# This set of tests checks the API, internals, and non-Perl stuff for UTF
# support, including Unicode properties. However, tests that give different
# results in 8-bit, 16-bit, and 32-bit modes are excluded (see tests 10 and
# 12).
#newline_default lf any anycrlf
# PCRE2 and Perl disagree about the characteristics of certain Unicode
# characters. For example, 061C was considered by Perl to be Arabic, though
# it was not listed as such in the Unicode Scripts.txt file for Unicode 8.
# However, it *is* in that file for Unicode 10, but when I came to re-check,
# Perl had changed in the meantime, with 5.026 not recognizing it as Arabic.
# 2066-2069 are graphic and printable according to Perl, though they are
# actually "isolate" control characters. That is why the following tests are
# here rather than in test 4.
/^[\p{Arabic}]/utf
\x{061c}
0: \x{61c}
/^[[:graph:]]+$/utf,ucp
\= Expect no match
\x{61c}
No match
\x{2066}
No match
\x{2067}
No match
\x{2068}
No match
\x{2069}
No match
/^[[:print:]]+$/utf,ucp
\= Expect no match
\x{61c}
No match
\x{2066}
No match
\x{2067}
No match
\x{2068}
No match
\x{2069}
No match
/^[[:^graph:]]+$/utf,ucp
\x{09}\x{0a}\x{1D}\x{20}\x{85}\x{a0}\x{61c}\x{1680}
0: \x{09}\x{0a}\x{1d} \x{85}\x{a0}\x{61c}\x{1680}
\x{2028}\x{2029}\x{202f}\x{2065}\x{2066}\x{2067}\x{2068}\x{2069}
0: \x{2028}\x{2029}\x{202f}\x{2065}\x{2066}\x{2067}\x{2068}\x{2069}
/^[[:^print:]]+$/utf,ucp
\x{09}\x{1D}\x{85}\x{61c}\x{2028}\x{2029}\x{2065}\x{2066}\x{2067}
0: \x{09}\x{1d}\x{85}\x{61c}\x{2028}\x{2029}\x{2065}\x{2066}\x{2067}
\x{2068}\x{2069}
0: \x{2068}\x{2069}
# Perl does not consider U+180e to be a space character. It is true that it
# does not appear in the Unicode PropList.txt file as such, but in many other
# sources it is listed as a space, and has been treated as such in PCRE for
# a long time.
/^>[[:blank:]]*/utf,ucp
>\x{20}\x{a0}\x{1680}\x{180e}\x{2000}\x{202f}\x{9}\x{b}\x{2028}
0: > \x{a0}\x{1680}\x{180e}\x{2000}\x{202f}\x{09}
/^A\s+Z/utf,ucp
A\x{85}\x{180e}\x{2005}Z
0: A\x{85}\x{180e}\x{2005}Z
/^A[\s]+Z/utf,ucp
A\x{2005}Z
0: A\x{2005}Z
A\x{85}\x{2005}Z
0: A\x{85}\x{2005}Z
/^[[:graph:]]+$/utf,ucp
\= Expect no match
\x{180e}
No match
/^[[:print:]]+$/utf,ucp
\x{180e}
0: \x{180e}
/^[[:^graph:]]+$/utf,ucp
\x{09}\x{0a}\x{1D}\x{20}\x{85}\x{a0}\x{61c}\x{1680}\x{180e}
0: \x{09}\x{0a}\x{1d} \x{85}\x{a0}\x{61c}\x{1680}\x{180e}
/^[[:^print:]]+$/utf,ucp
\= Expect no match
\x{180e}
No match
# End of U+180E tests.
# ---------------------------------------------------------------------
/\x{110000}/IB,utf
Failed: error 134 at offset 9: character code point value in \x{} or \o{} is too large
/\o{4200000}/IB,utf
Failed: error 134 at offset 10: character code point value in \x{} or \o{} is too large
/\x{ffffffff}/utf
Failed: error 134 at offset 11: character code point value in \x{} or \o{} is too large
/\o{37777777777}/utf
Failed: error 134 at offset 14: character code point value in \x{} or \o{} is too large
/\x{100000000}/utf
Failed: error 134 at offset 12: character code point value in \x{} or \o{} is too large
/\o{77777777777}/utf
Failed: error 134 at offset 14: character code point value in \x{} or \o{} is too large
/\x{d800}/utf
Failed: error 173 at offset 7: disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
/\o{154000}/utf
Failed: error 173 at offset 9: disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
/\x{dfff}/utf
Failed: error 173 at offset 7: disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
/\o{157777}/utf
Failed: error 173 at offset 9: disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
/\x{d7ff}/utf
/\o{153777}/utf
/\x{e000}/utf
/\o{170000}/utf
/^\x{100}a\x{1234}/utf
\x{100}a\x{1234}bcd
0: \x{100}a\x{1234}
/\x{0041}\x{2262}\x{0391}\x{002e}/IB,utf
------------------------------------------------------------------
Bra
A\x{2262}\x{391}.
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf
First code unit = 'A'
Last code unit = '.'
Subject length lower bound = 4
\x{0041}\x{2262}\x{0391}\x{002e}
0: A\x{2262}\x{391}.
/.{3,5}X/IB,utf
------------------------------------------------------------------
Bra
Any{3}
Any{0,2}
X
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf
Last code unit = 'X'
Subject length lower bound = 4
\x{212ab}\x{212ab}\x{212ab}\x{861}X
0: \x{212ab}\x{212ab}\x{212ab}\x{861}X
/.{3,5}?/IB,utf
------------------------------------------------------------------
Bra
Any{3}
Any{0,2}?
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf
Subject length lower bound = 3
\x{212ab}\x{212ab}\x{212ab}\x{861}
0: \x{212ab}\x{212ab}\x{212ab}
/^[ab]/IB,utf
------------------------------------------------------------------
Bra
^
[ab]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Compile options: utf
Overall options: anchored utf
Starting code units: a b
Subject length lower bound = 1
bar
0: b
\= Expect no match
c
No match
\x{ff}
No match
\x{100}
No match
/\x{100}*(\d+|"(?1)")/utf
1234
0: 1234
1: 1234
"1234"
0: "1234"
1: "1234"
\x{100}1234
0: \x{100}1234
1: 1234
"\x{100}1234"
0: \x{100}1234
1: 1234
\x{100}\x{100}12ab
0: \x{100}\x{100}12
1: 12
\x{100}\x{100}"12"
0: \x{100}\x{100}"12"
1: "12"
\= Expect no match
\x{100}\x{100}abcd
No match
/\x{100}*/IB,utf
------------------------------------------------------------------
Bra
\x{100}*+
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
May match empty string
Options: utf
Subject length lower bound = 0
/a\x{100}*/IB,utf
------------------------------------------------------------------
Bra
a
\x{100}*+
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf
First code unit = 'a'
Subject length lower bound = 1
/ab\x{100}*/IB,utf
------------------------------------------------------------------
Bra
ab
\x{100}*+
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2
/[\x{200}-\x{100}]/utf
Failed: error 108 at offset 15: range out of order in character class
/[Ä-Ä]/utf
\x{100}
0: \x{100}
\x{104}
0: \x{104}
\= Expect no match
\x{105}
No match
\x{ff}
No match
/[\xFF]/IB
------------------------------------------------------------------
Bra
\x{ff}
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
First code unit = \xff
Subject length lower bound = 1
>\xff<
0: \xff
/[^\xFF]/IB
------------------------------------------------------------------
Bra
[^\x{ff}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Subject length lower bound = 1
/[Ã-Ã]/utf
à # Matches without Study
0: \x{d6}
\x{d6}
0: \x{d6}
/[Ã-Ã]/utf
à <-- Same with Study
0: \x{d6}
\x{d6}
0: \x{d6}
/[\x{c4}-\x{dc}]/utf
à # Matches without Study
0: \x{d6}
\x{d6}
0: \x{d6}
/[\x{c4}-\x{dc}]/utf
à <-- Same with Study
0: \x{d6}
\x{d6}
0: \x{d6}
/[^\x{100}]abc(xyz(?1))/IB,utf
------------------------------------------------------------------
Bra
[^\x{100}]
abc
CBra 1
xyz
Recurse
Ket
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 1
Options: utf
Last code unit = 'z'
Subject length lower bound = 7
/(\x{100}(b(?2)c))?/IB,utf
------------------------------------------------------------------
Bra
Brazero
CBra 1
\x{100}
CBra 2
b
Recurse
c
Ket
Ket
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 2
May match empty string
Options: utf
Subject length lower bound = 0
/(\x{100}(b(?2)c)){0,2}/IB,utf
------------------------------------------------------------------
Bra
Brazero
Bra
CBra 1
\x{100}
CBra 2
b
Recurse
c
Ket
Ket
Brazero
CBra 1
\x{100}
CBra 2
b
Recurse
c
Ket
Ket
Ket
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 2
May match empty string
Options: utf
Subject length lower bound = 0
/(\x{100}(b(?1)c))?/IB,utf
------------------------------------------------------------------
Bra
Brazero
CBra 1
\x{100}
CBra 2
b
Recurse
c
Ket
Ket
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 2
May match empty string
Options: utf
Subject length lower bound = 0
/(\x{100}(b(?1)c)){0,2}/IB,utf
------------------------------------------------------------------
Bra
Brazero
Bra
CBra 1
\x{100}
CBra 2
b
Recurse
c
Ket
Ket
Brazero
CBra 1
\x{100}
CBra 2
b
Recurse
c
Ket
Ket
Ket
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 2
May match empty string
Options: utf
Subject length lower bound = 0
/\W/utf
A.B
0: .
A\x{100}B
0: \x{100}
/\w/utf
\x{100}X
0: X
# Use no_start_optimize because the first code unit is different in 8-bit from
# the wider modes.
/^\á´/IB,utf,no_start_optimize
------------------------------------------------------------------
Bra
^
\x{1234}
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Compile options: no_start_optimize utf
Overall options: anchored no_start_optimize utf
Subject length lower bound = 0
/()()()()()()()()()()
()()()()()()()()()()
()()()()()()()()()()
()()()()()()()()()()
A (x) (?41) B/x,utf
AxxB
Matched, but too many substrings
0: AxxB
1:
2:
3:
4:
5:
6:
7:
8:
9:
10:
11:
12:
13:
14:
/^[\x{100}\E-\Q\E\x{150}]/B,utf
------------------------------------------------------------------
Bra
^
[\x{100}-\x{150}]
Ket
End
------------------------------------------------------------------
/^[\QÄ\E-\QÅ\E]/B,utf
------------------------------------------------------------------
Bra
^
[\x{100}-\x{150}]
Ket
End
------------------------------------------------------------------
/^abc./gmx,newline=any,utf
abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK
0: abc1
0: abc2
0: abc3
0: abc4
0: abc5
0: abc6
0: abc7
0: abc8
0: abc9
/abc.$/gmx,newline=any,utf
abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9
0: abc1
0: abc2
0: abc3
0: abc4
0: abc5
0: abc6
0: abc7
0: abc8
0: abc9
/^a\Rb/bsr=unicode,utf
a\nb
0: a\x{0a}b
a\rb
0: a\x{0d}b
a\r\nb
0: a\x{0d}\x{0a}b
a\x0bb
0: a\x{0b}b
a\x0cb
0: a\x{0c}b
a\x{85}b
0: a\x{85}b
a\x{2028}b
0: a\x{2028}b
a\x{2029}b
0: a\x{2029}b
\= Expect no match
a\n\rb
No match
/^a\R*b/bsr=unicode,utf
ab
0: ab
a\nb
0: a\x{0a}b
a\rb
0: a\x{0d}b
a\r\nb
0: a\x{0d}\x{0a}b
a\x0bb
0: a\x{0b}b
a\x0c\x{2028}\x{2029}b
0: a\x{0c}\x{2028}\x{2029}b
a\x{85}b
0: a\x{85}b
a\n\rb
0: a\x{0a}\x{0d}b
a\n\r\x{85}\x0cb
0: a\x{0a}\x{0d}\x{85}\x{0c}b
/^a\R+b/bsr=unicode,utf
a\nb
0: a\x{0a}b
a\rb
0: a\x{0d}b
a\r\nb
0: a\x{0d}\x{0a}b
a\x0bb
0: a\x{0b}b
a\x0c\x{2028}\x{2029}b
0: a\x{0c}\x{2028}\x{2029}b
a\x{85}b
0: a\x{85}b
a\n\rb
0: a\x{0a}\x{0d}b
a\n\r\x{85}\x0cb
0: a\x{0a}\x{0d}\x{85}\x{0c}b
\= Expect no match
ab
No match
/^a\R{1,3}b/bsr=unicode,utf
a\nb
0: a\x{0a}b
a\n\rb
0: a\x{0a}\x{0d}b
a\n\r\x{85}b
0: a\x{0a}\x{0d}\x{85}b
a\r\n\r\nb
0: a\x{0d}\x{0a}\x{0d}\x{0a}b
a\r\n\r\n\r\nb
0: a\x{0d}\x{0a}\x{0d}\x{0a}\x{0d}\x{0a}b
a\n\r\n\rb
0: a\x{0a}\x{0d}\x{0a}\x{0d}b
a\n\n\r\nb
0: a\x{0a}\x{0a}\x{0d}\x{0a}b
\= Expect no match
a\n\n\n\rb
No match
a\r
No match
/\H\h\V\v/utf
X X\x0a
0: X X\x{0a}
X\x09X\x0b
0: X\x{09}X\x{0b}
\= Expect no match
\x{a0} X\x0a
No match
/\H*\h+\V?\v{3,4}/utf
\x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d}
\x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a
0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}\x{0d}
\x09\x20\x{a0}\x0a\x0b\x0c
0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}
\= Expect no match
\x09\x20\x{a0}\x0a\x0b
No match
/\H\h\V\v/utf
\x{3001}\x{3000}\x{2030}\x{2028}
0: \x{3001}\x{3000}\x{2030}\x{2028}
X\x{180e}X\x{85}
0: X\x{180e}X\x{85}
\= Expect no match
\x{2009} X\x0a
No match
/\H*\h+\V?\v{3,4}/utf
\x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a
0: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}\x{0d}
\x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a
0: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}\x{2028}
\x09\x20\x{202f}\x0a\x0b\x0c
0: \x{09} \x{202f}\x{0a}\x{0b}\x{0c}
\= Expect no match
\x09\x{200a}\x{a0}\x{2028}\x0b
No match
/[\h]/B,utf
------------------------------------------------------------------
Bra
[\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}]
Ket
End
------------------------------------------------------------------
>\x{1680}
0: \x{1680}
/[\h]{3,}/B,utf
------------------------------------------------------------------
