X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLEI.pm;h=e6f763e1067869e0a7c6d3bb8a90e2b544f45e0d;hb=7fc6e30aeab9925bece4bb00f88bb91af5646aa2;hp=475af8f00899f9cd20f5f7e449280be56f783156;hpb=cc276aa9548186cd82b59cd2c8d178010ab8c79d;p=public-inbox.git diff --git a/lib/PublicInbox/LEI.pm b/lib/PublicInbox/LEI.pm index 475af8f0..e6f763e1 100644 --- a/lib/PublicInbox/LEI.pm +++ b/lib/PublicInbox/LEI.pm @@ -23,18 +23,20 @@ use PublicInbox::Sigfd; use PublicInbox::DS qw(now dwaitpid); use PublicInbox::Spawn qw(spawn popen_rd); use PublicInbox::Lock; +use PublicInbox::Eml; 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, $oldset); -my ($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: @@ -64,32 +66,43 @@ sub opt_dash ($$) { ($spec, '<>' => $cb, $GLP_PASS) # for Getopt::Long } -sub rel2abs ($$) { +# rel2abs preserves symlinks in parent, unlike abs_path +sub rel2abs { my ($self, $p) = @_; - return $p if index($p, '/') == 0; # already absolute + 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}; + my $cwd; if (defined $pwd) { - my $cwd = $self->{3} // getcwd() // die "getcwd(PWD=$pwd): $!"; + my $xcwd = $self->{3} // + ($cwd = getcwd() // die "getcwd(PWD=$pwd): $!"); if (my @st_pwd = stat($pwd)) { - my @st_cwd = stat($cwd) or die "stat($cwd): $!"; + my @st_cwd = stat($xcwd) or die "stat($xcwd): $!"; "@st_pwd[1,0]" eq "@st_cwd[1,0]" or - $self->{env}->{PWD} = $pwd = $cwd; + $self->{env}->{PWD} = $pwd = undef; } else { # PWD was invalid - delete $self->{env}->{PWD}; - undef $pwd; + $self->{env}->{PWD} = $pwd = undef; } } - $pwd //= $self->{env}->{PWD} = getcwd() // die "getcwd(PWD=$pwd): $!"; + $pwd //= $self->{env}->{PWD} = $cwd // getcwd() // die "getcwd: $!"; File::Spec->rel2abs($p, $pwd); } -sub store_path ($) { +# abs_path resolves symlinks in parent iff all parents exist +sub abs_path { Cwd::abs_path($_[1]) // rel2abs(@_) } + +sub share_path ($) { # $HOME/.local/share/lei/$FOO my ($self) = @_; rel2abs($self, ($self->{env}->{XDG_DATA_HOME} // ($self->{env}->{HOME} // '/nonexistent').'/.local/share') - .'/lei/store'); + .'/lei'); } +sub store_path ($) { share_path($_[0]) . '/store' } + sub _config_path ($) { my ($self) = @_; rel2abs($self, ($self->{env}->{XDG_CONFIG_HOME} // @@ -104,6 +117,12 @@ 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 { @@ -115,7 +134,7 @@ 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) } @@ -124,6 +143,23 @@ 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 ] @@ -131,15 +167,32 @@ 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-as=s output|mfolder|o=s format|f=s dedupe|d=s threads|t+ + 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+), @c_opt, - opt_dash('limit|n=i', '[0-9]+') ], + 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 ], + +'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+ + 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 ], +'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 @@ -148,48 +201,69 @@ our %CMD = ( # sorted in order of importance/use: '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 ], -'ls-query' => [ '[FILTER...]', 'list saved search queries', - qw(name-only format|f=s), @c_opt ], -'rm-query' => [ 'QUERY_NAME', 'remove a saved search', @c_opt ], -'mv-query' => [ qw(OLD_NAME NEW_NAME), 'rename a saved search', @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 ], +'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 ], 'tag' => [ 'KEYWORDS...', 'set/unset keywords and/or labels on message(s)', - qw(stdin| in-format|F=s input|i=s@ oid=s@ mid=s@), @c_opt, + 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', qw(exact! all jobs:i indexed), @c_opt ], -'add-watch' => [ 'LOCATION', 'watch for new messages and flag changes', - qw(import! kw|keywords|flags! 