xref: /aosp_15_r20/external/pcre/testdata/testinput12 (revision 22dc650d8ae982c6770746019a6f94af92b0f024)

# This set of tests is for UTF-16 and UTF-32 support, including Unicode
# properties. It is relevant only to the 16-bit and 32-bit libraries. The
# output is different for each library, so there are separate output files.

/���xxx/IB,utf,no_utf_check

/abc/utf
    �]

# Check maximum character size

/\x{ffff}/IB,utf

/\x{10000}/IB,utf

/\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

/X/utf
    XX\x{d800}\=no_utf_check
    XX\x{da00}\=no_utf_check
    XX\x{dc00}\=no_utf_check
    XX\x{de00}\=no_utf_check
    XX\x{dfff}\=no_utf_check
\= Expect UTF error
    XX\x{d800}
    XX\x{da00}
    XX\x{dc00}
    XX\x{de00}
    XX\x{dfff}
    XX\x{110000}
    XX\x{d800}\x{1234}
\= Expect no match
    XX\x{d800}\=offset=3

/(?<=.)X/utf
    XX\x{d800}\=offset=3

/(*UTF16)\x{11234}/
  abcd\x{11234}pqr

/(*UTF)\x{11234}/I
  abcd\x{11234}pqr

/(*UTF-32)\x{11234}/
  abcd\x{11234}pqr

/(*UTF-32)\x{112}/
  abcd\x{11234}pqr

/(*CRLF)(*UTF16)(*BSR_UNICODE)a\Rb/I

/(*CRLF)(*UTF32)(*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
    \x{2000}ABC

/\R*A/I,bsr=unicode,utf
    CDBABC
    \x{2028}A

/\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=2
    a\x{123}aa\=offset=3
\= Expect no match
    a\x{123}aa\=offset=4
\= Expect bad offset error
    a\x{123}aa\=offset=5
    a\x{123}aa\=offset=6

/\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

# Check bad offset

/a/utf
\= Expect bad UTF-16 offset, or no match in 32-bit
    \x{10000}\=offset=1
    \x{10000}ab\=offset=1
\= Expect 16-bit match, 32-bit no match
    \x{10000}ab\=offset=2
\= Expect no match
    \x{10000}ab\=offset=3
\= Expect no match in 16-bit, bad offset in 32-bit
    \x{10000}ab\=offset=4
\= Expect bad offset
    \x{10000}ab\=offset=5

/�/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!

/(*UTF)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

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

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

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

# Non-UTF characters should give errors in both 16-bit and 32-bit modes.

/\x{110000}/utf

/\o{4200000}/utf

/\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

/./utf
    \x{110000}

/(*UTF)ab������z/B

/ab������z/utf

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

/[\W\pL]/B
    abc
    \x{100}
    \x{308}
\= Expect no match
    123

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

/\pP/ucp
    \x{7fffffff}

# A special extra option allows excaped surrogate code points in 32-bit mode,
# but subjects containing them must not be UTF-checked. These patterns give
# errors in 16-bit mode.

/\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

# A few script run tests in non-UTF mode (but they need Unicode support)

/^(*script_run:.{4})/
    \x{3041}\x{30a1}\x{3007}\x{3007}   Hiragana Katakana Han Han
    \x{30a1}\x{3041}\x{3007}\x{3007}   Katakana Hiragana Han Han
    \x{1100}\x{2e80}\x{2e80}\x{1101}   Hangul Han Han Hangul

/^(*sr:.*)/utf,allow_surrogate_escapes
    \x{2e80}\x{3105}\x{2e80}\x{30a1}   Han Bopomofo Han Katakana
    \x{d800}\x{dfff}                   Surrogates (Unknown) \=no_utf_check

/(?(n/utf

/(?(á/utf

# Invalid UTF-16/32 tests.

/.../g,match_invalid_utf
    abcd\x{df00}wxzy\x{df00}pqrs
    abcd\x{80}wxzy\x{df00}pqrs

/abc/match_invalid_utf
    ab\x{df00}ab\=ph
\= Expect no match
    ab\x{df00}cdef\=ph

/.a/match_invalid_utf
    ab\=ph
    ab\=ps
\= Expect no match
    b\x{df00}\=ph
    b\x{df00}\=ps

