* [PATCH 19/82] imap: support sequence number FETCH
2020-06-10 7:03 7% [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
@ 2020-06-10 7:04 5% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-06-10 7:04 UTC (permalink / raw)
To: meta
We'll return dummy messages for now when sequence numbers go
missing, in case clients can't handle missing messages.
---
lib/PublicInbox/IMAP.pm | 87 ++++++++++++++++++++++++++++++++++++-----
t/imapd.t | 18 +++++++++
2 files changed, 96 insertions(+), 9 deletions(-)
diff --git a/lib/PublicInbox/IMAP.pm b/lib/PublicInbox/IMAP.pm
index 673e1646216..2aa7ab346c1 100644
--- a/lib/PublicInbox/IMAP.pm
+++ b/lib/PublicInbox/IMAP.pm
@@ -348,11 +348,34 @@ sub fetch_body ($;$) {
join('', @hold);
}
+sub dummy_message ($$) {
+ my ($seqno, $ibx) = @_;
+ my $ret = <<EOF;
+From: nobody\@localhost\r
+To: nobody\@localhost\r
+Date: Thu, 01 Jan 1970 00:00:00 +0000\r
+Message-ID: <dummy-$seqno\@$ibx->{newsgroup}>\r
+Subject: dummy message #$seqno\r
+\r
+You're seeing this message because your IMAP client didn't use UIDs.\r
+The message which used to use this sequence number was likely spam\r
+and removed by the administrator.\r
+EOF
+ \$ret;
+}
+
sub uid_fetch_cb { # called by git->cat_async
my ($bref, $oid, $type, $size, $fetch_m_arg) = @_;
my ($self, undef, $ibx, undef, undef, $msgs, $want) = @$fetch_m_arg;
my $smsg = shift @$msgs or die 'BUG: no smsg';
- $smsg->{blob} eq $oid or die "BUG: $smsg->{blob} != $oid";
+ if (!defined($oid)) {
+ # it's possible to have TOCTOU if an admin runs
+ # public-inbox-(edit|purge), just move onto the next message
+ return unless defined $want->{-seqno};
+ $bref = dummy_message($smsg->{num}, $ibx);
+ } else {
+ $smsg->{blob} eq $oid or die "BUG: $smsg->{blob} != $oid";
+ }
$$bref =~ s/(?<!\r)\n/\r\n/sg; # make strict clients happy
# fixup old bug from import (pre-a0c07cba0e5d8b6a)
@@ -591,19 +614,19 @@ sub partial_emit ($$$) {
}
}
-sub cmd_uid_fetch ($$$;@) {
- my ($self, $tag, $range, @want) = @_;
+sub fetch_common ($$$$) {
+ my ($self, $tag, $range, $want) = @_;
my $ibx = $self->{ibx} or return "$tag BAD No mailbox selected\r\n";
- if ($want[0] =~ s/\A\(//s) {
- $want[-1] =~ s/\)\z//s or return "$tag BAD no rparen\r\n";
+ if ($want->[0] =~ s/\A\(//s) {
+ $want->[-1] =~ s/\)\z//s or return "$tag BAD no rparen\r\n";
}
my (%partial, %want);
- while (defined(my $att = shift @want)) {
+ while (defined(my $att = shift @$want)) {
$att = uc($att);
my $x = $FETCH_ATT{$att};
if ($x) {
%want = (%want, %$x);
- } elsif (!partial_prepare(\%partial, \@want, $att)) {
+ } elsif (!partial_prepare(\%partial, $want, $att)) {
return "$tag BAD param: $att\r\n";
}
}
@@ -629,8 +652,54 @@ sub cmd_uid_fetch ($$$;@) {
} else {
return "$tag BAD fetch range\r\n";
}
- long_response($self, \&uid_fetch_m, $tag, $ibx,
- \$beg, $end, $msgs, \%want);
+ [ $tag, $ibx, \$beg, $end, $msgs, \%want ];
+}
+
+sub cmd_uid_fetch ($$$;@) {
+ my ($self, $tag, $range, @want) = @_;
+ my $args = fetch_common($self, $tag, $range, \@want);
+ ref($args) eq 'ARRAY' ?
