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
202
tools/pcre/testdata/testoutput15
vendored
202
tools/pcre/testdata/testoutput15
vendored
@ -1,5 +1,7 @@
|
||||
/-- This set of tests is for UTF-8 support, and is relevant only to the 8-bit
|
||||
library. --/
|
||||
/-- This set of tests is for UTF-8 support but not Unicode property support,
|
||||
and is relevant only to the 8-bit library. --/
|
||||
|
||||
< forbid W
|
||||
|
||||
/X(\C{3})/8
|
||||
X\x{1234}
|
||||
@ -72,7 +74,7 @@ Failed: invalid UTF-8 string at offset 0
|
||||
/<2F><><EFBFBD>xxx/8
|
||||
Failed: invalid UTF-8 string at offset 0
|
||||
|
||||
/<2F><><EFBFBD>xxx/8?DZSS
|
||||
/<2F><><EFBFBD>xxx/8?DZSSO
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
\X{c0}\X{c0}\X{c0}xxx
|
||||
@ -80,7 +82,7 @@ Failed: invalid UTF-8 string at offset 0
|
||||
End
|
||||
------------------------------------------------------------------
|
||||
Capturing subpattern count = 0
|
||||
Options: utf no_utf_check
|
||||
Options: no_auto_possessify utf no_utf_check
|
||||
First char = \x{c3}
|
||||
Need char = 'x'
|
||||
|
||||
@ -163,8 +165,6 @@ Error -10 (bad UTF-8 string) offset=0 reason=20
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=21
|
||||
\xff
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=21
|
||||
\xef\xb7\x90
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
|
||||
/badutf/8
|
||||
\xfb\x80\x80\x80\x80
|
||||
@ -250,140 +250,6 @@ No match
|
||||
\?\xfd\x83\x80\x80\x80\x80
|
||||
No match
|
||||
|
||||
/noncharacter/8
|
||||
\x{fffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{ffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{1fffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{1ffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{2fffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{2ffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{3fffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{3ffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{4fffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{4ffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{5fffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{5ffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{6fffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{6ffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{7fffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{7ffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{8fffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{8ffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{9fffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{9ffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{afffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{affff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{bfffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{bffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{cfffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{cffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{dfffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{dffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{efffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{effff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{ffffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{10fffe}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{10ffff}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdd0}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdd1}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdd2}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdd3}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdd4}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdd5}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdd6}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdd7}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdd8}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdd9}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdda}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fddb}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fddc}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fddd}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdde}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fddf}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fde0}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fde1}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fde2}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fde3}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fde4}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fde5}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fde6}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fde7}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fde8}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fde9}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdea}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdeb}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdec}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fded}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdee}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
\x{fdef}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=22
|
||||
|
||||
/\x{100}/8DZ
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
@ -615,7 +481,7 @@ 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
|
||||
@ -644,7 +510,7 @@ No match
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
\x{100}{3}
|
||||
\x{100}?
|
||||
\x{100}?+
|
||||
Ket
|
||||
End
|
||||
------------------------------------------------------------------
|
||||
@ -653,7 +519,7 @@ Options: utf
|
||||
First char = \x{c4}
|
||||
Need char = \x{80}
|
||||
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}
|
||||
|
||||
@ -661,7 +527,7 @@ No set of starting bytes
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
CBra 1
|
||||
\x{100}+
|
||||
\x{100}++
|
||||
Alt
|
||||
x
|
||||
Ket
|
||||
@ -673,7 +539,7 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: x \xc4
|
||||
Starting chars: x \xc4
|
||||
|
||||
/(\x{100}*a|x)/8SDZ
|
||||
------------------------------------------------------------------
|
||||
@ -692,13 +558,13 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: a x \xc4
|
||||
Starting chars: a x \xc4
|
||||
|
||||
/(\x{100}{0,2}a|x)/8SDZ
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
CBra 1
|
||||
\x{100}{0,2}
|
||||
\x{100}{0,2}+
|
||||
a
|
||||
Alt
|
||||
x
|
||||
@ -711,14 +577,14 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: a x \xc4
|
||||
Starting chars: a x \xc4
|
||||
|
||||
/(\x{100}{1,2}a|x)/8SDZ
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
CBra 1
|
||||
\x{100}
|
||||
\x{100}{0,1}
|
||||
\x{100}{0,1}+
|
||||
a
|
||||
Alt
|
||||
x
|
||||
@ -731,7 +597,7 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: x \xc4
|
||||
Starting chars: x \xc4
|
||||
|
||||
/\x{100}/8DZ
|
||||
------------------------------------------------------------------
|
||||
@ -749,7 +615,7 @@ Need char = \x{80}
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
a\x{100}
|
||||
\x{101}*
|
||||
\x{101}*+
|
||||
Ket
|
||||
End
|
||||
------------------------------------------------------------------
|
||||
@ -762,7 +628,7 @@ Need char = \x{80}
|
||||
------------------------------------------------------------------
|
||||
Bra
|
||||
a\x{100}
|
||||
\x{101}+
|
||||
\x{101}++
|
||||
Ket
|
||||
End
|
||||
------------------------------------------------------------------
|
||||
@ -891,8 +757,6 @@ Failed: missing terminating ] for character class at offset 15
|
||||
/-- This tests the stricter UTF-8 check according to RFC 3629. --/
|
||||
|
||||
/X/8
|
||||
\x{0}\x{d7ff}\x{e000}\x{10ffff}
|
||||
Error -10 (bad UTF-8 string) offset=7 reason=22
|
||||
\x{d800}
|
||||
Error -10 (bad UTF-8 string) offset=0 reason=14
|
||||
\x{d800}\?
