1c67d6573Sopenharmony_ciNOTE implicit vs. explicit repetitions : 2009-02-02 2c67d6573Sopenharmony_ci 3c67d6573Sopenharmony_ci# Glenn Fowler <gsf@research.att.com> 4c67d6573Sopenharmony_ci# conforming matches (column 4) must match one of the following BREs 5c67d6573Sopenharmony_ci# NOMATCH 6c67d6573Sopenharmony_ci# (0,.)\((\(.\),\(.\))(?,?)(\2,\3)\)* 7c67d6573Sopenharmony_ci# (0,.)\((\(.\),\(.\))(\2,\3)(?,?)\)* 8c67d6573Sopenharmony_ci# i.e., each 3-tuple has two identical elements and one (?,?) 9c67d6573Sopenharmony_ci 10c67d6573Sopenharmony_ciE ((..)|(.)) NULL NOMATCH 11c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.)) NULL NOMATCH 12c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.))((..)|(.)) NULL NOMATCH 13c67d6573Sopenharmony_ci 14c67d6573Sopenharmony_ciE ((..)|(.)){1} NULL NOMATCH 15c67d6573Sopenharmony_ciE ((..)|(.)){2} NULL NOMATCH 16c67d6573Sopenharmony_ciE ((..)|(.)){3} NULL NOMATCH 17c67d6573Sopenharmony_ci 18c67d6573Sopenharmony_ciE ((..)|(.))* NULL (0,0) 19c67d6573Sopenharmony_ci 20c67d6573Sopenharmony_ciE ((..)|(.)) a (0,1)(0,1)(?,?)(0,1) 21c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.)) a NOMATCH 22c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.))((..)|(.)) a NOMATCH 23c67d6573Sopenharmony_ci 24c67d6573Sopenharmony_ciE ((..)|(.)){1} a (0,1)(0,1)(?,?)(0,1) 25c67d6573Sopenharmony_ciE ((..)|(.)){2} a NOMATCH 26c67d6573Sopenharmony_ciE ((..)|(.)){3} a NOMATCH 27c67d6573Sopenharmony_ci 28c67d6573Sopenharmony_ciE ((..)|(.))* a (0,1)(0,1)(?,?)(0,1) 29c67d6573Sopenharmony_ci 30c67d6573Sopenharmony_ciE ((..)|(.)) aa (0,2)(0,2)(0,2)(?,?) 31c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.)) aa (0,2)(0,1)(?,?)(0,1)(1,2)(?,?)(1,2) 32c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.))((..)|(.)) aa NOMATCH 33c67d6573Sopenharmony_ci 34c67d6573Sopenharmony_ciE ((..)|(.)){1} aa (0,2)(0,2)(0,2)(?,?) 35c67d6573Sopenharmony_ciE ((..)|(.)){2} aa (0,2)(1,2)(?,?)(1,2) 36c67d6573Sopenharmony_ciE ((..)|(.)){3} aa NOMATCH 37c67d6573Sopenharmony_ci 38c67d6573Sopenharmony_ciE ((..)|(.))* aa (0,2)(0,2)(0,2)(?,?) 39c67d6573Sopenharmony_ci 40c67d6573Sopenharmony_ciE ((..)|(.)) aaa (0,2)(0,2)(0,2)(?,?) 41c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.)) aaa (0,3)(0,2)(0,2)(?,?)(2,3)(?,?)(2,3) 42c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.))((..)|(.)) aaa (0,3)(0,1)(?,?)(0,1)(1,2)(?,?)(1,2)(2,3)(?,?)(2,3) 43c67d6573Sopenharmony_ci 44c67d6573Sopenharmony_ciE ((..)|(.)){1} aaa (0,2)(0,2)(0,2)(?,?) 45c67d6573Sopenharmony_ci#E ((..)|(.)){2} aaa (0,3)(2,3)(?,?)(2,3) 46c67d6573Sopenharmony_ciE ((..)|(.)){2} aaa (0,3)(2,3)(0,2)(2,3) RE2/Go 47c67d6573Sopenharmony_ciE ((..)|(.)){3} aaa (0,3)(2,3)(?,?)