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/test_regexp.rb

1090 lines
37 KiB
Ruby
Raw Normal View History

# coding: US-ASCII
require 'test/unit'
class TestRegexp < Test::Unit::TestCase
def setup
@verbose = $VERBOSE
$VERBOSE = nil
end
def teardown
$VERBOSE = @verbose
end
def test_has_NOENCODING
assert Regexp::NOENCODING
re = //n
assert_equal Regexp::NOENCODING, re.options
end
def test_ruby_dev_999
assert_match(/(?<=a).*b/, "aab")
assert_match(/(?<=\u3042).*b/, "\u3042ab")
end
def test_ruby_core_27247
assert_match(/(a){2}z/, "aaz")
end
def test_ruby_dev_24643
assert_nothing_raised("[ruby-dev:24643]") {
/(?:(?:[a]*[a])?b)*a*$/ =~ "aabaaca"
}
end
def test_ruby_talk_116455
assert_match(/^(\w{2,}).* ([A-Za-z\xa2\xc0-\xff]{2,}?)$/n, "Hallo Welt")
end
def test_ruby_dev_24887
assert_equal("a".gsub(/a\Z/, ""), "")
end
def test_yoshidam_net_20041111_1
s = "[\xC2\xA0-\xC3\xBE]"
assert_match(Regexp.new(s, nil, "u"), "\xC3\xBE")
end
def test_yoshidam_net_20041111_2
assert_raise(RegexpError) do
s = "[\xFF-\xFF]".force_encoding("utf-8")
Regexp.new(s, nil, "u")
end
end
def test_ruby_dev_31309
assert_equal('Ruby', 'Ruby'.sub(/[^a-z]/i, '-'))
end
def test_assert_normal_exit
# moved from knownbug. It caused core.
Regexp.union("a", "a")
end
def test_to_s
assert_equal '(?-mix:\x00)', Regexp.new("\0").to_s
str = "abcd\u3042"
[:UTF_16BE, :UTF_16LE, :UTF_32BE, :UTF_32LE].each do |es|
enc = Encoding.const_get(es)
rs = Regexp.new(str.encode(enc)).to_s
assert_equal("(?-mix:abcd\u3042)".encode(enc), rs)
assert_equal(enc, rs.encoding)
end
end
def test_union
assert_equal :ok, begin
Regexp.union(
"a",
Regexp.new("\xc2\xa1".force_encoding("euc-jp")),
Regexp.new("\xc2\xa1".force_encoding("utf-8")))
:ng
rescue ArgumentError
:ok
end
end
def test_word_boundary
assert_match(/\u3042\b /, "\u3042 ")
assert_not_match(/\u3042\ba/, "\u3042a")
end
def test_named_capture
m = /&(?<foo>.*?);/.match("aaa &amp; yyy")
assert_equal("amp", m["foo"])
assert_equal("amp", m[:foo])
assert_equal(5, m.begin(:foo))
assert_equal(8, m.end(:foo))
assert_equal([5,8], m.offset(:foo))
assert_equal("aaa [amp] yyy",
"aaa &amp; yyy".sub(/&(?<foo>.*?);/, '[\k<foo>]'))
assert_equal('#<MatchData "&amp; y" foo:"amp">',
/&(?<foo>.*?); (y)/.match("aaa &amp; yyy").inspect)
assert_equal('#<MatchData "&amp; y" 1:"amp" 2:"y">',
/&(.*?); (y)/.match("aaa &amp; yyy").inspect)
assert_equal('#<MatchData "&amp; y" foo:"amp" bar:"y">',
/&(?<foo>.*?); (?<bar>y)/.match("aaa &amp; yyy").inspect)
assert_equal('#<MatchData "&amp; y" foo:"amp" foo:"y">',
/&(?<foo>.*?); (?<foo>y)/.match("aaa &amp; yyy").inspect)
/(?<id>[A-Za-z_]+)/ =~ "!abc"
assert_equal("abc", Regexp.last_match(:id))
/a/ =~ "b" # doesn't match.
assert_equal(nil, Regexp.last_match)
assert_equal(nil, Regexp.last_match(1))
assert_equal(nil, Regexp.last_match(:foo))
assert_equal(["foo", "bar"], /(?<foo>.)(?<bar>.)/.names)
assert_equal(["foo"], /(?<foo>.)(?<foo>.)/.names)
assert_equal([], /(.)(.)/.names)
assert_equal(["foo", "bar"], /(?<foo>.)(?<bar>.)/.match("ab").names)
assert_equal(["foo"], /(?<foo>.)(?<foo>.)/.match("ab").names)
assert_equal([], /(.)(.)/.match("ab").names)
assert_equal({"foo"=>[1], "bar"=>[2]},
/(?<foo>.)(?<bar>.)/.named_captures)
assert_equal({"foo"=>[1, 2]},
/(?<foo>.)(?<foo>.)/.named_captures)
assert_equal({}, /(.)(.)/.named_captures)
assert_equal("a[b]c", "abc".sub(/(?<x>[bc])/, "[\\k<x>]"))
assert_equal("o", "foo"[/(?<bar>o)/, "bar"])
s = "foo"
s[/(?<bar>o)/, "bar"] = "baz"
assert_equal("fbazo", s)
end
def test_named_capture_with_nul
bug9902 = '[ruby-dev:48275] [Bug #9902]'
m = /(?<a>.*)/.match("foo")
assert_raise(IndexError, bug9902) {m["a\0foo"]}
assert_raise(IndexError, bug9902) {m["a\0foo".to_sym]}
m = Regexp.new("(?<foo\0bar>.*)").match("xxx")
assert_raise(IndexError, bug9902) {m["foo"]}
assert_raise(IndexError, bug9902) {m["foo".to_sym]}
assert_nothing_raised(IndexError, bug9902) {
assert_equal("xxx", m["foo\0bar"], bug9902)
assert_equal("xxx", m["foo\0bar".to_sym], bug9902)
}
end
def test_named_capture_nonascii
bug9903 = '[ruby-dev:48278] [Bug #9903]'
key = "\xb1\xb2".force_encoding(Encoding::EUC_JP)
m = /(?<#{key}>.*)/.match("xxx")
assert_equal("xxx", m[key])
assert_raise(IndexError, bug9903) {m[key.dup.force_encoding(Encoding::Shift_JIS)]}
end
def test_assign_named_capture
assert_equal("a", eval('/(?<foo>.)/ =~ "a"; foo'))
assert_equal("a", eval('foo = 1; /(?<foo>.)/ =~ "a"; foo'))
assert_equal("a", eval('1.times {|foo| /(?<foo>.)/ =~ "a"; break foo }'))
assert_nothing_raised { eval('/(?<Foo>.)/ =~ "a"') }
assert_nil(eval('/(?<Foo>.)/ =~ "a"; defined? Foo'))
end
def test_assign_named_capture_to_reserved_word
/(?<nil>.)/ =~ "a"
assert_not_include(local_variables, :nil, "[ruby-dev:32675]")
end
def test_match_regexp
r = /./
m = r.match("a")
assert_equal(r, m.regexp)
re = /foo/
assert_equal(re, re.match("foo").regexp)
end
def test_source
bug5484 = '[ruby-core:40364]'
assert_equal('', //.source)
assert_equal('\:', /\:/.source, bug5484)
assert_equal(':', %r:\::.source, bug5484)
end
def test_source_escaped
expected, result = "$*+.?^|".each_char.map {|c|
[
["\\#{c}", "\\#{c}", 1],
begin
re = eval("%r#{c}\\#{c}#{c}", nil, __FILE__, __LINE__)
