/* Regex in reverse - decompose regular expressions in Picat v3. From codegolf: Regex in reverse - decompose regular expressions https://codegolf.stackexchange.com/questions/25378/regex-in-reverse-decompose-regular-expressions """ The Problem I have a bunch of regular expressions that I need to use in some code, but I'm using a programming language that doesn't support regex! Luckily, I know that the test string will have a maximum length and will be composed of printable ASCII only. The Challenge You must input a regex and a number n, and output every string composed of printable ASCII (ASCII codes 32 to 126 inclusive, to ~, no tabs or newlines) of length less than or equal to n that matches that regex. You may not use built-in regular expressions or regex matching functions in your code at all. Regular expressions will be limited to the following: * Literal characters (and escapes, which force a character to be literal, so \. is a literal ., \n is a literal n (equivalent to just n), and \w is equivalent to w. You do not need to support escape sequences.) * . - wildcard (any character) * Character classes, [abc] means "a or b or c" and [d-f] means anything from d to f (so, d or e or f). The only characters that have special meaning in a character class are [ and ] (which will always be escaped, so don't worry about those), \ (the escape character, of course), ^ at the beginning of the character class (which is a negation), and - (which is a range). * | - the OR operator, alternation. foo|bar means either foo or bar, and (ab|cd)e matches either abe or cde. * * - match the previous token repeated zero or more times, greedy (it tries to repeat as many times as possible) * + - repeated one or more times, greedy * ? - zero or one times * Grouping with parentheses, to group tokens for |, *. +, or ? The input regex will always be valid (i.e., you do not have to handle input like ?abc or (foo or any invalid input). You may output the strings in any order you would like, but each string must appear only once (don't output any duplicates). The Test Cases Input: .*, 1 Output: (empty string), , !, ", ..., }, ~ Input: w\w+, 3 Output: ww, www Input: [abx-z][^ -}][\\], 3 Output: a~\, b~\, x~\, y~\, z~\ Input: ab*a|c[de]*, 3 Output: c, cd, ce, aa, cde, ced, cdd, cee, aba Input: (foo)+(bar)?!?, 6 Output: foo, foo!, foofoo, foobar Input: (a+|b*c)d, 4 Output: ad, cd, aad, bcd, aaad, bbcd Input: p+cg, 4 Output: pcg, ppcg Input: a{3}, 4 Output: a{3} The Winner This is code-golf, so the shortest code in bytes will win! """ This Picat model was created by Hakan Kjellerstrand, hakank@gmail.com See also my Picat page: http://www.hakank.org/picat/ */ import util. main => go. go ?