X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLEI.pm;h=bdeab7e39b74f4f90fb0b0331078859f6d30fdc7;hb=cfc2f64069e245a700b60113705be477857c51e5;hp=d5d9cf1f85ab86f8dec3ae111359ca12c02b403c;hpb=cf850cf6efac835445949b28ee0346f1dc34f8bd;p=public-inbox.git diff --git a/lib/PublicInbox/LEI.pm b/lib/PublicInbox/LEI.pm index d5d9cf1f..bdeab7e3 100644 --- a/lib/PublicInbox/LEI.pm +++ b/lib/PublicInbox/LEI.pm @@ -12,12 +12,11 @@ use parent qw(PublicInbox::DS PublicInbox::LeiExternal PublicInbox::LeiQuery); use Getopt::Long (); use Socket qw(AF_UNIX SOCK_SEQPACKET MSG_EOR pack_sockaddr_un); -use Errno qw(EAGAIN EINTR ECONNREFUSED ENOENT ECONNRESET); +use Errno qw(EPIPE EAGAIN EINTR ECONNREFUSED ENOENT ECONNRESET); use Cwd qw(getcwd); -use POSIX (); +use POSIX qw(strftime); use IO::Handle (); use Fcntl qw(SEEK_SET); -use Sys::Syslog qw(syslog openlog); use PublicInbox::Config; use PublicInbox::Syscall qw(SFD_NONBLOCK EPOLLIN EPOLLET); use PublicInbox::Sigfd; @@ -99,13 +98,21 @@ sub _config_path ($) { .'/lei/config'); } +sub index_opt { + # TODO: drop underscore variants everywhere, they're undocumented + qw(fsync|sync! jobs|j=i indexlevel|index-level|L=s compact+ + max_size|max-size=s sequential_shard|sequential-shard + batch_size|batch-size=s skip-docdata quiet|q verbose|v+) +} + # TODO: generate shell completion + help using %CMD and %OPTDESC # command => [ positional_args, 1-line description, Getopt::Long option spec ] our %CMD = ( # sorted in order of importance/use: -'q' => [ 'SEARCH_TERMS...', 'search for messages matching terms', qw( +'q' => [ '--stdin|SEARCH_TERMS...', 'search for messages matching terms', qw( save-as=s output|mfolder|o=s format|f=s dedupe|d=s thread|t augment|a sort|s=s reverse|r offset=i remote! local! external! pretty - mua-cmd|mua=s no-torsocks torsocks=s verbose|v + include|I=s@ exclude=s@ only=s@ jobs|j=s globoff|g stdin| + mua-cmd|mua=s no-torsocks torsocks=s verbose|v+ quiet|q received-after=s received-before=s sent-after=s sent-since=s), PublicInbox::LeiQuery::curl_opt(), opt_dash('limit|n=i', '[0-9]+') ], @@ -115,7 +122,8 @@ our %CMD = ( # sorted in order of importance/use: 'add-external' => [ 'URL_OR_PATHNAME', 'add/set priority of a publicinbox|extindex for extra matches', - qw(boost=i quiet|q) ], + qw(boost=i c=s@ mirror=s no-torsocks torsocks=s inbox-version=i), + index_opt(), PublicInbox::LeiQuery::curl_opt() ], 'ls-external' => [ '[FILTER...]', 'list publicinbox|extindex locations', qw(format|f=s z|0 local remote quiet|q) ], 'forget-external' => [ 'URL_OR_PATHNAME...|--prune', @@ -131,7 +139,7 @@ our %CMD = ( # sorted in order of importance/use: 'exclude mail matching From: or thread from non-Message-ID searches', qw(stdin| thread|t from|f=s mid=s oid=s) ], 'mark' => [ 'MESSAGE_FLAGS...', - 'set/unset flags on message(s) from stdin', + 'set/unset keywords on message(s) from stdin', qw(stdin| oid=s exact by-mid|mid:s) ], 'forget' => [ '[--stdin|--oid=OID|--by-mid=MID]', "exclude message(s) on stdin from `q' search results", @@ -152,7 +160,8 @@ our %CMD = ( # sorted in order of importance/use: 'add-watch' => [ '[URL_OR_PATHNAME]', 'watch for new messages and flag changes', - qw(import! flags! interval=s recursive|r exclude=s include=s) ], + qw(import! kw|keywords|flags! interval=s recursive|r + exclude=s include=s) ], 'ls-watch' => [ '[FILTER...]', 'list active watches with numbers and status', qw(format|f=s z) ], 'pause-watch' => [ '[WATCH_NUMBER_OR_FILTER]', qw(all local remote) ], @@ -160,9 +169,10 @@ our %CMD = ( # sorted in order of importance/use: 'forget-watch' => [ '{WATCH_NUMBER|--prune}', 'stop and forget a watch', qw(prune) ], -'import' => [ 'URL_OR_PATHNAME|--stdin', - 'one-shot import/update from URL or filesystem', - qw(stdin| offset=i recursive|r exclude=s include=s !flags), +'import' => [ 'URLS_OR_PATHNAMES...|--stdin', + 'one-time import/update from URL or filesystem', + qw(stdin| offset=i recursive|r exclude=s include|I=s + format|f=s kw|keywords|flags!), ], 'config' => [ '[...]', sub { @@ -194,14 +204,15 @@ our %CMD = ( # sorted in order of importance/use: # $spec => [@ALLOWED_VALUES (default is first), $description], # $spec => $description # "$SUB_COMMAND TAB $spec" => as above -my $stdin_formats = [ 'IN|auto|raw|mboxrd|mboxcl2|mboxcl|mboxo', - 'specify message input format' ]; +my $stdin_formats = [ 'MAIL_FORMAT|eml|mboxrd|mboxcl2|mboxcl|mboxo', + 'specify message input format' ]; my $ls_format = [ 'OUT|plain|json|null', 'listing output format' ]; my %OPTDESC = ( 'help|h' => 'show this built-in help', 'quiet|q' => 'be quiet', -'verbose|v' => 'be more verbose', +'globoff|g' => "do not match locations using '*?' wildcards and '[]' ranges", +'verbose|v+' => 'be more verbose', 'solve!' => 'do not attempt to reconstruct blobs from emails', 'torsocks=s' => ['auto|no|yes', 'whether or not to wrap git and curl commands with torsocks'], @@ -229,6 +240,18 @@ my %OPTDESC = ( 'q format|f=s' => [ 'OUT|maildir|mboxrd|mboxcl2|mboxcl|mboxo|html|json|jsonl|concatjson', 'specify output format, default depends on --output'], +'q exclude=s@' => [ 'URL_OR_PATHNAME', + 'exclude specified external(s) from search' ], +'q include|I=s@' => [ 'URL_OR_PATHNAME', + 'include specified external(s) in search' ], +'q only=s@' => [ 'URL_OR_PATHNAME', + 'only use specified external(s) for search' ], + +'q jobs=s' => [ '[SEARCH_JOBS][,WRITER_JOBS]', + 'control number of search and writer jobs' ], + +'import format|f=s' => $stdin_formats, + 'ls-query format|f=s' => $ls_format, 'ls-external format|f=s' => $ls_format, @@ -259,6 +282,8 @@ my %OPTDESC = ( 'by-mid|mid:s' => [ 'MID', 'match only by Message-ID, ignoring contents' ], 'jobs:i' => 'set parallelism level', +'kw|keywords|flags!' => 'disable/enable importing flags', + # xargs, env, use "-0", git(1) uses "-z". We support z|0 everywhere 'z|0' => 'use NUL \\0 instead of newline (CR) to delimit lines', @@ -269,116 +294,125 @@ my %CONFIG_KEYS = ( 'leistore.dir' => 'top-level storage location', ); +my @WQ_KEYS = qw(lxs l2m imp mrr); # internal workers + # pronounced "exit": x_it(1 << 8) => exit(1); x_it(13) => SIGPIPE sub x_it ($$) { my ($self, $code) = @_; # make sure client sees stdout before exit $self->{1}->autoflush(1) if $self->{1}; dump_and_clear_log(); - if (my $sock = $self->{sock}) { - send($sock, "x_it $code", MSG_EOR); - } elsif (!