summaryrefslogtreecommitdiff
path: root/test/test_unicode_normalize.rb
diff options
context:
space:
mode:
authorduerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2014-10-22 09:06:49 +0000
committerduerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2014-10-22 09:06:49 +0000
commit30b837b47c034ac01256936f8c09a49bba38e979 (patch)
tree58e5bb8c1007d3a022077c6f61f3d061f70f3db4 /test/test_unicode_normalize.rb
parent15bfe2793a849f500a15ae54553f4ffba5d55b41 (diff)
test/test-unicode_normalize.rb: Removed explicit require, changed method names, adjusted copyright.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@48085 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'test/test_unicode_normalize.rb')
-rw-r--r--test/test_unicode_normalize.rb35
1 files changed, 16 insertions, 19 deletions
diff --git a/test/test_unicode_normalize.rb b/test/test_unicode_normalize.rb
index 82c7fffbe1..690d5cb5b3 100644
--- a/test/test_unicode_normalize.rb
+++ b/test/test_unicode_normalize.rb
@@ -1,12 +1,9 @@
# coding: utf-8
-# Copyright 2010-2013 Ayumu Nojima (野島 歩) and Martin J. Dürst (duerst@it.aoyama.ac.jp)
-# available under the same licence as Ruby itself
-# (see http://www.ruby-lang.org/en/LICENSE.txt)
+# Copyright Ayumu Nojima (野島 歩) and Martin J. Dürst (duerst@it.aoyama.ac.jp)
Encoding.default_external = 'utf-8'
Encoding.default_internal = 'utf-8'
-require '../lib/string_normalize'
require 'test/unit'
NormTest = Struct.new :source, :NFC, :NFD, :NFKC, :NFKD, :line
@@ -25,7 +22,7 @@ class TestNormalize < Test::Unit::TestCase
end
end
- def to_codepoints(string) # this could be defined as a refinement on String
+ def to_codepoints(string)
string.codepoints.collect { |cp| cp.to_s(16).upcase.rjust(4, '0') }
end
@@ -38,7 +35,7 @@ class TestNormalize < Test::Unit::TestCase
@@tests.each do |test|
if not prechecked or test[source]==test[prechecked]
expected = test[target]
- actual = test[source].normalize(normalization)
+ actual = test[source].unicode_normalize(normalization)
if @@debug
assert_equal expected, actual,
"#{to_codepoints(expected)} expected but was #{to_codepoints(actual)} on line #{test[:line]} (#{normalization})"
@@ -88,7 +85,7 @@ class TestNormalize < Test::Unit::TestCase
def self.generate_test_check_true(source, normalization)
define_method "test_check_true_#{source}_as_#{normalization}" do
@@tests.each do |test|
- actual = test[source].normalized?(normalization)
+ actual = test[source].unicode_normalized?(normalization)
if @@debug
assert_equal true, actual,
"#{to_codepoints(test[source])} should check as #{normalization} but does not on line #{test[:line]}"
@@ -101,7 +98,7 @@ class TestNormalize < Test::Unit::TestCase
def one_false_check_test(test, compare_column, check_column, test_form, line)
if test[check_column- 1] != test[compare_column- 1]
- actual = test[check_column- 1].normalized?(test_form)
+ actual = test[check_column- 1].unicode_normalized?(test_form)
assert_equal false, actual, "failed on line #{line+1} (#{test_form})"
end
end
@@ -110,7 +107,7 @@ class TestNormalize < Test::Unit::TestCase
define_method "test_check_false_#{source}_as_#{normalization}" do
@@tests.each do |test|
if test[source] != test[compare]
- actual = test[source].normalized?(normalization)
+ actual = test[source].unicode_normalized?(normalization)
if @@debug
assert_equal false, actual,
"#{to_codepoints(test[source])} should not check as #{normalization} but does on line #{test[:line]}"
@@ -145,27 +142,27 @@ class TestNormalize < Test::Unit::TestCase
generate_test_check_false :NFKD, :NFKC, :nfkc
def test_non_UTF_8
- assert_equal "\u1E0A".encode('UTF-16BE'), "D\u0307".encode('UTF-16BE').normalize(:nfc)
- assert_equal true, "\u1E0A".encode('UTF-16BE').normalized?(:nfc)
- assert_equal false, "D\u0307".encode('UTF-16BE').normalized?(:nfc)
+ assert_equal "\u1E0A".encode('UTF-16BE'), "D\u0307".encode('UTF-16BE').unicode_normalize(:nfc)
+ assert_equal true, "\u1E0A".encode('UTF-16BE').unicode_normalized?(:nfc)
+ assert_equal false, "D\u0307".encode('UTF-16BE').unicode_normalized?(:nfc)
end
def test_singleton_with_accents
- assert_equal "\u0136", "\u212A\u0327".normalize(:nfc)
+ assert_equal "\u0136", "\u212A\u0327".unicode_normalize(:nfc)
end
def test_partial_jamo_compose
- assert_equal "\uAC01", "\uAC00\u11A8".normalize(:nfc)
+ assert_equal "\uAC01", "\uAC00\u11A8".unicode_normalize(:nfc)
end
def test_partial_jamo_decompose
- assert_equal "\u1100\u1161\u11A8", "\uAC00\u11A8".normalize(:nfd)
+ assert_equal "\u1100\u1161\u11A8", "\uAC00\u11A8".unicode_normalize(:nfd)
end
def test_hangul_plus_accents
- assert_equal "\uAC00\u0323\u0300", "\uAC00\u0300\u0323".normalize(:nfc)
- assert_equal "\uAC00\u0323\u0300", "\u1100\u1161\u0300\u0323".normalize(:nfc)
- assert_equal "\u1100\u1161\u0323\u0300", "\uAC00\u0300\u0323".normalize(:nfd)
- assert_equal "\u1100\u1161\u0323\u0300", "\u1100\u1161\u0300\u0323".normalize(:nfd)
+ assert_equal "\uAC00\u0323\u0300", "\uAC00\u0300\u0323".unicode_normalize(:nfc)
+ assert_equal "\uAC00\u0323\u0300", "\u1100\u1161\u0300\u0323".unicode_normalize(:nfc)
+ assert_equal "\u1100\u1161\u0323\u0300", "\uAC00\u0300\u0323".unicode_normalize(:nfd)
+ assert_equal "\u1100\u1161\u0323\u0300", "\u1100\u1161\u0300\u0323".unicode_normalize(:nfd)
end
end