smarter_csv 1.4.0 → 1.4.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c8236e4cc8f0081efd9b74f12ad4b5342707d0a2f883414b07538160910008a3
-  data.tar.gz: b04a53b0030bf6c623aa19fb15c0c6c5ca123ce2ff85d47f176884fffa0f9811
+  metadata.gz: 3be724101d41326ff480bcb723c1b40a3cabd879eb55e0c2f044372f8e5a57d0
+  data.tar.gz: 657db1421352f449bf042f8df4d5178167af048ad37836e4f2f2f8a6aea3ece0
 SHA512:
-  metadata.gz: f2ddaa7bf44362c8bb4439289172d40b6ca926a67a8a35fb335473ddf7349658a629f3008ece5314c6bc5fa17145a2ae89b4d706b9c130a1642a51f2434d5e21
-  data.tar.gz: b48908b657a07589886873fe251263dabbe6e2333a1fc025dfede085841544458d4498ba1d288a4a7c0de3875d1c14631cc584b2a1cb7fd0be1543b758781dd3
+  metadata.gz: 3430649df35ac8139d35b04b85e8691ca5fc3d98b7b15f0d3987855f571987bdb742e0ed6f807ddb7a2e61e61d696d529ac311bc58e30188325f1c4bb78098a4
+  data.tar.gz: 1b386af7cc7c39bc7ea934875e16f6641a2cc0c2bb5dfaa3b1f298739b1b355b2f41570e42998a2d7790a17f96feb07118b69c23d913acc634aae5901f0c9229

data/.gitignore

@@ -6,3 +6,5 @@
 .bundle
 Gemfile.lock
 pkg/*
+coverage/*
+.DS_Store

data/CHANGELOG.md

@@ -1,14 +1,18 @@
 
 # SmarterCSV 1.x Change Log
 
-## 1.4.0 (2022-01-11)
+## 1.4.1 (2022-02-12)
+  * minor fix: also support `col_sep: :auto`
+  * added simplecov
+
+## 1.4.0 (2022-02-11)
   * dropped GPL license, smarter_csv is now only using the MIT License
   * added experimental option `col_sep: 'auto` to auto-detect the column separator (issue #183)
     The default behavior is still to assume `,` is the column separator. 
   * fixed buggy behavior when using `remove_empty_values: false` (issue #168)
   * fixed Ruby 3.0 deprecation
 
-## 1.3.0 (2022-01-06) Breaking code change if you used `--key_mappings`
+## 1.3.0 (2022-02-06) Breaking code change if you used `--key_mappings`
  * fix bug for key_mappings (issue #181)   
    The values of the `key_mappings` hash will now be used "as is", and no longer forced to be symbols
 

