Regex: Update PCRE to v8.35.
I was über lazy at first, so took libs from SM. But actually it's quite easy to compile, so let's update to latest version \o/.
This commit is contained in:
Arkshine
74
tools/pcre/testdata/testoutput18-16
vendored
74
tools/pcre/testdata/testoutput18-16
vendored
@ -1,5 +1,7 @@
|
||||
/-- This set of tests is for UTF-16 and UTF-32 support, and is relevant only to the
|
||||
16- and 32-bit library. --/
|
||||
/-- This set of tests is for UTF-16 and UTF-32 support, and is relevant only to
|
||||
the 16- and 32-bit libraries. --/
|
||||
|
||||
< forbid W
|
||||
|
||||
/<2F><><EFBFBD>xxx/8?DZSS
|
||||
**Failed: invalid UTF-8 string cannot be converted to UTF-16
|
||||
@ -337,7 +339,7 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a
|
||||
Starting chars: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a
|
||||
\x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19
|
||||
\x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4
|
||||
5 6 7 8 9 : ; < = > ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y
|
||||
@ -367,7 +369,7 @@ No match
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
\x{100}{3}
|
||||
\x{100}?
|
||||
\x{100}?+
|
||||
Ket
|
||||
End
|
||||
------------------------------------------------------------------
|
||||
@ -376,7 +378,7 @@ Options: utf
|
||||
First char = \x{100}
|
||||
Need char = \x{100}
|
||||
Subject length lower bound = 3
|
||||
No set of starting bytes
|
||||
No starting char list
|
||||
\x{100}\x{100}\x{100}\x{100\x{100}
|
||||
0: \x{100}\x{100}\x{100}
|
||||
|
||||
@ -384,7 +386,7 @@ No set of starting bytes
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
CBra 1
|
||||
\x{100}+
|
||||
\x{100}++
|
||||
Alt
|
||||
x
|
||||
Ket
|
||||
@ -396,7 +398,7 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: x \xff
|
||||
Starting chars: x \xff
|
||||
|
||||
/(\x{100}*a|x)/8SDZ
|
||||
------------------------------------------------------------------
|
||||
@ -415,13 +417,13 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: a x \xff
|
||||
Starting chars: a x \xff
|
||||
|
||||
/(\x{100}{0,2}a|x)/8SDZ
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
CBra 1
|
||||
\x{100}{0,2}
|
||||
\x{100}{0,2}+
|
||||
a
|
||||
Alt
|
||||
x
|
||||
@ -434,14 +436,14 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: a x \xff
|
||||
Starting chars: a x \xff
|
||||
|
||||
/(\x{100}{1,2}a|x)/8SDZ
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
CBra 1
|
||||
\x{100}
|
||||
\x{100}{0,1}
|
||||
\x{100}{0,1}+
|
||||
a
|
||||
Alt
|
||||
x
|
||||
@ -454,7 +456,7 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: x \xff
|
||||
Starting chars: x \xff
|
||||
|
||||
/\x{100}/8DZ
|
||||
------------------------------------------------------------------
|
||||
@ -472,7 +474,7 @@ No need char
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
a\x{100}
|
||||
\x{101}*
|
||||
\x{101}*+
|
||||
Ket
|
||||
End
|
||||
------------------------------------------------------------------
|
||||
@ -485,7 +487,7 @@ Need char = \x{100}
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
a\x{100}
|
||||
\x{101}+
|
||||
\x{101}++
|
||||
Ket
|
||||
End
|
||||
------------------------------------------------------------------
|
||||
@ -608,8 +610,6 @@ Need char = 'X'
|
||||
Failed: missing terminating ] for character class at offset 13
|
||||
|
||||
/X/8
|
||||
\x{0}\x{d7ff}\x{e000}\x{10ffff}
|
||||
Error -10 (bad UTF-16 string) offset=4 reason=4
|
||||
\x{d800}
|
||||
Error -10 (bad UTF-16 string) offset=0 reason=1
|
||||
\x{d800}\?
