X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiStore.pm;h=08add8f5a05496ab234f5cfad9737903de0c009a;hb=47d4e53734820b4e;hp=6c557d9976f078ac799c64579d4ed8e955e53001;hpb=44917fdd24a8bec1125caa21949476f97d8658d4;p=public-inbox.git diff --git a/lib/PublicInbox/LeiStore.pm b/lib/PublicInbox/LeiStore.pm index 6c557d99..08add8f5 100644 --- a/lib/PublicInbox/LeiStore.pm +++ b/lib/PublicInbox/LeiStore.pm @@ -20,15 +20,18 @@ use PublicInbox::Eml; use PublicInbox::Import; use PublicInbox::InboxWritable qw(eml_from_path); use PublicInbox::V2Writable; -use PublicInbox::ContentHash qw(content_hash git_sha); +use PublicInbox::ContentHash qw(content_hash); use PublicInbox::MID qw(mids); use PublicInbox::LeiSearch; use PublicInbox::MDA; use PublicInbox::Spawn qw(spawn); -use List::Util qw(max); +use PublicInbox::MdirReader; +use PublicInbox::LeiToMail; use File::Temp (); use POSIX (); use IO::Handle (); # ->autoflush +use Sys::Syslog qw(syslog openlog); +use Errno qw(EEXIST ENOENT); sub new { my (undef, $dir, $opt) = @_; @@ -46,19 +49,6 @@ sub rotate_bytes { $_[0]->{rotate_bytes} // ((1024 * 1024 * 1024) / $_[0]->packing_factor) } -sub git_pfx { "$_[0]->{priv_eidx}->{topdir}/local" }; - -sub git_epoch_max { - my ($self) = @_; - if (opendir(my $dh, $self->git_pfx)) { - max(map { - substr($_, 0, -4) + 0; # drop ".git" suffix - } grep(/\A[0-9]+\.git\z/, readdir($dh))) // 0; - } else { - $!{ENOENT} ? 0 : die("opendir ${\$self->git_pfx}: $!\n"); - } -} - sub git_ident ($) { my ($git) = @_; my $rdr = {}; @@ -87,22 +77,16 @@ sub importer { $im->done; undef $im; $self->checkpoint; - $max = $self->git_epoch_max + 1; + $max = $self->{priv_eidx}->{mg}->git_epochs + 1; } my (undef, $tl) = eidx_init($self); # acquire lock - my $pfx = $self->git_pfx; - $max //= $self->git_epoch_max; + $max //= $self->{priv_eidx}->{mg}->git_epochs; while (1) { - my $latest = "$pfx/$max.git"; - my $old = -e $latest; - PublicInbox::Import::init_bare($latest); + my $latest = $self->{priv_eidx}->{mg}->add_epoch($max); my $git = PublicInbox::Git->new($latest); - if (!$old) { - $git->qx(qw(config core.sharedRepository 0600)); - $self->done; # unlock - # re-acquire lock, update alternates for new epoch - (undef, $tl) = eidx_init($self); - } + $self->done; # unlock + # re-acquire lock, update alternates for new epoch + (undef, $tl) = eidx_init($self); my $packed_bytes = $git->packed_bytes; my $unpacked_bytes = $packed_bytes / $self->packing_factor; if ($unpacked_bytes >= $self->rotate_bytes) { @@ -165,12 +149,88 @@ sub _docids_for ($$) { sort { $a <=> $b } values %docids; } +# n.b. similar to LeiExportKw->export_kw_md, but this is for a single eml +sub export1_kw_md ($$$$$) { + my ($self, $mdir, $bn, $oidbin, $vmdish) = @_; # vmd/vmd_mod + my $orig = $bn; + my (@try, $unkn, $kw); + if ($bn =~ s/:2,([a-zA-Z]*)\z//) { + ($kw, $unkn) = PublicInbox::MdirReader::flags2kw($1); + if (my $set = $vmdish->{kw}) { + $kw = $set; + } elsif (my $add = $vmdish->{'+kw'}) { + @$kw{@$add} = (); + } elsif (my $del = $vmdish->{-kw}) { + delete @$kw{@$del}; + } # else no changes... + @try = qw(cur new); + } else { # no keywords, yet, could be in new/ + @try = qw(new cur); + $unkn = []; + if (my $set = $vmdish->{kw}) { + $kw = $set; + } elsif (my $add = $vmdish->{'+kw'}) { + @$kw{@$add} = (); # auto-vivify + } else { # ignore $vmdish->{-kw} + $kw = []; + } + } + $kw = [ keys %$kw ] if ref($kw) eq 'HASH'; + $bn .