ritter 0.0.87 → 0.0.88

data/spec/test_urls.rb

@@ -0,0 +1,80 @@
+# encoding: utf-8
+
+module TestUrls
+  VALID = [
+    "http://google.com",
+    "http://foobar.com/#",
+    "http://google.com/#foo",
+    "http://google.com/#search?q=iphone%20-filter%3Alinks",
+    "http://twitter.com/#search?q=iphone%20-filter%3Alinks",
+    "http://somedomain.com/index.php?path=/abc/def/",
+    "http://www.boingboing.net/2007/02/14/katamari_damacy_phon.html",
+    "http://somehost.com:3000",
+    "http://xo.com/~matthew+%-x",
+    "http://en.wikipedia.org/wiki/Primer_(film)",
+    "http://www.ams.org/bookstore-getitem/item=mbk-59",
+    "http://chilp.it/?77e8fd",
+    "http://tell.me/why",
+    "http://longtlds.info",
+    "http://✪df.ws/ejp",
+    "http://日本.com",
+    "http://search.twitter.com/search?q=avro&lang=en",
+    "http://mrs.domain-dash.biz",
+    "http://x.com/has/one/char/domain",
+    "http://t.co/nwcLTFF",
+    "http://sub_domain-dash.twitter.com",
+    "http://a.b.cd",
+    "http://a_b.c-d.com",
+    "http://a-b.b.com",
+    "http://twitter-dash.com",
+    "http://msdn.microsoft.com/ja-jp/library/system.net.httpwebrequest(v=VS.100).aspx",
+    "www.foobar.com",
+    "WWW.FOOBAR.COM",
+    "www.foobar.co.jp",
+    "http://t.co",
+    "t.co/nwcLTFF"
+  ] unless defined?(TestUrls::VALID)
+
+  INVALID = [
+    "http://no-tld",
+    "http://tld-too-short.x",
+    "http://-doman_dash.com",
+    "http://_leadingunderscore.twitter.com",
+    "http://trailingunderscore_.twitter.com",
+    "http://-leadingdash.twitter.com",
+    "http://trailingdash-.twitter.com",
+    "http://-leadingdash.com",
+    "http://trailingdash-.com",
+    "http://no_underscores.com",
+    "http://test.c_o_m",
+    "http://test.c-o-m",
+    "http://twitt#{[0x202A].pack('U')}er.com",
+    "http://twitt#{[0x202B].pack('U')}er.com",
+    "http://twitt#{[0x202C].pack('U')}er.com",
+    "http://twitt#{[0x202D].pack('U')}er.com",
+    "http://twitt#{[0x202E].pack('U')}er.com"
+  ] unless defined?(TestUrls::INVALID)
+
+  TCO = [
+    "http://t.co/P53cv5yO!",
+    "http://t.co/fQJmiPGg***",
+    "http://t.co/pbY2NfTZ's",
+    "http://t.co/2vYHpAc5;",
+    "http://t.co/ulYGBYSo:",
+    "http://t.co/GeT4bSiw=win",
+    "http://t.co/8MkmHU0k+fun",
+    "http://t.co/TKLp64dY.yes,",
+    "http://t.co/8vuO27cI$$",
+    "http://t.co/rPYTvdA8/",
+    "http://t.co/WvtMw5ku%",
+    "http://t.co/8t7G3ddS#",
+    "http://t.co/nfHNJDV2/#!",
+    "http://t.co/gK6NOXHs[good]",
+    "http://t.co/dMrT0o1Y]bad",
+    "http://t.co/FNkPfmii-",
+    "http://t.co/sMgS3pjI_oh",
+    "http://t.co/F8Dq3Plb~",
+    "http://t.co/ivvH58vC&help",
+    "http://t.co/iUBL15zD|NZ5KYLQ8"
+  ] unless defined?(TestUrls::TCO)
+end

data/spec/twitter_text_spec.rb

@@ -0,0 +1,21 @@
+# encoding: utf-8
+require File.dirname(__FILE__) + '/spec_helper'
+
+major, minor, patch = RUBY_VERSION.split('.')
+if major.to_i == 1 && minor.to_i < 9
+  describe "base" do
+    before do
+      $KCODE = 'NONE'
+    end
+
+    after do
+      $KCODE = 'u'
+    end
+
+    it "should raise with invalid KCODE on Ruby < 1.9" do
+      lambda do
+        require 'twitter-text'
+      end.should raise_error
+    end
+  end
+end

