X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLEI.pm;h=ef72758c6d9a060ebe5813a7a8b0fbe8aca437a8;hb=4b9be88e2465ffcbf91901f06e19a749f6bdf818;hp=515bc2a3e121cf31f0d9bb8ea2774672484d5a74;hpb=3894c29d99646fcd315ca6794b65e32547fcbae2;p=public-inbox.git diff --git a/lib/PublicInbox/LEI.pm b/lib/PublicInbox/LEI.pm index 515bc2a3..ef72758c 100644 --- a/lib/PublicInbox/LEI.pm +++ b/lib/PublicInbox/LEI.pm @@ -22,12 +22,12 @@ use PublicInbox::Syscall qw(SFD_NONBLOCK EPOLLIN EPOLLET); use PublicInbox::Sigfd; use PublicInbox::DS qw(now dwaitpid); use PublicInbox::Spawn qw(spawn popen_rd); -use PublicInbox::OnDestroy; +use PublicInbox::Lock; 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, $listener); +our ($current_lei, $errors_log, $listener, $oldset); my ($recv_cmd, $send_cmd); my $GLP = Getopt::Long::Parser->new; $GLP->configure(qw(gnu_getopt no_ignore_case auto_abbrev)); @@ -64,32 +64,42 @@ 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 + 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} // @@ -97,6 +107,21 @@ sub _config_path ($) { .'/lei/config'); } +sub cache_dir ($) { + my ($self) = @_; + rel2abs($self, ($self->{env}->{XDG_CACHE_HOME} // + ($self->{env}->{HOME} // '/nonexistent').'/.cache') + .'/lei'); +} + +sub ale { + my ($self) = @_; + $self->{ale} //= do { + require PublicInbox::LeiALE; + $self->_lei_cfg(1)->{ale} //= PublicInbox::LeiALE->new($self); + }; +} + sub index_opt { # TODO: drop underscore variants everywhere, they're undocumented qw(fsync|sync! jobs|j=i indexlevel|L=s compact @@ -104,84 +129,107 @@ sub index_opt { 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()); + # 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 ] our %CMD = ( # sorted in order of importance/use: -'q' => [ '--stdin|SEARCH_TERMS...', 'search for messages matching terms', qw( - save-as=s output|mfolder|o=s format|f=s dedupe|d=s thread|t augment|a - sort|s=s reverse|r offset=i remote! local! external! pretty - include|I=s@ exclude=s@ only=s@ jobs|j=s globoff|g stdin| - mua-cmd|mua=s no-torsocks torsocks=s verbose|v+ quiet|q), - PublicInbox::LeiQuery::curl_opt(), opt_dash('limit|n=i', '[0-9]+') ], - -'show' => [ 'MID|OID', 'show a given object (Message-ID or object ID)', - qw(type=s solve! format|f=s dedupe|d=s thread|t remote local!), - pass_through('git show') ], +'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+ + 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]+') ], + +'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+), @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 ], 'add-external' => [ 'LOCATION', 'add/set priority of a publicinbox|extindex for extra matches', - qw(boost=i c=s@ mirror=s no-torsocks torsocks=s inbox-version=i), - qw(quiet|q verbose|v+), - index_opt(), PublicInbox::LeiQuery::curl_opt() ], -'ls-external' => [ '[FILTER...]', 'list publicinbox|extindex locations', - qw(format|f=s z|0 local remote quiet|q) ], + qw(boost=i mirror=s no-torsocks torsocks=s inbox-version=i + verbose|v+), @c_opt, index_opt(), + PublicInbox::LeiQuery::curl_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-sync' => [ '', 'list sync folders', + qw(z|0 z|0 globoff|g invert-match|v local remote), @c_opt ], 'forget-external' => [ 'LOCATION...|--prune', 'exclude further results from a publicinbox|extindex', - qw(prune quiet|q) ], - -'ls-query' => [ '[FILTER...]', 'list saved search queries', - qw(name-only format|f=s z) ], -'rm-query' => [ 'QUERY_NAME', 'remove a saved search' ], -'mv-query' => [ qw(OLD_NAME NEW_NAME), 'rename a saved search' ], - -'plonk' => [ '--thread|--from=IDENT', - 'exclude mail matching From: or thread from non-Message-ID searches', - qw(stdin| thread|t from|f=s mid=s oid=s) ], -'mark' => [ 'MESSAGE_FLAGS...', - 'set/unset keywords on message(s) from stdin', - qw(stdin| oid=s exact by-mid|mid:s) ], + 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 ], +'edit-search' => [ 