= ':2,'. PublicInbox::LeiToMail::kw2suffix($kw, @$unkn); + return if $orig eq $bn; # no change + + # we use link(2) + unlink(2) since rename(2) may + # inadvertently clobber if the "uniquefilename" part wasn't + # actually unique. + my $dst = "$mdir/cur/$bn"; + for my $d (@try) { + my $src = "$mdir/$d/$orig"; + if (link($src, $dst)) { + if (!unlink($src) and $! != ENOENT) { + syslog('warning', "unlink($src): $!"); + } + # TODO: verify oidbin? + $self->{lms}->mv_src("maildir:$mdir", + $oidbin, \$orig, $bn); + return; + } elsif ($! == EEXIST) { # lost race with "lei export-kw"? + return; + } elsif ($! != ENOENT) { + syslog('warning', "link($src -> $dst): $!"); + } + } + for (@try) { return if -e "$mdir/$_/$orig" }; + $self->{lms}->clear_src("maildir:$mdir", \$orig); +} + +sub sto_export_kw ($$$) { + my ($self, $docid, $vmdish) = @_; # vmdish (vmd or vmd_mod) + my ($eidx, $tl) = eidx_init($self); + my $lms = _lms_rw($self) // return; + my $xr3 = $eidx->{oidx}->get_xref3($docid, 1); + for my $row (@$xr3) { + my (undef, undef, $oidbin) = @$row; + my $locs = $lms->locations_for($oidbin) // next; + while (my ($loc, $ids) = each %$locs) { + if ($loc =~ s!\Amaildir:!!i) { + for my $id (@$ids) { + export1_kw_md($self, $loc, $id, + $oidbin, $vmdish); + } + } + # TODO: IMAP + } + } +} + +# vmd = { kw => [ qw(seen ...) ], L => [ qw(inbox ...) ] } sub set_eml_vmd { my ($self, $eml, $vmd, $docids) = @_; my ($eidx, $tl) = eidx_init($self); $docids //= [ _docids_for($self, $eml) ]; for my $docid (@$docids) { $eidx->idx_shard($docid)->ipc_do('set_vmd', $docid, $vmd); + sto_export_kw($self, $docid, $vmd); } $docids; } @@ -195,7 +255,7 @@ sub remove_eml_vmd { # remove just the VMD \@docids; } -sub _lms_rw ($) { +sub _lms_rw ($) { # it is important to have eidx processes open before lms my ($self) = @_; my ($eidx, $tl) = eidx_init($self); $self->{lms} //= do { @@ -207,27 +267,6 @@ sub _lms_rw ($) { }; } -sub lms_clear_src { - my ($self, $folder, $id) = @_; - _lms_rw($self)->clear_src($folder, $id); -} - -sub lms_mv_src { - my ($self, $folder, $oidbin, $id, $newbn) = @_; - _lms_rw($self)->mv_src($folder, $oidbin, $id, $newbn); -} - -sub lms_forget_folders { - my ($self, @folders) = @_; - my $lms = _lms_rw($self); - for my $f (@folders) { $lms->forget_folder($f) } -} - -sub lms_rename_folder { - my ($self, $old, $new) = @_; - _lms_rw($self)->rename_folder($old, $new); -} - sub set_sync_info { my ($self, $oidhex, $folder, $id) = @_; _lms_rw($self)->set_src(pack('H*', $oidhex), $folder, $id); @@ -284,6 +323,12 @@ EOF $docid; } +sub _add_vmd ($$$$) { + my ($self, $idx, $docid, $vmd) = @_; + $idx->ipc_do('add_vmd', $docid, $vmd); + sto_export_kw($self, $docid, $vmd); +} + sub