charazard 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 34b9d5367e647921915519d5a3a252f683ddf91b
-  data.tar.gz: b762b59f2e9ddeeefb4ade4afe6511a6756d1074
+  metadata.gz: 78cecee8b3d4cbc404f29ca445fe056e50560d32
+  data.tar.gz: 28d6d6e0982f2250ace5d28bc3451b1d2b646d38
 SHA512:
-  metadata.gz: 887e42a951e9fcb07146bcf9f7adc7dbde56f706dd6d964d32d345112bc27508a38d6210430218e2165ca785d07f1c5e37d840e74198938dc3a35c58f8b19a81
-  data.tar.gz: dd537a7e4d2ae0d675f06731a3aac65e729a0b28f341d6c4adcc8ec60073ab312aefa605722b03b3b093d76e5470af79bf430dc3d38b5e683a24390399334e1e
+  metadata.gz: b2f8ff14f35fad23fe61330df3f892a0a429799bbf24e936d20b9b94697834009154754c687d33b622ec46316e59613b991dac1b6b3ec62064434f5f9cd6018e
+  data.tar.gz: 59d6e5d5f2cf07daacbf9acb9e2ad36a1266f4d551090c3a9cd92ba6bd1609b4c1d74fa33066dd4f8ee4b7ee1caaa2be1cca02a7966268f2804ef0d72b5bee92

data/README.markdown

@@ -16,26 +16,15 @@ Charazard.fix_invalid_unicode_literals("\x93Smart quotes\x94 \xC3\x9Cber Unicode
 
 `Charazard.fix_invalid_unicode_literals` can be used in combination with
 [`filter_io`](https://github.com/jasoncodes/filter_io) to filter CSV streams.
-Here’s an example that handles UTF-8/ISO-8859-1 with mixed line endings:
+Since this is such a common use case, Charazard includes a handy
+[helper class](https://github.com/jasoncodes/charazard/blob/master/lib/charazard/io.rb):
 
 ``` ruby
-require 'filter_io'
-require 'charazard'
+require 'charazard/io'
 require 'csv'
 
 File.open(filename, external_encoding: 'UTF-8') do |io|
-  io = FilterIO.new(io) do |data, state|
-    # fix invalid UTF-8 literals
-    data = Charazard.fix_invalid_unicode_literals(data)
-
-    # grab another chunk if the last character is a delimiter
-    raise FilterIO::NeedMoreData if data =~ /[\r\n]\z/ && !state.eof?
-    # normalise line endings to LF
-    data = data.gsub /\r\n|\r|\n/, "\n"
-
-    data
-  end
-
+  io = Charazard::IO.new(io)
   CSV.parse(io, row_sep: "\n") do |row|
     p row
   end

data/charazard.gemspec

@@ -21,5 +21,7 @@ Gem::Specification.new do |spec|
 
   spec.add_development_dependency 'bundler', '~> 1.6'
   spec.add_development_dependency 'rake'
+  spec.add_development_dependency 'minitest'
+  spec.add_development_dependency 'filter_io'
   spec.add_development_dependency 'pry'
 end

data/lib/charazard/io.rb

@@ -0,0 +1,20 @@
+require 'charazard'
+require 'filter_io'
+
+module Charazard
+  class IO < FilterIO
+    def initialize(io)
+      super do |data, state|
+        # fix invalid UTF-8 literals
+        data = Charazard.fix_invalid_unicode_literals(data)
+
+        # grab another chunk if the last character is a delimiter
+        raise FilterIO::NeedMoreData if data =~ /[\r\n]\z/ && !state.eof?
+        # normalise line endings to LF
+        data = data.gsub /\r\n|\r|\n/, "\n"
+
+        data
+      end
+    end
+  end
+end

data/lib/charazard/version.rb

@@ -1,3 +1,3 @@
 module Charazard
-  VERSION = '0.0.1'
+  VERSION = '0.0.2'
 end

data/test/charazard_io_test.rb

@@ -0,0 +1,13 @@
+# -*- coding: utf-8 -*-
+
+require 'test_helper'
+require 'charazard/io'
+require 'csv'
+
+describe Charazard::IO do
+  it 'converts mixed character encodings into valid UTF-8' do
+    src = StringIO.new "Name,Character\nEm dash,\x97\r\nSmart quotes,\x93Quoted String\x94\r"
+    dst = Charazard::IO.new(src)
+    assert_equal "Name,Character\nEm dash,—\nSmart quotes,“Quoted String”\n", dst.read
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: charazard
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Jason Weathered
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-06-11 00:00:00.000000000 Z
+date: 2014-06-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -52,6 +52,34 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  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'
+- !ruby/object:Gem::Dependency
+  name: filter_io
+  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'
 - !ruby/object:Gem::Dependency
   name: pry
   requirement: !ruby/object:Gem::Requirement
@@ -80,7 +108,9 @@ files:
 - Rakefile
 - charazard.gemspec
 - lib/charazard.rb
+- lib/charazard/io.rb
 - lib/charazard/version.rb
+- test/charazard_io_test.rb
 - test/charazard_test.rb
 - test/test_helper.rb
 homepage: https://github.com/jasoncodes/charazard
@@ -108,5 +138,6 @@ signing_key:
 specification_version: 4
 summary: Cleans up bad character encodings with liberal application of fire.
 test_files:
+- test/charazard_io_test.rb
 - test/charazard_test.rb
 - test/test_helper.rb