package PublicInbox::LeiQuery;
use strict;
use v5.10.1;
-use PublicInbox::MID qw($MID_EXTRACT);
-use POSIX qw(strftime);
-use PublicInbox::Address qw(pairs);
use PublicInbox::DS qw(dwaitpid);
-sub _iso8601 ($) { strftime('%Y-%m-%dT%H:%M:%SZ', gmtime($_[0])) }
-
-# prepares an smsg for JSON
-sub _smsg_unbless ($) {
- my ($smsg) = @_;
-
- delete @$smsg{qw(lines bytes)};
- $smsg->{rcvd} = _iso8601(delete $smsg->{ts}); # JMAP receivedAt
- $smsg->{dt} = _iso8601(delete $smsg->{ds}); # JMAP UTCDate
-
- if (my $r = delete $smsg->{references}) {
- $smsg->{references} = [
- map { "<$_>" } ($r =~ m/$MID_EXTRACT/go) ];
- }
- if (my $m = delete($smsg->{mid})) {
- $smsg->{'m'} = "<$m>";
- }
- # XXX breaking to/cc, into structured arrays or tables which
- # distinguish "$phrase <$address>" causes pretty printing JSON
- # to take up too much vertical space. I can't get either
- # Cpanel::JSON::XS or JSON::XS or jq(1) only indent when
- # wrapping is necessary, rather than blindly indenting and
- # adding vertical space everywhere.
- for my $f (qw(from to cc)) {
- my $v = delete $smsg->{$f} or next;
- $smsg->{substr($f, 0, 1)} = $v;
- }
- $smsg->{'s'} = delete $smsg->{subject};
- # can we be bothered to parse From/To/Cc into arrays?
- scalar { %$smsg }; # unbless
+sub prep_ext { # externals_each callback
+ my ($lxs, $exclude, $loc) = @_;
+ $lxs->prepare_external($loc) unless $exclude->{$loc};
}
-sub _vivify_external { # _externals_each callback
- my ($src, $dir) = @_;
- if (-f "$dir/ei.lock") {
- require PublicInbox::ExtSearch;
- push @$src, PublicInbox::ExtSearch->new($dir);
- } elsif (-f "$dir/inbox.lock" || -d "$dir/public-inbox") { # v2, v1
- require PublicInbox::Inbox;
- push @$src, bless { inboxdir => $dir }, 'PublicInbox::Inbox';
+sub qstr_add { # for --stdin
+ my ($self) = @_; # $_[1] = $rbuf
+ if (defined($_[1])) {
+ return eval { $self->{lxs}->do_query($self) } if $_[1] eq '';
+ $self->{mset_opt}->{qstr} .= $_[1];
} else {
- warn "W: ignoring $dir, unable to determine type\n";
+ $self->fail("error reading stdin: $!");
}
}
# the main "lei q SEARCH_TERMS" method
sub lei_q {
my ($self, @argv) = @_;
- my $sto = $self->_lei_store(1);
- my $cfg = $self->_lei_cfg(1);
- my $opt = $self->{opt};
- require PublicInbox::LeiDedupe;
- my $dd = PublicInbox::LeiDedupe->new($self);
-
- # --local is enabled by default
- # src: LeiXSearch || LeiSearch || Inbox
- my @srcs = $opt->{'local'} ? ($sto->search) : ();
require PublicInbox::LeiXSearch;
- my $lxs = PublicInbox::LeiXSearch->new;
-
- # --external is enabled by default, but allow --no-external
- if ($opt->{external} // 1) {
- $self->_externals_each(\&_vivify_external, \@srcs);
+ require PublicInbox::LeiOverview;
+ require PublicInbox::V2Writable;
+ PublicInbox::Config->json; # preload before forking
+ my $opt = $self->{opt};
+ # prepare any number of LeiXSearch || LeiSearch || Inbox || URL
+ my $lxs = $self->{lxs} = PublicInbox::LeiXSearch->new;
+ my @only = @{$opt->{only} // []};
+ # --local is enabled by default unless --only is used
+ # we'll allow "--only $LOCATION --local"
+ if ($opt->{'local'} //= scalar(@only) ? 0 : 1) {
+ my $sto = $self->_lei_store(1);
+ $lxs->prepare_external($sto->search);
+ }
+ if (@only) {
+ for my $loc (@only) {
+ my @loc = $self->get_externals($loc) or return;
+ $lxs->prepare_external($_) for @loc;
+ }
+ } else {
+ for my $loc (@{$opt->{include} // []}) {
+ my @loc = $self->get_externals($loc) or return;
+ $lxs->prepare_external($_) for @loc;
+ }
+ # --external is enabled by default, but allow --no-external
+ if ($opt->{external} //= 1) {
+ my %x;
+ for my $loc (@{$opt->{exclude} // []}) {
+ my @l = $self->get_externals($loc, 1) or return;
+ $x{$_} = 1 for @l;
+ }
+ my $ne = $self->externals_each(\&prep_ext, $lxs, \%x);
+ $opt->{remote} //= !($lxs->locals - $opt->{'local'});
+ if ($opt->{'local'}) {
+ delete($lxs->{remotes}) if !$opt->{remote};
+ } else {
+ delete($lxs->{locals});
+ }
+ }
}
- my $j = $opt->{jobs} // scalar(@srcs) > 4 ? 4 : scalar(@srcs);
- $j = 1 if !$opt->{thread};
- if ($self->{pid}) {
- $lxs->wq_workers_start('lei_xsearch', $j, $self->oldset)
- // $self->wq_workers($j);
+ unless ($lxs->locals || $lxs->remotes) {
+ return $self->fail('no local or remote inboxes to search');
}
- my $out = $opt->{output} // '-';
- $out = 'json:/dev/stdout' if $out eq '-';
- my $isatty = -t $self->{1};
- # no forking workers after this
- my $pid_old12 = $self->start_pager if $isatty;
- my $json = substr($out, 0, 5) eq 'json:' ?
- ref(PublicInbox::Config->json)->new : undef;
- if ($json) {
- if ($opt->{pretty} //= $isatty) {
- $json->pretty(1)->space_before(0);
- $json->indent_length($opt->{indent} // 2);
+ my ($xj, $mj) = split(/,/, $opt->{jobs} // '');
+ if (defined($xj) && $xj ne '' && $xj !~ /\A[1-9][0-9]*\z/) {
+ return $self->fail("`$xj' search jobs must be >= 1");
+ }
+ $xj ||= $lxs->concurrency($opt); # allow: "--jobs ,$WRITER_ONLY"
+ my $nproc = $lxs->detect_nproc; # don't memoize, schedtool(1) exists
+ $xj = $nproc if $xj > $nproc;
+ PublicInbox::LeiOverview->new($self) or return;
+ $self->atfork_prepare_wq($lxs);
+ $lxs->wq_workers_start('lei_xsearch', $xj, $self->oldset);
+ delete $lxs->{-ipc_atfork_child_close};
+ if (my $l2m = $self->{l2m}) {
+ if (defined($mj) && $mj !~ /\A[1-9][0-9]*\z/) {
+ return $self->fail("`$mj' writer jobs must be >= 1");
}
- $json->utf8; # avoid Wide character in print warnings
- $json->ascii(1) if $opt->{ascii}; # for "\uXXXX"
- $json->canonical;
+ $mj //= $nproc;
+ $self->atfork_prepare_wq($l2m);
+ $l2m->wq_workers_start('lei2mail', $mj, $self->oldset);
+ delete $l2m->{-ipc_atfork_child_close};
}
+ # no forking workers after this
+
my %mset_opt = map { $_ => $opt->{$_} } qw(thread limit offset);
$mset_opt{asc} = $opt->{'reverse'} ? 1 : 0;
- $mset_opt{qstr} = join(' ', map {;
- # Consider spaces in argv to be for phrase search in Xapian.
- # In other words, the users should need only care about
- # normal shell quotes and not have to learn Xapian quoting.
- /\s/ ? (s/\A(\w+:)// ? qq{$1"$_"} : qq{"$_"}) : $_
- } @argv);
+ $mset_opt{limit} //= 10000;
if (defined(my $sort = $opt->{'sort'})) {
if ($sort eq 'relevance') {
$mset_opt{relevance} = 1;
die "unrecognized --sort=$sort\n";
}
}
- # $self->out($json->encode(\%mset_opt));
# descending docid order
$mset_opt{relevance} //= -2 if $opt->{thread};
- # my $wcb = PublicInbox::LeiToMail->write_cb($out, $self);
$self->{mset_opt} = \%mset_opt;
- $lxs->do_query($self, \@srcs);
- if ($pid_old12) {
- $self->{$_} = $pid_old12->[$_] for (1, 2);
- dwaitpid($pid_old12->[0], undef, $self->{sock});
+
+ if ($opt->{stdin}) {
+ return $self->fail(<<'') if @argv;
+no query allowed on command-line with --stdin
+
+ require PublicInbox::InputPipe;
+ PublicInbox::InputPipe::consume($self->{0}, \&qstr_add, $self);
+ return;
}
+ # Consider spaces in argv to be for phrase search in Xapian.
+ # In other words, the users should need only care about
+ # normal shell quotes and not have to learn Xapian quoting.
+ $mset_opt{qstr} = join(' ', map {;
+ /\s/ ? (s/\A(\w+:)// ? qq{$1"$_"} : qq{"$_"}) : $_
+ } @argv);
+ $lxs->do_query($self);
+}
+
+# shell completion helper called by lei__complete
+sub _complete_q {
+ my ($self, @argv) = @_;
+ my $ext = qr/\A(?:-I|(?:--(?:include|exclude|only)))\z/;
+ my @cur;
+ while (@argv) {
+ if ($argv[-1] =~ $ext) {
+ my @c = $self->_complete_forget_external(@cur);
+ # try basename match:
+ if (scalar(@cur) == 1 && index($cur[0], '/') < 0) {
+ my $all = $self->externals_each;
+ my %bn;
+ for my $loc (keys %$all) {
+ my $bn = (split(m!/!, $loc))[-1];
+ ++$bn{$bn};
+ }
+ push @c, grep {
+ $bn{$_} == 1 && /\A\Q$cur[0]/
+ } keys %bn;
+ }
+ return @c if @c;
+ }
+ unshift(@cur, pop @argv);
+ }
+ ();
+}
+
+# Stuff we may pass through to curl (as of 7.64.0), see curl manpage for
+# details, so most options which make sense for HTTP/HTTPS (including proxy
+# support for Tor and other methods of getting past weird networks).
+# Most of these are untested by us, some may not make sense for our use case
+# and typos below are likely.
+# n.b. some short options (-$NUMBER) are not supported since they conflict
+# with other "lei q" switches.
+# FIXME: Getopt::Long doesn't easily let us support support options with
+# '.' in them (e.g. --http1.1)
+sub curl_opt { qw(
+ abstract-unix-socket=s anyauth basic cacert=s capath=s
+ cert-status cert-type cert|E=s ciphers=s config|K=s@
+ connect-timeout=s connect-to=s cookie-jar|c=s cookie|b=s crlfile=s
+ digest disable dns-interface=s dns-ipv4-addr=s dns-ipv6-addr=s
+ dns-servers=s doh-url=s egd-file=s engine=s false-start
+ happy-eyeballs-timeout-ms=s haproxy-protocol header|H=s@
+ http2-prior-knowledge http2 insecure|k
+ interface=s ipv4 ipv6 junk-session-cookies
+ key-type=s key=s limit-rate=s local-port=s location-trusted location|L
+ max-redirs=i max-time=s negotiate netrc-file=s netrc-optional netrc
+ no-alpn no-buffer|N no-npn no-sessionid noproxy=s ntlm-wb ntlm
+ pass=s pinnedpubkey=s post301 post302 post303 preproxy=s
+ proxy-anyauth proxy-basic proxy-cacert=s proxy-capath=s
+ proxy-cert-type=s proxy-cert=s proxy-ciphers=s proxy-crlfile=s
+ proxy-digest proxy-header=s@ proxy-insecure
+ proxy-key-type=s proxy-key proxy-negotiate proxy-ntlm proxy-pass=s
+ proxy-pinnedpubkey=s proxy-service-name=s proxy-ssl-allow-beast
+ proxy-tls13-ciphers=s proxy-tlsauthtype=s proxy-tlspassword=s
+ proxy-tlsuser=s proxy-tlsv1 proxy-user|U=s proxy=s
+ proxytunnel=s pubkey=s random-file=s referer=s resolve=s
+ retry-connrefused retry-delay=s retry-max-time=s retry=i
+ sasl-ir service-name=s socks4=s socks4a=s socks5-basic
+ socks5-gssapi-service-name=s socks5-gssapi socks5-hostname=s socks5=s
+ speed-limit|Y speed-type|y ssl-allow-beast sslv2 sslv3
+ suppress-connect-headers tcp-fastopen tls-max=s
+ tls13-ciphers=s tlsauthtype=s tlspassword=s tlsuser=s
+ tlsv1 trace-ascii=s trace-time trace=s
+ unix-socket=s user-agent|A=s user|u=s
+)
}
1;