|
||||
@ -634,8 +634,6 @@ No match
|
||||
** Failed: character \x{110000} is greater than 0x10ffff and so cannot be converted to UTF-16
|
||||
\x{d800}\x{1234}
|
||||
Error -10 (bad UTF-16 string) offset=1 reason=2
|
||||
\x{fffe}
|
||||
Error -10 (bad UTF-16 string) offset=0 reason=4
|
||||
|
||||
/(*UTF16)\x{11234}/
|
||||
abcd\x{11234}pqr
|
||||
@ -650,7 +648,7 @@ Need char = \x{de34}
|
||||
0: \x{11234}
|
||||
|
||||
/(*UTF-32)\x{11234}/
|
||||
Failed: (*VERB) not recognized at offset 5
|
||||
Failed: (*VERB) not recognized or malformed at offset 5
|
||||
|
||||
/(*CRLF)(*UTF16)(*BSR_UNICODE)a\Rb/I
|
||||
Capturing subpattern count = 0
|
||||
@ -660,7 +658,7 @@ First char = 'a'
|
||||
Need char = 'b'
|
||||
|
||||
/(*CRLF)(*UTF32)(*BSR_UNICODE)a\Rb/I
|
||||
Failed: (*VERB) not recognized at offset 12
|
||||
Failed: (*VERB) not recognized or malformed at offset 12
|
||||
|
||||
/\h/SI8
|
||||
Capturing subpattern count = 0
|
||||
@ -668,7 +666,7 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \x09 \x20 \xa0 \xff
|
||||
Starting chars: \x09 \x20 \xa0 \xff
|
||||
ABC\x{09}
|
||||
0: \x{09}
|
||||
ABC\x{20}
|
||||
@ -694,7 +692,7 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \x0a \x0b \x0c \x0d \x85 \xff
|
||||
Starting chars: \x0a \x0b \x0c \x0d \x85 \xff
|
||||
ABC\x{0a}
|
||||
0: \x{0a}
|
||||
ABC\x{0b}
|
||||
@ -714,19 +712,19 @@ Options: utf
|
||||
No first char
|
||||
Need char = 'A'
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \x09 \x20 A \xa0 \xff
|
||||
Starting chars: \x09 \x20 A \xa0 \xff
|
||||
CDBABC
|
||||
0: A
|
||||
\x{2000}ABC
|
||||
0: \x{2000}A
|
||||
|
||||
/\R*A/SI8
|
||||
/\R*A/SI8<bsr_unicode>
|
||||
Capturing subpattern count = 0
|
||||
Options: utf
|
||||
Options: bsr_unicode utf
|
||||
No first char
|
||||
Need char = 'A'
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \x0a \x0b \x0c \x0d A \x85 \xff
|
||||
Starting chars: \x0a \x0b \x0c \x0d A \x85 \xff
|
||||
CDBABC
|
||||
0: A
|
||||
\x{2028}A
|
||||
@ -738,7 +736,7 @@ Options: utf
|
||||
No first char
|
||||
Need char = 'A'
|
||||
Subject length lower bound = 2
|
||||
Starting byte set: \x0a \x0b \x0c \x0d \x85 \xff
|
||||
Starting chars: \x0a \x0b \x0c \x0d \x85 \xff
|
||||
|
||||
/\s?xxx\s/8SI
|
||||
Capturing subpattern count = 0
|
||||
@ -746,7 +744,7 @@ Options: utf
|
||||
No first char
|
||||
Need char = 'x'
|
||||
Subject length lower bound = 4
|
||||
Starting byte set: \x09 \x0a \x0c \x0d \x20 x
|
||||
Starting chars: \x09 \x0a \x0b \x0c \x0d \x20 x
|
||||
|
||||
/\sxxx\s/I8ST1
|
||||
Capturing subpattern count = 0
|
||||
@ -754,7 +752,7 @@ Options: utf
|
||||
No first char
|
||||
Need char = 'x'
|
||||
Subject length lower bound = 5
|
||||
Starting byte set: \x09 \x0a \x0c \x0d \x20 \x85 \xa0
|
||||
Starting chars: \x09 \x0a \x0c \x0d \x20 \x85 \xa0
|
||||
AB\x{85}xxx\x{a0}XYZ
|
||||
0: \x{85}xxx\x{a0}
|
||||
AB\x{a0}xxx\x{85}XYZ
|
||||
@ -766,7 +764,7 @@ Options: utf
|
||||
No first char
|
||||
Need char = ' '
|
||||
Subject length lower bound = 3
|
||||
Starting byte set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0b \x0e
|
||||
Starting chars: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0b \x0e
|
||||
\x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d
|
||||
\x1e \x1f ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 9 : ; < = > ? @
|
||||
A B C D E F G H I J K L M N O P Q R S T U V W X Y Z [ \ ] ^ _ ` a b c d e
|
||||
@ -805,7 +803,7 @@ Options: caseless utf
|
||||
First char = \x{1234}
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
No set of starting bytes
|
||||
No starting char list
|
||||
|
||||
/\x{1234}+?/iS8I
|
||||
Capturing subpattern count = 0
|
||||
@ -813,7 +811,7 @@ Options: caseless utf
|
||||
First char = \x{1234}
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
No set of starting bytes
|
||||
No starting char list
|
||||
|
||||
/\x{1234}++/iS8I
|
||||
Capturing subpattern count = 0
|
||||
@ -821,7 +819,7 @@ Options: caseless utf
|
||||
First char = \x{1234}
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
No set of starting bytes
|
||||
No starting char list
|
||||
|
||||
/\x{1234}{2}/iS8I
|
||||
Capturing subpattern count = 0
|
||||
@ -829,7 +827,7 @@ Options: caseless utf
|
||||
First char = \x{1234}
|
||||
Need char = \x{1234}
|
||||
Subject length lower bound = 2
|
||||
No set of starting bytes
|
||||
No starting char list
|
||||
|
||||
/[^\x{c4}]/8DZ
|
||||
------------------------------------------------------------------
|
||||
@ -862,7 +860,7 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \x0a \x0b \x0c \x0d \x85 \xff
|
||||
Starting chars: \x0a \x0b \x0c \x0d \x85 \xff
|
||||
|
||||
/-- Check bad offset --/
|
||||
|
||||
@ -1019,4 +1017,10 @@ Failed: invalid UTF-16 string at offset 0
|
||||
\x{a0}\x20!
|
||||
0: \x{a0} !
|
||||
|
||||
/(*UTF)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 testinput18 --/
|
||||
|
||||
Reference in New Issue
Block a user