X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiToMail.pm;h=0fa0bd9a6a2ef124724b085be5677b5395738ecb;hb=91ae332610370d2a5da2cfb0bd1dff09463e5438;hp=587804bbc1aa52c167efb6d570a958c7b99092f3;hpb=42fc590f8cabd23455949d002e2ddf28bbec6d1e;p=public-inbox.git diff --git a/lib/PublicInbox/LeiToMail.pm b/lib/PublicInbox/LeiToMail.pm index 587804bb..0fa0bd9a 100644 --- a/lib/PublicInbox/LeiToMail.pm +++ b/lib/PublicInbox/LeiToMail.pm @@ -7,28 +7,19 @@ use strict; use v5.10.1; use parent qw(PublicInbox::IPC); use PublicInbox::Eml; -use PublicInbox::Lock; use PublicInbox::ProcessPipe; -use PublicInbox::Spawn qw(which spawn popen_rd); -use PublicInbox::LeiDedupe; -use PublicInbox::Git; -use PublicInbox::GitAsyncCat; +use PublicInbox::Spawn qw(spawn); use PublicInbox::PktOp qw(pkt_do); use Symbol qw(gensym); use IO::Handle; # ->autoflush use Fcntl qw(SEEK_SET SEEK_END O_CREAT O_EXCL O_WRONLY); -use Errno qw(EEXIST ESPIPE ENOENT EPIPE); -use Digest::SHA qw(sha256_hex); - -# struggles with short-lived repos, Gcf2Client makes little sense with lei; -# but we may use in-process libgit2 in the future. -$PublicInbox::GitAsyncCat::GCF2C = 0; my %kw2char = ( # Maildir characters draft => 'D', flagged => 'F', + forwarded => 'P', # passed answered => 'R', - seen => 'S' + seen => 'S', ); my %kw2status = ( @@ -42,19 +33,21 @@ sub _mbox_hdr_buf ($$$) { my ($eml, $type, $smsg) = @_; $eml->header_set($_) for (qw(Lines Bytes Content-Length)); - # Messages are always 'O' (non-\Recent in IMAP), it saves - # MUAs the trouble of rewriting the mbox if no other - # changes are made - my %hdr = (Status => [ 'O' ]); # set Status, X-Status + my %hdr = (Status => []); # set Status, X-Status for my $k (@{$smsg->{kw} // []}) { if (my $ent = $kw2status{$k}) { push @{$hdr{$ent->[0]}}, $ent->[1]; } else { # X-Label? - warn "TODO: keyword `$k' not supported for mbox\n"; + warn "# keyword `$k' not supported for mbox\n"; } } - while (my ($name, $chars) = each %hdr) { - $eml->header_set($name, join('', sort @$chars)); + # Messages are always 'O' (non-\Recent in IMAP), it saves + # MUAs the trouble of rewriting the mbox if no other + # changes are made. We put 'O' at the end (e.g. "Status: RO") + # to match mutt(1) output. + $eml->header_set('Status', join('', sort(@{$hdr{Status}})). 'O'); + if (my $chars = delete $hdr{'X-Status'}) { + $eml->header_set('X-Status', join('', sort(@$chars))); } my $buf = delete $eml->{hdr}; @@ -73,7 +66,7 @@ sub atomic_append { # for on-disk destinations (O_APPEND, or O_EXCL) if (defined(my $w = syswrite($lei->{1} // return, $$buf))) { return if $w == length($$buf); $buf = "short atomic write: $w != ".length($$buf); - } elsif ($! == EPIPE) { + } elsif ($!{EPIPE}) { return $lei->note_sigpipe(1); } else { $buf = "atomic write: $!"; @@ -144,18 +137,11 @@ sub eml2mboxcl2 { sub git_to_mail { # git->cat_async callback my ($bref, $oid, $type, $size, $arg) = @_; - if ($type ne 'blob') { - if ($type eq 'missing') { - warn "missing $oid\n"; - } else { - warn "unexpected type=$type for $oid\n"; - } - } + return warn("W: $oid is $type (!