Diff for /embedaddon/pcre/testdata/testoutput15 between versions 1.1.1.2 and 1.1.1.5

version 1.1.1.2, 2012/02/21 23:50:25 version 1.1.1.5, 2014/06/15 19:46:05
Line 1 Line 1
/-- This set of tests is for UTF-8 support, and is relevant only to the 8-bit /-- This set of tests is for UTF-8 support but not Unicode property support,
    library. --/    and is relevant only to the 8-bit library. --/
   
   < forbid W
   
 /X(\C{3})/8  /X(\C{3})/8
     X\x{1234}      X\x{1234}
  0: X\x{1234}   0: X\x{1234}
Line 72  Failed: invalid UTF-8 string at offset 0 Line 74  Failed: invalid UTF-8 string at offset 0
 /ÃÃÃxxx/8  /ÃÃÃxxx/8
 Failed: invalid UTF-8 string at offset 0  Failed: invalid UTF-8 string at offset 0
   
/ÃÃÃxxx/8?DZSS/ÃÃÃxxx/8?DZSSO
 ------------------------------------------------------------------  ------------------------------------------------------------------
         Bra          Bra
         \X{c0}\X{c0}\X{c0}xxx          \X{c0}\X{c0}\X{c0}xxx
Line 80  Failed: invalid UTF-8 string at offset 0 Line 82  Failed: invalid UTF-8 string at offset 0
         End          End
 ------------------------------------------------------------------  ------------------------------------------------------------------
 Capturing subpattern count = 0  Capturing subpattern count = 0
Options: utf no_utf_checkOptions: no_auto_possessify utf no_utf_check
 First char = \x{c3}  First char = \x{c3}
 Need char = 'x'  Need char = 'x'
   
/abc/8/badutf/8
    Ã]    \xdf
Error -10 (bad UTF-8 string) offset=0 reason=6 
    à
 Error -10 (bad UTF-8 string) offset=0 reason=1  Error -10 (bad UTF-8 string) offset=0 reason=1
    ÃÃà   \xef
Error -10 (bad UTF-8 string) offset=0 reason=6Error -10 (bad UTF-8 string) offset=0 reason=2
    ÃÃÃ\?    \xef\x80
No match 
    \xe1\x88  
 Error -10 (bad UTF-8 string) offset=0 reason=1  Error -10 (bad UTF-8 string) offset=0 reason=1
    \P\xe1\x88     \xf7
 Error -10 (bad UTF-8 string) offset=0 reason=3
     \xf7\x80
 Error -10 (bad UTF-8 string) offset=0 reason=2
     \xf7\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=1  Error -10 (bad UTF-8 string) offset=0 reason=1
    \P\P\xe1\x88     \xfb
 Error -10 (bad UTF-8 string) offset=0 reason=4
     \xfb\x80
 Error -10 (bad UTF-8 string) offset=0 reason=3
     \xfb\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=2
     \xfb\x80\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=1
     \xfd
 Error -10 (bad UTF-8 string) offset=0 reason=5
     \xfd\x80
 Error -10 (bad UTF-8 string) offset=0 reason=4
     \xfd\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=3
     \xfd\x80\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=2
     \xfd\x80\x80\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=1
     \xdf\x7f
 Error -10 (bad UTF-8 string) offset=0 reason=6
     \xef\x7f\x80
 Error -10 (bad UTF-8 string) offset=0 reason=6
     \xef\x80\x7f
 Error -10 (bad UTF-8 string) offset=0 reason=7
     \xf7\x7f\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=6
     \xf7\x80\x7f\x80
 Error -10 (bad UTF-8 string) offset=0 reason=7
     \xf7\x80\x80\x7f
 Error -10 (bad UTF-8 string) offset=0 reason=8
     \xfb\x7f\x80\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=6
     \xfb\x80\x7f\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=7
     \xfb\x80\x80\x7f\x80
 Error -10 (bad UTF-8 string) offset=0 reason=8
     \xfb\x80\x80\x80\x7f
 Error -10 (bad UTF-8 string) offset=0 reason=9
     \xfd\x7f\x80\x80\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=6
     \xfd\x80\x7f\x80\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=7
     \xfd\x80\x80\x7f\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=8
     \xfd\x80\x80\x80\x7f\x80
 Error -10 (bad UTF-8 string) offset=0 reason=9
     \xfd\x80\x80\x80\x80\x7f
 Error -10 (bad UTF-8 string) offset=0 reason=10
     \xed\xa0\x80
 Error -10 (bad UTF-8 string) offset=0 reason=14
     \xc0\x8f
 Error -10 (bad UTF-8 string) offset=0 reason=15
     \xe0\x80\x8f
 Error -10 (bad UTF-8 string) offset=0 reason=16
     \xf0\x80\x80\x8f
 Error -10 (bad UTF-8 string) offset=0 reason=17
     \xf8\x80\x80\x80\x8f
 Error -10 (bad UTF-8 string) offset=0 reason=18
     \xfc\x80\x80\x80\x80\x8f
 Error -10 (bad UTF-8 string) offset=0 reason=19
     \x80
 Error -10 (bad UTF-8 string) offset=0 reason=20
     \xfe
 Error -10 (bad UTF-8 string) offset=0 reason=21
     \xff
 Error -10 (bad UTF-8 string) offset=0 reason=21
 