Bra
[\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}]{3,}+
Ket
End
------------------------------------------------------------------
>\x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}<
0: \x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}
/[\v]/B,utf
------------------------------------------------------------------
Bra
[\x0a-\x0d\x85\x{2028}-\x{2029}]
Ket
End
------------------------------------------------------------------
/[\H]/B,utf
------------------------------------------------------------------
Bra
[\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff\x{100}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{10ffff}]
Ket
End
------------------------------------------------------------------
/[\V]/B,utf
------------------------------------------------------------------
Bra
[\x00-\x09\x0e-\x84\x86-\xff\x{100}-\x{2027}\x{202a}-\x{10ffff}]
Ket
End
------------------------------------------------------------------
/.*$/newline=any,utf
\x{1ec5}
0: \x{1ec5}
/a\Rb/I,bsr=anycrlf,utf
Capturing subpattern count = 0
Options: utf
\R matches CR, LF, or CRLF
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 3
a\rb
0: a\x{0d}b
a\nb
0: a\x{0a}b
a\r\nb
0: a\x{0d}\x{0a}b
\= Expect no match
a\x{85}b
No match
a\x0bb
No match
/a\Rb/I,bsr=unicode,utf
Capturing subpattern count = 0
Options: utf
\R matches any Unicode newline
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 3
a\rb
0: a\x{0d}b
a\nb
0: a\x{0a}b
a\r\nb
0: a\x{0d}\x{0a}b
a\x{85}b
0: a\x{85}b
a\x0bb
0: a\x{0b}b
/a\R?b/I,bsr=anycrlf,utf
Capturing subpattern count = 0
Options: utf
\R matches CR, LF, or CRLF
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2
a\rb
0: a\x{0d}b
a\nb
0: a\x{0a}b
a\r\nb
0: a\x{0d}\x{0a}b
\= Expect no match
a\x{85}b
No match
a\x0bb
No match
/a\R?b/I,bsr=unicode,utf
Capturing subpattern count = 0
Options: utf
\R matches any Unicode newline
First code unit = 'a'
Last code unit = 'b'
Subject length lower bound = 2
a\rb
0: a\x{0d}b
a\nb
0: a\x{0a}b
a\r\nb
0: a\x{0d}\x{0a}b
a\x{85}b
0: a\x{85}b
a\x0bb
0: a\x{0b}b
/.*a.*=.b.*/utf,newline=any
QQQ\x{2029}ABCaXYZ=!bPQR
0: ABCaXYZ=!bPQR
\= Expect no match
a\x{2029}b
No match
\x61\xe2\x80\xa9\x62
No match
/[[:a\x{100}b:]]/utf
Failed: error 130 at offset 3: unknown POSIX class name
/a[^]b/utf,alt_bsux,allow_empty_class,match_unset_backref
a\x{1234}b
0: a\x{1234}b
a\nb
0: a\x{0a}b
\= Expect no match
ab
No match
/a[^]+b/utf,alt_bsux,allow_empty_class,match_unset_backref
aXb
0: aXb
a\nX\nX\x{1234}b
0: a\x{0a}X\x{0a}X\x{1234}b
\= Expect no match
ab
No match
/(\x{de})\1/
\x{de}\x{de}
0: \xde\xde
1: \xde
/X/newline=any,utf,firstline
A\x{1ec5}ABCXYZ
0: X
/Xa{2,4}b/utf
X\=ps
Partial match: X
Xa\=ps
Partial match: Xa
Xaa\=ps
Partial match: Xaa
Xaaa\=ps
Partial match: Xaaa
Xaaaa\=ps
Partial match: Xaaaa
/Xa{2,4}?b/utf
X\=ps
Partial match: X
Xa\=ps
Partial match: Xa
Xaa\=ps
Partial match: Xaa
Xaaa\=ps
Partial match: Xaaa
Xaaaa\=ps
Partial match: Xaaaa
/Xa{2,4}+b/utf
X\=ps
Partial match: X
Xa\=ps
Partial match: Xa
Xaa\=ps
Partial match: Xaa
Xaaa\=ps
Partial match: Xaaa
Xaaaa\=ps
Partial match: Xaaaa
/X\x{123}{2,4}b/utf
X\=ps
Partial match: X
X\x{123}\=ps
Partial match: X\x{123}
X\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}
X\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}
X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}\x{123}
/X\x{123}{2,4}?b/utf
X\=ps
Partial match: X
X\x{123}\=ps
Partial match: X\x{123}
X\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}
X\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}
X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}\x{123}
/X\x{123}{2,4}+b/utf
X\=ps
Partial match: X
X\x{123}\=ps
Partial match: X\x{123}
X\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}
X\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}
X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}\x{123}
/X\x{123}{2,4}b/utf
\= Expect no match
Xx\=ps
No match
X\x{123}x\=ps
No match
X\x{123}\x{123}x\=ps
No match
X\x{123}\x{123}\x{123}x\=ps
No match
X\x{123}\x{123}\x{123}\x{123}x\=ps
No match
/X\x{123}{2,4}?b/utf
\= Expect no match
Xx\=ps
No match
X\x{123}x\=ps
No match
X\x{123}\x{123}x\=ps
No match
X\x{123}\x{123}\x{123}x\=ps
No match
X\x{123}\x{123}\x{123}\x{123}x\=ps
No match
/X\x{123}{2,4}+b/utf
\= Expect no match
Xx\=ps
No match
X\x{123}x\=ps
No match
X\x{123}\x{123}x\=ps
No match
X\x{123}\x{123}\x{123}x\=ps
No match
X\x{123}\x{123}\x{123}\x{123}x\=ps
No match
/X\d{2,4}b/utf
X\=ps
Partial match: X
X3\=ps
Partial match: X3
X33\=ps
Partial match: X33
X333\=ps
Partial match: X333
X3333\=ps
Partial match: X3333
/X\d{2,4}?b/utf
X\=ps
Partial match: X
X3\=ps
Partial match: X3
X33\=ps
Partial match: X33
X333\=ps
Partial match: X333
X3333\=ps
Partial match: X3333
/X\d{2,4}+b/utf
X\=ps
Partial match: X
X3\=ps
Partial match: X3
X33\=ps
Partial match: X33
X333\=ps
Partial match: X333
X3333\=ps
Partial match: X3333
/X\D{2,4}b/utf
X\=ps
Partial match: X
Xa\=ps
Partial match: Xa
Xaa\=ps
Partial match: Xaa
Xaaa\=ps
Partial match: Xaaa
Xaaaa\=ps
Partial match: Xaaaa
/X\D{2,4}?b/utf
X\=ps
Partial match: X
Xa\=ps
Partial match: Xa
Xaa\=ps
Partial match: Xaa
Xaaa\=ps
Partial match: Xaaa
Xaaaa\=ps
Partial match: Xaaaa
/X\D{2,4}+b/utf
X\=ps
Partial match: X
Xa\=ps
Partial match: Xa
Xaa\=ps
Partial match: Xaa
Xaaa\=ps
Partial match: Xaaa
Xaaaa\=ps
Partial match: Xaaaa
/X\D{2,4}b/utf
X\=ps
Partial match: X
X\x{123}\=ps
Partial match: X\x{123}
X\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}
X\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}
X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}\x{123}
/X\D{2,4}?b/utf
X\=ps
Partial match: X
X\x{123}\=ps
Partial match: X\x{123}
X\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}
X\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}
X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}\x{123}
/X\D{2,4}+b/utf
X\=ps
Partial match: X
X\x{123}\=ps
Partial match: X\x{123}
X\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}
X\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}
X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}\x{123}
/X[abc]{2,4}b/utf
X\=ps
Partial match: X
Xa\=ps
Partial match: Xa
Xaa\=ps
Partial match: Xaa
Xaaa\=ps
Partial match: Xaaa
Xaaaa\=ps
Partial match: Xaaaa
/X[abc]{2,4}?b/utf
X\=ps
Partial match: X
Xa\=ps
Partial match: Xa
Xaa\=ps
Partial match: Xaa
Xaaa\=ps
Partial match: Xaaa
Xaaaa\=ps
Partial match: Xaaaa
/X[abc]{2,4}+b/utf
X\=ps
Partial match: X
Xa\=ps
Partial match: Xa
Xaa\=ps
Partial match: Xaa
Xaaa\=ps
Partial match: Xaaa
Xaaaa\=ps
Partial match: Xaaaa
/X[abc\x{123}]{2,4}b/utf
X\=ps
Partial match: X
X\x{123}\=ps
Partial match: X\x{123}
X\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}
X\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}
X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}\x{123}
/X[abc\x{123}]{2,4}?b/utf
X\=ps
Partial match: X
X\x{123}\=ps
Partial match: X\x{123}
X\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}
X\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}
X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}\x{123}
/X[abc\x{123}]{2,4}+b/utf
X\=ps
Partial match: X
X\x{123}\=ps
Partial match: X\x{123}
X\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}
X\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}
X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}\x{123}
/X[^a]{2,4}b/utf
X\=ps
Partial match: X
Xz\=ps
Partial match: Xz
Xzz\=ps
Partial match: Xzz
Xzzz\=ps
Partial match: Xzzz
Xzzzz\=ps
Partial match: Xzzzz
/X[^a]{2,4}?b/utf
X\=ps
Partial match: X
Xz\=ps
Partial match: Xz
Xzz\=ps
Partial match: Xzz
Xzzz\=ps
Partial match: Xzzz
Xzzzz\=ps
Partial match: Xzzzz
/X[^a]{2,4}+b/utf
X\=ps
Partial match: X
Xz\=ps
Partial match: Xz
Xzz\=ps
Partial match: Xzz
Xzzz\=ps
Partial match: Xzzz
Xzzzz\=ps
Partial match: Xzzzz
/X[^a]{2,4}b/utf
X\=ps
Partial match: X
X\x{123}\=ps
Partial match: X\x{123}
X\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}
X\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}
X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}\x{123}
/X[^a]{2,4}?b/utf
X\=ps
Partial match: X
X\x{123}\=ps
Partial match: X\x{123}
X\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}
X\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}
X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}\x{123}
/X[^a]{2,4}+b/utf
X\=ps
Partial match: X
X\x{123}\=ps
Partial match: X\x{123}
X\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}
X\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}
X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: X\x{123}\x{123}\x{123}\x{123}
/(Y)X\1{2,4}b/utf
YX\=ps
Partial match: YX
YXY\=ps
Partial match: YXY
YXYY\=ps
Partial match: YXYY
YXYYY\=ps
Partial match: YXYYY
YXYYYY\=ps
Partial match: YXYYYY
/(Y)X\1{2,4}?b/utf
YX\=ps
Partial match: YX
YXY\=ps
Partial match: YXY
YXYY\=ps
Partial match: YXYY
YXYYY\=ps
Partial match: YXYYY
YXYYYY\=ps
Partial match: YXYYYY
/(Y)X\1{2,4}+b/utf
YX\=ps
Partial match: YX
YXY\=ps
Partial match: YXY
YXYY\=ps
Partial match: YXYY
YXYYY\=ps
Partial match: YXYYY
YXYYYY\=ps
Partial match: YXYYYY
/(\x{123})X\1{2,4}b/utf
\x{123}X\=ps
Partial match: \x{123}X
\x{123}X\x{123}\=ps
Partial match: \x{123}X\x{123}
\x{123}X\x{123}\x{123}\=ps
Partial match: \x{123}X\x{123}\x{123}
\x{123}X\x{123}\x{123}\x{123}\=ps
Partial match: \x{123}X\x{123}\x{123}\x{123}
\x{123}X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: \x{123}X\x{123}\x{123}\x{123}\x{123}
/(\x{123})X\1{2,4}?b/utf
\x{123}X\=ps
Partial match: \x{123}X
\x{123}X\x{123}\=ps
Partial match: \x{123}X\x{123}
\x{123}X\x{123}\x{123}\=ps
Partial match: \x{123}X\x{123}\x{123}
\x{123}X\x{123}\x{123}\x{123}\=ps
Partial match: \x{123}X\x{123}\x{123}\x{123}
\x{123}X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: \x{123}X\x{123}\x{123}\x{123}\x{123}
/(\x{123})X\1{2,4}+b/utf
\x{123}X\=ps
Partial match: \x{123}X
\x{123}X\x{123}\=ps
Partial match: \x{123}X\x{123}
\x{123}X\x{123}\x{123}\=ps
Partial match: \x{123}X\x{123}\x{123}
\x{123}X\x{123}\x{123}\x{123}\=ps
Partial match: \x{123}X\x{123}\x{123}\x{123}
\x{123}X\x{123}\x{123}\x{123}\x{123}\=ps
Partial match: \x{123}X\x{123}\x{123}\x{123}\x{123}
/\bthe cat\b/utf
the cat\=ps
0: the cat
the cat\=ph
Partial match: the cat
/abcd*/utf
xxxxabcd\=ps
0: abcd
xxxxabcd\=ph
Partial match: abcd
/abcd*/i,utf
xxxxabcd\=ps
0: abcd
xxxxabcd\=ph
Partial match: abcd
XXXXABCD\=ps
0: ABCD
XXXXABCD\=ph
Partial match: ABCD
/abc\d*/utf
xxxxabc1\=ps
0: abc1
xxxxabc1\=ph
Partial match: abc1
/(a)bc\1*/utf
xxxxabca\=ps
0: abca
1: a
xxxxabca\=ph
Partial match: abca
/abc[de]*/utf
xxxxabcde\=ps
0: abcde
xxxxabcde\=ph
Partial match: abcde
/X\W{3}X/utf
X\=ps
Partial match: X
/\sxxx\s/utf,tables=2
AB\x{85}xxx\x{a0}XYZ
0: \x{85}xxx\x{a0}
AB\x{a0}xxx\x{85}XYZ
0: \x{a0}xxx\x{85}
/\S \S/utf,tables=2
\x{a2} \x{84}
0: \x{a2} \x{84}
'A#Ñ
Ñ'Bx,newline=any,utf
------------------------------------------------------------------
Bra
A
Ket
End
------------------------------------------------------------------
'A#Ñ
Ñ
PQ'Bx,newline=any,utf
------------------------------------------------------------------
Bra
APQ
Ket
End
------------------------------------------------------------------
/a+#Ñ
aa
z#XX?/Bx,newline=any,utf
------------------------------------------------------------------
Bra
a++
z
Ket
End
------------------------------------------------------------------
/a+#Ñ
aa
z#Ñ
?/Bx,newline=any,utf
------------------------------------------------------------------
Bra
a++
z
Ket
End
------------------------------------------------------------------
/\g{A}xxx#bXX(?'A'123)
(?'A'456)/Bx,newline=any,utf
------------------------------------------------------------------
Bra
\1
xxx
CBra 1
456
Ket
Ket
End
------------------------------------------------------------------
/\g{A}xxx#bÑ
