diff options
| author | nagachika <nagachika@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2019-08-11 12:17:58 +0000 |
|---|---|---|
| committer | nagachika <nagachika@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2019-08-11 12:17:58 +0000 |
| commit | ad6ffac7d6121c193b95c15bc011c9969967f554 (patch) | |
| tree | 6ddd90a00ed0921a1201ca35767a1554c8eafe25 /test | |
| parent | e68627da985d118be573cd9f7e30617cb2bd76fc (diff) | |
merge revision(s) 8aecc90974ab1ac87056f77e2cb3406c5c041504,2f6cc15cdb3d64135b29cfd5ee376a5a03ebbee7: [Backport #15965]
Hoisted out WIDE_ENCODINGS
Fixed String#grapheme_clusters with wide encodings
* string.c (get_reg_grapheme_cluster): make regexp from properly
encoded sources fro wide-char encodings. [Bug #15965]
* regparse.c (node_extended_grapheme_cluster): suppress false
duplicated range warning for the time being.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/branches/ruby_2_6@67741 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'test')
| -rw-r--r-- | test/ruby/test_string.rb | 31 |
1 files changed, 19 insertions, 12 deletions
diff --git a/test/ruby/test_string.rb b/test/ruby/test_string.rb index 55dcfb5f35..aad4277d5f 100644 --- a/test/ruby/test_string.rb +++ b/test/ruby/test_string.rb @@ -4,6 +4,11 @@ require 'test/unit' class TestString < Test::Unit::TestCase ENUMERATOR_WANTARRAY = RUBY_VERSION >= "3.0.0" + WIDE_ENCODINGS = [ + Encoding::UTF_16BE, Encoding::UTF_16LE, + Encoding::UTF_32BE, Encoding::UTF_32LE, + ] + def initialize(*args) @cls = String @aref_re_nth = true @@ -667,8 +672,7 @@ CODE assert_raise(ArgumentError) {S("mypassword").crypt(S("\0a"))} assert_raise(ArgumentError) {S("mypassword").crypt(S("a\0"))} assert_raise(ArgumentError) {S("poison\u0000null").crypt(S("aa"))} - [Encoding::UTF_16BE, Encoding::UTF_16LE, - Encoding::UTF_32BE, Encoding::UTF_32LE].each do |enc| + WIDE_ENCODINGS.each do |enc| assert_raise(ArgumentError) {S("mypassword").crypt(S("aa".encode(enc)))} assert_raise(ArgumentError) {S("mypassword".encode(enc)).crypt(S("aa"))} end @@ -1032,13 +1036,20 @@ CODE "\u{1F468 200D 1F393}", "\u{1F46F 200D 2642 FE0F}", "\u{1f469 200d 2764 fe0f 200d 1f469}", - ].each do |g| + ].product([Encoding::UTF_8, *WIDE_ENCODINGS]) do |g, enc| + g = g.encode(enc) assert_equal [g], g.grapheme_clusters - assert_predicate g.dup.taint.grapheme_clusters[0], :tainted? + assert_predicate g.taint.grapheme_clusters[0], :tainted? end - assert_equal ["\u000A", "\u0324"], "\u{a 324}".grapheme_clusters - assert_equal ["\u000D", "\u0324"], "\u{d 324}".grapheme_clusters + [ + "\u{a 324}", + "\u{d 324}", + "abc", + ].product([Encoding::UTF_8, *WIDE_ENCODINGS]) do |g, enc| + g = g.encode(enc) + assert_equal g.chars, g.grapheme_clusters + end assert_equal ["a", "b", "c"], "abc".b.grapheme_clusters if ENUMERATOR_WANTARRAY @@ -1805,10 +1816,7 @@ CODE def test_split_wchar bug8642 = '[ruby-core:56036] [Bug #8642]' - [ - Encoding::UTF_16BE, Encoding::UTF_16LE, - Encoding::UTF_32BE, Encoding::UTF_32LE, - ].each do |enc| + WIDE_ENCODINGS.each do |enc| s = S("abc,def".encode(enc)) assert_equal(["abc", "def"].map {|c| c.encode(enc)}, s.split(",".encode(enc)), @@ -3018,8 +3026,7 @@ CODE def test_ascii_incomat_inspect bug4081 = '[ruby-core:33283]' - [Encoding::UTF_16LE, Encoding::UTF_16BE, - Encoding::UTF_32LE, Encoding::UTF_32BE].each do |e| + WIDE_ENCODINGS.each do |e| assert_equal('"abc"', "abc".encode(e).inspect) assert_equal('"\\u3042\\u3044\\u3046"', "\u3042\u3044\u3046".encode(e).inspect) assert_equal('"ab\\"c"', "ab\"c".encode(e).inspect, bug4081) |