data/spec/unicode_spec.rb

@@ -0,0 +1,31 @@
+# encoding: utf-8
+require File.dirname(__FILE__) + '/spec_helper'
+
+describe Twitter::Unicode do
+
+  it "should lazy-init constants" do
+    Twitter::Unicode.const_defined?(:UFEB6).should == false
+    Twitter::Unicode::UFEB6.should_not be_nil
+    Twitter::Unicode::UFEB6.should be_kind_of(String)
+    Twitter::Unicode.const_defined?(:UFEB6).should == true
+  end
+
+  it "should return corresponding character" do
+    Twitter::Unicode::UFEB6.should == [0xfeb6].pack('U')
+  end
+
+  it "should allow lowercase notation" do
+    Twitter::Unicode::Ufeb6.should == Twitter::Unicode::UFEB6
+    Twitter::Unicode::Ufeb6.should === Twitter::Unicode::UFEB6
+  end
+
+  it "should allow underscore notation" do
+    Twitter::Unicode::U_FEB6.should == Twitter::Unicode::UFEB6
+    Twitter::Unicode::U_FEB6.should === Twitter::Unicode::UFEB6
+  end
+
+  it "should raise on invalid codepoints" do
+    lambda { Twitter::Unicode::FFFFFF }.should raise_error(NameError)
+  end
+
+end

data/spec/validation_spec.rb

@@ -0,0 +1,43 @@
+# encoding: binary
+require File.dirname(__FILE__) + '/spec_helper'
+
+class TestValidation
+  include Twitter::Validation
+end
+
+describe Twitter::Validation do
+
+  it "should disallow invalid BOM character" do
+    TestValidation.new.tweet_invalid?("Bom:#{Twitter::Unicode::UFFFE}").should == :invalid_characters
+    TestValidation.new.tweet_invalid?("Bom:#{Twitter::Unicode::UFEFF}").should == :invalid_characters
+  end
+
+  it "should disallow invalid U+FFFF character" do
+    TestValidation.new.tweet_invalid?("Bom:#{Twitter::Unicode::UFFFF}").should == :invalid_characters
+  end
+
+  it "should disallow direction change characters" do
+    [0x202A, 0x202B, 0x202C, 0x202D, 0x202E].map{|cp| [cp].pack('U') }.each do |char|
+      TestValidation.new.tweet_invalid?("Invalid:#{char}").should == :invalid_characters
+    end
+  end
+
+  it "should disallow non-Unicode" do
+    TestValidation.new.tweet_invalid?("not-Unicode:\xfff0").should == :invalid_characters
+  end
+
+  it "should allow <= 140 combined accent characters" do
+    char = [0x65, 0x0301].pack('U')
+    TestValidation.new.tweet_invalid?(char * 139).should == false
+    TestValidation.new.tweet_invalid?(char * 140).should == false
+    TestValidation.new.tweet_invalid?(char * 141).should == :too_long
+  end
+
+  it "should allow <= 140 multi-byte characters" do
+    char = [ 0x1d106 ].pack('U')
+    TestValidation.new.tweet_invalid?(char * 139).should == false
+    TestValidation.new.tweet_invalid?(char * 140).should == false
+    TestValidation.new.tweet_invalid?(char * 141).should == :too_long
+  end
+
+end

