[Feature] Add learn condition to the default configuration

1 files changed, 47 insertions, 20 deletions

diff --git a/conf/statistic.conf b/conf/statistic.conf
index 697f1ccef..e574d0027 100644
--- a/conf/statistic.conf
+++ b/conf/statistic.conf
@@ -20,27 +20,54 @@
 # http://rspamd.com/rspamd_statistics/bayes.ham.sqlite
 
 classifier "bayes" {
-    tokenizer {
-        name = "osb";
-    }
-    cache {
-        path = "${DBDIR}/learn_cache.sqlite";
-    }
-    min_tokens = 11;
-    backend = "sqlite3";
-    languages_enabled = true;
-    min_learns = 200;
+  tokenizer {
+    name = "osb";
+  }
+  cache {
+    path = "${DBDIR}/learn_cache.sqlite";
+  }
+  min_tokens = 11;
+  backend = "sqlite3";
+  languages_enabled = true;
+  min_learns = 200;
 
-    statfile {
-        symbol = "BAYES_HAM";
-        path = "${DBDIR}/bayes.ham.sqlite";
-        spam = false;
-    }
-    statfile {
-        symbol = "BAYES_SPAM";
-        path = "${DBDIR}/bayes.spam.sqlite";
-        spam = true;
-    }
+  statfile {
+    symbol = "BAYES_HAM";
+    path = "${DBDIR}/bayes.ham.sqlite";
+    spam = false;
+  }
+  statfile {
+    symbol = "BAYES_SPAM";
+    path = "${DBDIR}/bayes.spam.sqlite";
+    spam = true;
+  }
+  learn_condition =<<EOD
+return function(task, is_spam, is_unlearn)
+  local prob = task:get_mempool():get_variable('bayes_prob', 'double')
+
+  if prob then
+    local in_class = false
+    local cl
+    if is_spam then
+      cl = 'spam'
+      in_class = prob >= 0.9
+    else
+      cl = 'ham'
+      in_class = prob <= 0.1
+    end
+
+    if is_unlearn and (not in_class) then
+      return false,string.format('not in class %s; probability %.2f%%',
+        cl, math.abs((prob - 0.5) * 200.0))
+    elseif (not is_unlearn) and in_class then
+      return false,string.format('already in class %s; probability %.2f%%',
+        cl, math.abs((prob - 0.5) * 200.0))
+    end
+  end
+
+  return true
+end
+EOD
 }
 
 .include(try=true; priority=1) "$LOCAL_CONFDIR/local.d/statistic.conf"