ruby_peter_v 0.0.9 → 0.0.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 9762b0492175ba460a71bc5602d2d42b5f1c2b5e
-  data.tar.gz: 3c7ae31f9dc676b795a2caa239bf1a5357e17c96
+  metadata.gz: 7190173c2c5c5a0bfadfcb55c312266cad3ac5d5
+  data.tar.gz: 2f8acf9357dfcd5806d1780f87dbc8457904aa8d
 SHA512:
-  metadata.gz: 562966d338daaf75304ace84f272bbefd9aa4454f61abaca07b69fb01e0efff1cfb0679e3f7c1e9a9a489da06547dc31b6d49da7b3a49d1721829c0d099fcb45
-  data.tar.gz: de6280af695b4badacd306374aa681b5c4865790330adebea3c77199addfb2a30871288597efd014e89353aebb024b9502e820314c8545da5a8961b698a24805
+  metadata.gz: 37531a42eef7fd73f99004ef47fccccae802a4219e8eb58ae30d26baffa9d4353c515102ae5a8741649decbcf61dae002036d6193f1a803545273a33b4ab3404
+  data.tar.gz: 43fe5335e3e48d2ce37a73e06b39cf36614c2dabade2b6e9b6dfb52ab185aefe075687e2fa531c3e5ec47c7a942ec622611c55c70ffac38cf2879b1ee0f2c7b0

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format progress

data/Guardfile

@@ -1,4 +1,4 @@
-guard :rspec do
+guard :rspec, :all_after_pass => true, :all_on_start => true do
   watch(%r{^spec/.+_spec\.rb$})
   watch(%r{^lib/(.+)\.rb$})     { |m| "spec/lib/#{m[1]}_spec.rb" }
   watch('spec/spec_helper.rb')  { "spec" }

data/HISTORY.txt

@@ -39,5 +39,9 @@
 
 * Object#each_recursively always returns self
 
+0.0.10 (2013-07-08)
+
+* truncate_utf8(max_byte_size)
+
 TODO
 * Object#assert_keys_in

data/README.md

@@ -120,3 +120,34 @@ d
 2.0.0-p195 :032 > b1 == b2
  => false
 ```
+
+### truncate_utf8(max_byte_size) on String
+
+  Cutting off on bytes inside a utf-8 encoded string will create invalid strings.
+  This implementation limits the number of _bytes_ (not the number of characters).
+  It is based on the response of "Angelo" on
+  http://joernhees.de/blog/2010/12/14/how-to-restrict-the-length-of-a-unicode-string/
+
+```
+/Users/peter_v/p/ruby_peter_v $ irb
+2.0.0-p247 :001 > require 'ruby_peter_v'
+ => true
+2.0.0-p247 :002 > s = 'ABCDüéàè'
+ => "ABCDüéàè"
+2.0.0-p247 :003 > s.size
+ => 8
+2.0.0-p247 :004 > s.bytesize
+ => 12
+2.0.0-p247 :005 > s.truncate_utf8(4)
+ => "ABCD"
+2.0.0-p247 :006 > s.truncate_utf8(5)
+ => "ABCD"
+2.0.0-p247 :007 > s.truncate_utf8(5).bytesize
+ => 4
+2.0.0-p247 :008 > s.truncate_utf8(6)
+ => "ABCDü"
+2.0.0-p247 :009 > s.truncate_utf8(7)
+ => "ABCDü"
+2.0.0-p247 :010 > s.truncate_utf8(7).valid_encoding?
+ => true
+```

data/lib/ruby_peter_v/truncate_utf8.rb

@@ -0,0 +1,7 @@
+class String
+
+  def truncate_utf8(max_byte_size)
+    self.bytes.to_a[0...max_byte_size].pack('c*').force_encoding('UTF-8').encode("UTF-16BE", :invalid => :replace, :replace =>"").encode("UTF-8")
+  end
+
+end

data/lib/ruby_peter_v/version.rb

@@ -1,3 +1,3 @@
 module RubyPeterV
-  VERSION = "0.0.9"
+  VERSION = "0.0.10"
 end

data/lib/ruby_peter_v.rb

@@ -3,3 +3,4 @@ require 'ruby_peter_v/single'
 require 'ruby_peter_v/set_once'
 require 'ruby_peter_v/define_equality'
 require 'ruby_peter_v/each_recursively'
+require 'ruby_peter_v/truncate_utf8'

data/spec/lib/ruby_peter_v/truncate_utf8_spec.rb

@@ -0,0 +1,55 @@
+# encoding=utf-8
+require 'spec_helper'
+
+describe 'truncate_utf8' do
+
+  context 'ASCII only' do
+
+    let (:a120) { 'A' * 120 }
+
+    it 'leaves untouched if max_size is larger' do
+      a120.truncate_utf8(140).should == a120
+    end
+
+    it 'leaves untouched if max_size is equal' do
+      a120.truncate_utf8(120).should == a120
+    end
+
+    it 'cuts-off if max_size is smaller' do
+      a120.truncate_utf8(100).should == 'A'*100
+    end
+  end
+
+  context 'UTF-8' do
+
+    let (:a120) { 'A' * 100 + 'üÜêéàèûôëï' }
+
+    it 'leaves untouched if max_size is larger' do
+      a120.truncate_utf8(140).should == a120
+    end
+
+    it 'leaves untouched if max_size is equal' do
+      a120.truncate_utf8(120).should == a120
+    end
+
+    it 'cuts-off if max_size is smaller' do
+      a120.truncate_utf8(100).should == 'A' * 100
+    end
+
+    context 'cut-off falls in the UTF-8 region' do
+      it 'on utf-8 boundary' do
+        a120.truncate_utf8(104).should == 'A' * 100 + 'üÜ'
+      end
+
+      context 'halfway in a utf-8 character' do
+        it 'keeps all up to one less' do
+          a120.truncate_utf8(103).should == 'A' * 100 + 'ü'
+        end
+
+        it 'is valid encoding' do
+          a120.truncate_utf8(103).should be_valid_encoding
+        end
+      end
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ruby_peter_v
 version: !ruby/object:Gem::Version
-  version: 0.0.9
+  version: 0.0.10
 platform: ruby
 authors:
 - Peter Vandenabeele
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-06-16 00:00:00.000000000 Z
+date: 2013-07-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -74,6 +74,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - .gitignore
+- .rspec
 - .rvmrc
 - .travis.yml
 - Gemfile
@@ -87,12 +88,14 @@ files:
 - lib/ruby_peter_v/each_recursively.rb
 - lib/ruby_peter_v/set_once.rb
 - lib/ruby_peter_v/single.rb
+- lib/ruby_peter_v/truncate_utf8.rb
 - lib/ruby_peter_v/version.rb
 - ruby_peter_v.gemspec
 - spec/lib/ruby_peter_v/define_equality_spec.rb
 - spec/lib/ruby_peter_v/each_recursively_spec.rb
 - spec/lib/ruby_peter_v/set_once_spec.rb
 - spec/lib/ruby_peter_v/single_spec.rb
+- spec/lib/ruby_peter_v/truncate_utf8_spec.rb
 - spec/spec_helper.rb
 homepage: https://github.com/petervandenabeele/ruby_peter_v
 licenses: []
@@ -122,4 +125,5 @@ test_files:
 - spec/lib/ruby_peter_v/each_recursively_spec.rb
 - spec/lib/ruby_peter_v/set_once_spec.rb
 - spec/lib/ruby_peter_v/single_spec.rb
+- spec/lib/ruby_peter_v/truncate_utf8_spec.rb
 - spec/spec_helper.rb