($code & 127)) { # oneshot, ignore signals + if (my $s = $self->{pkt_op_p} // $self->{sock}) { + send($s, "x_it $code", MSG_EOR); + } elsif ($self->{oneshot}) { # don't want to end up using $? from child processes - for my $f (qw(lxs l2m)) { + for my $f (@WQ_KEYS) { my $wq = delete $self->{$f} or next; $wq->DESTROY; } - $quit->($code >> 8); - } + # cleanup anything that has tempfiles + delete @$self{qw(ovv dedupe)}; + if (my $signum = ($code & 127)) { # usually SIGPIPE (13) + $SIG{PIPE} = 'DEFAULT'; # $SIG{$signum} doesn't work + kill $signum, $$; + sleep(1) while 1; # wait for signal + } else { + $quit->($code >> 8); + } + } # else ignore if client disconnected } -sub puts ($;@) { print { shift->{1} } map { "$_\n" } @_ } - -sub out ($;@) { print { shift->{1} } @_ } - sub err ($;@) { my $self = shift; - my $err = $self->{2} // ($self->{pgr} // [])->[2] // *STDERR{IO}; - print $err @_, (substr($_[-1], -1, 1) eq "\n" ? () : "\n"); + my $err = $self->{2} // ($self->{pgr} // [])->[2] // *STDERR{GLOB}; + my @eor = (substr($_[-1]//'', -1, 1) eq "\n" ? () : ("\n")); + print $err @_, @eor and return; + my $old_err = delete $self->{2}; + close($old_err) if $! == EPIPE && $old_err; + $err = $self->{2} = ($self->{pgr} // [])->[2] // *STDERR{GLOB}; + print $err @_, @eor or print STDERR @_, @eor; } sub qerr ($;@) { $_[0]->{opt}->{quiet} or err(shift, @_) } +sub fail_handler ($;$$) { + my ($lei, $code, $io) = @_; + for my $f (@WQ_KEYS) { + my $wq = delete $lei->{$f} or next; + $wq->wq_wait_old($lei) if $wq->wq_kill_old; # lei-daemon + } + close($io) if $io; # needed to avoid warnings on SIGPIPE + $lei->x_it($code // (1 >> 8)); +} + +sub sigpipe_handler { # handles SIGPIPE from @WQ_KEYS workers + fail_handler($_[0], 13, delete $_[0]->{1}); +} + sub fail ($$;$) { my ($self, $buf, $exit_code) = @_; - err($self, $buf); + err($self, $buf) if defined $buf; + # calls fail_handler: + send($self->{pkt_op_p}, '!', MSG_EOR) if $self->{pkt_op_p}; x_it($self, ($exit_code // 1) << 8); undef; } +sub out ($;@) { + my $self = shift; + return if print { $self->{1} // return } @_; # likely + return note_sigpipe($self, 1) if $! == EPIPE; + my $err = "error writing to stdout: $!"; + delete $self->{1}; + fail($self, $err); +} + +sub puts ($;@) { out(shift, map { "$_\n" } @_) } + sub child_error { # passes non-fatal curl exit codes to user - my ($self, $child_error) = @_; # child_error is $? - if (my $sock = $self->{sock}) { # send to lei(1) client - send($sock, "child_error $child_error", MSG_EOR); - } else { # oneshot + my ($self, $child_error, $msg) = @_; # child_error is $? + $self->err($msg) if $msg; + if (my $s = $self->{pkt_op_p} // $self->{sock}) { + # send to the parent lei-daemon or to lei(1) client + send($s, "child_error $child_error", MSG_EOR); + } elsif (!