lei prune-mail-sync: new command to prune invalid sync data

This will be invoked automatically by "lei import" eventually,
but it may make sense to expose as a separate command.

diff --git a/MANIFEST b/MANIFEST
index 7bdbf25200cdc0b894aeac35e7ab150d5e77d1ff..3d4c6cbd91668b9da3916d220484214402ff4a67 100644 (file)
--- a/MANIFEST
+++ b/MANIFEST
@@ -222,6 +222,7 @@ lib/PublicInbox/LeiMirror.pm
 lib/PublicInbox/LeiOverview.pm
 lib/PublicInbox/LeiP2q.pm
 lib/PublicInbox/LeiPmdir.pm
+lib/PublicInbox/LeiPruneMailSync.pm
 lib/PublicInbox/LeiQuery.pm
 lib/PublicInbox/LeiRediff.pm
 lib/PublicInbox/LeiRemote.pm

diff --git a/lib/PublicInbox/LEI.pm b/lib/PublicInbox/LEI.pm
index 77fc5b8fa278983dea3a332fc3277894ac5ff7d7..265b7047fdf63541fb0bd263071efc445e674c26 100644 (file)
--- a/lib/PublicInbox/LEI.pm
+++ b/lib/PublicInbox/LEI.pm
@@ -245,6 +245,8 @@ our %CMD = ( # sorted in order of importance/use:
        qw(no-torsocks torsocks=s), PublicInbox::LeiQuery::curl_opt(), @c_opt ],
 'forget-mail-sync' => [ 'LOCATION...',
        'forget sync information for a mail folder', @c_opt ],
+'prune-mail-sync' => [ 'LOCATION...|--all',
+       'prune dangling sync data for a mail folder', 'all:s', @c_opt ],
 'export-kw' => [ 'LOCATION...|--all',
        'one-time export of keywords of sync sources',
        qw(all:s mode=s), @c_opt ],

diff --git a/lib/PublicInbox/LeiPruneMailSync.pm b/lib/PublicInbox/LeiPruneMailSync.pm
new file mode 100644 (file)
index 0000000..79f3325
--- /dev/null
+++ b/lib/PublicInbox/LeiPruneMailSync.pm
@@ -0,0 +1,97 @@
+# Copyright (C) 2021 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+
+# "lei prune-mail-sync" drops dangling sync information
+package PublicInbox::LeiPruneMailSync;
+use strict;
+use v5.10.1;
+use parent qw(PublicInbox::IPC PublicInbox::LeiInput);
+use PublicInbox::LeiExportKw;
+use PublicInbox::InboxWritable qw(eml_from_path);
+
+sub eml_match ($$) {
+       my ($eml, $oidbin) = @_;
+       $oidbin eq git_sha(length($oidbin) == 20 ? 1 : 256, $eml)->digest;
+}
+
+sub prune_mdir { # lms->each_src callback
+       my ($oidbin, $id, $self, $mdir) = @_;
+       my @try = $$id =~ /:2,[a-zA-Z]*\z/ ? qw(cur new) : qw(new cur);
+       for my $d (@try) {
+               my $src = "$mdir/$d/$$id";
+               if ($self->{verify}) {
+                       my $eml = eml_from_path($src) or next;
+                       return if eml_match($eml, $oidbin);
+               } elsif (-f $src) {
+                       return;
+               }
+       }
+       # both tries failed
+       $self->{lei}->qerr("# maildir:$mdir $$id gone");
+       $self->{lei}->{sto}->ipc_do('lms_clear_src', "maildir:$mdir", $id);
+}
+
+sub prune_imap { # lms->each_src callback
+       my ($oidbin, $uid, $self, $uids, $url) = @_;
+       return if exists $uids->{$uid};
+       $self->{lei}->qerr("# $url $uid gone");
+       $self->{lei}->{sto}->ipc_do('lms_clear_src', $url, $uid);
+}
+
+sub input_path_url { # overrides PublicInbox::LeiInput::input_path_url
+       my ($self, $input, @args) = @_;
+       my $lms = $self->{-lms_ro} //= $self->{lse}->lms;
+       if ($input =~ /\Amaildir:(.+)/i) {
+               my $mdir = $1;
+               $lms->each_src($input, \&prune_mdir, $self, $mdir);
+       } elsif ($input =~ m!\Aimaps?://!i) {
+               my $uri = PublicInbox::URIimap->new($input);
+               my $mic = $self->{lei}->{net}->mic_for_folder($uri);
+               my $uids = $mic->search('UID 1:*');
+               $uids = +{ map { $_ => undef } @$uids };
+               $lms->each_src($$uri, \&prune_imap, $self, $uids, $$uri);
+       } else { die "BUG: $input not supported" }
+       my $wait = $self->{lei}->{sto}->ipc_do('done');
+}
+
+sub lei_prune_mail_sync {
+       my ($lei, @folders) = @_;
+       my $sto = $lei->_lei_store or return $lei->fail(<<EOM);
+lei/store uninitialized, see lei-import(1)
+EOM
+       my $lse = $sto->search;
+       my $lms = $lse->lms or return $lei->fail(<<EOM);
+lei mail_sync uninitialized, see lei-import(1)
+EOM
+       if (defined(my $all = $lei->{opt}->{all})) {
+               $lms->group2folders($lei, $all, \@folders) or return;
+       } else {
+               my $err = $lms->arg2folder($lei, \@folders);
+               $lei->qerr(@{$err->{qerr}}) if $err->{qerr};
+               return $lei->fail($err->{fail}) if $err->{fail};
+       }
+       delete $lms->{dbh};
+       $sto->write_prepare($lei);
+       my $self = bless { lse => $lse }, __PACKAGE__;
+       $lei->{opt}->{'mail-sync'} = 1; # for prepare_inputs
+       $self->prepare_inputs($lei, \@folders) or return;
+       my $j = $lei->{opt}->{jobs} || scalar(@{$self->{inputs}}) || 1;
+       undef $lms; # for fork
+       my $ops = {};
+       $sto->write_prepare($lei);
+       $lei->{auth}->op_merge($ops, $self) if $lei->{auth};
+       $self->{-wq_nr_workers} = $j // 1; # locked
+       (my $op_c, $ops) = $lei->workers_start($self, $j, $ops);
+       $lei->{wq1} = $self;
+       $lei->{-err_type} = 'non-fatal';
+       net_merge_all_done($self) unless $lei->{auth};
+       $lei->wait_wq_events($op_c, $ops); # net_merge_all_done if !{auth}
+}
+
+no warnings 'once';
+*_complete_prune_mail_sync = \&PublicInbox::LeiExportKw::_complete_export_kw;
+*ipc_atfork_child = \&PublicInbox::LeiInput::input_only_atfork_child;
+*net_merge_all = \&PublicInbox::LeiAuth::net_merge_all;
+*net_merge_all_done = \&PublicInbox::LeiInput::input_only_net_merge_all_done;
+
+1;