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', 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 - lock=s@ in-format|F=s kw|keywords|flags! verbose|v+), @c_opt ], + 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|keywords|flags!), @c_opt ], + 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', "use a patch to generate a query for `lei q --stdin'", qw(stdin| want|w=s@ uri debug), @c_opt ], @@ -197,6 +271,9 @@ 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 ], + 'init' => [ '[DIRNAME]', sub { "initialize storage, default: ".store_path($_[0]); }, @c_opt ], @@ -206,13 +283,12 @@ 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') ], @@ -236,8 +312,11 @@ my %OPTDESC = ( 'lock=s@' => [ 'METHOD|dotlock|fcntl|flock|none', 'mbox(5) locking method(s) to use (default: fcntl,dotlock)' ], +'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', 'mail!' => 'do not look in mail storage for OID', @@ -246,10 +325,13 @@ 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-as=s' => ['NAME', 'save a search terms by given name'], +'save' => "save a search for `lei up'", 'import-remote!' => 'do not memoize remote messages into local store', 'type=s' => [ 'any|mid|git', 'disambiguate type' ], @@ -274,6 +356,7 @@ 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'], @@ -288,7 +371,7 @@ 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', @@ -307,7 +390,12 @@ my %OPTDESC = ( 'jobs|j=i add-external' => 'set parallelism when indexing after --mirror', 'in-format|F=s' => $stdin_formats, -'format|f=s ls-query' => $ls_format, +'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' => $ls_format, 'limit|n=i@' => ['NUM', 'limit on number of matches (default: 10000)' ], @@ -324,6 +412,8 @@ my %OPTDESC = ( 'remote' => 'limit operations to those requiring network access', 'remote!' => 'prevent operations requiring network access', +'all:s up' => ['local', 'update all (local) saved searches' ], + 'mid=s' => 'specify the Message-ID of a message', 'oid=s' => 'specify the git object ID of a message', @@ -336,7 +426,7 @@ my %OPTDESC = ( 'by-mid|mid:s' => [ 'MID', 'match only by Message-ID, ignoring contents' ], -'kw|keywords|flags!' => 'disable/enable importing flags', +'kw!' => 'disable/enable importing keywords (aka "flags")', # xargs, env, use "-0", git(1) uses "-z". We support z|0 everywhere 'z|0' => 'use NUL \\0 instead of newline (CR) to delimit lines', @@ -348,11 +438,18 @@ my %CONFIG_KEYS = ( 'leistore.dir' => 'top-level storage location', ); -my @WQ_KEYS = qw(lxs l2m imp mrr cnv p2q tag sol); # internal workers +my @WQ_KEYS = qw(lxs l2m ikw pmd wq1 lne); # internal workers sub _drop_wq { my ($self) = @_; - for my $wq (grep(defined, delete(@$self{@WQ_KEYS}))) { $wq->DESTROY } + 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->DESTROY; + } } # pronounced "exit": x_it(1 << 8) => exit(1); x_it(13) => SIGPIPE @@ -361,21 +458,11 @@ 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); - } + stop_pager($self); + if ($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 } @@ -411,9 +498,10 @@ 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; } @@ -432,18 +520,17 @@ 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); } @@ -452,19 +539,15 @@ sub _lei_atfork_child { # we need to explicitly close things which are on stack if ($persist) { chdir '/' or die "chdir(/): $!"; - my @io = delete @$self{qw(0 1 2 sock)}; - unless ($self->{oneshot}) { - close($_) for @io; - } + 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 $!"; + STDERR->autoflush(1); } - for (delete @$self{qw(3 old_1 au_done)}) { - close($_) if defined($_); - } + close($_) for (grep(defined, delete @$self{qw(3 old_1 au_done)})); if (my $op_c = delete $self->{pkt_op_c}) { close(delete $op_c->{sock}); } @@ -473,9 +556,14 @@ sub _lei_atfork_child { } close $listener if $listener; undef $listener; + $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 + $SIG{__WARN__} = PublicInbox::Eml::warn_ignore_cb(); $current_lei = $persist ? undef : $self; # for SIG{__WARN__} } @@ -484,8 +572,8 @@ 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 { @@ -497,18 +585,26 @@ sub pkt_op_pair { $end; } +sub incr { + my ($self, $field, $nr) = @_; + $self->{counters}->{$field} += $nr; +} + sub workers_start { - my ($lei, $wq, $ident, $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->{''} //= [ \&dclose, $lei ]; + $ops->{''} //= [ $wq->can('_lei_wq_eof') || \&wq_eof, $lei ]; my $end = $lei->pkt_op_pair; - $wq->wq_workers_start($ident, $jobs, $lei->oldset, { lei => $lei }); + my $ident = $wq->{-wq_ident} // "lei-$lei->{cmd} worker"; + $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 = (); @@ -516,6 +612,15 @@ 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); @@ -568,7 +673,15 @@ 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; @@ -637,6 +750,7 @@ sub lazy_cb ($$$) { sub dispatch { my ($self, $cmd, @argv) = @_; 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 @@ -654,11 +768,7 @@ 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 @@ -676,10 +786,12 @@ 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) { @@ -693,14 +805,15 @@ sub _lei_cfg ($;$) { $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); - bless $cfg, 'PublicInbox::Config'; + my $cfg = PublicInbox::Config->git_config_dump($f); $cfg->{-st} = $cur_st; $cfg->{'-f'} = $f; if ($sto && File::Spec->canonpath($sto_dir // store_path($self)) eq File::Spec->canonpath($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 @@ -709,11 +822,13 @@ 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); @@ -835,16 +950,11 @@ sub start_mua { @cmd = map { $_ eq '%f' ? ($replaced = $mfolder) : $_ } @cmd; } push @cmd, $mfolder unless defined($replaced); - if (my $sock = $self->{sock}) { # lei(1) client process runs it - send($sock, exec_buf(\@cmd, {}), MSG_EOR); - } elsif ($self->{oneshot}) { - my $pid = fork // die "fork: $!"; - if ($pid > 0) { # original process - exec(@cmd); - warn "exec @cmd: $!\n"; - POSIX::_exit(1); - } - POSIX::setsid() > 0 or die "setsid: $!"; + if ($self->{sock}) { # lei(1) client process runs it + # 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, {}); } if ($self->{lxs} && $self->{au_done}) { # kick wait_startq syswrite($self->{au_done}, 'q' x ($self->{lxs}->{jobs} // 0)); @@ -865,14 +975,11 @@ 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.$$"}->{spawn($cmd)} = $cmd; - } + send($sock, exec_buf($cmd, {}), MSG_EOR) if $sock; } else { err($self, "W: unsupported --alert=$op"); # non-fatal } @@ -922,9 +1025,6 @@ sub start_pager { if ($self->{sock}) { # lei(1) process runs it delete @$new_env{keys %$env}; # only set iff unset send_exec_cmd($self, [ @$rdr{0..2} ], [$pager], $new_env); - } elsif ($self->{oneshot}) { - my $cmd = [$pager]; - $self->{"pid.$self.$$"}->{spawn($cmd, $new_env, $rdr)} = $cmd; } else { die 'BUG: start_pager w/o socket'; } @@ -960,9 +1060,8 @@ sub accept_dispatch { # Listener {post_accept} callback open($self->{$i++}, '+<&=', $fd) and next; send($sock, "open(+<&=$fd) (FD=$i): $!", MSG_EOR); } - return if scalar(@fds) != 4; + $i == 4 or return send($sock, 'not enough FDs='.($i-1), MSG_EOR) } - $self->{2}->autoflush(1); # keep stdout buffered until x_it|DESTROY # $ENV_STR = join('', map { "\0$_=$ENV{$_}" } keys %ENV); # $buf = "$argc\0".join("\0", @ARGV).$ENV_STR."