X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLEI.pm;h=833d9c4dde67f2d7c88159c22d6084c8748360db;hb=26c426cf6fd9a3f44f11fa30e4824aeac574a6a0;hp=7be68121d956958dd66dcb85c43844e0109e9c55;hpb=5ea3df7741fdb88ec9c10689934b4d775d61a3d6;p=public-inbox.git diff --git a/lib/PublicInbox/LEI.pm b/lib/PublicInbox/LEI.pm index 7be68121..833d9c4d 100644 --- a/lib/PublicInbox/LEI.pm +++ b/lib/PublicInbox/LEI.pm @@ -28,7 +28,7 @@ use Time::HiRes qw(stat); # ctime comparisons for config cache use File::Path qw(mkpath); use File::Spec; our $quit = \&CORE::exit; -our ($current_lei, $errors_log, $listener, $oldset); +our ($current_lei, $errors_log, $listener, $oldset, $dir_idle); my ($recv_cmd, $send_cmd); my $GLP = Getopt::Long::Parser->new; $GLP->configure(qw(gnu_getopt no_ignore_case auto_abbrev)); @@ -70,6 +70,7 @@ sub rel2abs { my ($self, $p) = @_; if (index($p, '/') == 0) { # already absolute $p =~ tr!/!/!s; # squeeze redundant slashes + chop($p) if substr($p, -1, 1) eq '/'; return $p; } my $pwd = $self->{env}->{PWD}; @@ -135,6 +136,23 @@ my @lxs_opt = (qw(remote! local! external! include|I=s@ exclude=s@ only=s@ import-remote! no-torsocks torsocks=s), PublicInbox::LeiQuery::curl_opt()); +# we don't support -C as an alias for --find-copies since it's already +# used for chdir +our @diff_opt = qw(unified|U=i output-indicator-new=s output-indicator-old=s + output-indicator-context=s indent-heuristic! + minimal patience histogram anchored=s@ diff-algorithm=s + color-moved:s color-moved-ws=s no-color-moved no-color-moved-ws + word-diff:s word-diff-regex=s color-words:s no-renames + rename-empty! check ws-error-highlight=s full-index binary + abbrev:i break-rewrites|B:s find-renames|M:s find-copies:s + find-copies-harder irreversible-delete|D l=i diff-filter=s + S=s G=s find-object=s pickaxe-all pickaxe-regex O=s R + relative:s text|a ignore-cr-at-eol ignore-space-at-eol + ignore-space-change|b ignore-all-space|w ignore-blank-lines + inter-hunk-context=i function-context|W exit-code ext-diff + no-ext-diff textconv! src-prefix=s dst-prefix=s no-prefix + line-prefix=s); + # we generate shell completion + help using %CMD and %OPTDESC, # see lei__complete() and PublicInbox::LeiHelp # command => [ positional_args, 1-line description, Getopt::Long option spec ] @@ -145,12 +163,12 @@ our %CMD = ( # sorted in order of importance/use: qw(save output|mfolder|o=s format|f=s dedupe|d=s threads|t+ sort|s=s reverse|r offset=i pretty jobs|j=s globoff|g augment|a import-before! lock=s@ rsyncable alert=s@ mua=s verbose|v+ - color! mail-sync!), @c_opt, opt_dash('limit|n=i', '[0-9]+') ], + shared color! mail-sync!), @c_opt, opt_dash('limit|n=i', '[0-9]+') ], 'up' => [ 'OUTPUT|--all', 'update saved search', qw(jobs|j=s lock=s@ alert=s@ mua=s verbose|v+ all:s), @c_opt ], -'lcat' => [ '--stdin|MSGID_OR_URL..', 'display local copy of message(s)', +'lcat' => [ '--stdin|MSGID_OR_URL...', 'display local copy of message(s)', 'stdin|', # /|\z/ must be first for lone dash # some of these options are ridiculous for