 /badutf/8
     \xfb\x80\x80\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=11
     \xfd\x80\x80\x80\x80\x80
 Error -10 (bad UTF-8 string) offset=0 reason=12
     \xf7\xbf\xbf\xbf
 Error -10 (bad UTF-8 string) offset=0 reason=13
 
 /shortutf/8
     \P\P\xdf
 Error -25 (short UTF-8 string) offset=0 reason=1  Error -25 (short UTF-8 string) offset=0 reason=1
    XX\xea    \P\P\xef
Error -10 (bad UTF-8 string) offset=2 reason=2Error -25 (short UTF-8 string) offset=0 reason=2
    \O0XX\xea    \P\P\xef\x80
Error -10 (bad UTF-8 string)Error -25 (short UTF-8 string) offset=0 reason=1
    \O1XX\xea    \P\P\xf7
Error -10 (bad UTF-8 string)Error -25 (short UTF-8 string) offset=0 reason=3
    \O2XX\xea    \P\P\xf7\x80
Error -10 (bad UTF-8 string) offset=2 reason=2Error -25 (short UTF-8 string) offset=0 reason=2
    XX\xf1    \P\P\xf7\x80\x80
Error -10 (bad UTF-8 string) offset=2 reason=3Error -25 (short UTF-8 string) offset=0 reason=1
    XX\xf8      \P\P\xfb
Error -10 (bad UTF-8 string) offset=2 reason=4Error -25 (short UTF-8 string) offset=0 reason=4
    XX\xfc    \P\P\xfb\x80
Error -10 (bad UTF-8 string) offset=2 reason=5Error -25 (short UTF-8 string) offset=0 reason=3
    ZZ\xea\xaf\x20YY    \P\P\xfb\x80\x80
Error -10 (bad UTF-8 string) offset=2 reason=7Error -25 (short UTF-8 string) offset=0 reason=2
    ZZ\xfd\xbf\xbf\x2f\xbf\xbfYY      \P\P\xfb\x80\x80\x80
Error -10 (bad UTF-8 string) offset=2 reason=8Error -25 (short UTF-8 string) offset=0 reason=1
    ZZ\xfd\xbf\xbf\xbf\x2f\xbfYY      \P\P\xfd
Error -10 (bad UTF-8 string) offset=2 reason=9Error -25 (short UTF-8 string) offset=0 reason=5
    ZZ\xfd\xbf\xbf\xbf\xbf\x2fYY      \P\P\xfd\x80
Error -10 (bad UTF-8 string) offset=2 reason=10Error -25 (short UTF-8 string) offset=0 reason=4
    ZZ\xffYY    \P\P\xfd\x80\x80
Error -10 (bad UTF-8 string) offset=2 reason=21Error -25 (short UTF-8 string) offset=0 reason=3
    ZZ\xfeYY      \P\P\xfd\x80\x80\x80
Error -10 (bad UTF-8 string) offset=2 reason=21Error -25 (short UTF-8 string) offset=0 reason=2
     \P\P\xfd\x80\x80\x80\x80
 Error -25 (short UTF-8 string) offset=0 reason=1
   