\0\0"; substr($buf, -2, 2, '') eq "\0\0" or # s/\0\0\z// @@ -983,7 +1082,7 @@ 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 } @@ -1007,6 +1106,7 @@ sub event_step { } die "unrecognized client signal: $buf"; } + _drop_wq($self); # EOF, client disconnected dclose($self); }; if (my $err = $@) { @@ -1017,10 +1117,11 @@ sub event_step { sub event_step_init { my ($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); - } + $sock; + }; } sub noop {} @@ -1036,12 +1137,59 @@ sub dump_and_clear_log { } } +sub cfg2lei ($) { + 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 /: $!"; + chdir($lei->{3}) or die "chdir /': $!"; + my ($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 { + local %ENV = %{$cfg->{-env}}; + 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}; + } +} + # lei(1) calls this when it can't connect 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; @@ -1057,7 +1205,6 @@ 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): $!"; @@ -1075,7 +1222,7 @@ sub lazy_start { (Socket::MsgHdr || Inline::C) missing/unconfigured (narg=$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); @@ -1085,17 +1232,17 @@ sub lazy_start { 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); 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; $lis->close; # DS::close PublicInbox::DS->SetLoopTimeout(1000); }; @@ -1113,9 +1260,13 @@ sub lazy_start { local @SIG{keys %$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 to hit PostLoopCallback set below + dir_idle_handler($_[0]) if $_[0]->fullname ne $path; + }, 1); + if ($sigfd) { + undef $sigfd; # unref, already in DS::DescriptorMap } else { # wake up every second to accept signals if we don't # have signalfd or IO::KQueue: @@ -1164,34 +1315,103 @@ sub lazy_start { sub busy { 1 } # prevent daemon-shutdown if client is connected -# for users w/o Socket::Msghdr installed or Inline::C enabled -sub oneshot { - my ($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 $self = bless { - oneshot => 1, - 0 => *STDIN{GLOB}, - 1 => *STDOUT{GLOB}, - 2 => *STDERR{GLOB}, - env => \%ENV - }, __PACKAGE__; - dispatch($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.$$"} or return; - waitpid($_, 0) for keys %$oneshot_pids; - $? = $err if $err; # preserve ->fail or ->x_it code + # preserve $? for ->fail or ->x_it code +} + +sub wq_done_wait { # dwaitpid callback + my ($arg, $pid) = @_; + my ($wq, $lei) = @$arg; + my $err_type = $lei->{-err_type}; + $? and $lei->child_error($?, + $err_type ? "$err_type errors during $lei->{cmd}" : ()); + $lei->dclose; +} + +sub fchdir { + my ($lei) = @_; + my $dh = $lei->{3} // die 'BUG: lei->{3} (CWD) gone'; + chdir($dh) || $lei->fail("fchdir: $!"); +} + +sub wq_eof { # EOF callback for main daemon + my ($lei) = @_; + my $wq1 = delete $lei->{wq1} // return $lei->fail; # already failed + $wq1->wq_wait_old(\&wq_done_wait, $lei); +} + +sub watch_state_ok ($) { + my ($state) = $_[-1]; # $_[0] may be $self + $state =~ /\Apause|(?:import|index|tag)-(?:ro|rw)\z/; +} + +sub cancel_maildir_watch ($$) { + my ($d, $cfg_f) = @_; + my $w = delete $MDIR2CFGPATH->{$d}->{$cfg_f}; + scalar(keys %{$MDIR2CFGPATH->{$d}}) or + delete $MDIR2CFGPATH->{$d}; + for my $x (@{$w // []}) { $x->cancel } +} + +sub refresh_watches { + my ($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; + my $lw = $watches->{$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 = File::Spec->canonpath($1); + if ($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 { # TODO: imap/nntp/jmap + $lei->child_error(1, + "E: watch $url not supported, yet"); + } + } + if ($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 = File::Spec->canonpath($1); + cancel_maildir_watch($d, $cfg_f); + } else { # TODO: imap/nntp/jmap + $lei->child_error(1, "E: watch $url TODO"); + } + } + } + if (scalar keys %$watches) { + $cfg->{-env} //= { %{$lei->{env}}, PWD => '/' }; # for cfg2lei + } else { + delete $cfg->{-watches}; + } } 1;