tiny-safe-mod 0.0.1

data/stringex-2.8.6/test/unit/string_extensions_test.rb

@@ -0,0 +1,321 @@
+# encoding: utf-8
+
+require "test_helper"
+require "stringex"
+
+if RUBY_VERSION.to_f < 1.9
+  $KCODE = "U"
+end
+
+# Try loading RedCloth but it's okay if it's not there
+begin
+  gem 'RedCloth'
+rescue LoadError
+  puts
+  puts ">> Could not load RedCloth. String#to_html was not tested."
+  puts ">> Please gem install RedCloth if you'd like to use this functionality."
+  puts
+end
+
+class StringExtensionsTest < Test::Unit::TestCase
+  def setup
+    Stringex::Localization.reset!
+  end
+
+  def test_to_url
+    {
+      "<p>This has 100% too much    <em>formatting</em></p>" =>
+        "this-has-100-percent-too-much-formatting",
+      "Tea   &amp; crumpets &amp; <strong>cr&ecirc;pes</strong> for me!" =>
+        "tea-and-crumpets-and-crepes-for-me",
+      "The Suspense... Is... Killing Me" =>
+        "the-suspense-dot-dot-dot-is-dot-dot-dot-killing-me",
+      "How to use attr_accessible and attr_protected" =>
+        "how-to-use-attr-accessible-and-attr-protected",
+      "I'm just making sure there's nothing wrong with things!" =>
+        "im-just-making-sure-theres-nothing-wrong-with-things",
+      "foo = bar and bar=foo" =>
+        "foo-equals-bar-and-bar-equals-foo",
+      "Period.period" =>
+        "period-dot-period",
+      "Will…This Work?" =>
+        "will-dot-dot-dot-this-work",
+      "We check the D.N.A for matches" =>
+        "we-check-the-dna-for-matches",
+      "We check the D.N.A. for matches" =>
+        "we-check-the-dna-for-matches",
+      "Go to the Y.M.C.America" =>
+        "go-to-the-ymcamerica",
+      "He shops at J.C. Penney" =>
+        "he-shops-at-jc-penney",
+      "¼ pound with cheese" =>
+        "one-fourth-pound-with-cheese",
+      "Will's Ferrel" =>
+        "wills-ferrel",
+      "Капитал" =>
+        "kapital",
+      "Ελλάδα" =>
+        "ellada",
+      "中文" =>
+        "zhong-wen",
+      "Paul Cézanne" =>
+        "paul-cezanne",
+      "21'17ʼ51" =>
+        "21-17-51",
+      "ITCZ÷1 (21°17ʼ51.78”N / 89°35ʼ28.18”O / 26-04-08 / 09:00 am)" =>
+        "itcz-divided-by-1-21-degrees-17-51-dot-78-n-slash-89-degrees-35-28-dot-18-o-slash-26-04-08-slash-09-00-am",
+      "／" =>
+        "slash",
+      "私はガラスを食べられます。それは私を傷つけません。" =>
+        "si-hagarasuwoshi-beraremasu-sorehasi-woshang-tukemasen",
+      "ǝ is a magical string" =>
+        "at-is-a-magical-string",
+      "either | or" =>
+        "either-or",
+      "La Maison d`Uliva" =>
+        "la-maison-duliva",
+      "カッページ・テラスに日系カフェ＆バー、店内にDJブースも - シンガポール経済新聞" =>
+        "katupeziterasuniri-xi-kahue-and-ba-dian-nei-nidjbusumo-singaporujing-ji-xin-wen",
+      "AVアンプ、ホームシアターシステム、スピーカーシステム等" =>
+        "avanpu-homusiatasisutemu-supikasisutemudeng",
+      "У лукоморья дуб зеленый" =>
+        "u-lukomoria-dub-zielienyi",
+      "Here are some {braces}" =>
+        "here-are-some-braces",
+      "$1,000" =>
+        "1000-dollars",
+      "«zut alors»" =>
+        "zut-alors",
+      "Rabbits aren't real" =>
+        "rabbits-arent-real",
+      "R$ isn't R" =>
+        "reais-isnt-r",
+      "Last Friday Night (T.G.I.F.)" =>
+        "last-friday-night-tgif",
+      "foo` bar" =>
+        "foo-bar",
+      "foo~ bar" =>
+        "foo-bar"
+    }.each do |html, plain|
+      assert_equal plain, html.to_url
+    end
+  end
+
+  def test_to_url_with_danish_characters
+    Stringex::Localization.locale = :da