+ long_response($self, \&uid_fetch_m, @$args) :
+ $args; # error
+}
+
+sub seq_fetch_m { # long_response
+ my ($self, $tag, $ibx, $beg, $end, $msgs, $want) = @_;
+ if (!@$msgs) { # refill
+ @$msgs = @{$ibx->over->query_xover($$beg, $end)};
+ if (!@$msgs) {
+ $self->write(\"$tag OK Fetch done\r\n");
+ return;
+ }
+ $$beg = $msgs->[-1]->{num} + 1;
+ }
+ my $seq = $want->{-seqno}++;
+ my $cur_num = $msgs->[0]->{num};
+ if ($cur_num == $seq) { # as expected
+ my $git = $ibx->git;
+ $git->cat_async_begin; # TODO: actually make async
+ $git->cat_async($msgs->[0]->{blob}, \&uid_fetch_cb, \@_);
+ $git->cat_async_wait;
+ } elsif ($cur_num > $seq) {
+ # send dummy messages until $seq catches up to $cur_num
+ my $smsg = bless { num => $seq, ts => 0 }, 'PublicInbox::Smsg';
+ unshift @$msgs, $smsg;
+ my $bref = dummy_message($seq, $ibx);
+ uid_fetch_cb($bref, undef, undef, undef, \@_);
+ } else { # should not happen
+ die "BUG: cur_num=$cur_num < seq=$seq";
+ }
+ 1; # more messages on the way
+}
+
+sub cmd_fetch ($$$;@) {
+ my ($self, $tag, $range, @want) = @_;
+ my $args = fetch_common($self, $tag, $range, \@want);
+ ref($args) eq 'ARRAY' ? do {
+ my $want = $args->[-1];
+ $want->{-seqno} = ${$args->[2]}; # $$beg
+ long_response($self, \&seq_fetch_m, @$args)
+ } : $args; # error
}
sub uid_search_all { # long_response
diff --git a/t/imapd.t b/t/imapd.t
index fcbbdc09d31..fc90948e182 100644
--- a/t/imapd.t
+++ b/t/imapd.t
@@ -306,6 +306,24 @@ Content-Disposition: attachment; filename="embed2x\.eml"\r
EOF
}); # each_inbox
+# message sequence numbers :<
+is($mic->Uid(0), 0, 'disable UID on '.ref($mic));
+ok($mic->reconnect, 'reconnected');
+$ret = $mic->fetch_hash('1:*', 'RFC822') or BAIL_OUT "FETCH $@";
+is(scalar keys %$ret, 3, 'got all 3 messages');
+{
+ my $rdr = { 0 => \($ret->{1}->{RFC822}) };
+ my $env = { HOME => $ENV{HOME} };
+ my @cmd = qw(-learn rm --all);
+ run_script(\@cmd, $env, $rdr) or BAIL_OUT('-learn rm');
+}
+my $r2 = $mic->fetch_hash('1:*', 'RFC822') or BAIL_OUT "FETCH $@";
+is(scalar keys %$r2, 3, 'still got all 3 messages');
+like($r2->{1}->{RFC822}, qr/dummy message #1/, 'got dummy message 1');
+is($r2->{2}->{RFC822}, $ret->{2}->{RFC822}, 'message 2 unchanged');
+is($r2->{3}->{RFC822}, $ret->{3}->{RFC822}, 'message 3 unchanged');
+ok($mic->logout, 'logged out');
+
$td->kill;
$td->join;
is($?, 0, 'no error in exited process');
^ permalink raw reply related [relevance 5%]
* [PATCH 00/82] public-inbox-imapd: read-only IMAP server
@ 2020-06-10 7:03 7% Eric Wong
2020-06-10 7:04 5% ` [PATCH 19/82] imap: support sequence number FETCH Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-06-10 7:03 UTC (permalink / raw)
To: meta
So I finally wrote my first IMAP server! And I'm actually
fairly satisfied with how it's turning out to support a bunch
of other performance + scalability work I've wanted to do.
Some previous notes here:
https://public-inbox.org/meta/20200609113442.GA16856@dcvr/
I finally seem to have gotten it to play nicely with mutt header
caching, so it's fit for public consumption :)
imaps://news.public-inbox.org/INBOX.comp.mail.public-inbox.meta.0
You can use any username+password, and AUTH=ANONYMOUS also
works if your client does that.