= blob)\n") if $type ne 'blob'; + return warn("E: $oid is empty\n") unless $size; my ($write_cb, $smsg) = @$arg; - if ($smsg->{blob} ne $oid) { - die "BUG: expected=$smsg->{blob} got=$oid"; - } - $write_cb->($bref, $smsg) if $size > 0; + die "BUG: expected=$smsg->{blob} got=$oid" if $smsg->{blob} ne $oid; + $write_cb->($bref, $smsg); } sub reap_compress { # dwaitpid callback @@ -165,56 +151,10 @@ sub reap_compress { # dwaitpid callback $lei->fail("@$cmd failed", $? >> 8); } -# all of these support -c for stdout and -d for decompression, -# mutt is commonly distributed with hooks for gz, bz2 and xz, at least -# { foo => '' } means "--foo" is passed to the command-line, -# otherwise { foo => '--bar' } passes "--bar" -our %zsfx2cmd = ( - gz => [ qw(GZIP pigz gzip), { rsyncable => '' } ], - bz2 => [ 'bzip2', {} ], - xz => [ 'xz', {} ], - # XXX does anybody care for these? I prefer zstd on entire FSes, - # so it's probably not necessary on a per-file basis - # zst => [ 'zstd', { -default => [ qw(-q) ], # it's noisy by default - # rsyncable => '', threads => '-T' } ], - # zz => [ 'pigz', { -default => [ '--zlib' ], - # rsyncable => '', threads => '-p' }], - # lzo => [ 'lzop', {} ], - # lzma => [ 'lzma', {} ], -); - -sub zsfx2cmd ($$$) { - my ($zsfx, $decompress, $lei) = @_; - my $x = $zsfx2cmd{$zsfx} // die "no support for suffix=.$zsfx"; - my @info = @$x; - my $cmd_opt = pop @info; - my @cmd = (undef, $decompress ? qw(-dc) : qw(-c)); - for my $exe (@info) { - # I think respecting client's ENV{GZIP} is OK, not sure - # about ENV overrides for other, less-common compressors - if ($exe eq uc($exe)) { - $exe = $lei->{env}->{$exe} or next; - } - $cmd[0] = which($exe) and last; - } - $cmd[0] // die join(' or ', @info)." missing for .$zsfx"; - # push @cmd, @{$cmd_opt->{-default}} if $cmd_opt->{-default}; - for my $bool (qw(rsyncable)) { - my $switch = $cmd_opt->{rsyncable} // next; - push @cmd, '--'.($switch || $bool); - } - for my $key (qw(rsyncable)) { # support compression level? - my $switch = $cmd_opt->{$key} // next; - my $val = $lei->{opt}->{$key} // next; - push @cmd, $switch, $val; - } - \@cmd; -} - -sub _post_augment_mbox { # open a compressor process +sub _post_augment_mbox { # open a compressor process from top-level process my ($self, $lei) = @_; my $zsfx = $self->{zsfx} or return; - my $cmd = zsfx2cmd($zsfx, undef, $lei); + my $cmd = PublicInbox::MboxReader::zsfx2cmd($zsfx, undef, $lei); my ($r, $w) = @{delete $lei->{zpipe}}; my $rdr = { 0 => $r, 1 => $lei->{1}, 2 => $lei->{2} }; my $pid = spawn($cmd, undef, $rdr); @@ -225,18 +165,6 @@ sub _post_augment_mbox { # open a compressor process $lei->{1} = $pp; } -sub decompress_src ($$$) { - my ($in, $zsfx, $lei) = @_; - my $cmd = zsfx2cmd($zsfx, 1, $lei); - popen_rd($cmd, undef, { 0 => $in, 2 => $lei->{2} }); -} - -sub dup_src ($) { - my ($in) = @_; - open my $dup, '+>>&', $in or die "dup: $!"; - $dup; -} - # --augment