=> % generate_string("w\\w+", 3,S), % generate_string("[abx-z][^ -}][\\\\]", 3, S), % generate_string("[^ ]+", 3, S), % 839514 strings generate_string("[abc]+[xyz]+", 3, S), % 63 strings println(s=S), fail, nl. go => true. % See mankell.pi and mankell_v3.pi % (Same result, but in different order) go2 ?=> % Kjellerstrand (48) println("kjellerstrand:"), K = findall(S,generate_string("k(je|รค)ll(er|ar)?(st|b)r?an?d",15,S)), println(K), println(len=K.len), nl, % Henning Mankell (1296) println("henning mankell"), M = findall(S,generate_string("[hm][ea](nk|n|nn)(ing|ell|all) [hm][ea](nk|n|nn)(ing|ell|all)",15,S)), % println(M), println(len=M.len), nl. go2 => true. % The tests. % Correct words but not always in correct order (fixing this by split.sort.join). go3 ?=> Tests = [ [".*", 1, "(empty string), , !, \", ..., }, ~"], ["w\\w+", 3, "ww, www"], ["[abx-z][^ -}][\\\\]", 3,"a~\\, b~\\, x~\\, y~\\, z~\\"], % ["ab*a|c[de]*", 3, "c, cd, ce, aa, cde, ced, cdd, cee, aba"], % not correct order ["ab*a|c[de]*", 3, "c, cd, ce, aa, cde, ced, cdd, cee, aba".split(", ").sort.join(", ")], ["(foo)+(bar)?!?", 6,"foo, foo!, foofoo, foobar".split(", ").sort.join(", ")], ["(a+|b*c)d", 4, "ad, cd, aad, bcd, aaad, bbcd".split(", ").sort.join(", ")], ["p+cg", 4, "pcg, ppcg"], ["a{3}", 4, "a{3}"], ["price[1234]",10,"price1, price2, price3, price4"], ["[a-c][a-c][a-c]",6,"aaa, aab, aac, aba, abb, abc, aca, acb, acc, baa, bab, bac, bba, bbb, bbc, bca, bcb, bcc, caa, cab, cac, cba, cbb, cbc, cca, ccb, ccc"], % hakank ["a(l(la?)?|n(anas|n(as?)?)?)?",20,"a, al, all, alla, an, ananas, ann, anna, annas"], ["(a|[bpk]a)lla",10,"alla, balla, kalla, palla"], ["(a(nd|t)|do|end|for|i[ns]|not|o[fr]|use)",10,"and, at, do, end, for, in, is, not, of, or, use"], % Generating all combinations of a, b, and c of length N. ["(a|b|c)+",3,"a, b, c, aa, ab, ac, ba, bb, bc, ca, cb, cc, aaa, aab, aac, aba, abb, abc, aca, acb, acc, baa, bab, bac, bba, bbb, bbc, bca, bcb, bcc, caa, cab, cac, cba, cbb, cbc, cca, ccb, ccc".split(", ").sort.join(", ")], % See regex_match_number.pi ["(eight|f(ive|our)|nine|one|s(even|ix)|t(hree|wo))",5,"one,two,three,four,five,six,seven,eight,nine".split(",").sort.join(", ")], ["(e(ight(een)?|leven)|f(i(fteen|ve)|our(teen)?)|nine(teen)?|one|s(even(teen)?|ix(teen)?)