zarby 0.1.4 → 0.1.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b77baffed4d87a5ea4f1b42a724ff83f437d2e8d8f5fee9188a826962797d954
-  data.tar.gz: 1fdf369f8e76f06dab6785ee54400aec28e730d391f4631891a4e50e628fc762
+  metadata.gz: 656415d6b0a326bad3ad11708792f82c83296f341bb4c0d58389942abb8d44ed
+  data.tar.gz: 2f4d28eb627d2bee49cf8ceb4e9d500cc6ba968e83fe6a2f77b5c37b6fb193b8
 SHA512:
-  metadata.gz: 4875f023186b998b527207b1e9c3b706c9c57eada03537050ba5f0d03e0f2f6fc273fe7c3622619fccfcf85e397ced4b236ef3327f07dabb2c01b66891ec9d01
-  data.tar.gz: 462fc6605506572793327457a9c3b84f145da2fbdb90fd2769b74ee5233c28d778e9e651b46bb34e412abc38e09f5a3375f11fa119339046d535229c17c90eb2
+  metadata.gz: bea273ad274d1f0e5acc1bc084ec7d78e5d7c88789e4e7e8725fa3fefaff5969b424667a58f3e73af7aa43a9adedce7bc9f3509e9d57783701dac21f3f1e22e5
+  data.tar.gz: 62219550c9ab648a856018395edb45ffb4527085a543d29cba2970c839a81e529a0b33e150ba3b448c861d3c5af60d791903f0e076b201ec83c94b89496e21b4

data/CHANGELOG.md

@@ -1,3 +1,20 @@
+# 0.1.5 / 2023-10-24
+
+## Enhancements
+
+* Refactoring method utf8 to Zarby::Csv class
+* Add documentation to Zarby::Csv module and Zarby::Normalize module
+
+# 0.1.4 / 2023-10-24
+
+* Remove missing debug log
+
+# 0.1.3 / 2023-10-24
+
+## Enhancements
+
+* Decode ASCII-8BIT (actually windows)
+
 # 0.1.2 / 2023-10-20
 
 ## Enhancements

data/lib/zarby/csv.rb

@@ -3,23 +3,30 @@
 module Zarby
   class NoColSepDetected < StandardError; end
 
+  # this class is used to detect the column separator in a CSV file
   class Csv
     COMMON_DELIMITERS = ['","', '";"', '":"', '"|"'].freeze
 
+    # @param [String] content
+    # @return [Csv]
     def initialize(content:)
       @content = content || ""
     end
 
+    # @param [String] content
+    # @return [String]
     def self.detect_separator(content)
       new(content: content).detect_separator
     end
 
+    # @return [String]
     def detect_separator
       valid? ? delimiters[0][0][1] : raise(Zarby::NoColSepDetected)
     end
 
     private
 
+    # @return [Boolean]
     def valid?
       !delimiters.collect(&:last).reduce(:+).zero?
     end
@@ -28,14 +35,17 @@ module Zarby
     # delimiters[0] #=> ["\";\"", 54]
     # delimiters[0][0] #=> "\",\""
     # delimiters[0][0][1] #=> ";"
+    # @return [Array<Array<String, Integer>>]
     def delimiters
       @delimiters ||= COMMON_DELIMITERS.inject({}, &count).sort(&most_found)
     end
 
+    # @return [Proc]
     def most_found
       ->(a, b) { b[1] <=> a[1] }
     end
 
+    # @return [Proc]
     def count
       lambda { |hash, delimiter|
         hash[delimiter] = @content.count(delimiter)

data/lib/zarby/normalize.rb

@@ -1,48 +1,36 @@
 # frozen_string_literal: true
 
 module Zarby
+  # this class is used to normalize the input string to UTF-8
   class Normalize
     # utf-8 converting from the string's given encoding
-    COMMON_ENCODINGS = %w[UTF-8 Windows-1252 ASCII-8BIT US-ASCII].freeze
+    COMMON_ENCODINGS = %w[UTF-8 Windows-1252 ASCII-8BIT ISO-8859-1 US-ASCII].freeze
 
+    # @param input [String]
+    # @return [String]
     def initialize(input:)
-      @input = input || ""
+      @input = input&.force_encoding(Encoding::UTF_8) || ''
     end
 
+    # @param input [String]
+    # @return [String]
     def self.utf8(input)
       new(input: input).utf8
     end
 
+    # @return [String]
     def utf8
       output = @input if valid?
-      COMMON_ENCODINGS.each do |encoding|
-        output ||= convert { @input.encode(encoding) }
-        output ||= convert { @input.force_encoding('UTF-8') } if encoding == 'UTF-8'
-      end
 
-      output ||= unpack_pack { @input.unpack("C*").pack("U*") } if output.nil?
 
-      # replace any unknown characters with a placeholder: �
-      output ||= convert { @input.encode('UTF-8', invalid: :replace, undef: :replace) }
-      output
-    end
-
-    private
-
-    def convert
-      string = yield
-      string if string.valid_encoding?
+      output ||= @input.force_encoding(Encoding::ISO_8859_1).encode!(Encoding::UTF_8)
     rescue Encoding::UndefinedConversionError, Encoding::InvalidByteSequenceError
       nil
     end
 
-    def unpack_pack
-      string = yield
-      string if string.valid_encoding?
-    rescue Encoding::UndefinedConversionError, Encoding::InvalidByteSequenceError
-      nil
-    end
+    private
 
+    # @return [Boolean]
     def valid?
       @input.encoding.name == 'UTF-8' && @input.valid_encoding?
     end

data/lib/zarby/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Zarby
-  VERSION = "0.1.4"
+  VERSION = "0.1.6"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: zarby
 version: !ruby/object:Gem::Version
-  version: 0.1.4
+  version: 0.1.6
 platform: ruby
 authors:
 - vianney.sonneville
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2023-10-24 00:00:00.000000000 Z
+date: 2023-11-24 00:00:00.000000000 Z
 dependencies: []
 description: 
 email: