# cf. https://en.wikipedia.org/wiki/JSON_streaming
my $JSONL = 'ldjson|ndjson|jsonl'; # 3 names for the same thing
-sub _iso8601 ($) { strftime('%Y-%m-%dT%H:%M:%SZ', gmtime($_[0])) }
+sub iso8601 ($) { strftime('%Y-%m-%dT%H:%M:%SZ', gmtime($_[0])) }
# we open this in the parent process before ->wq_io_do handoff
sub ovv_out_lk_init ($) {
my ($self) = @_;
- my $tmp = File::Temp->new("lei-ovv.dst.$$.lock-XXXXXX",
+ my $tmp = File::Temp->new("lei-ovv.dst.$$.lock-XXXX",
TMPDIR => 1, UNLINK => 0);
$self->{"lk_id.$self.$$"} = $self->{lock_path} = $tmp->filename;
}
unlink($lock_path);
}
-sub detect_fmt ($$) {
- my ($lei, $dst) = @_;
+sub detect_fmt ($) {
+ my ($dst) = @_;
if ($dst =~ m!\A([:/]+://)!) {
- $lei->fail("$1 support not implemented, yet\n");
+ die "$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");
+ die "unable to determine mbox family of $dst\n";
} else {
- $lei->fail("unable to determine format of $dst\n");
+ die "unable to determine format of $dst\n";
}
}
my $fmt = $opt->{$ofmt_key};
$fmt = lc($fmt) if defined $fmt;
if ($dst =~ m!\A([a-z0-9\+]+)://!is) {
- defined($fmt) and return $lei->fail(<<"");
+ defined($fmt) and die <<"";
--$ofmt_key=$fmt invalid with URL $dst
$fmt = lc $1;
} elsif ($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;
+ die <<"" if $fmt ne $ofmt;
--$ofmt_key=$fmt and --output=$ofmt conflict
}
- $fmt //= 'json' if $dst eq '/dev/stdout';
- $fmt //= detect_fmt($lei, $dst) or return;
+ my $devfd = $lei->path_to_fd($dst) // return;
+ $fmt //= $devfd >= 0 ? 'json' : detect_fmt($dst);
if (index($dst, '://') < 0) { # not a URL, so assume path
- $dst = File::Spec->canonpath($dst);
+ $dst = $lei->canonpath_harder($dst);
} # else URL
my $self = bless { fmt => $fmt, dst => $dst }, $class;
if ($fmt =~ /\A($JSONL|(?:concat)?json)\z/) {
$json = $self->{json} = ref(PublicInbox::Config->json);
}
- if ($dst eq '/dev/stdout') {
- my $isatty = $lei->{need_pager} = -t $lei->{1};
+ if ($devfd >= 0) {
+ my $isatty = $lei->{need_pager} = -t $lei->{$devfd};
$opt->{pretty} //= $isatty;
if (!$isatty && -f _) {
- my $fl = fcntl($lei->{1}, F_GETFL, 0) //
- return $lei->fail("fcntl(stdout): $!");
+ my $fl = fcntl($lei->{$devfd}, F_GETFL, 0) //
+ die("fcntl(/dev/fd/$devfd): $!\n");
ovv_out_lk_init($self) unless ($fl & O_APPEND);
} else {
ovv_out_lk_init($self);
if ($json) {
$lei->{dedupe} //= PublicInbox::LeiDedupe->new($lei);
} else {
- # default to the cheapest sort since MUA usually resorts
- $opt->{'sort'} //= 'docid' if $dst ne '/dev/stdout';
- $lei->{l2m} = eval { PublicInbox::LeiToMail->new($lei) };
- return $lei->fail($@) if $@;
+ $lei->{l2m} = PublicInbox::LeiToMail->new($lei);
if ($opt->{mua} && $lei->{l2m}->lock_free) {
$lei->{early_mua} = 1;
$opt->{alert} //= [ ':WINCH,:bell' ] if -t $lei->{1};
}
}
+ die("--shared is only for v2 inbox output\n") if
+ $self->{fmt} ne 'v2' && $lei->{opt}->{shared};
$self;
}
} # TODO HTML/Atom/...
