X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=t%2Fimport.t;h=ae76858ba2ab7827bc7aaa1d45db377a0954ee64;hb=13a2fcc724576a78d0955f64dc0f4494545153c3;hp=6918484e481804ffcaee9c77c8474d023cced105;hpb=2b673b707edc91f505836e567b690d0acd1120ff;p=public-inbox.git
diff --git a/t/import.t b/t/import.t
index 6918484e..ae76858b 100644
--- a/t/import.t
+++ b/t/import.t
@@ -1,36 +1,55 @@
-# Copyright (C) 2016 all contributors
+# Copyright (C) 2016-2021 all contributors
# License: AGPL-3.0+
use strict;
use warnings;
use Test::More;
-use Email::MIME;
+use PublicInbox::Eml;
+use PublicInbox::Smsg;
use PublicInbox::Git;
use PublicInbox::Import;
-use File::Temp qw/tempdir/;
-my $dir = tempdir('pi-import-XXXXXX', TMPDIR => 1, CLEANUP => 1);
+use Fcntl qw(:DEFAULT SEEK_SET);
+use PublicInbox::TestCommon;
+use MIME::Base64 3.05; # Perl 5.10.0 / 5.9.2
+my ($dir, $for_destroy) = tmpdir();
-is(system(qw(git init -q --bare), $dir), 0, 'git init successful');
my $git = PublicInbox::Git->new($dir);
-
my $im = PublicInbox::Import->new($git, 'testbox', 'test@example');
-my $mime = Email::MIME->create(
- header => [
- From => 'a@example.com',
- To => 'b@example.com',
- 'Content-Type' => 'text/plain',
- Subject => 'this is a subject',
- 'Message-ID' => '',
- ],
- body => "hello world\n",
-);
-like($im->add($mime), qr/\A:\d+\z/, 'added one message');
+$im->init_bare;
+my $mime = PublicInbox::Eml->new(<<'EOF');
+From: a@example.com
+To: b@example.com
+Subject: this is a subject
+Message-ID:
+Date: Fri, 02 Oct 1993 00:00:00 +0000
+
+hello world
+EOF
+
+my $v2 = require_git(2.6, 1);
+my $smsg = bless {}, 'PublicInbox::Smsg' if $v2;
+like($im->add($mime, undef, $smsg), qr/\A:[0-9]+\z/, 'added one message');
+
+if ($v2) {
+ like($smsg->{blob}, qr/\A[a-f0-9]{40}\z/, 'got last object_id');
+ my @cmd = ('git', "--git-dir=$git->{git_dir}", qw(hash-object --stdin));
+ open my $in, '+<', undef or BAIL_OUT "open(+<): $!";
+ print $in $mime->as_string or die "write failed: $!";
+ $in->flush or die "flush failed: $!";
+ seek($in, 0, SEEK_SET) or die "seek: $!";
+ chomp(my $hashed_obj = xqx(\@cmd, undef, { 0 => $in }));
+ is($?, 0, 'hash-object');
+ is($hashed_obj, $smsg->{blob}, "blob object_id matches exp");
+}
+
$im->done;
my @revs = $git->qx(qw(rev-list HEAD));
is(scalar @revs, 1, 'one revision created');
+my $odd = '"=?iso-8859-1?Q?J_K=FCpper?= header_set('From', $odd);
$mime->header_set('Message-ID', '');
$mime->header_set('Subject', 'msg2');
-like($im->add($mime), qr/\A:\d+\z/, 'added 2nd message');
+like($im->add($mime, sub { $mime }), qr/\A:\d+\z/, 'added 2nd message');
$im->done;
@revs = $git->qx(qw(rev-list HEAD));
is(scalar @revs, 2, '2 revisions exist');
@@ -50,16 +69,54 @@ $im->done;
is(scalar @revs, 26, '26 revisions exist after mass import');
my ($mark, $msg) = $im->remove($mime);
like($mark, qr/\A:\d+\z/, 'got mark');
-is(ref($msg), 'Email::MIME', 'got old message deleted');
+like(ref($msg), qr/\bPublicInbox::(?:Eml|MIME)\b/, 'got old message deleted');
is(undef, $im->remove($mime), 'remove is idempotent');
# mismatch on identical Message-ID
$mime->header_set('Message-ID', '');
($mark, $msg) = $im->remove($mime);
-is($mark, -1, 'mark == -1 on mismatch');
+is($mark, 'MISMATCH', 'mark == MISMATCH on mismatch');
is($msg->header('Message-ID'), '', 'Message-ID matches');
isnt($msg->header('Subject'), $mime->header('Subject'), 'subject mismatch');
+$mime->header_set('Message-Id', '');
+is($im->add($mime, sub { undef }), undef, 'check callback fails');
+is($im->remove($mime), undef, 'message not added, so not removed');
+is(undef, $im->checkpoint, 'checkpoint works before ->done');
$im->done;
+is(undef, $im->checkpoint, 'checkpoint works after ->done');
+$im->checkpoint;
+
+my $nogit = PublicInbox::Git->new("$dir/non-existent/dir");
+eval {
+ my $nope = PublicInbox::Import->new($nogit, 'nope', 'no@example.com');
+ $nope->add($mime);
+};
+ok($@, 'Import->add fails on non-existent dir');
+
+my @cls = qw(PublicInbox::Eml);
+SKIP: {
+ require_mods('PublicInbox::MIME', 1);
+ push @cls, 'PublicInbox::MIME';
+};
+
+$main::badchars = "\n\0\r";
+my $from = '=?UTF-8?B?'. encode_base64("B\ra\nd\0\$main::badchars", ''). '?=';
+for my $cls (@cls) {
+ my $eml = $cls->new(<
+Message-ID: <$cls\@example.com>
+
+EOF
+ ok($im->add($eml), "added $cls message with nasty char in From");
+}
+$im->done;
+my $bref = $git->cat_file('HEAD');
+like($$bref, qr/^author Ba d \$main::badchars /sm,
+ 'latest commit accepted by spammer');
+$git->qx(qw(fsck --no-progress --strict));
+is($?, 0, 'fsck reported no errors');
+$main::badchars = undef;
+
done_testing();