data/CONTRIBUTORS.md

@@ -0,0 +1,45 @@
+# A Big Thank You to all the Contributors!!
+
+
+A Big Thank you to everyone who filed issues, sent comments, and who contributed with pull requests:
+
+ * [Jack 0](https://github.com/xjlin0)
+ * [Alejandro](https://github.com/agaviria)
+ * [Lucas Camargo de Almeida](https://github.com/lcalmeida)
+ * [Raphaël Bleuse](https://github.com/bleuse)
+ * [feens](https://github.com/feens)
+ * [César Camacho](https://github.com/chanko)
+ * [innhyu](https://github.com/innhyu)
+ * [Benjamin Thouret](https://github.com/benichu)
+ * [Chris Hilton](https://github.com/chrismhilton)
+ * [Sean Duckett](http://github.com/sduckett)
+ * [Alex Ong](http://github.com/khaong)
+ * [Martin Nilsson](http://github.com/MrTin)
+ * [Eustáquio Rangel](http://github.com/taq)
+ * [Pavel](http://github.com/paxa)
+ * [Félix Bellanger](https://github.com/Keeguon)
+ * [Graham Wetzler](https://github.com/grahamwetzler)
+ * [Marcos G. Zimmermann](https://github.com/marcosgz)
+ * [Jordan Running](https://github.com/jrunning)
+ * [Dave Sanders](https://github.com/DaveSanders)
+ * [Hugo Lepetit](https://github.com/giglemad)
+ * [esBeee](https://github.com/esBeee)
+ * [Waldyr de Souza](https://github.com/waldyr)
+ * [Ben Maher](https://github.com/benmaher)
+ * [Wal McConnell](https://github.com/wal)
+ * [Jordan Graft](https://github.com/jordangraft)
+ * [Michael](https://github.com/polycarpou)
+ * [Kevin Coleman](https://github.com/KevinColemanInc)
+ * [Tirdad C.](https://github.com/tridadc)
+ * [Dave Myron](https://github.com/contentfree)
+ * [Ivan Ushakov](https://github.com/IvanUshakov)
+ * [Matthieu Paret](https://github.com/mtparet)
+ * [Rohit Amarnath](https://github.com/ramarnat)
+ * [Joshua Smith](https://github.com/enviable)
+ * [Colin Petruno](https://github.com/colinpetruno)
+ * [Diego Salido](https://github.com/salidux)
+ * [Elie](https://github.com/elieteyssedou)
+ * [Chris Wong](https://github.com/lightwave)
+ * [Olle Jonsson](https://github.com/olleolleolle)
+ * [Nicolas Guillemain](https://github.com/Viiruus)
+ * [Sp6](https://github.com/sp6)

data/LICENSE.txt

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2022 Tilo Sloboda
+Copyright (c) 2012..2022 Tilo Sloboda
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

data/README.md

@@ -1,17 +1,23 @@
-# SmarterCSV
-
-[![Build Status](https://secure.travis-ci.org/tilo/smarter_csv.svg?branch=master)](http://travis-ci.org/tilo/smarter_csv) [![Gem Version](https://badge.fury.io/rb/smarter_csv.svg)](http://badge.fury.io/rb/smarter_csv)
 
----------------
 #### Service Announcement
 
 * Work towards SmarterCSV 2.0 is still on it's way, with much improved features, and more streamlined options.
-  Please check the 2.0-develop branch, open any issues and pull requests with mention of v2.0.
+  Please check the [2.0-develop branch](https://github.com/tilo/smarter_csv/blob/master/README.md), open any issues and pull requests with mention of v2.0.
 
-* New versions on the 1.2 branch will soon print a deprecation warning if you set :verbose to true
+* New versions of SmarterCSV 1.x will soon print a deprecation warning if you set :verbose to true
   See below for list of deprecated options.
 
+#### Restructured Branches
+
+* default branch is `main` for 1.x development
+* 2.x development is on `2.0-development`
+
 ---------------
+
+# SmarterCSV
+
+[![Build Status](https://secure.travis-ci.org/tilo/smarter_csv.svg?branch=master)](http://travis-ci.org/tilo/smarter_csv) [![Gem Version](https://badge.fury.io/rb/smarter_csv.svg)](http://badge.fury.io/rb/smarter_csv)
+
 #### SmarterCSV 1.x
 
 `smarter_csv` is a Ruby Gem for smarter importing of CSV Files as Array(s) of Hashes, suitable for direct processing with Mongoid or ActiveRecord,
@@ -55,6 +61,7 @@ You can also set the `:row_sep` manually! Checkout Example 5 for unusual `:row_s
 #### Example 1a: How SmarterCSV processes CSV-files as array of hashes:
 Please note how each hash contains only the keys for columns with non-null values.
 
+```ruby
      $ cat pets.csv
      first name,last name,dogs,cats,birds,fish
      Dan,McAllister,2,,,
@@ -70,21 +77,25 @@ Please note how each hash contains only the keys for columns with non-null value
            {:first_name=>"Miles", :last_name=>"O'Brian", :fish=>"21"},
            {:first_name=>"Nancy", :last_name=>"Homes", :dogs=>"2", :birds=>"1"}
          ]
+```
 
 
 #### Example 1b: How SmarterCSV processes CSV-files as chunks, returning arrays of hashes:
 Please note how the returned array contains two sub-arrays containing the chunks which were read, each chunk containing 2 hashes.
 In case the number of rows is not cleanly divisible by `:chunk_size`, the last chunk contains fewer hashes.
 
