-# Copyright (C) 2021 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-# handles lei <q|ls-query|rm-query|mv-query> commands
+# handles "lei q" command and provides internals for
+# several other sub-commands (up, lcat, ...)
package PublicInbox::LeiQuery;
use strict;
use v5.10.1;
-use POSIX ();
+use PublicInbox::OverIdx;
sub prep_ext { # externals_each callback
my ($lxs, $exclude, $loc) = @_;
$lxs->prepare_external($loc) unless $exclude->{$loc};
}
-sub _start_query {
+sub _start_query { # used by "lei q" and "lei up"
my ($self) = @_;
+ require PublicInbox::LeiOverview;
+ PublicInbox::LeiOverview->new($self) or return;
+ my $opt = $self->{opt};
+ PublicInbox::OverIdx::fork_ok($opt);
+ my ($xj, $mj) = split(/,/, $opt->{jobs} // '');
+ (defined($xj) && $xj ne '' && $xj !~ /\A[1-9][0-9]*\z/) and
+ die "`$xj' search jobs must be >= 1\n";
+ my $lxs = $self->{lxs};
+ $xj ||= $lxs->concurrency($opt); # allow: "--jobs ,$WRITER_ONLY"
+ my $nproc = $lxs->detect_nproc || 1; # don't memoize, schedtool(1) exists
+ $xj = $nproc if $xj > $nproc;
+ $lxs->{-wq_nr_workers} = $xj;
+ (defined($mj) && $mj !~ /\A[1-9][0-9]*\z/) and
+ die "`$mj' writer jobs must be >= 1\n";
+ my $l2m = $self->{l2m};
+ # we use \1 (a ref) to distinguish between default vs. user-supplied
+ if ($l2m && grep { $opt->{$_} //= \1 } (qw(mail-sync import-remote
+ import-before))) {
+ $self->_lei_store(1)->write_prepare($self);
+ if ($opt->{'mail-sync'}) {
+ my $lms = $l2m->{-lms_rw} = $self->lms(1);
+ $lms->lms_write_prepare->lms_pause; # just create
+ }
+ }
+ $l2m and $l2m->{-wq_nr_workers} //= $mj // do {
+ # keep some CPU for git, and don't overload IMAP destinations
+ my $n = int($nproc * 0.75 + 0.5);
+ $self->{net} && $n > 4 ? 4 : $n;
+ };
+
+ # descending docid order is cheapest, MUA controls sorting order
+ $self->{mset_opt}->{relevance} //= -2 if $l2m || $opt->{threads};
+
+ my $tot = $self->{mset_opt}->{total} //= $self->{opt}->{limit} // 10000;
+ $self->{mset_opt}->{limit} = $tot > 10000 ? 10000 : $tot;
+ $self->{mset_opt}->{offset} //= 0;
+ $self->{mset_opt}->{threads} //= $opt->{threads};
+
if ($self->{net}) {
require PublicInbox::LeiAuth;
$self->{auth} = PublicInbox::LeiAuth->new
}
- $self->{lxs}->do_query($self);
+ $lxs->do_query($self);
}
sub qstr_add { # PublicInbox::InputPipe::consume callback for --stdin
- my ($self) = @_; # $_[1] = $rbuf
- if (defined($_[1])) {
- $_[1] eq '' and return eval {
- my $lse = delete $self->{lse};
- $lse->query_approxidate($lse->git,
- $self->{mset_opt}->{qstr});
- _start_query($self);
- };
- $self->{mset_opt}->{qstr} .= $_[1];
- } else {
- $self->fail("error reading stdin: $!");
- }
+ my ($lei) = @_; # $_[1] = $rbuf
+ $_[1] // $lei->fail("error reading stdin: $!");
+ return $lei->{mset_opt}->{qstr} .= $_[1] if $_[1] ne '';
+ eval {
+ $lei->fchdir;
+ $lei->{mset_opt}->{q_raw} = $lei->{mset_opt}->{qstr};
+ $lei->{lse}->query_approxidate($lei->{lse}->git,
+ $lei->{mset_opt}->{qstr});
+ _start_query($lei);
+ };
+ $lei->fail($@) if $@;
}
-# the main "lei q SEARCH_TERMS" method
-sub lei_q {
- my ($self, @argv) = @_;
+# make the URI||PublicInbox::{Inbox,ExtSearch} a config-file friendly string
+sub cfg_ext ($) {
+ my ($x) = @_;
+ $x->isa('URI') ? "$x" : ($x->{inboxdir} // $x->{topdir});
+}
+
+sub lxs_prepare {
+ my ($self) = @_;
require PublicInbox::LeiXSearch;
- 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 $opt = $self->{opt};
my @only = @{$opt->{only} // []};
# --local is enabled by default unless --only is used
# we'll allow "--only $LOCATION --local"
my $sto = $self->_lei_store(1);
- if (($opt->{'import-remote'} //= 1) |
- (($opt->{'import-before'} //= \1) ? 1 : 0)) {
- $sto->write_prepare($self);
- }
- my $lse = $sto->search;
+ $self->{lse} = $sto->search;
if ($opt->{'local'} //= scalar(@only) ? 0 : 1) {
- $lxs->prepare_external($lse);
+ $lxs->prepare_external($self->{lse});
}
if (@only) {
+ my $only;
for my $loc (@only) {
my @loc = $self->get_externals($loc) or return;
- $lxs->prepare_external($_) for @loc;
+ for (@loc) {
