X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLEI.pm;h=def85ef11112d8a8659afa91e1b67474e7e4c87a;hb=ee355020415fbbebbeb8fbe79be4e4f3fa2e657b;hp=c8d2f315b72b02da5dbed1f205fdab074649e24d;hpb=bfe6a3e13c286d60a5bfa46cef7625f83ae0ca18;p=public-inbox.git diff --git a/lib/PublicInbox/LEI.pm b/lib/PublicInbox/LEI.pm index c8d2f315..def85ef1 100644 --- a/lib/PublicInbox/LEI.pm +++ b/lib/PublicInbox/LEI.pm @@ -24,18 +24,22 @@ use PublicInbox::DS qw(now 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, $dir_idle); -my ($recv_cmd, $send_cmd); +our ($current_lei, $errors_log, $listener, $oldset, $dir_idle, + $recv_cmd, $send_cmd); my $GLP = Getopt::Long::Parser->new; $GLP->configure(qw(gnu_getopt no_ignore_case auto_abbrev)); my $GLP_PASS = Getopt::Long::Parser->new; $GLP_PASS->configure(qw(gnu_getopt no_ignore_case auto_abbrev pass_through)); our %PATH2CFG; # persistent for socket daemon +our $MDIR2CFGPATH; # /path/to/maildir => { /path/to/config => [ ino watches ] } # TBD: this is a documentation mechanism to show a subcommand # (may) pass options through to another command: @@ -93,6 +97,12 @@ sub rel2abs { # abs_path resolves symlinks in parent iff all parents exist sub abs_path { Cwd::abs_path($_[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, ($self->{env}->{XDG_DATA_HOME} // @@ -116,6 +126,12 @@ sub cache_dir ($) { .'/lei'); } +sub url_folder_cache { + my ($self) = @_; + require PublicInbox::SharedKV; # URI => updated_at_sec_ + PublicInbox::SharedKV->new(cache_dir($self).'/uri_folder'); +} + sub ale { my ($self) = @_; $self->{ale} //= do { @@ -127,14 +143,14 @@ sub ale { 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=s@ + import-remote!); # we don't support -C as an alias for --find-copies since it's already # used for chdir @@ -159,43 +175,46 @@ 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+ - 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 ], +'up' => [ 'OUTPUT...|--all', 'update saved search', + qw(jobs|j=s lock=s@ alert=s@ mua=s verbose|v+ + remote-fudge-time=s all:s), @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 ], + @diff_opt, @lxs_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 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 ], 'forget-external' => [ 'LOCATION...|--prune', 'exclude further results from a publicinbox|extindex', qw(prune), @c_opt ], @@ -206,28 +225,28 @@ 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 + 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') ], -'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 ], + @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', - qw(import! kw! interval=s recursive|r - exclude=s include=s), @c_opt ], +'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(format|f=s z), @c_opt ], + qw(l z|0), @c_opt ], 'pause-watch' => [ '[WATCH_NUMBER_OR_FILTER]', qw(all local remote), @c_opt ], 'resume-watch' => [ '[WATCH_NUMBER_OR_FILTER]', qw(all local remote), @c_opt ], 'forget-watch' => [ '{WATCH_NUMBER|--prune}', 'stop and forget a watch', @@ -235,23 +254,24 @@ 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 + 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 ], +'refresh-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 ], + 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 ], + @net_opt, @c_opt ], 'p2q' => [ 'FILE|COMMIT_OID|--stdin', "use a patch to generate a query for `lei q --stdin'", qw(stdin| want|w=s@ uri debug), @c_opt ], @@ -259,8 +279,8 @@ our %CMD = ( # sorted in order of importance/use: '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 ], +'inspect' => [ 'ITEMS...