use PublicInbox::Address qw(pairs);
use PublicInbox::Config;
use PublicInbox::Search qw(get_pct);
+use PublicInbox::LeiDedupe;
+use PublicInbox::LeiToMail;
# cf. https://en.wikipedia.org/wiki/JSON_streaming
my $JSONL = 'ldjson|ndjson|jsonl'; # 3 names for the same thing
unlink(delete($self->{lock_path}));
}
+sub detect_fmt ($$) {
+ my ($lei, $dst) = @_;
+ if ($dst =~ m!\A([:/]+://)!) {
+ $lei->fail("$1 support not implemented, yet\n");
+ } elsif (!-e $dst || -d _) {
+ 'maildir'; # the default TODO: MH?
+ } elsif (-f _ || -p _) {
+ $lei->fail("unable to determine mbox family of $dst\n");
+ } else {
+ $lei->fail("unable to determine format of $dst\n");
+ }
+}
+
sub new {
my ($class, $lei) = @_;
my $opt = $lei->{opt};
my $fmt = $opt->{'format'};
$fmt = lc($fmt) if defined $fmt;
- if ($dst =~ s/\A([a-z]+)://is) { # e.g. Maildir:/home/user/Mail/
+ if ($dst =~ s/\A([a-z0-9]+)://is) { # e.g. Maildir:/home/user/Mail/
my $ofmt = lc $1;
$fmt //= $ofmt;
return $lei->fail(<<"") if $fmt ne $ofmt;
}
$fmt //= 'json' if $dst eq '/dev/stdout';
- $fmt //= 'maildir'; # TODO
+ $fmt //= detect_fmt($lei, $dst) or return;
if (index($dst, '://') < 0) { # not a URL, so assume path
$dst = File::Spec->canonpath($dst);
} # else URL
my $self = bless { fmt => $fmt, dst => $dst }, $class;
+ $lei->{ovv} = $self;
my $json;
if ($fmt =~ /\A($JSONL|(?:concat)?json)\z/) {
$json = $self->{json} = ref(PublicInbox::Config->json);
} else {
ovv_out_lk_init($self);
}
- } elsif ($json) {
- return $lei->fail('JSON formats only output to stdout');
- } else {
- return $lei->fail("TODO: $dst -f $fmt");
}
+ if (!$json) {
+ # default to the cheapest sort since MUA usually resorts
+ $lei->{opt}->{'sort'} //= 'docid' if $dst ne '/dev/stdout';
+ $lei->{l2m} = eval { PublicInbox::LeiToMail->new($lei) };
+ return $lei->fail($@) if $@;
+ }
+ $lei->{dedupe} //= PublicInbox::LeiDedupe->new($lei);
$self;
}
# called once by parent (via PublicInbox::EOFpipe)
sub ovv_end {
my ($self, $lei) = @_;
+ my $out = $lei->{1} or return;
if ($self->{fmt} eq 'json') {
# JSON doesn't allow trailing commas, and preventing
# trailing commas is a PITA when parallelizing outputs
- print { $lei->{1} } "null]\n";
+ print $out "null]\n";
} elsif ($self->{fmt} eq 'concatjson') {
- print { $lei->{1} } "\n";
+ print $out "\n";
}
}
delete @$smsg{qw(lines bytes num tid)};
$smsg->{rt} = _iso8601(delete $smsg->{ts}); # JMAP receivedAt
$smsg->{dt} = _iso8601(delete $smsg->{ds}); # JMAP UTCDate
- $smsg->{relevance} = get_pct($mitem) if $mitem;
-
+ $smsg->{pct} = get_pct($mitem) if $mitem;
if (my $r = delete $smsg->{references}) {
- $smsg->{refs} = [
- map { "<$_>" } ($r =~ m/$MID_EXTRACT/go) ];
+ $smsg->{refs} = [ map { "<$_>" } ($r =~ m/$MID_EXTRACT/go) ];
}
if (my $m = delete($smsg->{mid})) {
$smsg->{'m'} = "<$m>";
sub ovv_atexit_child {
my ($self, $lei) = @_;
+ if (my $l2m = delete $lei->{l2m}) {
+ # gracefully stop lei2mail processes after all
+ # ->write_mail work is complete
+ delete $l2m->{-wq_s1};
+ if (my $rd = delete $l2m->{each_smsg_done}) {
+ read($rd, my $buf, 1); # wait for EOF
