/-- This set of tests is for features that are compatible with all versions of Perl >= 5.10, in non-UTF-8 mode. It should run clean for the 8-bit, 16-bit, and 32-bit PCRE libraries. --/ < forbid 89?=ABCDEFfGILMNPTUWXZ< /the quick brown fox/ the quick brown fox The quick brown FOX What do you know about the quick brown fox? What do you know about THE QUICK BROWN FOX? /The quick brown fox/i the quick brown fox The quick brown FOX What do you know about the quick brown fox? What do you know about THE QUICK BROWN FOX? /abcd\t\n\r\f\a\e\071\x3b\$\\\?caxyz/ abcd\t\n\r\f\a\e9;\$\\?caxyz /a*abc?xyz+pqr{3}ab{2,}xy{4,5}pq{0,6}AB{0,}zz/ abxyzpqrrrabbxyyyypqAzz abxyzpqrrrabbxyyyypqAzz aabxyzpqrrrabbxyyyypqAzz aaabxyzpqrrrabbxyyyypqAzz aaaabxyzpqrrrabbxyyyypqAzz abcxyzpqrrrabbxyyyypqAzz aabcxyzpqrrrabbxyyyypqAzz aaabcxyzpqrrrabbxyyyypAzz aaabcxyzpqrrrabbxyyyypqAzz aaabcxyzpqrrrabbxyyyypqqAzz aaabcxyzpqrrrabbxyyyypqqqAzz aaabcxyzpqrrrabbxyyyypqqqqAzz aaabcxyzpqrrrabbxyyyypqqqqqAzz aaabcxyzpqrrrabbxyyyypqqqqqqAzz aaaabcxyzpqrrrabbxyyyypqAzz abxyzzpqrrrabbxyyyypqAzz aabxyzzzpqrrrabbxyyyypqAzz aaabxyzzzzpqrrrabbxyyyypqAzz aaaabxyzzzzpqrrrabbxyyyypqAzz abcxyzzpqrrrabbxyyyypqAzz aabcxyzzzpqrrrabbxyyyypqAzz aaabcxyzzzzpqrrrabbxyyyypqAzz aaaabcxyzzzzpqrrrabbxyyyypqAzz aaaabcxyzzzzpqrrrabbbxyyyypqAzz aaaabcxyzzzzpqrrrabbbxyyyyypqAzz aaabcxyzpqrrrabbxyyyypABzz aaabcxyzpqrrrabbxyyyypABBzz >>>aaabxyzpqrrrabbxyyyypqAzz >aaaabxyzpqrrrabbxyyyypqAzz >>>>abcxyzpqrrrabbxyyyypqAzz *** Failers abxyzpqrrabbxyyyypqAzz abxyzpqrrrrabbxyyyypqAzz abxyzpqrrrabxyyyypqAzz aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz aaaabcxyzzzzpqrrrabbbxyyypqAzz aaabcxyzpqrrrabbxyyyypqqqqqqqAzz /^(abc){1,2}zz/ abczz abcabczz *** Failers zz abcabcabczz >>abczz /^(b+?|a){1,2}?c/ bc bbc bbbc bac bbac aac abbbbbbbbbbbc bbbbbbbbbbbac *** Failers aaac abbbbbbbbbbbac /^(b+|a){1,2}c/ bc bbc bbbc bac bbac aac abbbbbbbbbbbc bbbbbbbbbbbac *** Failers aaac abbbbbbbbbbbac /^(b+|a){1,2}?bc/ bbc /^(b*|ba){1,2}?bc/ babc bbabc bababc *** Failers bababbc babababc /^(ba|b*){1,2}?bc/ babc bbabc bababc *** Failers bababbc babababc /^\ca\cA\c[\c{\c:/ \x01\x01\e;z /^[ab\]cde]/ athing bthing ]thing cthing dthing ething *** Failers fthing [thing \\thing /^[]cde]/ ]thing cthing dthing ething *** Failers athing fthing /^[^ab\]cde]/ fthing [thing \\thing *** Failers athing bthing ]thing cthing dthing ething /^[^]cde]/ athing fthing *** Failers ]thing cthing dthing ething /^\/ /^/ /^[0-9]+$/ 0 1 2 3 4 5 6 7 8 9 10 100 *** Failers abc /^.*nter/ enter inter uponter /^xxx[0-9]+$/ xxx0 xxx1234 *** Failers xxx /^.+[0-9][0-9][0-9]$/ x123 xx123 123456 *** Failers 123 x1234 /^.+?[0-9][0-9][0-9]$/ x123 xx123 123456 *** Failers 123 x1234 /^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ abc!pqr=apquxz.ixr.zzz.ac.uk *** Failers !pqr=apquxz.ixr.zzz.ac.uk abc!=apquxz.ixr.zzz.ac.uk abc!pqr=apquxz:ixr.zzz.ac.uk abc!pqr=apquxz.ixr.zzz.ac.ukk /:/ Well, we need a colon: somewhere *** Fail if we don't /([\da-f:]+)$/i 0abc abc fed E :: 5f03:12C0::932e fed def Any old stuff *** Failers 0zzz gzzz fed\x20 Any old rubbish /^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ .1.2.3 A.12.123.0 *** Failers .1.2.3333 1.2.3 1234.2.3 /^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ 1 IN SOA non-sp1 non-sp2( 1 IN SOA non-sp1 non-sp2 ( *** Failers 1IN SOA non-sp1 non-sp2( /^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ a. Z. 2. ab-c.pq-r. sxk.zzz.ac.uk. x-.y-. *** Failers -abc.peq. /^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ *.a *.b0-a *.c3-b.c *.c-a.b-c *** Failers *.0 *.a- *.a-b.c- *.c-a.0-c /^(?