|--stdin', 'inspect lei/store and/or local external', + qw(stdin| pretty ascii dir=s), @c_opt ], 'init' => [ '[DIRNAME]', sub { "initialize storage, default: ".store_path($_[0]); @@ -271,13 +291,12 @@ 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') ], @@ -314,12 +333,13 @@ 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', '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' ], @@ -344,6 +364,7 @@ my %OPTDESC = ( "or\xa0`-'\x{a0}for\x{a0}stdout)" ], 'mua=s' => [ 'CMD', "MUA to run on --output Maildir or mbox (e.g.\xa0`mutt\xa0-f\xa0%f')" ], +'new-only import' => 'only import new messages from IMAP source', 'inbox-version=i' => [ 'NUM|1|2', 'force a public-inbox version with --mirror'], @@ -358,7 +379,7 @@ 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', @@ -380,6 +401,9 @@ my %OPTDESC = ( 'format|f=s ls-search' => ['OUT|json|jsonl|concatjson', 'listing output format' ], 'l ls-search' => 'long listing format', +'l ls-watch' => 'long listing format', +'l ls-mail-source' => 'long listing format', +'url ls-mail-source' => 'show full URL of newsgroup or IMAP folder', 'format|f=s ls-external' => $ls_format, 'limit|n=i@' => ['NUM', 'limit on number of matches (default: 10000)' ], @@ -396,7 +420,9 @@ my %OPTDESC = ( 'remote' => 'limit operations to those requiring network access', 'remote!' => 'prevent operations requiring network access', -'all:s up' => ['local', 'update all (local) saved searches' ], +'all:s up' => ['local|remote', 'update all remote or local saved searches' ], +'remote-fudge-time=s' => [ 'INTERVAL', + 'look for mail INTERVAL older than the last successful query' ], 'mid=s' => 'specify the Message-ID of a message', 'oid=s' => 'specify the git object ID of a message', @@ -422,7 +448,7 @@ my %CONFIG_KEYS = ( 'leistore.dir' => 'top-level storage location', ); -my @WQ_KEYS = qw(lxs l2m wq1); # internal workers +my @WQ_KEYS = qw(lxs l2m ikw pmd wq1 lne); # internal workers sub _drop_wq { my ($self) = @_; @@ -441,22 +467,13 @@ sub x_it ($$) { my ($self, $code) = @_; # make sure client sees stdout before exit $self->{1}->autoflush(1) if $self->{1}; - dump_and_clear_log(); - if (my $s = $self->{pkt_op_p} // $self->{sock}) { - send($s, "x_it $code", MSG_EOR); - } elsif ($self->{oneshot}) { - # don't want to end up using $? from child processes - _drop_wq($self); - # cleanup anything that has tempfiles or open file handles - %PATH2CFG = (); - delete @$self{qw(ovv dedupe sto cfg)}; - if (my $signum = ($code & 127)) { # usually SIGPIPE (13) - $SIG{PIPE} = 'DEFAULT'; # $SIG{$signum} doesn't work - kill $signum, $$; - sleep(1) while 1; # wait for signal - } else { - $quit->($code >> 8); - } + stop_pager($self); + if ($self->{pkt_op_p}) { # worker => lei-daemon + $self->{pkt_op_p}->pkt_do('x_it', $code); + } elsif ($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($code >> 8); } # else ignore if client disconnected } @@ -473,6 +490,12 @@ sub err ($;@) { 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, $msg); +} + sub