+    assert_equal "roedgroed-med-floede", "Rødgrød med fløde".to_url
+  end
+
+  def test_to_url_with_excludes
+    assert_equal "So Fucking Special", "So Fucking Special".to_url(:exclude => "So Fucking Special")
+  end
+
+  def test_to_url_without_forcing_downcase
+    assert_equal "I-have-CAPS", "I have CAPS".to_url(:force_downcase => false)
+  end
+
+  def test_to_url_with_limit
+    assert_equal "I am much too long".to_url(:limit => 13), "i-am-much-too"
+  end
+
+  def test_to_url_with_alternate_whitespace_replacement
+    assert_equal "under_scores", "Under Scores".to_url(:replace_whitespace_with => "_")
+  end
+
+  def test_to_url_with_alternate_whitespace_replacement_and_with_limit_and_with_truncate_words_disabled
+    assert_equal "i_am_much", "I am much too long".to_url(:replace_whitespace_with => "_", :limit => 12, :truncate_words => false)
+  end
+
+  def test_remove_formatting
+    {
+      "<p>This has 100% too much    <em>formatting</em></p>" =>
+        "This has 100 percent too much formatting",
+      "Tea   &amp; crumpets &amp; <strong>cr&ecirc;pes</strong> for me!" =>
+        "Tea and crumpets and crepes for me"
+    }.each do |html, plain|
+      assert_equal plain, html.remove_formatting
+    end
+  end
+
+  def test_strip_html_tags
+    {
+      "<h1><em>This</em> is good but <strong>that</strong> is better</h1>" =>
+        "This is good but that is better",
+      "<p>This is invalid XHTML but valid HTML, right?" =>
+        "This is invalid XHTML but valid HTML, right?",
+      "<p class='foo'>Everything goes!</p>" => "Everything goes!",
+      "<ol>This is completely invalid and just plain wrong</p>" =>
+        "This is completely invalid and just plain wrong"
+    }.each do |html, plain|
+      assert_equal plain, html.strip_html_tags
+    end
+  end
+
+  def test_convert_accented_html_entities
+    {
+      "&aring;"  => "a",
+      "&egrave;" => "e",
+      "&icirc;"  => "i",
+      "&Oslash;" => "O",
+      "&uuml;"   => "u",
+      "&Ntilde;" => "N",
+      "&ccedil;" => "c"
+    }.each do |entitied, plain|
+      assert_equal plain, entitied.convert_accented_html_entities
+    end
+  end
+
+  def test_localized_vulgar_fractions_conversion
+    Stringex::Localization.backend = :internal
+    Stringex::Localization.store_translations :da, :vulgar_fractions, {
+      :one_fourth => "en fjerdedel",
+      :half => "en halv"
+    }
+    Stringex::Localization.locale = :da
+
+    {
+      "&frac14;" => "en fjerdedel",
+      "½" => "en halv"
+    }.each do |entitied, plain|
+      assert_equal plain, entitied.convert_vulgar_fractions
+    end
+  end
+
+  def test_localized_html_entities_conversion
+    Stringex::Localization.backend = :internal
+    Stringex::Localization.store_translations :de, :html_entities, {
+      :amp => "und",
+      :ellipsis => " prik prik prik",
+      :frac14 => "en fjerdedel"
+    }
+    Stringex::Localization.locale = :de
+
+    {
+      "Tea &amp; Sympathy" => "Tea und Sympathy",
+      "To be continued&#8230;" => "To be continued prik prik prik",
+      "Det var til &frac14; af prisen" => "Det var til en fjerdedel af prisen"
+    }.each do |entitied, plain|
+      assert_equal plain, entitied.convert_miscellaneous_html_entities
+    end
+  end
+
+  def test_convert_smart_punctuation
+    {
+      "“smart quotes”" => '"smart quotes"',
+      "‘dumb quotes’" => "'dumb quotes'",
+      "I love you, but…" => "I love you, but...",
