the type "inconsistent_values"
+    And that warning should have the column "2"
+
+  Scenario: Inconsistent formatting for alphanumeric fields
+    Given I have a CSV with the following content:
+    """
+"Foo 123","Bar","Baz"
+"1","Bar","Baff"
+"Boff 432423","Giff","Goff"
+"Boff444","Giff","Goff"
+    """
+    And it is stored at the url "http://example.com/example1.csv"
+    And I ask if there are warnings
+    Then there should be 1 warnings
+    And that warning should have the type "inconsistent_values"
+    And that warning should have the column "1"
+
+
+