PCRE2Project/pcre2
1
0
Fork 0
mirror of https://github.com/PCRE2Project/pcre2.git synced 2025-10-17 07:04:13 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
pages
pcre2/testdata/testinput9
Nicholas Wilson 0d0ac3aa0f Update EBCDIC support to support testing on normal ASCII systems (#656) 
The pcre2test utility needs quite a few changes to accommodate this.
It is simpler to add a new mode to it, than to make it fully
EBCDIC-native. On an ASCII system, pcre2test performs ASCII I/O, but
tranlates the input when passing it to the fully-EBCDIC-supporting
library.
2025-02-12 22:31:00 +00:00

301 lines
12 KiB
Plaintext
Raw Permalink Blame History

# This set of tests is run only with the 8-bit library. They must not require
# UTF-8 or Unicode property support. */
#forbid_utf
#newline_default lf any anycrlf
#if !ebcdic
/a\xc4\xa3b/
a\N{U+123}b
\= Expect no match # error message (too big char)
a\x{0123}b
a\o{00443}b
a\443b
/fd bf bf bf bf bf/I,hex
\= Expect warning
\N{U+7fffffff}
\= Expect no match # error message (too big char)
\x{7fffffff}
#endif
/\x{100}/I
/\o{400}/I
#if !ebcdic
/ (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* # optional leading comment
(?: (?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
|
" (?: # opening quote...
[^\\\x80-\xff\n\015"] # Anything except backslash and quote
| # or
\\ [^\x80-\xff] # Escaped something (something != CR)
)* " # closing quote
) # initial word
(?: (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* \. (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* (?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
|
" (?: # opening quote...
[^\\\x80-\xff\n\015"] # Anything except backslash and quote
| # or
\\ [^\x80-\xff] # Escaped something (something != CR)
)* " # closing quote
) )* # further okay, if led by a period
(?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* @ (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* (?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
| \[ # [
(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff
\] # ]
) # initial subdomain
(?: #
(?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* \. # if led by a period...
(?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* (?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
| \[ # [
(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff
\] # ]
) # ...further okay
)*
# address
| # or
(?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
|
" (?: # opening quote...
[^\\\x80-\xff\n\015"] # Anything except backslash and quote
| # or
\\ [^\x80-\xff] # Escaped something (something != CR)
)* " # closing quote
) # one word, optionally followed by....
(?:
[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or...
\(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) | # comments, or...
" (?: # opening quote...
[^\\\x80-\xff\n\015"] # Anything except backslash and quote
| # or
\\ [^\x80-\xff] # Escaped something (something != CR)
)* " # closing quote
# quoted strings
)*
< (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* # leading <
(?: @ (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* (?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
| \[ # [
(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff
\] # ]
) # initial subdomain
(?: #
(?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* \. # if led by a period...
(?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* (?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
| \[ # [
(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff
\] # ]
) # ...further okay
)*
(?: (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* , (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* @ (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* (?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
| \[ # [
(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff
\] # ]
) # initial subdomain
(?: #
(?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* \. # if led by a period...
(?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* (?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
| \[ # [
(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff
\] # ]
) # ...further okay
)*
)* # further okay, if led by comma
: # closing colon
(?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* )? # optional route
(?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
|
" (?: # opening quote...
[^\\\x80-\xff\n\015"] # Anything except backslash and quote
| # or
\\ [^\x80-\xff] # Escaped something (something != CR)
)* " # closing quote
) # initial word
(?: (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* \. (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* (?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
|
" (?: # opening quote...
[^\\\x80-\xff\n\015"] # Anything except backslash and quote
| # or
\\ [^\x80-\xff] # Escaped something (something != CR)
)* " # closing quote
) )* # further okay, if led by a period
(?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* @ (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* (?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
| \[ # [
(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff
\] # ]
) # initial subdomain
(?: #
(?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* \. # if led by a period...
(?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* (?:
[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters...
(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
| \[ # [
(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff
\] # ]
) # ...further okay
)*
# address spec
(?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* > # trailing >
# name and address
) (?: [\040\t] | \(
(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )*
\) )* # optional trailing comment
/Ix
#endif
/\h/I
/\H/I
/\v/I
/\V/I
/\R/I
/[\h]/B
>\x09<
/[\h]+/B
>\x09\x20\xa0<
/[\v]/B
/[\H]/B
/[^\h]/B
/[\V]/B
#if !ebcdic
/[\x0a\V]/B
#endif
/\777/I
/(*:0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF)XX/mark
XX
/(*:0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF)XX/mark,alt_verbnames
XX
/(*:0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDE)XX/mark
XX
/(*:0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDEF0123456789ABCDE)XX/mark,alt_verbnames
XX
/\u0100/alt_bsux,allow_empty_class,match_unset_backref,dupnames
/[\u0100-\u0200]/alt_bsux,allow_empty_class,match_unset_backref,dupnames
#if !ebcdic
/[^\x00-a]{12,}[^b-\xff]*/B
#endif
/[^\s]*\s* [^\W]+\W+ [^\d]*?\d0 [^\d\w]{4,6}?\w*A/B
/(*MARK:a\x{100}b)z/alt_verbnames
/(*:*++++++++++++''''''''''''''''''''+''+++'+++x+++++++++++++++++++++++++++++++++++(++++++++++++++++++++:++++++%++:''''''''''''''''''''''''+++++++++++++++++++++++++++++++++++++++++++++++++++++-++++++++k+++++++''''+++'+++++++++++++++++++++++''''++++++++++++':ƿ)/
/(?i:A{1,}\6666666666)/
A\x{1b6}6666666
# Should cause an error
/abc/substitute_extended,replace=>\777<
abc
# Should cause an error
/abc/substitute_extended,replace=>\o{012345}<
abc
/i/turkish_casing
# End of testinput9
Reference in New Issue View Git Blame Copy Permalink