(?'A'123)
(?'A'456)/Bx,newline=any,utf
------------------------------------------------------------------
Bra
\1
xxx
CBra 1
456
Ket
Ket
End
------------------------------------------------------------------
/^\cģ/utf
Failed: error 168 at offset 3: \c must be followed by a printable ASCII character
/(\R*)(.)/s,utf
\r\n
0: \x{0d}
1:
2: \x{0d}
\r\r\n\n\r
0: \x{0d}\x{0d}\x{0a}\x{0a}\x{0d}
1: \x{0d}\x{0d}\x{0a}\x{0a}
2: \x{0d}
\r\r\n\n\r\n
0: \x{0d}\x{0d}\x{0a}\x{0a}\x{0d}
1: \x{0d}\x{0d}\x{0a}\x{0a}
2: \x{0d}
/(\R)*(.)/s,utf
\r\n
0: \x{0d}
1: <unset>
2: \x{0d}
\r\r\n\n\r
0: \x{0d}\x{0d}\x{0a}\x{0a}\x{0d}
1: \x{0a}
2: \x{0d}
\r\r\n\n\r\n
0: \x{0d}\x{0d}\x{0a}\x{0a}\x{0d}
1: \x{0a}
2: \x{0d}
/[^\x{1234}]+/Ii,utf
Capturing subpattern count = 0
Options: caseless utf
Subject length lower bound = 1
/[^\x{1234}]+?/Ii,utf
Capturing subpattern count = 0
Options: caseless utf
Subject length lower bound = 1
/[^\x{1234}]++/Ii,utf
Capturing subpattern count = 0
Options: caseless utf
Subject length lower bound = 1
/[^\x{1234}]{2}/Ii,utf
Capturing subpattern count = 0
Options: caseless utf
Subject length lower bound = 2
/f.*/
for\=ph
Partial match: for
/f.*/s
for\=ph
Partial match: for
/f.*/utf
for\=ph
Partial match: for
/f.*/s,utf
for\=ph
Partial match: for
/\x{d7ff}\x{e000}/utf
/\x{d800}/utf
Failed: error 173 at offset 7: disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
/\x{dfff}/utf
Failed: error 173 at offset 7: disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
/\h+/utf
\x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000}
0: \x{1680}\x{2000}\x{202f}\x{3000}
\x{3001}\x{2fff}\x{200a}\x{a0}\x{2000}
0: \x{200a}\x{a0}\x{2000}
/[\h\x{e000}]+/B,utf
------------------------------------------------------------------
Bra
[\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}\x{e000}]++
Ket
End
------------------------------------------------------------------
\x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000}
0: \x{1680}\x{2000}\x{202f}\x{3000}
\x{3001}\x{2fff}\x{200a}\x{a0}\x{2000}
0: \x{200a}\x{a0}\x{2000}
/\H+/utf
\x{1680}\x{180e}\x{167f}\x{1681}\x{180d}\x{180f}
0: \x{167f}\x{1681}\x{180d}\x{180f}
\x{2000}\x{200a}\x{1fff}\x{200b}
0: \x{1fff}\x{200b}
\x{202f}\x{205f}\x{202e}\x{2030}\x{205e}\x{2060}
0: \x{202e}\x{2030}\x{205e}\x{2060}
\x{a0}\x{3000}\x{9f}\x{a1}\x{2fff}\x{3001}
0: \x{9f}\x{a1}\x{2fff}\x{3001}
/[\H\x{d7ff}]+/B,utf
------------------------------------------------------------------
Bra
[\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff\x{100}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{10ffff}\x{d7ff}]++
Ket
End
------------------------------------------------------------------
\x{1680}\x{180e}\x{167f}\x{1681}\x{180d}\x{180f}
0: \x{167f}\x{1681}\x{180d}\x{180f}
\x{2000}\x{200a}\x{1fff}\x{200b}
0: \x{1fff}\x{200b}
\x{202f}\x{205f}\x{202e}\x{2030}\x{205e}\x{2060}
0: \x{202e}\x{2030}\x{205e}\x{2060}
\x{a0}\x{3000}\x{9f}\x{a1}\x{2fff}\x{3001}
0: \x{9f}\x{a1}\x{2fff}\x{3001}
/\v+/utf
\x{2027}\x{2030}\x{2028}\x{2029}
0: \x{2028}\x{2029}
\x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d
0: \x{85}\x{0a}\x{0b}\x{0c}\x{0d}
/[\v\x{e000}]+/B,utf
------------------------------------------------------------------
Bra
[\x0a-\x0d\x85\x{2028}-\x{2029}\x{e000}]++
Ket
End
------------------------------------------------------------------
\x{2027}\x{2030}\x{2028}\x{2029}
0: \x{2028}\x{2029}
\x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d
0: \x{85}\x{0a}\x{0b}\x{0c}\x{0d}
/\V+/utf
\x{2028}\x{2029}\x{2027}\x{2030}
0: \x{2027}\x{2030}
\x{85}\x0a\x0b\x0c\x0d\x09\x0e\x{84}\x{86}
0: \x{09}\x{0e}\x{84}\x{86}
/[\V\x{d7ff}]+/B,utf
------------------------------------------------------------------
Bra
[\x00-\x09\x0e-\x84\x86-\xff\x{100}-\x{2027}\x{202a}-\x{10ffff}\x{d7ff}]++
Ket
End
------------------------------------------------------------------
\x{2028}\x{2029}\x{2027}\x{2030}
0: \x{2027}\x{2030}
\x{85}\x0a\x0b\x0c\x0d\x09\x0e\x{84}\x{86}
0: \x{09}\x{0e}\x{84}\x{86}
/\R+/bsr=unicode,utf
\x{2027}\x{2030}\x{2028}\x{2029}
0: \x{2028}\x{2029}
\x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d
0: \x{85}\x{0a}\x{0b}\x{0c}\x{0d}
/(..)\1/utf
ab\=ps
Partial match: ab
aba\=ps
Partial match: aba
abab\=ps
0: abab
1: ab
/(..)\1/i,utf
ab\=ps
Partial match: ab
abA\=ps
Partial match: abA
aBAb\=ps
0: aBAb
1: aB
/(..)\1{2,}/utf
ab\=ps
Partial match: ab
aba\=ps
Partial match: aba
abab\=ps
Partial match: abab
ababa\=ps
Partial match: ababa
ababab\=ps
0: ababab
1: ab
ababab\=ph
Partial match: ababab
abababa\=ps
0: ababab
1: ab
abababa\=ph
Partial match: abababa
/(..)\1{2,}/i,utf
ab\=ps
Partial match: ab
aBa\=ps
Partial match: aBa
aBAb\=ps
Partial match: aBAb
AbaBA\=ps
Partial match: AbaBA
abABAb\=ps
0: abABAb
1: ab
aBAbaB\=ph
Partial match: aBAbaB
abABabA\=ps
0: abABab
1: ab
abaBABa\=ph
Partial match: abaBABa
/(..)\1{2,}?x/i,utf
ab\=ps
Partial match: ab
abA\=ps
Partial match: abA
aBAb\=ps
Partial match: aBAb
abaBA\=ps
Partial match: abaBA
abAbaB\=ps
Partial match: abAbaB
abaBabA\=ps
Partial match: abaBabA
abAbABaBx\=ps
0: abAbABaBx
1: ab
/./utf,newline=crlf
\r\=ps
0: \x{0d}
\r\=ph
Partial match: \x{0d}
/.{2,3}/utf,newline=crlf
\r\=ps
Partial match: \x{0d}
\r\=ph
Partial match: \x{0d}
\r\r\=ps
0: \x{0d}\x{0d}
\r\r\=ph
Partial match: \x{0d}\x{0d}
\r\r\r\=ps
0: \x{0d}\x{0d}\x{0d}
\r\r\r\=ph
Partial match: \x{0d}\x{0d}\x{0d}
/.{2,3}?/utf,newline=crlf
\r\=ps
Partial match: \x{0d}
\r\=ph
Partial match: \x{0d}
\r\r\=ps
0: \x{0d}\x{0d}
\r\r\=ph
Partial match: \x{0d}\x{0d}
\r\r\r\=ps
0: \x{0d}\x{0d}
\r\r\r\=ph
0: \x{0d}\x{0d}
/[^\x{100}][^\x{1234}][^\x{ffff}][^\x{10000}][^\x{10ffff}]/B,utf
------------------------------------------------------------------
Bra
[^\x{100}]
[^\x{1234}]
[^\x{ffff}]
[^\x{10000}]
[^\x{10ffff}]
Ket
End
------------------------------------------------------------------
/[^\x{100}][^\x{1234}][^\x{ffff}][^\x{10000}][^\x{10ffff}]/Bi,utf
------------------------------------------------------------------
Bra
/i [^\x{100}]
/i [^\x{1234}]
/i [^\x{ffff}]
/i [^\x{10000}]
/i [^\x{10ffff}]
Ket
End
------------------------------------------------------------------
/[^\x{100}]*[^\x{10000}]+[^\x{10ffff}]??[^\x{8000}]{4,}[^\x{7fff}]{2,9}?[^\x{fffff}]{5,6}+/B,utf
------------------------------------------------------------------
Bra
[^\x{100}]*
[^\x{10000}]+
[^\x{10ffff}]??
[^\x{8000}]{4}
[^\x{8000}]*
[^\x{7fff}]{2}
[^\x{7fff}]{0,7}?
[^\x{fffff}]{5}
[^\x{fffff}]?+
Ket
End
------------------------------------------------------------------
/[^\x{100}]*[^\x{10000}]+[^\x{10ffff}]??[^\x{8000}]{4,}[^\x{7fff}]{2,9}?[^\x{fffff}]{5,6}+/Bi,utf
------------------------------------------------------------------
Bra
/i [^\x{100}]*
/i [^\x{10000}]+
/i [^\x{10ffff}]??
/i [^\x{8000}]{4}
/i [^\x{8000}]*
/i [^\x{7fff}]{2}
/i [^\x{7fff}]{0,7}?
/i [^\x{fffff}]{5}
/i [^\x{fffff}]?+
Ket
End
------------------------------------------------------------------
/(?<=\x{1234}\x{1234})\bxy/I,utf
Capturing subpattern count = 0
Max lookbehind = 2
Options: utf
First code unit = 'x'
Last code unit = 'y'
Subject length lower bound = 2
/(?<!^)ETA/utf
\= Expect no match
ETA
No match
/\u0100/B,utf,alt_bsux,allow_empty_class,match_unset_backref
------------------------------------------------------------------
Bra
\x{100}
Ket
End
------------------------------------------------------------------
/[\u0100-\u0200]/B,utf,alt_bsux,allow_empty_class,match_unset_backref
------------------------------------------------------------------
Bra
[\x{100}-\x{200}]
Ket
End
------------------------------------------------------------------
/\ud800/utf,alt_bsux,allow_empty_class,match_unset_backref
Failed: error 173 at offset 6: disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
/^a+[a\x{200}]/B,utf
------------------------------------------------------------------
Bra
^
a+
[a\x{200}]
Ket
End
------------------------------------------------------------------
aa
0: aa
/[b-d\x{200}-\x{250}]*[ae-h]?#[\x{200}-\x{250}]{0,8}[\x00-\xff]*#[\x{200}-\x{250}]+[a-z]/B,utf
------------------------------------------------------------------
Bra
[b-d\x{200}-\x{250}]*+
[ae-h]?+
#
[\x{200}-\x{250}]{0,8}+
[\x00-\xff]*
#
[\x{200}-\x{250}]++
[a-z]
Ket
End
------------------------------------------------------------------
/[\p{L}]/IB
------------------------------------------------------------------
Bra
[\p{L}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Subject length lower bound = 1
/[\p{^L}]/IB
------------------------------------------------------------------
Bra
[\P{L}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Subject length lower bound = 1
/[\P{L}]/IB
------------------------------------------------------------------
Bra
[\P{L}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Subject length lower bound = 1
/[\P{^L}]/IB
------------------------------------------------------------------
Bra
[\p{L}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Subject length lower bound = 1
/[abc\p{L}\x{0660}]/IB,utf
------------------------------------------------------------------
Bra
[a-c\p{L}\x{660}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf
Subject length lower bound = 1
/[\p{Nd}]/IB,utf
------------------------------------------------------------------
Bra
[\p{Nd}]
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf
Subject length lower bound = 1
1234
0: 1
/[\p{Nd}+-]+/IB,utf
------------------------------------------------------------------
Bra
[+\-\p{Nd}]++
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: utf
Subject length lower bound = 1
1234
0: 1234
12-34
0: 12-34
12+\x{661}-34
0: 12+\x{661}-34
\= Expect no match
abcd
No match
/(?:[\PPa*]*){8,}/
/[\P{Any}]/B
------------------------------------------------------------------
Bra
[\P{Any}]
Ket
End
------------------------------------------------------------------
/[\P{Any}\E]/B
------------------------------------------------------------------
Bra
[\P{Any}]
Ket
End
------------------------------------------------------------------
/(\P{Yi}+\277)/
/(\P{Yi}+\277)?/
/(?<=\P{Yi}{3}A)X/
/\p{Yi}+(\P{Yi}+)(?1)/
/(\P{Yi}{2}\277)?/
/[\P{Yi}A]/
/[\P{Yi}\P{Yi}\P{Yi}A]/
/[^\P{Yi}A]/
/[^\P{Yi}\P{Yi}\P{Yi}A]/
/(\P{Yi}*\277)*/
/(\P{Yi}*?\277)*/
/(\p{Yi}*+\277)*/
/(\P{Yi}?\277)*/
/(\P{Yi}??\277)*/
/(\p{Yi}?+\277)*/
/(\P{Yi}{0,3}\277)*/
/(\P{Yi}{0,3}?\277)*/
/(\p{Yi}{0,3}+\277)*/
/\p{Zl}{2,3}+/B,utf
------------------------------------------------------------------
Bra
prop Zl {2}
prop Zl ?+
Ket
End
------------------------------------------------------------------
â¨â¨
0: \x{2028}\x{2028}
\x{2028}\x{2028}\x{2028}
0: \x{2028}\x{2028}\x{2028}
/\p{Zl}/B,utf
------------------------------------------------------------------
Bra
prop Zl
Ket
End
------------------------------------------------------------------
/\p{Lu}{3}+/B,utf
------------------------------------------------------------------
Bra
prop Lu {3}
Ket
End
------------------------------------------------------------------
/\pL{2}+/B,utf
------------------------------------------------------------------
Bra
prop L {2}
Ket
End
------------------------------------------------------------------
/\p{Cc}{2}+/B,utf
------------------------------------------------------------------
Bra
prop Cc {2}
Ket
End
------------------------------------------------------------------
/^\p{Cf}/utf
\x{180e}
0: \x{180e}
\x{061c}
0: \x{61c}
\x{2066}
0: \x{2066}
\x{2067}
0: \x{2067}
\x{2068}
0: \x{2068}
\x{2069}
0: \x{2069}
/^\p{Cs}/utf
\x{dfff}\=no_utf_check
0: \x{dfff}
\= Expect no match
\x{09f}
No match
/^\p{Mn}/utf
\x{1a1b}
0: \x{1a1b}
/^\p{Pe}/utf
\x{2309}
0: \x{2309}
\x{230b}
0: \x{230b}
/^\p{Ps}/utf
\x{2308}
0: \x{2308}
\x{230a}
0: \x{230a}
/^\p{Sc}+/utf
$\x{a2}\x{a3}\x{a4}\x{a5}\x{a6}
0: $\x{a2}\x{a3}\x{a4}\x{a5}
\x{9f2}
0: \x{9f2}
\= Expect no match
X
No match
\x{2c2}
No match
/^\p{Zs}/utf
\ \
0:
