-
Notifications
You must be signed in to change notification settings - Fork 70
/
bayessdbm_seen_delete.t
executable file
·286 lines (188 loc) · 6.31 KB
/
bayessdbm_seen_delete.t
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
#!/usr/bin/perl
use Data::Dumper;
use lib '.'; use lib 't';
use SATest; sa_t_init("bayessdbm_seen_delete");
use Test;
use constant HAS_SDBM_FILE => eval { require SDBM_File; };
BEGIN {
if (-e 't/test_dir') {
chdir 't';
}
if (-e 'test_dir') {
unshift(@INC, '../blib/lib');
}
plan tests => (HAS_SDBM_FILE ? 54 : 0);
};
exit unless HAS_SDBM_FILE;
tstlocalrules ("
bayes_store_module Mail::SpamAssassin::BayesStore::SDBM
bayes_learn_to_journal 0
");
use Mail::SpamAssassin;
my $sa = create_saobj();
$sa->init();
ok($sa);
ok($sa->{bayes_scanner});
ok(!$sa->{bayes_scanner}->is_scan_available());
open(MAIL,"< data/spam/001");
my $raw_message = do {
local $/;
<MAIL>;
};
close(MAIL);
ok($raw_message);
my $mail = $sa->parse( $raw_message );
ok($mail);
my $body = $sa->{bayes_scanner}->get_body_from_msg($mail);
ok($body);
my $toks = $sa->{bayes_scanner}->tokenize($mail, $body);
ok(scalar(keys %{$toks}) > 0);
my($msgid,$msgid_hdr) = $sa->{bayes_scanner}->get_msgid($mail);
# $msgid is the generated hash messageid
# $msgid_hdr is the Message-Id header
ok($msgid eq 'ce33e4a8bc5798c65428d6018380bae346c7c126@sa_generated');
ok($msgid_hdr eq '9PS291LhupY');
ok($sa->{bayes_scanner}->{store}->tie_db_writable());
ok(!$sa->{bayes_scanner}->{store}->seen_get($msgid));
$sa->{bayes_scanner}->{store}->untie_db();
ok($sa->{bayes_scanner}->learn(1, $mail));
ok(!$sa->{bayes_scanner}->learn(1, $mail));
ok($sa->{bayes_scanner}->{store}->tie_db_writable());
ok($sa->{bayes_scanner}->{store}->seen_get($msgid) eq 's');
$sa->{bayes_scanner}->{store}->untie_db();
ok($sa->{bayes_scanner}->{store}->tie_db_writable());
my $tokerror = 0;
foreach my $tok (keys %{$toks}) {
my ($spam, $ham, $atime) = $sa->{bayes_scanner}->{store}->tok_get($tok);
if ($spam == 0 || $ham > 0) {
$tokerror = 1;
}
}
ok(!$tokerror);
my $tokens = $sa->{bayes_scanner}->{store}->tok_get_all(keys %{$toks});
ok($tokens);
$tokerror = 0;
foreach my $tok (@{$tokens}) {
my ($token, $tok_spam, $tok_ham, $atime) = @{$tok};
if ($tok_spam == 0 || $tok_ham > 0) {
$tokerror = 1;
}
}
ok(!$tokerror);
$sa->{bayes_scanner}->{store}->untie_db();
ok($sa->{bayes_scanner}->learn(0, $mail));
ok($sa->{bayes_scanner}->{store}->tie_db_writable());
ok($sa->{bayes_scanner}->{store}->seen_get($msgid) eq 'h');
$sa->{bayes_scanner}->{store}->untie_db();
ok($sa->{bayes_scanner}->{store}->tie_db_writable());
$tokerror = 0;
foreach my $tok (keys %{$toks}) {
my ($spam, $ham, $atime) = $sa->{bayes_scanner}->{store}->tok_get($tok);
if ($spam > 0 || $ham == 0) {
$tokerror = 1;
}
}
ok(!$tokerror);
$sa->{bayes_scanner}->{store}->untie_db();
ok($sa->{bayes_scanner}->forget($mail));
ok($sa->{bayes_scanner}->{store}->tie_db_writable());
ok(!$sa->{bayes_scanner}->{store}->seen_get($msgid));
$sa->{bayes_scanner}->{store}->untie_db();
undef $sa;
sa_t_init('bayes'); # this wipes out what is there and begins anew
# make sure we learn to a journal
tstlocalrules ("
bayes_store_module Mail::SpamAssassin::BayesStore::SDBM
bayes_learn_to_journal 1
");
$sa = create_saobj();