data/test/conformance_test.rb

@@ -0,0 +1,182 @@
+require 'multi_json'
+require 'nokogiri'
+require 'test/unit'
+require 'yaml'
+
+# Ruby 1.8 encoding check
+major, minor, patch = RUBY_VERSION.split('.')
+if major.to_i == 1 && minor.to_i < 9
+  $KCODE='u'
+end
+
+require File.expand_path('../../lib/twitter-text', __FILE__)
+
+class ConformanceTest < Test::Unit::TestCase
+  include Twitter::Extractor
+  include Twitter::Autolink
+  include Twitter::HitHighlighter
+  include Twitter::Validation
+
+  private
+
+  %w(description expected text json hits).each do |key|
+    define_method key.to_sym do
+      @test_info[key]
+    end
+  end
+
+  def assert_equal_without_attribute_order(expected, actual, failure_message = nil)
+    assert_block(build_message(failure_message, "<?> expected but was\n<?>", expected, actual)) do
+      equal_nodes?(Nokogiri::HTML(expected).root, Nokogiri::HTML(actual).root)
+    end
+  end
+
+  def equal_nodes?(expected, actual)
+    return false unless expected.name == actual.name
+    return false unless ordered_attributes(expected) == ordered_attributes(actual)
+    return false if expected.text? && actual.text? && expected.content != actual.content
+
+    expected.children.each_with_index do |child, index|
+      return false unless equal_nodes?(child, actual.children[index])
+    end
+
+    true
+  end
+
+  def ordered_attributes(element)
+    element.attribute_nodes.map{|attr| [attr.name, attr.value]}.sort
+  end
+
+  CONFORMANCE_DIR = ENV['CONFORMANCE_DIR'] || File.expand_path("../twitter-text-conformance", __FILE__)
+
+  def self.def_conformance_test(file, test_type, &block)
+    yaml = YAML.load_file(File.join(CONFORMANCE_DIR, file))
+    raise  "No such test suite: #{test_type.to_s}" unless yaml["tests"][test_type.to_s]
+
+    yaml["tests"][test_type.to_s].each do |test_info|
+      name = :"test_#{test_type}_#{test_info['description']}"
+      define_method name do
+        @test_info = test_info
+        instance_eval(&block)
+      end
+    end
+  end
+
+  public
+
+  # Extractor Conformance
+  def_conformance_test("extract.yml", :replies) do
+    assert_equal expected, extract_reply_screen_name(text), description
+  end
+
+  def_conformance_test("extract.yml", :mentions) do
+    assert_equal expected, extract_mentioned_screen_names(text), description
+  end
+
+  def_conformance_test("extract.yml", :mentions_with_indices) do
+    e = expected.map{|elem| elem.inject({}){|h, (k,v)| h[k.to_sym] = v; h} }
+    assert_equal e, extract_mentioned_screen_names_with_indices(text), description
+  end
+
+  def_conformance_test("extract.yml", :mentions_or_lists_with_indices) do
+    e = expected.map{|elem| elem.inject({}){|h, (k,v)| h[k.to_sym] = v; h} }
+    assert_equal e, extract_mentions_or_lists_with_indices(text), description
+  end
+
+  def_conformance_test("extract.yml", :urls) do
+    assert_equal expected, extract_urls(text), description
+    expected.each do |expected_url|
+      assert_equal true, valid_url?(expected_url, true, false), "expected url [#{expected_url}] not valid"
+    end
+  end
+
+  def_conformance_test("extract.yml", :urls_with_indices) do
+    e = expected.map{|elem| elem.inject({}){|h, (k,v)| h[k.to_sym] = v; h} }
+    assert_equal e, extract_urls_with_indices(text), description
+  end
+
+  def_conformance_test("extract.yml", :hashtags) do
+    assert_equal expected, extract_hashtags(text), description
+  end
+
+  def_conformance_test("extract.yml", :hashtags_with_indices) do
+    e = expected.map{|elem| elem.inject({}){|h, (k,v)| h[k.to_sym] = v; h} }
+    assert_equal e, extract_hashtags_with_indices(text), description
+  end
+
+  def_conformance_test("extract.yml", :cashtags) do
+    assert_equal expected, extract_cashtags(text), description
+  end
+
+  def_conformance_test("extract.yml", :cashtags_with_indices) do
+    e = expected.map{|elem| elem.inject({}){|h, (k,v)| h[k.to_sym] = v; h} }
+    assert_equal e, extract_cashtags_with_indices(text), description
+  end
+
+  # Autolink Conformance
+  def_conformance_test("autolink.yml", :usernames) do
+    assert_equal_without_attribute_order expected, auto_link_usernames_or_lists(text, :suppress_no_follow => true), description
+  end
+
+  def_conformance_test("autolink.yml", :lists) do
+    assert_equal_without_attribute_order expected, auto_link_usernames_or_lists(text, :suppress_no_follow => true), description
+  end
+
+  def_conformance_test("autolink.yml", :urls) do
+    assert_equal_without_attribute_order expected, auto_link_urls(text, :suppress_no_follow => true), description
+  end
+
+  def_conformance_test("autolink.yml", :hashtags) do
+    assert_equal_without_attribute_order expected, auto_link_hashtags(text, :suppress_no_follow => true), description
+  end
+
+  def_conformance_test("autolink.yml", :cashtags) do
+    assert_equal_without_attribute_order expected, auto_link_cashtags(text, :suppress_no_follow => true), description
+  end
+
+  def_conformance_test("autolink.yml", :all) do
+    assert_equal_without_attribute_order expected, auto_link(text, :suppress_no_follow => true), description
+  end
+
+  def_conformance_test("autolink.yml", :json) do
+    assert_equal_without_attribute_order expected, auto_link_with_json(text, MultiJson.load(json), :suppress_no_follow => true), description
+  end
+
+  # HitHighlighter Conformance
+  def_conformance_test("hit_highlighting.yml", :plain_text) do
+    assert_equal expected, hit_highlight(text, hits), description
+  end
+
+  def_conformance_test("hit_highlighting.yml", :with_links) do
+    assert_equal expected, hit_highlight(text, hits), description
+  end
+
+  # Validation Conformance
+  def_conformance_test("validate.yml", :tweets) do
+    assert_equal expected, valid_tweet_text?(text), description
+  end
+
+  def_conformance_test("validate.yml", :usernames) do
+    assert_equal expected, valid_username?(text), description
+  end
+
+  def_conformance_test("validate.yml", :lists) do
+    assert_equal expected, valid_list?(text), description
+  end
+
+  def_conformance_test("validate.yml", :urls) do
+    assert_equal expected, valid_url?(text), description
+  end
+
+  def_conformance_test("validate.yml", :urls_without_protocol) do
+    assert_equal expected, valid_url?(text, true, false), description
+  end
+
+  def_conformance_test("validate.yml", :hashtags) do
+    assert_equal expected, valid_hashtag?(text), description
+  end
+
+  def_conformance_test("validate.yml", :lengths) do
+    assert_equal expected, tweet_length(text), description
+  end
+end