$PublicInbox::DS::in_loop) { $self->{child_error} = $child_error; - } - undef; + } # else noop if client disconnected +} + +sub note_sigpipe { # triggers sigpipe_handler + my ($self, $fd) = @_; + close(delete($self->{$fd})); # explicit close silences Perl warning + send($self->{pkt_op_p}, '|', MSG_EOR) if $self->{pkt_op_p}; + x_it($self, 13); } -sub atfork_prepare_wq { - my ($self, $wq) = @_; - my $tcafc = $wq->{-ipc_atfork_child_close} //= [ $listener // () ]; - if (my $sock = $self->{sock}) { - push @$tcafc, @$self{qw(0 1 2 3)}, $sock; +sub lei_atfork_child { + my ($self, $persist) = @_; + # we need to explicitly close things which are on stack + if ($persist) { + my @io = delete @$self{0,1,2}; + unless ($self->{oneshot}) { + close($_) for @io; + } + } else { + delete $self->{0}; } - if (my $pgr = $self->{pgr}) { - push @$tcafc, @$pgr[1,2]; + for (delete @$self{qw(3 sock old_1 au_done)}) { + close($_) if defined($_); } - if (my $old_1 = $self->{old_1}) { - push @$tcafc, $old_1; + if (my $op_c = delete $self->{pkt_op_c}) { + close(delete $op_c->{sock}); } - for my $f (qw(lxs l2m)) { - my $ipc = $self->{$f} or next; - push @$tcafc, grep { defined } - @$ipc{qw(-wq_s1 -wq_s2 -ipc_req -ipc_res)}; + if (my $pgr = delete $self->{pgr}) { + close($_) for (@$pgr[1,2]); } -} - -# usage: my %sig = $lei->atfork_child_wq($wq); -# local @SIG{keys %sig} = values %sig; -sub atfork_child_wq { - my ($self, $wq) = @_; - my ($sock, $l2m_wq_s1); - (@$self{qw(0 1 2)}, $sock, $l2m_wq_s1) = delete(@$wq{0..4}); - $self->{sock} = $sock if -S $sock; - $self->{l2m}->{-wq_s1} = $l2m_wq_s1 if $l2m_wq_s1 && -S $l2m_wq_s1; + close $listener if $listener; + undef $listener; %PATH2CFG = (); undef $errors_log; $quit = \&CORE::exit; - (__WARN__ => sub { err($self, @_) }, - PIPE => sub { - $self->x_it(13); # SIGPIPE = 13 - # we need to close explicitly to avoid Perl warning on SIGPIPE - for my $i (1, 2) { - next unless $self->{$i} && (-p $self->{$i} || -S _); - close(delete $self->{$i}); - } - # trigger the LeiXSearch $done OpPipe: - syswrite($self->{0}, '!') if $self->{0} && -p $self->{0}; - $SIG{PIPE} = 'DEFAULT'; - die bless(\"$_[0]", 'PublicInbox::SIGPIPE'), - }); -} - -# usage: ($lei, @io) = $lei->atfork_parent_wq($wq); -sub atfork_parent_wq { - my ($self, $wq) = @_; - my $env = delete $self->{env}; # env is inherited at fork - my $ret = bless { %$self }, ref($self); - if (my $dedupe = delete $ret->{dedupe}) { - $ret->{dedupe} = $wq->deep_clone($dedupe); - } - $self->{env} = $env; - delete @$ret{qw(3 -lei_store cfg old_1 pgr lxs)}; # keep l2m - my @io = delete @$ret{0..2}; - $io[3] = delete($ret->{sock}) // $io[2]; - my $l2m = $ret->{l2m}; - if ($l2m && $l2m != $wq) { # $wq == lxs - $io[4] = $l2m->{-wq_s1} if $l2m->{-wq_s1}; - $l2m->wq_close(1); - } - ($ret, @io); + $current_lei = $persist ? undef : $self; # for SIG{__WARN__} } sub _help ($;$) { @@ -403,7 +437,7 @@ sub _help ($;$) { my (@vals, @s, @l); my $x = $sw; if ($x =~ s/!\z//) { # solve! => --no-solve - $x = "no-$x"; + $x =~ s/(\A|\|)/$1no-/g } elsif ($x =~ s/:.+//) { # optional args: $x = "mid:s" @vals = (' [', undef, ']'); } elsif ($x =~ s/=.+//) { # required arg: $x = "type=s" @@ -452,7 +486,9 @@ EOF $msg .= $rhs; $msg .= "\n"; } - print { $self->{$errmsg ? 