infrastructure/mox
1
0
Fork 0
mirror of https://github.com/mjl-/mox.git synced 2025-07-14 01:34:37 +03:00
Code Issues Packages Projects Releases Wiki Activity

junk filter: fix adjusting word counts after train/untrain

Browse Source 
after seeing some junk messages pass the filter, i investigated word counts in
junkfilter.db. i had seen suspicious counts that were just around powers of
two. did not make sense at the time. more investigating makes it clear: instead
of setting new word counts when updating the junk filter, we were adding the
new value to the current value (instead of just setting the new value). so the
counts got approximately doubled when being updated.

users should retrain the junk filter after this update using the "retrain"
subcommand.

this also adds logging for the hypothetical case where numbers would get
decreased below zero (which would wrap around due to uints).

and this fixes junk filter tests that were passing wrong parameters to
train/untrain...
This commit is contained in:
Mechiel Lukkien
2024-12-07 16:53:53 +01:00
parent 69a4995449
commit 17baf9a883
3 changed files with 23 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
junk/filter_test.go
View File

@ -126,7 +126,7 @@ func TestFilter(t *testing.T) {
tcheck(t, err, "train spam message")
_, err = spamf.Seek(0, 0)
tcheck(t, err, "seek spam message")
err = f.TrainMessage(ctxbg, spamf, spamsize, true)
err = f.TrainMessage(ctxbg, spamf, spamsize, false)
tcheck(t, err, "train spam message")
if !f.modified {
@ -166,16 +166,16 @@ func TestFilter(t *testing.T) {
tcheck(t, err, "untrain ham message")
_, err = hamf.Seek(0, 0)
tcheck(t, err, "seek ham message")
err = f.UntrainMessage(ctxbg, hamf, spamsize, true)
err = f.UntrainMessage(ctxbg, hamf, hamsize, true)
tcheck(t, err, "untrain ham message")
_, err = spamf.Seek(0, 0)
tcheck(t, err, "seek spam message")
err = f.UntrainMessage(ctxbg, spamf, spamsize, true)
err = f.UntrainMessage(ctxbg, spamf, spamsize, false)
tcheck(t, err, "untrain spam message")
_, err = spamf.Seek(0, 0)
tcheck(t, err, "seek spam message")
err = f.UntrainMessage(ctxbg, spamf, spamsize, true)
err = f.UntrainMessage(ctxbg, spamf, spamsize, false)
tcheck(t, err, "untrain spam message")
if !f.modified {