fail_handler ($;$$) { my ($lei, $code, $io) = @_; close($io) if $io; # needed to avoid warnings on SIGPIPE @@ -492,9 +515,10 @@ sub sigint_reap { sub fail ($$;$) { my ($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}; + # calls fail_handler + $self->{pkt_op_p}->pkt_do('!') if $self->{pkt_op_p}; x_it($self, ($exit_code // 1) << 8); undef; } @@ -512,19 +536,21 @@ sub puts ($;@) { out(shift, map { "$_\n" } @_) } sub child_error { # passes non-fatal curl exit codes to user my ($self, $child_error, $msg) = @_; # child_error is $? + $child_error ||= 1 << 8; $self->err($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 { # 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->{$fd})); # explicit close silences Perl warning - send($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); } @@ -535,7 +561,7 @@ sub _lei_atfork_child { chdir '/' or die "chdir(/): $!"; close($_) for (grep(defined, delete @$self{qw(0 1 2 sock)})); if (my $cfg = $self->{cfg}) { - delete $cfg->{-lei_store}; + delete @$cfg{qw(-lei_store -watches -lei_note_event)}; } } else { # worker, Net::NNTP (Net::Cmd) uses STDERR directly open STDERR, '+>&='.fileno($self->{2}) or warn "open $!"; @@ -550,8 +576,10 @@ sub _lei_atfork_child { } close $listener if $listener; undef $listener; - undef $dir_idle; + $dir_idle->force_close if $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 @@ -564,8 +592,8 @@ 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 { @@ -577,19 +605,29 @@ sub pkt_op_pair { $end; } +sub incr { + my ($self, $field, $nr) = @_; + $self->{counters}->{$field} += $nr; +} + +sub pkt_ops { + my ($lei, $ops) = @_; + $ops->{'!'} = [ \&fail_handler, $lei ]; + $ops->{'|'} = [ \&sigpipe_handler, $lei ]; + $ops->{x_it} = [ \&x_it, $lei ]; + $ops->{child_error} = [ \&child_error, $lei ]; + $ops->{incr} = [ \&incr, $lei ]; + $ops; +} + sub workers_start { - my ($lei, $wq, $jobs, $ops) = @_; - $ops = { - '!' => [ \&fail_handler, $lei ], - '|' => [ \&sigpipe_handler, $lei ], - 'x_it' => [ \&x_it, $lei ], - 'child_error' => [ \&child_error, $lei ], - ($ops ? %$ops : ()), - }; + my ($lei, $wq, $jobs, $ops, $flds) = @_; + $ops = pkt_ops($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 = (); @@ -597,6 +635,15 @@ 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); @@ -649,7 +696,15 @@ sub optparse ($$$) { my $ok; for my $o (@or) { if ($o =~ /\A--([a-z0-9\-]+)/) { - $ok = defined($OPT->{$1}); + my $sw = $1; + # assume pipe/regular file on stdin + # w/o args means stdin + if ($sw eq 'stdin' && !@$argv && + (-p $self->{0} || + -f _) && -r _) { + $OPT->{stdin} //= 1; + } + $ok = defined($OPT->{$sw}); last if $ok; } elsif (defined($argv->[$i])) { $ok = 1; @@ -717,9 +772,10 @@ sub lazy_cb ($$$) { sub dispatch { my ($self, $cmd, @argv) = @_; + fchdir($self) or return; + 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') { @@ -736,11 +792,7 @@ sub dispatch { next if $d eq ''; # same as git(1) chdir $d or return fail($self, "cd $d: $!"); } - if (delete $self->{3}) { # update cwd for rel2abs - opendir my $dh, '.' or - return fail($self, "opendir . $!"); - $self->{3} = $dh; - } + open $self->{3}, '.' or return fail($self, "open . $!"); } $cb->($self, @argv); } elsif (grep(/\A-/, $cmd, @argv)) { # --help or -h only @@ -758,30 +810,34 @@ sub _lei_cfg ($;$) { my $f = _config_path($self); my @st = stat($f); my $cur_st = @st ? pack('dd', $st[10], $st[7]) : ''; # 10:ctime, 7:size - my ($sto, $sto_dir); + my ($sto, $sto_dir, $watches, $lne); if (my $cfg = $PATH2CFG{$f}) { # reuse existing object in common case return ($self->{cfg} = $cfg) if $cur_st eq $cfg->{-st}; - ($sto, $sto_dir) = @$cfg{qw(-lei_store leistore.dir)}; + ($sto, $sto_dir, $watches, $lne) = + @$cfg{qw(-lei_store leistore.dir -watches + -lei_note_event)}; } if (!