\x{a0}
0: \x{a0}
\x{1680}
0: \x{1680}
\x{2000}
0: \x{2000}
\x{2001}
0: \x{2001}
\= Expect no match
\x{2028}
No match
\x{200d}
No match
# These are here because Perl has problems with the negative versions of the
# properties and has changed how it behaves for caseless matching.
/\p{^Lu}/i,utf
1234
0: 1
\= Expect no match
ABC
No match
/\P{Lu}/i,utf
1234
0: 1
\= Expect no match
ABC
No match
/\p{Ll}/i,utf
a
0: a
Az
0: z
\= Expect no match
ABC
No match
/\p{Lu}/i,utf
A
0: A
a\x{10a0}B
0: \x{10a0}
\= Expect no match
a
No match
\x{1d00}
No match
/\p{Lu}/i,utf
A
0: A
aZ
0: Z
\= Expect no match
abc
No match
/[\x{c0}\x{391}]/i,utf
\x{c0}
0: \x{c0}
\x{e0}
0: \x{e0}
# The next two are special cases where the lengths of the different cases of
# the same character differ. The first went wrong with heap frame storage; the
# second was broken in all cases.
/^\x{023a}+?(\x{0130}+)/i,utf
\x{023a}\x{2c65}\x{0130}
0: \x{23a}\x{2c65}\x{130}
1: \x{130}
/^\x{023a}+([^X])/i,utf
\x{023a}\x{2c65}X
0: \x{23a}\x{2c65}
1: \x{2c65}
/\x{c0}+\x{116}+/i,utf
\x{c0}\x{e0}\x{116}\x{117}
0: \x{c0}\x{e0}\x{116}\x{117}
/[\x{c0}\x{116}]+/i,utf
\x{c0}\x{e0}\x{116}\x{117}
0: \x{c0}\x{e0}\x{116}\x{117}
/(\x{de})\1/i,utf
\x{de}\x{de}
0: \x{de}\x{de}
1: \x{de}
\x{de}\x{fe}
0: \x{de}\x{fe}
1: \x{de}
\x{fe}\x{fe}
0: \x{fe}\x{fe}
1: \x{fe}
\x{fe}\x{de}
0: \x{fe}\x{de}
1: \x{fe}
/^\x{c0}$/i,utf
\x{c0}
0: \x{c0}
\x{e0}
0: \x{e0}
/^\x{e0}$/i,utf
\x{c0}
0: \x{c0}
\x{e0}
0: \x{e0}
# The next two should be Perl-compatible, but it fails to match \x{e0}. PCRE
# will match it only with UCP support, because without that it has no notion
# of case for anything other than the ASCII letters.
/((?i)[\x{c0}])/utf
\x{c0}
0: \x{c0}
1: \x{c0}
\x{e0}
0: \x{e0}
1: \x{e0}
/(?i:[\x{c0}])/utf
\x{c0}
0: \x{c0}
\x{e0}
0: \x{e0}
# These are PCRE's extra properties to help with Unicodizing \d etc.
/^\p{Xan}/utf
ABCD
0: A
1234
0: 1
\x{6ca}
0: \x{6ca}
\x{a6c}
0: \x{a6c}
\x{10a7}
0: \x{10a7}
\= Expect no match
_ABC
No match
/^\p{Xan}+/utf
ABCD1234\x{6ca}\x{a6c}\x{10a7}_
0: ABCD1234\x{6ca}\x{a6c}\x{10a7}
\= Expect no match
_ABC
No match
/^\p{Xan}+?/utf
\x{6ca}\x{a6c}\x{10a7}_
0: \x{6ca}
/^\p{Xan}*/utf
ABCD1234\x{6ca}\x{a6c}\x{10a7}_
0: ABCD1234\x{6ca}\x{a6c}\x{10a7}
/^\p{Xan}{2,9}/utf
ABCD1234\x{6ca}\x{a6c}\x{10a7}_
0: ABCD1234\x{6ca}
/^\p{Xan}{2,9}?/utf
\x{6ca}\x{a6c}\x{10a7}_
0: \x{6ca}\x{a6c}
/^[\p{Xan}]/utf
ABCD1234_
0: A
1234abcd_
0: 1
\x{6ca}
0: \x{6ca}
\x{a6c}
0: \x{a6c}
\x{10a7}
0: \x{10a7}
\= Expect no match
_ABC
No match
/^[\p{Xan}]+/utf
ABCD1234\x{6ca}\x{a6c}\x{10a7}_
0: ABCD1234\x{6ca}\x{a6c}\x{10a7}
\= Expect no match
_ABC
No match
/^>\p{Xsp}/utf
>\x{1680}\x{2028}\x{0b}
0: >\x{1680}
>\x{a0}
0: >\x{a0}
\= Expect no match
\x{0b}
No match
/^>\p{Xsp}+/utf
> \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
/^>\p{Xsp}+?/utf
>\x{1680}\x{2028}\x{0b}
0: >\x{1680}
/^>\p{Xsp}*/utf
> \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
/^>\p{Xsp}{2,9}/utf
> \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
/^>\p{Xsp}{2,9}?/utf
> \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
0: > \x{09}
/^>[\p{Xsp}]/utf
>\x{2028}\x{0b}
0: >\x{2028}
/^>[\p{Xsp}]+/utf
> \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
/^>\p{Xps}/utf
>\x{1680}\x{2028}\x{0b}
0: >\x{1680}
>\x{a0}
0: >\x{a0}
\= Expect no match
\x{0b}
No match
/^>\p{Xps}+/utf
> \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
/^>\p{Xps}+?/utf
>\x{1680}\x{2028}\x{0b}
0: >\x{1680}
/^>\p{Xps}*/utf
> \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
/^>\p{Xps}{2,9}/utf
> \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
/^>\p{Xps}{2,9}?/utf
> \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
0: > \x{09}
/^>[\p{Xps}]/utf
>\x{2028}\x{0b}
0: >\x{2028}
/^>[\p{Xps}]+/utf
> \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
/^\p{Xwd}/utf
ABCD
0: A
1234
0: 1
\x{6ca}
0: \x{6ca}
\x{a6c}
0: \x{a6c}
\x{10a7}
0: \x{10a7}
_ABC
0: _
\= Expect no match
[]
No match
/^\p{Xwd}+/utf
ABCD1234\x{6ca}\x{a6c}\x{10a7}_
0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_
/^\p{Xwd}+?/utf
\x{6ca}\x{a6c}\x{10a7}_
0: \x{6ca}
/^\p{Xwd}*/utf
ABCD1234\x{6ca}\x{a6c}\x{10a7}_
0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_
/^\p{Xwd}{2,9}/utf
A_B12\x{6ca}\x{a6c}\x{10a7}
0: A_B12\x{6ca}\x{a6c}\x{10a7}
/^\p{Xwd}{2,9}?/utf
\x{6ca}\x{a6c}\x{10a7}_
0: \x{6ca}\x{a6c}
/^[\p{Xwd}]/utf
ABCD1234_
0: A
1234abcd_
0: 1
\x{6ca}
0: \x{6ca}
\x{a6c}
0: \x{a6c}
\x{10a7}
0: \x{10a7}
_ABC
0: _
\= Expect no match
[]
No match
/^[\p{Xwd}]+/utf
ABCD1234\x{6ca}\x{a6c}\x{10a7}_
0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_
# A check not in UTF-8 mode
/^[\p{Xwd}]+/
ABCD1234_
0: ABCD1234_
# Some negative checks
/^[\P{Xwd}]+/utf
!.+\x{019}\x{35a}AB
0: !.+\x{19}\x{35a}
/^[\p{^Xwd}]+/utf
!.+\x{019}\x{35a}AB
0: !.+\x{19}\x{35a}
/[\D]/B,utf,ucp
------------------------------------------------------------------
Bra
[\P{Nd}]
Ket
End
------------------------------------------------------------------
1\x{3c8}2
0: \x{3c8}
/[\d]/B,utf,ucp
------------------------------------------------------------------
Bra
[\p{Nd}]
Ket
End
------------------------------------------------------------------
>\x{6f4}<
0: \x{6f4}
/[\S]/B,utf,ucp
------------------------------------------------------------------
Bra
[\P{Xsp}]
Ket
End
------------------------------------------------------------------
\x{1680}\x{6f4}\x{1680}
0: \x{6f4}
/[\s]/B,utf,ucp
------------------------------------------------------------------
Bra
[\p{Xsp}]
Ket
End
------------------------------------------------------------------
>\x{1680}<
0: \x{1680}
/[\W]/B,utf,ucp
------------------------------------------------------------------
Bra
[\P{Xwd}]
Ket
End
------------------------------------------------------------------
A\x{1712}B
0: \x{1712}
/[\w]/B,utf,ucp
------------------------------------------------------------------
Bra
[\p{Xwd}]
Ket
End
------------------------------------------------------------------
>\x{1723}<
0: \x{1723}
/\D/B,utf,ucp
------------------------------------------------------------------
Bra
notprop Nd
Ket
End
------------------------------------------------------------------
1\x{3c8}2
0: \x{3c8}
/\d/B,utf,ucp
------------------------------------------------------------------
Bra
prop Nd
Ket
End
------------------------------------------------------------------
>\x{6f4}<
0: \x{6f4}
/\S/B,utf,ucp
------------------------------------------------------------------
Bra
notprop Xsp
Ket
End
------------------------------------------------------------------
\x{1680}\x{6f4}\x{1680}
0: \x{6f4}
/\s/B,utf,ucp
------------------------------------------------------------------
Bra
prop Xsp
Ket
End
------------------------------------------------------------------
>\x{1680}>
0: \x{1680}
/\W/B,utf,ucp
------------------------------------------------------------------
Bra
notprop Xwd
Ket
End
------------------------------------------------------------------
A\x{1712}B
0: \x{1712}
/\w/B,utf,ucp
------------------------------------------------------------------
Bra
prop Xwd
Ket
End
------------------------------------------------------------------
>\x{1723}<
0: \x{1723}
/[[:alpha:]]/B,ucp
------------------------------------------------------------------
Bra
[\p{L}]
Ket
End
------------------------------------------------------------------
/[[:lower:]]/B,ucp
------------------------------------------------------------------
Bra
[\p{Ll}]
Ket
End
------------------------------------------------------------------
/[[:upper:]]/B,ucp
------------------------------------------------------------------
Bra
[\p{Lu}]
Ket
End
------------------------------------------------------------------
/[[:alnum:]]/B,ucp
------------------------------------------------------------------
Bra
[\p{Xan}]
Ket
End
------------------------------------------------------------------
/[[:ascii:]]/B,ucp
------------------------------------------------------------------
Bra
[\x00-\x7f]
Ket
End
------------------------------------------------------------------
/[[:cntrl:]]/B,ucp
------------------------------------------------------------------
Bra
[\p{Cc}]
Ket
End
------------------------------------------------------------------
/[[:digit:]]/B,ucp
------------------------------------------------------------------
Bra
[\p{Nd}]
Ket
End
------------------------------------------------------------------
/[[:graph:]]/B,ucp
------------------------------------------------------------------
Bra
[[:graph:]]
Ket
End
------------------------------------------------------------------
/[[:print:]]/B,ucp
------------------------------------------------------------------
Bra
[[:print:]]
Ket
End
------------------------------------------------------------------
/[[:punct:]]/B,ucp
------------------------------------------------------------------
Bra
[[:punct:]]
Ket
End
------------------------------------------------------------------
/[[:space:]]/B,ucp
------------------------------------------------------------------
Bra
[\p{Xps}]
Ket
End
------------------------------------------------------------------
/[[:word:]]/B,ucp
------------------------------------------------------------------
Bra
[\p{Xwd}]
Ket
End
------------------------------------------------------------------
/[[:xdigit:]]/B,ucp
------------------------------------------------------------------
Bra
[0-9A-Fa-f]
Ket
End
------------------------------------------------------------------
# Unicode properties for \b abd \B
/\b...\B/utf,ucp
abc_
0: abc
\x{37e}abc\x{376}
0: abc
\x{37e}\x{376}\x{371}\x{393}\x{394}
0: \x{376}\x{371}\x{393}
!\x{c0}++\x{c1}\x{c2}
0: ++\x{c1}
!\x{c0}+++++
0: \x{c0}++
# Without PCRE_UCP, non-ASCII always fail, even if < 256
/\b...\B/utf
abc_
0: abc
\= Expect no match
\x{37e}abc\x{376}
No match
\x{37e}\x{376}\x{371}\x{393}\x{394}
No match
!\x{c0}++\x{c1}\x{c2}
No match
!\x{c0}+++++
No match
# With PCRE_UCP, non-UTF8 chars that are < 256 still check properties
/\b...\B/ucp
abc_
0: abc
!\x{c0}++\x{c1}\x{c2}
0: ++\xc1
!\x{c0}+++++
0: \xc0++
# Some of these are silly, but they check various combinations
/[[:^alpha:][:^cntrl:]]+/B,utf,ucp
------------------------------------------------------------------
Bra
[\P{L}\P{Cc}]++
Ket
End
------------------------------------------------------------------
123
0: 123
abc
0: abc
/[[:^cntrl:][:^alpha:]]+/B,utf,ucp
------------------------------------------------------------------
Bra
[\P{Cc}\P{L}]++
Ket
End
------------------------------------------------------------------
123
0: 123
abc
0: abc
/[[:alpha:]]+/B,utf,ucp
------------------------------------------------------------------
Bra
[\p{L}]++
Ket
End
------------------------------------------------------------------
abc
0: abc
/[[:^alpha:]\S]+/B,utf,ucp
------------------------------------------------------------------
Bra
[\P{L}\P{Xsp}]++
Ket
End
------------------------------------------------------------------
123
0: 123
abc
0: abc
/[^\d]+/B,utf,ucp
------------------------------------------------------------------
Bra
[^\p{Nd}]++
Ket
End
------------------------------------------------------------------
abc123
0: abc
abc\x{123}
0: abc\x{123}
\x{660}abc
0: abc
/\p{Lu}+9\p{Lu}+B\p{Lu}+b/B
------------------------------------------------------------------
Bra
prop Lu ++
9
prop Lu +
B
prop Lu ++
b
Ket
End
------------------------------------------------------------------
/\p{^Lu}+9\p{^Lu}+B\p{^Lu}+b/B
------------------------------------------------------------------
Bra
notprop Lu +
9
notprop Lu ++
B
notprop Lu +
b
Ket
End
------------------------------------------------------------------
/\P{Lu}+9\P{Lu}+B\P{Lu}+b/B
------------------------------------------------------------------
Bra
notprop Lu +
9
notprop Lu ++
B
notprop Lu +
b
Ket
End
------------------------------------------------------------------
/\p{Han}+X\p{Greek}+\x{370}/B,utf
------------------------------------------------------------------
Bra
prop Han ++
X
prop Greek +
\x{370}
Ket
End
------------------------------------------------------------------
/\p{Xan}+!\p{Xan}+A/B
------------------------------------------------------------------
Bra
prop Xan ++
!
