* [PATCH 20/36] lei_store: handle messages without Message-ID at all
2020-12-31 13:51 6% [PATCH 00/36] another round of lei stuff Eric Wong
@ 2020-12-31 13:51 7% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-12-31 13:51 UTC (permalink / raw)
To: meta
For personal mail, unsent drafts messages are a common source of
messages without Message-IDs.
---
lib/PublicInbox/LeiStore.pm | 20 ++++++++++++++++----
lib/PublicInbox/OverIdx.pm | 2 ++
lib/PublicInbox/Smsg.pm | 6 ++----
t/lei_store.t | 24 ++++++++++++++++++++++++
4 files changed, 44 insertions(+), 8 deletions(-)
diff --git a/lib/PublicInbox/LeiStore.pm b/lib/PublicInbox/LeiStore.pm
index 43fddf6d..c8b9d75e 100644
--- a/lib/PublicInbox/LeiStore.pm
+++ b/lib/PublicInbox/LeiStore.pm
@@ -15,8 +15,8 @@ use PublicInbox::ExtSearchIdx;
use PublicInbox::Import;
use PublicInbox::InboxWritable;
use PublicInbox::V2Writable;
-use PublicInbox::ContentHash qw(content_hash);
-use PublicInbox::MID qw(mids);
+use PublicInbox::ContentHash qw(content_hash content_digest);
+use PublicInbox::MID qw(mids mids_in);
use PublicInbox::LeiSearch;
use List::Util qw(max);
@@ -107,14 +107,26 @@ sub eidx_init {
$eidx;
}
+# when a message has no Message-IDs at all, this is needed for
+# unsent Draft messages, at least
+sub _fake_mid_for ($$) {
+ my ($eml, $dig) = @_;
+ my $mids = mids_in($eml, qw(X-Alt-Message-ID Resent-Message-ID));
+ $eml->{-lei_fake_mid} =
+ $mids->[0] // PublicInbox::Import::digest2mid($dig, $eml);
+}
+
sub _docids_for ($$) {
my ($self, $eml) = @_;
my %docids;
- my $chash = content_hash($eml);
+ my $dig = content_digest($eml);
+ my $chash = $dig->clone->digest;
my $eidx = eidx_init($self);
my $oidx = $eidx->{oidx};
my $im = $self->{im};
- for my $mid (@{mids($eml)}) {
+ my $mids = mids($eml);
+ $mids->[0] //= _fake_mid_for($eml, $dig);
+ for my $mid (@$mids) {
my ($id, $prev);
while (my $cur = $oidx->next_by_mid($mid, \$id, \$prev)) {
my $oid = $cur->{blob};
diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index bc2e3ef4..dad3966d 100644
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -284,6 +284,8 @@ sub add_overview {
$smsg->{lines} = $eml->body_raw =~ tr!\n!\n!;
my $mids = mids_for_index($eml);
my $refs = parse_references($smsg, $eml, $mids);
+ $mids->[0] //= $smsg->{mid} //= $eml->{-lei_fake_mid};
+ $smsg->{mid} //= '';
my $subj = $smsg->{subject};
my $xpath;
if ($subj ne '') {
diff --git a/lib/PublicInbox/Smsg.pm b/lib/PublicInbox/Smsg.pm
index 14086538..9db10c64 100644
--- a/lib/PublicInbox/Smsg.pm
+++ b/lib/PublicInbox/Smsg.pm
@@ -69,7 +69,7 @@ sub psgi_cull ($) {
$self;
}
-# for Import and v1 non-SQLite WWW code paths
+# used for v2, Import and v1 non-SQLite WWW code paths
sub populate {
my ($self, $hdr, $sync) = @_;
for my $f (qw(From To Cc Subject)) {
@@ -100,9 +100,7 @@ sub populate {
