X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FLEI.pm;h=9ab91714d0b8b725fdda3b92889b70574dce6b83;hp=52c551cf998b7561d3b4a9cec57aa957a9502b3f;hb=6b52fe53a1f9e69a6ecfce16216a1fa180e4645f;hpb=a1539672716f91acc67397a1a7d16e99df068931 diff --git a/lib/PublicInbox/LEI.pm b/lib/PublicInbox/LEI.pm index 52c551cf..9ab91714 100644 --- a/lib/PublicInbox/LEI.pm +++ b/lib/PublicInbox/LEI.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2020-2021 all contributors +# Copyright (C) all contributors # License: AGPL-3.0+ # Backend for `lei' (local email interface). Unlike the C10K-oriented @@ -12,21 +12,23 @@ 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(EPIPE EAGAIN EINTR ECONNREFUSED ENOENT ECONNRESET); +use Errno qw(EPIPE EAGAIN ECONNREFUSED ENOENT ECONNRESET); use Cwd qw(getcwd); use POSIX qw(strftime); use IO::Handle (); use Fcntl qw(SEEK_SET); use PublicInbox::Config; -use PublicInbox::Syscall qw(SFD_NONBLOCK EPOLLIN EPOLLET); -use PublicInbox::Sigfd; -use PublicInbox::DS qw(now dwaitpid); +use PublicInbox::Syscall qw(EPOLLIN); +use PublicInbox::DS qw(dwaitpid); use PublicInbox::Spawn qw(spawn popen_rd); use PublicInbox::Lock; use PublicInbox::Eml; +use PublicInbox::Import; +use PublicInbox::ContentHash qw(git_sha); use Time::HiRes qw(stat); # ctime comparisons for config cache use File::Path qw(mkpath); use File::Spec; +use Sys::Syslog qw(openlog syslog closelog); our $quit = \&CORE::exit; our ($current_lei, $errors_log, $listener, $oldset, $dir_idle, $recv_cmd, $send_cmd); @@ -75,25 +77,28 @@ sub rel2abs { return $p; } my $pwd = $self->{env}->{PWD}; - my $cwd; if (defined $pwd) { - my $xcwd = $self->{3} // - ($cwd = getcwd() // die "getcwd(PWD=$pwd): $!"); if (my @st_pwd = stat($pwd)) { - my @st_cwd = stat($xcwd) or die "stat($xcwd): $!"; + my @st_cwd = stat($self->{3}) or die "stat({3}): $!"; "@st_pwd[1,0]" eq "@st_cwd[1,0]" or $self->{env}->{PWD} = $pwd = undef; } else { # PWD was invalid $self->{env}->{PWD} = $pwd = undef; } } - $pwd //= $self->{env}->{PWD} = $cwd // getcwd() // die "getcwd: $!"; + $pwd //= $self->{env}->{PWD} = getcwd() // die "getcwd: $!"; File::Spec->rel2abs($p, $pwd); } # abs_path resolves symlinks in parent iff all parents exist sub abs_path { Cwd::abs_path($_[1]) // rel2abs(@_) } +sub canonpath_harder { + my $p = $_[-1]; # $_[0] may be self + $p = File::Spec->canonpath($p); + $p =~ m!(?:/*|\A)\.\.(?:/*|\z)! && -e $p ? Cwd::abs_path($p) : $p; +} + sub share_path ($) { # $HOME/.local/share/lei/$FOO my ($self) = @_; rel2abs($self, ($self->{env}->{XDG_DATA_HOME} // @@ -125,23 +130,24 @@ sub url_folder_cache { sub ale { my ($self) = @_; - $self->{ale} //= do { + $self->{ale} // do { require PublicInbox::LeiALE; - $self->_lei_cfg(1)->{ale} //= PublicInbox::LeiALE->new($self); + my $cfg = $self->_lei_cfg(1); + $self->{ale} = $cfg->{ale} //= PublicInbox::LeiALE->new($self); }; } sub index_opt { # TODO: drop underscore variants everywhere, they're undocumented qw(fsync|sync! jobs|j=i indexlevel|L=s compact - max_size|max-size=s sequential_shard|sequential-shard + max_size|max-size=s sequential-shard batch_size|batch-size=s skip-docdata) } my @c_opt = qw(c=s@ C=s@ quiet|q); -my @lxs_opt = (qw(remote! local! external! include|I=s@ exclude=s@ only=s@ - import-remote! no-torsocks torsocks=s), - PublicInbox::LeiQuery::curl_opt()); +my @net_opt = (qw(no-torsocks torsocks=s), PublicInbox::LeiQuery::curl_opt()); +my @lxs_opt = qw(remote! local! external! include|I=s@ exclude=s@ only|O=s@ + import-remote!); # we don't support -C as an alias for --find-copies since it's already # used for chdir @@ -166,74 +172,81 @@ our @diff_opt = qw(unified|U=i output-indicator-new=s output-indicator-old=s our %CMD = ( # sorted in order of importance/use: 'q' => [ '--stdin|SEARCH_TERMS...', 'search for messages matching terms', 'stdin|', # /|\z/ must be first for lone dash - @lxs_opt, - qw(save output|mfolder|o=s format|f=s dedupe|d=s threads|t+ + @lxs_opt, @net_opt, + 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+ 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 ], +'up' => [ 'OUTPUT...