lcat @lxs_opt, qw(output|mfolder|o=s format|f=s dedupe|d=s threads|t+ @@ -162,6 +180,12 @@ our %CMD = ( # sorted in order of importance/use: qw(git-dir=s@ cwd! verbose|v+ mail! oid-a|A=s path-a|a=s path-b|b=s), @lxs_opt, @c_opt ], +'rediff' => [ '--stdin|LOCATION...', + 'regenerate a diff with different options', + 'stdin|', # /|\z/ must be first for lone dash + qw(git-dir=s@ cwd! verbose|v+ color:s no-color), + @diff_opt, @lxs_opt, @c_opt ], + 'add-external' => [ 'LOCATION', 'add/set priority of a publicinbox|extindex for extra matches', qw(boost=i mirror=s no-torsocks torsocks=s inbox-version=i @@ -172,6 +196,8 @@ our %CMD = ( # sorted in order of importance/use: 'ls-label' => [ '', 'list labels', qw(z|0 stats:s), @c_opt ], 'ls-mail-sync' => [ '[FILTER]', 'list mail sync folders', qw(z|0 globoff|g invert-match|v local remote), @c_opt ], +'ls-mail-source' => [ 'URL', 'list IMAP or NNTP mail source folders', + qw(z|0 ascii l), @c_opt ], 'forget-external' => [ 'LOCATION...|--prune', 'exclude further results from a publicinbox|extindex', qw(prune), @c_opt ], @@ -182,7 +208,10 @@ our %CMD = ( # sorted in order of importance/use: qw(verbose|v+), @c_opt ], 'edit-search' => [ 'OUTPUT', "edit saved search via `git config --edit'", @c_opt ], - +'rm' => [ '--stdin|LOCATION...', + 'remove a message from the index and prevent reindexing', + 'stdin|', # /|\z/ must be first for lone dash + @c_opt ], 'plonk' => [ '--threads|--from=IDENT', 'exclude mail matching From: or threads from non-Message-ID searches', qw(stdin| threads|t from|f=s mid=s oid=s), @c_opt ], @@ -191,9 +220,6 @@ our %CMD = ( # sorted in order of importance/use: qw(stdin| in-format|F=s input|i=s@ oid=s@ mid=s@), qw(no-torsocks torsocks=s), PublicInbox::LeiQuery::curl_opt(), @c_opt, pass_through('-kw:foo for delete') ], -'forget' => [ '[--stdin|--oid=OID|--by-mid=MID]', - "exclude message(s) on stdin from `q' search results", - qw(stdin| oid=s exact by-mid|mid:s), @c_opt ], 'purge-mailsource' => [ 'LOCATION|--all', 'remove imported messages from IMAP, Maildirs, and MH', @@ -209,11 +235,23 @@ our %CMD = ( # sorted in order of importance/use: 'forget-watch' => [ '{WATCH_NUMBER|--prune}', 'stop and forget a watch', qw(prune), @c_opt ], +'index' => [ 'LOCATION...', 'one-time index from URL or filesystem', + qw(in-format|F=s kw! offset=i recursive|r exclude=s include|I=s + verbose|v+ incremental!), + PublicInbox::LeiQuery::curl_opt(), # mainly for --proxy= + @c_opt ], 'import' => [ 'LOCATION...|--stdin', 'one-time import/update from URL or filesystem', - qw(stdin| offset=i recursive|r exclude=s include|I=s + qw(stdin| offset=i recursive|r exclude=s include|I=s jobs=s new-only lock=s@ in-format|F=s kw! verbose|v+ incremental! mail-sync!), qw(no-torsocks torsocks=s), PublicInbox::LeiQuery::curl_opt(), @c_opt ], +'forget-mail-sync' => [ 'LOCATION...', + 'forget sync information for a mail folder', @c_opt ], +'prune-mail-sync' => [ 'LOCATION...|--all', + 'prune dangling sync data for a mail folder', 'all:s', @c_opt ], +'export-kw' => [ 'LOCATION...