archive/ruby
1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2025-09-15 16:44:01 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

* test/test_unicode_normalize.rb: Add test to check for availability of

Browse source 
Unicode data file; refactoring; fix an error with tests for destructive
  method (unicode_normalize!).


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55196 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
duerst 2016-05-28 11:34:20 +00:00
parent 7a622b18d9
commit 3883bb6bae
2 changed files with 21 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ChangeLog
View file

@ -1,3 +1,9 @@
Sat May 28 20:34:19 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
* test/test_unicode_normalize.rb: Add test to check for availability of
Unicode data file; refactoring; fix an error with tests for destructive
method (unicode_normalize!).
Sat May 28 19:08:36 2016 Martin Duerst <duerst@it.aoyama.ac.jp> Sat May 28 19:08:36 2016 Martin Duerst <duerst@it.aoyama.ac.jp>
* test/ruby/enc/test_case_comprehensive.rb: Add error messages to tests * test/ruby/enc/test_case_comprehensive.rb: Add error messages to tests

21
test/test_unicode_normalize.rb
View file

@ -9,11 +9,16 @@ require 'unicode_normalize/normalize'
class TestUnicodeNormalize < Test::Unit::TestCase class TestUnicodeNormalize < Test::Unit::TestCase
UNICODE_VERSION = UnicodeNormalize::UNICODE_VERSION UNICODE_VERSION = UnicodeNormalize::UNICODE_VERSION
UNICODE_DATA_PATH = "../enc/unicode/data/#{UNICODE_VERSION}"
def expand_filename(basename)
File.expand_path("#{UNICODE_DATA_PATH}/#{basename}.txt", __dir__)
end
NormTest = Struct.new :source, :NFC, :NFD, :NFKC, :NFKD, :line NormTest = Struct.new :source, :NFC, :NFD, :NFKC, :NFKD, :line
def read_tests def read_tests
IO.readlines(File.expand_path("../enc/unicode/data/#{UNICODE_VERSION}/NormalizationTest.txt", __dir__), encoding: 'utf-8') IO.readlines(expand_filename('NormalizationTest'), encoding: 'utf-8')
.tap { |lines| assert_include(lines[0], "NormalizationTest-#{UNICODE_VERSION}.txt")} .tap { |lines| assert_include(lines[0], "NormalizationTest-#{UNICODE_VERSION}.txt")}
.collect.with_index { |linedata, linenumber| [linedata, linenumber]} .collect.with_index { |linedata, linenumber| [linedata, linenumber]}
.reject { |line| line[0] =~ /^[\#@]/ } .reject { |line| line[0] =~ /^[\#@]/ }
@ -32,7 +37,6 @@ class TestUnicodeNormalize < Test::Unit::TestCase
@@tests ||= read_tests @@tests ||= read_tests
rescue Errno::ENOENT => e rescue Errno::ENOENT => e
@@tests ||= [] @@tests ||= []
skip e.message
end end
def self.generate_test_normalize(target, normalization, source, prechecked) def self.generate_test_normalize(target, normalization, source, prechecked)
@ -133,6 +137,11 @@ class TestUnicodeNormalize < Test::Unit::TestCase
generate_test_check_false :NFD, :NFKC, :nfkc generate_test_check_false :NFD, :NFKC, :nfkc
generate_test_check_false :NFKD, :NFKC, :nfkc generate_test_check_false :NFKD, :NFKC, :nfkc
def test_AAAAA_data_file_available # AAAAA makes sure this test is run first
expanded = expand_filename 'NormalizationTest'
assert File.exist?(expanded), "File #{expanded} missing."
end
def test_non_UTF_8 def test_non_UTF_8
assert_equal "\u1E0A".encode('UTF-16BE'), "D\u0307".encode('UTF-16BE').unicode_normalize(: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 true, "\u1E0A".encode('UTF-16BE').unicode_normalized?(:nfc)
@ -172,10 +181,10 @@ class TestUnicodeNormalize < Test::Unit::TestCase
assert_equal ascii_string, ascii_string.unicode_normalize(:nfkc) assert_equal ascii_string, ascii_string.unicode_normalize(:nfkc)
assert_equal ascii_string, ascii_string.unicode_normalize(:nfkd) assert_equal ascii_string, ascii_string.unicode_normalize(:nfkd)
assert_equal ascii_string, ascii_string.unicode_normalize! assert_equal ascii_string, ascii_string.dup.unicode_normalize!
assert_equal ascii_string, ascii_string.unicode_normalize!(:nfd) assert_equal ascii_string, ascii_string.dup.unicode_normalize!(:nfd)
assert_equal ascii_string, ascii_string.unicode_normalize!(:nfkc) assert_equal ascii_string, ascii_string.dup.unicode_normalize!(:nfkc)
assert_equal ascii_string, ascii_string.unicode_normalize!(:nfkd) assert_equal ascii_string, ascii_string.dup.unicode_normalize!(:nfkd)
assert_equal true, ascii_string.unicode_normalized? assert_equal true, ascii_string.unicode_normalized?
assert_equal true, ascii_string.unicode_normalized?(:nfd) assert_equal true, ascii_string.unicode_normalized?(:nfd)