t = eval("/\\#{c}/", nil, __FILE__, __LINE__).source
rescue SyntaxError => e
[e, t, nil]
else
[re.source, t, re =~ "a#{c}a"]
end
]
}.transpose
assert_equal(expected, result)
end
def test_source_escaped_paren
bug7610 = '[ruby-core:51088] [Bug #7610]'
bug8133 = '[ruby-core:53578] [Bug #8133]'
[
["(", ")", bug7610], ["[", "]", bug8133],
["{", "}", bug8133], ["<", ">", bug8133],
].each do |lparen, rparen, bug|
s = "\\#{lparen}a\\#{rparen}"
assert_equal(/#{s}/, eval("%r#{lparen}#{s}#{rparen}"), bug)
end
end
def test_source_unescaped
expected, result = "!\"#%&',-/:;=@_`~".each_char.map {|c|
[
["#{c}", "\\#{c}", 1],
begin
re = eval("%r#{c}\\#{c}#{c}", nil, __FILE__, __LINE__)
t = eval("%r{\\#{c}}", nil, __FILE__, __LINE__).source
rescue SyntaxError => e
[e, t, nil]
else
[re.source, t, re =~ "a#{c}a"]
end
]
}.transpose
assert_equal(expected, result)
end
def test_inspect
assert_equal('//', //.inspect)
assert_equal('//i', //i.inspect)
assert_equal('/\//i', /\//i.inspect)
assert_equal('/\//i', %r"#{'/'}"i.inspect)
assert_equal('/\/x/i', /\/x/i.inspect)
assert_equal('/\x00/i', /#{"\0"}/i.inspect)
assert_equal("/\n/i", /#{"\n"}/i.inspect)
s = [0xf1, 0xf2, 0xf3].pack("C*")
assert_equal('/\/\xF1\xF2\xF3/i', /\/#{s}/i.inspect)
end
def test_char_to_option
assert_equal("BAR", "FOOBARBAZ"[/b../i])
assert_equal("bar", "foobarbaz"[/ b . . /x])
assert_equal("bar\n", "foo\nbar\nbaz"[/b.../m])
assert_raise(SyntaxError) { eval('//z') }
end
def test_char_to_option_kcode
assert_equal("bar", "foobarbaz"[/b../s])
assert_equal("bar", "foobarbaz"[/b../e])
assert_equal("bar", "foobarbaz"[/b../u])
end
def test_to_s2
assert_equal('(?-mix:foo)', /(?:foo)/.to_s)
assert_equal('(?m-ix:foo)', /(?:foo)/m.to_s)
assert_equal('(?mi-x:foo)', /(?:foo)/mi.to_s)
assert_equal('(?mix:foo)', /(?:foo)/mix.to_s)
assert_equal('(?m-ix:foo)', /(?m-ix:foo)/.to_s)
assert_equal('(?mi-x:foo)', /(?mi-x:foo)/.to_s)
assert_equal('(?mix:foo)', /(?mix:foo)/.to_s)
assert_equal('(?mix:)', /(?mix)/.to_s)
assert_equal('(?-mix:(?mix:foo) )', /(?mix:foo) /.to_s)
end
def test_casefold_p
assert_equal(false, /a/.casefold?)
assert_equal(true, /a/i.casefold?)
assert_equal(false, /(?i:a)/.casefold?)
end
def test_options
assert_equal(Regexp::IGNORECASE, /a/i.options)
assert_equal(Regexp::EXTENDED, /a/x.options)
assert_equal(Regexp::MULTILINE, /a/m.options)
end
def test_match_init_copy
m = /foo/.match("foo")
assert_equal(/foo/, m.dup.regexp)
assert_raise(TypeError) do
m.instance_eval { initialize_copy(nil) }
end
assert_equal([0, 3], m.offset(0))
assert_equal(/foo/, m.dup.regexp)
end
def test_match_size
m = /(.)(.)(\d+)(\d)/.match("THX1138.")
assert_equal(5, m.size)
end
def test_match_offset_begin_end
m = /(?<x>b..)/.match("foobarbaz")
assert_equal([3, 6], m.offset("x"))
assert_equal(3, m.begin("x"))
assert_equal(6, m.end("x"))
assert_raise(IndexError) { m.offset("y") }
assert_raise(IndexError) { m.offset(2) }
assert_raise(IndexError) { m.begin(2) }
assert_raise(IndexError) { m.end(2) }
m = /(?<x>q..)?/.match("foobarbaz")
assert_equal([nil, nil], m.offset("x"))
assert_equal(nil, m.begin("x"))
assert_equal(nil, m.end("x"))
m = /\A\u3042(.)(.)?(.)\z/.match("\u3042\u3043\u3044")
assert_equal([1, 2], m.offset(1))
assert_equal([nil, nil], m.offset(2))
assert_equal([2, 3], m.offset(3))
end
def test_match_to_s
m = /(?<x>b..)/.match("foobarbaz")
assert_equal("bar", m.to_s)
end
def test_match_pre_post
m = /(?<x>b..)/.match("foobarbaz")
assert_equal("foo", m.pre_match)
assert_equal("baz", m.post_match)
end
def test_match_array
m = /(...)(...)(...)(...)?/.match("foobarbaz")
assert_equal(["foobarbaz", "foo", "bar", "baz", nil], m.to_a)
end
def test_match_captures
m = /(...)(...)(...)(...)?/.match("foobarbaz")
assert_equal(["foo", "bar", "baz", nil], m.captures)
end
def test_match_aref
m = /(...)(...)(...)(...)?/.match("foobarbaz")
assert_equal("foo", m[1])
assert_equal(["foo", "bar", "baz"], m[1..3])
assert_nil(m[5])
assert_raise(IndexError) { m[:foo] }
end
def test_match_values_at
m = /(...)(...)(...)(...)?/.match("foobarbaz")
assert_equal(["foo", "bar", "baz"], m.values_at(1, 2, 3))
end
def test_match_string
m = /(?<x>b..)/.match("foobarbaz")
assert_equal("foobarbaz", m.string)
end
def test_match_inspect
m = /(...)(...)(...)(...)?/.match("foobarbaz")
assert_equal('#<MatchData "foobarbaz" 1:"foo" 2:"bar" 3:"baz" 4:nil>', m.inspect)
end
def test_initialize
assert_raise(ArgumentError) { Regexp.new }
assert_equal(/foo/, Regexp.new(/foo/, Regexp::IGNORECASE))
assert_equal(Encoding.find("US-ASCII"), Regexp.new("b..", nil, "n").encoding)
assert_equal("bar", "foobarbaz"[Regexp.new("b..", nil, "n")])
assert_equal(//n, Regexp.new("", nil, "n"))
arg_encoding_none = 32 # ARG_ENCODING_NONE is implementation defined value
assert_equal(arg_encoding_none, Regexp.new("", nil, "n").options)
assert_equal(arg_encoding_none, Regexp.new("", nil, "N").options)
assert_raise(RegexpError) { Regexp.new(")(") }
end
def test_unescape
assert_raise(ArgumentError) { s = '\\'; /#{ s }/ }
assert_equal(/\xFF/n, /#{ s="\\xFF" }/n)
assert_equal(/\177/, (s = '\177'; /#{ s }/))