 /anything/8  /anything/8
     \xc0\x80      \xc0\x80
Line 430  No match Line 510  No match
 ------------------------------------------------------------------  ------------------------------------------------------------------
         Bra          Bra
         \x{100}{3}          \x{100}{3}
        \x{100}?        \x{100}?+
         Ket          Ket
         End          End
 ------------------------------------------------------------------  ------------------------------------------------------------------
Line 447  No set of starting bytes Line 527  No set of starting bytes
 ------------------------------------------------------------------  ------------------------------------------------------------------
         Bra          Bra
         CBra 1          CBra 1
        \x{100}+        \x{100}++
         Alt          Alt
         x          x
         Ket          Ket
Line 484  Starting byte set: a x \xc4  Line 564  Starting byte set: a x \xc4 
 ------------------------------------------------------------------  ------------------------------------------------------------------
         Bra          Bra
         CBra 1          CBra 1
        \x{100}{0,2}        \x{100}{0,2}+
         a          a
         Alt          Alt
         x          x
Line 504  Starting byte set: a x \xc4  Line 584  Starting byte set: a x \xc4 
         Bra          Bra
         CBra 1          CBra 1
         \x{100}          \x{100}
        \x{100}{0,1}        \x{100}{0,1}+
         a          a
         Alt          Alt
         x          x
Line 535  Need char = \x{80} Line 615  Need char = \x{80}
 ------------------------------------------------------------------  ------------------------------------------------------------------
         Bra          Bra
         a\x{100}          a\x{100}
        \x{101}*        \x{101}*+
         Ket          Ket
         End          End
 ------------------------------------------------------------------  ------------------------------------------------------------------
Line 548  Need char = \x{80} Line 628  Need char = \x{80}
 ------------------------------------------------------------------  ------------------------------------------------------------------
         Bra          Bra
         a\x{100}          a\x{100}
        \x{101}+        \x{101}++
         Ket          Ket
         End          End
 ------------------------------------------------------------------  ------------------------------------------------------------------
Line 560  Need char = \x{81} Line 640  Need char = \x{81}
 /[^\x{c4}]/DZ  /[^\x{c4}]/DZ
 ------------------------------------------------------------------  ------------------------------------------------------------------
         Bra          Bra
        [^\xc4]        [^\x{c4}]
         Ket          Ket
         End          End
 ------------------------------------------------------------------  ------------------------------------------------------------------
Line 606  Need char = \x{bf} Line 686  Need char = \x{bf}
 /[^\xff]/8DZ  /[^\xff]/8DZ
 ------------------------------------------------------------------  ------------------------------------------------------------------
         Bra          Bra
        [\x00-\xfe] (neg)        [^\x{ff}]
         Ket          Ket
         End          End
 ------------------------------------------------------------------  ------------------------------------------------------------------
Line 677  Failed: missing terminating ] for character class at o Line 757  Failed: missing terminating ] for character class at o
 /-- This tests the stricter UTF-8 check according to RFC 3629. --/   /-- This tests the stricter UTF-8 check according to RFC 3629. --/ 
           
 /X/8  /X/8
     \x{0}\x{d7ff}\x{e000}\x{10ffff}  
 No match  
     \x{d800}      \x{d800}
 Error -10 (bad UTF-8 string) offset=0 reason=14  Error -10 (bad UTF-8 string) offset=0 reason=14
     \x{d800}\?      \x{d800}\?
Line 708  No match Line 786  No match
   abcd\x{1234}pqr    abcd\x{1234}pqr
  0: \x{1234}   0: \x{1234}
   
/(*CRLF)(*UTF8)(*BSR_UNICODE)a\Rb/I/(*CRLF)(*UTF)(*BSR_UNICODE)a\Rb/I
 Capturing subpattern count = 0  Capturing subpattern count = 0
 Options: bsr_unicode utf  Options: bsr_unicode utf
 Forced newline sequence: CRLF  Forced newline sequence: CRLF
Line 785  Options: utf Line 863  Options: utf
 No first char  No first char
 Need char = 'x'  Need char = 'x'
 Subject length lower bound = 4  Subject length lower bound = 4
Starting byte set: \x09 \x0a \x0c \x0d \x20 x Starting byte set: \x09 \x0a \x0b \x0c \x0d \x20 x 
   