data/twitter-text.gemspec

@@ -0,0 +1,29 @@
+# encoding: utf-8
+
+Gem::Specification.new do |s|
+  s.name = "ritter"
+  s.version = "0.0.88"
+  s.authors = ["Fernando Paladini", "Matt Sanford", "Patrick Ewing", "Ben Cherry", "Britt Selvitelle",
+               "Raffi Krikorian", "J.P. Cummins", "Yoshimasa Niwa", "Keita Fujii", "James Koval"]
+  s.email = ["fernando.paladini@techsempre.com","matt@twitter.com", "patrick.henry.ewing@gmail.com", "bcherry@gmail.com", "bs@brittspace.com",
+             "raffi@twitter.com", "jcummins@twitter.com", "niw@niw.at", "keita@twitter.com", "jkoval@twitter.com"]
+  s.homepage = "http://www.noise.com"
+  s.description = s.summary = "A edited gem that provides text handling for Twitter that parse any hashtag (except blank spaces)"
+
+  s.platform = Gem::Platform::RUBY
+  s.has_rdoc = true
+  s.summary = "Twitter text handling library"
+
+  s.add_development_dependency "multi_json", "~> 1.3"
+  s.add_development_dependency "nokogiri"
+  s.add_development_dependency "rake"
+  s.add_development_dependency "rdoc"
+  s.add_development_dependency "rspec"
+  s.add_development_dependency "simplecov"
+  s.add_runtime_dependency     "unf", "~> 0.1.0"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ritter
 version: !ruby/object:Gem::Version
-  version: 0.0.87
+  version: 0.0.88
 platform: ruby
 authors:
 - Fernando Paladini
@@ -17,7 +17,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-04-12 00:00:00.000000000 Z
+date: 2013-05-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: multi_json
@@ -109,15 +109,16 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 0.0.5
+        version: 0.1.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 0.0.5
-description: A gem that provides text handling
+        version: 0.1.0
+description: A edited gem that provides text handling for Twitter that parse any hashtag
+  (except blank spaces)
 email:
 - fernando.paladini@techsempre.com
 - matt@twitter.com
@@ -132,8 +133,41 @@ email:
 executables: []
 extensions: []
 extra_rdoc_files: []
-files: []
-homepage: http://instablah.herokuapp.com
+files:
+- .gemtest
+- .gitignore
+- .gitmodules
+- .rspec
+- .travis.yml
+- Gemfile
+- LICENSE
+- README.rdoc
+- Rakefile
+- lib/twitter-text.rb
+- lib/twitter-text/autolink.rb
+- lib/twitter-text/deprecation.rb
+- lib/twitter-text/extractor.rb
+- lib/twitter-text/hash_helper.rb
+- lib/twitter-text/hit_highlighter.rb
+- lib/twitter-text/regex.rb
+- lib/twitter-text/rewriter.rb
+- lib/twitter-text/unicode.rb
+- lib/twitter-text/validation.rb
+- script/destroy
+- script/generate
+- spec/autolinking_spec.rb
+- spec/extractor_spec.rb
+- spec/hithighlighter_spec.rb
+- spec/regex_spec.rb
+- spec/rewriter_spec.rb
+- spec/spec_helper.rb
+- spec/test_urls.rb
+- spec/twitter_text_spec.rb
+- spec/unicode_spec.rb
+- spec/validation_spec.rb
+- test/conformance_test.rb
+- twitter-text.gemspec
+homepage: http://www.noise.com
 licenses: []
 metadata: {}
 post_install_message: 
@@ -155,5 +189,5 @@ rubyforge_project:
 rubygems_version: 2.0.3
 signing_key: 
 specification_version: 4
-summary: Text handling library
+summary: Twitter text handling library
 test_files: []