xref: /aosp_15_r20/external/pcre/testdata/testinput10 (revision 22dc650d8ae982c6770746019a6f94af92b0f024)

# This set of tests is for UTF-8 support and Unicode property support, with
# relevance only for the 8-bit library.

#newline_default lf any anycrlf

# The next 5 patterns have UTF-8 errors

/[�]/utf

/�/utf

/���xxx/utf

/��������/utf

/��������/match_invalid_utf

# Now test subjects

/badutf/utf
\= Expect UTF-8 errors
    X\xdf
    XX\xef
    XXX\xef\x80
    X\xf7
    XX\xf7\x80
    XXX\xf7\x80\x80
    \xfb
    \xfb\x80
    \xfb\x80\x80
    \xfb\x80\x80\x80
    \xfd
    \xfd\x80
    \xfd\x80\x80
    \xfd\x80\x80\x80
    \xfd\x80\x80\x80\x80
    \xdf\x7f
    \xef\x7f\x80
    \xef\x80\x7f
    \xf7\x7f\x80\x80
    \xf7\x80\x7f\x80
    \xf7\x80\x80\x7f
    \xfb\x7f\x80\x80\x80
    \xfb\x80\x7f\x80\x80
    \xfb\x80\x80\x7f\x80
    \xfb\x80\x80\x80\x7f
    \xfd\x7f\x80\x80\x80\x80
    \xfd\x80\x7f\x80\x80\x80
    \xfd\x80\x80\x7f\x80\x80
    \xfd\x80\x80\x80\x7f\x80
    \xfd\x80\x80\x80\x80\x7f
    \xed\xa0\x80
    \xc0\x8f
    \xe0\x80\x8f
    \xf0\x80\x80\x8f
    \xf8\x80\x80\x80\x8f
    \xfc\x80\x80\x80\x80\x8f
    \x80
    \xfe
    \xff

/badutf/utf
\= Expect UTF-8 errors
    XX\xfb\x80\x80\x80\x80
    XX\xfd\x80\x80\x80\x80\x80
    XX\xf7\xbf\xbf\xbf

/shortutf/utf
\= Expect UTF-8 errors
    XX\xdf\=ph
    XX\xef\=ph
    XX\xef\x80\=ph
    \xf7\=ph
    \xf7\x80\=ph
    \xf7\x80\x80\=ph
    \xfb\=ph
    \xfb\x80\=ph
    \xfb\x80\x80\=ph
    \xfb\x80\x80\x80\=ph
    \xfd\=ph
    \xfd\x80\=ph
    \xfd\x80\x80\=ph
    \xfd\x80\x80\x80\=ph
    \xfd\x80\x80\x80\x80\=ph

/anything/utf
\= Expect UTF-8 errors
    X\xc0\x80
    XX\xc1\x8f
    XXX\xe0\x9f\x80
    \xf0\x8f\x80\x80
    \xf8\x87\x80\x80\x80
    \xfc\x83\x80\x80\x80\x80
    \xfe\x80\x80\x80\x80\x80
    \xff\x80\x80\x80\x80\x80
    \xf8\x88\x80\x80\x80
    \xf9\x87\x80\x80\x80
    \xfc\x84\x80\x80\x80\x80
    \xfd\x83\x80\x80\x80\x80
\= Expect no match
    \xc3\x8f
    \xe0\xaf\x80
    \xe1\x80\x80
    \xf0\x9f\x80\x80
    \xf1\x8f\x80\x80
    \xf8\x88\x80\x80\x80\=no_utf_check
    \xf9\x87\x80\x80\x80\=no_utf_check
    \xfc\x84\x80\x80\x80\x80\=no_utf_check
    \xfd\x83\x80\x80\x80\x80\=no_utf_check

# Similar tests with offsets

/badutf/utf
\= Expect UTF-8 errors
    X\xdfabcd
    X\xdfabcd\=offset=1
\= Expect no match
    X\xdfabcd\=offset=2

/(?<=x)badutf/utf
\= Expect UTF-8 errors
    X\xdfabcd
    X\xdfabcd\=offset=1
    X\xdfabcd\=offset=2
    X\xdfabcd\xdf\=offset=3
\= Expect no match
    X\xdfabcd\=offset=3

/(?<=xx)badutf/utf
\= Expect UTF-8 errors
    X\xdfabcd
    X\xdfabcd\=offset=1
    X\xdfabcd\=offset=2
    X\xdfabcd\=offset=3