 /\sxxx\s/I8ST1  /\sxxx\s/I8ST1
 Capturing subpattern count = 0  Capturing subpattern count = 0
Line 868  Starting byte set: \xe1  Line 946  Starting byte set: \xe1 
 /[^\x{c4}]/8DZ  /[^\x{c4}]/8DZ
 ------------------------------------------------------------------  ------------------------------------------------------------------
         Bra          Bra
        [\x00-\xc3\xc5-\xff] (neg)        [^\x{c4}]
         Ket          Ket
         End          End
 ------------------------------------------------------------------  ------------------------------------------------------------------
Line 909  Capturing subpattern count = 0 Line 987  Capturing subpattern count = 0
 Options: utf  Options: utf
 First char = \x{c7}  First char = \x{c7}
 Need char = \x{bf}  Need char = \x{bf}
   
   /\w+\x{C4}/8BZ
   ------------------------------------------------------------------
           Bra
           \w++
           \x{c4}
           Ket
           End
   ------------------------------------------------------------------
       a\x{C4}\x{C4}
    0: a\x{c4}
   
   /\w+\x{C4}/8BZT1
   ------------------------------------------------------------------
           Bra
           \w+
           \x{c4}
           Ket
           End
   ------------------------------------------------------------------
       a\x{C4}\x{C4}
    0: a\x{c4}\x{c4}
       
   /\W+\x{C4}/8BZ
   ------------------------------------------------------------------
           Bra
           \W+
           \x{c4}
           Ket
           End
   ------------------------------------------------------------------
       !\x{C4}
    0: !\x{c4}
    
   /\W+\x{C4}/8BZT1
   ------------------------------------------------------------------
           Bra
           \W++
           \x{c4}
           Ket
           End
   ------------------------------------------------------------------
       !\x{C4}
    0: !\x{c4}
   
   /\W+\x{A1}/8BZ
   ------------------------------------------------------------------
           Bra
           \W+
           \x{a1}
           Ket
           End
   ------------------------------------------------------------------
       !\x{A1}
    0: !\x{a1}
    
   /\W+\x{A1}/8BZT1
   ------------------------------------------------------------------
           Bra
           \W+
           \x{a1}
           Ket
           End
   ------------------------------------------------------------------
       !\x{A1}
    0: !\x{a1}
   
   /X\s+\x{A0}/8BZ
   ------------------------------------------------------------------
           Bra
           X
           \s++
           \x{a0}
           Ket
           End
   ------------------------------------------------------------------
       X\x20\x{A0}\x{A0}
    0: X \x{a0}
   
   /X\s+\x{A0}/8BZT1
   ------------------------------------------------------------------
           Bra
           X
           \s+
           \x{a0}
           Ket
           End
   ------------------------------------------------------------------
       X\x20\x{A0}\x{A0}
    0: X \x{a0}\x{a0}
   
   /\S+\x{A0}/8BZ
   ------------------------------------------------------------------
           Bra
           \S+
           \x{a0}
           Ket
           End
   ------------------------------------------------------------------
       X\x{A0}\x{A0}
    0: X\x{a0}\x{a0}
   
   /\S+\x{A0}/8BZT1
   ------------------------------------------------------------------
           Bra
           \S++
           \x{a0}
           Ket
           End
   ------------------------------------------------------------------
       X\x{A0}\x{A0}
    0: X\x{a0}
   
   /\x{a0}+\s!/8BZ
   ------------------------------------------------------------------
           Bra
           \x{a0}++
           \s
           !
           Ket
           End
   ------------------------------------------------------------------
       \x{a0}\x20!
    0: \x{a0} !
   
   /\x{a0}+\s!/8BZT1
   ------------------------------------------------------------------
           Bra
           \x{a0}+
           \s
           !
           Ket
           End
   ------------------------------------------------------------------
       \x{a0}\x20!
    0: \x{a0} !
   
   /A/8
     \x{ff000041}
   ** Character \x{ff000041} is greater than 0x7fffffff and so cannot be converted to UTF-8
     \x{7f000041} 
   Error -10 (bad UTF-8 string) offset=0 reason=12
   
   /(*UTF8)abc/9
   Failed: setting UTF is disabled by the application at offset 0
   
   /abc/89
   Failed: setting UTF is disabled by the application at offset 0
   
 /-- End of testinput15 --/  /-- End of testinput15 --/

Removed from v.1.1.1.2  
changed lines
  Added in v.1.1.1.5


FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>