assert_raise(ArgumentError) { s = '\u'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\u{ ffffffff }'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\u{ ffffff }'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\u{ ffff X }'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\u{ }'; /#{ s }/ }
assert_equal("b", "abc"[(s = '\u{0062}'; /#{ s }/)])
assert_equal("b", "abc"[(s = '\u0062'; /#{ s }/)])
assert_raise(ArgumentError) { s = '\u0'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\u000X'; /#{ s }/ }
assert_raise(ArgumentError) { s = "\xff" + '\u3042'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\u3042' + [0xff].pack("C"); /#{ s }/ }
assert_raise(SyntaxError) { s = ''; eval(%q(/\u#{ s }/)) }
assert_equal(/a/, eval(%q(s="\u0061";/#{s}/n)))
assert_raise(RegexpError) { s = "\u3042"; eval(%q(/#{s}/n)) }
assert_raise(RegexpError) { s = "\u0061"; eval(%q(/\u3042#{s}/n)) }
assert_raise(RegexpError) { s1=[0xff].pack("C"); s2="\u3042"; eval(%q(/#{s1}#{s2}/)); [s1, s2] }
assert_raise(ArgumentError) { s = '\x'; /#{ s }/ }
assert_equal("\xe1", [0x00, 0xe1, 0xff].pack("C*")[/\M-a/])
assert_equal("\xdc", [0x00, 0xdc, 0xff].pack("C*")[/\M-\\/])
assert_equal("\x8a", [0x00, 0x8a, 0xff].pack("C*")[/\M-\n/])
assert_equal("\x89", [0x00, 0x89, 0xff].pack("C*")[/\M-\t/])
assert_equal("\x8d", [0x00, 0x8d, 0xff].pack("C*")[/\M-\r/])
assert_equal("\x8c", [0x00, 0x8c, 0xff].pack("C*")[/\M-\f/])
assert_equal("\x8b", [0x00, 0x8b, 0xff].pack("C*")[/\M-\v/])
assert_equal("\x87", [0x00, 0x87, 0xff].pack("C*")[/\M-\a/])
assert_equal("\x9b", [0x00, 0x9b, 0xff].pack("C*")[/\M-\e/])
assert_equal("\x01", [0x00, 0x01, 0xff].pack("C*")[/\C-a/])
assert_raise(ArgumentError) { s = '\M'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\M-\M-a'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\M-\\'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\C'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\c'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\C-\C-a'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\M-\z'; /#{ s }/ }
assert_raise(ArgumentError) { s = '\M-\777'; /#{ s }/ }
assert_equal("\u3042\u3042", "\u3042\u3042"[(s = "\u3042" + %q(\xe3\x81\x82); /#{s}/)])
assert_raise(ArgumentError) { s = "\u3042" + %q(\xe3); /#{s}/ }
assert_raise(ArgumentError) { s = "\u3042" + %q(\xe3\xe3); /#{s}/ }
assert_raise(ArgumentError) { s = '\u3042' + [0xff].pack("C"); /#{s}/ }
assert_raise(SyntaxError) { eval("/\u3042/n") }
s = ".........."
5.times { s.sub!(".", "") }
assert_equal(".....", s)
end
def test_equal
bug5484 = '[ruby-core:40364]'
assert_equal(/abc/, /abc/)
assert_not_equal(/abc/, /abc/m)
assert_not_equal(/abc/, /abd/)
assert_equal(/\/foo/, Regexp.new('/foo'), bug5484)
end
def test_match
assert_nil(//.match(nil))
assert_equal("abc", /.../.match(:abc)[0])
assert_raise(TypeError) { /.../.match(Object.new)[0] }
assert_equal("bc", /../.match('abc', 1)[0])
assert_equal("bc", /../.match('abc', -2)[0])
assert_nil(/../.match("abc", -4))
assert_nil(/../.match("abc", 4))
assert_equal('\x', /../n.match("\u3042" + '\x', 1)[0])
r = nil
/.../.match("abc") {|m| r = m[0] }
assert_equal("abc", r)
$_ = "abc"; assert_equal(1, ~/bc/)
$_ = "abc"; assert_nil(~/d/)
$_ = nil; assert_nil(~/./)
end
def test_eqq
assert_equal(false, /../ === nil)
end
def test_quote
assert_equal("\xff", Regexp.quote([0xff].pack("C")))
assert_equal("\\ ", Regexp.quote("\ "))
assert_equal("\\t", Regexp.quote("\t"))
assert_equal("\\n", Regexp.quote("\n"))
assert_equal("\\r", Regexp.quote("\r"))
assert_equal("\\f", Regexp.quote("\f"))
assert_equal("\\v", Regexp.quote("\v"))
assert_equal("\u3042\\t", Regexp.quote("\u3042\t"))
assert_equal("\\t\xff", Regexp.quote("\t" + [0xff].pack("C")))
end
def test_try_convert
assert_equal(/re/, Regexp.try_convert(/re/))
assert_nil(Regexp.try_convert("re"))
o = Object.new
assert_nil(Regexp.try_convert(o))
def o.to_regexp() /foo/ end
assert_equal(/foo/, Regexp.try_convert(o))
end
def test_union2
assert_equal(/(?!)/, Regexp.union)
assert_equal(/foo/, Regexp.union(/foo/))
assert_equal(/foo/, Regexp.union([/foo/]))
assert_equal(/\t/, Regexp.union("\t"))
assert_equal(/(?-mix:\u3042)|(?-mix:\u3042)/, Regexp.union(/\u3042/, /\u3042/))
assert_equal("\u3041", "\u3041"[Regexp.union(/\u3042/, "\u3041")])
end
def test_dup
assert_equal(//, //.dup)
assert_raise(TypeError) { //.instance_eval { initialize_copy(nil) } }
end
def test_regsub
assert_equal("fooXXXbaz", "foobarbaz".sub!(/bar/, "XXX"))
s = [0xff].pack("C")
assert_equal(s, "X".sub!(/./, s))
assert_equal('\\' + s, "X".sub!(/./, '\\' + s))
assert_equal('\k', "foo".sub!(/.../, '\k'))
assert_raise(RuntimeError) { "foo".sub!(/(?<x>o)/, '\k<x') }
assert_equal('foo[bar]baz', "foobarbaz".sub!(/(b..)/, '[\0]'))
assert_equal('foo[foo]baz', "foobarbaz".sub!(/(b..)/, '[\`]'))
assert_equal('foo[baz]baz', "foobarbaz".sub!(/(b..)/, '[\\\']'))
assert_equal('foo[r]baz', "foobarbaz".sub!(/(b)(.)(.)/, '[\+]'))
assert_equal('foo[\\]baz', "foobarbaz".sub!(/(b..)/, '[\\\\]'))
assert_equal('foo[\z]baz', "foobarbaz".sub!(/(b..)/, '[\z]'))
end
def test_regsub_K
bug8856 = '[ruby-dev:47694] [Bug #8856]'
result = "foobarbazquux/foobarbazquux".gsub(/foo\Kbar/, "")
assert_equal('foobazquux/foobazquux', result, bug8856)