(2,3) 48c67d6573Sopenharmony_ci 49c67d6573Sopenharmony_ci#E ((..)|(.))* aaa (0,3)(2,3)(?,?)(2,3) 50c67d6573Sopenharmony_ciE ((..)|(.))* aaa (0,3)(2,3)(0,2)(2,3) RE2/Go 51c67d6573Sopenharmony_ci 52c67d6573Sopenharmony_ciE ((..)|(.)) aaaa (0,2)(0,2)(0,2)(?,?) 53c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.)) aaaa (0,4)(0,2)(0,2)(?,?)(2,4)(2,4)(?,?) 54c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.))((..)|(.)) aaaa (0,4)(0,2)(0,2)(?,?)(2,3)(?,?)(2,3)(3,4)(?,?)(3,4) 55c67d6573Sopenharmony_ci 56c67d6573Sopenharmony_ciE ((..)|(.)){1} aaaa (0,2)(0,2)(0,2)(?,?) 57c67d6573Sopenharmony_ciE ((..)|(.)){2} aaaa (0,4)(2,4)(2,4)(?,?) 58c67d6573Sopenharmony_ci#E ((..)|(.)){3} aaaa (0,4)(3,4)(?,?)(3,4) 59c67d6573Sopenharmony_ciE ((..)|(.)){3} aaaa (0,4)(3,4)(0,2)(3,4) RE2/Go 60c67d6573Sopenharmony_ci 61c67d6573Sopenharmony_ciE ((..)|(.))* aaaa (0,4)(2,4)(2,4)(?,?) 62c67d6573Sopenharmony_ci 63c67d6573Sopenharmony_ciE ((..)|(.)) aaaaa (0,2)(0,2)(0,2)(?,?) 64c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.)) aaaaa (0,4)(0,2)(0,2)(?,?)(2,4)(2,4)(?,?) 65c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.))((..)|(.)) aaaaa (0,5)(0,2)(0,2)(?,?)(2,4)(2,4)(?,?)(4,5)(?,?)(4,5) 66c67d6573Sopenharmony_ci 67c67d6573Sopenharmony_ciE ((..)|(.)){1} aaaaa (0,2)(0,2)(0,2)(?,?) 68c67d6573Sopenharmony_ciE ((..)|(.)){2} aaaaa (0,4)(2,4)(2,4)(?,?) 69c67d6573Sopenharmony_ci#E ((..)|(.)){3} aaaaa (0,5)(4,5)(?,?)(4,5) 70c67d6573Sopenharmony_ciE ((..)|(.)){3} aaaaa (0,5)(4,5)(2,4)(4,5) RE2/Go 71c67d6573Sopenharmony_ci 72c67d6573Sopenharmony_ci#E ((..)|(.))* aaaaa (0,5)(4,5)(?,?)(4,5) 73c67d6573Sopenharmony_ciE ((..)|(.))* aaaaa (0,5)(4,5)(2,4)(4,5) RE2/Go 74c67d6573Sopenharmony_ci 75c67d6573Sopenharmony_ciE ((..)|(.)) aaaaaa (0,2)(0,2)(0,2)(?,?) 76c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.)) aaaaaa (0,4)(0,2)(0,2)(?,?)(2,4)(2,4)(?,?) 77c67d6573Sopenharmony_ciE ((..)|(.))((..)|(.))((..)|(.)) aaaaaa (0,6)(0,2)(0,2)(?,?)(2,4)(2,4)(?,?)(4,6)(4,6)(?,?) 78c67d6573Sopenharmony_ci 79c67d6573Sopenharmony_ciE ((..)|(.)){1} aaaaaa (0,2)(0,2)(0,2)(?,?) 80c67d6573Sopenharmony_ciE ((..)|(.)){2} aaaaaa (0,4)(2,4)(2,4)(?,?) 81c67d6573Sopenharmony_ciE ((..)|(.)){3} aaaaaa (0,6)(4,6)(4,6)(?,?) 82c67d6573Sopenharmony_ci 83c67d6573Sopenharmony_ciE ((..)|(.))* aaaaaa (0,6)(4,6)(4,6)(?,?) 84c67d6573Sopenharmony_ci 85c67d6573Sopenharmony_ciNOTE additional repetition tests graciously provided by Chris Kuklewicz www.haskell.org 2009-02-02 86c67d6573Sopenharmony_ci 87c67d6573Sopenharmony_ci# These test a bug in OS X / FreeBSD / NetBSD, and libtree. 88c67d6573Sopenharmony_ci# Linux/GLIBC gets the {8,} and {8,8} wrong. 