2 : 1} } $msg; + my $out = $self->{$errmsg ? 2 : 1}; + start_pager($self) if -t $out; + print $out $msg; x_it($self, $errmsg ? 1 << 8 : 0); # stderr => failure undef; } @@ -497,12 +533,13 @@ sub optparse ($$$) { } elsif ($var =~ /\A\[-?$POS_ARG\]\z/) { # one optional arg $i++; } elsif ($var =~ /\A.+?\|/) { # required FOO|--stdin + $inf = 1 if index($var, '...') > 0; my @or = split(/\|/, $var); my $ok; for my $o (@or) { if ($o =~ /\A--([a-z0-9\-]+)/) { $ok = defined($OPT->{$1}); - last; + last if $ok; } elsif (defined($argv->[$i])) { $ok = 1; $i++; @@ -607,6 +644,11 @@ sub lei_config { x_it($self, $?) if $?; } +sub lei_import { + require PublicInbox::LeiImport; + PublicInbox::LeiImport->call(@_); +} + sub lei_init { my ($self, $dir) = @_; my $cfg = _lei_cfg($self, 1); @@ -680,8 +722,10 @@ sub lei__complete { } puts $self, grep(/$re/, map { # generate short/long names if (s/[:=].+\z//) { # req/optional args, e.g output|o=i - } else { # negation: solve! => no-solve|solve - s/\A(.+)!\z/no-$1|$1/; + } elsif (s/\+\z//) { # verbose|v+ + } elsif (s/!\z//) { + # negation: solve! => no-solve|solve + s/([\w\-]+)/$1|no-$1/g } map { my $x = length > 1 ? "--$_" : "-$_"; @@ -697,8 +741,7 @@ sub lei__complete { my $opt = quotemeta $1; puts $self, map { my $v = $OPTDESC{$_}; - $v = $v->[0] if ref($v); - my @v = split(/\|/, $v); + my @v = ref($v) ? split(/\|/, $v->[0]) : (); # get rid of ALL CAPS placeholder (e.g "OUT") # (TODO: completion for external paths) shift(@v) if uc($v[0]) eq $v[0]; @@ -738,9 +781,10 @@ sub start_mua { push @cmd, $mfolder unless defined($replaced); if (my $sock = $self->{sock}) { # lei(1) client process runs it send($sock, exec_buf(\@cmd, {}), MSG_EOR); - } else { # oneshot + } elsif ($self->{oneshot}) { $self->{"mua.pid.$self.$$"} = spawn(\@cmd); } + delete $self->{-progress}; } # caller needs to "-t $self->{1}" to check if tty @@ -756,13 +800,16 @@ sub start_pager { $new_env->{MORE} = 'FRX' if $^O eq 'freebsd'; pipe(my ($r, $wpager)) or return warn "pipe: $!"; my $rdr = { 0 => $r, 1 => $self->{1}, 2 => $self->{2} }; - my $pgr = [ undef, @$rdr{1, 2}, $$ ]; + my $pgr = [ undef, @$rdr{1, 2} ]; if (my $sock = $self->{sock}) { # lei(1) process runs it delete @$new_env{keys %$env}; # only set iff unset my $fds = [ map { fileno($_) } @$rdr{0..2} ]; $send_cmd->($sock, $fds, exec_buf([$pager], $new_env), MSG_EOR); - } else { + } elsif ($self->{oneshot}) { $pgr->[0] = spawn([$pager], $new_env, $rdr); + $pgr->[3] = $$; # ew'll reap it + } else { + die 'BUG: start_pager w/o socket'; } $self->{1} = $wpager; $self->{2} = $wpager if -t $self->{2}; @@ -777,7 +824,7 @@ sub stop_pager { # do not restore original stdout, just close it so we error out close(delete($self->{1})) if $self->{1}; my $pid = $pgr->[0]; - dwaitpid($pid, undef, $self->{sock}) if $pid && $pgr->[3] == $$; + dwaitpid($pid) if $pid && ($pgr->[3] // 0) == $$; } sub accept_dispatch { # Listener {post_accept} callback @@ -785,7 +832,7 @@ sub accept_dispatch { # Listener {post_accept} callback $sock->autoflush(1); my $self = bless { sock => $sock }, __PACKAGE__; vec(my $rvec = '', fileno($sock), 1) = 1; - select($rvec, undef, undef, 1) or + select($rvec, undef, undef, 60) or return send($sock, 'timed out waiting to recv FDs', MSG_EOR); my @fds = $recv_cmd->($sock, my $buf, 4096 * 33); # >MAX_ARG_STRLEN if (scalar(@fds) == 4) { @@ -795,7 +842,9 @@ sub accept_dispatch { # Listener {post_accept} callback send($sock, "open(+<&=$fd) (FD=$i): $!", MSG_EOR); } } else { - return send($sock, "recv_cmd failed: $!", MSG_EOR); + my $msg = "recv_cmd failed: $!"; + warn $msg; + return send($sock, $msg, MSG_EOR); } $self->{2}->autoflush(1); # keep stdout buffered until x_it|DESTROY # $ENV_STR = join('', map { "\0$_=$ENV{$_}" } keys %ENV); @@ -817,12 +866,13 @@ sub accept_dispatch { # Listener {post_accept} callback sub dclose { my ($self) = @_; - for my $f (qw(lxs l2m)) { + delete $self->{-progress}; + for my $f (@WQ_KEYS) { my $wq = delete $self->{$f} or next; if ($wq->wq_kill) { - $self->wq_close + $wq->wq_close } elsif ($wq->wq_kill_old) { - $wq->wq_wait_old; + $wq->wq_wait_old($self); } } close(delete $self->{1}) if $self->{1}; # may reap_compress @@ -859,7 +909,6 @@ sub event_step { sub event_step_init { my ($self) = @_; if (my $sock = $self->{sock}) { # using DS->EventLoop - $sock->blocking(0); $self->SUPER::new($sock, EPOLLIN|EPOLLET); } } @@ -886,6 +935,11 @@ sub lazy_start { $! = $errno; # allow interpolation to stringify in die die "connect($path): $!"; } + if (eval { require BSD::Resource }) { + my $NOFILE = BSD::Resource::RLIMIT_NOFILE(); + my ($s, $h) = BSD::Resource::getrlimit($NOFILE); + BSD::Resource::setrlimit($NOFILE, $h, $h) if $s < $h; + } umask(077) // die("umask(077): $!"); local $listener; socket($listener, AF_UNIX, SOCK_SEQPACKET, 0) or die "socket: $!"; @@ -963,9 +1017,9 @@ sub lazy_start { warn "$path dev/ino changed, quitting\n"; $path = undef; } - } elsif (defined($path)) { - warn "stat($path): $!, quitting ...\n"; - undef $path; # don't unlink + } elsif (defined($path)) { # ENOENT is common + warn "stat($path): $!, quitting ...\n" if $! != ENOENT; + undef $path; $quit->(); } return 1 if defined($path); @@ -985,18 +1039,14 @@ sub lazy_start { # STDIN was redirected to /dev/null above, closing STDERR and # STDOUT will cause the calling `lei' client process to finish # reading the <$daemon> pipe. - openlog($path, 'pid', 'user'); local $SIG{__WARN__} = sub { - $current_lei ? err($current_lei, @_) : syslog('warning', "@_"); + $current_lei ? err($current_lei, @_) : warn( + strftime('%Y-%m-%dT%H:%M:%SZ', gmtime(time))," $$ ", @_); }; - my $on_destroy = PublicInbox::OnDestroy->new($$, sub { - syslog('crit', "$@") if $@; - }); open STDERR, '>&STDIN' or die "redirect stderr failed: $!"; open STDOUT, '>&STDIN' or die "redirect stdout failed: $!"; # $daemon pipe to `lei' closed, main loop begins: PublicInbox::DS->EventLoop; - @$on_destroy = (); # cancel on_destroy if we get here exit($exit_code // 0); } @@ -1008,6 +1058,7 @@ sub oneshot { local %PATH2CFG; umask(077) // die("umask(077): $!"); my $self = bless { + oneshot => 1, 0 => *STDIN{GLOB}, 1 => *STDOUT{GLOB}, 2 => *STDERR{GLOB},