/.a$/match_invalid_utf
    ab\=ph
    ab\=ps
\= Expect no match
    b\x{df00}\=ph
    b\x{df00}\=ps

/ab$/match_invalid_utf
    ab\x{df00}cdeab
\= Expect no match
    ab\x{df00}cde

/.../g,match_invalid_utf
    abcd\x{80}wxzy\x{df00}pqrs

/(?<=x)../g,match_invalid_utf
    abcd\x{80}wxzy\x{df00}pqrs
    abcd\x{80}wxzy\x{df00}xpqrs

/X$/match_invalid_utf
\= Expect no match
    X\x{df00}

/(?<=..)X/match_invalid_utf,aftertext
    AB\x{df00}AQXYZ
    AB\x{df00}AQXYZ\=offset=5
    AB\x{df00}\x{df00}AXYZXC\=offset=5
\= Expect no match
    AB\x{df00}XYZ
    AB\x{df00}XYZ\=offset=3
    AB\x{df00}AXYZ
    AB\x{df00}AXYZ\=offset=4
    AB\x{df00}\x{df00}AXYZ\=offset=5

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

/aa/utf,ucp,match_invalid_utf,global
    aa\x{d800}aa

/aa/utf,ucp,match_invalid_utf,global
    \x{d800}aa

/A\z/utf,match_invalid_utf
    A\x{df00}\n

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

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

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

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

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

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

/[Ss]/I

/[Ss]/I,utf

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

# ----------------------------------------------------
# UCP and casing tests

/\x{120}/i,I

/\x{c1}/i,I,ucp

/[\x{120}\x{121}]/iB,ucp

/[ab\x{120}]+/iB,ucp
    aABb\x{121}\x{120}

/\x{c1}/i,no_start_optimize
\= Expect no match
    \x{e1}

/\x{120}\x{c1}/i,ucp,no_start_optimize
    \x{121}\x{e1}

/\x{120}\x{c1}/i,ucp
    \x{121}\x{e1}

/[^\x{120}]/i,no_start_optimize
    \x{121}

/[^\x{120}]/i,ucp,no_start_optimize
\= Expect no match
    \x{121}

/[^\x{120}]/i
    \x{121}

/[^\x{120}]/i,ucp
\= Expect no match
    \x{121}

/\x{120}{2}/i,ucp
    \x{121}\x{121}

/[^\x{120}]{2}/i,ucp
\= Expect no match
    \x{121}\x{121}

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

/\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

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

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

/X(\x{121})Y/ucp,replace=>\U$1<,substitute_extended
    X\x{121}Y

/s/i,ucp
    \x{17f}

/s/i,utf
    \x{17f}

/[^s]/i,ucp
\= Expect no match
    \x{17f}

/[^s]/i,utf
\= Expect no match
    \x{17f}

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

# Quantifier after a literal that has the value of META_ACCEPT (not UTF). This
# fails in 16-bit mode, but is OK for 32-bit.

/\x{802a0000}*/
    \x{802a0000}\x{802a0000}

# UTF matching without UTF, check invalid UTF characters
/\X++/
    a\x{110000}\x{ffffffff}

# This used to loop in 32-bit mode; it will fail in 16-bit mode.
/[\x{ffffffff}]/caseless,ucp
    \x{ffffffff}xyz

# These are 32-bit tests for handing 0xffffffff when in UCP caselsss mode. They
# will give errors in 16-bit mode.

/k*\x{ffffffff}/caseless,ucp
    \x{ffffffff}

/k+\x{ffffffff}/caseless,ucp,no_start_optimize
    K\x{ffffffff}
\= Expect no match
    \x{ffffffff}\x{ffffffff}

/k{2}\x{ffffffff}/caseless,ucp,no_start_optimize
\= Expect no match
    \x{ffffffff}\x{ffffffff}\x{ffffffff}

/k\x{ffffffff}/caseless,ucp,no_start_optimize
    K\x{ffffffff}
\= Expect no match
    \x{ffffffff}\x{ffffffff}\x{ffffffff}

/k{2,}?Z/caseless,ucp,no_start_optimize,no_auto_possess
\= Expect no match
    Kk\x{ffffffff}\x{ffffffff}\x{ffffffff}Z

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

# End of testinput12