+```ruby
      > pets_by_owner = SmarterCSV.process('/tmp/pets.csv', {:chunk_size => 2, :key_mapping => {:first_name => :first, :last_name => :last}})
        => [ [ {:first=>"Dan", :last=>"McAllister", :dogs=>"2"}, {:first=>"Lucy", :last=>"Laweless", :cats=>"5"} ],
             [ {:first=>"Miles", :last=>"O'Brian", :fish=>"21"}, {:first=>"Nancy", :last=>"Homes", :dogs=>"2", :birds=>"1"} ]
           ]
+```
 
 #### Example 1c: How SmarterCSV processes CSV-files as chunks, and passes arrays of hashes to a given block:
 Please note how the given block is passed the data for each chunk as the parameter (array of hashes),
 and how the `process` method returns the number of chunks when called with a block
 
+```ruby
      > total_chunks = SmarterCSV.process('/tmp/pets.csv', {:chunk_size => 2, :key_mapping => {:first_name => :first, :last_name => :last}}) do |chunk|
          chunk.each do |h|   # you can post-process the data from each row to your heart's content, and also create virtual attributes:
            h[:full_name] = [h[:first],h[:last]].join(' ')  # create a virtual attribute
@@ -96,16 +107,16 @@ and how the `process` method returns the number of chunks when called with a blo
        [{:dogs=>"2", :full_name=>"Dan McAllister"}, {:cats=>"5", :full_name=>"Lucy Laweless"}]
        [{:fish=>"21", :full_name=>"Miles O'Brian"}, {:dogs=>"2", :birds=>"1", :full_name=>"Nancy Homes"}]
         => 2
-
+```
 #### Example 2: Reading a CSV-File in one Chunk, returning one Array of Hashes:
-
+```ruby
     filename = '/tmp/input_file.txt' # TAB delimited file, each row ending with Control-M
     recordsA = SmarterCSV.process(filename, {:col_sep => "\t", :row_sep => "\cM"})  # no block given
 
     => returns an array of hashes
-
+```
 #### Example 3: Populate a MySQL or MongoDB Database with SmarterCSV:
-
+```ruby
     # without using chunks:
     filename = '/tmp/some.csv'
     options = {:key_mapping => {:unwanted_row => nil, :old_row_name => :new_name}}
@@ -116,9 +127,9 @@ and how the `process` method returns the number of chunks when called with a blo
     end
 
      => returns number of chunks / rows we processed
-
+```
 #### Example 4: Populate a MongoDB Database in Chunks of 100 records with SmarterCSV:
-
+```ruby
     # using chunks:
     filename = '/tmp/some.csv'
     options = {:chunk_size => 100, :key_mapping => {:unwanted_row => nil, :old_row_name => :new_name}}
@@ -129,10 +140,10 @@ and how the `process` method returns the number of chunks when called with a blo
     end
 
      => returns number of chunks we processed
-
+```
 
 #### Example 5: Reading a CSV-like File, and Processing it with Resque:
-
+```ruby
     filename = '/tmp/strange_db_dump'   # a file with CRTL-A as col_separator, and with CTRL-B\n as record_separator (hello iTunes!)
     options = {
       :col_sep => "\cA", :row_sep => "\cB\n", :comment_regexp => /^#/,
@@ -142,11 +153,11 @@ and how the `process` method returns the number of chunks when called with a blo
         Resque.enque( ResqueWorkerClass, chunk ) # pass chunks of CSV-data to Resque workers for parallel processing
     end
     => returns number of chunks
-
+```
 #### Example 6: Using Value Converters
 