end
def test_KCODE
assert_nil($KCODE)
assert_nothing_raised { $KCODE = nil }
assert_equal(false, $=)
assert_nothing_raised { $= = nil }
end
def test_match_setter
/foo/ =~ "foo"
m = $~
/bar/ =~ "bar"
$~ = m
assert_equal("foo", $&)
end
def test_last_match
/(...)(...)(...)(...)?/.match("foobarbaz")
assert_equal("foobarbaz", Regexp.last_match(0))
assert_equal("foo", Regexp.last_match(1))
assert_nil(Regexp.last_match(5))
assert_nil(Regexp.last_match(-1))
end
def test_getter
alias $__REGEXP_TEST_LASTMATCH__ $&
alias $__REGEXP_TEST_PREMATCH__ $`
alias $__REGEXP_TEST_POSTMATCH__ $'
alias $__REGEXP_TEST_LASTPARENMATCH__ $+
/(b)(.)(.)/.match("foobarbaz")
assert_equal("bar", $__REGEXP_TEST_LASTMATCH__)
assert_equal("foo", $__REGEXP_TEST_PREMATCH__)
assert_equal("baz", $__REGEXP_TEST_POSTMATCH__)
assert_equal("r", $__REGEXP_TEST_LASTPARENMATCH__)
/(...)(...)(...)/.match("foobarbaz")
assert_equal("baz", $+)
end
def test_rindex_regexp
assert_equal(3, "foobarbaz\u3042".rindex(/b../n, 5))
end
def test_taint
m = Thread.new do
"foo"[/foo/]
* safe.c (rb_set_safe_level, safe_setter): raise an ArgumentError when $SAFE is set to 4. $SAFE=4 is now obsolete. [ruby-core:55222] [Feature #8468] * object.c (rb_obj_untrusted, rb_obj_untrust, rb_obj_trust): Kernel#untrusted?, untrust, and trust are now deprecated. Their behavior is same as tainted?, taint, and untaint, respectively. * include/ruby/ruby.h (OBJ_UNTRUSTED, OBJ_UNTRUST): OBJ_UNTRUSTED() and OBJ_UNTRUST() are aliases of OBJ_TAINTED() and OBJ_TAINT(), respectively. * array.c, class.c, debug.c, dir.c, encoding.c, error.c, eval.c, ext/curses/curses.c, ext/dbm/dbm.c, ext/dl/cfunc.c, ext/dl/cptr.c, ext/dl/dl.c, ext/etc/etc.c, ext/fiddle/fiddle.c, ext/fiddle/pointer.c, ext/gdbm/gdbm.c, ext/readline/readline.c, ext/sdbm/init.c, ext/socket/ancdata.c, ext/socket/basicsocket.c, ext/socket/socket.c, ext/socket/udpsocket.c, ext/stringio/stringio.c, ext/syslog/syslog.c, ext/tk/tcltklib.c, ext/win32ole/win32ole.c, file.c, gc.c, hash.c, io.c, iseq.c, load.c, marshal.c, object.c, proc.c, process.c, random.c, re.c, safe.c, string.c, thread.c, transcode.c, variable.c, vm_insnhelper.c, vm_method.c, vm_trace.c: remove code for $SAFE=4. * test/dl/test_dl2.rb, test/erb/test_erb.rb, test/readline/test_readline.rb, test/readline/test_readline_history.rb, test/ruby/test_alias.rb, test/ruby/test_array.rb, test/ruby/test_dir.rb, test/ruby/test_encoding.rb, test/ruby/test_env.rb, test/ruby/test_eval.rb, test/ruby/test_exception.rb, test/ruby/test_file_exhaustive.rb, test/ruby/test_hash.rb, test/ruby/test_io.rb, test/ruby/test_method.rb, test/ruby/test_module.rb, test/ruby/test_object.rb, test/ruby/test_pack.rb, test/ruby/test_rand.rb, test/ruby/test_regexp.rb, test/ruby/test_settracefunc.rb, test/ruby/test_struct.rb, test/ruby/test_thread.rb, test/ruby/test_time.rb: remove tests for $SAFE=4. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@41259 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2013-06-12 10:20:51 -04:00
$SAFE = 3
/foo/.match("foo")
end.value
assert_predicate(m, :tainted?)
assert_nothing_raised('[ruby-core:26137]') {
* safe.c (rb_set_safe_level, safe_setter): raise an ArgumentError when $SAFE is set to 4. $SAFE=4 is now obsolete. [ruby-core:55222] [Feature #8468] * object.c (rb_obj_untrusted, rb_obj_untrust, rb_obj_trust): Kernel#untrusted?, untrust, and trust are now deprecated. Their behavior is same as tainted?, taint, and untaint, respectively. * include/ruby/ruby.h (OBJ_UNTRUSTED, OBJ_UNTRUST): OBJ_UNTRUSTED() and OBJ_UNTRUST() are aliases of OBJ_TAINTED() and OBJ_TAINT(), respectively. * array.c, class.c, debug.c, dir.c, encoding.c, error.c, eval.c, ext/curses/curses.c, ext/dbm/dbm.c, ext/dl/cfunc.c, ext/dl/cptr.c, ext/dl/dl.c, ext/etc/etc.c, ext/fiddle/fiddle.c, ext/fiddle/pointer.c, ext/gdbm/gdbm.c, ext/readline/readline.c, ext/sdbm/init.c, ext/socket/ancdata.c, ext/socket/basicsocket.c, ext/socket/socket.c, ext/socket/udpsocket.c, ext/stringio/stringio.c, ext/syslog/syslog.c, ext/tk/tcltklib.c, ext/win32ole/win32ole.c, file.c, gc.c, hash.c, io.c, iseq.c, load.c, marshal.c, object.c, proc.c, process.c, random.c, re.c, safe.c, string.c, thread.c, transcode.c, variable.c, vm_insnhelper.c, vm_method.c, vm_trace.c: remove code for $SAFE=4. * test/dl/test_dl2.rb, test/erb/test_erb.rb, test/readline/test_readline.rb, test/readline/test_readline_history.rb, test/ruby/test_alias.rb, test/ruby/test_array.rb, test/ruby/test_dir.rb, test/ruby/test_encoding.rb, test/ruby/test_env.rb, test/ruby/test_eval.rb, test/ruby/test_exception.rb, test/ruby/test_file_exhaustive.rb, test/ruby/test_hash.rb, test/ruby/test_io.rb, test/ruby/test_method.rb, test/ruby/test_module.rb, test/ruby/test_object.rb, test/ruby/test_pack.rb, test/ruby/test_rand.rb, test/ruby/test_regexp.rb, test/ruby/test_settracefunc.rb, test/ruby/test_struct.rb, test/ruby/test_thread.rb, test/ruby/test_time.rb: remove tests for $SAFE=4. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@41259 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2013-06-12 10:20:51 -04:00
m = proc {$SAFE = 3; %r"#{ }"o}.call
}
assert_predicate(m, :tainted?)
