http://bugzilla.spamassassin.org/show_bug.cgi?id=4094
------- Additional Comments From [EMAIL PROTECTED] 2005-02-22 12:42 ------- Subject: Re: Add plugin to make fuzzy matching easier On Tue, Feb 22, 2005 at 12:26:43PM -0800, [EMAIL PROTECTED] wrote: > it should have been in SVN earlier though, which could have avoided this. <slightly bitter> Definitely. I wouldn't have spent (wasted?) the past several days working on the code + rules just to have it "replaced" seemingly at random without any discussion, etc. </slightly bitter> Anyway, if the consensus is that the plugin is the better method, that's fine with me. My goal was to at least get a rule hit for messages that are otherwise missed by set 0, and the obfu stuff was a big target. Someone will need to merge out the rules and such, though, between the plugin and non-plugin versions. The non-plugin version has an almost universally better hitrate right now, at least according to the results from the most recent 2 weeks in my corpus: OVERALL% SPAM% HAM% S/O RANK SCORE NAME 49623 43664 5959 0.880 0.00 0.00 (all messages) 100.000 87.9915 12.0085 0.880 0.00 0.00 (all messages as %) 0.244 0.2771 0.0000 1.000 0.43 0.01 T_INT_AFFORDABLE 0.236 0.2680 0.0000 1.000 0.42 0.01 T_INT_AFFORDABLE2 0.206 0.2336 0.0000 1.000 0.37 0.01 T_INT_ANXIETY 0.040 0.0458 0.0000 1.000 0.26 0.01 T_INT_ANXIETY2 0.973 1.1062 0.0000 1.000 0.86 0.01 T_INT_BILLION 0.947 1.0764 0.0000 1.000 0.83 0.01 T_INT_BILLION2 0.091 0.1031 0.0000 1.000 0.31 0.01 T_INT_CELEBREX 0.004 0.0046 0.0000 1.000 0.15 0.01 T_INT_CELEBREX2 3.244 3.6872 0.0000 1.000 1.00 0.01 T_INT_CIALIS 3.543 3.9163 0.8055 0.829 0.42 0.01 T_INT_CIALIS2 0.538 0.6115 0.0000 1.000 0.64 0.01 T_INT_CREDIT 0.010 0.0115 0.0000 1.000 0.18 0.01 T_INT_CREDIT2 0.018 0.0206 0.0000 1.000 0.21 0.01 T_INT_ERECT 0.111 0.1260 0.0000 1.000 0.34 0.01 T_INT_ERECT2 0.318 0.3619 0.0000 1.000 0.48 0.01 T_INT_FREE 0.099 0.1122 0.0000 1.000 0.32 0.01 T_INT_FREE2 0.006 0.0069 0.0000 1.000 0.17 0.01 T_INT_HUNDREDS 0.000 0.0000 0.0000 0.500 0.13 0.01 T_INT_HUNDREDS2 0.500 0.5680 0.0000 1.000 0.61 0.01 T_INT_LEVITRA 0.026 0.0298 0.0000 1.000 0.24 0.01 T_INT_LEVITRA2 0.288 0.3275 0.0000 1.000 0.46 0.01 T_INT_MILF 0.020 0.0229 0.0000 1.000 0.23 0.01 T_INT_MILF2 1.141 1.2940 0.0168 0.987 0.72 0.01 T_INT_MILLION 1.153 1.3077 0.0168 0.987 0.74 0.01 T_INT_MILLION2 0.466 0.5290 0.0000 1.000 0.59 0.01 T_INT_MONEY 0.425 0.4832 0.0000 1.000 0.54 0.01 T_INT_MONEY2 0.895 1.0169 0.0000 1.000 0.78 0.01 T_INT_MORTGAGE 0.006 0.0069 0.0000 1.000 0.17 0.01 T_INT_MORTGAGE2 0.433 0.4924 0.0000 1.000 0.56 0.01 T_INT_OBLIGATION 0.006 0.0069 0.0000 1.000 0.17 0.01 T_INT_OBLIGATION2 0.639 0.7260 0.0000 1.000 0.69 0.01 T_INT_OFFERS 0.574 0.6527 0.0000 1.000 0.65 0.01 T_INT_OFFERS2 0.335 0.3802 0.0000 1.000 0.50 0.01 T_INT_PENIS 0.214 0.2359 0.0503 0.824 0.09 0.01 T_INT_PENIS2 0.947 1.0764 0.0000 1.000 0.83 0.01 T_INT_PHARMACY 0.012 0.0137 0.0000 1.000 0.20 0.01 T_INT_PHARMACY2 0.161 0.1832 0.0000 1.000 0.35 0.01 T_INT_PHENT 0.000 0.0000 0.0000 0.500 0.13 0.01 T_INT_PHENT2 2.118 2.4070 0.0000 1.000 0.95 0.01 T_INT_PILLS 3.120 2.9063 4.6820 0.383 0.22 0.01 T_INT_PILLS2 0.590 0.6710 0.0000 1.000 0.67 0.01 T_INT_PRESCRIPT 0.445 0.5061 0.0000 1.000 0.57 0.01 T_INT_PRESCRIPT2 0.278 0.3023 0.1007 0.750 0.00 0.01 T_INT_PRICES 0.417 0.4741 0.0000 1.000 0.53 0.01 T_INT_PRICES2 0.058 0.0664 0.0000 1.000 0.28 0.01 T_INT_PROFIT 0.058 0.0664 0.0000 1.000 0.28 0.01 T_INT_PROFIT2 0.748 0.8497 0.0000 1.000 0.73 0.01 T_INT_REFINANCE 0.532 0.6046 0.0000 1.000 0.62 0.01 T_INT_REFINANCE2 0.091 0.1031 0.0000 1.000 0.31 0.01 T_INT_ROLEX 0.060 0.0687 0.0000 1.000 0.29 0.01 T_INT_ROLEX2 0.867 0.9848 0.0000 1.000 0.76 0.01 T_INT_SOFTWARE 0.752 0.8543 0.0000 1.000 0.75 0.01 T_INT_SOFTWARE2 0.905 1.0283 0.0000 1.000 0.81 0.01 T_INT_THOUSANDS 0.899 1.0214 0.0000 1.000 0.80 0.01 T_INT_THOUSANDS2 1.548 1.7589 0.0000 1.000 0.94 0.01 T_INT_VALIUM 1.217 1.3833 0.0000 1.000 0.91 0.01 T_INT_VALIUM2 2.721 3.0918 0.0000 1.000 0.98 0.01 T_INT_VIAGRA 1.461 1.6604 0.0000 1.000 0.92 0.01 T_INT_VIAGRA2 0.955 1.0856 0.0000 1.000 0.84 0.01 T_INT_VICODIN 0.752 0.8543 0.0000 1.000 0.75 0.01 T_INT_VICODIN2 0.345 0.3916 0.0000 1.000 0.51 0.01 T_INT_VIOXX 0.230 0.2611 0.0000 1.000 0.40 0.01 T_INT_VIOXX2 0.723 0.8222 0.0000 1.000 0.72 0.01 T_INT_XANAX 0.689 0.7833 0.0000 1.000 0.70 0.01 T_INT_XANAX2 ------- You are receiving this mail because: ------- You are on the CC list for the bug, or are watching someone who is.
