X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiQuery.pm;h=352ee60131aaf6bc9baabfbd4ae735c4a0f06568;hb=97a9139a75729c41bb91acd711e8b088e6379600;hp=a7938e8b1406c488c62d56a40b1470c35155bab3;hpb=0ca8bd671784ffd1a4ed59914e0b9a0bef7c0ea5;p=public-inbox.git diff --git a/lib/PublicInbox/LeiQuery.pm b/lib/PublicInbox/LeiQuery.pm index a7938e8b..352ee601 100644 --- a/lib/PublicInbox/LeiQuery.pm +++ b/lib/PublicInbox/LeiQuery.pm @@ -1,53 +1,123 @@ # Copyright (C) 2021 all contributors # License: AGPL-3.0+ -# handles lei 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 PublicInbox::DS qw(dwaitpid); -# the main "lei q SEARCH_TERMS" method -sub lei_q { - my ($self, @argv) = @_; - require PublicInbox::LeiXSearch; +sub prep_ext { # externals_each callback + my ($lxs, $exclude, $loc) = @_; + $lxs->prepare_external($loc) unless $exclude->{$loc}; +} + +sub _start_query { # used by "lei q" and "lei up" + my ($self) = @_; require PublicInbox::LeiOverview; - PublicInbox::Config->json; # preload before forking + PublicInbox::LeiOverview->new($self) or return; my $opt = $self->{opt}; - my $lxs = $self->{lxs} = PublicInbox::LeiXSearch->new; - # any number of LeiXSearch || LeiSearch || Inbox - if ($opt->{'local'} //= 1) { # --local is enabled by default - my $sto = $self->_lei_store(1); - $lxs->prepare_external($sto->search); + 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} //= $mj // + int($nproc * 0.75 + 0.5); # keep some CPU for git - # --external is enabled by default, but allow --no-external - if ($opt->{external} //= 1) { - my $cb = $lxs->can('prepare_external'); - $self->_externals_each($cb, $lxs); - } - my $xj = $lxs->concurrency($opt); - my $ovv = PublicInbox::LeiOverview->new($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}) { - my $mj = 4; # TODO: configurable - $self->atfork_prepare_wq($l2m); - $l2m->wq_workers_start('lei2mail', $mj, $self->oldset); - delete $l2m->{-ipc_atfork_child_close}; + # 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 } + $lxs->do_query($self); +} - # no forking workers after this +sub qstr_add { # PublicInbox::InputPipe::consume callback for --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 $@; +} - my %mset_opt = map { $_ => $opt->{$_} } qw(thread limit offset); +sub lxs_prepare { + my ($self) = @_; + require PublicInbox::LeiXSearch; + # 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); + $self->{lse} = $sto->search; + if ($opt->{'local'} //= scalar(@only) ? 0 : 1) { + $lxs->prepare_external($self->{lse}); + } + if (@only) { + for my $loc (@only) { + my @loc = $self->get_externals($loc) or return; + $lxs->prepare_external($_) for @loc; + } + } else { + my (@ilocals, @iremotes); + for my $loc (@{$opt->{include} // []}) { + my @loc = $self->get_externals($loc) or return; + $lxs->prepare_external($_) for @loc; + @ilocals = @{$lxs->{locals} // []}; + @iremotes = @{$lxs->{remotes} // []}; + } + # --external is enabled by default, but allow --no-external + if ($opt->{external} //= 1) { + my $ex = $self->canonicalize_excludes($opt->{exclude}); + $self->externals_each(\&prep_ext, $lxs, $ex); + $opt->{remote} //= !($lxs->locals - $opt->{'local'}); + $lxs->{locals} = \@ilocals if !$opt->{'local'}; + $lxs->{remotes} = \@iremotes if !$opt->{remote}; + } + } + ($lxs->locals || $lxs->remotes) ? ($self->{lxs} = $lxs) : + die("no local or remote inboxes to search\n"); +} + +# the main "lei q SEARCH_TERMS" method +sub lei_q { + my ($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{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); if (defined(my $sort = $opt->{'sort'})) { if ($sort eq 'relevance') { $mset_opt{relevance} = 1; @@ -58,12 +128,50 @@ sub lei_q { } else { die "unrecognized --sort=$sort\n"; } + $opt->{save} and return + $self->fail('--save and --sort are incompatible'); } - # descending docid order - $mset_opt{relevance} //= -2 if $opt->{thread}; $self->{mset_opt} = \%mset_opt; - $ovv->ovv_begin($self); - $lxs->do_query($self); + + 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; + } + $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 @cur; + my $cb = $self->lazy_cb(qw(forget-external _complete_)); + while (@argv) { + if ($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; + 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 @@ -75,18 +183,24 @@ sub lei_q { # with other "lei q" switches. # 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 +# our other CLI options +# Note: some names are renamed to avoid potential conflicts, +# see %lei2curl in lib/PublicInbox/LeiCurl.pm sub curl_opt { qw( + curl-config=s@ 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 + cert-status cert-type cert=s ciphers=s + connect-timeout=s connect-to=s cookie-jar=s cookie=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 + happy-eyeballs-timeout-ms=s haproxy-protocol header=s@ + http2-prior-knowledge http2 insecure interface=s ipv4 ipv6 junk-session-cookies - key-type=s key=s limit-rate=s local-port=s location-trusted location|L + key-type=s key=s limit-rate=s local-port=s location-trusted location 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 + no-alpn no-buffer 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 @@ -94,16 +208,16 @@ sub curl_opt { qw( 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 + proxy-tlsuser=s proxy-tlsv1 proxy-user=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 + speed-limit speed-type 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 + unix-socket=s user-agent=s user=s ) }