|
||||
@ -935,7 +799,7 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \x09 \x20 \xc2 \xe1 \xe2 \xe3
|
||||
Starting chars: \x09 \x20 \xc2 \xe1 \xe2 \xe3
|
||||
ABC\x{09}
|
||||
0: \x{09}
|
||||
ABC\x{20}
|
||||
@ -961,7 +825,7 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \x0a \x0b \x0c \x0d \xc2 \xe2
|
||||
Starting chars: \x0a \x0b \x0c \x0d \xc2 \xe2
|
||||
ABC\x{0a}
|
||||
0: \x{0a}
|
||||
ABC\x{0b}
|
||||
@ -981,7 +845,7 @@ Options: utf
|
||||
No first char
|
||||
Need char = 'A'
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \x09 \x20 A \xc2 \xe1 \xe2 \xe3
|
||||
Starting chars: \x09 \x20 A \xc2 \xe1 \xe2 \xe3
|
||||
CDBABC
|
||||
0: A
|
||||
|
||||
@ -991,7 +855,7 @@ Options: utf
|
||||
No first char
|
||||
Need char = 'A'
|
||||
Subject length lower bound = 2
|
||||
Starting byte set: \x0a \x0b \x0c \x0d \xc2 \xe2
|
||||
Starting chars: \x0a \x0b \x0c \x0d \xc2 \xe2
|
||||
|
||||
/\s?xxx\s/8SI
|
||||
Capturing subpattern count = 0
|
||||
@ -999,7 +863,7 @@ 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
|
||||
@ -1007,7 +871,7 @@ Options: utf
|
||||
No first char
|
||||
Need char = 'x'
|
||||
Subject length lower bound = 5
|
||||
Starting byte set: \x09 \x0a \x0c \x0d \x20 \xc2
|
||||
Starting chars: \x09 \x0a \x0c \x0d \x20 \xc2
|
||||
AB\x{85}xxx\x{a0}XYZ
|
||||
0: \x{85}xxx\x{a0}
|
||||
AB\x{a0}xxx\x{85}XYZ
|
||||
@ -1019,7 +883,7 @@ 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
|
||||
@ -1053,7 +917,7 @@ Options: caseless utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \xe1
|
||||
Starting chars: \xe1
|
||||
|
||||
/\x{1234}+?/iS8I
|
||||
Capturing subpattern count = 0
|
||||
@ -1061,7 +925,7 @@ Options: caseless utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \xe1
|
||||
Starting chars: \xe1
|
||||
|
||||
/\x{1234}++/iS8I
|
||||
Capturing subpattern count = 0
|
||||
@ -1069,7 +933,7 @@ Options: caseless utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \xe1
|
||||
Starting chars: \xe1
|
||||
|
||||
/\x{1234}{2}/iS8I
|
||||
Capturing subpattern count = 0
|
||||
@ -1077,7 +941,7 @@ Options: caseless utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 2
|
||||
Starting byte set: \xe1
|
||||
Starting chars: \xe1
|
||||
|
||||
/[^\x{c4}]/8DZ
|
||||
------------------------------------------------------------------
|
||||
@ -1110,7 +974,7 @@ Options: utf
|
||||
No first char
|
||||
No need char
|
||||
Subject length lower bound = 1
|
||||
Starting byte set: \x0a \x0b \x0c \x0d \xc2 \xe2
|
||||
Starting chars: \x0a \x0b \x0c \x0d \xc2 \xe2
|
||||
|
||||
/\777/8DZ
|
||||
------------------------------------------------------------------
|
||||
@ -1266,4 +1130,10 @@ Need char = \x{bf}
|
||||
\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 --/
|
||||
|
||||
Reference in New Issue
Block a user