+ my $x = $lxs->prepare_external($_);
+ push(@$only, cfg_ext($x)) if $x;
+ }
}
+ $opt->{only} = $only if $only;
} else {
- my (@ilocals, @iremotes);
+ my (@ilocals, @iremotes, $incl);
for my $loc (@{$opt->{include} // []}) {
my @loc = $self->get_externals($loc) or return;
- $lxs->prepare_external($_) for @loc;
+ for (@loc) {
+ my $x = $lxs->prepare_external($_);
+ push(@$incl, cfg_ext($x)) if $x;
+ }
@ilocals = @{$lxs->{locals} // []};
@iremotes = @{$lxs->{remotes} // []};
}
+ $opt->{include} = $incl if $incl;
# --external is enabled by default, but allow --no-external
if ($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);
+ my $ex = $self->canonicalize_excludes($opt->{exclude});
+ my @excl = keys %$ex;
+ $opt->{exclude} = \@excl if scalar(@excl);
+ $self->externals_each(\&prep_ext, $lxs, $ex);
$opt->{remote} //= !($lxs->locals - $opt->{'local'});
- if ($opt->{'local'}) {
- $lxs->{remotes} = \@iremotes if !$opt->{remote};
- } else {
- $lxs->{locals} = \@ilocals;
- }
+ $lxs->{locals} = \@ilocals if !$opt->{'local'};
+ $lxs->{remotes} = \@iremotes if !$opt->{remote};
}
}
- unless ($lxs->locals || $lxs->remotes) {
- return $self->fail('no local or remote inboxes to search');
- }
- $self->ale->refresh_externals($lxs);
- 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 // 1; # don't memoize, schedtool(1) exists
- $xj = $nproc if $xj > $nproc;
- $lxs->{-wq_nr_workers} = $xj;
- if (defined($mj) && $mj !~ /\A[1-9][0-9]*\z/) {
- return $self->fail("`$mj' writer jobs must be >= 1");
- }
- PublicInbox::LeiOverview->new($self) or return;
- $self->{l2m} and $self->{l2m}->{-wq_nr_workers} = $mj // do {
- $mj = POSIX::lround($nproc * 3 / 4); # keep some CPU for git
- $mj <= 0 ? 1 : $mj;
- };
+ ($lxs->locals || $lxs->remotes) ? ($self->{lxs} = $lxs) :
+ die("no local or remote inboxes to search\n");
+}
- my %mset_opt = map { $_ => $opt->{$_} } qw(threads limit offset);
+# the main "lei q SEARCH_TERMS" method
+sub lei_q {
+ my ($self, @argv) = @_;
+ PublicInbox::Config->json; # preload before forking
+ my $lxs = lxs_prepare($self) or return;
+ $self->ale->refresh_externals($lxs, $self);
+ my $opt = $self->{opt};
+ my %mset_opt;
$mset_opt{asc} = $opt->{'reverse'} ? 1 : 0;
- $mset_opt{limit} //= 10000;
if (defined(my $sort = $opt->{'sort'})) {
if ($sort eq 'relevance') {
$mset_opt{relevance} = 1;
} else {
die "unrecognized --sort=$sort\n";
}
+ $opt->{save} and return
+ $self->fail('--save and --sort are incompatible');
}
- # descending docid order
- $mset_opt{relevance} //= -2 if $opt->{threads};
$self->{mset_opt} = \%mset_opt;
if ($opt->{stdin}) {
no query allowed on command-line with --stdin
require PublicInbox::InputPipe;
- $self->{lse} = $lse; # for query_approxidate
PublicInbox::InputPipe::consume($self->{0}, \&qstr_add, $self);
return;
}
- $mset_opt{qstr} = $lse->query_argv_to_string($lse->git, \@argv);
+ chomp(@argv) and $self->qerr("# trailing `\\n' removed");
+ $mset_opt{q_raw} = [ @argv ]; # copy
+ $mset_opt{qstr} =
+ $self->{lse}->query_argv_to_string($self->{lse}->git, \@argv);
_start_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;
+ my $cb = $self->lazy_cb(qw(forget-external _complete_));
while (@argv) {
- if ($argv[-1] =~ $ext) {
- my @c = $self->_complete_forget_external(@cur);
+ if ($argv[-1] =~ /\A(?:-I|(?:--(?:include|exclude|only)))\z/) {
+ my @c = $cb->($self, @cur);
# try basename match:
if (scalar(@cur) == 1 && index($cur[0], '/') < 0) {
my $all = $self->externals_each;
# FIXME: Getopt::Long doesn't easily let us support support options with
# '.' in them (e.g. --http1.1)
# TODO: should we depend on "-c http.*" options for things which have
-# analogues in git(1)? that would reduce likelyhood of conflicts with
+# analogues in git(1)? that would reduce likelihood of conflicts with
# our other CLI options
# Note: some names are renamed to avoid potential conflicts,
-# see %lei2mail in lib/PublicInbox/LeiCurl.pm
+# see %lei2curl in lib/PublicInbox/LeiCurl.pm
sub curl_opt { qw(
curl-config=s@
abstract-unix-socket=s anyauth basic cacert=s capath=s