commit b0fbe8b53fdc235750205fe4b8b47de8f1e7d761 Author: Karl Seguin Date: Tue Nov 2 09:42:12 2010 -0400 initial commit diff --git a/README.textile b/README.textile new file mode 100644 index 0000000..01339ec --- /dev/null +++ b/README.textile @@ -0,0 +1,7 @@ +h1. Overview + +This project aims to make available a list of regular expression which match vulgar words. The list is far from comprehensive, but hopefully can be used as a first line of defense. + +As a general rule, words which can have a legitimate use (say _hancock_) must be exact matches to (@^(c|k|ck|q)[o0](c|k|ck|q)[s$]?$@) + +For best performance, if your library supports it, consider enabling explicit captures. \ No newline at end of file diff --git a/en.txt b/en.txt new file mode 100644 index 0000000..42dd240 --- /dev/null +++ b/en.txt @@ -0,0 +1,73 @@ +^[a@][s$][s$]$ +[a@][s$][s$]h[o0][l1][e3][s$]? +b[a@][s$][t+][a@]rd +b[e3][a@][s$][t+][i1][a@]?[l1]([i1][t+]y)? +b[e3][a@][s$][t+][i1][l1][i1][t+]y +b[e3][s$][t+][i1][a@][l1]([i1][t+]y)? +b[i1][t+]ch[s$]? +b[i1][t+]ch[e3]r[s$]? +b[i1][t+]ch[e3][s$] +b[i1][t+]ch[i1]ng? +b[l1][o0]wj[o0]b[s$]? +c[l1][i1][t+] +^(c|k|ck|q)[o0](c|k|ck|q)[s$]?$ +(c|k|ck|q)[o0](c|k|ck|q)[s$]u +(c|k|ck|q)[o0](c|k|ck|q)[s$]u(c|k|ck|q)[e3]d +(c|k|ck|q)[o0](c|k|ck|q)[s$]u(c|k|ck|q)[e3]r +(c|k|ck|q)[o0](c|k|ck|q)[s$]u(c|k|ck|q)[i1]ng +(c|k|ck|q)o0](c|k|ck|q)[s$]u(c|k|ck|q)[s$] +^cum[s$]?$ +cumm[e3]r +cumm[i1]ngcock +cum[s$]h[o0][t+] +cun[i1][l1][i1]ngu[s$] +cun[i1][l1][l1][i1]ngu[s$] +cunn[i1][l1][i1]ngu[s$] +cun[t+][s$]? +cun[t+][l1][i1](c|k|ck|q) +cun[t+][l1][i1](c|k|ck|q)[e3]r +cun[t+][l1][i1](c|k|ck|q)i1]ng +cyb[e3]r(ph|f)u(c|k|ck|q) +d[a@]mn +d[i1][l1]d[o0] +d[i1][l1]d[o0][s$] +d[i1]n(c|k|ck|q) +d[i1]n(c|k|ck|q)[s$] +[e3]j[a@]cu[l1] +(ph|f)[a@]g[s$]? +(ph|f)[a@]gg[i1]ng +(ph|f)[a@]gg?[o0][t+][s$]? +(ph|f)[a@]gg[s$] +(ph|f)[e3][l1][l1]?[a@][t+][i1][o0] +(ph|f)u(c|k|ck|q) +(ph|f)u(c|k|ck|q)[s$]? +g[a@]ngb[a@]ng[s$]? +g[a@]ngb[a@]ng[e3]d +g[a@]y +h[o0]m?m[o0] +h[o0]rny +j[a@](c|k|ck|q)\-?[o0](ph|f)(ph|f)? +j[e3]rk\-?[o0](ph|f)(ph|f)? +j[i1][s$]m +j[i1]z +j[i1]zm +k[o0]ndum[s$]? +mast(e|ur)b(8|ait|ate) +n[i1]gg?[e3]r[s$]? +[o0]rg[a@][s$][i1]m[s$]? +[o0]rg[a@][s$]m[s$]? +p[e3]nn?[i1][s$] +p[i1][s$][s$] +p[i1][s$][s$][o0](ph|f)(ph|f) +p[o0]rn +p[o0]rn[o0][s$]? +p[o0]rn[o0]gr[a@]phy +pr[i1]ck[s$]? +pu[s$][s$][i1][e3][s$] +pu[s$][s$]y[s$]? +[s$][e3]x +[s$]h[i1][t+][s$]? +[s$][l1]u[t+][s$]? +[s$]mu[t+][s$]? +[s$]punk[s$]? +[t+]w[a@][t+][s$]? diff --git a/license.txt b/license.txt new file mode 100644 index 0000000..53c7183 --- /dev/null +++ b/license.txt @@ -0,0 +1 @@ +This work is licensed under the Creative Commons Attribution 3.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/3.0/ or send a letter to Creative Commons, 171 Second Street, Suite 300, San Francisco, California, 94105, USA. \ No newline at end of file