diff --git a/lib/PublicInbox/NetReader.pm b/lib/PublicInbox/NetReader.pm
index 058f431398a6a8bcf5579e668db30ef6c1660bd5..2795a9d4d85e4bbc21c7669a13825db1d6870ba8 100644 (file)
--- a/lib/PublicInbox/NetReader.pm
+++ b/lib/PublicInbox/NetReader.pm
@@ -747,4 +747,23 @@ sub nntp_each {
 
 sub new { bless {}, shift };
 
+# updates $uri with UIDVALIDITY
+sub mic_for_folder {
+       my ($self, $uri) = @_;
+       my $mic = $self->mic_get($uri) or die "E: not connected: $@";
+       my $m = $self->isa('PublicInbox::NetWriter') ? 'select' : 'examine';
+       $mic->$m($uri->mailbox) or return;
+       my $uidval;
+       for ($mic->Results) {
+               /^\* OK \[UIDVALIDITY ([0-9]+)\].*/ or next;
+               $uidval = $1;
+               last;
+       }
+       $uidval //= $mic->uidvalidity($uri->mailbox) or
+               die "E: failed to get uidvalidity from <$uri>: $@";
+       $uri->uidvalidity($uidval);
+       $mic;
+}
+
+
 1;

diff --git a/lib/PublicInbox/NetWriter.pm b/lib/PublicInbox/NetWriter.pm
index 8ec7f85c876b568cf6102cc9dbdf705203bb2d03..82288e6bc6391106c0d2123ee7bc1e03c24af489 100644 (file)
--- a/lib/PublicInbox/NetWriter.pm
+++ b/lib/PublicInbox/NetWriter.pm
@@ -26,26 +26,9 @@ sub imap_append {
                die "APPEND $folder: $@";
 }
 
-# updates $uri with UIDVALIDITY
-sub mic_for_folder {
-       my ($self, $uri) = @_;
-       my $mic = $self->mic_get($uri) or die "E: not connected: $@";
-       $mic->select($uri->mailbox) or return;
-       my $uidval;
-       for ($mic->Results) {
-               /^\* OK \[UIDVALIDITY ([0-9]+)\].*/ or next;
-               $uidval = $1;
-               last;
-       }
-       $uidval //= $mic->uidvalidity($uri->mailbox) or
-               die "E: failed to get uidvalidity from <$uri>: $@";
-       $uri->uidvalidity($uidval);
-       $mic;
-}
-
 sub imap_delete_all {
        my ($self, $uri) = @_;
-       my $mic = mic_for_folder($self, $uri) or return;
+       my $mic = $self->mic_for_folder($uri) or return;
        my $sec = $self->can('uri_section')->($uri);
        local $0 = $uri->mailbox." $sec";
        if ($mic->delete_message('1:*')) {
@@ -55,7 +38,7 @@ sub imap_delete_all {
 
 sub imap_delete_1 {
        my ($self, $uri, $uid, $delete_mic) = @_;
-       $$delete_mic //= mic_for_folder($self, $uri) or return;
+       $$delete_mic //= $self->mic_for_folder($uri) or return;
        $$delete_mic->delete_message($uid);
 }