|t(en|h(irteen|ree)|w(elve|o)))",10,["one","two","three","four","five","six","seven","eight","nine","ten","eleven","twelve","thirteen","fourteen","fifteen","sixteen","seventeen","eighteen","nineteen"].sort.join(", ")] ], foreach([Regex,N,Check] in Tests) println([regex=Regex,n=N,check=Check]), All=findall(S,generate_string(Regex, N, S)).sort().join(", "), println(All), if All == Check then println(ok) else println(not_ok) end, nl end, nl. go3 => true. go4 ?=> wordle_regexp(Regex), N = 5, All=findall(S,generate_string(Regex, N, S)), println(all=All), println(All.len), nl. go4 => true. % % Prolog solution by ankh-morpork (adjusted to Picat by hakank) % From % https://codegolf.stackexchange.com/questions/25378/regex-in-reverse-decompose-regular-expressions % % Prolog, ungolfed % generate_string(R, L, S) :- % parse regex % string_codes(R, RC), RC = to_codes(R), % hakank regex_union(RE, RC, []), % bound string length between(0, L, M), bp.length(SC, M), % hakank % find string match(SC, RE, []), % string_codes(S, SC). S = [chr(C) : C in SC]. % hakank % Parsers %%%%%%%%% regex_union(R) -->regex_concat(S), regex_union1(S, R). regex_union1(R,T) --> [124], regex_concat(S), regex_union1($regex_union(R,S), T). regex_union1(R, R) --> []. regex_concat(R) --> regex_op(S), regex_concat1(S, R). regex_concat1(R, T) --> regex_op(S), regex_concat1($regex_concat(R,S), T). regex_concat1(R, R) --> []. regex_op(regex_kleene(R)) --> regex_lit(R), [42]. regex_op(regex_concat(R,regex_kleene(R))) --> regex_lit(R), [43]. regex_op(regex_union(regex_empty,R)) --> regex_lit(R), [63]. regex_op(R) --> regex_lit(R). regex_lit(regex_char([C])) --> [C], {\+ regex_ctrl(C)}. regex_lit(regex_char([C])) --> [92], [C]. regex_lit(regex_char(CS)) --> [46], % {findall(C, between(32,126, C), CS)}. {CS = findall(C, between(32,126, C))}. % hakank regex_lit(regex_char(DS)) --> [91], [94], !, class_body(CS), [93], % {findall(C, (between(32, 126, C), \+ member(C, CS)), DS)}. {DS = findall(C, (between(32, 126, C), \+ member(C, CS)))}. % hakank regex_lit(regex_char(CS)) --> [91], class_body(CS), [93]. regex_lit(R) --> [40], regex_union(R), [41]. class_body([C|T]) --> class_lit(C),class_body(T). class_body(CS) --> class_lit(C0), [45], class_lit(C1), class_body(T), % {findall(C, between(C0, C1, C), H), append(H,T,CS)}. {H = findall(C, between(C0, C1, C)), append(H,T,CS)}. % hakank class_body([]) --> []. class_lit(C) --> [C], {\+ class_ctrl(C)}. class_lit(C) --> [92], [C]. class_ctrl(C) :- CS=to_codes("\\[]-"), member(C, CS). % hakank regex_ctrl(C) :- CS=to_codes("\\.[]|+?