+ }
+ }
+ # order matters, git->{-tmp}->DESTROY must not fire until
+ # {each_smsg_done} hits EOF above
+ if (my $git = delete $self->{git}) {
+ $git->async_wait_all;
+ }
if (my $bref = delete $lei->{ovv_buf}) {
+ my $out = $lei->{1} or return;
my $lk = $self->lock_for_scope;
- print { $lei->{1} } $$bref;
+ print $out $$bref;
}
}
qq{ "$k": }.$v;
}
-sub ovv_each_smsg_cb {
- my ($self, $lei) = @_;
- $lei->{ovv_buf} = \(my $buf = '');
- delete(@$self{qw(lock_path tmp_lk_id)}) unless $lei->{-parallel};
- my $json = $self->{json}->new;
+sub ovv_each_smsg_cb { # runs in wq worker usually
+ my ($self, $lei, $ibxish) = @_;
+ my $json;
$lei->{1}->autoflush(1);
- if ($json) {
+ my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
+ if (my $pkg = $self->{json}) {
+ $json = $pkg->new;
$json->utf8->canonical;
$json->ascii(1) if $lei->{opt}->{ascii};
}
- if ($self->{fmt} =~ /\A(concat)?json\z/ && $lei->{opt}->{pretty}) {
+ my $l2m = $lei->{l2m} or $dedupe->prepare_dedupe;
+ if ($l2m && !$ibxish) { # remote https?:// mboxrd
+ delete $l2m->{-wq_s1};
+ my $g2m = $l2m->can('git_to_mail');
+ my $wcb = $l2m->write_cb($lei);
+ sub {
+ my ($smsg, undef, $eml) = @_; # no mitem in $_[1]
+ $wcb->(undef, $smsg, $eml);
+ };
+ } elsif ($l2m && $l2m->{-wq_s1}) {
+ my ($lei_ipc, @io) = $lei->atfork_parent_wq($l2m);
+ # $io[-1] becomes a notification pipe that triggers EOF
+ # in this wq worker when all outstanding ->write_mail
+ # calls are complete
+ pipe($l2m->{each_smsg_done}, $io[$#io + 1]) or die "pipe: $!";
+ fcntl($io[-1], 1031, 4096) if $^O eq 'linux'; # F_SETPIPE_SZ
+ delete @$lei_ipc{qw(l2m opt mset_opt cmd)};
+ $lei_ipc->{each_smsg_not_done} = $#io;
+ my $git = $ibxish->git; # (LeiXSearch|Inbox|ExtSearch)->git
+ $self->{git} = $git;
+ my $git_dir = $git->{git_dir};
+ sub {
+ my ($smsg, $mitem) = @_;
+ $smsg->{pct} = get_pct($mitem) if $mitem;
+ $l2m->wq_do('write_mail', \@io, $git_dir, $smsg,
+ $lei_ipc);
+ }
+ } elsif ($l2m) {
+ my $wcb = $l2m->write_cb($lei);
+ my $git = $ibxish->git; # (LeiXSearch|Inbox|ExtSearch)->git
+ $self->{git} = $git; # for ovv_atexit_child
+ my $g2m = $l2m->can('git_to_mail');
+ $dedupe->prepare_dedupe;
+ sub {
+ my ($smsg, $mitem) = @_;
+ $smsg->{pct} = get_pct($mitem) if $mitem;
+ $git->cat_async($smsg->{blob}, $g2m, [ $wcb, $smsg ]);
+ };
+ } elsif ($self->{fmt} =~ /\A(concat)?json\z/ && $lei->{opt}->{pretty}) {
my $EOR = ($1//'') eq 'concat' ? "\n}" : "\n},";
+ $lei->{ovv_buf} = \(my $buf = '');
sub { # DIY prettiness :P
my ($smsg, $mitem) = @_;
+ return if $dedupe->is_smsg_dup($smsg);
$smsg = _unbless_smsg($smsg, $mitem);
$buf .= "{\n";
$buf .= join(",\n", map {
}
} elsif ($json) {
my $ORS = $self->{fmt} eq 'json' ? ",\n" : "\n"; # JSONL
+ $lei->{ovv_buf} = \(my $buf = '');
sub {
my ($smsg, $mitem) = @_;
- delete @$smsg{qw(tid num)};
+ return if $dedupe->is_smsg_dup($smsg);
$buf .= $json->encode(_unbless_smsg(@_)) . $ORS;
if (length($buf) > 65536) {
my $lk = $self->lock_for_scope;
$buf = '';
}
}
- } elsif ($self->{fmt} eq 'oid') {
- sub {
- my ($smsg, $mitem) = @_;
- }
} # else { ...
}