prop Xan +
A
Ket
End
------------------------------------------------------------------
/\p{Xsp}+!\p{Xsp}\t/B
------------------------------------------------------------------
Bra
prop Xsp ++
!
prop Xsp
\x09
Ket
End
------------------------------------------------------------------
/\p{Xps}+!\p{Xps}\t/B
------------------------------------------------------------------
Bra
prop Xps ++
!
prop Xps
\x09
Ket
End
------------------------------------------------------------------
/\p{Xwd}+!\p{Xwd}_/B
------------------------------------------------------------------
Bra
prop Xwd ++
!
prop Xwd
_
Ket
End
------------------------------------------------------------------
/A+\p{N}A+\dB+\p{N}*B+\d*/B,ucp
------------------------------------------------------------------
Bra
A++
prop N
A++
prop Nd
B+
prop N *+
B++
prop Nd *+
Ket
End
------------------------------------------------------------------
# These behaved oddly in Perl, so they are kept in this test
/(\x{23a}\x{23a}\x{23a})?\1/i,utf
\= Expect no match
\x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}
No match
/(ȺȺȺ)?\1/i,utf
\= Expect no match
ȺȺȺⱥⱥ
No match
/(\x{23a}\x{23a}\x{23a})?\1/i,utf
\x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
1: \x{23a}\x{23a}\x{23a}
/(ȺȺȺ)?\1/i,utf
ȺȺȺⱥⱥⱥ
0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
1: \x{23a}\x{23a}\x{23a}
/(\x{23a}\x{23a}\x{23a})\1/i,utf
\= Expect no match
\x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}
No match
/(ȺȺȺ)\1/i,utf
\= Expect no match
ȺȺȺⱥⱥ
No match
/(\x{23a}\x{23a}\x{23a})\1/i,utf
\x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
1: \x{23a}\x{23a}\x{23a}
/(ȺȺȺ)\1/i,utf
ȺȺȺⱥⱥⱥ
0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
1: \x{23a}\x{23a}\x{23a}
/(\x{2c65}\x{2c65})\1/i,utf
\x{2c65}\x{2c65}\x{23a}\x{23a}
0: \x{2c65}\x{2c65}\x{23a}\x{23a}
1: \x{2c65}\x{2c65}
/(ⱥⱥ)\1/i,utf
ⱥⱥȺȺ
0: \x{2c65}\x{2c65}\x{23a}\x{23a}
1: \x{2c65}\x{2c65}
/(\x{23a}\x{23a}\x{23a})\1Y/i,utf
X\x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}YZ
0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}Y
1: \x{23a}\x{23a}\x{23a}
/(\x{2c65}\x{2c65})\1Y/i,utf
X\x{2c65}\x{2c65}\x{23a}\x{23a}YZ
0: \x{2c65}\x{2c65}\x{23a}\x{23a}Y
1: \x{2c65}\x{2c65}
# These scripts weren't yet in Perl when I added Unicode 6.0.0 to PCRE
/^[\p{Batak}]/utf
\x{1bc0}
0: \x{1bc0}
\x{1bff}
0: \x{1bff}
\= Expect no match
\x{1bf4}
No match
/^[\p{Brahmi}]/utf
\x{11000}
0: \x{11000}
\x{1106f}
0: \x{1106f}
\= Expect no match
\x{1104e}
No match
/^[\p{Mandaic}]/utf
\x{840}
0: \x{840}
\x{85e}
0: \x{85e}
\= Expect no match
\x{85c}
No match
\x{85d}
No match
/(\X*)(.)/s,utf
A\x{300}
0: A
1:
2: A
/^S(\X*)e(\X*)$/utf
SteÌreÌo
0: Ste\x{301}re\x{301}o
1: te\x{301}r
2: \x{301}o
/^\X/utf
ÌreÌo
0: \x{301}
/^a\X41z/alt_bsux,allow_empty_class,match_unset_backref,dupnames
aX41z
0: aX41z
\= Expect no match
aAz
No match
/\X/
a\=ps
0: a
a\=ph
Partial match: a
/\Xa/
aa\=ps
0: aa
aa\=ph
0: aa
/\X{2}/
aa\=ps
0: aa
aa\=ph
Partial match: aa
/\X+a/
a\=ps
Partial match: a
aa\=ps
0: aa
aa\=ph
Partial match: aa
/\X+?a/
a\=ps
Partial match: a
ab\=ps
Partial match: ab
aa\=ps
0: aa
aa\=ph
0: aa
aba\=ps
0: aba
# These Unicode 6.1.0 scripts are not known to Perl.
/\p{Chakma}\d/utf,ucp
\x{11100}\x{1113c}
0: \x{11100}\x{1113c}
/\p{Takri}\d/utf,ucp
\x{11680}\x{116c0}
0: \x{11680}\x{116c0}
/^\X/utf
A\=ps
0: A
A\=ph
Partial match: A
A\x{300}\x{301}\=ps
0: A\x{300}\x{301}
A\x{300}\x{301}\=ph
Partial match: A\x{300}\x{301}
A\x{301}\=ps
0: A\x{301}
A\x{301}\=ph
Partial match: A\x{301}
/^\X{2,3}/utf
A\=ps
Partial match: A
A\=ph
Partial match: A
AA\=ps
0: AA
AA\=ph
Partial match: AA
A\x{300}\x{301}\=ps
Partial match: A\x{300}\x{301}
A\x{300}\x{301}\=ph
Partial match: A\x{300}\x{301}
A\x{300}\x{301}A\x{300}\x{301}\=ps
0: A\x{300}\x{301}A\x{300}\x{301}
A\x{300}\x{301}A\x{300}\x{301}\=ph
Partial match: A\x{300}\x{301}A\x{300}\x{301}
/^\X{2}/utf
AA\=ps
0: AA
AA\=ph
Partial match: AA
A\x{300}\x{301}A\x{300}\x{301}\=ps
0: A\x{300}\x{301}A\x{300}\x{301}
A\x{300}\x{301}A\x{300}\x{301}\=ph
Partial match: A\x{300}\x{301}A\x{300}\x{301}
/^\X+/utf
AA\=ps
0: AA
AA\=ph
Partial match: AA
/^\X+?Z/utf
AA\=ps
Partial match: AA
AA\=ph
Partial match: AA
/A\x{3a3}B/IBi,utf
------------------------------------------------------------------
Bra
/i A
clist 03a3 03c2 03c3
/i B
Ket
End
------------------------------------------------------------------
Capturing subpattern count = 0
Options: caseless utf
First code unit = 'A' (caseless)
Last code unit = 'B' (caseless)
Subject length lower bound = 3
/[\x{3a3}]/Bi,utf
------------------------------------------------------------------
Bra
clist 03a3 03c2 03c3
Ket
End
------------------------------------------------------------------
/[^\x{3a3}]/Bi,utf
------------------------------------------------------------------
Bra
not clist 03a3 03c2 03c3
Ket
End
------------------------------------------------------------------
/[\x{3a3}]+/Bi,utf
------------------------------------------------------------------
Bra
clist 03a3 03c2 03c3 ++
Ket
End
------------------------------------------------------------------
/[^\x{3a3}]+/Bi,utf
------------------------------------------------------------------
Bra
not clist 03a3 03c2 03c3 ++
Ket
End
------------------------------------------------------------------
/a*\x{3a3}/Bi,utf
------------------------------------------------------------------
Bra
/i a*+
clist 03a3 03c2 03c3
Ket
End
------------------------------------------------------------------
/\x{3a3}+a/Bi,utf
------------------------------------------------------------------
Bra
clist 03a3 03c2 03c3 ++
/i a
Ket
End
------------------------------------------------------------------
/\x{3a3}*\x{3c2}/Bi,utf
------------------------------------------------------------------
Bra
clist 03a3 03c2 03c3 *
clist 03a3 03c2 03c3
Ket
End
------------------------------------------------------------------
/\x{3a3}{3}/i,utf,aftertext
\x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2}
0: \x{3a3}\x{3c3}\x{3c2}
0+ \x{3a3}\x{3c3}\x{3c2}
/\x{3a3}{2,4}/i,utf,aftertext
\x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2}
0: \x{3a3}\x{3c3}\x{3c2}\x{3a3}
0+ \x{3c3}\x{3c2}
/\x{3a3}{2,4}?/i,utf,aftertext
\x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2}
0: \x{3a3}\x{3c3}
0+ \x{3c2}\x{3a3}\x{3c3}\x{3c2}
/\x{3a3}+./i,utf,aftertext
\x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2}
0: \x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2}
0+
/\x{3a3}++./i,utf,aftertext
\= Expect no match
\x{3a3}\x{3c3}\x{3c2}\x{3a3}\x{3c3}\x{3c2}
No match
/\x{3a3}*\x{3c2}/Bi,utf
------------------------------------------------------------------
Bra
clist 03a3 03c2 03c3 *
clist 03a3 03c2 03c3
Ket
End
------------------------------------------------------------------
/[^\x{3a3}]*\x{3c2}/Bi,utf
------------------------------------------------------------------
Bra
not clist 03a3 03c2 03c3 *+
clist 03a3 03c2 03c3
Ket
End
------------------------------------------------------------------
/[^a]*\x{3c2}/Bi,utf
------------------------------------------------------------------
Bra
/i [^a]*
clist 03a3 03c2 03c3
Ket
End
------------------------------------------------------------------
/ist/Bi,utf
------------------------------------------------------------------
Bra
/i i
clist 0053 0073 017f
/i t
Ket
End
------------------------------------------------------------------
\= Expect no match
ikt
No match
/is+t/i,utf
iSs\x{17f}t
0: iSs\x{17f}t
\= Expect no match
ikt
No match
/is+?t/i,utf
\= Expect no match
ikt
No match
/is?t/i,utf
\= Expect no match
ikt
No match
/is{2}t/i,utf
\= Expect no match
iskt
No match
# This property is a PCRE special
/^\p{Xuc}/utf
$abc
0: $
@abc
0: @
`abc
0: `
\x{1234}abc
0: \x{1234}
\= Expect no match
abc
No match
/^\p{Xuc}+/utf
$@`\x{a0}\x{1234}\x{e000}**
0: $@`\x{a0}\x{1234}\x{e000}
\= Expect no match
\x{9f}
No match
/^\p{Xuc}+?/utf
$@`\x{a0}\x{1234}\x{e000}**
0: $
\= Expect no match
\x{9f}
No match
/^\p{Xuc}+?\*/utf
$@`\x{a0}\x{1234}\x{e000}**
0: $@`\x{a0}\x{1234}\x{e000}*
\= Expect no match
\x{9f}
No match
/^\p{Xuc}++/utf
$@`\x{a0}\x{1234}\x{e000}**
0: $@`\x{a0}\x{1234}\x{e000}
\= Expect no match
\x{9f}
No match
/^\p{Xuc}{3,5}/utf
$@`\x{a0}\x{1234}\x{e000}**
0: $@`\x{a0}\x{1234}
\= Expect no match
\x{9f}
No match
/^\p{Xuc}{3,5}?/utf
$@`\x{a0}\x{1234}\x{e000}**
0: $@`
\= Expect no match
\x{9f}
No match
/^[\p{Xuc}]/utf
$@`\x{a0}\x{1234}\x{e000}**
0: $
\= Expect no match
\x{9f}
No match
/^[\p{Xuc}]+/utf
$@`\x{a0}\x{1234}\x{e000}**
0: $@`\x{a0}\x{1234}\x{e000}
\= Expect no match
\x{9f}
No match
/^\P{Xuc}/utf
abc
0: a
\= Expect no match
$abc
No match
@abc
No match
`abc
No match
\x{1234}abc
No match
/^[\P{Xuc}]/utf
abc
0: a
\= Expect no match
$abc
No match
@abc
No match
`abc
No match
\x{1234}abc
No match
# Some auto-possessification tests
/\pN+\z/B
------------------------------------------------------------------
Bra
prop N ++
\z
Ket
End
------------------------------------------------------------------
/\PN+\z/B
------------------------------------------------------------------
Bra
notprop N ++
\z
Ket
End
------------------------------------------------------------------
/\pN+/B
------------------------------------------------------------------
Bra
prop N ++
Ket
End
------------------------------------------------------------------
/\PN+/B
------------------------------------------------------------------
Bra
notprop N ++
Ket
End
------------------------------------------------------------------
/\p{Any}+\p{Any} \p{Any}+\P{Any} \p{Any}+\p{L&} \p{Any}+\p{L} \p{Any}+\p{Lu} \p{Any}+\p{Han} \p{Any}+\p{Xan} \p{Any}+\p{Xsp} \p{Any}+\p{Xps} \p{Xwd}+\p{Any} \p{Any}+\p{Xuc}/Bx,ucp
------------------------------------------------------------------
Bra
prop Any +
prop Any
prop Any +
notprop Any
prop Any +
prop L&
prop Any +
prop L
prop Any +
prop Lu
prop Any +
prop Han
prop Any +
prop Xan
prop Any +
prop Xsp
prop Any +
prop Xps
prop Xwd +
prop Any
prop Any +
prop Xuc
Ket
End
------------------------------------------------------------------
/\p{L&}+\p{Any} \p{L&}+\p{L&} \P{L&}+\p{L&} \p{L&}+\p{L} \p{L&}+\p{Lu} \p{L&}+\p{Han} \p{L&}+\p{Xan} \p{L&}+\P{Xan} \p{L&}+\p{Xsp} \p{L&}+\p{Xps} \p{Xwd}+\p{L&} \p{L&}+\p{Xuc}/Bx,ucp