*()"), member(C, CS). % hakank % Regex Engine %%%%%%%%%%%%%% % The regex empty matches any string without consuming any characters. match(S, regex_empty, S). % A regex consisting of a single character matches any string starting with % that character. The chanter is consumed. match([C|S], regex_char(CS), S) :- member(C, CS). % A union of two regex only needs to satisify one of the branches. match(S, regex_union(L,R), T) :- match(S, L, T); match(S, R, T). % A concat of two regex must satisfy the left and then the right. match(S, regex_concat(L, R), U) :- match(S, L, T), match(T, R, U). % The kleene closure of a regex can match the regex 0 times or it can the regex % once before matching the kleene closure again. match(S, regex_kleene(_), S). match(S, regex_kleene(K), U) :- match(S, K, T), S != T, match(T, $regex_kleene(K), U). % See wordle_dcg.pi for comparison (using DCG) wordle_regexp(Wordle) :- % This (prefix) regex was generated by make_regex.pi (go3/0). Wordle = "(a(b(a(ck|se|te)|b(ey|ot)|hor|ide|led|o(de|rt|ut|ve)|use|yss)|c(orn|rid|tor|ute)|d(a(ge|pt)|ept|mi[nt]|o(be|pt|r[en])|ult)|f(fix|ire|o(ot|ul)|ter)|g(a(in|pe|te)|ent|i(le|ng)|low|o(ny|ra)|ree)|head|i(der|sle)|l(arm|bum|ert|gae|i(bi|en|gn|ke|ve)|l(ay|ey|o[twy])|o(ft|n[eg]|of|ud)|pha|t(ar|er))|m(a(ss|ze)|b(er|le)|end|i(ss|ty)|ong|pl[ey]|use)|n(g(e[lr]|le|ry|st)|ime|kle|n(ex|oy|ul)|ode|tic|vil)|orta|p(art|hid|ing|nea|pl[ey]|ron|tly)|r(bor|dor|ena|gue|ise|mor|o(ma|se)|r(ay|ow)|son|tsy)|s(cot|hen|ide|kew|s(ay|et))|t(o(ll|ne)|tic)|u(di[ot]|gur|nty)|v(ail|ert|ian|oid)|w(a(it|ke|r[de]|sh)|ful|oke)|xi(al|o[mn])|zure)|b(a(con|d(ge|ly)|g(el|gy)|ker|l(er|my)|n(al|jo)|r(ge|on)|s(al|i[clns]|te)|t(ch|he|on|ty)|wdy|you)|e(a(ch|dy|rd|st)|e(ch|fy)|fit|g(a[nt]|et|in|un)|ing|l(ch|ie|l[ey]|ow)|nch|r(et|ry|th)|set|tel|vel|zel)|i(ble|cep|ddy|got|l(ge|ly)|ng[eo]|ome|r(ch|th)|son|tty)|l(a(ck|de|me|n[dk]|re|st|ze)|e(a[kt]|e[dp]|nd|ss)|i(mp|n[dk]|ss|tz)|o(at|ck|ke|nd|o[dm]|wn)|u(er|ff|nt|r[bt]|sh))|o(a(rd|st)|bby|n(ey|go|us)|o(by|st|t[hy]|z[ey])|r(ax|ne)|s(om|sy)|tch|u(gh|le|nd)|wel|xer)|r(a(ce|i[dn]|ke|nd|s[hs]|v[eo]|w[ln])|e(a[dk]|ed)|i(ar|be|ck|de|ef|n[egky]|sk)|o(ad|il|ke|o[dkm]|th|wn)|u(nt|sh|te))|u(d(dy|ge)|g(gy|le)|il[dt]|l(ge|ky|ly)|n(ch|ny)|r(ly|nt|st)|s(ed|hy)|t(ch|te)|xom|yer)|ylaw)|c(a(b(al|by|in|le)|c(ao|he|ti)|d(dy|et)|gey|irn|me[lo]|n(al|dy|ny|o[en])|p(er|ut)|r(at|go|ol|ry|ve)|ste|t(ch|er|ty)|u(lk|se)|vil)|e(ase|dar|llo)|h(a(f[ef]|i[nr]|lk|mp|nt|os|r[dmt]|s[em])|e(a[pt]|ck|e[kr]|s[st])|i(ck|de|ef|l[dil]|me|na|rp)|o(ck|ir|ke|r[de]|se)|u(ck|mp|nk|rn|te))|i(der|gar|nch|rca|vi[cl])|l(a(ck|im|mp|n[gk]|s[hps])|e(a[nrt]|ft|rk)|i(ck|ff|mb|n[gk])|o(ak|ck|ne|se|th|u[dt]|ve|wn)|u(ck|ed|mp|ng))|o(a(ch|st)|bra|coa|lo[nr]|m(et|fy|ic