89c67d6573Sopenharmony_ci 90c67d6573Sopenharmony_ci:HA#100:E X(.?){0,}Y X1234567Y (0,9)(7,8) 91c67d6573Sopenharmony_ci:HA#101:E X(.?){1,}Y X1234567Y (0,9)(7,8) 92c67d6573Sopenharmony_ci:HA#102:E X(.?){2,}Y X1234567Y (0,9)(7,8) 93c67d6573Sopenharmony_ci:HA#103:E X(.?){3,}Y X1234567Y (0,9)(7,8) 94c67d6573Sopenharmony_ci:HA#104:E X(.?){4,}Y X1234567Y (0,9)(7,8) 95c67d6573Sopenharmony_ci:HA#105:E X(.?){5,}Y X1234567Y (0,9)(7,8) 96c67d6573Sopenharmony_ci:HA#106:E X(.?){6,}Y X1234567Y (0,9)(7,8) 97c67d6573Sopenharmony_ci:HA#107:E X(.?){7,}Y X1234567Y (0,9)(7,8) 98c67d6573Sopenharmony_ci:HA#108:E X(.?){8,}Y X1234567Y (0,9)(8,8) 99c67d6573Sopenharmony_ci#:HA#110:E X(.?){0,8}Y X1234567Y (0,9)(7,8) 100c67d6573Sopenharmony_ci:HA#110:E X(.?){0,8}Y X1234567Y (0,9)(8,8) RE2/Go 101c67d6573Sopenharmony_ci#:HA#111:E X(.?){1,8}Y X1234567Y (0,9)(7,8) 102c67d6573Sopenharmony_ci:HA#111:E X(.?){1,8}Y X1234567Y (0,9)(8,8) RE2/Go 103c67d6573Sopenharmony_ci#:HA#112:E X(.?){2,8}Y X1234567Y (0,9)(7,8) 104c67d6573Sopenharmony_ci:HA#112:E X(.?){2,8}Y X1234567Y (0,9)(8,8) RE2/Go 105c67d6573Sopenharmony_ci#:HA#113:E X(.?){3,8}Y X1234567Y (0,9)(7,8) 106c67d6573Sopenharmony_ci:HA#113:E X(.?){3,8}Y X1234567Y (0,9)(8,8) RE2/Go 107c67d6573Sopenharmony_ci#:HA#114:E X(.?){4,8}Y X1234567Y (0,9)(7,8) 108c67d6573Sopenharmony_ci:HA#114:E X(.?){4,8}Y X1234567Y (0,9)(8,8) RE2/Go 109c67d6573Sopenharmony_ci#:HA#115:E X(.?){5,8}Y X1234567Y (0,9)(7,8) 110c67d6573Sopenharmony_ci:HA#115:E X(.?){5,8}Y X1234567Y (0,9)(8,8) RE2/Go 111c67d6573Sopenharmony_ci#:HA#116:E X(.?){6,8}Y X1234567Y (0,9)(7,8) 112c67d6573Sopenharmony_ci:HA#116:E X(.?){6,8}Y X1234567Y (0,9)(8,8) RE2/Go 113c67d6573Sopenharmony_ci#:HA#117:E X(.?){7,8}Y X1234567Y (0,9)(7,8) 114c67d6573Sopenharmony_ci:HA#117:E X(.?){7,8}Y X1234567Y (0,9)(8,8) RE2/Go 115c67d6573Sopenharmony_ci:HA#118:E X(.?){8,8}Y X1234567Y (0,9)(8,8) 116c67d6573Sopenharmony_ci 117c67d6573Sopenharmony_ci# These test a fixed bug in my regex-tdfa that did not keep the expanded 118c67d6573Sopenharmony_ci# form properly grouped, so right association did the wrong thing with 119c67d6573Sopenharmony_ci# these ambiguous patterns (crafted just to test my code when I became 120c67d6573Sopenharmony_ci# suspicious of my implementation). The first subexpression should use 121c67d6573Sopenharmony_ci# "ab" then "a" then "bcd". 122c67d6573Sopenharmony_ci 123c67d6573Sopenharmony_ci# OS X / FreeBSD / NetBSD badly fail many of these, with impossible 124c67d6573Sopenharmony_ci# results like (0,6)(4,5)(6,6). 