end
def assert_regexp(re, ss, fs = [], msg = nil)
re = Regexp.new(re) unless re.is_a?(Regexp)
ss = [ss] unless ss.is_a?(Array)
ss.each do |e, s|
s ||= e
assert_match(re, s, msg)
m = re.match(s)
assert_equal(e, m[0], msg)
end
fs = [fs] unless fs.is_a?(Array)
fs.each {|s| assert_no_match(re, s, msg) }
end
alias check assert_regexp
def assert_fail(re)
assert_raise(RegexpError) { %r"#{ re }" }
end
alias failcheck assert_fail
def test_parse
check(/\*\+\?\{\}\|\(\)\<\>\`\'/, "*+?{}|()<>`'")
check(/\A\w\W\z/, %w(a. b!), %w(.. ab))
check(/\A.\b.\b.\B.\B.\z/, %w(a.aaa .a...), %w(aaaaa .....))
check(/\A\s\S\z/, [' a', "\n."], [' ', "\n\n", 'a '])
check(/\A\d\D\z/, '0a', %w(00 aa))
check(/\A\h\H\z/, %w(0g ag BH), %w(a0 af GG))
check(/\Afoo\Z\s\z/, "foo\n", ["foo", "foo\nbar"])
assert_equal(%w(a b c), "abc def".scan(/\G\w/))
check(/\A\u3042\z/, "\u3042", ["", "\u3043", "a"])
check(/\A(..)\1\z/, %w(abab ....), %w(abba aba))
failcheck('\1')
check(/\A\80\z/, "80", ["\100", ""])
check(/\A\77\z/, "?")
check(/\A\78\z/, "\7" + '8', ["\100", ""])
check(eval('/\A\Qfoo\E\z/'), "QfooE")
check(/\Aa++\z/, "aaa")
check('\Ax]\z', "x]")
check(/x#foo/x, "x", "#foo")
check(/\Ax#foo#{ "\n" }x\z/x, "xx", ["x", "x#foo\nx"])
check(/\A\p{Alpha}\z/, ["a", "z"], [".", "", ".."])
check(/\A\p{^Alpha}\z/, [".", "!"], ["!a", ""])
check(/\A\n\z/, "\n")
check(/\A\t\z/, "\t")
check(/\A\r\z/, "\r")
check(/\A\f\z/, "\f")
check(/\A\a\z/, "\007")
check(/\A\e\z/, "\033")
check(/\A\v\z/, "\v")
failcheck('(')
failcheck('(?foo)')
failcheck('/\p{foobarbazqux}/')
failcheck('/\p{foobarbazqux' + 'a' * 1000 + '}/')
failcheck('/[1-\w]/')
end
def test_exec
check(/A*B/, %w(B AB AAB AAAB), %w(A))
check(/\w*!/, %w(! a! ab! abc!), %w(abc))
check(/\w*\W/, %w(! a" ab# abc$), %w(abc))
check(/\w*\w/, %w(z az abz abcz), %w(!))
check(/[a-z]*\w/, %w(z az abz abcz), %w(!))
check(/[a-z]*\W/, %w(! a" ab# abc$), %w(A))
check(/((a|bb|ccc|dddd)(1|22|333|4444))/i, %w(a1 bb1 a22), %w(a2 b1))
check(/\u0080/, (1..4).map {|i| ["\u0080", "\u0080" * i] }, ["\u0081"])
check(/\u0080\u0080/, (2..4).map {|i| ["\u0080" * 2, "\u0080" * i] }, ["\u0081"])
check(/\u0080\u0080\u0080/, (3..4).map {|i| ["\u0080" * 3, "\u0080" * i] }, ["\u0081"])
check(/\u0080\u0080\u0080\u0080/, (4..4).map {|i| ["\u0080" * 4, "\u0080" * i] }, ["\u0081"])
check(/[^\u3042\u3043\u3044]/, %W(a b \u0080 \u3041 \u3045), %W(\u3042 \u3043 \u3044))
check(/a.+/m, %W(a\u0080 a\u0080\u0080 a\u0080\u0080\u0080), %W(a))
check(/a.+z/m, %W(a\u0080z a\u0080\u0080z a\u0080\u0080\u0080z), %W(az))
check(/abc\B.\Bxyz/, %w(abcXxyz abc0xyz), %w(abc|xyz abc-xyz))
check(/\Bxyz/, [%w(xyz abcXxyz), %w(xyz abc0xyz)], %w(abc xyz abc-xyz))
check(/abc\B/, [%w(abc abcXxyz), %w(abc abc0xyz)], %w(abc xyz abc-xyz))
failcheck('(?<foo>abc)\1')
check(/^(A+|B+)(?>\g<1>)*[BC]$/, %w(AC BC ABC BAC AABBC), %w(AABB))
check(/^(A+|B(?>\g<1>)*)[AC]$/, %w(AAAC BBBAAAAC), %w(BBBAAA))
check(/^()(?>\g<1>)*$/, "", "a")
check(/^(?>(?=a)(#{ "a" * 1000 }|))++$/, ["a" * 1000, "a" * 2000, "a" * 3000], ["", "a" * 500, "b" * 1000])
check(eval('/^(?:a?)?$/'), ["", "a"], ["aa"])
check(eval('/^(?:a+)?$/'), ["", "a", "aa"], ["ab"])
check(/^(?:a?)+?$/, ["", "a", "aa"], ["ab"])
check(/^a??[ab]/, [["a", "a"], ["a", "aa"], ["b", "b"], ["a", "ab"]], ["c"])
check(/^(?:a*){3,5}$/, ["", "a", "aa", "aaa", "aaaa", "aaaaa", "aaaaaa"], ["b"])
check(/^(?:a+){3,5}$/, ["aaa", "aaaa", "aaaaa", "aaaaaa"], ["", "a", "aa", "b"])
end
def test_parse_look_behind
check(/(?<=A)B(?=C)/, [%w(B ABC)], %w(aBC ABc aBc))
check(/(?<!A)B(?!C)/, [%w(B aBc)], %w(ABC aBC ABc))
failcheck('(?<=.*)')
failcheck('(?<!.*)')
check(/(?<=A|B.)C/, [%w(C AC), %w(C BXC)], %w(C BC))
check(/(?<!A|B.)C/, [%w(C C), %w(C BC)], %w(AC BXC))
assert_not_match(/(?<!aa|b)c/i, "Aac")
assert_not_match(/(?<!b|aa)c/i, "Aac")
end
def test_parse_kg
check(/\A(.)(.)\k<1>(.)\z/, %w(abac abab ....), %w(abcd aaba xxx))
check(/\A(.)(.)\k<-1>(.)\z/, %w(abbc abba ....), %w(abcd aaba xxx))
check(/\A(?<n>.)(?<x>\g<n>){0}(?<y>\k<n+0>){0}\g<x>\g<y>\z/, "aba", "abb")
check(/\A(?<n>.)(?<x>\g<n>){0}(?<y>\k<n+1>){0}\g<x>\g<y>\z/, "abb", "aba")
check(/\A(?<x>..)\k<x>\z/, %w(abab ....), %w(abac abba xxx))
check(/\A(.)(..)\g<-1>\z/, "abcde", %w(.... ......))