|ma)|n(ch|do|ic)|pse|r(al|er|ny)|u(ch|gh|ld|nt|pe|rt)|ve[nrty]|wer|yly)|r(a(ck|ft|mp|n[ek]|s[hs]|te|ve|wl|z[ey])|e(a[km]|do|e[dkp]|me|p[et]|s[st])|i(ck|e[dr]|m[ep]|sp)|o(ak|ck|n[ey]|ok|ss|up|w[dn])|u(de|el|m[bp]|s[ht])|ypt)|u(bic|min|r(io|ly|ry|se|v[ey])|tie)|y(ber|cle|nic))|d(a(ddy|i(ly|ry|sy)|lly|n(ce|dy)|tum|unt)|e(a(lt|th)|b(ar|it|u[gt])|c(a[ly]|o[ry]|ry)|fer|i(gn|ty)|l(ay|ta|ve)|m(on|ur)|n(im|se)|p(ot|th)|rby|t(er|ox)|uce|vil)|i(ary|cey|git|lly|mly|n(er|g[oy])|ode|r(ge|ty)|sco|t(ch|t[oy])|ver|zzy)|o(dg[ey]|gma|ing|lly|n(or|ut)|pey|u(bt|gh)|w(dy|el|ny|ry)|zen)|r(a(ft|in|ke|ma|nk|pe|w[ln])|e(a[dm]|ss)|i(e[dr]|ft|ll|nk|ve)|o(it|ll|ne|o[lp]|ss|ve|wn)|u(id|nk)|y(er|ly))|u(chy|lly|m(my|py)|nce|s(ky|ty)|tch|vet)|w(arf|el[lt])|ying)|e(a(g(er|le)|r(ly|th)|sel|te[nr])|bony|clat|di(ct|fy)|erie|gret|ight|ject|king|l(ate|bow|der|e(ct|gy)|fin|i(de|te)|ope|ude)|m(ail|be[dr]|cee|pty)|n(act|dow|em[ay]|joy|nui|sue|t(er|ry)|voy)|po(ch|xy)|qu(al|ip)|r(ase|ect|ode|ror|upt)|s(say|ter)|t(h(er|ic|os)|ude)|v(ade|e(nt|ry)|ict|oke)|x(a(ct|lt)|cel|ert|i(le|st)|pel|t(ol|ra)|ult)|ying)|f(a(ble|cet|i(nt|ry|th)|lse|n(cy|ny)|rce|t(al|ty)|u(lt|na)|vor)|e(ast|cal|ign|l(la|on)|m(me|ur)|nce|r(al|ry)|t(al|ch|id|us)|ver|wer)|i(b(er|re)|cus|e(ld|nd|ry)|ft[hy]|ght|l(e[rt]|ly|my|th)|n(al|ch|er)|rst|shy|xer|zzy)|jord|l(a(ck|i[lr]|k[ey]|me|nk|re|s[hk])|e(ck|et|sh)|i(ck|er|n[gt]|rt)|o(at|ck|o[dr]|ra|ss|u[rt]|wn)|u(ff|id|ke|me|n[gk]|sh|te)|yer)|o(amy|c(al|us)|ggy|ist|l(io|ly)|r(ay|ce|g[eo]|t[ehy]|um)|und|yer)|r(a(il|me|nk|ud)|e(ak|e[dr]|sh)|i(ar|ed|ll|sk|tz)|o(ck|n[dt]|st|th|wn|ze)|uit)|u(dge|gue|lly|n(gi|ky|ny)|r(or|ry)|ssy|zzy))|g(a(ffe|ily|m(er|ma|ut)|ssy|u(dy|ge|nt|ze)|vel|wky|y(er|ly)|zer)|e(cko|e(ky|se)|n(ie|re))|ho(st|ul)|i(ant|ddy|psy|r(ly|th)|ve[nr])|l(a(de|nd|re|ss|ze)|ea[mn]|i(de|nt)|o(at|be|om|ry|ss|ve)|yph)|n(ash|ome)|o(dly|ing|l(em|ly)|n(ad|er)|o(dy|ey|fy|se)|rge|u(ge|rd))|r(a(ce|de|ft|i[ln]|n[dt]|p[eh]|s[ps]|te|v[ey]|ze)|e(at|e[dnt])|i(ef|ll|m[ey]|nd|pe)|o(an|in|om|pe|ss|u[pt]|ve|w[ln])|u(el|ff|nt))|u(a(rd|va)|es[st]|i(de|l[det]|se)|l(ch|ly)|m(bo|my)|ppy|st[oy])|ypsy)|h(a(bit|iry|lve|ndy|ppy|r(dy|em|py|ry|sh)|st[ey]|t(ch|er)|u(nt|te)|v(en|oc)|zel)|e(a(dy|r[dt]|th|v[ey])|dge|fty|ist|l(ix|lo)|nce|ron)|i(lly|nge|pp[oy]|tch)|o(ard|bby|ist|lly|mer|n(ey|or)|r(de|ny|se)|t(el|ly)|u(nd|se)|ve[lr]|wdy)|u(m(an|id|or|ph|us)|n(ch|ky)|rry|s(ky|sy)|tch)|y(dro|ena|men|per))|i(ci(ly|ng)|d(eal|io[mt]|ler|yll)|gloo|liac|m(age|bue|p(el|ly))|n(ane|box|cur|dex|e(pt|rt)|fer|got|l(ay|et)|ner|put|t(er|ro))|onic|r(ate|ony)|s(let|sue)|tchy|vory)|j(a(unt|zzy)|e(lly|rky|tty