 NOTE: If you use `key_mappings` and `value_converters`, make sure that the value converters has references the keys based on the final mapped name, not the original name in the CSV file.
-
+```ruby
     $ cat spec/fixtures/with_dates.csv
     first,last,date,price
     Ben,Miller,10/30/1998,$44.50
@@ -179,7 +190,7 @@ NOTE: If you use `key_mappings` and `value_converters`, make sure that the value
       => 44.50
     data[0][:price].class
       => Float
-
+```
 ## Parallel Processing
 [Jack](https://github.com/xjlin0) wrote an interesting article about [Speeding up CSV parsing with parallel processing](http://xjlin0.github.io/tech/2015/05/25/faster-parsing-csv-with-parallel-processing)
 
@@ -206,7 +217,7 @@ The options and the block are optional.
      | :skip_lines                 |   nil    | how many lines to skip before the first line or header line is processed             |
      | :comment_regexp             |   /^#/   | regular expression which matches comment lines (see NOTE about the CSV header)       |
      ---------------------------------------------------------------------------------------------------------------------------------
-     | :col_sep                    |   ','    | column separator, can be set to 'auto'                                               |
+     | :col_sep                    |   ','    | column separator, can be set to :auto                                                |
      | :force_simple_split         |   false  | force simple splitting on :col_sep character for non-standard CSV-files.             |
      |                             |          | e.g. when :quote_char is not properly escaped                                        |
      | :row_sep                    | $/ ,"\n" | row separator or record separator , defaults to system's $/ , which defaults to "\n" |
@@ -258,19 +269,19 @@ And header and data validations will also be supported in 2.x
 #### NOTES about File Encodings:
  * if you have a CSV file which contains unicode characters, you can process it as follows:
 
-
+```ruby
        File.open(filename, "r:bom|utf-8") do |f|
          data = SmarterCSV.process(f);
        end
-
+```
 * if the CSV file with unicode characters is in a remote location, similarly you need to give the encoding as an option to the `open` call:
-
+```ruby
        require 'open-uri'
        file_location = 'http://your.remote.org/sample.csv'
        open(file_location, 'r:utf-8') do |f|   # don't forget to specify the UTF-8 encoding!!
          data = SmarterCSV.process(f)
        end
-
+```
 #### NOTES about CSV Headers:
  * as this method parses CSV files, it is assumed that the first line of any file will contain a valid header
  * the first line with the CSV header may or may not be commented out according to the :comment_regexp
@@ -304,64 +315,27 @@ And header and data validations will also be supported in 2.x
 ## Installation
 
 Add this line to your application's Gemfile:
-
+```ruby
     gem 'smarter_csv'
-
+```
 And then execute:
-
+```ruby
     $ bundle
-
+```
 Or install it yourself as:
-
+```ruby
     $ gem install smarter_csv
-
+```
 ## [ChangeLog](./CHANGELOG.md)
 
 ## Reporting Bugs / Feature Requests
 
 Please [open an Issue on GitHub](https://github.com/tilo/smarter_csv/issues) if you have feedback, new feature requests, or want to report a bug. Thank you!
 
+  * please include a small sample CSV file
+  * please mention your version of SmarterCSV, Ruby, Rails
 