@st) { unless ($creat) { 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; + $cfg->{-watches} = $watches if $watches; } if (scalar(keys %PATH2CFG) > 5) { # FIXME: use inotify/EVFILT_VNODE to detect unlinked configs @@ -790,11 +846,13 @@ sub _lei_cfg ($;$) { } } $self->{cfg} = $PATH2CFG{$f} = $cfg; + refresh_watches($self); + $cfg; } sub _lei_store ($;$) { my ($self, $creat) = @_; - my $cfg = _lei_cfg($self, $creat); + my $cfg = _lei_cfg($self, $creat) // return; $cfg->{-lei_store} //= do { require PublicInbox::LeiStore; my $dir = $cfg->{'leistore.dir'} // store_path($self); @@ -903,6 +961,9 @@ sub exec_buf ($$) { sub start_mua { my ($self) = @_; + if ($self->{ovv}->{fmt} =~ /\A(?:maildir)\z/) { # TODO: IMAP + refresh_watches($self); + } my $mua = $self->{opt}->{mua} // return; my $mfolder = $self->{ovv}->{dst}; my (@cmd, $replaced); @@ -917,21 +978,10 @@ sub start_mua { } push @cmd, $mfolder unless defined($replaced); if ($self->{sock}) { # lei(1) client process runs it - # restore terminal: echo $query | lei q -stdin --mua=... + # restore terminal: echo $query | lei q --stdin --mua=... my $io = []; $io->[0] = $self->{1} if $self->{opt}->{stdin} && -t $self->{1}; send_exec_cmd($self, $io, \@cmd, {}); - } elsif ($self->{oneshot}) { - my $pid = fork // die "fork: $!"; - if ($pid > 0) { # original process - if ($self->{opt}->{stdin} && -t STDOUT) { - open STDIN, '+<&', \*STDOUT or die "dup2: $!"; - } - exec(@cmd); - warn "exec @cmd: $!\n"; - POSIX::_exit(1); - } - POSIX::setsid() > 0 or die "setsid: $!"; } if ($self->{lxs} && $self->{au_done}) { # kick wait_startq syswrite($self->{au_done}, 'q' x ($self->{lxs}->{jobs} // 0)); @@ -952,14 +1002,11 @@ sub send_exec_cmd { # tell script/lei to execute a command sub poke_mua { # forces terminal MUAs to wake up and hopefully notice new mail my ($self) = @_; my $alerts = $self->{opt}->{alert} // return; + my $sock = $self->{sock}; while (my $op = shift(@$alerts)) { if ($op eq ':WINCH') { # hit the process group that started the MUA - if ($self->{sock}) { - send($self->{sock}, '-WINCH', MSG_EOR); - } elsif ($self->{oneshot}) { - kill('-WINCH', $$); - } + 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.$$"}->{spawn($cmd)} = $cmd; - } + send($sock, exec_buf($cmd, {}), MSG_EOR) if $sock; } else { err($self, "W: unsupported --alert=$op"); # non-fatal } @@ -995,13 +1038,15 @@ sub path_to_fd { # caller needs to "-t $self->{1}" to check if tty sub start_pager { - my ($self) = @_; + my ($self, $new_env) = @_; my $fh = popen_rd([qw(git var GIT_PAGER)]); chomp(my $pager = <$fh> // ''); close($fh) or warn "`git var PAGER' error: \$?