|wel)|iffy|o(i(nt|st)|ker|lly|ust)|u(dge|ic[ey]|m(bo|py)|nt[ao]|ror))|k(a(ppa|rma|yak)|ebab|haki|i(nky|osk|tty)|n(a(ck|ve)|e(ad|e[dl]|lt)|ife|o(ck|ll|wn))|oala|rill)|l(a(b(el|or)|d(en|le)|ger|n(ce|ky)|p(el|se)|r(ge|va)|sso|t(ch|er|he|te)|ugh|yer)|e(a(ch|fy|ky|nt|pt|rn|s[eht]|ve)|dge|e(ch|ry)|fty|g(al|gy)|m(on|ur)|per|ve[lr])|i(bel|ege|ght|ken|lac|m(bo|it)|n(e[nr]|go)|pid|the|v(er|id))|lama|o(a(my|th)|bby|c(al|us)|dge|fty|gi[cn]|o(py|se)|rry|ser|us[ey]|ver|w(er|ly)|yal)|u(c(id|ky)|m(en|py)|n(ar|ch|ge)|pus|r(ch|id)|sty)|y(ing|mph|nch|ric))|m(a(c(aw|ho|ro)|d(am|ly)|fia|g(ic|ma)|ize|jor|ker|m(bo|m[ay])|n(g[aeoy]|i[ac]|ly|or)|ple|r(ch|ry|sh)|s(on|se)|t(ch|ey)|uve|xim|y(be|or))|e(a(ly|nt|ty)|cca|d(al|i[ac])|l(ee|on)|r(cy|ge|it|ry)|t(al|er|ro))|i(cro|d(ge|st)|ght|lky|mic|n(ce|er|im|or|ty|us)|rth|s(er|sy))|o(cha|d(al|e[lm])|gul|ist|l(ar|dy)|n(ey|th)|o(dy|se)|r(al|on|ph)|ssy|t(el|if|or|to)|u(lt|n[dt]|rn|se|th)|v(er|ie)|wer)|u(c(ky|us)|ddy|lch|mmy|nch|r(al|ky)|s(hy|ic|ky|ty))|yrrh)|n(a(dir|ive|nny|s(al|ty)|tal|v(al|el))|e(edy|igh|r(dy|ve)|ver|w(er|ly))|i(c(er|he)|ece|ght|n(ja|ny|th))|o(bl[ey]|is[ey]|mad|ose|rth|sey|tch|vel)|u(dge|rse|tty)|y(lon|mph))|o(aken|bese|c(cur|ean|t(al|et))|dd(er|ly)|f(f(al|er)|ten)|l(de[nr]|ive)|m(bre|ega)|n(ion|set)|p(era|i(ne|um)|tic)|r(bit|der|gan)|t(her|ter)|u(ght|nce|t(do|er|go))|v(a(ry|te)|ert|ine|oid)|w(ing|ner)|xide|zone)|p(a(ddy|gan|int|l(er|sy)|n(el|ic|sy)|p(al|er)|r(er|ka|ry|se|ty)|st[aey]|t(ch|io|sy|ty)|use|ye[er])|e(a(c[eh]|rl)|can|dal|n(al|ce|n[ey])|r(ch|il|ky)|s(ky|to)|t(al|ty))|h(ase|o(n[ey]|to))|i(ano|cky|e(ce|ty)|ggy|lot|n(ch|ey|ky|to)|per|que|t(ch|hy)|vot|x(el|ie)|zza)|l(a(ce|i[dnt]|n[ekt]|te|za)|ea[dt]|ie[dr]|u(ck|m[bep]|nk|sh))|o(esy|i(nt|se)|ker|l(ar|ka|yp)|och|ppy|rch|s(er|it|se)|u(ch|nd|ty)|wer)|r(a(nk|wn)|e(en|ss)|i(c[ek]|de|ed|m[eo]|nt|or|sm|vy|ze)|o(be|n[eg]|of|se|ud|ve|wl|xy)|u(de|ne))|salm|u(bic|dgy|ffy|l(py|se)|nch|p(al|il|py)|r(e[er]|ge|se)|shy|tty)|ygmy)|qu(a(ck|il|ke|lm|r[kt]|s[hi])|e(e[nr]|ll|ry|st|ue)|i(ck|et|l[lt]|rk|te)|ot[aeh])|r(a(b(bi|id)|cer|d(ar|i[io])|i(ny|se)|jah|l(ly|ph)|men|n(ch|dy|ge)|pid|rer|spy|t(io|ty)|ven|yon|zor)|e(a(c[ht]|dy|lm|rm)|b(ar|el|u[st])|c(ap|u[rt])|edy|f(er|it)|gal|hab|ign|l(a[xy]|ic)|mit|n(al|ew)|p(ay|el|ly)|run|s(et|in)|t(ch|r[oy])|use|v(el|ue))|h(ino|yme)|i(d(er|ge)|fle|g(ht|id|or)|nse|pe[nr]|s(e[nr]|ky)|v(al|e[rt]))|o(a(ch|st)|b(in|ot)|cky|deo|g(er|ue)|o(my|st)|tor|u(g[eh]|nd|se|te)|ver|w(dy|er)|yal)|u(d(dy|er)|gby|ler|m(ba|or)|pee|ral|sty))|s(a(dly|fer|int|l(ad|ly|on|sa|ty|v[eo])|n(dy|er)|ppy|ssy|t(in|yr)|u(c[ey]|na|te)|v(o[ry]|vy))|c(a