/(?<=xxxx)badutf/utf
\= Expect UTF-8 errors
    X\xdfabcd
    X\xdfabcd\=offset=1
    X\xdfabcd\=offset=2
    X\xdfabcd\=offset=3
    X\xdfabc\xdf\=offset=6
    X\xdfabc\xdf\=offset=7
\= Expect no match
    X\xdfabcd\=offset=6

/\x{100}/IB,utf

/\x{1000}/IB,utf

/\x{10000}/IB,utf

/\x{100000}/IB,utf

/\x{10ffff}/IB,utf

/[\x{ff}]/IB,utf

/[\x{100}]/IB,utf

/\x80/IB,utf

/\xff/IB,utf

/\x{D55c}\x{ad6d}\x{C5B4}/IB,utf
    \x{D55c}\x{ad6d}\x{C5B4}

/\x{65e5}\x{672c}\x{8a9e}/IB,utf
    \x{65e5}\x{672c}\x{8a9e}

/\x{80}/IB,utf

/\x{084}/IB,utf

/\x{104}/IB,utf

/\x{861}/IB,utf

/\x{212ab}/IB,utf

/[^ab\xC0-\xF0]/IB,utf
    \x{f1}
    \x{bf}
    \x{100}
    \x{1000}
\= Expect no match
    \x{c0}
    \x{f0}

/Ā{3,4}/IB,utf
  \x{100}\x{100}\x{100}\x{100\x{100}

/(\x{100}+|x)/IB,utf

/(\x{100}*a|x)/IB,utf

/(\x{100}{0,2}a|x)/IB,utf

/(\x{100}{1,2}a|x)/IB,utf

/\x{100}/IB,utf

/a\x{100}\x{101}*/IB,utf

/a\x{100}\x{101}+/IB,utf

/[^\x{c4}]/IB

/[\x{100}]/IB,utf
    \x{100}
    Z\x{100}
    \x{100}Z

/[\xff]/IB,utf
    >\x{ff}<

/[^\xff]/IB,utf

/\x{100}abc(xyz(?1))/IB,utf

/\777/I,utf
  \x{1ff}
  \777

/\x{100}+\x{200}/IB,utf

/\x{100}+X/IB,utf

/^[\QĀ\E-\QŐ\E/B,utf

# This tests the stricter UTF-8 check according to RFC 3629.

/X/utf
\= Expect UTF-8 errors
    \x{d800}
    \x{da00}
    \x{dfff}
    \x{110000}
    \x{2000000}
    \x{7fffffff}
\= Expect no match
    \x{d800}\=no_utf_check
    \x{da00}\=no_utf_check
    \x{dfff}\=no_utf_check
    \x{110000}\=no_utf_check
    \x{2000000}\=no_utf_check
    \x{7fffffff}\=no_utf_check

/(*UTF8)\x{1234}/
    abcd\x{1234}pqr

/(*CRLF)(*UTF)(*BSR_UNICODE)a\Rb/I

/\h/I,utf
    ABC\x{09}
    ABC\x{20}
    ABC\x{a0}
    ABC\x{1680}
    ABC\x{180e}
    ABC\x{2000}
    ABC\x{202f}
    ABC\x{205f}
    ABC\x{3000}

/\v/I,utf
    ABC\x{0a}
    ABC\x{0b}
    ABC\x{0c}
    ABC\x{0d}
    ABC\x{85}
    ABC\x{2028}

/\h*A/I,utf
    CDBABC

/\v+A/I,utf

/\s?xxx\s/I,utf

/\sxxx\s/I,utf,tables=2
    AB\x{85}xxx\x{a0}XYZ
    AB\x{a0}xxx\x{85}XYZ

/\S \S/I,utf,tables=2
    \x{a2} \x{84}
    A Z

/a+/utf
    a\x{123}aa\=offset=1
    a\x{123}aa\=offset=3
    a\x{123}aa\=offset=4
\= Expect bad offset value
    a\x{123}aa\=offset=6
\= Expect bad UTF-8 offset
    a\x{123}aa\=offset=2
\= Expect no match
    a\x{123}aa\=offset=5