'OUTPUT', "edit saved search via `git config --edit'", + @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, + 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 quiet|q) ], + 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) ], - -# code repos are used for `show' to solve blobs from patch mails -'add-coderepo' => [ 'DIRNAME', 'add or set priority of a git code repo', - qw(boost=i) ], -'ls-coderepo' => [ '[FILTER_TERMS...]', - 'list known code repos', qw(format|f=s z) ], -'forget-coderepo' => [ 'DIRNAME', - 'stop using repo to solve blobs from patches', - qw(prune) ], + 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) ], + qw(import! kw! interval=s recursive|r + exclude=s include=s), @c_opt ], 'ls-watch' => [ '[FILTER...]', 'list active watches with numbers and status', - qw(format|f=s z) ], -'pause-watch' => [ '[WATCH_NUMBER_OR_FILTER]', qw(all local remote) ], -'resume-watch' => [ '[WATCH_NUMBER_OR_FILTER]', qw(all local remote) ], + qw(format|f=s z), @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) ], + qw(prune), @c_opt ], 'import' => [ 'LOCATION...|--stdin', 'one-time import/update from URL or filesystem', qw(stdin| offset=i recursive|r exclude=s include|I=s - format|f=s kw|keywords|flags!), - ], - + lock=s@ in-format|F=s kw! verbose|v+ incremental! sync!), @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!), @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 ], 'config' => [ '[...]', sub { 'git-config(1) wrapper for '._config_path($_[0]); }, qw(config-file|system|global|file|f=s), # for conflict detection - pass_through('git config') ], + qw(c=s@ C=s@), pass_through('git config') ], +'inspect' => [ 'ITEMS...', 'inspect lei/store and/or local external', + qw(pretty ascii dir=s), @c_opt ], + 'init' => [ '[DIRNAME]', sub { - "initialize storage, default: "._store_path($_[0]); - }, qw(quiet|q) ], + "initialize storage, default: ".store_path($_[0]); + }, @c_opt ], 'daemon-kill' => [ '[-SIGNAL]', 'signal the lei-daemon', + # "-C DIR" conflicts with -CHLD, here, and chdir makes no sense, here opt_dash('signal|s=s', '[0-9]+|(?:[A-Z][A-Z0-9]+)') ], 'daemon-pid' => [ '', 'show the PID of the lei-daemon' ], 'help' => [ '[SUBCOMMAND]', 'show help' ], @@ -191,7 +239,7 @@ our %CMD = ( # sorted in order of importance/use: 'reorder-local-store-and-break-history' => [ '[REFNAME]', 'rewrite git history in an attempt to improve compression', - 'gc!' ], + qw(gc!), @c_opt ], # internal commands are prefixed with '_' '_complete' => [ '[...]', 'internal shell completion helper', @@ -210,42 +258,57 @@ my $ls_format = [ 'OUT|plain|json|null', 'listing output format' ]; # we use \x{a0} (non-breaking SP) to avoid wrapping in PublicInbox::LeiHelp my %OPTDESC = ( 'help|h' => 'show this built-in help', +'c=s@' => [ 'NAME=VALUE', 'set config option' ], +'C=s@' => [ 'DIR', 'chdir to specify to directory' ], 'quiet|q' => 'be quiet', +'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", 'verbose|v+' => 'be more verbose', -'solve!' => 'do not attempt to reconstruct blobs from emails', +'external!' => 'do not use externals', +'mail!' => 'do not look in mail storage for OID', +'cwd!' => 'do not look in git repo of current working directory', +'oid-a|A=s' => 'pre-image OID', +'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', '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' ], 'dedupe|d=s' => ['STRATEGY|content|oid|mid|none', 'deduplication strategy'], -'show thread|t' => 'display entire thread a message belongs to', -'q thread|t' => - 'return all messages in the same thread as the actual match(es)', +'threads|t+' => + 'return all messages in the same threads as the actual match(es)', + +'want|w=s@' => [ 'PREFIX|dfpost|dfn', # common ones in help... + 'search prefixes to extract (default: dfpost7)' ], + +'alert=s@' => ['CMD,:WINCH,:bell,', + 'run command(s) or perform ops when done writing to output ' . + '(default: ":WINCH,:bell" with --mua and Maildir/IMAP output, ' . + 'nothing otherwise)' ], + 'augment|a' => 'augment --output destination instead of clobbering', 'output|mfolder|o=s' => [ 'MFOLDER', "destination (e.g.