|--all', + 'one-time export of keywords of sync sources', + qw(all:s mode=s), @c_opt ], 'convert' => [ 'LOCATION...|--stdin', 'one-time conversion from URL or filesystem to another format', qw(stdin| in-format|F=s out-format|f=s output|mfolder|o=s lock=s@ kw!), @@ -237,13 +275,12 @@ our %CMD = ( # sorted in order of importance/use: 'daemon-pid' => [ '', 'show the PID of the lei-daemon' ], 'help' => [ '[SUBCOMMAND]', 'show help' ], -# XXX do we need this? -# 'git' => [ '[ANYTHING...]', 'git(1) wrapper', pass_through('git') ], - -'reorder-local-store-and-break-history' => [ '[REFNAME]', - 'rewrite git history in an attempt to improve compression', - qw(gc!), @c_opt ], - +# TODO +#'reorder-local-store-and-break-history' => [ '[REFNAME]', +# 'rewrite git history in an attempt to improve compression', +# qw(gc!), @c_opt ], +#'fuse-mount' => [ 'PATHNAME', 'expose lei/store as Maildir(s)', @c_opt ], +# # internal commands are prefixed with '_' '_complete' => [ '[...]', 'internal shell completion helper', pass_through('everything') ], @@ -270,6 +307,7 @@ my %OPTDESC = ( 'incremental! import' => 'import already seen IMAP and NNTP articles', 'globoff|g' => "do not match locations using '*?' wildcards ". "and\xa0'[]'\x{a0}ranges", +'invert-match|v' => 'select non-matching lines', 'color!' => 'disable color (for --format=text)', 'verbose|v+' => 'be more verbose', 'external!' => 'do not use externals', @@ -345,6 +383,7 @@ my %OPTDESC = ( 'format|f=s ls-search' => ['OUT|json|jsonl|concatjson', 'listing output format' ], 'l ls-search' => 'long listing format', +'l ls-mail-source' => 'long listing format', 'format|f=s ls-external' => $ls_format, 'limit|n=i@' => ['NUM', 'limit on number of matches (default: 10000)' ], @@ -387,7 +426,7 @@ my %CONFIG_KEYS = ( 'leistore.dir' => 'top-level storage location', ); -my @WQ_KEYS = qw(lxs l2m wq1); # internal workers +my @WQ_KEYS = qw(lxs l2m ikw pmd wq1); # internal workers sub _drop_wq { my ($self) = @_; @@ -407,21 +446,10 @@ sub x_it ($$) { # make sure client sees stdout before exit $self->{1}->autoflush(1) if $self->{1}; dump_and_clear_log(); - if (my $s = $self->{pkt_op_p} // $self->{sock}) { - send($s, "x_it $code", MSG_EOR); - } elsif ($self->{oneshot}) { - # don't want to end up using $? from child processes - _drop_wq($self); - # cleanup anything that has tempfiles or open file handles - %PATH2CFG = (); - delete @$self{qw(ovv dedupe sto cfg)}; - if (my $signum = ($code & 127)) { # usually SIGPIPE (13) - $SIG{PIPE} = 'DEFAULT'; # $SIG{$signum} doesn't work - kill $signum, $$; - sleep(1) while 1; # wait for signal - } else { - $quit->($code >> 8); - } + if ($self->{pkt_op_p}) { # to top lei-daemon + $self->{pkt_op_p}->pkt_do('x_it', $code); + } elsif ($self->{sock}) { # to lei(1) client + send($self->{sock}, "x_it $code", MSG_EOR); } # else ignore if client disconnected } @@ -457,9 +485,10 @@ sub sigint_reap { sub fail ($$;$) { my ($self, $buf, $exit_code) = @_; + $self->{failed}++; err($self, $buf) if defined $buf; # calls