=ab(de))(abd)(e)/ abde /^(?!(ab)de|x)(abd)(f)/ abdf /^(?=(ab(cd)))(ab)/ abcd /^[\da-f](\.[\da-f])*$/i a.b.c.d A.B.C.D a.b.c.1.2.3.C /^\".*\"\s*(;.*)?$/ \"1234\" \"abcd\" ; \"\" ; rhubarb *** Failers \"1234\" : things /^$/ \ *** Failers / ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x ab c *** Failers abc ab cde /(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ ab c *** Failers abc ab cde /^ a\ b[c ]d $/x a bcd a b d *** Failers abcd ab d /^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ abcdefhijklm /^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ abcdefhijklm /^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ a+ Z0+\x08\n\x1d\x12 /^[.^$|()*+?{,}]+/ .^\$(*+)|{?,?} /^a*\w/ z az aaaz a aa aaaa a+ aa+ /^a*?\w/ z az aaaz a aa aaaa a+ aa+ /^a+\w/ az aaaz aa aaaa aa+ /^a+?\w/ az aaaz aa aaaa aa+ /^\d{8}\w{2,}/ 1234567890 12345678ab 12345678__ *** Failers 1234567 /^[aeiou\d]{4,5}$/ uoie 1234 12345 aaaaa *** Failers 123456 /^[aeiou\d]{4,5}?/ uoie 1234 12345 aaaaa 123456 /\A(abc|def)=(\1){2,3}\Z/ abc=abcabc def=defdefdef *** Failers abc=defdef /^(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\11*(\3\4)\1(?#)2$/ abcdefghijkcda2 abcdefghijkkkkcda2 /(cat(a(ract|tonic)|erpillar)) \1()2(3)/ cataract cataract23 catatonic catatonic23 caterpillar caterpillar23 /^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ From abcd Mon Sep 01 12:33:02 1997 /^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ From abcd Mon Sep 01 12:33:02 1997 From abcd Mon Sep 1 12:33:02 1997 *** Failers From abcd Sep 01 12:33:02 1997 /^12.34/s 12\n34 12\r34 /\w+(?=\t)/ the quick brown\t fox /foo(?!bar)(.*)/ foobar is foolish see? /(?:(?!foo)...|^.{0,2})bar(.*)/ foobar crowbar etc barrel 2barrel A barrel /^(\D*)(?=\d)(?!123)/ abc456 *** Failers abc123 /^1234(?# test newlines inside)/ 1234 /^1234 #comment in extended re /x 1234 /#rhubarb abcd/x abcd /^abcd#rhubarb/x abcd /^(a)\1{2,3}(.)/ aaab aaaab aaaaab aaaaaab /(?!^)abc/ the abc *** Failers abc /(?=^)abc/ abc *** Failers the abc /^[ab]{1,3}(ab*|b)/ aabbbbb /^[ab]{1,3}?(ab*|b)/ aabbbbb /^[ab]{1,3}?(ab*?|b)/ aabbbbb /^[ab]{1,3}(ab*?|b)/ aabbbbb / (?: [\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 /x Alan Other user\@dom.ain \"A. Other\" (a comment) A. Other (a comment) \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay A missing angle @,;:".\\\[\]\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 # Atom | # or " # " [^\\\x80-\xff\n\015"] * # normal (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* " # " # Quoted string ) [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. (?: \. [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. (?: [^(\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 # Atom | # or " # " [^\\\x80-\xff\n\015"] * # normal (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* " # " # Quoted string ) [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. # additional words )* @ [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. (?: [^(\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 \] # ] ) [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. # optional trailing comments (?: \. [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. (?: [^(\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 \] # ] ) [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. # optional trailing comments )* # 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 # Atom | # or " # " [^\\\x80-\xff\n\015"] * # normal (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* " # " # Quoted string ) # leading word [^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces (?: (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) | " # " [^\\\x80-\xff\n\015"] * # normal (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* " # " ) # "special" comment or quoted string [^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" )* < [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. # < (?: @ [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. (?: [^(\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 \] # ] ) [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. # optional trailing comments (?: \. [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. (?: [^(\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 \] # ] ) [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. # optional trailing comments )* (?: , [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. @ [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. (?: [^(\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 \] # ] ) [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. # optional trailing comments (?: \. [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. (?: [^(\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 \] # ] ) [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. # optional trailing comments )* )* # additional domains : [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. # optional trailing comments )? # 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 # Atom | # or " # " [^\\\x80-\xff\n\015"] * # normal (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* " # " # Quoted string ) [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. (?: \. [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. (?: [^(\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 # Atom | # or " # " [^\\\x80-\xff\n\015"] * # normal (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* " # " # Quoted string ) [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. # additional words )* @ [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. (?: [^(\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 \] # ] ) [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. # optional trailing comments (?: \. [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. (?: [^(\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 \] # ] ) [\040\t]* # Nab whitespace. (?: \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: # ( (?: \\ [^\x80-\xff] | \( # ( [^\\\x80-\xff\n\015()] * # normal* (?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* \) # ) ) # special [^\\\x80-\xff\n\015()] * # normal* )* # )* \) # ) [\040\t]* )* # If comment found, allow more spaces. # optional trailing comments )* # address spec > # > # name and address ) /x Alan Other user\@dom.ain \"A. Other\" (a comment) A. Other (a comment) \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay A missing angle ]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide /a[^a]b/ acb a\nb /a.b/ acb *** Failers a\nb /a[^a]b/s acb a\nb /a.b/s acb a\nb /^(b+?|a){1,2}?c/ bac bbac bbbac bbbbac bbbbbac /^(b+|a){1,2}?c/ bac bbac bbbac bbbbac bbbbbac /(?!\A)x/m x\nb\n a\bx\n /\x0{ab}/ \0{ab} /(A|B)*?CD/ CD /(A|B)*CD/ CD /(AB)*?\1/ ABABAB /(AB)*\1/ ABABAB /(?.*/)foo" /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ "(?>.*/)foo" /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo /(?>(\.\d\d[1-9]?))\d+/ 1.230003938 1.875000282 *** Failers 1.235 /^((?>\w+)|(?>\s+))*$/ now is the time for all good men to come to the aid of the party *** Failers this is not a line with only words and spaces! /(\d+)(\w)/ 12345a 12345+ /((?