existing output destination, with deduplication sub _augment { # MboxReader eml_cb my ($eml, $lei) = @_; @@ -246,8 +174,8 @@ sub _augment { # MboxReader eml_cb sub _mbox_augment_kw_maybe { my ($eml, $lei, $lse, $augment) = @_; - my @kw = PublicInbox::LeiStore::mbox_keywords($eml); - update_kw_maybe($lei, $lse, $eml, \@kw); + my $kw = PublicInbox::MboxReader::mbox_keywords($eml); + update_kw_maybe($lei, $lse, $eml, $kw); _augment($eml, $lei) if $augment; } @@ -261,10 +189,12 @@ sub _mbox_write_cb ($$) { my $atomic_append = !defined($ovv->{lock_path}); my $dedupe = $lei->{dedupe}; $dedupe->prepare_dedupe; + my $lse = $lei->{lse}; # may be undef sub { # for git_to_mail my ($buf, $smsg, $eml) = @_; $eml //= PublicInbox::Eml->new($buf); - return if $dedupe->is_dup($eml, $smsg->{blob}); + return if $dedupe->is_dup($eml, $smsg); + $lse->xsmsg_vmd($smsg) if $lse; $buf = $eml2mbox->($eml, $smsg); return atomic_append($lei, $buf) if $atomic_append; my $lk = $ovv->lock_for_scope; @@ -275,25 +205,23 @@ sub _mbox_write_cb ($$) { sub update_kw_maybe ($$$$) { my ($lei, $lse, $eml, $kw) = @_; return unless $lse; - my $x = $lse->kw_changed($eml, $kw); - if ($x) { - $lei->{sto}->ipc_do('set_eml', $eml, @$kw); - } elsif (!defined($x)) { - $lei->{sto}->ipc_do('set_xkw', $eml, $kw); - } -} - -sub _augment_or_unlink { # maildir_each_eml cb - my ($f, $kw, $eml, $lei, $lse, $mod, $shard, $unlink) = @_; - if ($mod) { - # can't get dirent.d_ino w/ pure Perl, so we extract the OID - # if it looks like one: - my $hex = $f =~ m!\b([a-f0-9]{40,})[^/]*\z! ? - $1 : sha256_hex($f); - my $recno = hex(substr($hex, 0, 8)); - return if ($recno % $mod) != $shard; - update_kw_maybe($lei, $lse, $eml, $kw); - } + my $c = $lse->kw_changed($eml, $kw, my $docids = []); + my $vmd = { kw => $kw }; + if (scalar @$docids) { # already in lei/store + $lei->{sto}->ipc_do('set_eml_vmd', undef, $vmd, $docids) if $c; + } elsif (my $xoids = $lei->{ale}->xoids_for($eml)) { + # it's in an external, only set kw, here + $lei->{sto}->ipc_do('set_xvmd', $xoids, $eml, $vmd); + } else { # never-before-seen, import the whole thing + # XXX this is critical in protecting against accidental + # data loss without --augment + $lei->{sto}->ipc_do('set_eml', $eml, $vmd); + } +} + +sub _md_update { # maildir_each_eml cb + my ($f, $kw, $eml, $lei, $lse, $unlink) = @_; + update_kw_maybe($lei, $lse, $eml, $kw); $unlink ? unlink($f) : _augment($eml, $lei); } @@ -316,7 +244,7 @@ sub _buf2maildir { do { $tmp = $dst.'tmp/'.$rand.$common; } while (!($ok = sysopen($fh, $tmp, O_CREAT|O_EXCL|O_WRONLY)) && - $! == EEXIST && ($rand = _rand.',')); + $!{EEXIST} && ($rand = _rand.',')); if ($ok && print $fh $$buf and close($fh)) { # ignore new/ and write only to cur/, otherwise MUAs # with R/W access to the Maildir will end up doing @@ -326,7 +254,7 @@ sub _buf2maildir { $rand = ''; do { $final = $dst.$rand.$common.':2,'.$sfx; - } while (!($ok = link($tmp, $final)) && $! == EEXIST && + } while (!($ok = link($tmp, $final)) && $!