(l[depy]|mp|nt|r[efy])|en[et]|ion|o(ff|ld|ne|op|pe|r[en]|u[rt]|wl)|r(a[mp]|e[ew]|u[bm])|uba)|e(dan|edy|gue|ize|men|nse|pia|r(if|um|ve)|tup|ve[nr]|wer)|h(a(ck|d[ey]|ft|k[ey]|l[elt]|me|nk|pe|r[dekp]|ve|wl)|e(ar|e[nprt]|ik|l[fl])|i(ed|ft|n[ey]|r[ekt])|o(al|ck|ne|o[kt]|r[ent]|ut|ve|w[ny])|r(ew|u[bg])|u(ck|nt|sh)|yly)|i(e(ge|ve)|g(ht|ma)|l(ky|ly)|n(ce|ew|ge)|ren|ssy|xt[hy])|k(ate|i(er|ff|ll|mp|rt)|u(l[kl]|nk))|l(a(ck|in|n[gt]|sh|te|ve)|e(e[kpt]|pt)|i(c[ek]|de|m[ey]|n[gk])|o(op|pe|sh|th)|u(mp|n[gk]|rp|sh)|yly)|m(a(ck|ll|rt|sh)|e(ar|l[lt])|i(le|rk|t[eh])|o(ck|k[ey]|te))|n(a(ck|il|k[ey]|r[el])|e(ak|er)|i(de|ff|pe)|o(op|r[et]|ut|wy)|u(ck|ff))|o(apy|ber|ggy|l(ar|id|ve)|n(ar|ic)|ot[hy]|rry|u(nd|th)|wer)|p(a(ce|de|nk|r[ek]|sm|wn)|e(a[kr]|ck|ed|l[lt]|n[dt]|rm)|i(c[ey]|e[dl]|k[ey]|l[lt]|n[ey]|re|te)|l(at|it)|o(il|ke|o[fkln]|r[et]|ut)|r(ay|ee|ig)|u(nk|r[nt]))|qu(a[dt]|ib)|t(a(ck|ff|ge|i[dnr]|ke|l[ekl]|mp|n[dk]|r[ekt]|sh|te|ve)|e(a[dklm]|e[dlpr]|in|rn)|i(ck|ff|l[lt]|n[gkt])|o(ck|ic|ke|le|mp|n[ey]|o[dlp]|r[ekmy]|ut|ve)|r(a[pwy]|ip|ut)|u(ck|dy|ff|mp|n[gkt])|yle)|u(ave|gar|i(ng|te)|l(ky|ly)|mac|nny|per|r(er|ge|ly)|shi)|w(a(m[ip]|rm|sh|th)|e(a[rt]|e[pt]|ll|pt)|i(ft|ll|n[eg]|rl|sh)|o(o[np]|r[den])|ung)|y(nod|rup))|t(a(b(by|le|oo)|c(it|ky)|ffy|int|ke[nr]|l(ly|on)|mer|ng[oy]|p(er|ir)|r(dy|ot)|st[ey]|tty|unt|wny)|e(a(ch|ry|se)|ddy|eth|mpo|n(et|or|se|th)|p(ee|id)|r(ra|se)|sty)|h(ank|e(ft|ir|me|re|se|ta)|i(ck|ef|gh|n[gk]|rd)|o(ng|rn|se)|r(e[ew]|o[bw]|um)|um[bp]|yme)|i(ara|bia|dal|g(er|ht)|lde|m(er|id)|psy|t(an|he|le))|o(ast|d(ay|dy)|ken|n(al|ga|ic)|oth|p(az|ic)|r(ch|so|us)|t(al|em)|u(ch|gh)|we[lr]|xi[cn])|r(a(c[ekt]|de|i[lnt]|mp|sh|wl)|e(a[dt]|nd)|i(a[dl]|be|c[ek]|ed|pe|te)|o(ll|op|pe|ut|ve)|u(c[ek]|er|ly|mp|nk|s[st]|th)|yst)|u(b(al|er)|l(ip|le)|mor|nic|rbo|tor)|w(ang|e(ak|e[dt])|i(ce|ne|rl|st|xt))|ying)|u(dder|l(cer|tra)|mbra|n(c(le|ut)|d(er|id|ue)|f(ed|it)|i(fy|on|t[ey])|lit|met|set|ti[el]|wed|zip)|p(per|set)|r(ban|ine)|s(age|her|ing|u(al|rp))|t(ile|ter))|v(a(gue|l(et|id|or|ue|ve)|p(id|or)|u(lt|nt))|e(gan|n(om|ue)|r(ge|s[eo]|ve))|i(car|deo|g(il|or)|lla|nyl|ola|per|r(al|us)|s(it|or|ta)|tal|vid|xen)|o(cal|dka|gue|i(ce|la)|mit|ter|uch|wel)|ying)|w(a(cky|fer|g(er|on)|i(st|ve)|ltz|rty|ste|t(ch|er)|ver|xen)|e(a(ry|ve)|dge|edy|i(gh|rd)|l(ch|sh)|nch)|h(a(ck|le|rf)|e(at|el|lp|re)|i(ch|ff|le|n[ey]|rl|sk|te)|o(le|op|se))|i(d(e[nr]|ow|th)|eld|ght|lly|mpy|n(c[eh]|dy)|s(er|py)|t(ch|ty))|o(ken|m(an|en)|o(dy|er|ly|zy)|r(dy|ld|ry|s[et]|th)|u(ld|nd)|ven)|r(a(ck|th)|e(ak|ck|st)|i(ng|st|te)|o(ng|te)|ung|yly))|y(acht|ea(rn|st)|ield|ou(ng|th))|z(e(bra|sty)|onal))".