+    }.each do |smart, plain|
+      assert_equal plain, smart.convert_smart_punctuation
+    end
+  end
+
+  def test_localized_character_conversions
+    Stringex::Localization.backend = :internal
+    Stringex::Localization.store_translations :de, :characters, {
+      "and" => "und",
+      :percent => "procent"
+    }
+    Stringex::Localization.locale = :de
+
+    {
+      "ich & dich" => "ich und dich",
+      "det var 100% godt" => "det var 100 procent godt"
+    }.each do |misc, plain|
+      assert_equal plain, misc.convert_miscellaneous_characters
+    end
+  end
+
+  def test_replace_whitespace
+    {
+      "this has     too much space" => "this has too much space",
+      "\t\tThis is merely formatted with superfluous whitespace\n" =>
+        " This is merely formatted with superfluous whitespace "
+    }.each do |whitespaced, plain|
+      assert_equal plain, whitespaced.replace_whitespace
+    end
+
+    assert_equal "now-with-more-hyphens", "now with more hyphens".replace_whitespace("-")
+  end
+
+  def test_collapse
+    {
+      "too      much space" => "too much space",
+      "  at the beginning" => "at the beginning"
+    }.each do |uncollapsed, plain|
+      assert_equal plain, uncollapsed.collapse
+    end
+
+    assert_equal "now-with-hyphens", "----now---------with-hyphens--------".collapse("-")
+  end
+
+  def test_empty_translations
+    Stringex::Localization.backend = :internal
+    Stringex::Localization.store_translations :de, :characters, {
+      :star => "",
+      :percent => "prozent"
+    }
+    Stringex::Localization.locale = :de
+
+    assert_equal "foobar ist 100 prozent gut", "foo*bar ist 100% gut".convert_miscellaneous_characters
+  end
+
+  def test_overriding_to_ascii_allows_utf8_urls
+    String.class_eval do
+      alias :old_to_ascii :to_ascii
+
+      def to_ascii
+        self
+      end
+    end
+
+    {
+      "مصدر أمني: مجهولون يطلقون «خرطوش» على متظاهرين بمترو عزبة النخل وإصابة 16" =>
+        "مصدر-أمني-مجهولون-يطلقون-«خرطوش»-على-متظاهرين-بمترو-عزبة-النخل-وإصابة-16",
+      "c'est ça" =>
+        "cest-ça",
+      "la muñeca" =>
+        "la-muñeca"
+    }.each do |original, converted|
+      assert_equal converted, original.to_url
+    end
+  ensure
+    String.class_eval do
+      remove_method :to_ascii
+
+      def to_ascii
+        old_to_ascii
+      end
+    end
+  end
+
+  def test_remove_nonreadable_characters
+    cases = { "Jörg Immendor\u0014. Les théâtres" => "jorg-immendor-les-theatres",
+            }
+    cases.each do |plain, converted|
+      assert_equal converted, plain.to_url
+    end
+  end
+
+  if defined?(RedCloth)
+    def test_to_html
+      {
+        "h1. A Solution" => "<h1>A Solution</h1>",
+        "I hated wrapping textilize around a string.\n\nIt always felt dirty." =>
+          "<p>I hated wrapping textilize around a string.</p>\n<p>It always felt dirty.</p>",
+        "I think _this_ is awesome" => "<p>I think <em>this</em> is awesome</p>",
+        "Um... _*really*_, man" => "<p>Um&#8230; <em><strong>really</strong></em>, man</p>"
+      }.each do |plain, html|
+        assert_equal html, plain.to_html
+      end
+    end
+
+    def test_to_html_lite
+      {
+        "I have no pee on me" => "I have no pee on me",
+        "But I _do_ get Textile!" => "But I <em>do</em> get Textile!"
+      }.each do |plain, html|
+        assert_equal html, plain.to_html(:lite)
+      end
+    end
+  end
+end

