xref: /aosp_15_r20/external/pcre/testdata/testoutput14-8 (revision 22dc650d8ae982c6770746019a6f94af92b0f024)

# These test special UTF and UCP features of DFA matching. The output is
# different for the different widths.

#subject dfa

# ----------------------------------------------------
# These are a selection of the more comprehensive tests that are run for
# non-DFA matching.

/X/utf
    XX\x{d800}
Failed: error -16: UTF-8 error: code points 0xd800-0xdfff are not defined at offset 2
    XX\x{d800}\=offset=3
Error -36 (bad UTF-8 offset)
    XX\x{d800}\=no_utf_check
 0: X
    XX\x{da00}
Failed: error -16: UTF-8 error: code points 0xd800-0xdfff are not defined at offset 2
    XX\x{da00}\=no_utf_check
 0: X
    XX\x{dc00}
Failed: error -16: UTF-8 error: code points 0xd800-0xdfff are not defined at offset 2
    XX\x{dc00}\=no_utf_check
 0: X
    XX\x{de00}
Failed: error -16: UTF-8 error: code points 0xd800-0xdfff are not defined at offset 2
    XX\x{de00}\=no_utf_check
 0: X
    XX\x{dfff}
Failed: error -16: UTF-8 error: code points 0xd800-0xdfff are not defined at offset 2
    XX\x{dfff}\=no_utf_check
 0: X
    XX\x{110000}
Failed: error -15: UTF-8 error: code points greater than 0x10ffff are not defined at offset 2
    XX\x{d800}\x{1234}
Failed: error -16: UTF-8 error: code points 0xd800-0xdfff are not defined at offset 2

/badutf/utf
    X\xdf
Failed: error -3: UTF-8 error: 1 byte missing at end at offset 1
    XX\xef
Failed: error -4: UTF-8 error: 2 bytes missing at end at offset 2
    XXX\xef\x80
Failed: error -3: UTF-8 error: 1 byte missing at end at offset 3
    X\xf7
Failed: error -5: UTF-8 error: 3 bytes missing at end at offset 1
    XX\xf7\x80
Failed: error -4: UTF-8 error: 2 bytes missing at end at offset 2
    XXX\xf7\x80\x80
Failed: error -3: UTF-8 error: 1 byte missing at end at offset 3

/shortutf/utf
    XX\xdf\=ph
Failed: error -3: UTF-8 error: 1 byte missing at end at offset 2
    XX\xef\=ph
Failed: error -4: UTF-8 error: 2 bytes missing at end at offset 2
    XX\xef\x80\=ph
Failed: error -3: UTF-8 error: 1 byte missing at end at offset 2
    \xf7\=ph
Failed: error -5: UTF-8 error: 3 bytes missing at end at offset 0
    \xf7\x80\=ph
Failed: error -4: UTF-8 error: 2 bytes missing at end at offset 0

# ----------------------------------------------------
# UCP and casing tests - except for the first two, these will all fail in 8-bit
# mode because they are testing UCP without UTF and use characters > 255.

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

/\x{c1}+\x{e1}/iB,ucp
------------------------------------------------------------------
        Bra
     /i \x{c1}+
     /i \x{e1}
        Ket
        End
------------------------------------------------------------------
    \x{c1}\x{c1}\x{c1}
 0: \xc1\xc1\xc1
 1: \xc1\xc1
    \x{e1}\x{e1}\x{e1}
 0: \xe1\xe1\xe1
 1: \xe1\xe1

/\x{120}\x{c1}/i,ucp,no_start_optimize
Failed: error 134 at offset 6: character code point value in \x{} or \o{} is too large
    \x{121}\x{e1}

/\x{120}\x{c1}/i,ucp
Failed: error 134 at offset 6: character code point value in \x{} or \o{} is too large
    \x{121}\x{e1}

/[^\x{120}]/i,no_start_optimize
Failed: error 134 at offset 8: character code point value in \x{} or \o{} is too large
    \x{121}

/[^\x{120}]/i,ucp,no_start_optimize
Failed: error 134 at offset 8: character code point value in \x{} or \o{} is too large
\= Expect no match
    \x{121}

/[^\x{120}]/i
Failed: error 134 at offset 8: character code point value in \x{} or \o{} is too large
    \x{121}

/[^\x{120}]/i,ucp
Failed: error 134 at offset 8: character code point value in \x{} or \o{} is too large
\= Expect no match
    \x{121}

/\x{120}{2}/i,ucp
Failed: error 134 at offset 6: character code point value in \x{} or \o{} is too large
    \x{121}\x{121}

/[^\x{120}]{2}/i,ucp
Failed: error 134 at offset 8: character code point value in \x{} or \o{} is too large
\= Expect no match
    \x{121}\x{121}

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

# ----------------------------------------------------
# Tests for handling 0xffffffff in caseless UCP mode. They only apply to 32-bit
# mode; for the other widths they will fail.

/k*\x{ffffffff}/caseless,ucp
Failed: error 134 at offset 13: character code point value in \x{} or \o{} is too large
    \x{ffffffff}

/k+\x{ffffffff}/caseless,ucp,no_start_optimize
Failed: error 134 at offset 13: character code point value in \x{} or \o{} is too large
    K\x{ffffffff}
\= Expect no match
    \x{ffffffff}\x{ffffffff}

/k{2}\x{ffffffff}/caseless,ucp,no_start_optimize
Failed: error 134 at offset 15: character code point value in \x{} or \o{} is too large
\= Expect no match
    \x{ffffffff}\x{ffffffff}\x{ffffffff}

/k\x{ffffffff}/caseless,ucp,no_start_optimize
Failed: error 134 at offset 12: character code point value in \x{} or \o{} is too large
    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
** Character \x{ffffffff} is greater than 255 and UTF-8 mode is not enabled.
** Truncation will probably give the wrong result.
** Character \x{ffffffff} is greater than 255 and UTF-8 mode is not enabled.
** Truncation will probably give the wrong result.
** Character \x{ffffffff} is greater than 255 and UTF-8 mode is not enabled.
** Truncation will probably give the wrong result.
No match

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

# End of testinput14