------------------------------------------------------------------
Bra
prop L& +
prop Any
prop L& +
prop L&
notprop L& ++
prop L&
prop L& +
prop L
prop L& +
prop Lu
prop L& +
prop Han
prop L& +
prop Xan
prop L& ++
notprop Xan
prop L& ++
prop Xsp
prop L& ++
prop Xps
prop Xwd +
prop L&
prop L& +
prop Xuc
Ket
End
------------------------------------------------------------------
/\p{N}+\p{Any} \p{N}+\p{L&} \p{N}+\p{L} \p{N}+\P{L} \p{N}+\P{N} \p{N}+\p{Lu} \p{N}+\p{Han} \p{N}+\p{Xan} \p{N}+\p{Xsp} \p{N}+\p{Xps} \p{Xwd}+\p{N} \p{N}+\p{Xuc}/Bx,ucp
------------------------------------------------------------------
Bra
prop N +
prop Any
prop N +
prop L&
prop N ++
prop L
prop N +
notprop L
prop N ++
notprop N
prop N ++
prop Lu
prop N +
prop Han
prop N +
prop Xan
prop N ++
prop Xsp
prop N ++
prop Xps
prop Xwd +
prop N
prop N +
prop Xuc
Ket
End
------------------------------------------------------------------
/\p{Lu}+\p{Any} \p{Lu}+\p{L&} \p{Lu}+\p{L} \p{Lu}+\p{Lu} \P{Lu}+\p{Lu} \p{Lu}+\p{Nd} \p{Lu}+\P{Nd} \p{Lu}+\p{Han} \p{Lu}+\p{Xan} \p{Lu}+\p{Xsp} \p{Lu}+\p{Xps} \p{Xwd}+\p{Lu} \p{Lu}+\p{Xuc}/Bx,ucp
------------------------------------------------------------------
Bra
prop Lu +
prop Any
prop Lu +
prop L&
prop Lu +
prop L
prop Lu +
prop Lu
notprop Lu ++
prop Lu
prop Lu ++
prop Nd
prop Lu +
notprop Nd
prop Lu +
prop Han
prop Lu +
prop Xan
prop Lu ++
prop Xsp
prop Lu ++
prop Xps
prop Xwd +
prop Lu
prop Lu +
prop Xuc
Ket
End
------------------------------------------------------------------
/\p{Han}+\p{Lu} \p{Han}+\p{L&} \p{Han}+\p{L} \p{Han}+\p{Lu} \p{Han}+\p{Arabic} \p{Arabic}+\p{Arabic} \p{Han}+\p{Xan} \p{Han}+\p{Xsp} \p{Han}+\p{Xps} \p{Xwd}+\p{Han} \p{Han}+\p{Xuc}/Bx,ucp
------------------------------------------------------------------
Bra
prop Han +
prop Lu
prop Han +
prop L&
prop Han +
prop L
prop Han +
prop Lu
prop Han ++
prop Arabic
prop Arabic +
prop Arabic
prop Han +
prop Xan
prop Han +
prop Xsp
prop Han +
prop Xps
prop Xwd +
prop Han
prop Han +
prop Xuc
Ket
End
------------------------------------------------------------------
/\p{Xan}+\p{Any} \p{Xan}+\p{L&} \P{Xan}+\p{L&} \p{Xan}+\p{L} \p{Xan}+\p{Lu} \p{Xan}+\p{Han} \p{Xan}+\p{Xan} \p{Xan}+\P{Xan} \p{Xan}+\p{Xsp} \p{Xan}+\p{Xps} \p{Xwd}+\p{Xan} \p{Xan}+\p{Xuc}/Bx,ucp
------------------------------------------------------------------
Bra
prop Xan +
prop Any
prop Xan +
prop L&
notprop Xan ++
prop L&
prop Xan +
prop L
prop Xan +
prop Lu
prop Xan +
prop Han
prop Xan +
prop Xan
prop Xan ++
notprop Xan
prop Xan ++
prop Xsp
prop Xan ++
prop Xps
prop Xwd +
prop Xan
prop Xan +
prop Xuc
Ket
End
------------------------------------------------------------------
/\p{Xsp}+\p{Any} \p{Xsp}+\p{L&} \p{Xsp}+\p{L} \p{Xsp}+\p{Lu} \p{Xsp}+\p{Han} \p{Xsp}+\p{Xan} \p{Xsp}+\p{Xsp} \P{Xsp}+\p{Xsp} \p{Xsp}+\p{Xps} \p{Xwd}+\p{Xsp} \p{Xsp}+\p{Xuc}/Bx,ucp
------------------------------------------------------------------
Bra
prop Xsp +
prop Any
prop Xsp ++
prop L&
prop Xsp ++
prop L
prop Xsp ++
prop Lu
prop Xsp +
prop Han
prop Xsp ++
prop Xan
prop Xsp +
prop Xsp
notprop Xsp ++
prop Xsp
prop Xsp +
prop Xps
prop Xwd ++
prop Xsp
prop Xsp +
prop Xuc
Ket
End
------------------------------------------------------------------
/\p{Xwd}+\p{Any} \p{Xwd}+\p{L&} \p{Xwd}+\p{L} \p{Xwd}+\p{Lu} \p{Xwd}+\p{Han} \p{Xwd}+\p{Xan} \p{Xwd}+\p{Xsp} \p{Xwd}+\p{Xps} \p{Xwd}+\p{Xwd} \p{Xwd}+\P{Xwd} \p{Xwd}+\p{Xuc}/Bx,ucp
------------------------------------------------------------------
Bra
prop Xwd +
prop Any
prop Xwd +
prop L&
prop Xwd +
prop L
prop Xwd +
prop Lu
prop Xwd +
prop Han
prop Xwd +
prop Xan
prop Xwd ++
prop Xsp
prop Xwd ++
prop Xps
prop Xwd +
prop Xwd
prop Xwd ++
notprop Xwd
prop Xwd +
prop Xuc
Ket
End
------------------------------------------------------------------
/\p{Xuc}+\p{Any} \p{Xuc}+\p{L&} \p{Xuc}+\p{L} \p{Xuc}+\p{Lu} \p{Xuc}+\p{Han} \p{Xuc}+\p{Xan} \p{Xuc}+\p{Xsp} \p{Xuc}+\p{Xps} \p{Xwd}+\p{Xuc} \p{Xuc}+\p{Xuc} \p{Xuc}+\P{Xuc}/Bx,ucp
------------------------------------------------------------------
Bra
prop Xuc +
prop Any
prop Xuc +
prop L&
prop Xuc +
prop L
prop Xuc +
prop Lu
prop Xuc +
prop Han
prop Xuc +
prop Xan
prop Xuc +
prop Xsp
prop Xuc +
prop Xps
prop Xwd +
prop Xuc
prop Xuc +
prop Xuc
prop Xuc ++
notprop Xuc
Ket
End
------------------------------------------------------------------
/\p{N}+\p{Ll} \p{N}+\p{Nd} \p{N}+\P{Nd}/Bx,ucp
------------------------------------------------------------------
Bra
prop N ++
prop Ll
prop N +
prop Nd
prop N +
notprop Nd
Ket
End
------------------------------------------------------------------
/\p{Xan}+\p{L} \p{Xan}+\p{N} \p{Xan}+\p{C} \p{Xan}+\P{L} \P{Xan}+\p{N} \p{Xan}+\P{C}/Bx,ucp
------------------------------------------------------------------
Bra
prop Xan +
prop L
prop Xan +
prop N
prop Xan ++
prop C
prop Xan +
notprop L
notprop Xan ++
prop N
prop Xan +
notprop C
Ket
End
------------------------------------------------------------------
/\p{L}+\p{Xan} \p{N}+\p{Xan} \p{C}+\p{Xan} \P{L}+\p{Xan} \p{N}+\p{Xan} \P{C}+\p{Xan} \p{L}+\P{Xan}/Bx,ucp
------------------------------------------------------------------
Bra
prop L +
prop Xan
prop N +
prop Xan
prop C ++
prop Xan
notprop L +
prop Xan
prop N +
prop Xan
notprop C +
prop Xan
prop L ++
notprop Xan
Ket
End
------------------------------------------------------------------
/\p{Xan}+\p{Lu} \p{Xan}+\p{Nd} \p{Xan}+\p{Cc} \p{Xan}+\P{Ll} \P{Xan}+\p{No} \p{Xan}+\P{Cf}/Bx,ucp
------------------------------------------------------------------
Bra
prop Xan +
prop Lu
prop Xan +
prop Nd
prop Xan ++
prop Cc
prop Xan +
notprop Ll
notprop Xan ++
prop No
prop Xan +
notprop Cf
Ket
End
------------------------------------------------------------------
/\p{Lu}+\p{Xan} \p{Nd}+\p{Xan} \p{Cs}+\p{Xan} \P{Lt}+\p{Xan} \p{Nl}+\p{Xan} \P{Cc}+\p{Xan} \p{Lt}+\P{Xan}/Bx,ucp
------------------------------------------------------------------
Bra
prop Lu +
prop Xan
prop Nd +
prop Xan
prop Cs ++
prop Xan
notprop Lt +
prop Xan
prop Nl +
prop Xan
notprop Cc +
prop Xan
prop Lt ++
notprop Xan
Ket
End
------------------------------------------------------------------
/\w+\p{P} \w+\p{Po} \w+\s \p{Xan}+\s \s+\p{Xan} \s+\w/Bx,ucp
------------------------------------------------------------------
Bra
prop Xwd +
prop P
prop Xwd +
prop Po
prop Xwd ++
prop Xsp
prop Xan ++
prop Xsp
prop Xsp ++
prop Xan
prop Xsp ++
prop Xwd
Ket
End
------------------------------------------------------------------
/\w+\P{P} \W+\p{Po} \w+\S \P{Xan}+\s \s+\P{Xan} \s+\W/Bx,ucp
------------------------------------------------------------------
Bra
prop Xwd +
notprop P
notprop Xwd +
prop Po
prop Xwd +
notprop Xsp
notprop Xan +
prop Xsp
prop Xsp +
notprop Xan
prop Xsp +
notprop Xwd
Ket
End
------------------------------------------------------------------
/\w+\p{Po} \w+\p{Pc} \W+\p{Po} \W+\p{Pc} \w+\P{Po} \w+\P{Pc}/Bx,ucp
------------------------------------------------------------------
Bra
prop Xwd +
prop Po
prop Xwd ++
prop Pc
notprop Xwd +
prop Po
notprop Xwd +
prop Pc
prop Xwd +
notprop Po
prop Xwd +
notprop Pc
Ket
End
------------------------------------------------------------------
/\p{Nl}+\p{Xan} \P{Nl}+\p{Xan} \p{Nl}+\P{Xan} \P{Nl}+\P{Xan}/Bx,ucp
------------------------------------------------------------------
Bra
prop Nl +
prop Xan
notprop Nl +
prop Xan
prop Nl ++
notprop Xan
notprop Nl +
notprop Xan
Ket
End
------------------------------------------------------------------
/\p{Xan}+\p{Nl} \P{Xan}+\p{Nl} \p{Xan}+\P{Nl} \P{Xan}+\P{Nl}/Bx,ucp
------------------------------------------------------------------
Bra
prop Xan +
prop Nl
notprop Xan ++
prop Nl
prop Xan +
notprop Nl
notprop Xan +
notprop Nl
Ket
End
------------------------------------------------------------------
/\p{Xan}+\p{Nd} \P{Xan}+\p{Nd} \p{Xan}+\P{Nd} \P{Xan}+\P{Nd}/Bx,ucp
------------------------------------------------------------------
Bra
prop Xan +
prop Nd
notprop Xan ++
prop Nd
prop Xan +
notprop Nd
notprop Xan +
notprop Nd
Ket
End
------------------------------------------------------------------
# End auto-possessification tests
/\w+/B,utf,ucp,auto_callout
------------------------------------------------------------------
Bra
Callout 255 0 3
prop Xwd ++
Callout 255 3 0
Ket
End
------------------------------------------------------------------
abcd
--->abcd
+0 ^ \w+
+3 ^ ^ End of pattern
0: abcd
/[\p{N}]?+/B,no_auto_possess
------------------------------------------------------------------
Bra
[\p{N}]?+
Ket
End
------------------------------------------------------------------
/[\p{L}ab]{2,3}+/B,no_auto_possess
------------------------------------------------------------------
Bra
[ab\p{L}]{2,3}+
Ket
End
------------------------------------------------------------------
/\D+\X \d+\X \S+\X \s+\X \W+\X \w+\X \R+\X \H+\X \h+\X \V+\X \v+\X a+\X \n+\X .+\X/Bx
------------------------------------------------------------------
Bra
\D+
extuni
\d+
extuni
\S+
extuni
\s+
extuni
\W+
extuni
\w+
extuni
\R+
extuni
\H+
extuni
\h+
extuni
\V+
extuni
\v+
extuni
a+
extuni
\x0a+
extuni
Any+
extuni
Ket
End
------------------------------------------------------------------
/.+\X/Bsx
------------------------------------------------------------------
Bra
AllAny+
extuni
Ket
End
------------------------------------------------------------------
/\X+$/Bmx
------------------------------------------------------------------
Bra
extuni+
/m $
Ket
End
------------------------------------------------------------------
/\X+\D \X+\d \X+\S \X+\s \X+\W \X+\w \X+. \X+\R \X+\H \X+\h \X+\V \X+\v \X+\X \X+\Z \X+\z \X+$/Bx
------------------------------------------------------------------
Bra
extuni+
\D
extuni+
\d
extuni+
\S
extuni+
\s
extuni+
\W
extuni+
\w
extuni+
Any
extuni+
\R
extuni+
\H
extuni+
\h
extuni+
\V
extuni+
\v
extuni+
extuni
extuni+
\Z
extuni++
\z
extuni+
$
Ket
End
------------------------------------------------------------------
/\d+\s{0,5}=\s*\S?=\w{0,4}\W*/B,utf,ucp
------------------------------------------------------------------
Bra
prop Nd ++
prop Xsp {0,5}+
=
prop Xsp *+
notprop Xsp ?