|--all', 'update saved search', + qw(jobs|j=s lock=s@ alert=s@ mua=s verbose|v+ exclude=s@ + remote-fudge-time=s all:s remote! local! external!), @net_opt, @c_opt ], '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+ + @lxs_opt, @net_opt, + qw(output|mfolder|o=s format|f=s dedupe|d=s threads|t+ sort|s=s reverse|r offset=i jobs|j=s globoff|g augment|a import-before! lock=s@ rsyncable alert=s@ mua=s verbose|v+ color!), @c_opt, opt_dash('limit|n=i', '[0-9]+') ], 'blob' => [ 'OID', 'show a git blob, reconstructing from mail if necessary', qw(git-dir=s@ cwd! verbose|v+ mail! oid-a|A=s path-a|a=s path-b|b=s), - @lxs_opt, @c_opt ], + @lxs_opt, @net_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 ], + qw(git-dir=s@ cwd! verbose|v+ color:s no-color drq:1 dequote-only:1), + @diff_opt, @lxs_opt, @net_opt, @c_opt ], + +'mail-diff' => [ '--stdin|LOCATION...', 'diff the contents of emails', + 'stdin|', # /|\z/ must be first for lone dash + qw(verbose|v+ in-format|F=s color:s no-color raw-header), + @diff_opt, @net_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 - verbose|v+), @c_opt, index_opt(), - PublicInbox::LeiQuery::curl_opt() ], + qw(boost=i mirror=s inbox-version=i epoch=s verbose|v+), + @c_opt, index_opt(), @net_opt ], 'ls-external' => [ '[FILTER]', 'list publicinbox|extindex locations', qw(format|f=s z|0 globoff|g invert-match|v local remote), @c_opt ], '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 url), @c_opt ], + qw(z|0 ascii l pretty url), @net_opt, @c_opt ], 'forget-external' => [ 'LOCATION...|--prune', 'exclude further results from a publicinbox|extindex', qw(prune), @c_opt ], 'ls-search' => [ '[PREFIX]', 'list saved search queries', qw(format|f=s pretty l ascii z|0), @c_opt ], -'forget-search' => [ 'OUTPUT', 'forget a saved search', - qw(verbose|v+), @c_opt ], +'forget-search' => [ 'OUTPUT...|--prune', 'forget a saved search', + qw(verbose|v+ prune:s), @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 ], + qw(in-format|F=s lock=s@), @net_opt, @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 ], 'tag' => [ 'KEYWORDS...', 'set/unset keywords and/or labels on message(s)', 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') ], + @net_opt, @c_opt, pass_through('-kw:foo for delete') ], 'purge-mailsource' => [ 'LOCATION|--all', 'remove imported messages from IMAP, Maildirs, and MH', qw(exact! all jobs:i indexed), @c_opt ], -'add-watch' => [ 'LOCATION', 'watch for new messages and flag changes', +'add-watch' => [ 'LOCATION...', 'watch for new messages and flag changes', qw(poll-interval=s state=s recursive|r), @c_opt ], +'rm-watch' => [ 'LOCATION...', 'remove specified watch(es)', + qw(recursive|r), @c_opt ], 'ls-watch' => [ '[FILTER...]', 'list active watches with numbers and status', qw(l z|0), @c_opt ], 'pause-watch' => [ '[WATCH_NUMBER_OR_FILTER]', qw(all local remote), @c_opt ], @@ -243,34 +256,34 @@ our %CMD = ( # sorted in order of importance/use: '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= + verbose|v+ incremental!), @net_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 jobs=s new-only + qw(stdin| offset=i recursive|r exclude=s include|I=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 ], + @net_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 ], +'refresh-mail-sync' => [ 'LOCATION...|--all', + 'prune dangling sync data for a mail folder', 'all:s', + @net_opt, @c_opt ], 'export-kw' => [ 'LOCATION...|--all', 'one-time export of keywords of sync sources', - qw(all:s mode=s), @c_opt ], + qw(all:s mode=s), @net_opt, @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!), - qw(no-torsocks torsocks=s), PublicInbox::LeiQuery::curl_opt(), @c_opt ], -'p2q' => [ 'FILE|COMMIT_OID|--stdin', + @net_opt, @c_opt ], +'p2q' => [ 'LOCATION_OR_COMMIT...|--stdin', "use a patch to generate a query for `lei q --stdin'", - qw(stdin| want|w=s@ uri debug), @c_opt ], + qw(stdin| in-format|F=s want|w=s@ uri debug), @net_opt, @c_opt ], 'config' => [ '[...]', sub { 'git-config(1) wrapper for '._config_path($_[0]); }, qw(config-file|system|global|file|f=s), # for conflict detection - qw(c=s@ C=s@), pass_through('git config') ], -'inspect' => [ 'ITEMS...', 'inspect lei/store and/or local external', - qw(pretty ascii dir=s), @c_opt ], + qw(edit|e c=s@ C=s@), pass_through('git config') ], +'inspect' => [ 'ITEMS...