=$?"; return if $pager eq 'cat' || $pager eq ''; - my $new_env = { LESS => 'FRX', LV => '-c' }; - $new_env->{MORE} = 'FRX' if $^O eq 'freebsd'; + $new_env //= {}; + $new_env->{LESS} //= 'FRX'; + $new_env->{LV} //= '-c'; + $new_env->{MORE} = $new_env->{LESS} if $^O eq 'freebsd'; pipe(my ($r, $wpager)) or return warn "pipe: $!"; my $rdr = { 0 => $r, 1 => $self->{1}, 2 => $self->{2} }; my $pgr = [ undef, @$rdr{1, 2} ]; @@ -1009,9 +1054,6 @@ sub start_pager { if ($self->{sock}) { # lei(1) process runs it delete @$new_env{keys %$env}; # only set iff unset send_exec_cmd($self, [ @$rdr{0..2} ], [$pager], $new_env); - } elsif ($self->{oneshot}) { - my $cmd = [$pager]; - $self->{"pid.$self.$$"}->{spawn($cmd, $new_env, $rdr)} = $cmd; } else { die 'BUG: start_pager w/o socket'; } @@ -1021,12 +1063,23 @@ sub start_pager { $self->{pgr} = $pgr; } +# display a message for user before spawning full-screen $VISUAL +sub pgr_err { + my ($self, @msg) = @_; + return $self->err(@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} = $pgr->[1]; } sub accept_dispatch { # Listener {post_accept} callback @@ -1056,20 +1109,15 @@ sub accept_dispatch { # Listener {post_accept} callback my ($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) }; + send($sock, $@, MSG_EOR) if $@; } sub dclose { my ($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 } @@ -1093,6 +1141,7 @@ sub event_step { } die "unrecognized client signal: $buf"; } + _drop_wq($self); # EOF, client disconnected dclose($self); }; if (my $err = $@) { @@ -1103,10 +1152,11 @@ sub event_step { sub event_step_init { my ($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 {} @@ -1115,10 +1165,57 @@ 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', $l) } + closelog(); # don't share across fork + } +} + +sub cfg2lei ($) { + my ($cfg) = @_; + my $lei = bless { env => { %{$cfg->{-env}} } }, __PACKAGE__; + 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 /: $!"; + my ($x, $y); + socketpair($x, $y, AF_UNIX, SOCK_SEQPACKET, 0) or die "socketpair: $!"; + $lei->{sock} = $x; + require PublicInbox::LeiSelfSocket; + PublicInbox::LeiSelfSocket->new($y); # adds to event loop + $lei; +} + +sub dir_idle_handler ($) { # PublicInbox::DirIdle callback + my ($ev) = @_; # Linux::Inotify2::Event or duck type + 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; + for my $f (keys %{$MDIR2CFGPATH->{$mdir} // {}}) { + my $cfg = $PATH2CFG{$f} // next; + eval { + my $lei = cfg2lei($cfg); + $lei->dispatch('note-event', + "maildir:$mdir", $nc, $bn, $fn); + }; + warn "E note-event $f: $@\n" if $@; + } + } + if ($ev->can('cancel') && ($ev->IN_IGNORE || $ev->IN_UNMOUNT)) { + $ev->cancel; + } + if ($fn =~ m!\A(.+)/(?:new|cur)\z! && !-e $fn) { + delete $MDIR2CFGPATH->{$1}; + } + if (!-e $fn) { # config file or Maildir gone + for my $cfgpaths (values %$MDIR2CFGPATH) { + delete $cfgpaths->{$fn}; + } + delete $PATH2CFG{$fn}; } } @@ -1143,7 +1240,6 @@ sub lazy_start { } 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): $!"; @@ -1165,12 +1261,13 @@ 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; $0 = "lei-daemon $path"; local %PATH2CFG; + local $MDIR2CFGPATH; $listener->blocking(0); my $exit_code; my $pil = PublicInbox::Listener->new($listener, \&accept_dispatch); @@ -1178,6 +1275,7 @@ 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; @@ -1200,8 +1298,8 @@ sub lazy_start { local $SIG{PIPE} = 'IGNORE'; 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 $path; + # just rely on wakeup