-## Special Thanks
-
-Many thanks to people who have filed issues and sent comments.
-And a special thanks to those who contributed pull requests:
-
- * [Jack 0](https://github.com/xjlin0)
- * [Alejandro](https://github.com/agaviria)
- * [Lucas Camargo de Almeida](https://github.com/lcalmeida)
- * [Raphaël Bleuse](https://github.com/bleuse)
- * [feens](https://github.com/feens)
- * [César Camacho](https://github.com/chanko)
- * [innhyu](https://github.com/innhyu)
- * [Benjamin Thouret](https://github.com/benichu)
- * [Chris Hilton](https://github.com/chrismhilton)
- * [Sean Duckett](http://github.com/sduckett)
- * [Alex Ong](http://github.com/khaong)
- * [Martin Nilsson](http://github.com/MrTin)
- * [Eustáquio Rangel](http://github.com/taq)
- * [Pavel](http://github.com/paxa)
- * [Félix Bellanger](https://github.com/Keeguon)
- * [Graham Wetzler](https://github.com/grahamwetzler)
- * [Marcos G. Zimmermann](https://github.com/marcosgz)
- * [Jordan Running](https://github.com/jrunning)
- * [Dave Sanders](https://github.com/DaveSanders)
- * [Hugo Lepetit](https://github.com/giglemad)
- * [esBeee](https://github.com/esBeee)
- * [Waldyr de Souza](https://github.com/waldyr)
- * [Ben Maher](https://github.com/benmaher)
- * [Wal McConnell](https://github.com/wal)
- * [Jordan Graft](https://github.com/jordangraft)
- * [Michael](https://github.com/polycarpou)
- * [Kevin Coleman](https://github.com/KevinColemanInc)
- * [Tirdad C.](https://github.com/tridadc)
- * [Dave Myron](https://github.com/contentfree)
- * [Ivan Ushakov](https://github.com/IvanUshakov)
- * [Matthieu Paret](https://github.com/mtparet)
- * [Rohit Amarnath](https://github.com/ramarnat)
- * [Joshua Smith](https://github.com/enviable)
- * [Colin Petruno](https://github.com/colinpetruno)
- * [Diego Salido](https://github.com/salidux)
+## [A Special Thanks to all Contributors!](CONTRIBUTORS.md) 🎉🎉🎉
 
 
 ## Contributing

data/Rakefile

@@ -1,26 +1,19 @@
 #!/usr/bin/env rake
 require "bundler/gem_tasks"
-
 require 'rubygems'
 require 'rake'
-
 require 'rspec/core/rake_task'
 
+task :default => :spec
+
 desc "Run RSpec"
 RSpec::Core::RakeTask.new do |t|
-  t.verbose = false
+  # t.verbose = false
 end
 
-desc "Run specs for all test cases"
-task :spec_all do 
-  system "rake spec"
+desc 'Run spec with coverage'
+task :coverage do
+  ENV['COVERAGE'] = 'true'
+  Rake::Task['spec'].execute
+  `open coverage/index.html`
 end
-
-# task :spec_all do
-#   %w[active_record data_mapper mongoid].each do |model_adapter|
-#     puts "MODEL_ADAPTER = #{model_adapter}"
-#     system "rake spec MODEL_ADAPTER=#{model_adapter}"
-#   end
-# end
-
-task :default => :spec

data/lib/smarter_csv/smarter_csv.rb

@@ -7,16 +7,9 @@ module SmarterCSV
   class NoColSepDetected < SmarterCSVException; end
 
   def SmarterCSV.process(input, options={}, &block)   # first parameter: filename or input object with readline method
-    default_options = {:col_sep => ',', :row_sep => $INPUT_RECORD_SEPARATOR, :quote_char => '"', :force_simple_split => false , :verbose => false ,
-      :remove_empty_values => true, :remove_zero_values => false , :remove_values_matching => nil , :remove_empty_hashes => true , :strip_whitespace => true,
-      :convert_values_to_numeric => true, :strip_chars_from_headers => nil , :user_provided_headers => nil , :headers_in_file => true,
-      :comment_regexp => /\A#/, :chunk_size => nil , :key_mapping_hash => nil , :downcase_header => true, :strings_as_keys => false, :file_encoding => 'utf-8',
-      :remove_unmapped_keys => false, :keep_original_headers => false, :value_converters => nil, :skip_lines => nil, :force_utf8 => false, :invalid_byte_sequence => '',
-      :auto_row_sep_chars => 500, :required_headers => nil
-    }
     options = default_options.merge(options)
     options[:invalid_byte_sequence] = '' if options[:invalid_byte_sequence].nil?
-    csv_options = options.select{|k,v| [:col_sep, :row_sep, :quote_char].include?(k)} # options.slice(:col_sep, :row_sep, :quote_char)
+
     headerA = []
     result = []
     old_row_sep = $INPUT_RECORD_SEPARATOR
@@ -26,22 +19,21 @@ module SmarterCSV
     begin
       f = input.respond_to?(:readline) ? input : File.open(input, "r:#{options[:file_encoding]}")
 