>\d+))(\w)/ 12345a *** Failers 12345+ /(?>a+)b/ aaab /((?>a+)b)/ aaab /(?>(a+))b/ aaab /(?>b)+/ aaabbbccc /(?>a+|b+|c+)*c/ aaabbbbccccd /((?>[^()]+)|\([^()]*\))+/ ((abc(ade)ufh()()x /\(((?>[^()]+)|\([^()]+\))+\)/ (abc) (abc(def)xyz) *** Failers ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa /a(?-i)b/i ab Ab *** Failers aB AB /(a (?x)b c)d e/ a bcd e *** Failers a b cd e abcd e a bcde /(a b(?x)c d (?-x)e f)/ a bcde f *** Failers abcdef /(a(?i)b)c/ abc aBc *** Failers abC aBC Abc ABc ABC AbC /a(?i:b)c/ abc aBc *** Failers ABC abC aBC /a(?i:b)*c/ aBc aBBc *** Failers aBC aBBC /a(?=b(?i)c)\w\wd/ abcd abCd *** Failers aBCd abcD /(?s-i:more.*than).*million/i more than million more than MILLION more \n than Million *** Failers MORE THAN MILLION more \n than \n million /(?:(?s-i)more.*than).*million/i more than million more than MILLION more \n than Million *** Failers MORE THAN MILLION more \n than \n million /(?>a(?i)b+)+c/ abc aBbc aBBc *** Failers Abc abAb abbC /(?=a(?i)b)\w\wc/ abc aBc *** Failers Ab abC aBC /(?<=a(?i)b)(\w\w)c/ abxxc aBxxc *** Failers Abxxc ABxxc abxxC /(?:(a)|b)(?(1)A|B)/ aA bB *** Failers aB bA /^(a)?(?(1)a|b)+$/ aa b bb *** Failers ab /^(?(?=abc)\w{3}:|\d\d)$/ abc: 12 *** Failers 123 xyz /^(?(?!abc)\d\d|\w{3}:)$/ abc: 12 *** Failers 123 xyz /(?(?<=foo)bar|cat)/ foobar cat fcat focat *** Failers foocat /(?(?a*)*/ a aa aaaa /(abc|)+/ abc abcabc abcabcabc xyz /([a]*)*/ a aaaaa /([ab]*)*/ a b ababab aaaabcde bbbb /([^a]*)*/ b bbbb aaa /([^ab]*)*/ cccc abab /([a]*?)*/ a aaaa /([ab]*?)*/ a b abab baba /([^a]*?)*/ b bbbb aaa /([^ab]*?)*/ c cccc baba /(?>a*)*/ a aaabcde /((?>a*))*/ aaaaa aabbaa /((?>a*?))*/ aaaaa aabbaa /(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x 12-sep-98 12-09-98 *** Failers sep-12-98 /(?<=(foo))bar\1/ foobarfoo foobarfootling *** Failers foobar barfoo /(?i:saturday|sunday)/ saturday sunday Saturday Sunday SATURDAY SUNDAY SunDay /(a(?i)bc|BB)x/ abcx aBCx bbx BBx *** Failers abcX aBCX bbX BBX /^([ab](?i)[cd]|[ef])/ ac aC bD elephant Europe frog France *** Failers Africa /^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ ab aBd xy xY zebra Zambesi *** Failers aCD XY /(?<=foo\n)^bar/m foo\nbar *** Failers bar baz\nbar /(?<=(?]&/ <&OUT /^(a\1?){4}$/ aaaaaaaaaa *** Failers AB aaaaaaaaa aaaaaaaaaaa /^(a(?(1)\1)){4}$/ aaaaaaaaaa *** Failers aaaaaaaaa aaaaaaaaaaa /(?:(f)(o)(o)|(b)(a)(r))*/ foobar /(?<=a)b/ ab *** Failers cb b /(?a+)ab/ /(?>a+)b/ aaab /([[:]+)/ a:[b]: /([[=]+)/ a=[b]= /([[.]+)/ a.[b]. /((?>a+)b)/ aaab /(?>(a+))b/ aaab /((?>[^()]+)|\([^()]*\))+/ ((abc(ade)ufh()()x /a\Z/ *** Failers aaab a\nb\n /b\Z/ a\nb\n /b\z/ /b\Z/ a\nb /b\z/ a\nb *** Failers /^(?>(?(1)\.|())[^\W_](?>[a-z0-9-]*[^\W_])?)+$/ a abc a-b 0-9 a.b 5.6.7 the.quick.brown.fox a100.b200.300c 12-ab.1245 *** Failers \ .a -a a- a. a_b a.- a.. ab..bc the.quick.brown.fox- the.quick.brown.fox. the.quick.brown.fox_ the.quick.brown.fox+ /(?>.*)(?<=(abcd|wxyz))/ alphabetabcd endingwxyz *** Failers a rather long string that doesn't end with one of them /word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ word cat dog elephant mussel cow horse canary baboon snake shark otherword word cat dog elephant mussel cow horse canary baboon snake shark /word (?>[a-zA-Z0-9]+ ){0,30}otherword/ word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope /(?<=\d{3}(?!999))foo/ 999foo 123999foo *** Failers 123abcfoo /(?<=(?!...999)\d{3})foo/ 999foo 123999foo *** Failers 123abcfoo /(?<=\d{3}(?!999)...)foo/ 123abcfoo 123456foo *** Failers 123999foo /(?<=\d{3}...)(?\s*)=(?>\s*) # find Z)+|A)*/ ZABCDEFG /((?