data/stringex-2.8.6/test/unit/unicode_point_suite/basic_greek_test.rb

@@ -0,0 +1,113 @@
+# encoding: UTF-8
+
+require "test/unit"
+require "stringex"
+require File.join(File.expand_path(File.dirname(__FILE__)), "codepoint_test_helper.rb")
+include CodepointTestHelper
+
+class BasicGreekTest < Test::Unit::TestCase
+  # This test suite is just regression test and debugging
+  # to better transliterate the Basic Latin Unicode codepoints
+  #
+  # http://unicode.org/charts/
+  # http://unicode.org/charts/PDF/U0000.pdf
+
+  # NOTE: I can't figure out how to test control characters.
+  # Get weird results trying to pack them to unicode.
+
+  def test_greek_letters
+    {
+      "Α" => "A",
+      "Ά" => "A",
+      "Β" => "B",
+      "Γ" => "G",
+      "Δ" => "D",
+      "Ε" => "E",
+      "Έ" => "E",
+      "Ζ" => "Z",
+      "Η" => "H",
+      "Θ" => "Th",
+      "Ι" => "I",
+      "Ί" => "I",
+      "Ϊ" => "I",
+      "Κ" => "K",
+      "Λ" => "L",
+      "Μ" => "M",
+      "Ν" => "N",
+      "Ξ" => "Ks",
+      "Ο" => "O",
+      "Ό" => "O",
+      "Π" => "P",
+      "Ρ" => "R",
+      "Σ" => "S",
+      "Τ" => "T",
+      "Υ" => "Y",
+      "Ϋ" => "Y",
+      "Ύ" => "Y",
+      "Φ" => "Ph",
+      "Χ" => "X",
+      "Ψ" => "Ps",
+      "Ω" => "O",
+      "Ώ" => "O",
+      "α" => "a",
+      "ά" => "a",
+      "β" => "b",
+      "γ" => "g",
+      "δ" => "d",
+      "ε" => "e",
+      "έ" => "e",
+      "ζ" => "z",
+      "η" => "i",
+      "ή" => "i",
+      "θ" => "th",
+      "ι" => "i",
+      "ί" => "i",
+      "ϊ" => "i",
+      "ΐ" => "i",
+      "κ" => "k",
+      "λ" => "l",
+      "μ" => "m",
+      "ν" => "n",
+      "ξ" => "ks",
+      "ο" => "o",
+      "ό" => "o",
+      "π" => "p",
+      "ρ" => "r",
+      "σ" => "s",
+      "ς" => "s",
+      "τ" => "t",
+      "υ" => "u",
+      "ύ" => "u",
+      "ϋ" => "u",
+      "ΰ" => "u",
+      "φ" => "ph",
+      "χ" => "x",
+      "ψ" => "ps",
+      "ω" => "o",
+      "ώ" => "o"
+    }.each do |letter, ascii|
+      assert_equal letter.to_ascii, ascii
+    end
+  end
+
+
+  def test_greek_words
+    {
+      "Καλημέρα" => "Kalimera",
+      "Προϊόν" => "Proion",
+      "Θαλασσογραφία" => "Thalassographia",
+      "Να μας πάρεις μακριά" => "Na mas pareis makria",
+      "να μας πας στα πέρα μέρη" => "na mas pas sta pera meri",
+      "φύσα θάλασσα πλατιά" => "phusa thalassa platia",
+      "φύσα αγέρι φύσα αγέρι" => "phusa ageri phusa ageri",
+      "Αν θέλεις να λέγεσαι άνθρωπος" => "An theleis na legesai anthropos",
+      "δεν θα πάψεις ούτε στιγμή ν΄αγωνίζεσαι για την ειρήνη και" => "den tha papseis oute stigmi nagonizesai gia tin eirini kai",
+      "για το δίκαιο." => "gia to dikaio.",
+      "Θα βγείς στους δρόμους, θα φωνάξεις, τα χείλια σου θα" => "Tha bgeis stous dromous, tha phonakseis, ta xeilia sou tha",
+      "ματώσουν απ΄τις φωνές" => "matosoun aptis phones",
+      "το πρόσωπό σου θα ματώσει από τις σφαίρες – μα ούτε βήμα πίσω." => "to prosopo sou tha matosei apo tis sphaires -- ma oute bima piso.",
+    }.each do |letter, ascii|
+      assert_equal letter.to_ascii, ascii
+    end
+  end
+end