failcheck('\k<x>')
failcheck('\k<')
failcheck('\k<>')
failcheck('\k<.>')
failcheck('\k<x.>')
failcheck('\k<1.>')
failcheck('\k<x')
failcheck('\k<x+')
failcheck('()\k<-2>')
failcheck('()\g<-2>')
check(/\A(?<x>.)(?<x>.)\k<x>\z/, %w(aba abb), %w(abc .. ....))
check(/\A(?<x>.)(?<x>.)\k<x>\z/i, %w(aba ABa abb ABb), %w(abc .. ....))
check('\k\g', "kg")
failcheck('(.\g<1>)')
failcheck('(.\g<2>)')
failcheck('(?=\g<1>)')
failcheck('((?=\g<1>))')
failcheck('(\g<1>|.)')
failcheck('(.|\g<1>)')
check(/(!)(?<=(a)|\g<1>)/, ["!"], %w(a))
check(/^(a|b\g<1>c)$/, %w(a bac bbacc bbbaccc), %w(bbac bacc))
check(/^(a|b\g<2>c)(B\g<1>C){0}$/, %w(a bBaCc bBbBaCcCc bBbBbBaCcCcCc), %w(bBbBaCcC BbBaCcCc))
check(/\A(?<n>.|X\g<n>)(?<x>\g<n>){0}(?<y>\k<n+0>){0}\g<x>\g<y>\z/, "XXaXbXXa", %w(XXabXa abb))
check(/\A(?<n>.|X\g<n>)(?<x>\g<n>){0}(?<y>\k<n+1>){0}\g<x>\g<y>\z/, "XaXXbXXb", %w(aXXbXb aba))
failcheck('(?<x>)(?<x>)(\g<x>)')
check(/^(?<x>foo)(bar)\k<x>/, %w(foobarfoo), %w(foobar barfoo))
check(/^(?<a>f)(?<a>o)(?<a>o)(?<a>b)(?<a>a)(?<a>r)(?<a>b)(?<a>a)(?<a>z)\k<a>{9}$/, %w(foobarbazfoobarbaz foobarbazbazbarfoo foobarbazzabraboof), %w(foobar barfoo))
end
def test_parse_curly_brace
check(/\A{/, ["{", ["{", "{x"]])
check(/\A{ /, ["{ ", ["{ ", "{ x"]])
check(/\A{,}\z/, "{,}")
check(/\A{}\z/, "{}")
check(/\Aa{0}+\z/, "", %w(a aa aab))
check(/\Aa{1}+\z/, %w(a aa), ["", "aab"])
check(/\Aa{1,2}b{1,2}\z/, %w(ab aab abb aabb), ["", "aaabb", "abbb"])
check(/(?!x){0,1}/, [ ['', 'ab'], ['', ''] ])
check(/c\z{0,1}/, [ ['c', 'abc'], ['c', 'cab']], ['abd'])
check(/\A{0,1}a/, [ ['a', 'abc'], ['a', '____abc']], ['bcd'])
failcheck('.{100001}')
failcheck('.{0,100001}')
failcheck('.{1,0}')
failcheck('{0}')
end
def test_parse_comment
check(/\A(?#foo\)bar)\z/, "", "a")
failcheck('(?#')
end
def test_char_type
check(/\u3042\d/, ["\u30421", "\u30422"])
# CClassTable cache test
assert_match(/\u3042\d/, "\u30421")
assert_match(/\u3042\d/, "\u30422")
end
def test_char_class
failcheck('[]')
failcheck('[x')
check('\A[]]\z', "]", "")
check('\A[]\.]+\z', %w(] . ]..]), ["", "["])
check(/\A[\u3042]\z/, "\u3042", "\u3042aa")
check(/\A[\u3042\x61]+\z/, ["aa\u3042aa", "\u3042\u3042", "a"], ["", "b"])
check(/\A[\u3042\x61\x62]+\z/, "abab\u3042abab\u3042")
check(/\A[abc]+\z/, "abcba", ["", "ada"])
check(/\A[\w][\W]\z/, %w(a. b!), %w(.. ab))
check(/\A[\s][\S]\z/, [' a', "\n."], [' ', "\n\n", 'a '])
check(/\A[\d][\D]\z/, '0a', %w(00 aa))
check(/\A[\h][\H]\z/, %w(0g ag BH), %w(a0 af GG))
check(/\A[\p{Alpha}]\z/, ["a", "z"], [".", "", ".."])
check(/\A[\p{^Alpha}]\z/, [".", "!"], ["!a", ""])
check(/\A[\xff]\z/, "\xff", ["", "\xfe"])
check(/\A[\80]+\z/, "8008", ["\\80", "\100", "\1000"])
check(/\A[\77]+\z/, "???")
check(/\A[\78]+\z/, "\788\7")
check(/\A[\0]\z/, "\0")
check(/\A[[:0]]\z/, [":", "0"], ["", ":0"])
check(/\A[0-]\z/, ["0", "-"], "0-")
check('\A[a-&&\w]\z', "a", "-")
check('\A[--0]\z', ["-", "/", "0"], ["", "1"])
check('\A[\'--0]\z', %w(* + \( \) 0 ,), ["", ".", "1"])
check(/\A[a-b-]\z/, %w(a b -), ["", "c"])
check('\A[a-b-&&\w]\z', %w(a b), ["", "-"])
check('\A[a-b-&&\W]\z', "-", ["", "a", "b"])
check('\A[a-c-e]\z', %w(a b c e -), %w(d))
check(/\A[a-f&&[^b-c]&&[^e]]\z/, %w(a d f), %w(b c e g 0))
check(/\A[[^b-c]&&[^e]&&a-f]\z/, %w(a d f), %w(b c e g 0))
check(/\A[\n\r\t]\z/, ["\n", "\r", "\t"])
failcheck('[9-1]')
assert_match(/\A\d+\z/, "0123456789")
assert_no_match(/\d/, "\uff10\uff11\uff12\uff13\uff14\uff15\uff16\uff17\uff18\uff19")
assert_match(/\A\w+\z/, "09azAZ_")
assert_no_match(/\w/, "\uff10\uff19\uff41\uff5a\uff21\uff3a")
assert_match(/\A\s+\z/, "\r\n\v\f\r\s")
assert_no_match(/\s/, "\u0085")
end
def test_posix_bracket
check(/\A[[:alpha:]0]\z/, %w(0 a), %w(1 .))
