1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
ruby--ruby/test/ruby/enc/test_iso_8859.rb
duerst 0e29256175 * test/ruby/enc/test_iso_8859.rb: Excluded dotless i/I with dot from
case-insensitive matching because they are not a case pair.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55647 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2016-07-12 23:40:26 +00:00

166 lines
5 KiB
Ruby
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# frozen_string_literal: false
require 'test/unit'
class TestISO8859 < Test::Unit::TestCase
ASSERTS = %q(
assert_match(/^(\xdf)\1$/i, "\xdf\xdf")
assert_match(/^(\xdf)\1$/i, "ssss")
# assert_match(/^(\xdf)\1$/i, "\xdfss") # this must be bug...
assert_match(/^[\xdfz]+$/i, "sszzsszz")
assert_match(/^SS$/i, "\xdf")
assert_match(/^Ss$/i, "\xdf")
((0xc0..0xde).to_a - [0xd7]).each do |c|
c1 = c.chr("ENCODING")
c2 = (c + 0x20).chr("ENCODING")
assert_match(/^(#{ c1 })\1$/i, c2 + c1)
assert_match(/^(#{ c2 })\1$/i, c1 + c2)
assert_match(/^[#{ c1 }]+$/i, c2 + c1)
assert_match(/^[#{ c2 }]+$/i, c1 + c2)
end
assert_match(/^\xff$/i, "\xff")
)
def test_iso_8859_1
eval("# encoding: iso8859-1\n" + ASSERTS.gsub(/ENCODING/m, "iso8859-1"))
end
def test_iso_8859_2
eval("# encoding: iso8859-2\n" + ASSERTS.gsub(/ENCODING/m, "iso8859-2"))
end
def test_iso_8859_3
# todo: decide on behavior, test, and fix implementation re. İ and ı (0xA9/0xB9)
# treating them as case equivalents is definitely an error
eval(%q(# encoding: iso8859-3
assert_match(/^(\xdf)\1$/i, "\xdf\xdf")
assert_match(/^(\xdf)\1$/i, "ssss")
assert_match(/^[\xdfz]+$/i, "sszzsszz")
assert_match(/^SS$/i, "\xdf")
assert_match(/^Ss$/i, "\xdf")
[0xa1, 0xa6, *(0xaa..0xac), 0xaf].each do |c|
c1 = c.chr("iso8859-3")
c2 = (c + 0x10).chr("iso8859-3")
assert_match(/^(#{ c1 })\1$/i, c2 + c1)
assert_match(/^(#{ c2 })\1$/i, c1 + c2)
assert_match(/^[#{ c1 }]+$/i, c2 + c1)
assert_match(/^[#{ c2 }]+$/i, c1 + c2)
end
([*(0xc0..0xde)] - [0xc3, 0xd0, 0xd7]).each do |c|
c1 = c.chr("iso8859-3")
c2 = (c + 0x20).chr("iso8859-3")
assert_match(/^(#{ c1 })\1$/i, c2 + c1)
assert_match(/^(#{ c2 })\1$/i, c1 + c2)
assert_match(/^[#{ c1 }]+$/i, c2 + c1)
assert_match(/^[#{ c2 }]+$/i, c1 + c2)
end
))
end
def test_iso_8859_4
eval("# encoding: iso8859-4\n" + ASSERTS.gsub(/ENCODING/m, "iso8859-4"))
end
def test_iso_8859_5
eval(%q(# encoding: iso8859-5
(0xb0..0xcf).each do |c|
c1 = c.chr("iso8859-5")
c2 = (c + 0x20).chr("iso8859-5")
assert_match(/^(#{ c1 })\1$/i, c2 + c1)
assert_match(/^(#{ c2 })\1$/i, c1 + c2)
assert_match(/^[#{ c1 }]+$/i, c2 + c1)
assert_match(/^[#{ c2 }]+$/i, c1 + c2)
end
((0xa1..0xaf).to_a - [0xad]).each do |c|
c1 = c.chr("iso8859-5")
c2 = (c + 0x50).chr("iso8859-5")
assert_match(/^(#{ c1 })\1$/i, c2 + c1)
assert_match(/^(#{ c2 })\1$/i, c1 + c2)
assert_match(/^[#{ c1 }]+$/i, c2 + c1)
assert_match(/^[#{ c2 }]+$/i, c1 + c2)
end
))
end
def test_iso_8859_6
eval(%q(# encoding: iso8859-6
[0xa4, 0xac, 0xbb, 0xbf, *(0xc1..0xda), *(0xe0..0xf2)].each do |c|
c1 = c.chr("iso8859-6")
assert_match(/^(#{ c1 })\1$/i, c1 * 2)
end
))
end
def test_iso_8859_7
eval(%q(# encoding: iso8859-7
((0xa0..0xfe).to_a - [0xae, 0xd2]).each do |c|
c1 = c.chr("iso8859-7")
assert_match(/^(#{ c1 })\1$/i, c1 * 2)
end
((0xc1..0xd9).to_a - [0xd2]).each do |c|
c1 = c.chr("iso8859-7")
c2 = (c + 0x20).chr("iso8859-7")
assert_match(/^(#{ c1 })\1$/i, c2 + c1)
assert_match(/^(#{ c2 })\1$/i, c1 + c2)
assert_match(/^[#{ c1 }]+$/i, c2 + c1)
assert_match(/^[#{ c2 }]+$/i, c1 + c2)
end
))
end
def test_iso_8859_8
eval(%q(# encoding: iso8859-8
[0xa0, *(0xa2..0xbe), *(0xdf..0xfa), 0xfc, 0xfd].each do |c|
c1 = c.chr("iso8859-8")
assert_match(/^(#{ c1 })\1$/i, c1 * 2)
end
))
end
def test_iso_8859_9
eval(%q(# encoding: iso8859-9
assert_match(/^(\xdf)\1$/i, "\xdf\xdf")
assert_match(/^(\xdf)\1$/i, "ssss")
assert_match(/^[\xdfz]+$/i, "sszzsszz")
assert_match(/^SS$/i, "\xdf")
assert_match(/^Ss$/i, "\xdf")
([*(0xc0..0xdc)] - [0xd7]).each do |c|
c1 = c.chr("iso8859-9")
c2 = (c + 0x20).chr("iso8859-9")
assert_match(/^(#{ c1 })\1$/i, c2 + c1)
assert_match(/^(#{ c2 })\1$/i, c1 + c2)
assert_match(/^[#{ c1 }]+$/i, c2 + c1)
assert_match(/^[#{ c2 }]+$/i, c1 + c2)
end
))
end
def test_iso_8859_10
eval("# encoding: iso8859-10\n" + ASSERTS.gsub(/ENCODING/m, "iso8859-10"))
end
def test_iso_8859_11
eval(%q(# encoding: iso8859-11
[*(0xa0..0xda), *(0xdf..0xfb)].each do |c|
c1 = c.chr("iso8859-11")
assert_match(/^(#{ c1 })\1$/i, c1 * 2)
end
))
end
def test_iso_8859_13
eval("# encoding: iso8859-13\n" + ASSERTS.gsub(/ENCODING/m, "iso8859-13"))
end
def test_iso_8859_14
eval("# encoding: iso8859-14\n" + ASSERTS.gsub(/ENCODING/m, "iso8859-14"))
end
def test_iso_8859_15
eval("# encoding: iso8859-15\n" + ASSERTS.gsub(/ENCODING/m, "iso8859-15"))
end
def test_iso_8859_16
eval("# encoding: iso8859-16\n" + ASSERTS.gsub(/ENCODING/m, "iso8859-16"))
end
end