+      # auto-detect the row separator
+      options[:row_sep] = SmarterCSV.guess_line_ending(f, options) if options[:row_sep].to_sym == :auto
+      $INPUT_RECORD_SEPARATOR = options[:row_sep]
       # attempt to auto-detect column separator
-      options[:col_sep] = guess_column_separator(f) if options[:col_sep] == 'auto'
+      options[:col_sep] = guess_column_separator(f) if options[:col_sep].to_sym == :auto
+      # preserve options, in case we need to call the CSV class
+      csv_options = options.select{|k,v| [:col_sep, :row_sep, :quote_char].include?(k)} # options.slice(:col_sep, :row_sep, :quote_char)
+      csv_options.delete(:row_sep) if [nil, :auto].include?( options[:row_sep].to_sym )
+      csv_options.delete(:col_sep) if [nil, :auto].include?( options[:col_sep].to_sym )
 
       if (options[:force_utf8] || options[:file_encoding] =~ /utf-8/i) && ( f.respond_to?(:external_encoding) && f.external_encoding != Encoding.find('UTF-8') || f.respond_to?(:encoding) && f.encoding != Encoding.find('UTF-8') )
         puts 'WARNING: you are trying to process UTF-8 input, but did not open the input with "b:utf-8" option. See README file "NOTES about File Encodings".'
       end
 
-      if options[:row_sep] == :auto
-        options[:row_sep] = line_ending = SmarterCSV.guess_line_ending( f, options )
-        f.rewind
-      end
-      $INPUT_RECORD_SEPARATOR = options[:row_sep]
-
-      if options[:skip_lines].to_i > 0
-        options[:skip_lines].to_i.times{f.readline}
-      end
+      options[:skip_lines].to_i.times{f.readline} if options[:skip_lines].to_i > 0
 
       if options[:headers_in_file]        # extract the header line
         # process the header line in the CSV file..
@@ -87,7 +79,7 @@ module SmarterCSV
       else
         headerA = file_headerA
       end
-      header_size = headerA.size
+      header_size = headerA.size # used for splitting lines
 
       headerA.map!{|x| x.to_sym } unless options[:strings_as_keys] || options[:keep_original_headers]
 
@@ -141,8 +133,8 @@ module SmarterCSV
         # cater for the quoted csv data containing the row separator carriage return character
         # in which case the row data will be split across multiple lines (see the sample content in spec/fixtures/carriage_returns_rn.csv)
         # by detecting the existence of an uneven number of quote characters
-        multiline = line.count(options[:quote_char])%2 == 1
-        while line.count(options[:quote_char])%2 == 1
+        multiline = line.count(options[:quote_char])%2 == 1 # should handle quote_char nil
+        while line.count(options[:quote_char])%2 == 1 # should handle quote_char nil
           next_line = f.readline
           next_line = next_line.force_encoding('utf-8').encode('utf-8', invalid: :replace, undef: :replace, replace: options[:invalid_byte_sequence]) if options[:force_utf8] || options[:file_encoding] !~ /utf-8/i
           line += next_line
@@ -269,6 +261,39 @@ module SmarterCSV
 
   private
 
+  def self.default_options
+    {
+      auto_row_sep_chars: 500,
+      chunk_size: nil ,
+      col_sep: ',',
+      comment_regexp: /\A#/,
+      convert_values_to_numeric: true,
+      downcase_header: true,
+      file_encoding: 'utf-8',
+      force_simple_split: false ,
+      force_utf8: false,
+      headers_in_file: true,
+      invalid_byte_sequence: '',
+      keep_original_headers: false,
+      key_mapping_hash: nil ,
+      quote_char: '"',
+      remove_empty_hashes: true ,
+      remove_empty_values: true,
+      remove_unmapped_keys: false,
+      remove_values_matching: nil,
+      remove_zero_values: false,
+      required_headers: nil,
+      row_sep: $INPUT_RECORD_SEPARATOR,
+      skip_lines: nil,
+      strings_as_keys: false,
+      strip_chars_from_headers: nil,
+      strip_whitespace: true,
+      user_provided_headers: nil,
+      value_converters: nil,
+      verbose: false,
+    }
+  end
+
   def self.blank?(value)
     case value
     when Array
@@ -347,6 +372,8 @@ module SmarterCSV
       lines += 1
       break if options[:auto_row_sep_chars] && options[:auto_row_sep_chars] > 0 && lines >= options[:auto_row_sep_chars]
     end
+    filehandle.rewind
+
     counts["\r"] += 1 if last_char == "\r"
     # find the key/value pair with the largest counter:
     k,_ = counts.max_by{|_,v| v}