check(eval('/\A[[:^alpha:]0]\z/'), %w(0 1 .), "a")
check(eval('/\A[[:alpha\:]]\z/'), %w(a l p h a :), %w(b 0 1 .))
check(eval('/\A[[:alpha:foo]0]\z/'), %w(0 a), %w(1 .))
check(/\A[[:xdigit:]&&[:alpha:]]\z/, "a", %w(g 0))
check('\A[[:abcdefghijklmnopqrstu:]]+\z', "[]")
failcheck('[[:alpha')
failcheck('[[:alpha:')
failcheck('[[:alp:]]')
assert_match(/\A[[:digit:]]+\z/, "\uff10\uff11\uff12\uff13\uff14\uff15\uff16\uff17\uff18\uff19")
assert_match(/\A[[:alnum:]]+\z/, "\uff10\uff19\uff41\uff5a\uff21\uff3a")
assert_match(/\A[[:space:]]+\z/, "\r\n\v\f\r\s\u0085")
assert_match(/\A[[:ascii:]]+\z/, "\x00\x7F")
assert_no_match(/[[:ascii:]]/, "\x80\xFF")
end
def test_backward
assert_equal(3, "foobar".rindex(/b.r/i))
assert_equal(nil, "foovar".rindex(/b.r/i))
assert_equal(3, ("foo" + "bar" * 1000).rindex(/#{"bar"*1000}/))
assert_equal(4, ("foo\nbar\nbaz\n").rindex(/bar/i))
end
def test_uninitialized
assert_raise(TypeError) { Regexp.allocate.hash }
assert_raise(TypeError) { Regexp.allocate.eql? Regexp.allocate }
assert_raise(TypeError) { Regexp.allocate == Regexp.allocate }
assert_raise(TypeError) { Regexp.allocate =~ "" }
assert_equal(false, Regexp.allocate === Regexp.allocate)
assert_nil(~Regexp.allocate)
assert_raise(TypeError) { Regexp.allocate.match("") }
assert_raise(TypeError) { Regexp.allocate.to_s }
assert_match(/^#<Regexp:.*>$/, Regexp.allocate.inspect)
assert_raise(TypeError) { Regexp.allocate.source }
assert_raise(TypeError) { Regexp.allocate.casefold? }
assert_raise(TypeError) { Regexp.allocate.options }
assert_equal(Encoding.find("ASCII-8BIT"), Regexp.allocate.encoding)
assert_equal(false, Regexp.allocate.fixed_encoding?)
assert_raise(TypeError) { Regexp.allocate.names }
assert_raise(TypeError) { Regexp.allocate.named_captures }
assert_raise(TypeError) { MatchData.allocate.regexp }
assert_raise(TypeError) { MatchData.allocate.names }
assert_raise(TypeError) { MatchData.allocate.size }
assert_raise(TypeError) { MatchData.allocate.length }
assert_raise(TypeError) { MatchData.allocate.offset(0) }
assert_raise(TypeError) { MatchData.allocate.begin(0) }
assert_raise(TypeError) { MatchData.allocate.end(0) }
assert_raise(TypeError) { MatchData.allocate.to_a }
assert_raise(TypeError) { MatchData.allocate[:foo] }
assert_raise(TypeError) { MatchData.allocate.captures }
assert_raise(TypeError) { MatchData.allocate.values_at }
assert_raise(TypeError) { MatchData.allocate.pre_match }
assert_raise(TypeError) { MatchData.allocate.post_match }
assert_raise(TypeError) { MatchData.allocate.to_s }
assert_match(/^#<MatchData:.*>$/, MatchData.allocate.inspect)
assert_raise(TypeError) { MatchData.allocate.string }
$~ = MatchData.allocate
assert_raise(TypeError) { $& }
assert_raise(TypeError) { $` }
assert_raise(TypeError) { $' }
assert_raise(TypeError) { $+ }
end
def test_unicode
assert_match(/^\u3042{0}\p{Any}$/, "a")
assert_match(/^\u3042{0}\p{Any}$/, "\u3041")
assert_match(/^\u3042{0}\p{Any}$/, "\0")
assert_match(/^\p{Lo}{4}$/u, "\u3401\u4E01\u{20001}\u{2A701}")
assert_no_match(/^\u3042{0}\p{Any}$/, "\0\0")
assert_no_match(/^\u3042{0}\p{Any}$/, "")
assert_raise(SyntaxError) { eval('/^\u3042{0}\p{' + "\u3042" + '}$/') }
assert_raise(SyntaxError) { eval('/^\u3042{0}\p{' + 'a' * 1000 + '}$/') }
assert_raise(SyntaxError) { eval('/^\u3042{0}\p{foobarbazqux}$/') }
assert_match(/^(\uff21)(a)\1\2$/i, "\uff21A\uff41a")
assert_no_match(/^(\uff21)\1$/i, "\uff21A")
assert_no_match(/^(\uff41)\1$/i, "\uff41a")
assert_match(/^\u00df$/i, "\u00df")
assert_match(/^\u00df$/i, "ss")
#assert_match(/^(\u00df)\1$/i, "\u00dfss") # this must be bug...
assert_match(/^\u00df{2}$/i, "\u00dfss")
assert_match(/^\u00c5$/i, "\u00c5")
assert_match(/^\u00c5$/i, "\u00e5")
assert_match(/^\u00c5$/i, "\u212b")
assert_match(/^(\u00c5)\1\1$/i, "\u00c5\u00e5\u212b")
assert_match(/^\u0149$/i, "\u0149")
assert_match(/^\u0149$/i, "\u02bcn")
#assert_match(/^(\u0149)\1$/i, "\u0149\u02bcn") # this must be bug...
assert_match(/^\u0149{2}$/i, "\u0149\u02bcn")
assert_match(/^\u0390$/i, "\u0390")
assert_match(/^\u0390$/i, "\u03b9\u0308\u0301")
#assert_match(/^(\u0390)\1$/i, "\u0390\u03b9\u0308\u0301") # this must be bug...
assert_match(/^\u0390{2}$/i, "\u0390\u03b9\u0308\u0301")
assert_match(/^\ufb05$/i, "\ufb05")
assert_match(/^\ufb05$/i, "\ufb06")
assert_match(/^\ufb05$/i, "st")
#assert_match(/^(\ufb05)\1\1$/i, "\ufb05\ufb06st") # this must be bug...