=
prop Xwd {0,4}+
notprop Xwd *+
Ket
End
------------------------------------------------------------------
/[RST]+/Bi,utf,ucp
------------------------------------------------------------------
Bra
[R-Tr-t\x{17f}]++
Ket
End
------------------------------------------------------------------
/[R-T]+/Bi,utf,ucp
------------------------------------------------------------------
Bra
[R-Tr-t\x{17f}]++
Ket
End
------------------------------------------------------------------
/[Q-U]+/Bi,utf,ucp
------------------------------------------------------------------
Bra
[Q-Uq-u\x{17f}]++
Ket
End
------------------------------------------------------------------
/^s?c/Iim,utf
Capturing subpattern count = 0
Options: caseless multiline utf
First code unit at start or follows newline
Last code unit = 'c' (caseless)
Subject length lower bound = 1
scat
0: sc
/\X?abc/utf,no_start_optimize
\xff\x7f\x00\x00\x03\x00\x41\xcc\x80\x41\x{300}\x61\x62\x63\x00\=no_utf_check,offset=06
0: A\x{300}abc
/\x{100}\x{200}\K\x{300}/utf,startchar
\x{100}\x{200}\x{300}
0: \x{100}\x{200}\x{300}
^^^^^^^^^^^^^^
# Test UTF characters in a substitution
/ábc/utf,replace=Xá´Z
123ábc123
1: 123X\x{1234}Z123
/(?<=abc)(|def)/g,utf,replace=<$0>
123abcáyzabcdef789abcá´qr
4: 123abc<>\x{e1}yzabc<><def>789abc<>\x{1234}qr
/[A-`]/iB,utf
------------------------------------------------------------------
Bra
[A-z\x{212a}\x{17f}]
Ket
End
------------------------------------------------------------------
abcdefghijklmno
0: a
/(?<=\K\x{17f})/g,utf,aftertext
\x{17f}\x{17f}\x{17f}\x{17f}\x{17f}
0: \x{17f}
0+ \x{17f}\x{17f}\x{17f}\x{17f}
0: \x{17f}
0+ \x{17f}\x{17f}\x{17f}
0: \x{17f}
0+ \x{17f}\x{17f}
0: \x{17f}
0+ \x{17f}
0: \x{17f}
0+
/(?<=\K\x{17f})/altglobal,utf,aftertext
\x{17f}\x{17f}\x{17f}\x{17f}\x{17f}
0: \x{17f}
0+ \x{17f}\x{17f}\x{17f}\x{17f}
0: \x{17f}
0+ \x{17f}\x{17f}\x{17f}
0: \x{17f}
0+ \x{17f}\x{17f}
0: \x{17f}
0+ \x{17f}
0: \x{17f}
0+
"\xa\xf<(.\pZ*\P{Xwd}+^\xa8\3'3yq.::?(?J:()\xd1+!~:3'(8?:)':(?'d'(?'d'^u]!.+.+\\A\Ah(n+?9){7}+\K;(?'X'u'(?'c'(?'z'(?<y>\xb::\xf0'|\xd3(\xae?'w(z\x8?P>l)\x8?P>a)'\H\R\xd1+!!~:3'(?:h$N{26875}\W+?\\=D{2}\x89(?i:Uy0\N({2\xa(\v\x85*){y*\A(()\p{L}+?\P{^Xan}'+?\xff\+pS\?|).{;y*\A(()\p{L}+?\8}\d?1(|)(/1){7}.+[Lp{Me}].\s\xdcC*?(?(<y>))(?<!^)$C((;*?(R))+(\xbf(R))\x8a\X*?\x8a\xb\xd1^9\3*+(\xc1,\k'R'\xb4)\xcc(z\z(?J)(?'X'\x1b(\xb\xd1^9\?'3*+P{^Xan}+?\xff\+(\xc1.]k+\xb'Pm'\xb4)\xcc4f\xa7'\xd1V(?i:U,{2,2})'(?'X'))?-%--\x95$9*\4'|\xd1(\x9c''%\x94$9)#(?'R')3\x7?('P\xed7'\xa8\xb1^u\xeaw\1\0\0\(|(?1){7}.+[\p{Me}].\s\xdcC*^\x14?(?(<y>))(?<!^)$C((;*?(R*?))+(?(R)\x8a\X*?\x8a\xb\xd1^9\3*+|(\xc1,\k'R'\xb4)\xcc! z)\z(?JJ)(?'X';(\xb\xd1^9\?'3*+(\xc1.]k+\xb'Pm'\xb4))':(?'d')(?'RD'(d')|)|$)'|(?<x>\g{d});\g{x}\x11\g{d}\x81\|$((?'X'\'X'(?'W''\x92()'9'\x83*))\xba*\!?^ <){)':;\xcc4'\xd1'(?'X'28))?-%--\x95$9*\4'|\xd1((''e\x94*$9:)*#(?'R')3)\x7?('P\xed')\\x16:;()\x1e\x10*:(?<y>)\xd1+0!~:(?)'d'E:yD!\s(?'R'\x1e;\x10:U))|'\x9g!\xb0*){)\\x16:;()\x1e\x10\x87*:(?<y>)\xd1+!~:(?)'}'\d'E:yD!\s(?'R'\x1e;\x10:U))|'))|)g!\xb0*R+9{29+)#(?'P'})*?pS\{3,}\x85,{0,}l{*UTF)(\xe{7}){3722,{9,}d{2,?|))|{)\(A?&d}}{\xa,}2}){3,}7,l{)22}(,}l:7{2,4}}29\x19+)#?'P'})*v?))\x5"
Failed: error 122 at offset 1227: unmatched closing parenthesis
/$(&.+[\p{Me}].\s\xdcC*?(?(<y>))(?<!^)$C((;*?(R))+(?(R)){0,6}?|){12\x8a\X*?\x8a\x0b\xd1^9\3*+(\xc1,\k'P'\xb4)\xcc(z\z(?JJ)(?'X'8};(\x0b\xd1^9\?'3*+(\xc1.]k+\x0b'Pm'\xb4\xcc4'\xd1'(?'X'))?-%--\x95$9*\4'|\xd1(''%\x95*$9)#(?'R')3\x07?('P\xed')\\x16:;()\x1e\x10*:(?<y>)\xd1+!~:(?)''(d'E:yD!\s(?'R'\x1e;\x10:U))|')g!\xb0*){29+))#(?'P'})*?/
"(*UTF)(*UCP)(.UTF).+X(\V+;\^(\D|)!999}(?(?C{7(?C')\H*\S*/^\x5\xa\\xd3\x85n?(;\D*(?m).[^mH+((*UCP)(*U:F)})(?!^)(?'"
Failed: error 162 at offset 113: subpattern name expected
/[\pS#moq]/
=
0: =
/(*:a\x{12345}b\t(d\)c)xxx/utf,alt_verbnames,mark
cxxxz
0: xxx
MK: a\x{12345}b\x{09}(d)c
/abcd/utf,replace=x\x{824}y\o{3333}z(\Q12\$34$$\x34\E5$$),substitute_extended
abcd
1: x\x{824}y\x{6db}z(12\$34$$\x345$)
/a(\x{e0}\x{101})(\x{c0}\x{102})/utf,replace=a\u$1\U$1\E$1\l$2\L$2\Eab\U\x{e0}\x{101}\L\x{d0}\x{160}\EDone,substitute_extended
a\x{e0}\x{101}\x{c0}\x{102}
1: a\x{c0}\x{101}\x{c0}\x{100}\x{e0}\x{101}\x{e0}\x{102}\x{e0}\x{103}ab\x{c0}\x{100}\x{f0}\x{161}Done
/((?<digit>\d)|(?<letter>\p{L}))/g,substitute_extended,replace=<${digit:+digit; :not digit; }${letter:+letter:not a letter}>
ab12cde
7: <not digit; letter><not digit; letter><digit; not a letter><digit; not a letter><not digit; letter><not digit; letter><not digit; letter>
/(*UCP)(*UTF)[[:>:]]X/B
------------------------------------------------------------------
Bra
\b
AssertB
Reverse
prop Xwd
Ket
X
Ket
End
------------------------------------------------------------------
/abc/utf,replace=xyz
abc\=zero_terminate
1: xyz
/a[[:punct:]b]/ucp,bincode
------------------------------------------------------------------
Bra
a
[b[:punct:]]
Ket
End
------------------------------------------------------------------
/a[[:punct:]b]/utf,ucp,bincode
------------------------------------------------------------------
Bra
a
[b[:punct:]]
Ket
End
------------------------------------------------------------------
/a[b[:punct:]]/utf,ucp,bincode
------------------------------------------------------------------
Bra
a
[b[:punct:]]
Ket
End
------------------------------------------------------------------
/[[:^ascii:]]/utf,ucp,bincode
------------------------------------------------------------------
Bra
[\x80-\xff] (neg)
Ket
End
------------------------------------------------------------------
/[[:^ascii:]\w]/utf,ucp,bincode
------------------------------------------------------------------
Bra
[\x80-\xff\p{Xwd}\x{100}-\x{10ffff}]
Ket
End
------------------------------------------------------------------
/[\w[:^ascii:]]/utf,ucp,bincode
------------------------------------------------------------------
Bra
[\x80-\xff\p{Xwd}\x{100}-\x{10ffff}]
Ket
End
------------------------------------------------------------------
/[^[:ascii:]\W]/utf,ucp,bincode
------------------------------------------------------------------
Bra
[^\x00-\x7f\P{Xwd}]
Ket
End
------------------------------------------------------------------
\x{de}
0: \x{de}
\x{200}
0: \x{200}
\= Expect no match
\x{300}
No match
\x{37e}
No match
/[[:^ascii:]a]/utf,ucp,bincode
------------------------------------------------------------------
Bra
[a\x80-\xff] (neg)
Ket
End
------------------------------------------------------------------
/L(?#(|++<!(2)?/B,utf,no_auto_possess,auto_callout
------------------------------------------------------------------
Bra
Callout 255 0 14
L?
Callout 255 14 0
Ket
End
------------------------------------------------------------------
/L(?#(|++<!(2)?/B,utf,ucp,auto_callout
------------------------------------------------------------------
Bra
Callout 255 0 14
L?+
Callout 255 14 0
Ket
End
------------------------------------------------------------------
/(*UTF)C\x09((?<!'(?x)!*H? #\xcc\x9a[^$]/
Failed: error 114 at offset 39: missing closing parenthesis
/[\D]/utf
\x{1d7cf}
0: \x{1d7cf}
/[\D\P{Nd}]/utf
\x{1d7cf}
0: \x{1d7cf}
/[^\D]/utf
a9b
0: 9
\= Expect no match
\x{1d7cf}
No match
/[^\D\P{Nd}]/utf
a9b
0: 9
\x{1d7cf}
0: \x{1d7cf}
\= Expect no match
\x{10000}
No match
# Hex uses pattern length, not zero-terminated. This tests for overrunning
# the given length of a pattern.
/'(*UTF)'/hex
/'#('/hex,extended,utf
/a(?<=A\XB)/utf
Failed: error 125 at offset 1: lookbehind assertion is not fixed length
/ab(?<=A\RB)/utf
Failed: error 125 at offset 2: lookbehind assertion is not fixed length
/../utf,auto_callout
\n\x{123}\x{123}\x{123}\x{123}
--->\x{0a}\x{123}\x{123}\x{123}\x{123}
+0 ^ .
+0 ^ .
+1 ^ ^ .