>)+|A)*/ ZABCDEFG /a*/g abbab /^[\d-a]/ abcde -things 0digit *** Failers bcdef /[[:space:]]+/ > \x09\x0a\x0c\x0d\x0b< /[[:blank:]]+/ > \x09\x0a\x0c\x0d\x0b< /[\s]+/ > \x09\x0a\x0c\x0d\x0b< /\s+/ > \x09\x0a\x0c\x0d\x0b< /a b/x ab /(?!\A)x/m a\nxb\n /(?!^)x/m a\nxb\n /abc\Qabc\Eabc/ abcabcabc /abc\Q(*+|\Eabc/ abc(*+|abc / abc\Q abc\Eabc/x abc abcabc *** Failers abcabcabc /abc#comment \Q#not comment literal\E/x abc#not comment\n literal /abc#comment \Q#not comment literal/x abc#not comment\n literal /abc#comment \Q#not comment literal\E #more comment /x abc#not comment\n literal /abc#comment \Q#not comment literal\E #more comment/x abc#not comment\n literal /\Qabc\$xyz\E/ abc\\\$xyz /\Qabc\E\$\Qxyz\E/ abc\$xyz /\Gabc/ abc *** Failers xyzabc /\Gabc./g abc1abc2xyzabc3 /abc./g abc1abc2xyzabc3 /a(?x: b c )d/ XabcdY *** Failers Xa b c d Y /((?x)x y z | a b c)/ XabcY AxyzB /(?i)AB(?-i)C/ XabCY *** Failers XabcY /((?i)AB(?-i)C|D)E/ abCE DE *** Failers abcE abCe dE De /(.*)\d+\1/ abc123abc abc123bc /(.*)\d+\1/s abc123abc abc123bc /((.*))\d+\1/ abc123abc abc123bc /-- This tests for an IPv6 address in the form where it can have up to eight components, one and only one of which is empty. This must be an internal component. --/ /^(?!:) # colon disallowed at start (?: # start of item (?: [0-9a-f]{1,4} | # 1-4 hex digits or (?(1)0 | () ) ) # if null previously matched, fail; else null : # followed by colon ){1,7} # end item; 1-7 of them required [0-9a-f]{1,4} $ # final hex number at end of string (?(1)|.) # check that there was an empty component /xi a123::a123 a123:b342::abcd a123:b342::324e:abcd a123:ddde:b342::324e:abcd a123:ddde:b342::324e:dcba:abcd a123:ddde:9999:b342::324e:dcba:abcd *** Failers 1:2:3:4:5:6:7:8 a123:bce:ddde:9999:b342::324e:dcba:abcd a123::9999:b342::324e:dcba:abcd abcde:2:3:4:5:6:7:8 ::1 abcd:fee0:123:: :1 1: /[z\Qa-d]\E]/ z a - d ] *** Failers b /[\z\C]/ z C /\M/ M /(a+)*b/ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa /(?i)reg(?:ul(?:[a]|ae)r|ex)/ REGular regulaer Regex regulr /[--]+/ /(?<=Z)X./ \x84XAZXB /ab cd (?x) de fg/ ab cd defg /ab cd(?x) de fg/ ab cddefg ** Failers abcddefg /(?a|)*\d/ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 /(?:a|)*\d/ aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 /\Z/g abc\n /^(?s)(?>.*)(?(a))b|(a)c/ ac /(?=(a))ab|(a)c/ ac /((?>(a))b|(a)c)/ ac /((?>(a))b|(a)c)++/ ac /(?:(?>(a))b|(a)c)++/ ac /(?=(?>(a))b|(a)c)(..)/ ac /(?>(?>(a))b|(a)c)/ ac /(?:(?>([ab])))+a=/+ =ba= /(?>([ab]))+a=/+ =ba= /((?>(a+)b)+(aabab))/ aaaabaaabaabab /(?>a+|ab)+?c/ aabc /(?>a+|ab)+c/ aabc /(?:a+|ab)+c/ aabc /(?(?=(a))a)/ a /(?(?=(a))a)(b)/ ab /^(?:a|ab)++c/ aaaabc /^(?>a|ab)++c/ aaaabc /^(?:a|ab)+c/ aaaabc /(?=abc){3}abc/+ abcabcabc ** Failers xyz /(?=abc)+abc/+ abcabcabc ** Failers xyz /(?=abc)++abc/+ abcabcabc ** Failers xyz /(?=abc){0}xyz/ xyz /(?=abc){1}xyz/ ** Failers xyz /(?=(a))?./ ab bc /(?=(a))??./ ab bc /^(?=(?1))?[az]([abc])d/ abd zcdxx /^(?!a){0}\w+/ aaaaa /(?<=(abc))?xyz/ abcxyz pqrxyz /^[\g]+/ ggg<<>> ** Failers \\ga /^[\ga]+/ gggagagaxyz /^[:a[:digit:]]+/ aaaa444:::Z /^[:a[:digit:]:b]+/ aaaa444:::bbbZ /[:a]xxx[b:]/ :xxx: /(?<=a{2})b/i xaabc ** Failers xabc /(?XNNNYZ > X NYQZ ** Failers >XYZ > X NY Z /\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ >XY\x0aZ\x0aA\x0bNN\x0c >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c /(foo)\Kbar/ foobar /(foo)(\Kbar|baz)/ foobar foobaz /(foo\Kbar)baz/ foobarbaz /abc\K|def\K/g+ Xabcdefghi /ab\Kc|de\Kf/g+ Xabcdefghi /(?=C)/g+ ABCDECBA /^abc\K/+ abcdef ** Failers defabcxyz /^(a(b))\1\g1\g{1}\g-1\g{-1}\g{-02}Z/ ababababbbabZXXXX /(?tom|bon)-\g{A}/ tom-tom bon-bon /(^(a|b\g{-1}))/ bacxxx /(?