assert_match(/^\ufb05{3}$/i, "\ufb05\ufb06st")
assert_match(/^\u03b9\u0308\u0301$/i, "\u0390")
end
def test_unicode_age
assert_match(/^\p{Age=6.0}$/u, "\u261c")
assert_match(/^\p{Age=1.1}$/u, "\u261c")
assert_no_match(/^\P{age=6.0}$/u, "\u261c")
assert_match(/^\p{age=6.0}$/u, "\u31f6")
assert_match(/^\p{age=3.2}$/u, "\u31f6")
assert_no_match(/^\p{age=3.1}$/u, "\u31f6")
assert_no_match(/^\p{age=3.0}$/u, "\u31f6")
assert_no_match(/^\p{age=1.1}$/u, "\u31f6")
assert_match(/^\p{age=6.0}$/u, "\u2754")
assert_no_match(/^\p{age=5.0}$/u, "\u2754")
assert_no_match(/^\p{age=4.0}$/u, "\u2754")
assert_no_match(/^\p{age=3.0}$/u, "\u2754")
assert_no_match(/^\p{age=2.0}$/u, "\u2754")
assert_no_match(/^\p{age=1.1}$/u, "\u2754")
end
MatchData_A = eval("class MatchData_\u{3042} < MatchData; self; end")
def test_matchdata
a = "haystack".match(/hay/)
b = "haystack".match(/hay/)
assert_equal(a, b, '[ruby-core:24748]')
h = {a => 42}
assert_equal(42, h[b], '[ruby-core:24748]')
assert_match(/#<TestRegexp::MatchData_\u{3042}:/, MatchData_A.allocate.inspect)
end
def test_regexp_poped
assert_nothing_raised { eval("a = 1; /\#{ a }/; a") }
assert_nothing_raised { eval("a = 1; /\#{ a }/o; a") }
end
def test_invalid_fragment
bug2547 = '[ruby-core:27374]'
assert_raise(SyntaxError, bug2547) {eval('/#{"\\\\"}y/')}
end
def test_dup_warn
assert_warning(/duplicated/) { Regexp.new('[\u3042\u3043\u3042]') }
assert_warning(/duplicated/) { Regexp.new('[\u3042\u3043\u3043]') }
assert_warning(/\A\z/) { Regexp.new('[\u3042\u3044\u3043]') }
assert_warning(/\A\z/) { Regexp.new('[\u3042\u3045\u3043]') }
assert_warning(/\A\z/) { Regexp.new('[\u3042\u3045\u3044]') }
assert_warning(/\A\z/) { Regexp.new('[\u3042\u3045\u3043-\u3044]') }
assert_warning(/duplicated/) { Regexp.new('[\u3042\u3045\u3042-\u3043]') }
assert_warning(/duplicated/) { Regexp.new('[\u3042\u3045\u3044-\u3045]') }
assert_warning(/\A\z/) { Regexp.new('[\u3042\u3046\u3044]') }
assert_warning(/duplicated/) { Regexp.new('[\u1000-\u2000\u3042-\u3046\u3044]') }
assert_warning(/duplicated/) { Regexp.new('[\u3044\u3041-\u3047]') }
assert_warning(/duplicated/) { Regexp.new('[\u3042\u3044\u3046\u3041-\u3047]') }
bug7471 = '[ruby-core:50344]'
assert_warning('', bug7471) { Regexp.new('[\D]') =~ "\u3042" }
bug8151 = '[ruby-core:53649]'
assert_warning(/\A\z/, bug8151) { Regexp.new('(?:[\u{33}])').to_s }
end
def test_property_warn
assert_in_out_err('-w', 'x=/\p%s/', [], %r"warning: invalid Unicode Property \\p: /\\p%s/")
end
def test_invalid_escape_error
bug3539 = '[ruby-core:31048]'
error = assert_raise(SyntaxError) {eval('/\x/', nil, bug3539)}
assert_match(/invalid hex escape/, error.message)
assert_equal(1, error.message.scan(/.*invalid .*escape.*/i).size, bug3539)
end
def test_raw_hyphen_and_tk_char_type_after_range
bug6853 = '[ruby-core:47115]'
# use Regexp.new instead of literal to ignore a parser warning.
check(Regexp.new('[0-1-\\s]'), [' ', '-'], ['2', 'a'], bug6853)
end
def test_error_message_on_failed_conversion
bug7539 = '[ruby-core:50733]'
assert_equal false, /x/=== 42
assert_raise_with_message(TypeError, 'no implicit conversion of Fixnum into String', bug7539) {
Regexp.quote(42)
}
end
def test_conditional_expression
bug8583 = '[ruby-dev:47480] [Bug #8583]'
conds = {"xy"=>true, "yx"=>true, "xx"=>false, "yy"=>false}
assert_match_each(/\A((x)|(y))(?(2)y|x)\z/, conds, bug8583)
assert_match_each(/\A((?<x>x)|(?<y>y))(?(<x>)y|x)\z/, conds, bug8583)
end
def test_options_in_look_behind
assert_nothing_raised {
assert_match_at("(?<=(?i)ab)cd", "ABcd", [[2,4]])
assert_match_at("(?<=(?i:ab))cd", "ABcd", [[2,4]])
assert_match_at("(?<!(?i)ab)cd", "aacd", [[2,4]])
assert_match_at("(?<!(?i:ab))cd", "aacd", [[2,4]])
assert_not_match("(?<=(?i)ab)cd", "ABCD")
assert_not_match("(?<=(?i:ab))cd", "ABCD")
assert_not_match("(?<!(?i)ab)cd", "ABcd")
assert_not_match("(?<!(?i:ab))cd", "ABcd")
}
end
def test_once
pr1 = proc{|i| /#{i}/o}
assert_equal(/0/, pr1.call(0))
assert_equal(/0/, pr1.call(1))
assert_equal(/0/, pr1.call(2))
end
def test_once_recursive
pr2 = proc{|i|
if i > 0
/#{pr2.call(i-1).to_s}#{i}/
else
//
end
}
assert_equal(/(?-mix:(?-mix:(?-mix:)1)2)3/, pr2.call(3))
end
def test_once_multithread
m = Mutex.new
pr3 = proc{|i|
/#{m.unlock; sleep 0.5; i}/o
}
ary = []
n = 0
th1 = Thread.new{m.lock; ary << pr3.call(n+=1)}
th2 = Thread.new{m.lock; ary << pr3.call(n+=1)}
th1.join; th2.join
assert_equal([/1/, /1/], ary)
end
def test_once_escape
pr4 = proc{|i|
catch(:xyzzy){
/#{throw :xyzzy, i}/o =~ ""
:ng
}
}
assert_equal(0, pr4.call(0))
assert_equal(1, pr4.call(1))
end
def test_eq_tilde_can_be_overridden
assert_separately([], <<-RUBY)
class Regexp
undef =~
def =~(str)
"foo"
end
end
assert_equal("foo", // =~ "")
RUBY
end
# This assertion is for porting x2() tests in testpy.py of Onigmo.
def assert_match_at(re, str, positions, msg = nil)
re = Regexp.new(re) unless re.is_a?(Regexp)
match = re.match(str)
assert_not_nil match, message(msg) {
"Expected #{re.inspect} to match #{str.inspect}"
}
if match
actual_positions = (0...match.size).map { |i|
[match.begin(i), match.end(i)]
}
assert_equal positions, actual_positions, message(msg) {
"Expected #{re.inspect} to match #{str.inspect} at: #{positions.inspect}"
}
end
end
def assert_match_each(re, conds, msg = nil)
errs = conds.select {|str, match| match ^ (re =~ str)}
msg = message(msg) {
"Expected #{re.inspect} to\n" +
errs.map {|str, match| "\t#{'not ' unless match}match #{str.inspect}"}.join(",\n")
}
assert_empty(errs, msg)
end
end