/\x{1234}+/Ii,utf

/\x{1234}+?/Ii,utf

/\x{1234}++/Ii,utf

/\x{1234}{2}/Ii,utf

/[^\x{c4}]/IB,utf

/X+\x{200}/IB,utf

/\R/I,utf

/\777/IB,utf

/\w+\x{C4}/B,utf
    a\x{C4}\x{C4}

/\w+\x{C4}/B,utf,tables=2
    a\x{C4}\x{C4}

/\W+\x{C4}/B,utf
    !\x{C4}

/\W+\x{C4}/B,utf,tables=2
    !\x{C4}

/\W+\x{A1}/B,utf
    !\x{A1}

/\W+\x{A1}/B,utf,tables=2
    !\x{A1}

/X\s+\x{A0}/B,utf
    X\x20\x{A0}\x{A0}

/X\s+\x{A0}/B,utf,tables=2
    X\x20\x{A0}\x{A0}

/\S+\x{A0}/B,utf
    X\x{A0}\x{A0}

/\S+\x{A0}/B,utf,tables=2
    X\x{A0}\x{A0}

/\x{a0}+\s!/B,utf
    \x{a0}\x20!

/\x{a0}+\s!/B,utf,tables=2
    \x{a0}\x20!

/A/utf
  \x{ff000041}
  \x{7f000041}

/(*UTF8)abc/never_utf

/abc/utf,never_utf

/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/IBi,utf

/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/IB,utf

/AB\x{1fb0}/IB,utf

/AB\x{1fb0}/IBi,utf

/\x{401}\x{420}\x{421}\x{422}\x{423}\x{424}\x{425}\x{426}\x{427}\x{428}\x{429}\x{42a}\x{42b}\x{42c}\x{42d}\x{42e}\x{42f}/Ii,utf
    \x{401}\x{420}\x{421}\x{422}\x{423}\x{424}\x{425}\x{426}\x{427}\x{428}\x{429}\x{42a}\x{42b}\x{42c}\x{42d}\x{42e}\x{42f}
    \x{451}\x{440}\x{441}\x{442}\x{443}\x{444}\x{445}\x{446}\x{447}\x{448}\x{449}\x{44a}\x{44b}\x{44c}\x{44d}\x{44e}\x{44f}

/[ⱥ]/Bi,utf

/[^ⱥ]/Bi,utf

/\h/I

/\v/I

/\R/I

/[[:blank:]]/B,ucp

/\x{212a}+/Ii,utf
    KKkk\x{212a}

/s+/Ii,utf
    SSss\x{17f}

/\x{100}*A/IB,utf
    A

/\x{100}*\d(?R)/IB,utf

/[Z\x{100}]/IB,utf
    Z\x{100}
    \x{100}
    \x{100}Z

/[z-\x{100}]/IB,utf

/[z\Qa-d]Ā\E]/IB,utf
    \x{100}
    Ā

/[ab\x{100}]abc(xyz(?1))/IB,utf

/\x{100}*\s/IB,utf

/\x{100}*\d/IB,utf

/\x{100}*\w/IB,utf

/\x{100}*\D/IB,utf

/\x{100}*\S/IB,utf

/\x{100}*\W/IB,utf

/[\x{105}-\x{109}]/IBi,utf
    \x{104}
    \x{105}
    \x{109}
\= Expect no match
    \x{100}
    \x{10a}

/[z-\x{100}]/IBi,utf
    Z
    z
    \x{39c}
    \x{178}
    |
    \x{80}
    \x{ff}
    \x{100}
    \x{101}
\= Expect no match
    \x{102}
    Y
    y

/[z-\x{100}]/IBi,utf

/\x{3a3}B/IBi,utf

/abc/utf,replace=�
    abc

/(?<=(a)(?-1))x/I,utf
    a\x80zx\=offset=3

/[\W\p{Any}]/B
    abc
    123

/[\W\pL]/B
    abc
\= Expect no match
    123

/(*:*++++++++++++''''''''''''''''''''+''+++'+++x+++++++++++++++++++++++++++++++++++(++++++++++++++++++++:++++++%++:''''''''''''''''''''''''+++++++++++++++++++++++++++++++++++++++++++++++++++++-++++++++k+++++++''''+++'+++++++++++++++++++++++''''++++++++++++':ƿ)/utf

/[\s[:^ascii:]]/B,ucp

# A special extra option allows excaped surrogate code points in 8-bit mode,
# but subjects containing them must not be UTF-checked.