{EEXIST} && ($rand = _rand.',')); die "link($tmp, $final): $!" unless $ok; unlink($tmp) or warn "W: failed to unlink $tmp: $!\n"; @@ -343,13 +271,15 @@ sub _maildir_write_cb ($$) { my $dedupe = $lei->{dedupe}; $dedupe->prepare_dedupe if $dedupe; my $dst = $lei->{ovv}->{dst}; + my $lse = $lei->{lse}; # may be undef sub { # for git_to_mail my ($buf, $smsg, $eml) = @_; $dst // return $lei->fail; # dst may be undef-ed in last run $buf //= \($eml->as_string); + $lse->xsmsg_vmd($smsg) if $lse; return _buf2maildir($dst, $buf, $smsg) if !$dedupe; $eml //= PublicInbox::Eml->new($$buf); # copy buf - return if $dedupe->is_dup($eml, $smsg->{blob}); + return if $dedupe->is_dup($eml, $smsg); undef $eml; _buf2maildir($dst, $buf, $smsg); } @@ -362,13 +292,15 @@ sub _imap_write_cb ($$) { my $imap_append = $lei->{net}->can('imap_append'); my $mic = $lei->{net}->mic_get($self->{uri}); my $folder = $self->{uri}->mailbox; + my $lse = $lei->{lse}; # may be undef sub { # for git_to_mail my ($bref, $smsg, $eml) = @_; - $mic // return $lei->fail; # dst may be undef-ed in last run + $mic // return $lei->fail; # mic may be undef-ed in last run if ($dedupe) { $eml //= PublicInbox::Eml->new($$bref); # copy bref - return if $dedupe->is_dup($eml, $smsg->{blob}); + return if $dedupe->is_dup($eml, $smsg); } + $lse->xsmsg_vmd($smsg) if $lse; eval { $imap_append->($mic, $folder, $bref, $smsg, $eml) }; if (my $err = $@) { undef $mic; @@ -403,21 +335,29 @@ sub new { $self->{base_type} = 'mbox'; } elsif ($fmt =~ /\Aimaps?\z/) { # TODO .onion support require PublicInbox::NetWriter; + require PublicInbox::URIimap; my $net = PublicInbox::NetWriter->new; - $net->add_url($dst); $net->{quiet} = $lei->{opt}->{quiet}; - my $err = $net->errors($dst); + my $uri = PublicInbox::URIimap->new($dst)->canonical; + $net->add_url($uri); + my $err = $net->errors; return $lei->fail($err) if $err; - require PublicInbox::URIimap; # TODO: URI cast early - $self->{uri} = PublicInbox::URIimap->new($dst); - $self->{uri}->mailbox or die "No mailbox: $dst"; + $uri->mailbox or return $lei->fail("No mailbox: $dst"); + $self->{uri} = $uri; + $dst = $lei->{ovv}->{dst} = $$uri; # canonicalized $lei->{net} = $net; $self->{base_type} = 'imap'; } else { die "bad mail --format=$fmt\n"; } $self->{dst} = $dst; - $lei->{dedupe} = PublicInbox::LeiDedupe->new($lei); + $lei->{dedupe} = $lei->{lss} // do { + my $dd_cls = 'PublicInbox::'. + ($lei->{opt}->{save} ? 'LeiSavedSearch' : 'LeiDedupe'); + eval "require $dd_cls"; + die "$dd_cls: $@" if $@; + $dd_cls->new($lei); + }; $self; } @@ -435,23 +375,22 @@ sub _pre_augment_maildir { sub _do_augment_maildir { my ($self, $lei) = @_; + return if ($lei->{opt}->{save} // 0) < 0; my $dst = $lei->{ovv}->{dst}; - my $lse = $lei->{sto}->search if $lei->{opt}->{'import-before'}; - my ($mod, $shard) = @{$self->{shard_info} // []}; + my $lse = $lei->{opt}->{'import-before'} ? $lei->{lse} : undef; + my $mdr = PublicInbox::MdirReader->new; if ($lei->{opt}->{augment}) { my $dedupe = $lei->{dedupe}; if ($dedupe && $dedupe->prepare_dedupe) { - PublicInbox::MdirReader::maildir_each_eml($dst, - \&_augment_or_unlink, - $lei, $lse, $mod, $shard); + $mdr->{shard_info} = $self->{shard_info}; + $mdr->maildir_each_eml($dst, \&_md_update, $lei, $lse); $dedupe->pause_dedupe; } } elsif ($lse) { - PublicInbox::MdirReader::maildir_each_eml($dst, - \&_augment_or_unlink, - $lei, $lse, $mod, $shard, 1); + $mdr->{shard_info} = $self->{shard_info}; + $mdr->maildir_each_eml($dst, \&_md_update, $lei, $lse, 1); } else {# clobber existing Maildir - PublicInbox::MdirReader::maildir_each_file($dst, \&_unlink); + $mdr->maildir_each_file($dst, \&_unlink); } } @@ -467,8 +406,9 @@ sub _imap_augment_or_delete { # PublicInbox::NetReader::imap_each cb sub _do_augment_imap { my ($self, $lei) = @_; + return if ($lei->{opt}->{save} // 0) < 0; my $net = $lei->{net}; - my $lse = $lei->{sto}->search if $lei->{opt}->{'import-before'}; + my $lse = $lei->{opt}->{'import-before'} ? $lei->{lse} : undef; if ($lei->{opt}->{augment}) { my $dedupe = $lei->{dedupe}; if ($dedupe && $dedupe->prepare_dedupe) { @@ -490,10 +430,12 @@ sub _do_augment_imap { sub _pre_augment_mbox { my ($self, $lei) = @_; my $dst = $lei->{ovv}->{dst}; - my $out = $lei->{1}; - if ($dst ne '/dev/stdout') { + my $out; + my $devfd = $lei->path_to_fd($dst) // die "bad $dst"; + if ($devfd >= 0) { + $out = $lei->{$devfd}; + } else { # normal-looking path if (-p $dst) { - $out = undef; open $out, '>', $dst or die "open($dst): $!"; } elsif (-f _ || !-e _) { require PublicInbox::MboxLock; @@ -501,23 +443,24 @@ sub _pre_augment_mbox { PublicInbox::MboxLock->defaults; $self->{mbl} = PublicInbox::MboxLock->acq($dst, 1, $m); $out = $self->{mbl}->{fh}; + } else { + die "$dst is not a file or FIFO\n"; } $lei->{old_1} = $lei->{1}; # keep for spawning MUA } # Perl does SEEK_END even with O_APPEND :< $self->{seekable} = seek($out, 0, SEEK_SET); - if (!$self->{seekable} && $! != ESPIPE && $dst ne '/dev/stdout') { + if (!$self->{seekable} && !$!{ESPIPE} && !defined($devfd)) { die "seek($dst): $!\n"; } if (!$self->{seekable}) { - my $ia = $lei->{opt}->{'import-before'}; + my $imp_before = $lei->{opt}->{'import-before'}; die "--import-before specified but $dst is not seekable\n" - if $ia && !ref($ia); + if $imp_before && !ref($imp_before); die "--augment specified but $dst is not seekable\n" if $lei->{opt}->{augment}; } - state $zsfx_allow = join('|', keys %zsfx2cmd); - if (($self->{zsfx}) = ($dst =~ /\.($zsfx_allow)\z/)) { + if ($self->{zsfx} = PublicInbox::MboxReader::zsfx($dst)) { pipe(my ($r, $w)) or die "pipe: $!"; $lei->{zpipe} = [ $r, $w ]; $lei->{ovv}->{lock_path} and @@ -534,6 +477,7 @@ sub _do_augment_mbox { my ($self, $lei) = @_; return unless $self->{seekable}; my $opt = $lei->{opt}; + return if ($opt->{save} // 0) < 0; my $out = $lei->{1}; my ($fmt, $dst) = @{$lei->{ovv}}{qw(fmt dst)}; return unless -s $out; @@ -541,15 +485,19 @@ sub _do_augment_mbox { truncate($out, 0) or die "truncate($dst): $!"; return; } - my $zsfx = $self->{zsfx}; - my $rd = $zsfx ? decompress_src($out, $zsfx, $lei) : dup_src($out); + my $rd; + if (my $zsfx = $self->{zsfx}) { + $rd = PublicInbox::MboxReader::zsfxcat($out, $zsfx, $lei); + } else { + open($rd, '+>>&', $out) or die "dup: $!"; + } my $dedupe; if ($opt->{augment}) { $dedupe = $lei->{dedupe}; $dedupe->prepare_dedupe if $dedupe; } if ($opt->{'import-before'}) { # the default - my $lse = $lei->{sto}->search; + my $lse = $lei->{lse}; PublicInbox::MboxReader->$fmt($rd, \&_mbox_augment_kw_maybe, $lei, $lse, $opt->{augment}); if (!$opt->{augment} and !truncate($out, 0)) { @@ -587,6 +535,7 @@ sub post_augment { $m->($self, $lei, @args); } +# called by every single l2m worker process sub do_post_auth { my ($self) = @_; my $lei = $self->{lei}; @@ -594,16 +543,16 @@ sub do_post_auth { pkt_do($lei->{pkt_op_p}, 'incr_start_query') or die "incr_start_query: $!"; my $aug; - if (lock_free($self)) { + if (lock_free($self)) { # all workers do_augment my $mod = $self->{-wq_nr_workers}; my $shard = $self->{-wq_worker_nr}; if (my $net = $lei->{net}) { $net->{shard_info} = [ $mod, $shard ]; - } else { # Maildir (MH?) + } else { # Maildir $self->{shard_info} = [ $mod, $shard ]; } $aug = '+'; # incr_post_augment - } elsif ($self->{-wq_worker_nr} == 0) { + } elsif ($self->{-wq_worker_nr} == 0) { # 1st worker do_augment $aug = '.'; # do_post_augment } if ($aug) { @@ -613,6 +562,7 @@ sub do_post_auth { pkt_do($lei->{pkt_op_p}, $aug) == 1 or die "do_post_augment trigger: $!"; } + # done augmenting, connect the compressor pipe for each worker if (my $zpipe = delete $lei->{zpipe}) { $lei->{1} = $zpipe->[1]; close $zpipe->[0]; @@ -623,38 +573,36 @@ sub do_post_auth { sub ipc_atfork_child { my ($self) = @_; my $lei = $self->{lei}; - $lei->lei_atfork_child; + $lei->_lei_atfork_child; $lei->{auth}->do_auth_atfork($self) if $lei->{auth}; $SIG{__WARN__} = PublicInbox::Eml::warn_ignore_cb(); $self->SUPER::ipc_atfork_child; } sub lock_free { - $_[0]->{base_type} =~ /\A(?:maildir|mh|imap|jmap)\z/ ? 1 : 0; + $_[0]->{base_type} =~ /\A(?:maildir|imap|jmap)\z/ ? 1 : 0; } +# wakes up the MUA when complete so it can refresh messages list sub poke_dst { my ($self) = @_; if ($self->{base_type} eq 'maildir') { my $t = time + 1; - utime($t, $t, "$self->{dst}/cur"); + utime($t, $t, $self->{dst} . 'cur'); } } sub write_mail { # via ->wq_io_do - my ($self, $git_dir, $smsg) = @_; - my $git = $self->{"$$\0$git_dir"} //= PublicInbox::Git->new($git_dir); - git_async_cat($git, $smsg->{blob}, \&git_to_mail, + my ($self, $smsg, $eml) = @_; + return $self->{wcb}->(undef, $smsg, $eml) if $eml; + $self->{lei}->{ale}->git->cat_async($smsg->{blob}, \&git_to_mail, [$self->{wcb}, $smsg]); } sub wq_atexit_child { my ($self) = @_; delete $self->{wcb}; - for my $git (delete @$self{grep(/\A$$\0/, keys %$self)}) { - $git->async_wait_all; - } - $SIG{__WARN__} = 'DEFAULT'; + $self->{lei}->{ale}->git->async_wait_all; } # called in top-level lei-daemon when LeiAuth is done