X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=t%2Flei_dedupe.t;fp=t%2Flei_dedupe.t;h=08f38aa0059e9f9c49165ccef84c52808a932246;hb=d2a7dcb58ffb9604b2023159431fcdc4871f368f;hp=0000000000000000000000000000000000000000;hpb=7f17df5c6f1892ef53f149a0ab24a5d917cce7d9;p=public-inbox.git diff --git a/t/lei_dedupe.t b/t/lei_dedupe.t new file mode 100644 index 00000000..08f38aa0 --- /dev/null +++ b/t/lei_dedupe.t @@ -0,0 +1,59 @@ +#!perl -w +# Copyright (C) 2020 all contributors +# License: AGPL-3.0+ +use strict; +use v5.10.1; +use Test::More; +use PublicInbox::TestCommon; +use PublicInbox::Eml; +require_mods(qw(DBD::SQLite)); +use_ok 'PublicInbox::LeiDedupe'; +my $eml = eml_load('t/plack-qp.eml'); +my $mid = $eml->header_raw('Message-ID'); +my $different = eml_load('t/msg_iter-order.eml'); +$different->header_set('Message-ID', $mid); + +my $lei = { opt => { dedupe => 'none' } }; +my $dd = PublicInbox::LeiDedupe->new($lei); +$dd->prepare_dedupe; +ok(!$dd->is_dup($eml), '1st is_dup w/o dedupe'); +ok(!$dd->is_dup($eml), '2nd is_dup w/o dedupe'); +ok(!$dd->is_dup($different), 'different is_dup w/o dedupe'); + +for my $strat (undef, 'content') { + $lei->{opt}->{dedupe} = $strat; + $dd = PublicInbox::LeiDedupe->new($lei); + $dd->prepare_dedupe; + my $desc = $strat // 'default'; + ok(!$dd->is_dup($eml), "1st is_dup with $desc dedupe"); + ok($dd->is_dup($eml), "2nd seen with $desc dedupe"); + ok(!$dd->is_dup($different), "different is_dup with $desc dedupe"); +} +$lei->{opt}->{dedupe} = 'bogus'; +eval { PublicInbox::LeiDedupe->new($lei) }; +like($@, qr/unsupported.*bogus/, 'died on bogus strategy'); + +$lei->{opt}->{dedupe} = 'mid'; +$dd = PublicInbox::LeiDedupe->new($lei); +$dd->prepare_dedupe; +ok(!$dd->is_dup($eml), '1st is_dup with mid dedupe'); +ok($dd->is_dup($eml), '2nd seen with mid dedupe'); +ok($dd->is_dup($different), 'different seen with mid dedupe'); + +$lei->{opt}->{dedupe} = 'oid'; +$dd = PublicInbox::LeiDedupe->new($lei); +$dd->prepare_dedupe; + +# --augment won't have OIDs: +ok(!$dd->is_dup($eml), '1st is_dup with oid dedupe (augment)'); +ok($dd->is_dup($eml), '2nd seen with oid dedupe (augment)'); +ok(!$dd->is_dup($different), 'different is_dup with mid dedupe (augment)'); +$different->header_set('Status', 'RO'); +ok($dd->is_dup($different), 'different seen with oid dedupe Status removed'); + +ok(!$dd->is_dup($eml, '01d'), '1st is_dup with oid dedupe'); +ok($dd->is_dup($different, '01d'), 'different content ignored if oid matches'); +ok($dd->is_dup($eml, '01D'), 'case insensitive oid comparison :P'); +ok(!$dd->is_dup($eml, '01dbad'), 'case insensitive oid comparison :P'); + +done_testing;