data/lib/smarter_csv/version.rb

@@ -1,3 +1,3 @@
 module SmarterCSV
-  VERSION = "1.4.0"
+  VERSION = "1.4.2"
 end

data/lib/smarter_csv.rb

@@ -1,3 +1,11 @@
+if ENV['COVERAGE']
+  require 'simplecov'
+  SimpleCov.start do
+    add_filter "/spec/"
+    add_filter "/pkg/"
+  end
+end
+
 require 'csv'
 require "smarter_csv/version"
 require "extensions/hash.rb"

data/smarter_csv.gemspec

@@ -18,6 +18,7 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
   spec.requirements  = ['csv'] # for CSV.parse() only needed in case we have quoted fields
   spec.add_development_dependency "rspec"
+  spec.add_development_dependency "simplecov"
   #  spec.add_development_dependency "guard-rspec"
 
   spec.metadata["homepage_uri"] = spec.homepage

data/spec/smarter_csv/carriage_return_spec.rb

@@ -3,7 +3,6 @@ require 'spec_helper'
 fixture_path = 'spec/fixtures'
 
 describe 'process files with line endings explicitly pre-specified' do
-
   it 'should process a file with \n for line endings and within data fields' do
     sep = "\n"
     options = {:row_sep => sep}
@@ -83,14 +82,14 @@ describe 'process files with line endings explicitly pre-specified' do
     data[1][:members].should == ["Jimmy Page", "Robert Plant", "John Bonham", "John Paul Jones"].join(text_sep)
     data[1][:albums].should == ["Led Zeppelin", "Led Zeppelin II", "Led Zeppelin III", "Led Zeppelin IV"].join(text_sep)
   end
-
 end
 
 describe 'process files with line endings in automatic mode' do
+  let(:options) { { row_sep: :auto } }
 
   it 'should process a file with \n for line endings and within data fields' do
     sep = "\n"
-    data = SmarterCSV.process("#{fixture_path}/carriage_returns_n.csv", {:row_sep => :auto})
+    data = SmarterCSV.process("#{fixture_path}/carriage_returns_n.csv", options)
     data.flatten.size.should == 8
     data[0][:name].should == "Anfield"
     data[0][:street].should == "Anfield Road"
@@ -112,7 +111,29 @@ describe 'process files with line endings in automatic mode' do
 
   it 'should process a file with \r for line endings and within data fields' do
     sep = "\r"
-    data = SmarterCSV.process("#{fixture_path}/carriage_returns_r.csv", {:row_sep => :auto})
+    data = SmarterCSV.process("#{fixture_path}/carriage_returns_r.csv", options)
+    data.flatten.size.should == 8
+    data[0][:name].should == "Anfield"
+    data[0][:street].should == "Anfield Road"
+    data[0][:city].should == "Liverpool"
+    data[1][:name].should == ["Highbury", "Highbury House"].join(sep)
+    data[2][:street].should == ["Sir Matt ", "Busby Way"].join(sep)
+    data[3][:city].should == ["Newcastle-upon-tyne ", "Tyne and Wear"].join(sep)
+    data[4][:name].should == ["White Hart Lane", "(The Lane)"].join(sep)
+    data[4][:street].should == ["Bill Nicholson Way ", "748 High Rd"].join(sep)
+    data[4][:city].should == ["Tottenham", "London"].join(sep)
+    data[5][:name].should == "Stamford Bridge"
+    data[5][:street].should == ["Fulham Road", "London"].join(sep)
+    data[5][:city].should be_nil
+    data[6][:name].should == ["Etihad Stadium", "Rowsley St", "Manchester"].join(sep)
+    data[7][:name].should == "Goodison"
+    data[7][:street].should == "Goodison Road"
+    data[7][:city].should == "Liverpool"
+  end
+
+  it 'also works when auto is given a string' do
+    sep = "\r"
+    data = SmarterCSV.process("#{fixture_path}/carriage_returns_r.csv", {row_sep: 'auto'})
     data.flatten.size.should == 8
     data[0][:name].should == "Anfield"
     data[0][:street].should == "Anfield Road"
@@ -134,7 +155,7 @@ describe 'process files with line endings in automatic mode' do
 