fail_handler: - send($self->{pkt_op_p}, '!', MSG_EOR) if $self->{pkt_op_p}; + $self->{pkt_op_p}->pkt_do('!') if $self->{pkt_op_p}; x_it($self, ($exit_code // 1) << 8); undef; } @@ -478,18 +507,17 @@ sub puts ($;@) { out(shift, map { "$_\n" } @_) } sub child_error { # passes non-fatal curl exit codes to user 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; + if ($self->{pkt_op_p}) { # to top lei-daemon + $self->{pkt_op_p}->pkt_do('child_error', $child_error); + } elsif ($self->{sock}) { # to lei(1) client + send($self->{sock}, "child_error $child_error", MSG_EOR); } # 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}; + $self->{pkt_op_p}->pkt_do('|') if $self->{pkt_op_p}; x_it($self, 13); } @@ -515,6 +543,7 @@ sub _lei_atfork_child { } close $listener if $listener; undef $listener; + undef $dir_idle; %PATH2CFG = (); undef $errors_log; $quit = \&CORE::exit; @@ -528,8 +557,8 @@ sub _delete_pkt_op { # OnDestroy callback to prevent leaks on die if (my $op = delete $self->{pkt_op_c}) { # in case of die $op->close; # PublicInbox::PktOp::close } - my $unclosed_after_die = delete($self->{pkt_op_p}) or return; - close $unclosed_after_die; + my $pkt_op_p = delete($self->{pkt_op_p}) or return; + close $pkt_op_p->{op_p}; } sub pkt_op_pair { @@ -541,19 +570,26 @@ sub pkt_op_pair { $end; } +sub incr { + my ($self, $field, $nr) = @_; + $self->{counters}->{$field} += $nr; +} + sub workers_start { - my ($lei, $wq, $jobs, $ops) = @_; + my ($lei, $wq, $jobs, $ops, $flds) = @_; $ops = { '!' => [ \&fail_handler, $lei ], '|' => [ \&sigpipe_handler, $lei ], 'x_it' => [ \&x_it, $lei ], 'child_error' => [ \&child_error, $lei ], + 'incr' => [ \&incr, $lei ], ($ops ? %$ops : ()), }; $ops->{''} //= [ $wq->can('_lei_wq_eof') || \&wq_eof, $lei ]; my $end = $lei->pkt_op_pair; my $ident = $wq->{-wq_ident} // "lei-$lei->{cmd} worker"; - $wq->wq_workers_start($ident, $jobs, $lei->oldset, { lei => $lei }); + $flds->{lei} = $lei; + $wq->wq_workers_start($ident, $jobs, $lei->oldset, $flds); delete $lei->{pkt_op_p}; my $op_c = delete $lei->{pkt_op_c}; @$end = (); @@ -561,6 +597,15 @@ sub workers_start { ($op_c, $ops); } +# call this when we're ready to wait on events and yield to other clients +sub wait_wq_events { + my ($lei, $op_c, $ops) = @_; + for my $wq (grep(defined, @$lei{qw(ikw pmd)})) { # auxiliary WQs + $wq->wq_close(1); + } + $op_c->{ops} = $ops; +} + sub _help { require PublicInbox::LeiHelp; PublicInbox::LeiHelp::call($_[0], $_[1], \%CMD, \%OPTDESC); @@ -613,7 +658,15 @@ sub optparse ($$$) { my $ok; for my $o (@or) { if ($o =~ /\A--([a-z0-9\-]+)/) { - $ok = defined($OPT->{$1}); + my $sw = $1; + # assume pipe/regular file on stdin + # w/o args means stdin + if ($sw eq 'stdin' && !