$self->{-ts} = [ my @ts = msg_timestamp($hdr, $sync->{cotime}) ];
$self->{ds} //= $ds[0]; # no zone
$self->{ts} //= $ts[0];
-
- # for v1 users w/o SQLite
- $self->{mid} //= eval { mids($hdr)->[0] } // '';
+ $self->{mid} //= mids($hdr)->[0];
}
# no strftime, that is locale-dependent and not for RFC822
diff --git a/t/lei_store.t b/t/lei_store.t
index bc0d66c2..beb5a8c4 100644
--- a/t/lei_store.t
+++ b/t/lei_store.t
@@ -100,6 +100,30 @@ for my $parallel (0, 1) {
SKIP: {
require_mods(qw(Storable), 1);
ok($lst->can('ipc_do'), 'ipc_do works if we have Storable');
+ $eml->header_set('Message-ID', '<ipc-test@example>');
+ my $pid = $lst->ipc_worker_spawn('lei-store');
+ ok($pid > 0, 'got a worker');
+ my $smsg = $lst->ipc_do('set_eml', $eml, qw(seen));
+ is(ref($smsg), 'PublicInbox::Smsg', 'set_eml works over ipc');
+ my $ids = $lst->ipc_do('set_eml', $eml, qw(seen));
+ is_deeply($ids, [ $smsg->{num} ], 'docid returned');
+
+ $eml->header_set('Message-ID');
+ my $no_mid = $lst->ipc_do('set_eml', $eml, qw(seen));
+ my $wait = $lst->ipc_do('done');
+ my @kw = $lst->search->msg_keywords($no_mid->{num});
+ is_deeply(\@kw, [qw(seen)], 'ipc set changed kw');
+
+ is(ref($smsg), 'PublicInbox::Smsg', 'no mid works ipc');
+ $ids = $lst->ipc_do('set_eml', $eml, qw(seen));
+ is_deeply($ids, [ $no_mid->{num} ], 'docid returned w/o mid w/ ipc');
+ $lst->ipc_do('done');
+ $lst->ipc_worker_stop;
+ $ids = $lst->ipc_do('set_eml', $eml, qw(seen answered));
+ is_deeply($ids, [ $no_mid->{num} ], 'docid returned w/o mid w/o ipc');
+ $wait = $lst->ipc_do('done');
+ @kw = $lst->search->msg_keywords($no_mid->{num});
+ is_deeply(\@kw, [qw(answered seen)], 'set changed kw w/o ipc');
}
done_testing;
^ permalink raw reply related [relevance 7%]
* [PATCH 00/36] another round of lei stuff
@ 2020-12-31 13:51 6% Eric Wong
2020-12-31 13:51 7% ` [PATCH 20/36] lei_store: handle messages without Message-ID at all Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-12-31 13:51 UTC (permalink / raw)
To: meta
This is against lei branch @ commit
0c8106d44f317175e122744b43407bf067183175 in
https://public-inbox.org/public-inbox.git
Infrastructure stuff for reading + writing local Maildirs and a
bunch of mbox formats are done (including gz/bz2/xz support)
and it's usage should be familiar to mairix(1) users.
Infrastructure for deduplication + augmenting search results
in place and tested.
Going to skip MH and MMDF for now; but IMAP/JMAP might happen
sooner but deduplication needs low-latency.
"extinbox" renamed "external"
Basic infrastructure like PublicInbox::IPC and SharedKV
should've been done and in use ages ago... I look forward to
using them, at least.
Some DS safety fixes since lei will use it in stranger ways
than current.
Bad enough we have messages with duplicate Message-IDs, lei will
need to deal with Unsent/Drafts messages w/o Message-IDs at all!