It doesn't support UTF-7 (mailbox names) or advertise UTF-8
in CAPABILITIES, yet; I still have RFCs to read :P
And there's a bunch of new things which could use some
testing from non-mutt/mbsync/offlineimap users.
Maybe you'll find some client-side bugs like I did :P
v1 reindexing also gets a little bit of parallelism :)
Anyways, I'll probably be porting some of the scalability
and slow-storage work to older parts of the code before
fiddling with more IMAP extensions.
Eric Wong (82):
doc: add some IMAP standards
nntpd: restrict allowed newsgroup names
preliminary imap server implementation
inboxidle: new class to detect inbox changes
imap: support IDLE
msgmap: split ->max into its own method
imap: delay InboxIdle start, support refresh
imap: implement STATUS command
imap: use Text::ParseWords::parse_line to handle quoted words
imap: support LIST command
t/imapd: support FakeInotify and KQNotify
imap: support fetch for BODYSTRUCTURE and BODY
eml: each_part: single part $idx is 1
imap: allow fetch of partial of BODY[...] and headers
imap: always include `resp-text' in responses
imap: split out unit tests and benchmarks
imap: fix multi-message partial header fetches
imap: simplify partial fetch structure
imap: support sequence number FETCH
imap: do not include ".PEEK" in responses
imap: support the CLOSE command
imap: speed up HEADER.FIELDS[.NOT] range fetches
git: async: flatten the inflight array
git: do our own read buffering for cat-file
imap: use git-cat-file asynchronously
git: idle rbuf for async
imap: support LSUB command
imap: FETCH: support comma-delimited ranges
add imapd compression test
testcommon: tcp_(server|connect): BAIL_OUT on failure
*deflate: drop invalid comment about rbuf
imap: fix pipelining with async git
git: cat_async: provide requested OID + "missing" on missing blobs
git: move async_cat reference to PublicInbox::Git
git: async: automatic retry on alternates change
imapclient: wrapper for Mail::IMAPClient
xt: add imapd-validate and imapd-mbsync-oimap
imap: support out-of-bounds ranges
xt/perf-imap-list: time refresh_inboxlist
imap: case-insensitive mailbox name comparisons
imap: break giant inboxes into sub-inboxes of 50K messages
imap: start introducing iterative config reloading
imap: require ".$UID_MIN-$UID_END" suffix
imapd: ensure LIST is sorted alphabetically, for now
imap: omit $UID_END from mailbox name, use index
t/config.t: always compare against git bool behavior
xt/*: show some tunable parameters
imap: STATUS and LIST are case-insensitive, too
imap: EXAMINE/STATUS: return correct counts
imap: avoid uninitialized warnings on incomplete commands
imap: start parsing out queries for SQLite and Xapian
imap: SEARCH: clamp results to the 50K UID range
imap: allow UID range search on timestamps
over: get_art: use dbh->prepare_cached
search: index byte size of a message for IMAP search
search: index UID for IMAP search, too
imap: remove dummies from sequence number FETCH
imap: compile UID FETCH to opcodes
imap: UID FETCH: optimize for smsg-only case
imap: UID FETCH: optimize (UID FLAGS) harder
imap: IDLE: avoid extraneous wakeups, keep-alive
imap: 30 minute auto-logout timer
imap: split ->logged_in attribute into a separate class
searchidx: v1 (re)-index uses git asynchronously
index: account for CRLF conversion when storing bytes
imap: rely on smsg->{bytes} for RFC822.SIZE