/\x{d800}/I,utf,allow_surrogate_escapes
    \x{d800}\=no_utf_check

/\udfff\o{157401}/utf,alt_bsux,allow_surrogate_escapes
    \x{dfff}\x{df01}\=no_utf_check

# This has different starting code units in 8-bit mode.

/^[^ab]/IB,utf
    c
    \x{ff}
    \x{100}
\= Expect no match
    aaa

# Offsets are different in 8-bit mode.

/(?<=abc)(|def)/g,utf,replace=<$0>,substitute_callout
    123abcáyzabcdef789abcሴqr

# Check name length with non-ASCII characters

/(?'ABáC678901234567890123456789012012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf

/(?'ABáC6789012345678901234567890123012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf

/(?'ABZC6789012345678901234567890123012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf

/(?(n/utf

/(?(á/utf

# Invalid UTF-8 tests

/.../g,match_invalid_utf
    abcd\x80wxzy\x80pqrs
    abcd\x{80}wxzy\x80pqrs

/abc/match_invalid_utf
    ab\x80ab\=ph
\= Expect no match
    ab\x80cdef\=ph

/.a/match_invalid_utf
    ab\=ph
    ab\=ps
    b\xf0\x91\x88b\=ph
    b\xf0\x91\x88b\=ps
    b\xf0\x91\x88\xb4a
\= Expect no match
    b\x80\=ph
    b\x80\=ps
    b\xf0\x91\x88\=ph
    b\xf0\x91\x88\=ps

/.a$/match_invalid_utf
    ab\=ph
    ab\=ps
\= Expect no match
    b\xf0\x91\x98\=ph
    b\xf0\x91\x98\=ps

/ab$/match_invalid_utf
    ab\x80cdeab
\= Expect no match
    ab\x80cde

/.../g,match_invalid_utf
    abcd\x{80}wxzy\x80pqrs

/(?<=x)../g,match_invalid_utf
    abcd\x{80}wxzy\x80pqrs
    abcd\x{80}wxzy\x80xpqrs

/X$/match_invalid_utf
\= Expect no match
    X\xc4

/(?<=..)X/match_invalid_utf,aftertext
    AB\x80AQXYZ
    AB\x80AQXYZ\=offset=5
    AB\x80\x80AXYZXC\=offset=5
\= Expect no match
    AB\x80XYZ
    AB\x80XYZ\=offset=3
    AB\xfeXYZ
    AB\xffXYZ\=offset=3
    AB\x80AXYZ
    AB\x80AXYZ\=offset=4
    AB\x80\x80AXYZ\=offset=5

/.../match_invalid_utf
    AB\xc4CCC
\= Expect no match
    A\x{d800}B
    A\x{110000}B
    A\xc4B

/\bX/match_invalid_utf
    A\x80X

/\BX/match_invalid_utf
\= Expect no match
    A\x80X

/(?<=...)X/match_invalid_utf
    AAA\x80BBBXYZ
\= Expect no match
    AAA\x80BXYZ
    AAA\x80BBXYZ

# -------------------------------------

/(*UTF)(?=\x{123})/I

/[\x{c1}\x{e1}]X[\x{145}\x{146}]/I,utf

/[��,]/BI,utf

/[\x{fff4}-\x{ffff8}]/I,utf

/[\x{fff4}-\x{afff8}\x{10ffff}]/I,utf

/[\xff\x{ffff}]/I,utf

/[\xff\x{ff}]/I,utf
    abc\x{ff}def

/[\xff\x{ff}]/I
    abc\x{ff}def

/[Ss]/I

/[Ss]/I,utf

/(?:\x{ff}|\x{3000})/I,utf

/x/utf
    abxyz
    \x80\=startchar
    abc\x80\=startchar
    abc\x80\=startchar,offset=3

/\x{c1}+\x{e1}/iIB,ucp
    \x{c1}\x{c1}\x{c1}
    \x{e1}\x{e1}\x{e1}

/a|\x{c1}/iI,ucp
    \x{e1}xxx

/a|\x{c1}/iI,utf
    \x{e1}xxx

/\x{c1}|\x{e1}/iI,ucp

/X(\x{e1})Y/ucp,replace=>\U$1<,substitute_extended
    X\x{e1}Y

/X(\x{e1})Y/i,ucp,replace=>\L$1<,substitute_extended
    X\x{c1}Y

# Without UTF or UCP characters > 127 have only one case in the default locale.

/X(\x{e1})Y/replace=>\U$1<,substitute_extended
    X\x{e1}Y

/A/utf,match_invalid_utf,caseless
    \xe5A

/\bch\b/utf,match_invalid_utf
    qchq\=ph
    qchq\=ps

/line1\nbreak/firstline,utf,match_invalid_utf
    line1\nbreak
    line0\nline1\nbreak

/A\z/utf,match_invalid_utf
    A\x80\x42\n

# End of testinput10