|--stdin', 'inspect lei/store and/or local external', + qw(stdin| pretty ascii dir|d=s), @c_opt ], 'init' => [ '[DIRNAME]', sub { "initialize storage, default: ".store_path($_[0]); @@ -323,13 +336,14 @@ my %OPTDESC = ( 'path-a|a=s' => 'pre-image pathname associated with OID', 'path-b|b=s' => 'post-image pathname associated with OID', 'git-dir=s@' => 'additional git repository to scan', -'dir=s inspect' => 'specify a inboxdir, extindex topdir or Xapian shard', +'dir|d=s inspect' => + 'specify a inboxdir, extindex topdir or Xapian shard', 'proxy=s' => [ 'PROTO://HOST[:PORT]', # shared with curl(1) "proxy for (e.g. `socks5h://0:9050')" ], 'torsocks=s' => ['VAL|auto|no|yes', 'whether or not to wrap git and curl commands with torsocks'], 'no-torsocks' => 'alias for --torsocks=no', -'save' => "save a search for `lei up'", +'save!' => "do not save a search for `lei up'", 'import-remote!' => 'do not memoize remote messages into local store', 'type=s' => [ 'any|mid|git', 'disambiguate type' ], @@ -341,6 +355,7 @@ my %OPTDESC = ( 'want|w=s@' => [ 'PREFIX|dfpost|dfn', # common ones in help... 'search prefixes to extract (default: dfpost7)' ], +'uri p2q' => [ 'URI escape output' ], 'alert=s@' => ['CMD,:WINCH,:bell,', 'run command(s) or perform ops when done writing to output ' . @@ -369,7 +384,7 @@ my %OPTDESC = ( 'do not index messages larger than SIZE (default: infinity)' ], 'batch_size|batch-size=s' => [ 'SIZE', 'flush changes to OS after given number of bytes (default: 1m)' ], -'sequential_shard|sequential-shard' => +'sequential-shard' => 'index Xapian shards sequentially for slow storage', 'skip-docdata' => 'drop compatibility w/ public-inbox <1.6 to save ~1.5% space', @@ -381,7 +396,7 @@ my %OPTDESC = ( 'exclude specified external(s) from search' ], 'include|I=s@ q' => [ 'LOCATION', 'include specified external(s) in search' ], -'only=s@ q' => [ 'LOCATION', +'only|O=s@ q' => [ 'LOCATION', 'only use specified external(s) for search' ], 'jobs=s q' => [ '[SEARCH_JOBS][,WRITER_JOBS]', 'control number of search and writer jobs' ], @@ -396,6 +411,9 @@ my %OPTDESC = ( 'url ls-mail-source' => 'show full URL of newsgroup or IMAP folder', 'format|f=s ls-external' => $ls_format, +'prune:s forget-search' => + ['TYPE|local|remote', 'prune all, remote or local folders' ], + 'limit|n=i@' => ['NUM', 'limit on number of matches (default: 10000)' ], 'offset=i' => ['OFF', 'search result offset (default: 0)'], @@ -410,7 +428,11 @@ my %OPTDESC = ( 'remote' => 'limit operations to those requiring network access', 'remote!' => 'prevent operations requiring network access', -'all:s up' => ['local', 'update all (local) saved searches' ], +# up, refresh-mail-sync, export-kw +'all:s' => ['TYPE|local|remote', 'all remote or local folders' ], + +'remote-fudge-time=s' => [ 'INTERVAL', + 'look for mail INTERVAL older than the last successful query' ], 'mid=s' => 'specify the Message-ID of a message', 'oid=s' => 'specify the git object ID of a message', @@ -436,16 +458,12 @@ my %CONFIG_KEYS = ( 'leistore.dir' => 'top-level storage location', ); -my @WQ_KEYS = qw(lxs l2m ikw pmd wq1 lne); # internal workers +my @WQ_KEYS = qw(lxs l2m ikw pmd wq1 lne v2w); # internal workers sub _drop_wq { my ($self) = @_; for my $wq (grep(defined, delete(@$self{@WQ_KEYS}))) { - if ($wq->wq_kill) { - $wq->wq_close(0, undef, $self); - } elsif ($wq->wq_kill_old) { - $wq->wq_wait_old(undef, $self); - } + $wq->wq_kill('-TERM'); $wq->DESTROY; } } @@ -453,14 +471,16 @@ sub _drop_wq { # pronounced "exit": x_it(1 << 8) => exit(1); x_it(13) => SIGPIPE sub x_it ($$) { my ($self, $code) = @_; + local $current_lei = $self; # make sure client sees stdout before exit $self->{1}->autoflush(1) if $self->{1}; - dump_and_clear_log(); stop_pager($self); - if ($self->{pkt_op_p}) { # to top lei-daemon + if ($self->{pkt_op_p}) { # worker => lei-daemon $self->{pkt_op_p}->pkt_do('x_it', $code); - } elsif ($self->{sock}) { # to lei(1) client + } elsif ($self->{sock}) { # lei->daemon => lei(1) client send($self->{sock}, "x_it $code", MSG_EOR); + } elsif ($quit == \&CORE::exit) { # an admin (one-shot) command + exit($code >> 8); } # else ignore if client disconnected } @@ -477,8 +497,15 @@ sub err ($;@) { sub qerr ($;@) { $_[0]->{opt}->{quiet} or