\xa0`/path/to/Maildir', ". "or\xa0`-'\x{a0}for\x{a0}stdout)" ], -'mua-cmd|mua=s' => [ 'CMD', +'mua=s' => [ 'CMD', "MUA to run on --output Maildir or mbox (e.g.\xa0`mutt\xa0-f\xa0%f')" ], -'show format|f=s' => [ 'OUT|plain|raw|html|mboxrd|mboxcl2|mboxcl', - 'message/object output format' ], -'mark format|f=s' => $stdin_formats, -'forget format|f=s' => $stdin_formats, - -'add-external inbox-version=i' => [ 'NUM|1|2', +'inbox-version=i' => [ 'NUM|1|2', 'force a public-inbox version with --mirror'], -'add-external mirror=s' => [ 'URL', 'mirror a public-inbox'], +'mirror=s' => [ 'URL', 'mirror a public-inbox'], # public-inbox-index options -'add-external jobs|j=i' => 'set parallelism when indexing after --mirror', 'fsync!' => 'speed up indexing after --mirror, risk index corruption', 'compact' => 'run compact index after mirroring', 'indexlevel|L=s' => [ 'LEVEL|full|medium|basic', @@ -259,23 +322,24 @@ my %OPTDESC = ( 'skip-docdata' => 'drop compatibility w/ public-inbox <1.6 to save ~1.5% space', -'q format|f=s' => [ +'format|f=s q' => [ 'OUT|maildir|mboxrd|mboxcl2|mboxcl|mboxo|html|json|jsonl|concatjson', 'specify output format, default depends on --output'], -'q exclude=s@' => [ 'LOCATION', +'exclude=s@ q' => [ 'LOCATION', 'exclude specified external(s) from search' ], -'q include|I=s@' => [ 'LOCATION', +'include|I=s@ q' => [ 'LOCATION', 'include specified external(s) in search' ], -'q only=s@' => [ 'LOCATION', +'only=s@ q' => [ 'LOCATION', 'only use specified external(s) for search' ], - -'q jobs=s' => [ '[SEARCH_JOBS][,WRITER_JOBS]', +'jobs=s q' => [ '[SEARCH_JOBS][,WRITER_JOBS]', 'control number of search and writer jobs' ], +'jobs|j=i add-external' => 'set parallelism when indexing after --mirror', -'import format|f=s' => $stdin_formats, - -'ls-query format|f=s' => $ls_format, -'ls-external format|f=s' => $ls_format, +'in-format|F=s' => $stdin_formats, +'format|f=s ls-search' => ['OUT|json|jsonl|concatjson', + 'listing output format' ], +'l ls-search' => 'long listing format', +'format|f=s ls-external' => $ls_format, 'limit|n=i@' => ['NUM', 'limit on number of matches (default: 10000)' ], 'offset=i' => ['OFF', 'search result offset (default: 0)'], @@ -291,6 +355,8 @@ my %OPTDESC = ( 'remote' => 'limit operations to those requiring network access', 'remote!' => 'prevent operations requiring network access', +'all:s up' => ['local', 'update all (local) saved searches' ], + 'mid=s' => 'specify the Message-ID of a message', 'oid=s' => 'specify the git object ID of a message', @@ -303,7 +369,7 @@ my %OPTDESC = ( 'by-mid|mid:s' => [ 'MID', 'match only by Message-ID, ignoring contents' ], -'kw|keywords|flags!' => 'disable/enable importing flags', +'kw!' => 'disable/enable importing keywords (aka "flags")', # xargs, env, use "-0", git(1) uses "-z". We support z|0 everywhere 'z|0' => 'use NUL \\0 instead of newline (CR) to delimit lines', @@ -315,7 +381,12 @@ my %CONFIG_KEYS = ( 'leistore.dir' => 'top-level storage location', ); -my @WQ_KEYS = qw(lxs l2m imp mrr); # internal workers +my @WQ_KEYS = qw(lxs l2m imp mrr cnv p2q tag sol lsss); # internal workers + +sub _drop_wq { + my ($self) = @_; + for my $wq (grep(defined, delete(@$self{@WQ_KEYS}))) { $wq->DESTROY } +} # pronounced "exit": x_it(1 << 8) => exit(1); x_it(13) => SIGPIPE sub x_it ($$) { @@ -327,12 +398,10 @@ sub x_it ($$) { send($s, "x_it $code", MSG_EOR); } elsif ($self->{oneshot}) { # don't want to end up using $? from child processes - for my $f (@WQ_KEYS) { - my $wq = delete $self->{$f} or next; - $wq->DESTROY; - } - # cleanup anything that has tempfiles - delete @$self{qw(ovv dedupe)}; + _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, $$; @@ -358,12 +427,9 @@ sub qerr ($;@) { $_[0]->{opt}->{quiet} or err(shift, @_) } sub fail_handler ($;$$) { my ($lei, $code, $io) = @_; - for my $f (@WQ_KEYS) { - my $wq = delete $lei->{$f} or next; - $wq->wq_wait_old($lei) if $wq->wq_kill_old; # lei-daemon - } close($io) if $io; # needed to avoid warnings on SIGPIPE - $lei->x_it($code // (1 >> 8)); + _drop_wq($lei); + x_it($lei, $code // (1 << 8)); } sub sigpipe_handler { # handles SIGPIPE from @WQ_KEYS workers @@ -389,7 +455,7 @@ sub out ($;@) { my $self = shift; return if print { $self->{1} // return } @_; # likely return note_sigpipe($self, 1) if $! == EPIPE; - my $err = "error writing to stdout: $!"; + my $err = "error writing to output: $!"; delete $self->{1}; fail($self, $err); } @@ -414,18 +480,22 @@ sub note_sigpipe { # triggers sigpipe_handler x_it($self, 13); } -sub lei_atfork_child { +sub _lei_atfork_child { my ($self, $persist) = @_; # we need to explicitly close things which are on stack if ($persist) { - my @io = delete @$self{0,1,2}; + chdir '/' or die "chdir(/): $!"; + my @io = delete @$self{qw(0 1 2 sock)}; unless ($self->{oneshot}) { close($_) for @io; } - } else { - delete $self->{0}; + if (my $cfg = $self->{cfg}) { + delete $cfg->{-lei_store}; + } + } else { # worker, Net::NNTP (Net::Cmd) uses STDERR directly + open STDERR, '+>&='.fileno($self->{2}) or warn "open $!"; } - for (delete @$self{qw(3 sock old_1 au_done)}) { + for (delete @$self{qw(3 old_1 au_done)}) { close($_) if defined($_); } if (my $op_c = delete $self->{pkt_op_c}) { @@ -442,6 +512,43 @@ sub lei_atfork_child { $current_lei = $persist ? undef : $self; # for SIG{__WARN__} } +sub _delete_pkt_op { # OnDestroy callback to prevent leaks on die + my ($self) = @_; + 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 $unclosed_after_die; +} + +sub pkt_op_pair { + my ($self) = @_; + require PublicInbox::OnDestroy; + require PublicInbox::PktOp; + my $end = PublicInbox::OnDestroy->new($$, \&_delete_pkt_op, $self); + @$self{qw(pkt_op_c pkt_op_p)} = PublicInbox::PktOp->pair; + $end; +} + +sub workers_start { + my ($lei, $wq, $ident, $jobs, $ops) = @_; + $ops = { + '!' => [ \&fail_handler, $lei ], + '|' => [ \&sigpipe_handler, $lei ], + 'x_it' => [ \&x_it, $lei ], + 'child_error' => [ \&child_error, $lei ], + ($ops ? %$ops : ()), + }; + $ops->{''} //= [ $wq->can('_lei_wq_eof') || \&dclose, $lei ]; + my $end = $lei->pkt_op_pair; + $wq->wq_workers_start($ident, $jobs, $lei->oldset, { lei => $lei }); + delete $lei->{pkt_op_p}; + my $op_c = delete $lei->{pkt_op_c}; + @$end = (); + $lei->event_step_init; + ($op_c, $ops); +} + sub _help { require PublicInbox::LeiHelp; PublicInbox::LeiHelp::call($_[0], $_[1], \%CMD, \%OPTDESC); @@ -452,7 +559,7 @@ sub optparse ($$$) { # allow _complete --help to complete, not show help return 1 if substr($cmd, 0, 1) eq '_'; $self->{cmd} = $cmd; - $OPT = $self->{opt} = {}; + $OPT = $self->{opt} //= {}; my $info = $CMD{$cmd} // [ '[...]' ]; my ($proto, undef, @spec) = @$info; my $glp = ref($spec[-1]) eq ref($GLP) ? pop(@spec) : $GLP; @@ -516,20 +623,80 @@ sub optparse ($$$) { $err ? fail($self, "usage: lei $cmd $proto\nE: $err") : 1; } +sub _tmp_cfg { # for lei -c = ... + my ($self) = @_; + my $cfg = _lei_cfg($self, 1); + require File::Temp; + my $ft = File::Temp->new(TEMPLATE => 'lei_cfg-XXXX', TMPDIR => 1); + my $tmp = { '-f' => $ft->filename, -tmp => $ft }; + $ft->autoflush(1); + print $ft <{-f}: $!"); +[include] + path = $cfg->{-f} +EOM + $tmp = $self->{cfg} = bless { %$cfg, %$tmp }, ref($cfg); + for (@{$self->{opt}->{c}}) { + /\A([^=\.]+\.[^=]+)(?:=(.*))?\z/ or return fail($self, <=' +EOM + my $name = $1; + my $value = $2 // 1; + _config($self, '--add', $name, $value); + if (defined(my $v = $tmp->{$name})) { + if (ref($v) eq 'ARRAY') { + push @$v, $value; + } else { + $tmp->{$name} = [ $v, $value ]; + } + } else { + $tmp->{$name} = $value; + } + } +} + +sub lazy_cb ($$$) { + my ($self, $cmd, $pfx) = @_; + my $ucmd = $cmd; + $ucmd =~ tr/-/_/; + my $cb; + $cb = $self->can($pfx.