|(abc)|(xyz))\1/ abcabc xyzxyz ** Failers abcxyz xyzabc /(?|(abc)|(xyz))(?1)/ abcabc xyzabc ** Failers xyzxyz /^X(?5)(a)(?|(b)|(q))(c)(d)(Y)/ XYabcdY /^X(?7)(a)(?|(b|(r)(s))|(q))(c)(d)(Y)/ XYabcdY /^X(?7)(a)(?|(b|(?|(r)|(t))(s))|(q))(c)(d)(Y)/ XYabcdY /(?'abc'\w+):\k{2}/ a:aaxyz ab:ababxyz ** Failers a:axyz ab:abxyz /(?'abc'\w+):\g{abc}{2}/ a:aaxyz ab:ababxyz ** Failers a:axyz ab:abxyz /^(?a)? (?()b|c) (?('ab')d|e)/x abd ce /^(a.)\g-1Z/ aXaXZ /^(a.)\g{-1}Z/ aXaXZ /^(?(DEFINE) (? a) (? b) ) (?&A) (?&B) /x abcd /(?(?&NAME_PAT))\s+(?(?&ADDRESS_PAT)) (?(DEFINE) (?[a-z]+) (?\d+) )/x metcalfe 33 /(?(DEFINE)(?2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))\b(?&byte)(\.(?&byte)){3}/ 1.2.3.4 131.111.10.206 10.0.0.0 ** Failers 10.6 455.3.4.5 /\b(?&byte)(\.(?&byte)){3}(?(DEFINE)(?2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))/ 1.2.3.4 131.111.10.206 10.0.0.0 ** Failers 10.6 455.3.4.5 /^(\w++|\s++)*$/ now is the time for all good men to come to the aid of the party *** Failers this is not a line with only words and spaces! /(\d++)(\w)/ 12345a *** Failers 12345+ /a++b/ aaab /(a++b)/ aaab /(a++)b/ aaab /([^()]++|\([^()]*\))+/ ((abc(ade)ufh()()x /\(([^()]++|\([^()]+\))+\)/ (abc) (abc(def)xyz) *** Failers ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa /^([^()]|\((?1)*\))*$/ abc a(b)c a(b(c))d *** Failers) a(b(c)d /^>abc>([^()]|\((?1)*\))*abc>123abc>1(2)3abc>(1(2)3)]*+) | (?2)) * >))/x <> hij> hij> def> *** Failers a)(?<=b(?&X))/ baz /^(?|(abc)|(def))\1/ abcabc defdef ** Failers abcdef defabc /^(?|(abc)|(def))(?1)/ abcabc defabc ** Failers defdef abcdef /(?:a(? (?')|(?")) |b(? (?')|(?")) ) (?('quote')[a-z]+|[0-9]+)/xJ a\"aaaaa b\"aaaaa ** Failers b\"11111 /(?:(?1)|B)(A(*F)|C)/ ABCD CCD ** Failers CAD /^(?:(?1)|B)(A(*F)|C)/ CCD BCD ** Failers ABCD CAD BAD /(?:(?1)|B)(A(*ACCEPT)XX|C)D/ AAD ACD BAD BCD BAX ** Failers ACX ABC /(?(DEFINE)(A))B(?1)C/ BAC /(?(DEFINE)((A)\2))B(?1)C/ BAAC /(? \( ( [^()]++ | (?&pn) )* \) )/x (ab(cd)ef) /^(?=a(*SKIP)b|ac)/ ** Failers ac /^(?=a(*PRUNE)b)/ ab ** Failers ac /^(?=a(*ACCEPT)b)/ ac /(?>a\Kb)/ ab /((?>a\Kb))/ ab /(a\Kb)/ ab /^a\Kcz|ac/ ac /(?>a\Kbz|ab)/ ab /^(?&t)(?(DEFINE)(?a\Kb))$/ ab /^([^()]|\((?1)*\))*$/ a(b)c a(b(c)d)e /(?P(?P0)(?P>L1)|(?P>L2))/ 0 00 0000 /(?P(?P0)|(?P>L2)(?P>L1))/ 0 00 0000 /--- This one does fail, as expected, in Perl. It needs the complex item at the end of the pattern. A single letter instead of (B|D) makes it not fail, which I think is a Perl bug. --- / /A(*COMMIT)(B|D)/ ACABX /--- Check the use of names for failure ---/ /^(A(*PRUNE:A)B|C(*PRUNE:B)D)/K ** Failers AC CB /--- Force no study, otherwise mark is not seen. The studied version is in test 2 because it isn't Perl-compatible. ---/ /(*MARK:A)(*SKIP:B)(C|X)/KSS C D /^(A(*THEN:A)B|C(*THEN:B)D)/K ** Failers CB /^(?:A(*THEN:A)B|C(*THEN:B)D)/K CB /^(?>A(*THEN:A)B|C(*THEN:B)D)/K CB /--- This should succeed, as the skip causes bump to offset 1 (the mark). Note that we have to have something complicated such as (B|Z) at the end because, for Perl, a simple character somehow causes an unwanted optimization to mess with the handling of backtracking verbs. ---/ /A(*MARK:A)A+(*SKIP:A)(B|Z) | AC/xK AAAC /--- Test skipping over a non-matching mark. ---/ /A(*MARK:A)A+(*MARK:B)(*SKIP:A)(B|Z) | AC/xK AAAC /--- Check shorthand for MARK ---/ /A(*:A)A+(*SKIP:A)(B|Z) | AC/xK AAAC /--- Don't loop! Force no study, otherwise mark is not seen. ---/ /(*:A)A+(*SKIP:A)(B|Z)/KSS AAAC /--- This should succeed, as a non-existent skip name disables the skip ---/ /A(*MARK:A)A+(*SKIP:B)(B|Z) | AC/xK AAAC /A(*MARK:A)A+(*SKIP:B)(B|Z) | AC(*:B)/xK AAAC /--- COMMIT at the start of a pattern should act like an anchor. Again, however, we need the complication for Perl. ---/ /(*COMMIT)(A|P)(B|P)(C|P)/ ABCDEFG ** Failers DEFGABC /--- COMMIT inside an atomic group can't stop backtracking over the group. ---/ /(\w+)(?