err(shift, @_) } +sub qfin { # show message on finalization (LeiFinmsg) + my ($lei, $msg) = @_; + return if $lei->{opt}->{quiet}; + $lei->{fmsg} ? push(@{$lei->{fmsg}}, "$msg\n") : qerr($lei, $msg); +} + sub fail_handler ($;$$) { my ($lei, $code, $io) = @_; + local $current_lei = $lei; close($io) if $io; # needed to avoid warnings on SIGPIPE _drop_wq($lei); x_it($lei, $code // (1 << 8)); @@ -488,18 +515,12 @@ sub sigpipe_handler { # handles SIGPIPE from @WQ_KEYS workers fail_handler($_[0], 13, delete $_[0]->{1}); } -# PublicInbox::OnDestroy callback for SIGINT to take out the entire pgid -sub sigint_reap { - my ($pgid) = @_; - dwaitpid($pgid) if kill('-INT', $pgid); -} - sub fail ($$;$) { - my ($self, $buf, $exit_code) = @_; + my ($self, $msg, $exit_code) = @_; + local $current_lei = $self; $self->{failed}++; - err($self, $buf) if defined $buf; - # calls fail_handler: - $self->{pkt_op_p}->pkt_do('!') if $self->{pkt_op_p}; + warn(substr($msg, -1, 1) eq "\n" ? $msg : "$msg\n") if defined $msg; + $self->{pkt_op_p}->pkt_do('fail_handler') if $self->{pkt_op_p}; x_it($self, ($exit_code // 1) << 8); undef; } @@ -517,18 +538,22 @@ sub puts ($;@) { out(shift, map { "$_\n" } @_) } sub child_error { # passes non-fatal curl exit codes to user my ($self, $child_error, $msg) = @_; # child_error is $? - $self->err($msg) if $msg; + local $current_lei = $self; + $child_error ||= 1 << 8; + warn(substr($msg, -1, 1) eq "\n" ? $msg : "$msg\n") if defined $msg; if ($self->{pkt_op_p}) { # to top lei-daemon $self->{pkt_op_p}->pkt_do('child_error', $child_error); } elsif ($self->{sock}) { # to lei(1) client send($self->{sock}, "child_error $child_error", MSG_EOR); + } else { # non-lei admin command + $self->{child_error} ||= $child_error; } # else noop if client disconnected } sub note_sigpipe { # triggers sigpipe_handler my ($self, $fd) = @_; close(delete($self->{$fd})); # explicit close silences Perl warning - $self->{pkt_op_p}->pkt_do('|') if $self->{pkt_op_p}; + $self->{pkt_op_p}->pkt_do('sigpipe_handler') if $self->{pkt_op_p}; x_it($self, 13); } @@ -536,7 +561,8 @@ sub _lei_atfork_child { my ($self, $persist) = @_; # we need to explicitly close things which are on stack if ($persist) { - chdir '/' or die "chdir(/): $!"; + open $self->{3}, '<', '/' or die "open(/) $!"; + fchdir($self); close($_) for (grep(defined, delete @$self{qw(0 1 2 sock)})); if (my $cfg = $self->{cfg}) { delete @$cfg{qw(-lei_store -watches -lei_note_event)}; @@ -544,8 +570,10 @@ sub _lei_atfork_child { } else { # worker, Net::NNTP (Net::Cmd) uses STDERR directly open STDERR, '+>&='.fileno($self->{2}) or warn "open $!"; STDERR->autoflush(1); + POSIX::setpgid(0, $$) // die "setpgid(0, $$): $!"; } - close($_) for (grep(defined, delete @$self{qw(3 old_1 au_done)})); + close($_) for (grep(defined, delete @$self{qw(old_1 au_done)})); + delete $self->{-socks}; if (my $op_c = delete $self->{pkt_op_c}) { close(delete $op_c->{sock}); } @@ -554,14 +582,20 @@ sub _lei_atfork_child { } close $listener if $listener; undef $listener; + $dir_idle->force_close if $dir_idle; undef $dir_idle; %PATH2CFG = (); $MDIR2CFGPATH = {}; eval 'no warnings; undef $PublicInbox::LeiNoteEvent::to_flush'; undef $errors_log; $quit = \&CORE::exit; - $self->{-eml_noisy} or # only "lei import" sets this atm - $SIG{__WARN__} = PublicInbox::Eml::warn_ignore_cb(); + if (!$self->{-eml_noisy}) { # only "lei import" sets this atm + my $cb = $SIG{__WARN__} // \&CORE::warn; + $SIG{__WARN__} = sub { + $cb->(@_) unless PublicInbox::Eml::warn_ignore(@_) + }; + } + $SIG{TERM} = sub { exit(128 + 15) }; $current_lei = $persist ? undef : $self; # for SIG{__WARN__} } @@ -588,16 +622,22 @@ sub incr { $self->{counters}->{$field} += $nr; } +sub pkt_ops { + my ($lei, $ops) = @_; + $ops->{fail_handler} = [ $lei ]; + $ops->{sigpipe_handler} = [ $lei ]; + $ops->{x_it} = [ $lei ]; + $ops->{child_error} = [ $lei ]; + $ops->{incr} = [ $lei ]; + $ops; +} + sub workers_start { 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('net_merge_all_done') && $lei->{auth}) and + $lei->{auth}->op_merge($ops, $wq, $lei); + pkt_ops($lei, $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"; @@ -607,18 +647,29 @@ sub workers_start { my $op_c = delete $lei->{pkt_op_c}; @$end = (); $lei->event_step_init; + $wq->wq_wait_async($wq->can('_wq_done_wait') // \&wq_done_wait, $lei); ($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) = @_; + my $wq1 = $lei->{wq1}; + ($wq1 && $wq1->can('net_merge_all_done') && !