$ucmd) and return $cb; + my $base = $ucmd; + $base =~ s/_([a-z])/\u$1/g; + my $pkg = "PublicInbox::Lei\u$base"; + ($INC{"PublicInbox/Lei\u$base.pm"} // eval("require $pkg")) ? + $pkg->can($pfx.$ucmd) : undef; +} + sub dispatch { my ($self, $cmd, @argv) = @_; local $current_lei = $self; # for __WARN__ dump_and_clear_log("from previous run\n"); return _help($self, 'no command given') unless defined($cmd); - my $func = "lei_$cmd"; - $func =~ tr/-/_/; - if (my $cb = __PACKAGE__->can($func)) { + # do not support Getopt bundling for this + while ($cmd eq '-C' || $cmd eq '-c') { + my $v = shift(@argv) // return fail($self, $cmd eq '-C' ? + '-C DIRECTORY' : '-c ='); + push @{$self->{opt}->{substr($cmd, 1, 1)}}, $v; + $cmd = shift(@argv) // return _help($self, 'no command given'); + } + if (my $cb = lazy_cb(__PACKAGE__, $cmd, 'lei_')) { optparse($self, $cmd, \@argv) or return; + $self->{opt}->{c} and (_tmp_cfg($self) // return); + if (my $chdir = $self->{opt}->{C}) { + for my $d (@$chdir) { + 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; + } + } $cb->($self, @argv); } elsif (grep(/\A-/, $cmd, @argv)) { # --help or -h only - my $opt = {}; - $GLP->getoptionsfromarray([$cmd, @argv], $opt, qw(help|h)) or - return _help($self, 'bad arguments or options'); + $GLP->getoptionsfromarray([$cmd, @argv], {}, qw(help|h C=s@)) + or return _help($self, 'bad arguments or options'); _help($self); } else { fail($self, "`$cmd' is not an lei command"); @@ -538,27 +705,41 @@ sub dispatch { sub _lei_cfg ($;$) { my ($self, $creat) = @_; + return $self->{cfg} if $self->{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); 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)}; } if (!@st) { unless ($creat) { delete $self->{cfg}; - return; + return bless {}, 'PublicInbox::Config'; } my (undef, $cfg_dir, undef) = File::Spec->splitpath($f); -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, "I: $f created") if $self->{cmd} ne 'config'; + qerr($self, "# $f created") if $self->{cmd} ne 'config'; } - my $cfg = PublicInbox::Config::git_config_dump($f); + my $cfg = PublicInbox::Config->git_config_dump($f); $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; + } + 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 + } + } $self->{cfg} = $PATH2CFG{$f} = $cfg; } @@ -567,29 +748,19 @@ sub _lei_store ($;$) { my $cfg = _lei_cfg($self, $creat); $cfg->{-lei_store} //= do { require PublicInbox::LeiStore; - my $dir = $cfg->{'leistore.dir'}; - $dir //= $creat ? _store_path($self) : return; + my $dir = $cfg->{'leistore.dir'} // store_path($self); + return unless $creat || -d $dir; PublicInbox::LeiStore->new($dir, { creat => $creat }); }; } -sub lei_show { - my ($self, @argv) = @_; -} - -sub lei_mark { - my ($self, @argv) = @_; -} - sub _config { my ($self, @argv) = @_; - my $env = $self->{env}; - delete local $env->{GIT_CONFIG}; - delete local $ENV{GIT_CONFIG}; + my %env = (%{$self->{env}}, GIT_CONFIG => undef); my $cfg = _lei_cfg($self, 1); my $cmd = [ qw(git config -f), $cfg->{'-f'}, @argv ]; my %rdr = map { $_ => $self->{$_} } (0..2); - waitpid(spawn($cmd, $env, \%rdr), 0); + waitpid(spawn($cmd, \%env, \%rdr), 0); } sub lei_config { @@ -600,43 +771,6 @@ sub lei_config { x_it($self, $?) if $?; } -sub lei_import { - require PublicInbox::LeiImport; - PublicInbox::LeiImport->call(@_); -} - -sub lei_init { - my ($self, $dir) = @_; - my $cfg = _lei_cfg($self, 1); - my $cur = $cfg->{'leistore.dir'}; - $dir //= _store_path($self); - $dir = rel2abs($self, $dir); - my @cur = stat($cur) if defined($cur); - $cur = File::Spec->canonpath($cur // $dir); - my @dir = stat($dir); - my $exists = "I: leistore.dir=$cur already initialized" if @dir; - if (@cur) { - if ($cur eq $dir) { - _lei_store($self, 1)->done; - return qerr($self, $exists); - } - - # some folks like symlinks and bind mounts :P - if (@dir && "@cur[1,0]" eq "@dir[1,0]") { - lei_config($self, 'leistore.dir', $dir); - _lei_store($self, 1)->done; - return qerr($self, "$exists (as $cur)"); - } - return fail($self, <<""); -E: leistore.dir=$cur already initialized and it is not $dir - - } - lei_config($self, 'leistore.dir', $dir); - _lei_store($self, 1)->done; - $exists //= "I: leistore.dir=$dir newly initialized"; - return qerr($self, $exists); -} - sub lei_daemon_pid { puts shift, $$ } sub lei_daemon_kill { @@ -645,15 +779,13 @@ sub lei_daemon_kill { kill($sig, $$) or fail($self, "kill($sig, $$): $!"); } -sub lei_help { _help($_[0]) } - # Shell completion helper. Used by lei-completion.bash and hopefully # other shells. Try to do as much here as possible to avoid redundancy # and improve maintainability. sub lei__complete { my ($self, @argv) = @_; # argv = qw(lei and any other args...) shift @argv; # ignore "lei", the entire command is sent - @argv or return puts $self, grep(!/^_/, keys %CMD), qw(--help -h); + @argv or return puts $self, grep(!/^_/, keys %CMD), qw(--help -h -C); my $cmd = shift @argv; my $info = $CMD{$cmd} // do { # filter matching commands @argv or puts $self, grep(/\A\Q$cmd\E/, keys %CMD); @@ -662,7 +794,7 @@ sub lei__complete { my ($proto, undef, @spec) = @$info; my $cur = pop @argv; my $re = defined($cur) ? qr/\A\Q$cur\E/ : qr/./; - if (substr($cur // '-', 0, 1) eq '-') { # --switches + if (substr(my $_cur = $cur // '-', 0, 1) eq '-') { # --switches # gross special case since the only git-config options # Consider moving to a table if we need more special cases # we use Getopt::Long for are the ones we reject, so these @@ -677,18 +809,18 @@ sub lei__complete { # fall-through } # generate short/long names from Getopt::Long specs - puts $self, grep(/$re/, qw(--help -h), map { + puts $self, grep(/$re/, qw(--help -h -C), map { if (s/[:=].+\z//) { # req/optional args, e.g output|o=i } elsif (s/\+\z//) { # verbose|v+ } elsif (s/!\z//) { - # negation: solve! => no-solve|solve + # negation: mail! => no-mail|mail s/([\w\-]+)/$1|no-$1/g } map { my $x = length > 1 ? "--$_" : "-$_"; - $x eq $cur ? () : $x; + $x eq $_cur ? () : $x; } grep(!/_/, split(/\|/, $_, -1)) # help|h - } grep { $OPTDESC{"$cmd\t$_"} || $OPTDESC{$_} } @spec); + } grep { $OPTDESC{"$_\t$cmd"} || $OPTDESC{$_} } @spec); } elsif ($cmd eq 'config' && !@argv && !$CONFIG_KEYS{$cur}) { puts $self, grep(/$re/, keys %CONFIG_KEYS); } @@ -701,13 +833,12 @@ sub lei__complete { my @v = ref($v) ? split(/\|/, $v->[0]) : (); # get rid of ALL CAPS placeholder (e.g "OUT") # (TODO: completion for external paths) - shift(@v) if uc($v[0]) eq $v[0]; + shift(@v) if scalar(@v) && uc($v[0]) eq $v[0]; @v; - } grep(/\A(?:$cmd\t|)(?:[\w-]+\|)*$opt\b/, keys %OPTDESC); + } grep(/\A(?:[\w-]+\|)*$opt\b.*?(?:\t$cmd)?\z/, keys %OPTDESC); } - $cmd =~ tr/-/_/; - if (my $sub = $self->can("_complete_$cmd")) { - puts $self, $sub->($self, @argv, $cur); + if (my $cb = lazy_cb($self, $cmd, '_complete_')) { + puts $self, $cb->($self, @argv, $cur ? ($cur) : ()); } # TODO: URLs, pathnames, OIDs, MIDs, etc... See optparse() for # proto parsing. @@ -723,7 +854,7 @@ sub exec_buf ($$) { sub start_mua { my ($self) = @_; - my $mua = $self->{opt}->{'mua-cmd'} // return; + my $mua = $self->{opt}->{mua} // return; my $mfolder = $self->{ovv}->{dst}; my (@cmd, $replaced); if ($mua =~ /\A(?:mutt|mailx|mail|neomutt)\z/) { @@ -731,40 +862,107 @@ sub start_mua { # TODO: help wanted: other common FOSS MUAs } else { require Text::ParseWords; - my @cmd = Text::ParseWords::shellwords($mua); + @cmd = Text::ParseWords::shellwords($mua); # mutt uses '%f' for open-hook with compressed mbox, we follow @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); + 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, $io, \@cmd, {}); } elsif ($self->{oneshot}) { - $self->{"mua.pid.$self.