125c67d6573Sopenharmony_ci 126c67d6573Sopenharmony_ci:HA#260:E (a|ab|c|bcd){0,}(d*) ababcd (0,1)(0,1)(1,1) 127c67d6573Sopenharmony_ci:HA#261:E (a|ab|c|bcd){1,}(d*) ababcd (0,1)(0,1)(1,1) 128c67d6573Sopenharmony_ci:HA#262:E (a|ab|c|bcd){2,}(d*) ababcd (0,6)(3,6)(6,6) 129c67d6573Sopenharmony_ci:HA#263:E (a|ab|c|bcd){3,}(d*) ababcd (0,6)(3,6)(6,6) 130c67d6573Sopenharmony_ci:HA#264:E (a|ab|c|bcd){4,}(d*) ababcd NOMATCH 131c67d6573Sopenharmony_ci:HA#265:E (a|ab|c|bcd){0,10}(d*) ababcd (0,1)(0,1)(1,1) 132c67d6573Sopenharmony_ci:HA#266:E (a|ab|c|bcd){1,10}(d*) ababcd (0,1)(0,1)(1,1) 133c67d6573Sopenharmony_ci:HA#267:E (a|ab|c|bcd){2,10}(d*) ababcd (0,6)(3,6)(6,6) 134c67d6573Sopenharmony_ci:HA#268:E (a|ab|c|bcd){3,10}(d*) ababcd (0,6)(3,6)(6,6) 135c67d6573Sopenharmony_ci:HA#269:E (a|ab|c|bcd){4,10}(d*) ababcd NOMATCH 136c67d6573Sopenharmony_ci:HA#270:E (a|ab|c|bcd)*(d*) ababcd (0,1)(0,1)(1,1) 137c67d6573Sopenharmony_ci:HA#271:E (a|ab|c|bcd)+(d*) ababcd (0,1)(0,1)(1,1) 138c67d6573Sopenharmony_ci 139c67d6573Sopenharmony_ci# The above worked on Linux/GLIBC but the following often fail. 140c67d6573Sopenharmony_ci# They also trip up OS X / FreeBSD / NetBSD: 141c67d6573Sopenharmony_ci 142c67d6573Sopenharmony_ci#:HA#280:E (ab|a|c|bcd){0,}(d*) ababcd (0,6)(3,6)(6,6) 143c67d6573Sopenharmony_ci:HA#280:E (ab|a|c|bcd){0,}(d*) ababcd (0,6)(4,5)(5,6) RE2/Go 144c67d6573Sopenharmony_ci#:HA#281:E (ab|a|c|bcd){1,}(d*) ababcd (0,6)(3,6)(6,6) 145c67d6573Sopenharmony_ci:HA#281:E (ab|a|c|bcd){1,}(d*) ababcd (0,6)(4,5)(5,6) RE2/Go 146c67d6573Sopenharmony_ci#:HA#282:E (ab|a|c|bcd){2,}(d*) ababcd (0,6)(3,6)(6,6) 147c67d6573Sopenharmony_ci:HA#282:E (ab|a|c|bcd){2,}(d*) ababcd (0,6)(4,5)(5,6) RE2/Go 148c67d6573Sopenharmony_ci#:HA#283:E (ab|a|c|bcd){3,}(d*) ababcd (0,6)(3,6)(6,6) 149c67d6573Sopenharmony_ci:HA#283:E (ab|a|c|bcd){3,}(d*) ababcd (0,6)(4,5)(5,6) RE2/Go 150c67d6573Sopenharmony_ci:HA#284:E (ab|a|c|bcd){4,}(d*) ababcd NOMATCH 151c67d6573Sopenharmony_ci#:HA#285:E (ab|a|c|bcd){0,10}(d*) ababcd (0,6)(3,6)(6,6) 152c67d6573Sopenharmony_ci:HA#285:E (ab|a|c|bcd){0,10}(d*) ababcd (0,6)(4,5)(5,6) RE2/Go 153c67d6573Sopenharmony_ci#:HA#286:E (ab|a|c|bcd){1,10}(d*) ababcd (0,6)(3,6)(6,6) 154c67d6573Sopenharmony_ci:HA#286:E (ab|a|c|bcd){1,10}(d*) ababcd (0,6)(4,5)(5,6) RE2/Go 155c67d6573Sopenharmony_ci#:HA#287:E (ab|a|c|bcd){2,10}(d*) ababcd (0,6)(3,6)(6,6) 156c67d6573Sopenharmony_ci:HA#287:E (ab|a|c|bcd){2,10}(d*) ababcd (0,6)(4,5)(5,6) RE2/Go 157c67d6573Sopenharmony_ci#:HA#288:E (ab|a|c|bcd){3,10}(d*) ababcd (0,6)(3,6)(6,6) 158c67d6573Sopenharmony_ci:HA#288:E (ab|a|c|bcd){3,10}(d*) ababcd (0,6)(4,5)(5,6) RE2/Go 159c67d6573Sopenharmony_ci:HA#289:E (ab|a|c|bcd){4,10}(d*) ababcd NOMATCH 160c67d6573Sopenharmony_ci#:HA#290:E (ab|a|c|bcd)*(d*) ababcd (0,6)(3,6)(6,6) 161c67d6573Sopenharmony_ci:HA#290:E (ab|a|c|bcd)*(d*) ababcd (0,6)(4,5)(5,6) RE2/Go 162c67d6573Sopenharmony_ci#:HA#291:E (ab|a|c|bcd)+(d*) ababcd (0,6)(3,6)(6,6) 163c67d6573Sopenharmony_ci:HA#291:E (ab|a|c|bcd)+(d*) ababcd (0,6)(4,5)(5,6) RE2/Go 164