$lei->{auth}) and + $wq1->net_merge_all_done; for my $wq (grep(defined, @$lei{qw(ikw pmd)})) { # auxiliary WQs - $wq->wq_close(1); + $wq->wq_close; } $op_c->{ops} = $ops; } +sub wq1_start { + my ($lei, $wq, $jobs) = @_; + my ($op_c, $ops) = workers_start($lei, $wq, $jobs // 1); + $lei->{wq1} = $wq; + wait_wq_events($lei, $op_c, $ops); # net_merge_all_done if !{auth} +} + sub _help { require PublicInbox::LeiHelp; PublicInbox::LeiHelp::call($_[0], $_[1], \%CMD, \%OPTDESC); @@ -747,9 +798,10 @@ sub lazy_cb ($$$) { sub dispatch { my ($self, $cmd, @argv) = @_; + fchdir($self); + local %ENV = %{$self->{env}}; local $current_lei = $self; # for __WARN__ $self->{2}->autoflush(1); # keep stdout buffered until x_it|DESTROY - dump_and_clear_log("from previous run\n"); return _help($self, 'no command given') unless defined($cmd); # do not support Getopt bundling for this while ($cmd eq '-C' || $cmd eq '-c') { @@ -766,7 +818,8 @@ sub dispatch { next if $d eq ''; # same as git(1) chdir $d or return fail($self, "cd $d: $!"); } - open $self->{3}, '.' or return fail($self, "open . $!"); + open $self->{3}, '<', '.' or + return fail($self, "open . $!"); } $cb->($self, @argv); } elsif (grep(/\A-/, $cmd, @argv)) { # --help or -h only @@ -796,18 +849,18 @@ sub _lei_cfg ($;$) { delete $self->{cfg}; return bless {}, 'PublicInbox::Config'; } - my (undef, $cfg_dir, undef) = File::Spec->splitpath($f); + my ($cfg_dir) = ($f =~ m!(.*?/)[^/]+\z!); -d $cfg_dir or mkpath($cfg_dir) or die "mkpath($cfg_dir): $!\n"; open my $fh, '>>', $f or die "open($f): $!\n"; @st = stat($fh) or die "fstat($f): $!\n"; $cur_st = pack('dd', $st[10], $st[7]); qerr($self, "# $f created") if $self->{cmd} ne 'config'; } - my $cfg = PublicInbox::Config->git_config_dump($f); + my $cfg = PublicInbox::Config->git_config_dump($f, $self->{2}); $cfg->{-st} = $cur_st; $cfg->{'-f'} = $f; - if ($sto && File::Spec->canonpath($sto_dir // store_path($self)) - eq File::Spec->canonpath($cfg->{'leistore.dir'} // + if ($sto && canonpath_harder($sto_dir // store_path($self)) + eq canonpath_harder($cfg->{'leistore.dir'} // store_path($self))) { $cfg->{-lei_store} = $sto; $cfg->{-lei_note_event} = $lne; @@ -815,9 +868,7 @@ sub _lei_cfg ($;$) { } if (scalar(keys %PATH2CFG) > 5) { # FIXME: use inotify/EVFILT_VNODE to detect unlinked configs - for my $k (keys %PATH2CFG) { - delete($PATH2CFG{$k}) unless -f $k - } + delete(@PATH2CFG{grep(!-f, keys %PATH2CFG)}); } $self->{cfg} = $PATH2CFG{$f} = $cfg; refresh_watches($self); @@ -844,14 +895,6 @@ sub _config { waitpid(spawn($cmd, \%env, \%rdr), 0); } -sub lei_config { - my ($self, @argv) = @_; - $self->{opt}->{'config-file'} and return fail $self, - "config file switches not supported by `lei config'"; - _config(@_); - x_it($self, $?) if $?; -} - sub lei_daemon_pid { puts shift, $$ } sub lei_daemon_kill { @@ -935,6 +978,9 @@ sub exec_buf ($$) { sub start_mua { my ($self) = @_; + if ($self->{ovv}->{fmt} =~ /\A(?:maildir)\z/) { # TODO: IMAP + refresh_watches($self); + } my $mua = $self->{opt}->{mua} // return; my $mfolder = $self->{ovv}->{dst}; my (@cmd, $replaced); @@ -988,7 +1034,7 @@ sub poke_mua { # forces terminal MUAs to wake up and hopefully notice new mail $cmd = [ Text::ParseWords::shellwords($cmd) ]; send($sock, exec_buf($cmd, {}), MSG_EOR) if $sock; } else { - err($self, "W: unsupported --alert=$op"); # non-fatal + warn("W: unsupported --alert=$op\n"); # non-fatal } } } @@ -1009,13 +1055,15 @@ sub path_to_fd { # caller needs to "-t $self->{1}" to check if tty sub start_pager { - my ($self) = @_; + my ($self, $new_env) = @_; my $fh = popen_rd([qw(git var GIT_PAGER)]); chomp(my $pager = <$fh> // ''); close($fh) or warn "`git var PAGER' error: \$?