@$argv && + (-p $self->{0} || + -f _) && -r _) { + $OPT->{stdin} //= 1; + } + $ok = defined($OPT->{$sw}); last if $ok; } elsif (defined($argv->[$i])) { $ok = 1; @@ -881,21 +934,10 @@ sub start_mua { } push @cmd, $mfolder unless defined($replaced); if ($self->{sock}) { # lei(1) client process runs it - # restore terminal: echo $query | lei q -stdin --mua=... + # restore terminal: echo $query | lei q --stdin --mua=... my $io = []; $io->[0] = $self->{1} if $self->{opt}->{stdin} && -t $self->{1}; send_exec_cmd($self, $io, \@cmd, {}); - } elsif ($self->{oneshot}) { - my $pid = fork // die "fork: $!"; - if ($pid > 0) { # original process - if ($self->{opt}->{stdin} && -t STDOUT) { - open STDIN, '+<&', \*STDOUT or die "dup2: $!"; - } - exec(@cmd); - warn "exec @cmd: $!\n"; - POSIX::_exit(1); - } - POSIX::setsid() > 0 or die "setsid: $!"; } if ($self->{lxs} && $self->{au_done}) { # kick wait_startq syswrite($self->{au_done}, 'q' x ($self->{lxs}->{jobs} // 0)); @@ -916,14 +958,11 @@ sub send_exec_cmd { # tell script/lei to execute a command sub poke_mua { # forces terminal MUAs to wake up and hopefully notice new mail my ($self) = @_; my $alerts = $self->{opt}->{alert} // return; + my $sock = $self->{sock}; while (my $op = shift(@$alerts)) { if ($op eq ':WINCH') { # hit the process group that started the MUA - if ($self->{sock}) { - send($self->{sock}, '-WINCH', MSG_EOR); - } elsif ($self->{oneshot}) { - kill('-WINCH', $$); - } + send($sock, '-WINCH', MSG_EOR) if $sock; } elsif ($op eq ':bell') { out($self, "\a"); } elsif ($op =~ /(?{sock}) { - send($s, exec_buf($cmd, {}), MSG_EOR); - } elsif ($self->{oneshot}) { - $self->{"pid.$self.$$"}->{spawn($cmd)} = $cmd; - } + send($sock, exec_buf($cmd, {}), MSG_EOR) if $sock; } else { err($self, "W: unsupported --alert=$op"); # non-fatal } @@ -973,9 +1008,6 @@ sub start_pager { if ($self->{sock}) { # lei(1) process runs it delete @$new_env{keys %$env}; # only set iff unset send_exec_cmd($self, [ @$rdr{0..2} ], [$pager], $new_env); - } elsif ($self->{oneshot}) { - my $cmd = [$pager]; - $self->{"pid.$self.$$"}->{spawn($cmd, $new_env, $rdr)} = $cmd; } else { die 'BUG: start_pager w/o socket'; } @@ -1033,7 +1065,7 @@ sub accept_dispatch { # Listener {post_accept} callback sub dclose { my ($self) = @_; delete $self->{-progress}; - _drop_wq($self); + _drop_wq($self) if $self->{failed}; close(delete $self->{1}) if $self->{1}; # may reap_compress $self->close if $self->{-event_init_done}; # PublicInbox::DS::close } @@ -1067,10 +1099,11 @@ sub event_step { sub event_step_init { my ($self) = @_; - return if $self->{-event_init_done}++; - if (my $sock = $self->{sock}) { # using DS->EventLoop + my $sock = $self->{sock} or return; + $self->{-event_init_done} //= do { # persist til $ops done $self->SUPER::new($sock, EPOLLIN|EPOLLET); - } + $sock; + }; } sub noop {} @@ -1090,8 +1123,8 @@ sub dump_and_clear_log { sub lazy_start { my ($path, $errno, $narg) = @_; local ($errors_log, $listener); - ($errors_log) = ($path =~ m!\A(.+?/)[^/]+\z!); - $errors_log .= 'errors.log'; + my ($sock_dir) = ($path =~ m!\A(.+?)