imap: UID FETCH requires at least one data item
imap: LIST shows "INBOX" in all caps
imap: support 8000 octet lines
imap: reinstate some message sequence number support
imap: cleanup ->{uid_base} usage
imap: FETCH: more granular CRLF conversion
imap: further speed up HEADER.FIELDS FETCH requests
imap: FETCH: try to make fake MSNs sequentially
imap: STATUS/EXAMINE: rely on SQLite overview
imap: UID SEARCH: support multiple ranges
imap: wire up Xapian search, msn SEARCH and multiple ranges
imap: misc cleanups and notes
imapd: don't bother sorting LIST output
imap: drop non-UID SEARCH for now
over: uid_range: remove LIMIT
imap: FETCH: proper MSN => UID mapping for requests
Documentation/public-inbox-imapd.pod | 91 ++
Documentation/standards.perl | 10 +
MANIFEST | 18 +
lib/PublicInbox/Config.pm | 18 +
lib/PublicInbox/Daemon.pm | 24 +-
lib/PublicInbox/DummyInbox.pm | 22 +
lib/PublicInbox/Eml.pm | 9 +-
lib/PublicInbox/FakeInotify.pm | 59 ++
lib/PublicInbox/Git.pm | 163 +--
lib/PublicInbox/GitAsyncCat.pm | 51 +
lib/PublicInbox/IMAP.pm | 1397 ++++++++++++++++++++++++++
lib/PublicInbox/IMAPClient.pm | 119 +++
lib/PublicInbox/IMAPD.pm | 114 +++
lib/PublicInbox/IMAPdeflate.pm | 126 +++
lib/PublicInbox/Import.pm | 2 +-
lib/PublicInbox/In2Tie.pm | 17 +
lib/PublicInbox/Inbox.pm | 33 +-
lib/PublicInbox/InboxIdle.pm | 79 ++
lib/PublicInbox/KQNotify.pm | 66 ++
lib/PublicInbox/Lock.pm | 7 +
lib/PublicInbox/MsgIter.pm | 2 +-
lib/PublicInbox/Msgmap.pm | 20 +-
lib/PublicInbox/NNTPD.pm | 12 +-
lib/PublicInbox/NNTPdeflate.pm | 1 -
lib/PublicInbox/Over.pm | 50 +-
lib/PublicInbox/Search.pm | 32 +-
lib/PublicInbox/SearchIdx.pm | 89 +-
lib/PublicInbox/SearchIdxShard.pm | 11 +-
lib/PublicInbox/Smsg.pm | 8 +-
lib/PublicInbox/TestCommon.pm | 7 +-
lib/PublicInbox/V2Writable.pm | 10 +-
script/public-inbox-imapd | 14 +
t/config.t | 15 +-
t/eml.t | 2 +-
t/git.t | 40 +-
t/imap.t | 133 +++
t/imapd-tls.t | 204 ++++
t/imapd.t | 398 ++++++++
t/import.t | 5 +-
t/inbox_idle.t | 72 ++
t/nntpd.t | 5 +-
t/over.t | 3 +
t/search.t | 19 +
xt/cmp-msgstr.t | 1 -
xt/cmp-msgview.t | 1 -
xt/eml_check_limits.t | 6 +-
xt/git_async_cmp.t | 2 +-
xt/imapd-mbsync-oimap.t | 132 +++
xt/imapd-validate.t | 177 ++++
xt/mem-msgview.t | 1 +
xt/msgtime_cmp.t | 1 -
xt/perf-msgview.t | 1 -
52 files changed, 3718 insertions(+), 181 deletions(-)
create mode 100644 Documentation/public-inbox-imapd.pod
create mode 100644 lib/PublicInbox/DummyInbox.pm
create mode 100644 lib/PublicInbox/FakeInotify.pm
create mode 100644 lib/PublicInbox/GitAsyncCat.pm
create mode 100644 lib/PublicInbox/IMAP.pm
create mode 100644 lib/PublicInbox/IMAPClient.pm
create mode 100644 lib/PublicInbox/IMAPD.pm
create mode 100644 lib/PublicInbox/IMAPdeflate.pm
create mode 100644 lib/PublicInbox/In2Tie.pm
create mode 100644 lib/PublicInbox/InboxIdle.pm
create mode 100644 lib/PublicInbox/KQNotify.pm
create mode 100644 script/public-inbox-imapd
create mode 100644 t/imap.t
create mode 100644 t/imapd-tls.t
create mode 100644 t/imapd.t
create mode 100644 t/inbox_idle.t
create mode 100644 xt/imapd-mbsync-oimap.t
create mode 100644 xt/imapd-validate.t
^ permalink raw reply [relevance 7%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2020-06-10 7:03 7% [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
2020-06-10 7:04 5% ` [PATCH 19/82] imap: support sequence number FETCH Eric Wong
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).