zarby 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3979c8c12db4aaa03312129567f9836f09fd4ef4c1288b4f6737e3b030e4aae7
-  data.tar.gz: 265f5cf58138de71a8a4cd977bc7222a78c20c6cecd5346744c5561ecca41a62
+  metadata.gz: fe5948267cd436af9d1cd8639040bee740b642b57f3d79cdb9cf26537508f08e
+  data.tar.gz: a7989a59ed50492a700bd258d63dedbf4bd8a3e4cb38caea59c1300d3e76453e
 SHA512:
-  metadata.gz: 32832c0c4d326ca5bb0ec5fbee10b05cacc01712f178cb1c8aacb3e9148571e0b6a3a7389c744572c46c25ba1a783bf6852b8c1a672708995885ded6ecbfe5d4
-  data.tar.gz: 6fe7d3c06a98f18dc921f9dadc9a272e0389cb341f567df6f1d2bf6222555fac02fe44e4d60a83ffca8e56f5dfb08b6fd06f547d6210772d4ffa20c3b27bb04f
+  metadata.gz: adaab75a5d8988eb5074068a4746d02fde6267bf2abad0e842eaec851771f9b135fe942001a77467806c911b34fc77ee4b39c3022eb7fe43e3a45a8cfeaaa44d
+  data.tar.gz: da24b0a4c02b6ca7296cec3caf79292faebb2803eaae4aa3de9ce3545eac4b7f0f4247139be8d264e43b722808050cbb6e8fea29b013d1d823257b43d7b7c705

data/lib/zarby/normalize.rb

@@ -0,0 +1,43 @@
+# frozen_string_literal: true
+
+module Zarby
+  class Normalize
+    # utf-8 converting from the string's given encoding
+    COMMON_ENCODINGS = %w[UTF-8 Windows-1252 ASCII-8BIT US-ASCII].freeze
+
+    def initialize(input:)
+      @input = input
+    end
+
+    def self.utf8(input)
+      new(input: input).utf8
+    end
+
+    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
+
+      # 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?
+    rescue Encoding::UndefinedConversionError, Encoding::InvalidByteSequenceError
+      nil
+    end
+
+    def valid?
+      @input.encoding.name == 'UTF-8' && @input.valid_encoding?
+    end
+  end
+end

data/lib/zarby/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Zarby
-  VERSION = "0.1.0"
+  VERSION = "0.1.1"
 end

data/lib/zarby.rb

@@ -2,6 +2,7 @@
 
 require_relative 'zarby/version'
 require_relative 'zarby/csv'
+require_relative 'zarby/normalize'
 
 module Zarby
   class ZarbyError < StandardError; end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: zarby
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - vianney.sonneville
@@ -22,6 +22,7 @@ files:
 - Rakefile
 - lib/zarby.rb
 - lib/zarby/csv.rb
+- lib/zarby/normalize.rb
 - lib/zarby/version.rb
 - sig/zarby.rbs
 - zarby.gemspec
@@ -49,7 +50,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
+rubygems_version: 3.2.3
 signing_key: 
 specification_version: 4
 summary: String encoding and decoding with Ruby.