/[^/]+\z!); + $errors_log = "$sock_dir/errors.log"; my $addr = pack_sockaddr_un($path); my $lk = bless { lock_path => $errors_log }, 'PublicInbox::Lock'; $lk->lock_acquire; @@ -1125,7 +1158,7 @@ sub lazy_start { (Socket::MsgHdr || Inline::C) missing/unconfigured (narg=$narg); require PublicInbox::Listener; - require PublicInbox::EOFpipe; + require PublicInbox::PktOp; (-p STDOUT) or die "E: stdout must be a pipe\n"; open(STDIN, '+>>', $errors_log) or die "open($errors_log): $!"; STDIN->autoflush(1); @@ -1139,13 +1172,12 @@ sub lazy_start { my $exit_code; my $pil = PublicInbox::Listener->new($listener, \&accept_dispatch); local $quit = do { - pipe(my ($eof_r, $eof_w)) or die "pipe: $!"; - PublicInbox::EOFpipe->new($eof_r, \&noop, undef); + my (undef, $eof_p) = PublicInbox::PktOp->pair; sub { $exit_code //= shift; my $lis = $pil or exit($exit_code); - # closing eof_w triggers \&noop wakeup - $listener = $eof_w = $pil = $path = undef; + # closing eof_p triggers \&noop wakeup + $listener = $eof_p = $pil = $path = undef; $lis->close; # DS::close PublicInbox::DS->SetLoopTimeout(1000); }; @@ -1163,9 +1195,13 @@ sub lazy_start { local @SIG{keys %$sig} = values(%$sig) unless $sigfd; undef $sig; local $SIG{PIPE} = 'IGNORE'; - if ($sigfd) { # TODO: use inotify/kqueue to detect unlinked sockets - undef $sigfd; - PublicInbox::DS->SetLoopTimeout(5000); + require PublicInbox::DirIdle; + local $dir_idle = PublicInbox::DirIdle->new([$sock_dir], sub { + # just rely on wakeup ot hit PostLoopCallback set below + _dir_idle_handler(@_) if $_[0]->fullname ne $path; + }, 1); + if ($sigfd) { + undef $sigfd; # unref, already in DS::DescriptorMap } else { # wake up every second to accept signals if we don't # have signalfd or IO::KQueue: @@ -1214,29 +1250,19 @@ sub lazy_start { sub busy { 1 } # prevent daemon-shutdown if client is connected -# for users w/o Socket::Msghdr installed or Inline::C enabled -sub oneshot { - my ($main_pkg) = @_; - my $exit = $main_pkg->can('exit'); # caller may override exit() - local $quit = $exit if $exit; - local %PATH2CFG; - umask(077) // die("umask(077): $!"); - my $self = bless { oneshot => 1, env => \%ENV }, __PACKAGE__; - for (0..2) { open($self->{$_}, '+<&=', $_) or die "open fd=$_: $!" } - dispatch($self, @ARGV); - x_it($self, $self->{child_error}) if $self->{child_error}; -} - # ensures stdout hits the FS before sock disconnects so a client # can immediately reread it sub DESTROY { my ($self) = @_; + if (my $counters = delete $self->{counters}) { + for my $k (sort keys %$counters) { + my $nr = $counters->{$k}; + $self->child_error(1 << 8, "$nr $k messages"); + } + } $self->{1}->autoflush(1) if $self->{1}; stop_pager($self); - my $err = $?; - my $oneshot_pids = delete $self->{"pid.$self.$$"} or return; - waitpid($_, 0) for keys %$oneshot_pids; - $? = $err if $err; # preserve ->fail or ->x_it code + # preserve $? for ->fail or ->x_it code } sub wq_done_wait { # dwaitpid callback @@ -1248,6 +1274,12 @@ sub wq_done_wait { # dwaitpid callback $lei->dclose; } +sub fchdir { + my ($lei) = @_; + my $dh = $lei->{3} // die 'BUG: lei->{3} (CWD) gone'; + chdir($dh) || $lei->fail("fchdir: $!"); +} + sub wq_eof { # EOF callback for main daemon my ($lei) = @_; my $wq1 = delete $lei->{wq1} // return $lei->fail; # already failed