$sa->init();
ok(!-e 'log/user_state/bayes_journal');
ok($sa->{bayes_scanner}->learn(1, $mail));
ok(-e 'log/user_state/bayes_journal');
$sa->{bayes_scanner}->sync(1); # always returns 0, so no need to check return
ok(!-e 'log/user_state/bayes_journal');
ok(-e 'log/user_state/bayes_seen.pag');
ok(-e 'log/user_state/bayes_seen.dir');
ok(-e 'log/user_state/bayes_toks.pag');
ok(-e 'log/user_state/bayes_toks.dir');
undef $sa;
sa_t_init('bayes'); # this wipes out what is there and begins anew
# make sure we learn to a journal
tstlocalrules ("
bayes_store_module Mail::SpamAssassin::BayesStore::SDBM
bayes_learn_to_journal 0
bayes_min_spam_num 10
bayes_min_ham_num 10
");
# we get to bastardize the existing pattern matching code here. It lets us provide
# our own checking callback and keep using the existing ok_all_patterns call
%patterns = ( 1 => 'Acted on message' );
ok(salearnrun("--spam data/spam", \&check_examined));
ok_all_patterns();
ok(salearnrun("--ham data/nice", \&check_examined));
ok_all_patterns();
ok(salearnrun("--ham data/whitelists", \&check_examined));
ok_all_patterns();
%patterns = ( 'non-token data: bayes db version' => 'db version' );
ok(salearnrun("--dump magic", \&patterns_run_cb));
ok_all_patterns();
# now delete the journal and bayes_seen -- should still be possible
# for Bayes to continue...
unlink 'log/user_state/bayes_journal';
ok(unlink 'log/user_state/bayes_seen.pag');
ok(unlink 'log/user_state/bayes_seen.dir');
use constant SCAN_USING_PERL_CODE_TEST => 1;
if (SCAN_USING_PERL_CODE_TEST) {
$sa = create_saobj();
$sa->init();
open(MAIL,"< ../sample-nonspam.txt");
$raw_message = do {
local $/;
<MAIL>;
};
close(MAIL);
$mail = $sa->parse( $raw_message );
$body = $sa->{bayes_scanner}->get_body_from_msg($mail);
my $msgstatus = Mail::SpamAssassin::PerMsgStatus->new($sa, $mail);
ok($msgstatus);
my $score = $sa->{bayes_scanner}->scan($msgstatus, $mail, $body);
# Pretty much we can't count on the data returned with such little training
# so just make sure that the score wasn't equal to .5 which is the default
# return value.
print "\treturned score: $score\n";
ok($score =~ /\d/ && $score <= 1.0 && $score != .5);
open(MAIL,"< ../sample-spam.txt");
$raw_message = do {
local $/;
<MAIL>;
};
close(MAIL);
$mail = $sa->parse( $raw_message );
$body = $sa->{bayes_scanner}->get_body_from_msg($mail);
$msgstatus = Mail::SpamAssassin::PerMsgStatus->new($sa, $mail);
$score = $sa->{bayes_scanner}->scan($msgstatus, $mail, $body);
# Pretty much we can't count on the data returned with such little training
# so just make sure that the score wasn't equal to .5 which is the default
# return value.
print "\treturned score: $score\n";
ok($score =~ /\d/ && $score <= 1.0 && $score != .5);
}
ok($sa->{bayes_scanner}->{store}->clear_database());
ok(!-e 'log/user_state/bayes_journal');
ok(!-e 'log/user_state/bayes_seen.pag');
ok(!-e 'log/user_state/bayes_seen.dir');
ok(!-e 'log/user_state/bayes_toks.pag');
ok(!-e 'log/user_state/bayes_toks.dir');
sub check_examined {
local ($_);
my $string = shift;
if (defined $string) {
$_ = $string;
} else {
$_ = join ('', <IN>);
}
if ($_ =~ /(?:Forgot|Learned) tokens from \d+ message\(s\) \(\d+ message\(s\) examined\)/) {
$found{'Acted on message'}++;
}
}