   it 'should process a file with \r\n for line endings and within data fields' do
     sep = "\r\n"
-    data = SmarterCSV.process("#{fixture_path}/carriage_returns_rn.csv", {:row_sep => :auto})
+    data = SmarterCSV.process("#{fixture_path}/carriage_returns_rn.csv", options)
     data.flatten.size.should == 8
     data[0][:name].should == "Anfield"
     data[0][:street].should == "Anfield Road"
@@ -157,7 +178,7 @@ describe 'process files with line endings in automatic mode' do
   it 'should process a file with more quoted text carriage return characters (\r) than line ending characters (\n)' do
     row_sep = "\n"
     text_sep = "\r"
-    data = SmarterCSV.process("#{fixture_path}/carriage_returns_quoted.csv", {:row_sep => :auto})
+    data = SmarterCSV.process("#{fixture_path}/carriage_returns_quoted.csv", options)
     data.flatten.size.should == 2
     data[0][:band].should == "New Order"
     data[0][:members].should == ["Bernard Sumner", "Peter Hook", "Stephen Morris", "Gillian Gilbert"].join(text_sep)
@@ -166,5 +187,4 @@ describe 'process files with line endings in automatic mode' do
     data[1][:members].should == ["Jimmy Page", "Robert Plant", "John Bonham", "John Paul Jones"].join(text_sep)
     data[1][:albums].should == ["Led Zeppelin", "Led Zeppelin II", "Led Zeppelin III", "Led Zeppelin IV"].join(text_sep)
   end
-
 end

data/spec/smarter_csv/column_separator_spec.rb

@@ -48,7 +48,7 @@ describe 'can handle col_sep' do
   end
 
   describe 'auto-detection of separator' do
-    options = {:col_sep => 'auto'}
+    options = {col_sep: :auto}
 
     it 'auto-detects comma separator and loads data' do
       data = SmarterCSV.process("#{fixture_path}/separator_comma.csv", options)
@@ -85,5 +85,11 @@ describe 'can handle col_sep' do
         SmarterCSV.process("#{fixture_path}/binary.csv", options)
       }.to raise_exception SmarterCSV::NoColSepDetected
     end
+
+    it 'also works when auto is given a string' do
+      data = SmarterCSV.process("#{fixture_path}/separator_pipe.csv", col_sep: 'auto')
+      data.first.keys.size.should == 4
+      data.size.should eq 3
+    end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: smarter_csv
 version: !ruby/object:Gem::Version
-  version: 1.4.0
+  version: 1.4.2
 platform: ruby
 authors:
 - Tilo Sloboda
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-02-11 00:00:00.000000000 Z
+date: 2022-02-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -24,6 +24,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: Ruby Gem for smarter importing of CSV Files as Array(s) of Hashes, with
   optional features for processing large files in parallel, embedded comments, unusual
   field- and record-separators, flexible mapping of CSV-headers to Hash-keys
@@ -38,6 +52,7 @@ files:
 - ".rvmrc"
 - ".travis.yml"
 - CHANGELOG.md
+- CONTRIBUTORS.md
 - Gemfile
 - LICENSE.txt
 - README.md
@@ -143,7 +158,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements:
 - csv
-rubygems_version: 3.1.4
+rubygems_version: 3.1.6
 signing_key:
 specification_version: 4
 summary: Ruby Gem for smarter importing of CSV Files (and CSV-like files), with lots