$$"} = spawn(\@cmd); + my $pid = fork // die "fork: $!"; + if ($pid > 0) { # original process + if ($self->{opt}->{stdin} && -t STDOUT) { + open STDIN, '+<&', \*STDOUT or die "dup2: $!"; + } + exec(@cmd); + warn "exec @cmd: $!\n"; + POSIX::_exit(1); + } + POSIX::setsid() > 0 or die "setsid: $!"; + } + if ($self->{lxs} && $self->{au_done}) { # kick wait_startq + syswrite($self->{au_done}, 'q' x ($self->{lxs}->{jobs} // 0)); } + return unless -t $self->{2}; # XXX how to determine non-TUI MUAs? + $self->{opt}->{quiet} = 1; delete $self->{-progress}; + delete $self->{opt}->{verbose}; +} + +sub send_exec_cmd { # tell script/lei to execute a command + my ($self, $io, $cmd, $env) = @_; + my $sock = $self->{sock} // die 'lei client gone'; + my $fds = [ map { fileno($_) } @$io ]; + $send_cmd->($sock, $fds, exec_buf($cmd, $env), MSG_EOR); +} + +sub poke_mua { # forces terminal MUAs to wake up and hopefully notice new mail + my ($self) = @_; + my $alerts = $self->{opt}->{alert} // return; + while (my $op = shift(@$alerts)) { + if ($op eq ':WINCH') { + # hit the process group that started the MUA + if ($self->{sock}) { + send($self->{sock}, '-WINCH', MSG_EOR); + } elsif ($self->{oneshot}) { + kill('-WINCH', $$); + } + } elsif ($op eq ':bell') { + out($self, "\a"); + } elsif ($op =~ /(?{sock}) { + send($s, exec_buf($cmd, {}), MSG_EOR); + } elsif ($self->{oneshot}) { + $self->{"pid.$self.$$"}->{spawn($cmd)} = $cmd; + } + } else { + err($self, "W: unsupported --alert=$op"); # non-fatal + } + } +} + +my %path_to_fd = ('/dev/stdin' => 0, '/dev/stdout' => 1, '/dev/stderr' => 2); +$path_to_fd{"/dev/fd/$_"} = $_ for (0..2); + +# this also normalizes the path +sub path_to_fd { + my ($self, $path) = @_; + $path = rel2abs($self, $path); + $path =~ tr!/!/!s; + $path_to_fd{$path} // ( + ($path =~ m!\A/(?:dev|proc/self)/fd/[0-9]+\z!) ? + fail($self, "cannot open $path from daemon") : -1 + ); } # caller needs to "-t $self->{1}" to check if tty sub start_pager { my ($self) = @_; - my $env = $self->{env}; - my $fh = popen_rd([qw(git var GIT_PAGER)], $env); + my $fh = popen_rd([qw(git var GIT_PAGER)]); chomp(my $pager = <$fh> // ''); close($fh) or warn "`git var PAGER' error: \$?=$?"; return if $pager eq 'cat' || $pager eq ''; - # TODO TIOCGWINSZ - my $new_env = { LESS => 'FRX', LV => '-c', COLUMNS => 80 }; + my $new_env = { LESS => 'FRX', LV => '-c' }; $new_env->{MORE} = 'FRX' if $^O eq 'freebsd'; pipe(my ($r, $wpager)) or return warn "pipe: $!"; my $rdr = { 0 => $r, 1 => $self->{1}, 2 => $self->{2} }; my $pgr = [ undef, @$rdr{1, 2} ]; - if (my $sock = $self->{sock}) { # lei(1) process runs it + my $env = $self->{env}; + if ($self->{sock}) { # lei(1) process runs it delete @$new_env{keys %$env}; # only set iff unset - my $fds = [ map { fileno($_) } @$rdr{0..2} ]; - $send_cmd->($sock, $fds, exec_buf([$pager], $new_env), MSG_EOR); + send_exec_cmd($self, [ @$rdr{0..2} ], [$pager], $new_env); } elsif ($self->{oneshot}) { - $pgr->[0] = spawn([$pager], $new_env, $rdr); - $pgr->[3] = $$; # ew'll reap it + my $cmd = [$pager]; + $self->{"pid.$self.$$"}->{spawn($cmd, $new_env, $rdr)} = $cmd; } else { die 'BUG: start_pager w/o socket'; } @@ -780,8 +978,6 @@ sub stop_pager { $self->{2} = $pgr->[2]; # do not restore original stdout, just close it so we error out close(delete($self->{1})) if $self->{1}; - my $pid = $pgr->[0]; - dwaitpid($pid) if $pid && ($pgr->[3] // 0) == $$; } sub accept_dispatch { # Listener {post_accept} callback @@ -791,17 +987,18 @@ sub accept_dispatch { # Listener {post_accept} callback vec(my $rvec = '', fileno($sock), 1) = 1; select($rvec, undef, undef, 60) or return send($sock, 'timed out waiting to recv FDs', MSG_EOR); - my @fds = $recv_cmd->($sock, my $buf, 4096 * 33); # >MAX_ARG_STRLEN - if (scalar(@fds) == 4) { - for my $i (0..3) { - my $fd = shift(@fds); - open($self->{$i}, '+<&=', $fd) and next; + # (4096 * 33) >MAX_ARG_STRLEN + my @fds = $recv_cmd->($sock, my $buf, 4096 * 33) or return; # EOF + if (!defined($fds[0])) { + warn(my $msg = "recv_cmd