add_eml { my ($self, $eml, $vmd, $xoids) = @_; my $im = $self->{-fake_im} // $self->importer; # may create new epoch @@ -310,7 +355,7 @@ sub add_eml { @$vivify_xvmd = sort { $a <=> $b } keys(%docids); } } - if (@$vivify_xvmd) { + if (@$vivify_xvmd) { # docids list $xoids //= {}; $xoids->{$smsg->{blob}} = 1; for my $docid (@$vivify_xvmd) { @@ -327,7 +372,7 @@ sub add_eml { for my $oid (keys %$xoids) { $oidx->add_xref3($docid, -1, $oid, '.'); } - $idx->ipc_do('add_vmd', $docid, $vmd) if $vmd; + _add_vmd($self, $idx, $docid, $vmd) if $vmd; } $vivify_xvmd; } elsif (my @docids = _docids_for($self, $eml)) { @@ -337,7 +382,7 @@ sub add_eml { $oidx->add_xref3($docid, -1, $smsg->{blob}, '.'); # add_eidx_info for List-Id $idx->ipc_do('add_eidx_info', $docid, '.', $eml); - $idx->ipc_do('add_vmd', $docid, $vmd) if $vmd; + _add_vmd($self, $idx, $docid, $vmd) if $vmd; } \@docids; } else { # totally new message @@ -347,7 +392,7 @@ sub add_eml { $oidx->add_xref3($smsg->{num}, -1, $smsg->{blob}, '.'); my $idx = $eidx->idx_shard($smsg->{num}); $idx->index_eml($eml, $smsg); - $idx->ipc_do('add_vmd', $smsg->{num}, $vmd) if $vmd; + _add_vmd($self, $idx, $smsg->{num}, $vmd) if $vmd; $smsg; } } @@ -365,6 +410,7 @@ sub index_eml_only { set_eml($self, $eml, $vmd, $xoids); } +# store {kw} / {L} info for a message which is only in an external sub _external_only ($$$) { my ($self, $xoids, $eml) = @_; my $eidx = $self->{priv_eidx}; @@ -398,6 +444,7 @@ sub update_xvmd { next if $seen{$docid}++; my $idx = $eidx->idx_shard($docid); $idx->ipc_do('update_vmd', $docid, $vmd_mod); + sto_export_kw($self, $docid, $vmd_mod); } return unless scalar(keys(%$xoids)); @@ -410,12 +457,14 @@ sub update_xvmd { } my $idx = $eidx->idx_shard($docid); $idx->ipc_do('update_vmd', $docid, $vmd_mod); + sto_export_kw($self, $docid, $vmd_mod); } return; } # totally unseen my ($smsg, $idx) = _external_only($self, $xoids, $eml); $idx->ipc_do('update_vmd', $smsg->{num}, $vmd_mod); + sto_export_kw($self, $smsg->{num}, $vmd_mod); } # set or update keywords for external message, called via ipc_do @@ -433,6 +482,7 @@ sub set_xvmd { next if $seen{$docid}++; my $idx = $eidx->idx_shard($docid); $idx->ipc_do('set_vmd', $docid, $vmd); + sto_export_kw($self, $docid, $vmd); } return unless scalar(keys(%$xoids)); @@ -443,6 +493,7 @@ sub set_xvmd { # totally unseen: my ($smsg, $idx) = _external_only($self, $xoids, $eml); $idx->ipc_do('add_vmd', $smsg->{num}, $vmd); + sto_export_kw($self, $smsg->{num}, $vmd); } sub checkpoint { @@ -497,6 +548,7 @@ sub ipc_atfork_child { if (my $to_close = delete($self->{to_close})) { close($_) for @$to_close; } + openlog('lei/store', 'pid,nowait,nofatal,ndelay', 'user'); $self->SUPER::ipc_atfork_child; } @@ -530,11 +582,4 @@ sub write_prepare { $lei->{sto} = $self; } -# TODO: support SHA-256 -sub git_blob_id { # called via LEI->git_blob_id - my ($self, $eml) = @_; - $eml->header_set($_) for @PublicInbox::Import::UNWANTED_HEADERS; - git_sha(1, $eml)->hexdigest; -} - 1;