>b(*COMMIT))\w{2}/ abbb /(\w+)b(*COMMIT)\w{2}/ abbb /--- Check opening parens in comment when seeking forward reference. ---/ /(?&t)(?#()(?(DEFINE)(?a))/ bac /--- COMMIT should override THEN ---/ /(?>(*COMMIT)(?>yes|no)(*THEN)(*F))?/ yes /(?>(*COMMIT)(yes|no)(*THEN)(*F))?/ yes /b?(*SKIP)c/ bc abc /(*SKIP)bc/ a /(*SKIP)b/ a /(?P(?P=abn)xxx|)+/ xxx /(?i:([^b]))(?1)/ aa aA ** Failers ab aB Ba ba /^(?&t)*+(?(DEFINE)(?a))\w$/ aaaaaaX ** Failers aaaaaa /^(?&t)*(?(DEFINE)(?a))\w$/ aaaaaaX aaaaaa /^(a)*+(\w)/ aaaaX YZ ** Failers aaaa /^(?:a)*+(\w)/ aaaaX YZ ** Failers aaaa /^(a)++(\w)/ aaaaX ** Failers aaaa YZ /^(?:a)++(\w)/ aaaaX ** Failers aaaa YZ /^(a)?+(\w)/ aaaaX YZ /^(?:a)?+(\w)/ aaaaX YZ /^(a){2,}+(\w)/ aaaaX ** Failers aaa YZ /^(?:a){2,}+(\w)/ aaaaX ** Failers aaa YZ /(a|)*(?1)b/ b ab aab /(a)++(?1)b/ ** Failers ab aab /(a)*+(?1)b/ ** Failers ab aab /(?1)(?:(b)){0}/ b /(foo ( \( ((?:(?> [^()]+ )|(?2))*) \) ) )/x foo(bar(baz)+baz(bop)) /(A (A|B(*ACCEPT)|C) D)(E)/x AB /\A.*?(a|bc)/ ba /\A.*?(?:a|bc)++/ ba /\A.*?(a|bc)++/ ba /\A.*?(?:a|bc|d)/ ba /(?:(b))++/ beetle /(?(?=(a(*ACCEPT)z))a)/ a /^(a)(?1)+ab/ aaaab /^(a)(?1)++ab/ aaaab /^(?=a(*:M))aZ/K aZbc /^(?!(*:M)b)aZ/K aZbc /(?(DEFINE)(a))?b(?1)/ backgammon /^\N+/ abc\ndef /^\N{1,}/ abc\ndef /(?(R)a+|(?R)b)/ aaaabcde /(?(R)a+|((?R))b)/ aaaabcde /((?(R)a+|(?1)b))/ aaaabcde /((?(R1)a+|(?1)b))/ aaaabcde /a(*:any name)/K abc /(?>(?&t)c|(?&t))(?(DEFINE)(?a|b(*PRUNE)c))/ a ba bba /--- Checking revised (*THEN) handling ---/ /--- Capture ---/ /^.*? (a(*THEN)b) c/x aabc /^.*? (a(*THEN)b|(*F)) c/x aabc /^.*? ( (a(*THEN)b) | (*F) ) c/x aabc /^.*? ( (a(*THEN)b) ) c/x aabc /--- Non-capture ---/ /^.*? (?:a(*THEN)b) c/x aabc /^.*? (?:a(*THEN)b|(*F)) c/x aabc /^.*? (?: (?:a(*THEN)b) | (*F) ) c/x aabc /^.*? (?: (?:a(*THEN)b) ) c/x aabc /--- Atomic ---/ /^.*? (?>a(*THEN)b) c/x aabc /^.*? (?>a(*THEN)b|(*F)) c/x aabc /^.*? (?> (?>a(*THEN)b) | (*F) ) c/x aabc /^.*? (?> (?>a(*THEN)b) ) c/x aabc /--- Possessive capture ---/ /^.*? (a(*THEN)b)++ c/x aabc /^.*? (a(*THEN)b|(*F))++ c/x aabc /^.*? ( (a(*THEN)b)++ | (*F) )++ c/x aabc /^.*? ( (a(*THEN)b)++ )++ c/x aabc /--- Possessive non-capture ---/ /^.*? (?:a(*THEN)b)++ c/x aabc /^.*? (?:a(*THEN)b|(*F))++ c/x aabc /^.*? (?: (?:a(*THEN)b)++ | (*F) )++ c/x aabc /^.*? (?: (?:a(*THEN)b)++ )++ c/x aabc /--- Condition assertion ---/ /^(?(?=a(*THEN)b)ab|ac)/ ac /--- Condition ---/ /^.*?(?(?=a)a|b(*THEN)c)/ ba /^.*?(?:(?(?=a)a|b(*THEN)c)|d)/ ba /^.*?(?(?=a)a(*THEN)b|c)/ ac /--- Assertion ---/ /^.*(?=a(*THEN)b)/ aabc /------------------------------/ /(?>a(*:m))/imsxSK a /(?>(a)(*:m))/imsxSK a /(?<=a(*ACCEPT)b)c/ xacd /(?<=(a(*ACCEPT)b))c/ xacd /(?<=(a(*COMMIT)b))c/ xabcd ** Failers xacd /(?a?)*)*c/ aac /(?>.*?a)(?<=ba)/ aba /(?:.*?a)(?<=ba)/ aba /.*?a(*PRUNE)b/ aab /.*?a(*PRUNE)b/s aab /^a(*PRUNE)b/s aab /.*?a(*SKIP)b/ aab /(?>.*?a)b/s aab /(?>.*?a)b/ aab /(?>^a)b/s aab /(?>.*?)(?<=(abcd)|(wxyz))/ alphabetabcd endingwxyz /(?>.*)(?<=(abcd)|(wxyz))/ alphabetabcd endingwxyz "(?>.*)foo" abcdfooxyz "(?>.*?)foo" abcdfooxyz /(?:(a(*PRUNE)b)){0}(?:(?1)|ac)/ ac /(?:(a(*SKIP)b)){0}(?:(?1)|ac)/ ac /(?