+2 ^ ^ End of pattern
0: \x{123}\x{123}
# This tests processing wide characters in extended mode.
/XÈ/x,utf
# These three test a bug fix that was not clearing up after a locale setting
# when the test or a subsequent one matched a wide character.
//locale=C
/[\P{Yi}]/utf
\x{2f000}
0: \x{2f000}
/[\P{Yi}]/utf,locale=C
\x{2f000}
0: \x{2f000}
/^(?<!(?=ô¡))/B,utf
------------------------------------------------------------------
Bra
^
AssertB not
Assert
\x{10385c}
Ket
Ket
Ket
End
------------------------------------------------------------------
# Horizontal and vertical space lists ignore caseless
/[\HH]/Bi,utf
------------------------------------------------------------------
Bra
[\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff\x{100}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{10ffff}]
Ket
End
------------------------------------------------------------------
/[^\HH]/Bi,utf
------------------------------------------------------------------
Bra
[^\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff\x{100}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{10ffff}]
Ket
End
------------------------------------------------------------------
//g,utf
\=zero_terminate
0:
/^(?1)\p{Nd}{3}(a)/
a123a
0: a123a
1: a
/\p{Nd}{0,3}[\pL](*:abc)(?C1)xxx/callout_info
Callout 1 x
# ---------------------------------------------------------------------------
# A bunch of tests that hit lines of code that others do not (at least when
# these were created).
/^[^a]{3,}?x/i,utf,no_start_optimize,no_auto_possess
\= Expect no match
bbb
No match
cc
No match
/^[ac]{3,}?x/i,utf,no_start_optimize,no_auto_possess
\= Expect no match
aaa\x{100}
No match
/^X\X/no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X\p{L&}+?/no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X\p{L}+?/no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X\p{Lu}+?/no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X\p{Arabic}+?/no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X\p{Xan}+?/ucp,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X\s+?/ucp,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
XX
No match
/^X\S+?/ucp,no_start_optimize,no_auto_possess
XX
0: XX
\= Expect no match
X
No match
/^X\w+?/ucp,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X[^\x{b5}]+?/i,utf,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X[\x{b5}]+?/i,utf,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X\p{Xuc}+?/utf,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X.+?Z/s,utf,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X\R+?/utf,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X\H+?/utf,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X\V+?/utf,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X\s+?/utf,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
XX
No match
/^X\S+?/utf,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
/^X\p{Any}{1,3}?Z/s,no_start_optimize,no_auto_possess
XYYYZ
0: XYYYZ
\= Expect no match
XY
No match
XYY
No match
XYYY
No match
XYYYYZ
No match
/^X\p{L&}{1,3}?Z/s,no_start_optimize,no_auto_possess
\= Expect no match
XY
No match
XY!
No match
/^X\p{L}{1,3}?Z/s,no_start_optimize,no_auto_possess
\= Expect no match
XY
No match
XY!
No match
/^X\p{Lu}{1,3}?Z/s,no_start_optimize,no_auto_possess
\= Expect no match
XY
No match
XY!
No match
/^X\P{Han}{1,3}?Z/s,utf,no_start_optimize,no_auto_possess
\= Expect no match
XY
No match
XY!
No match
XY\x{2f00}!
No match
/^X\p{Xan}{1,3}?Z/s,no_start_optimize,no_auto_possess
\= Expect no match
XY
No match
XY!
No match
/^X\p{Xsp}{1,3}?Z/s,no_start_optimize,no_auto_possess
\= Expect no match
X\n
No match
X\n!
No match
X\n\n!
No match
/^X\P{Xsp}{1,3}?Z/s,no_start_optimize,no_auto_possess
\= Expect no match
XYY\n
No match
/^X\p{Xwd}{1,3}?Z/s,no_start_optimize,no_auto_possess
\= Expect no match
XY
No match
XY!
No match
XYY!
No match
/^X\x{b5}+?Z/i,utf,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
X\x{b5}
No match
X\x{b5}\x{b5}Y
No match
/^X\p{Xuc}+?Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
X$
No match
X@@Y
No match
/(*CRLF)^X.+?Z/utf,no_start_optimize,no_auto_possess
\= Expect partial match
XYY\r\=ph
Partial match: XYY\x{0d}
\= Expect no match
X
No match
/^X.+?Z/s,utf,no_start_optimize,no_auto_possess
\= Expect no match
X
No match
XYY
No match
/^X\R+?Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
X\nX
No match
X\n\rX
No match
X\n\r\nX
No match
X\n\n
No match
X\n\x{0c}
No match
/(*BSR_ANYCRLF)^X\R+?Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
X\nX
No match
X\n\rX
No match
X\n\r\nX
No match
X\n\n
No match
X\n\x{0c}
No match
/^X\H+?Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
XY\t
No match
XYY
No match
/^X\h+?Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
X\t\t
No match
X\tY
No match
/^X\V+?Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
XY\n
No match
XYY
No match
/^X\v+?Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
X\n\n
No match
X\nY
No match
/^X\D+?Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
XY9
No match
XYY
No match
/^X\d+?Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
X99
No match
X9Y
No match
/^X\S+?Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
XY\n
No match
XYY
No match
/^X\s+?Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
X\n\n
No match
X\nY
No match
/^X\W+?Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
X.A
No match
X++
No match
/^X\p{L&}{1,3}Z/no_start_optimize,no_auto_possess
\= Expect no match
XY
No match
XY!
No match
/^X\p{L}{1,3}Z/no_start_optimize,no_auto_possess
\= Expect no match
XY
No match
/^X\p{Xan}{1,3}Z/no_start_optimize,no_auto_possess
\= Expect no match
XY
No match
/^X\P{Xsp}{1,3}Z/no_start_optimize,no_auto_possess
\= Expect no match
XYY
No match
/^X\p{Xuc}+Z/utf,no_start_optimize,no_auto_possess
\= Expect no match
X$
No match
# ----------------------------------------------------------------------
# These test the dangerous PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL option.
/\x{d800}/B,utf,bad_escape_is_literal
------------------------------------------------------------------
Bra
x{d800}
Ket
End
------------------------------------------------------------------
/\ud800/B,utf,alt_bsux,bad_escape_is_literal
------------------------------------------------------------------
Bra
ud800
Ket
End
------------------------------------------------------------------
# ----------------------------------------------------------------------
/Aá´+B/literal,utf,no_utf_check
Aá´+B
0: A\x{1234}+B
# These are here because I upgraded to Unicode 10.0.0 before Perl did, so it
# doesn't recognize all these scripts. In time these three tests can be moved
# to test 4.
/^(\p{Adlam}+)(\p{Bhaiksuki}+)(\p{Marchen}+)(\p{Newa}+)(\p{Osage}+)
(\p{Tangut}+)(\p{Masaram_Gondi}+)(\p{Nushu}+)(\p{Soyombo}+)
(\p{Zanabazar_Square}+)/x,utf
\x{1E900}\x{1E924}\x{1E953}\x{11C00}\x{11C2D}\x{11C3E}\x{11C70}\x{11C77}\x{11CAB}\x{11400}\x{1142F}\x{11455}\x{104B0}\x{104D8}\x{104FB}\x{16FE0}\x{18800}\x{18AF2}\x{11D00}\x{11D3A}\x{11D59}\x{16FE1}\x{1B170}\x{1B2FB}\x{11A50}\x{11A58}\x{11AA2}\x{11A00}\x{11A07}\x{11A47}
0: \x{1e900}\x{1e924}\x{1e953}\x{11c00}\x{11c2d}\x{11c3e}\x{11c70}\x{11c77}\x{11cab}\x{11400}\x{1142f}\x{11455}\x{104b0}\x{104d8}\x{104fb}\x{16fe0}\x{18800}\x{18af2}\x{11d00}\x{11d3a}\x{11d59}\x{16fe1}\x{1b170}\x{1b2fb}\x{11a50}\x{11a58}\x{11aa2}\x{11a00}\x{11a07}\x{11a47}
1: \x{1e900}\x{1e924}\x{1e953}
2: \x{11c00}\x{11c2d}\x{11c3e}
3: \x{11c70}\x{11c77}\x{11cab}
4: \x{11400}\x{1142f}\x{11455}
5: \x{104b0}\x{104d8}\x{104fb}
6: \x{16fe0}\x{18800}\x{18af2}
7: \x{11d00}\x{11d3a}\x{11d59}
8: \x{16fe1}\x{1b170}\x{1b2fb}
9: \x{11a50}\x{11a58}\x{11aa2}
10: \x{11a00}\x{11a07}\x{11a47}
/^\x{1E900}\x{104B0}/i,utf
\x{1E900}\x{104B0}
0: \x{1e900}\x{104b0}
\x{1E922}\x{104D8}
0: \x{1e922}\x{104d8}
/^(?:(\X)(?C))+$/utf
\x{1E900}\x{1E924}\x{1E953}\x{11C00}\x{11C2D}\x{11C3E}\x{11C70}\x{11C77}\x{11CAB}\x{11400}\x{1142F}\x{11455}\x{104B0}\x{104D8}\x{104FB}\x{16FE0}\x{18800}\x{18AF2}\x{11D00}\x{11D3A}\x{11D59}\x{16FE1}\x{1B170}\x{1B2FB}\x{11A50}\x{11A58}\x{11AA2}\x{11A00}\x{11A07}\x{11A47}\=callout_capture,callout_no_where
Callout 0: last capture = 1
1: \x{1e900}
Callout 0: last capture = 1
1: \x{1e924}
Callout 0: last capture = 1
1: \x{1e953}
Callout 0: last capture = 1
1: \x{11c00}
Callout 0: last capture = 1
1: \x{11c2d}\x{11c3e}
Callout 0: last capture = 1
1: \x{11c70}
Callout 0: last capture = 1
1: \x{11c77}\x{11cab}
Callout 0: last capture = 1
1: \x{11400}
Callout 0: last capture = 1
1: \x{1142f}
Callout 0: last capture = 1
1: \x{11455}
Callout 0: last capture = 1
1: \x{104b0}
Callout 0: last capture = 1
1: \x{104d8}
Callout 0: last capture = 1
1: \x{104fb}
Callout 0: last capture = 1
1: \x{16fe0}
Callout 0: last capture = 1
1: \x{18800}
Callout 0: last capture = 1
1: \x{18af2}
Callout 0: last capture = 1
1: \x{11d00}\x{11d3a}
Callout 0: last capture = 1
1: \x{11d59}
Callout 0: last capture = 1
1: \x{16fe1}
Callout 0: last capture = 1
1: \x{1b170}
Callout 0: last capture = 1
1: \x{1b2fb}
Callout 0: last capture = 1
1: \x{11a50}\x{11a58}
Callout 0: last capture = 1
1: \x{11aa2}
Callout 0: last capture = 1
1: \x{11a00}\x{11a07}\x{11a47}
0: \x{1e900}\x{1e924}\x{1e953}\x{11c00}\x{11c2d}\x{11c3e}\x{11c70}\x{11c77}\x{11cab}\x{11400}\x{1142f}\x{11455}\x{104b0}\x{104d8}\x{104fb}\x{16fe0}\x{18800}\x{18af2}\x{11d00}\x{11d3a}\x{11d59}\x{16fe1}\x{1b170}\x{1b2fb}\x{11a50}\x{11a58}\x{11aa2}\x{11a00}\x{11a07}\x{11a47}
1: \x{11a00}\x{11a07}\x{11a47}
# Similarly for Unicode 11.0.0
/^(\p{Dogra}+)(\p{Gunjala_Gondi}+)(\p{Hanifi_Rohingya}+)(\p{Makasar}+)
(\p{Medefaidrin}+)(\p{Old_Sogdian}+)(\p{Sogdian}+)/x,utf
\x{11800}\x{11da9}\x{10d27}\x{11ee0}\x{16e48}\x{10f27}\x{10f30}
0: \x{11800}\x{11da9}\x{10d27}\x{11ee0}\x{16e48}\x{10f27}\x{10f30}
1: \x{11800}
2: \x{11da9}
3: \x{10d27}
4: \x{11ee0}
5: \x{16e48}
6: \x{10f27}
7: \x{10f30}
# These two are here because of differences from Perl.
/^\X/utf
A\x{200d}B A ZWJ
0: A\x{200d}
\x{261d}\x{261d}B Extended_Pictographic Extended_Pictographic
0: \x{261d}\x{261d}
\x{261D}\x{1F3FB}B Extended_Pictographic Extend
0: \x{261d}\x{1f3fb}
\x{1F1E6}\x{1F1E7}B RegionalIndicator RegionalIndicator
0: \x{1f1e6}\x{1f1e7}
\x{261D}\x{1F3FB}\x{261d}B Extended_Pictographic Extend E-P
0: \x{261d}\x{1f3fb}\x{261d}
\x{261D}\x{1F3FB}\x{200d}\x{261d}B Extended_Pictographic Extend ZWJ E-P
0: \x{261d}\x{1f3fb}\x{200d}\x{261d}
# Regional indicators
/^(\X)(\X)/utf,aftertext
\x{1F1E6}\x{1F1E7}\x{1F1E7}B
0: \x{1f1e6}\x{1f1e7}\x{1f1e7}
0+ B
1: \x{1f1e6}\x{1f1e7}
2: \x{1f1e7}
\x{1F1E6}\x{1F1E7}\x{1F1E7}\x{1F1E6}B
0: \x{1f1e6}\x{1f1e7}\x{1f1e7}\x{1f1e6}
0+ B
1: \x{1f1e6}\x{1f1e7}
2: \x{1f1e7}\x{1f1e6}
# More differences from Perl
/^[\p{Arabic}]/utf
\= Expect no match
\x{650}
No match
\x{651}
No match
\x{652}
No match
\x{653}
No match
\x{654}
No match
\x{655}
No match
/^\p{Common}/utf
\x{589}
0: \x{589}
\x{60c}
0: \x{60c}
\x{61f}
0: \x{61f}
\x{964}
0: \x{964}
\x{965}
0: \x{965}
/^\p{Inherited}/utf
\x{64b}
0: \x{64b}
\x{654}
0: \x{654}
\x{655}
0: \x{655}
\x{1D1AA}
0: \x{1d1aa}
/\N{U+}/
Failed: error 193 at offset 2: \N{U+dddd} is supported only in Unicode (UTF) mode
/\N{U+}/utf
Failed: error 178 at offset 5: digits missing in \x{} or \o{} or \N{U+}
/\N{U}/
Failed: error 137 at offset 2: PCRE2 does not support \F, \L, \l, \N{name}, \U, or \u
# This tests the non-UTF Unicode NEL pattern whitespace character, only
# recognized by PCRE2 with /x when there is Unicode support.
/A
B/x
AB
0: AB
# This tests Unicode Pattern White Space characters in verb names when they
# are being processed with PCRE2_EXTENDED. Note: there are UTF-8 characters
# with code points greater than 255 between A, B, and C in the pattern.
/(*: AâBâ¨C)abc/x,utf,mark,alt_verbnames
abc
0: abc
MK: ABC
# End of testinput5