data/stringex-2.8.6/test/unit/unicode_point_suite/basic_latin_test.rb

@@ -0,0 +1,144 @@
+# encoding: UTF-8
+
+require "test/unit"
+require "stringex"
+require File.join(File.expand_path(File.dirname(__FILE__)), "codepoint_test_helper.rb")
+include CodepointTestHelper
+
+class BasicLatinTest < Test::Unit::TestCase
+  # This test suite is just regression test and debugging
+  # to better transliterate the Basic Latin Unicode codepoints
+  #
+  # http://unicode.org/charts/
+  # http://unicode.org/charts/PDF/U0000.pdf
+
+  # NOTE: I can't figure out how to test control characters.
+  # Get weird results trying to pack them to unicode.
+
+  def test_spaces
+    assert_equal_encoded " ", %w{0020 00a0}
+    assert_equal_encoded "",  %w{200b 2060}
+  end
+
+  def test_exclamation_marks
+    assert_equal_encoded "!", %w{0021 2762}
+    assert_equal_encoded "!!", "203c"
+    assert_equal_encoded "", "00a1"
+    assert_equal_encoded "?!", "203d"
+  end
+
+  def test_quotation_marks
+    assert_equal_encoded "\"", %w{0022 02ba 2033 3003}
+  end
+
+  def test_apostrophes
+    assert_equal_encoded "'", %w{0027 02b9 02bc 02c8 2032}
+  end
+
+  def test_asterisks
+    assert_equal_encoded "*", %w{002a 066d 204e 2217 26b9 2731}
+  end
+
+  def test_commas
+    assert_equal_encoded ",", %w{002c 060c}
+  end
+
+  def test_periods
+    assert_equal_encoded ".", %w{002e 06d4}
+  end
+
+  def test_hyphens
+    assert_equal_encoded "-", %w{002d 2010 2011 2012 2212}
+  end
+
+  def test_endash
+    assert_equal_encoded "--", %w{2013 2015}
+  end
+
+  def test_emdash
+    assert_equal_encoded "---", %w{2014}
+  end
+
+  def test_dotleader
+    assert_equal_encoded "..", %w{2025}
+  end
+
+  def test_ellipsis
+    assert_equal_encoded "...", %w{2026}
+  end
+
+  def test_slashes
+    assert_equal_encoded "/", %w{002f 2044 2215}
+    assert_equal_encoded "\\", %w{005c 2216}
+  end
+
+  def test_colons
+    assert_equal_encoded ":", %w{003a 2236}
+  end
+
+  def test_semicolons
+    assert_equal_encoded ";", %w{003b 061b}
+  end
+
+  def test_less_thans
+    assert_equal_encoded "<", %w{003c 2039 2329 27e8 3008}
+  end
+
+  def test_equals
+    assert_equal_encoded "=", "003d"
+  end
+
+  def test_greater_thans
+    assert_equal_encoded ">", %w{003e 203a 232a 27e9 3009}
+  end
+
+  def test_question_marks
+    assert_equal_encoded "?", %w{003f 061f}
+    assert_equal_encoded "", "00bf"
+    assert_equal_encoded "?!", %w{203d 2048}
+    assert_equal_encoded "!?", "2049"
+  end
+
+  def test_circumflexes
+    assert_equal_encoded "^", %w{005e 2038 2303}
+  end
+
+  def test_underscores
+    assert_equal_encoded "_", %w{005f 02cd 2017}
+  end
+
+  def test_grave_accents
+    assert_equal_encoded "'", %w{02cb 2035}
+    # Ascii grave accent should remain as ascii!
+    assert_equal_encoded "`", "0060"
+  end
+
+  def test_bars
+    assert_equal_encoded "|", %w{007c 2223 2758}
+  end
+
+  def test_tildes
+    assert_equal_encoded "~", %w{007e 02dc 2053 223c ff5e}
+  end
+
+  def test_related_letters
+    {
+      "B" => "212c",
+      "C" => %w{2102 212d},
+      "E" => %w{2107 2130},
+      "F" => "2131",
+      "H" => %w{210b 210c 210d},
+      "I" => %w{0130 0406 04c0 2110 2111 2160},
+      "K" => "212a",
+      "L" => "2112",
+      "M" => "2133",
+      "N" => "2115",
+      "P" => "2119",
+      "Q" => "211a",
+      "R" => %w{211b 211c 211d},
+      "Z" => %w{2124 2128}
+    }.each do |expected, encode_mes|
+      assert_equal_encoded expected, encode_mes
+    end
+  end
+end

data/stringex-2.8.6/test/unit/unicode_point_suite/codepoint_test_helper.rb

@@ -0,0 +1,32 @@
+# encoding: UTF-8
+
+# 100% shorthand
+module CodepointTestHelper
+  def assert_equal_encoded(expected, encode_mes)
+    # Killing a duck because Ruby 1.9 doesn't mix Enumerable into String
+    encode_mes = [encode_mes] if encode_mes.is_a?(String)
+    encode_mes.each do |encode_me|
+      encoded = encode(encode_me)
+      actual = encoded.to_ascii
+      if expected == actual
+        # Let's not retest it
+        assert true
+      else
+        message = "<#{expected.inspect}> expected but was\n<#{actual.inspect}>\n"
+        message << "  defined in #{Stringex::Unidecoder.in_yaml_file(encoded)}"
+        reporting_class = defined?(Test::Unit::AssertionFailedError) ?
+           Test::Unit::AssertionFailedError : ActiveSupport::TestCase::Assertion
+        raise reporting_class.new(message)
+      end
+    end
+  end
+
+private
+  def encode(codepoint)
+    Stringex::Unidecoder.encode(codepoint)
+  end
+
+  def which_yaml(codepoint)
+    Stringex::Unidecoder.in_yaml_file(encode(codepoint))
+  end
+end

data/stringex-2.8.6/test/unit/unidecoder/bad_localization.yml

@@ -0,0 +1 @@
+Anything not correct

data/stringex-2.8.6/test/unit/unidecoder/localization.yml

@@ -0,0 +1,4 @@
+en:
+  é: ee
+xx:
+  é: xx