=$?"; return if $pager eq 'cat' || $pager eq ''; - my $new_env = { LESS => 'FRX', LV => '-c' }; - $new_env->{MORE} = 'FRX' if $^O eq 'freebsd'; + $new_env //= {}; + $new_env->{LESS} //= 'FRX'; + $new_env->{LV} //= '-c'; + $new_env->{MORE} = $new_env->{LESS} 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} ]; @@ -1032,12 +1080,23 @@ sub start_pager { $self->{pgr} = $pgr; } +# display a message for user before spawning full-screen $VISUAL +sub pgr_err { + my ($self, @msg) = @_; + return warn(@msg) unless $self->{sock} && -t $self->{2}; + start_pager($self, { LESS => 'RX' }); # no 'F' so we prompt + print { $self->{2} } @msg; + $self->{2}->autoflush(1); + stop_pager($self); + send($self->{sock}, 'wait', MSG_EOR); # wait for user to quit pager +} + sub stop_pager { my ($self) = @_; my $pgr = delete($self->{pgr}) or return; $self->{2} = $pgr->[2]; - # do not restore original stdout, just close it so we error out close(delete($self->{1})) if $self->{1}; + $self->{1} = $pgr->[1]; } sub accept_dispatch { # Listener {post_accept} callback @@ -1067,21 +1126,16 @@ sub accept_dispatch { # Listener {post_accept} callback my ($argc, @argv) = split(/\0/, $buf, -1); undef $buf; my %env = map { split(/=/, $_, 2) } splice(@argv, $argc); - if (chdir($self->{3})) { - local %ENV = %env; - $self->{env} = \%env; - eval { dispatch($self, @argv) }; - send($sock, $@, MSG_EOR) if $@; - } else { - send($sock, "fchdir: $!", MSG_EOR); # implicit close - } + $self->{env} = \%env; + eval { dispatch($self, @argv) }; + $self->fail($@) if $@; } sub dclose { my ($self) = @_; + local $current_lei = $self; delete $self->{-progress}; _drop_wq($self) if $self->{failed}; - close(delete $self->{1}) if $self->{1}; # may reap_compress $self->close if $self->{-event_init_done}; # PublicInbox::DS::close } @@ -1089,23 +1143,31 @@ sub dclose { sub event_step { my ($self) = @_; local %ENV = %{$self->{env}}; - my $sock = $self->{sock}; local $current_lei = $self; eval { - while (my @fds = $recv_cmd->($sock, my $buf, 4096)) { - if (scalar(@fds) == 1 && !defined($fds[0])) { - return if $! == EAGAIN; - next if $! == EINTR; - last if $! == ECONNRESET; - die "recvmsg: $!"; - } - for my $fd (@fds) { - open my $rfh, '+<&=', $fd; + my @fds = $recv_cmd->($self->{sock} // return, my $buf, 4096); + if (scalar(@fds) == 1 && !defined($fds[0])) { + return if $! == EAGAIN; + die "recvmsg: $!" if $! != ECONNRESET; + $buf = ''; + @fds = (); # for open loop below: + } + for (@fds) { open my $rfh, '+<&=', $_ } + if ($buf eq '') { + _drop_wq($self); # EOF, client disconnected + dclose($self); + $buf = 'TERM'; + } + if ($buf =~ /\A(?:STOP|CONT|TERM)\z/) { + my $sig = "-$buf"; + for my $wq (grep(defined, @$self{@WQ_KEYS})) { + $wq->wq_kill($sig); } + } else { die "unrecognized client signal: $buf"; } - _drop_wq($self); # EOF, client disconnected - dclose($self); + my $s = $self->{-socks} // []; # lei up --all + @$s = grep { send($_, $buf, MSG_EOR) } @$s; }; if (my $err = $@) { eval { $self->fail($err) }; @@ -1116,9 +1178,10 @@ sub event_step { sub event_step_init { my ($self) = @_; my $sock = $self->{sock} or return; - $self->{-event_init_done} //= do { # persist til $ops done - $self->SUPER::new($sock, EPOLLIN|EPOLLET); - $sock; + $self->{-event_init_done} // do { # persist til $ops done + $sock->blocking(0); + $self->SUPER::new($sock, EPOLLIN); + $self->{-event_init_done} = $sock; }; } @@ -1128,10 +1191,12 @@ sub oldset { $oldset } sub dump_and_clear_log { if (defined($errors_log) && -s STDIN && seek(STDIN, 0, SEEK_SET)) { - my @pfx = @_; - unshift(@pfx, "$errors_log ") if @pfx; - warn @pfx, do { local $/; }; - truncate(STDIN, 0) or warn "ftruncate ($errors_log): $!"; + openlog('lei-daemon', 'pid,nowait,nofatal,ndelay', 'user'); + chomp(my @lines = ); + truncate(STDIN, 0) or + syslog('warning', "ftruncate (%s): %m", $errors_log); + for my $l (@lines) { syslog('warning', '%s', $l) } + closelog(); # don't share across fork } } @@ -1141,8 +1206,7 @@ sub cfg2lei ($) { open($lei->{0}, '<&', \*STDIN) or die "dup 0: $!"; open($lei->{1}, '>>&', \*STDOUT) or die "dup 1: $!"; open($lei->{2}, '>>&', \*STDERR) or die "dup 2: $!"; - open($lei->{3}, '/') or die "open /: $!"; - chdir($lei->{3}) or die "chdir /': $!"; + open($lei->{3}, '<', '/') or die "open /: $!"; my ($x, $y); socketpair($x, $y, AF_UNIX, SOCK_SEQPACKET, 0) or die "socketpair: $!"; $lei->{sock} = $x; @@ -1156,16 +1220,15 @@ sub dir_idle_handler ($) { # PublicInbox::DirIdle callback my $fn = $ev->fullname; if ($fn =~ m!