--- embedaddon/pcre/testdata/testinput2 2012/02/21 23:05:52 1.1.1.1 +++ embedaddon/pcre/testdata/testinput2 2012/02/21 23:50:25 1.1.1.2 @@ -5,13 +5,9 @@ either because PCRE can't be compatible, or there is a possible Perl bug. - NOTE: This is a non-UTF-8 set of tests. When UTF-8 is needed, use test - 5, and if Unicode Property Support is needed, use test 13. --/ + NOTE: This is a non-UTF set of tests. When UTF support is needed, use + test 5, and if Unicode Property Support is needed, use test 7. --/ -/-- Originally, the Perl >= 5.10 things were in here too, but now I have - separated many (most?) of them out into test 11. However, there may still - be some that were overlooked. --/ - /(a)b|/I /abc/I @@ -147,40 +143,6 @@ defabc \Zdefabc -/abc/P - abc - *** Failers - -/^abc|def/P - abcdef - abcdef\B - -/.*((abc)$|(def))/P - defabc - \Zdefabc - -/the quick brown fox/P - the quick brown fox - *** Failers - The Quick Brown Fox - -/the quick brown fox/Pi - the quick brown fox - The Quick Brown Fox - -/abc.def/P - *** Failers - abc\ndef - -/abc$/P - abc - abc\n - -/(abc)\2/P - -/(abc\1)/P - abc - /)/ /a[]b/ @@ -445,8 +407,6 @@ /abc/\ -/abc/\P - /abc/\i /(a)bc(d)/I @@ -494,9 +454,6 @@ /\Biss\B/I+ Mississippi -/\Biss\B/I+P - Mississippi - /iss/IG+ Mississippi @@ -632,15 +589,6 @@ *** Failers \Nabc -/a*(b+)(z)(z)/P - aaaabbbbzzzz - aaaabbbbzzzz\O0 - aaaabbbbzzzz\O1 - aaaabbbbzzzz\O2 - aaaabbbbzzzz\O3 - aaaabbbbzzzz\O4 - aaaabbbbzzzz\O5 - /^.?abcd/IS /\( # ( at start @@ -1494,17 +1442,6 @@ ** Failers line one\nthis is a line\nbreak in the second line -/ab.cd/P - ab-cd - ab=cd - ** Failers - ab\ncd - -/ab.cd/Ps - ab-cd - ab=cd - ab\ncd - /(?i)(?-i)AbCd/I AbCd ** Failers @@ -1555,14 +1492,6 @@ (this) ((this)) -/a(b)c/PN - abc - -/a(?Pb)c/PN - abc - -/\x{100}/I - /\x{0000ff}/I /^((?Pa1)|(?Pa2)b)/I @@ -1640,8 +1569,6 @@ a random value. /Ix /()()()()()()()()()(?:(?(A)(?P=A)a|b)(?PX|Y))+/I bXXaYYaY -/\777/I - /\s*,\s*/IS \x0b,\x0b \x0c,\x0d @@ -2244,22 +2171,6 @@ a random value. /Ix xabcpqrx xxyzx -/[\h]/BZ - >\x09< - -/[\h]+/BZ - >\x09\x20\xa0< - -/[\v]/BZ - -/[\H]/BZ - -/[^\h]/BZ - -/[\V]/BZ - -/[\x0a\V]/BZ - /\H++X/BZ ** Failers XXXX @@ -2619,11 +2530,6 @@ a random value. /Ix /(?(?=.*b).*b|^d)/I -/a?|b?/P - abc - ** Failers - ddd\N - /xyz/C xyz abcxyz @@ -2815,12 +2721,6 @@ a random value. /Ix abc\P abc\P\P -/\w+A/P - CDAAAAB - -/\w+A/PU - CDAAAAB - /abc\K123/ xyzabc123pqr xyzabc12\P @@ -2964,201 +2864,6 @@ a random value. /Ix /^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]/SI -/ (?: [\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 -/xSI - /]{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>/isIS "(?>.*/)foo"SI @@ -3875,5 +3580,25 @@ replaced by single letters. --/ /^a(*:X)bcde/K abc\P + +/-- These are here because Perl doesn't return a mark, except for the first --/ + +/(?=(*:x))(q|)/K+ + abc + +/(?=(*:x))((*:y)q|)/K+ + abc + +/(?=(*:x))(?:(*:y)q|)/K+ + abc + +/(?=(*:x))(?>(*:y)q|)/K+ + abc + +/(?=a(*:x))(?!a(*:y)c)/K+ + ab + +/(?=a(*:x))(?=a(*:y)c|)/K+ + ab /-- End of testinput2 --/