<=(*SKIP)ac)a/ aa /A(*MARK:A)A+(*SKIP:B)(B|Z) | AC/xK AAAC /a(*SKIP:m)x|ac(*:n)(*SKIP:n)d|ac/K acacd /A(*SKIP:m)x|A(*SKIP:n)x|AB/K AB /((*SKIP:r)d){0}a(*SKIP:m)x|ac(*:n)|ac/K acacd /-- Tests that try to figure out how Perl works. My hypothesis is that the first verb that is backtracked onto is the one that acts. This seems to be the case almost all the time, but there is one exception that is perhaps a bug. --/ /-- This matches "aaaac"; each PRUNE advances one character until the subject no longer starts with 5 'a's. --/ /aaaaa(*PRUNE)b|a+c/ aaaaaac /-- Putting SKIP in front of PRUNE makes no difference, as it is never backtracked onto, whether or not it has a label. --/ /aaaaa(*SKIP)(*PRUNE)b|a+c/ aaaaaac /aaaaa(*SKIP:N)(*PRUNE)b|a+c/ aaaaaac /aaaa(*:N)a(*SKIP:N)(*PRUNE)b|a+c/ aaaaaac /-- Putting THEN in front makes no difference. */ /aaaaa(*THEN)(*PRUNE)b|a+c/ aaaaaac /-- However, putting COMMIT in front of the prune changes it to "no match". I think this is inconsistent and possibly a bug. For the moment, running this test is moved out of the Perl-compatible file. --/ /aaaaa(*COMMIT)(*PRUNE)b|a+c/ /---- OK, lets play the same game again using SKIP instead of PRUNE. ----/ /-- This matches "ac" because SKIP forces the next match to start on the sixth "a". --/ /aaaaa(*SKIP)b|a+c/ aaaaaac /-- Putting PRUNE in front makes no difference. --/ /aaaaa(*PRUNE)(*SKIP)b|a+c/ aaaaaac /-- Putting THEN in front makes no difference. --/ /aaaaa(*THEN)(*SKIP)b|a+c/ aaaaaac /-- In this case, neither does COMMIT. This still matches "ac". --/ /aaaaa(*COMMIT)(*SKIP)b|a+c/ aaaaaac /-- This gives "no match", as expected. --/ /aaaaa(*COMMIT)b|a+c/ aaaaaac /------ Tests using THEN ------/ /-- This matches "aaaaaac", as expected. --/ /aaaaa(*THEN)b|a+c/ aaaaaac /-- Putting SKIP in front makes no difference. --/ /aaaaa(*SKIP)(*THEN)b|a+c/ aaaaaac /-- Putting PRUNE in front makes no difference. --/ /aaaaa(*PRUNE)(*THEN)b|a+c/ aaaaaac /-- Putting COMMIT in front makes no difference. --/ /aaaaa(*COMMIT)(*THEN)b|a+c/ aaaaaac /-- End of "priority" tests --/ /aaaaa(*:m)(*PRUNE:m)(*SKIP:m)m|a+/ aaaaaa /aaaaa(*:m)(*MARK:m)(*PRUNE)(*SKIP:m)m|a+/ aaaaaa /aaaaa(*:n)(*PRUNE:m)(*SKIP:m)m|a+/ aaaaaa /aaaaa(*:n)(*MARK:m)(*PRUNE)(*SKIP:m)m|a+/ aaaaaa /a(*MARK:A)aa(*PRUNE:A)a(*SKIP:A)b|a+c/ aaaac /a(*MARK:A)aa(*MARK:A)a(*SKIP:A)b|a+c/ aaaac /aaa(*PRUNE:A)a(*SKIP:A)b|a+c/ aaaac /aaa(*MARK:A)a(*SKIP:A)b|a+c/ aaaac /a(*:m)a(*COMMIT)(*SKIP:m)b|a+c/K aaaaaac /.?(a|b(*THEN)c)/ ba /(a(*COMMIT)b)c|abd/ abc abd /(?=a(*COMMIT)b)abc|abd/ abc abd /(?>a(*COMMIT)b)c|abd/ abc abd /a(?=b(*COMMIT)c)[^d]|abd/ abd abc /a(?=bc).|abd/ abd abc /a(?>b(*COMMIT)c)d|abd/ abceabd /a(?>bc)d|abd/ abceabd /(?>a(*COMMIT)b)c|abd/ abd /(?>a(*COMMIT)c)d|abd/ abd /((?=a(*COMMIT)b)ab|ac){0}(?:(?1)|a(c))/ ac /-- These tests were formerly in test 2, but changes in PCRE and Perl have made them compatible. --/ /^(a)?(?(1)a|b)+$/ *** Failers a /(?=a\Kb)ab/ ab /(?!a\Kb)ac/ ac /^abc(?<=b\Kc)d/ abcd /^abc(?b))/K abc /(*PRUNE:m(m)(?&y)(?(DEFINE)(?b))/K abc /(*SKIP:m(m)(?&y)(?(DEFINE)(?b))/K abc /(*THEN:m(m)(?&y)(?(DEFINE)(?b))/K abc /^\d*\w{4}/ 1234 123 /^[^b]*\w{4}/ aaaa aaa /^[^b]*\w{4}/i aaaa aaa /^a*\w{4}/ aaaa aaa /^a*\w{4}/i aaaa aaa /(?(?=ab)ab)/+ ca cd /(?:(?foo)|(?bar))\k/J foofoo barbar /(?A)(?:(?foo)|(?bar))\k/J AfooA AbarA ** Failers Afoofoo Abarbar /^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ 1 IN SOA non-sp1 non-sp2( /^ (?:(?A)|(?'B'B)(?A)) (?('A')x) (?()y)$/xJ Ax BAxy /^A\xZ/ A\0Z /^A\o{123}B/ A\123B / ^ a + + b $ /x aaaab / ^ a + #comment + b $ /x aaaab / ^ a + #comment #comment + b $ /x aaaab / ^ (?> a + ) b $ /x aaaab / ^ ( a + ) + + \w $ /x aaaab /(?:a\Kb)*+/+ ababc /(?>a\Kb)*/+ ababc /(?:a\Kb)*/+ ababc /(a\Kb)*+/+ ababc /(a\Kb)*/+ ababc /-- End of testinput1 --/