\A(.+)/(new|cur)/([^/]+)\z!) { # Maildir file my ($mdir, $nc, $bn) = ($1, $2, $3); - $nc = '' if $ev->IN_DELETE; + $nc = '' if $ev->IN_DELETE || $ev->IN_MOVED_FROM; for my $f (keys %{$MDIR2CFGPATH->{$mdir} // {}}) { my $cfg = $PATH2CFG{$f} // next; eval { - local %ENV = %{$cfg->{-env}}; my $lei = cfg2lei($cfg); $lei->dispatch('note-event', "maildir:$mdir", $nc, $bn, $fn); }; - warn "E note-event $f: $@\n" if $@; + warn "E: note-event $f: $@\n" if $@; } } if ($ev->can('cancel') && ($ev->IN_IGNORE || $ev->IN_UNMOUNT)) { @@ -1190,6 +1253,7 @@ sub lazy_start { $errors_log = "$sock_dir/errors.log"; my $addr = pack_sockaddr_un($path); my $lk = bless { lock_path => $errors_log }, 'PublicInbox::Lock'; + umask(077) // die("umask(077): $!"); $lk->lock_acquire; socket($listener, AF_UNIX, SOCK_SEQPACKET, 0) or die "socket: $!"; if ($errno == ECONNREFUSED || $errno == ENOENT) { @@ -1201,9 +1265,7 @@ sub lazy_start { $! = $errno; # allow interpolation to stringify in die die "connect($path): $!"; } - umask(077) // die("umask(077): $!"); bind($listener, $addr) or die "bind($path): $!"; - listen($listener, 1024) or die "listen: $!"; $lk->lock_release; undef $lk; my @st = stat($path) or die "stat($path): $!"; @@ -1225,7 +1287,7 @@ sub lazy_start { (-p STDOUT) or die "E: stdout must be a pipe\n"; open(STDIN, '+>>', $errors_log) or die "open($errors_log): $!"; STDIN->autoflush(1); - dump_and_clear_log("from previous daemon process:\n"); + dump_and_clear_log(); POSIX::setsid() > 0 or die "setsid: $!"; my $pid = fork // die "fork: $!"; return if $pid; @@ -1239,6 +1301,7 @@ sub lazy_start { my (undef, $eof_p) = PublicInbox::PktOp->pair; sub { $exit_code //= shift; + eval 'PublicInbox::LeiNoteEvent::flush_task()'; my $lis = $pil or exit($exit_code); # closing eof_p triggers \&noop wakeup $listener = $eof_p = $pil = $path = undef; @@ -1255,23 +1318,12 @@ sub lazy_start { USR1 => \&noop, USR2 => \&noop, }; - my $sigfd = PublicInbox::Sigfd->new($sig, SFD_NONBLOCK); - local @SIG{keys %$sig} = values(%$sig) unless $sigfd; - undef $sig; - local $SIG{PIPE} = 'IGNORE'; require PublicInbox::DirIdle; - local $dir_idle = PublicInbox::DirIdle->new([$sock_dir], sub { + local $dir_idle = PublicInbox::DirIdle->new(sub { # just rely on wakeup to hit PostLoopCallback set below dir_idle_handler($_[0]) if $_[0]->fullname ne $path; - }, 1); - if ($sigfd) { - undef $sigfd; # unref, already in DS::DescriptorMap - } else { - # wake up every second to accept signals if we don't - # have signalfd or IO::KQueue: - PublicInbox::DS::sig_setmask($oldset); - PublicInbox::DS->SetLoopTimeout(1000); - } + }); + $dir_idle->add_watches([$sock_dir]); PublicInbox::DS->SetPostLoopCallback(sub { my ($dmap, undef) = @_; if (@st = defined($path) ? stat($path) : ()) { @@ -1285,11 +1337,10 @@ sub lazy_start { $quit->(); } return 1 if defined($path); - my $now = now(); my $n = 0; for my $s (values %$dmap) { $s->can('busy') or next; - if ($s->busy($now)) { + if ($s->busy) { ++$n; } else { $s->close; @@ -1308,7 +1359,11 @@ sub lazy_start { open STDERR, '>&STDIN' or die "redirect stderr failed: $!"; open STDOUT, '>&STDIN' or die "redirect stdout failed: $!"; # $daemon pipe to `lei' closed, main loop begins: - PublicInbox::DS->EventLoop; + eval { PublicInbox::DS::event_loop($sig, $oldset) }; + warn "event loop error: $@\n" if $@; + # exit() may trigger waitpid via various DESTROY, ensure interruptible + PublicInbox::DS::sig_setmask($oldset); + dump_and_clear_log(); exit($exit_code // 0); } @@ -1321,17 +1376,19 @@ sub DESTROY { if (my $counters = delete $self->{counters}) { for my $k (sort keys %$counters) { my $nr = $counters->{$k}; - $self->child_error(1 << 8, "$nr $k messages"); + $self->child_error(0, "$nr $k messages"); } } $self->{1}->autoflush(1) if $self->{1}; stop_pager($self); + dump_and_clear_log(); # preserve $? for ->fail or ->x_it code } sub wq_done_wait { # dwaitpid callback my ($arg, $pid) = @_; my ($wq, $lei) = @$arg; + local $current_lei = $lei; my $err_type = $lei->{-err_type}; $? and $lei->child_error($?, $err_type ? "$err_type errors during $lei->{cmd}" : ()); @@ -1341,13 +1398,13 @@ sub wq_done_wait { # dwaitpid callback sub fchdir { my ($lei) = @_; my $dh = $lei->{3} // die 'BUG: lei->{3} (CWD) gone'; - chdir($dh) || $lei->fail("fchdir: $!"); + chdir($dh) || die "fchdir: $!"; } sub wq_eof { # EOF callback for main daemon my ($lei) = @_; - my $wq1 = delete $lei->{wq1} // return $lei->fail; # already failed - $wq1->wq_wait_old(\&wq_done_wait, $lei); + local $current_lei = $lei; + delete $lei->{wq1} // return $lei->fail; # already failed } sub watch_state_ok ($) { @@ -1363,8 +1420,17 @@ sub cancel_maildir_watch ($$) { for my $x (@{$w // []}) { $x->cancel } } +sub add_maildir_watch ($$) { + my ($d, $cfg_f) = @_; + if (!exists($MDIR2CFGPATH->{$d}->{$cfg_f})) { + my @w = $dir_idle->add_watches(["$d/cur", "$d/new"], 1); + push @{$MDIR2CFGPATH->{$d}->{$cfg_f}}, @w if @w; + } +} + sub refresh_watches { my ($lei) = @_; + $dir_idle or return; my $cfg = _lei_cfg($lei) or return; my $old = $cfg->{-watches}; my $watches = $cfg->{-watches} //= {}; @@ -1373,25 +1439,41 @@ sub refresh_watches { for my $w (grep(/\Awatch\..+\.state\z/, keys %$cfg)) { my $url = substr($w, length('watch.'), -length('.state')); require PublicInbox::LeiWatch; - my $lw = $watches->{$url} //= PublicInbox::LeiWatch->new($url); + $watches->{$url} //= PublicInbox::LeiWatch->new($url); $seen{$url} = undef; - my $state = $cfg->get_1("watch.$url", 'state'); + my $state = $cfg->get_1("watch.$url.state"); if (!watch_state_ok($state)) { - $lei->err("watch.$url.state=$state not supported"); + warn("watch.$url.state=$state not supported\n"); next; } if ($url =~ /\Amaildir:(.+)/i) { - my $d = File::Spec->canonpath($1); + my $d = canonpath_harder($1); if ($state eq 'pause') { cancel_maildir_watch($d, $cfg_f); - } elsif (!exists($MDIR2CFGPATH->{$d}->{$cfg_f})) { - my @w = $dir_idle->add_watches( - ["$d/cur", "$d/new"], 1); - push @{$MDIR2CFGPATH->{$d}->{$cfg_f}}, @w if @w; + } else { + add_maildir_watch($d, $cfg_f); } } else { # TODO: imap/nntp/jmap - $lei->child_error(1, - "E: watch $url not supported, yet"); + $lei->child_error(0, "E: watch $url not supported, yet") + } + } + + # add all known Maildir folders as implicit watches + my $lms = $lei->lms; + if ($lms) { + $lms->lms_write_prepare; + for my $d ($lms->folders('maildir:')) { + substr($d, 0, length('maildir:')) = ''; + + # fixup old bugs while we're iterating: + my $cd = canonpath_harder($d); + my $f = "maildir:$cd"; + $lms->rename_folder("maildir:$d", $f) if $d ne $cd; + next if $watches->{$f}; # may be set to pause + require PublicInbox::LeiWatch; + $watches->{$f} = PublicInbox::LeiWatch->new($f); + $seen{$f} = undef; + add_maildir_watch($cd, $cfg_f); } } if ($old) { # cull old non-existent entries @@ -1399,10 +1481,10 @@ sub refresh_watches { next if exists $seen{$url}; delete $old->{$url}; if ($url =~ /\Amaildir:(.+)/i) { - my $d = File::Spec->canonpath($1); + my $d = canonpath_harder($1); cancel_maildir_watch($d, $cfg_f); } else { # TODO: imap/nntp/jmap - $lei->child_error(1, "E: watch $url TODO"); + $lei->child_error(0, "E: watch $url TODO"); } } } @@ -1413,4 +1495,51 @@ sub refresh_watches { } } +# TODO: support SHA-256 +sub git_oid { + my $eml = $_[-1]; + $eml->header_set($_) for @PublicInbox::Import::UNWANTED_HEADERS; + git_sha(1, $eml); +} + +sub lms { + my ($lei, $creat) = @_; + my $sto = $lei->{sto} // _lei_store($lei) // return; + require PublicInbox::LeiMailSync; + my $f = "$sto->{priv_eidx}->{topdir}/mail_sync.sqlite3"; + (-f $f || $creat) ? PublicInbox::LeiMailSync->new($f) : undef; +} + +sub sto_done_request { + my ($lei, $sock) = @_; + local $current_lei = $lei; + eval { + if ($sock //= $lei->{sock}) { # issue, async wait + $lei->{sto}->wq_io_do('done', [ $sock ]); + } else { # forcibly wait + my $wait = $lei->{sto}->wq_do('done'); + } + }; + warn($@) if $@; +} + +sub cfg_dump ($$) { + my ($lei, $f) = @_; + my $ret = eval { PublicInbox::Config->git_config_dump($f, $lei->{2}) }; + return $ret if !$@; + warn($@); + undef; +} + +sub request_umask { + my ($lei) = @_; + my $s = $lei->{sock} // return; + send($s, 'umask', MSG_EOR) // die "send: $!"; + vec(my $rvec = '', fileno($s), 1) = 1; + select($rvec, undef, undef, 2) or die 'timeout waiting for umask'; + recv($s, my $v, 5, 0) // die "recv: $!"; + (my $u, $lei->{client_umask}) = unpack('AV', $v); + $u eq 'u' or warn "E: recv $v has no umask"; +} + 1;