to hit PostLoopCallback set below + dir_idle_handler($_[0]) if $_[0]->fullname ne $path; }, 1); if ($sigfd) { undef $sigfd; # unref, already in DS::DescriptorMap @@ -1247,35 +1345,28 @@ 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->EventLoop }; + warn "event loop error: $@\n" if $@; + dump_and_clear_log(); exit($exit_code // 0); } 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}; + $self->child_error(0, "$nr $k messages"); + } + } $self->{1}->autoflush(1) if $self->{1}; stop_pager($self); - my $err = $?; - my $oneshot_pids = delete $self->{"pid.$self.$$"} or return; - waitpid($_, 0) for keys %$oneshot_pids; - $? = $err if $err; # preserve ->fail or ->x_it code + dump_and_clear_log(); + # preserve $? for ->fail or ->x_it code } sub wq_done_wait { # dwaitpid callback @@ -1287,10 +1378,130 @@ sub wq_done_wait { # dwaitpid callback $lei->dclose; } +sub fchdir { + my ($lei) = @_; + my $dh = $lei->{3} // die 'BUG: lei->{3} (CWD) gone'; + chdir($dh) || $lei->fail("fchdir: $!"); +} + sub wq_eof { # EOF callback for main daemon my ($lei) = @_; my $wq1 = delete $lei->{wq1} // return $lei->fail; # already failed $wq1->wq_wait_old(\&wq_done_wait, $lei); } +sub watch_state_ok ($) { + my ($state) = $_[-1]; # $_[0] may be $self + $state =~ /\Apause|(?:import|index|tag)-(?:ro|rw)\z/; +} + +sub cancel_maildir_watch ($$) { + my ($d, $cfg_f) = @_; + my $w = delete $MDIR2CFGPATH->{$d}->{$cfg_f}; + scalar(keys %{$MDIR2CFGPATH->{$d}}) or + delete $MDIR2CFGPATH->{$d}; + 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) = @_; + my $cfg = _lei_cfg($lei) or return; + my $old = $cfg->{-watches}; + my $watches = $cfg->{-watches} //= {}; + my %seen; + my $cfg_f = $cfg->{'-f'}; + for my $w (grep(/\Awatch\..+\.state\z/, keys %$cfg)) { + my $url = substr($w, length('watch.'), -length('.state')); + require PublicInbox::LeiWatch; + $watches->{$url} //= PublicInbox::LeiWatch->new($url); + $seen{$url} = undef; + my $state = $cfg->get_1("watch.$url", 'state'); + if (!watch_state_ok($state)) { + $lei->err("watch.$url.state=$state not supported"); + next; + } + if ($url =~ /\Amaildir:(.+)/i) { + my $d = canonpath_harder($1); + if ($state eq 'pause') { + cancel_maildir_watch($d, $cfg_f); + } else { + add_maildir_watch($d, $cfg_f); + } + } else { # TODO: imap/nntp/jmap + $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 + for my $url (keys %$old) { + next if exists $seen{$url}; + delete $old->{$url}; + if ($url =~ /\Amaildir:(.+)/i) { + my $d = canonpath_harder($1); + cancel_maildir_watch($d, $cfg_f); + } else { # TODO: imap/nntp/jmap + $lei->child_error(0, "E: watch $url TODO"); + } + } + } + if (scalar keys %$watches) { + $cfg->{-env} //= { %{$lei->{env}}, PWD => '/' }; # for cfg2lei + } else { + delete $cfg->{-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, $rw) = @_; + my $sto = $lei->{sto} // _lei_store($lei) // return; + require PublicInbox::LeiMailSync; + my $f = "$sto->{priv_eidx}->{topdir}/mail_sync.sqlite3"; + (-f $f || $rw) ? PublicInbox::LeiMailSync->new($f) : undef; +} + +sub sto_done_request { + my ($lei, $sock) = @_; + eval { + if ($sock //= $lei->{sock}) { # issue, async wait + $lei->{sto}->wq_io_do('done', [ $sock ]); + } else { # forcibly wait + my $wait = $lei->{sto}->wq_do('done'); + } + }; + $lei->err($@) if $@; +} + 1;