}
-# called once by parent (via PublicInbox::EOFpipe)
+# called once by parent (via PublicInbox::PktOp '' => query_done)
sub ovv_end {
my ($self, $lei) = @_;
if ($self->{fmt} eq 'json') {
sub _unbless_smsg {
my ($smsg, $mitem) = @_;
- delete @$smsg{qw(lines bytes num tid)};
- $smsg->{rt} = _iso8601(delete $smsg->{ts}); # JMAP receivedAt
- $smsg->{dt} = _iso8601(delete $smsg->{ds}); # JMAP UTCDate
+ # TODO: make configurable
+ # num/tid are nonsensical with multi-inbox search,
+ # lines/bytes are not generally useful
+ delete @$smsg{qw(num tid lines bytes)};
+ $smsg->{rt} = iso8601(delete $smsg->{ts}); # JMAP receivedAt
+ $smsg->{dt} = iso8601(delete $smsg->{ds}); # JMAP UTCDate
$smsg->{pct} = get_pct($mitem) if $mitem;
if (my $r = delete $smsg->{references}) {
- $smsg->{refs} = [ map { "<$_>" } ($r =~ m/$MID_EXTRACT/go) ];
+ @{$smsg->{refs}} = ($r =~ m/$MID_EXTRACT/go);
}
if (my $m = delete($smsg->{mid})) {
- $smsg->{'m'} = "<$m>";
+ $smsg->{'m'} = $m;
}
for my $f (qw(from to cc)) {
my $v = delete $smsg->{$f} or next;
$smsg->{substr($f, 0, 1)} = pairs($v);
}
$smsg->{'s'} = delete $smsg->{subject};
- # can we be bothered to parse From/To/Cc into arrays?
- scalar { %$smsg }; # unbless
+ my $kw = delete($smsg->{kw});
+ scalar { %$smsg, ($kw && scalar(@$kw) ? (kw => $kw) : ()) }; # unbless
}
sub ovv_atexit_child {
$pair =~ s/(null|"),"/$1, "/g;
$pair;
} @$v) . ']';
- } else { # references
+ } elsif ($k eq 'kw') { # keywords are short, one-line
+ $v = $json->encode($v);
+ $v =~ s/","/", "/g;
+ } else { # refs, labels, ...
$v = '[' . join($sep, map {
substr($json->encode([$_]), 1, -1);
} @$v) . ']';
}
sub ovv_each_smsg_cb { # runs in wq worker usually
- my ($self, $lei, $ibxish) = @_;
+ my ($self, $lei) = @_;
my ($json, $dedupe);
if (my $pkg = $self->{json}) {
$json = $pkg->new;
$dedupe->prepare_dedupe;
}
$lei->{ovv_buf} = \(my $buf = '') if !$l2m;
- if ($l2m && !$ibxish) { # remote https?:// mboxrd
- 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 $git_dir = $ibxish->git->{git_dir};
+ if ($l2m) {
sub {
- my ($smsg, $mitem) = @_;
+ my ($smsg, $mitem, $eml) = @_;
$smsg->{pct} = get_pct($mitem) if $mitem;
- $l2m->wq_io_do('write_mail', [], $git_dir, $smsg);
+ $l2m->wq_io_do('write_mail', [], $smsg, $eml);
}
} elsif ($self->{fmt} =~ /\A(concat)?json\z/ && $lei->{opt}->{pretty}) {
my $EOR = ($1//'') eq 'concat' ? "\n}" : "\n},";
+ my $lse = $lei->{lse};
sub { # DIY prettiness :P
my ($smsg, $mitem) = @_;
return if $dedupe->is_smsg_dup($smsg);
+ $lse->xsmsg_vmd($smsg, $smsg->{L} ? undef : 1);
$smsg = _unbless_smsg($smsg, $mitem);
$buf .= "{\n";
$buf .= join(",\n", map {
}
} elsif ($json) {
my $ORS = $self->{fmt} eq 'json' ? ",\n" : "\n"; # JSONL
+ my $lse = $lei->{lse};
sub {
my ($smsg, $mitem) = @_;
return if $dedupe->is_smsg_dup($smsg);
+ $lse->xsmsg_vmd($smsg, $smsg->{L} ? undef : 1);
$buf .= $json->encode(_unbless_smsg(@_)) . $ORS;
return if length($buf) < 65536;
my $lk = $self->lock_for_scope;