utf8_attribute_sanitiser 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 138d5535c2fb1140fddb6bab8404f4f94b4a7da8
-  data.tar.gz: 8fbf3eb56cd339505aa474a56b0a943696f3ccbc
+  metadata.gz: cbb7d85533242790e75e8f9e43895bf387de33ab
+  data.tar.gz: 54c1ea7a00a4484421aa15a70e4aab27cb9afe23
 SHA512:
-  metadata.gz: 9211b4d1f72ef09a3a65660fba1867c601694a9c35d7493f239dd855684b5241ee1a185f3afbffeaaf2b870d40d3ff58f23a2ea8a9669434d5616c11151fde5f
-  data.tar.gz: 7e1925b3c6b60d7f22916d98f96be48a322e08e1b2f81da186297059f16c96877aaa36e95130932f2c80ec668046b816cf8d16c80fb25f8f38b5e3a83ad5f594
+  metadata.gz: 932b99e00cbd3efd7623202b5d37a46abb4331ca898be055f4ea57099cee8051650beaab4ebcb038973f5b3ed83d2bbc50b9fa97efbfd45d3196bb6b3c6d9edb
+  data.tar.gz: af36edb47e5ff513201b4d0598071d0d1dd2cb8ae845e259490718e6d04048cc7c87988f5df7cdcef5bf6dda9228ef7185bce1c469a3286031798cd76a7e6099

data/README.md

@@ -26,13 +26,21 @@ In your model add utf8_attribute_sanitiser, specyfing list of attribute names to
       utf8_attribute_sanitiser :name, :address
     end
 
+Default cleaning method is `utf8mb4only` and it only affects 4 byte characters
+
+You can use aggressive clean method that strips out all invalud utf8 characters like
+
+    class User < ActiveRecord::Base
+      utf8_attribute_sanitiser :name, :address, method: :aggressive
+    end
+
 ## Running tests
 
     $ rspec
 
 ## Contributing
 
-Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/utf8_attribute_sanitiser.
+Bug reports and pull requests are welcome on GitHub at https://github.com/tomdracz/utf8_attribute_sanitiser.
 
 
 ## License

data/lib/utf8_attribute_sanitiser.rb

@@ -1,11 +1,15 @@
 require "utf8_attribute_sanitiser/version"
 
 module Utf8AttributeSanitiser
-  def utf8_attribute_sanitiser(*attributes)
+  def utf8_attribute_sanitiser(*attributes, method: :utf8mb4only)
     attributes.each do |attribute|
       before_validation do |record|
         value = record[attribute]
-        sanitised_value = value.respond_to?(:encode) ? value.encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: "") : value
+        if method == :utf8mb4only
+          sanitised_value = value.respond_to?(:encode) ? value.each_char.select{|c| c.bytes.count < 4 }.join('') : value
+        elsif method == :aggressive
+          sanitised_value = value.respond_to?(:gsub) ? value.encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: "") : value
+        end
         record[attribute] = sanitised_value
       end
     end

data/lib/utf8_attribute_sanitiser/version.rb

@@ -1,3 +1,3 @@
 module Utf8AttributeSanitiser
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: utf8_attribute_sanitiser
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Tom Dracz
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-01-24 00:00:00.000000000 Z
+date: 2017-07-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -90,7 +90,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.6.8
+rubygems_version: 2.6.10
 signing_key: 
 specification_version: 4
 summary: Sanitise attributes to avoid invalid byte sequence argument errors