Eric Wong (36):
import: respect init.defaultBranch
lei_store: use per-machine refname as git HEAD
revert "lei_store: use per-machine refname as git HEAD"
lei_to_mail: initial implementation for writing mbox formats
sharedkv: fork()-friendly key-value store
sharedkv: split out index_values
lei_to_mail: start atomic and compressed mbox writing
mboxreader: new class for reading various mbox formats
lei_to_mail: start --augment, dedupe, bz2 and xz
lei: implement various deduplication strategies
lei_to_mail: lazy-require LeiDedupe
lei_to_mail: support for non-seekable outputs
lei_to_mail: support Maildir, fix+test --augment
ipc: generic IPC dispatch based on Storable
ipc: support Sereal
lei_store: add ->set_eml, ->add_eml can return smsg
lei: rename "extinbox" => "external"
mid: use defined-or with `push' for uniqueness check
mid: hoist out mids_in sub
lei_store: handle messages without Message-ID at all
ipc: use shutdown(2), base atfork* callback
lei_to_mail: unlink mboxes if not augmenting
lei: add --mfolder as an option
spawn: move run_die here from PublicInbox::Import
init: remove embedded UnlinkMe package
t/run.perl: avoid uninitialized var on incomplete test
gcf2client: reap process on DESTROY
lei_to_mail: open FIFOs O_WRONLY so we block
searchidxshard: call DS->Reset at worker start
t/ipc.t: test for references via `die'
use PublicInbox::DS for dwaitpid
syscall: SFD_NONBLOCK can be a constant, again
lei: avoid Spawn package when starting daemon
avoid calling waitpid from children in DESTROY
ds: clobber $in_loop first at reset
on_destroy: support PID owner guard
MANIFEST | 12 +-
lib/PublicInbox/DS.pm | 42 +-
lib/PublicInbox/DSKQXS.pm | 4 +-
lib/PublicInbox/Daemon.pm | 4 +-
lib/PublicInbox/Gcf2Client.pm | 18 +-
lib/PublicInbox/Git.pm | 7 +-
lib/PublicInbox/IPC.pm | 165 ++++++++
lib/PublicInbox/Import.pm | 36 +-
lib/PublicInbox/LEI.pm | 44 +--
lib/PublicInbox/LeiDedupe.pm | 100 +++++
.../{LeiExtinbox.pm => LeiExternal.pm} | 18 +-
lib/PublicInbox/LeiStore.pm | 32 +-
lib/PublicInbox/LeiToMail.pm | 361 ++++++++++++++++++
lib/PublicInbox/LeiXSearch.pm | 2 +-
lib/PublicInbox/Lock.pm | 17 +-
lib/PublicInbox/MID.pm | 15 +-
lib/PublicInbox/MboxReader.pm | 127 ++++++
lib/PublicInbox/OnDestroy.pm | 5 +
lib/PublicInbox/OverIdx.pm | 2 +
lib/PublicInbox/ProcessPipe.pm | 34 +-
lib/PublicInbox/Qspawn.pm | 43 +--
lib/PublicInbox/SearchIdxShard.pm | 1 +
lib/PublicInbox/SharedKV.pm | 148 +++++++
lib/PublicInbox/Sigfd.pm | 4 +-
lib/PublicInbox/Smsg.pm | 6 +-
lib/PublicInbox/Spawn.pm | 9 +-
lib/PublicInbox/Syscall.pm | 4 +-
lib/PublicInbox/TestCommon.pm | 25 +-
lib/PublicInbox/V2Writable.pm | 10 +-
script/lei | 17 +-
script/public-inbox-init | 32 +-
script/public-inbox-watch | 4 +-
t/convert-compact.t | 4 +-
t/index-git-times.t | 3 +-
t/ipc.t | 80 ++++
t/lei.t | 22 +-
t/lei_dedupe.t | 59 +++
t/lei_store.t | 47 ++-
t/lei_to_mail.t | 246 ++++++++++++
t/lei_xsearch.t | 2 +-
t/mbox_reader.t | 75 ++++
t/on_destroy.t | 9 +
t/plack.t | 4 +-
t/run.perl | 3 +-
t/shared_kv.t | 58 +++
t/sigfd.t | 6 +-
46 files changed, 1755 insertions(+), 211 deletions(-)
create mode 100644 lib/PublicInbox/IPC.pm
create mode 100644 lib/PublicInbox/LeiDedupe.pm
rename lib/PublicInbox/{LeiExtinbox.pm => LeiExternal.pm} (75%)
create mode 100644 lib/PublicInbox/LeiToMail.pm
create mode 100644 lib/PublicInbox/MboxReader.pm
create mode 100644 lib/PublicInbox/SharedKV.pm
create mode 100644 t/ipc.t
create mode 100644 t/lei_dedupe.t
create mode 100644 t/lei_to_mail.t
create mode 100644 t/mbox_reader.t
create mode 100644 t/shared_kv.t
^ permalink raw reply [relevance 6%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2020-12-31 13:51 6% [PATCH 00/36] another round of lei stuff Eric Wong
2020-12-31 13:51 7% ` [PATCH 20/36] lei_store: handle messages without Message-ID at all 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).