failed: $!"); + return send($sock, $msg, MSG_EOR); + } else { + my $i = 0; + for my $fd (@fds) { + open($self->{$i++}, '+<&=', $fd) and next; send($sock, "open(+<&=$fd) (FD=$i): $!", MSG_EOR); } - } else { - my $msg = "recv_cmd failed: $!"; - warn $msg; - return send($sock, $msg, MSG_EOR); + return if scalar(@fds) != 4; } $self->{2}->autoflush(1); # keep stdout buffered until x_it|DESTROY # $ENV_STR = join('', map { "\0$_=$ENV{$_}" } keys %ENV); @@ -824,16 +1021,9 @@ sub accept_dispatch { # Listener {post_accept} callback sub dclose { my ($self) = @_; delete $self->{-progress}; - for my $f (@WQ_KEYS) { - my $wq = delete $self->{$f} or next; - if ($wq->wq_kill) { - $wq->wq_close - } elsif ($wq->wq_kill_old) { - $wq->wq_wait_old($self); - } - } + _drop_wq($self); close(delete $self->{1}) if $self->{1}; # may reap_compress - $self->close if $self->{sock}; # PublicInbox::DS::close + $self->close if $self->{-event_init_done}; # PublicInbox::DS::close } # for long-running results @@ -865,6 +1055,7 @@ sub event_step { sub event_step_init { my ($self) = @_; + return if $self->{-event_init_done}++; if (my $sock = $self->{sock}) { # using DS->EventLoop $self->SUPER::new($sock, EPOLLIN|EPOLLET); } @@ -872,7 +1063,7 @@ sub event_step_init { sub noop {} -our $oldset; sub oldset { $oldset } +sub oldset { $oldset } sub dump_and_clear_log { if (defined($errors_log) && -s STDIN && seek(STDIN, 0, SEEK_SET)) { @@ -886,22 +1077,27 @@ sub dump_and_clear_log { # lei(1) calls this when it can't connect sub lazy_start { my ($path, $errno, $narg) = @_; - if ($errno == ECONNREFUSED) { - unlink($path) or die "unlink($path): $!"; - } elsif ($errno != ENOENT) { + local ($errors_log, $listener); + ($errors_log) = ($path =~ m!\A(.+?/)[^/]+\z!); + $errors_log .= 'errors.log'; + my $addr = pack_sockaddr_un($path); + my $lk = bless { lock_path => $errors_log }, 'PublicInbox::Lock'; + $lk->lock_acquire; + socket($listener, AF_UNIX, SOCK_SEQPACKET, 0) or die "socket: $!"; + if ($errno == ECONNREFUSED || $errno == ENOENT) { + return if connect($listener, $addr); # another process won + if ($errno == ECONNREFUSED && -S $path) { + unlink($path) or die "unlink($path): $!"; + } + } else { $! = $errno; # allow interpolation to stringify in die die "connect($path): $!"; } - if (eval { require BSD::Resource }) { - my $NOFILE = BSD::Resource::RLIMIT_NOFILE(); - my ($s, $h) = BSD::Resource::getrlimit($NOFILE); - BSD::Resource::setrlimit($NOFILE, $h, $h) if $s < $h; - } umask(077) // die("umask(077): $!"); - local $listener; - socket($listener, AF_UNIX, SOCK_SEQPACKET, 0) or die "socket: $!"; - bind($listener, pack_sockaddr_un($path)) or die "bind($path): $!"; + bind($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): $!"; my $dev_ino_expect = pack('dd', $st[0], $st[1]); # dev+ino local $oldset = PublicInbox::DS::block_signals(); @@ -919,9 +1115,6 @@ sub lazy_start { require PublicInbox::Listener; require PublicInbox::EOFpipe; (-p STDOUT) or die "E: stdout must be a pipe\n"; - local $errors_log; - ($errors_log) = ($path =~ m!\A(.+?/)[^/]+\z!); - $errors_log .= 'errors.log'; open(STDIN, '+>>', $errors_log) or die "open($errors_log): $!"; STDIN->autoflush(1); dump_and_clear_log("from previous daemon process:\n"); @@ -1007,6 +1200,8 @@ sub lazy_start { exit($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 ($main_pkg) = @_; @@ -1031,9 +1226,17 @@ sub DESTROY { my ($self) = @_; $self->{1}->autoflush(1) if $self->{1}; stop_pager($self); - if (my $mua_pid = delete $self->{"mua.pid.$self.$$"}) { - waitpid($mua_pid, 0); - } + my $err = $?; + my $oneshot_pids = delete $self->{"pid.$self.$$"} or return; + waitpid($_, 0) for keys %$oneshot_pids; + $? = $err if $err; # preserve ->fail or ->x_it code +} + +sub wq_done_wait { # dwaitpid callback + my ($arg, $pid) = @_; + my ($wq, $lei, $e) = @$arg; + $? and $lei->child_error($?, $e ? "$e errors during $lei->{cmd}" : ()); + $lei->dclose; } 1;