-# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# Backend for `lei' (local email interface). Unlike the C10K-oriented
package PublicInbox::LEI;
use strict;
use v5.10.1;
-use parent qw(PublicInbox::DS);
+use parent qw(PublicInbox::DS PublicInbox::LeiExternal
+ PublicInbox::LeiQuery);
use Getopt::Long ();
use Socket qw(AF_UNIX SOCK_STREAM pack_sockaddr_un);
use Errno qw(EAGAIN ECONNREFUSED ENOENT);
use IO::Handle ();
use Sys::Syslog qw(syslog openlog);
use PublicInbox::Config;
-use PublicInbox::Syscall qw($SFD_NONBLOCK EPOLLIN EPOLLONESHOT);
+use PublicInbox::Syscall qw(SFD_NONBLOCK EPOLLIN EPOLLONESHOT);
use PublicInbox::Sigfd;
-use PublicInbox::DS qw(now);
-use PublicInbox::Spawn qw(spawn);
+use PublicInbox::DS qw(now dwaitpid);
+use PublicInbox::Spawn qw(spawn run_die popen_rd);
use PublicInbox::OnDestroy;
use Text::Wrap qw(wrap);
use File::Path qw(mkpath);
use File::Spec;
our $quit = \&CORE::exit;
+my $recv_cmd;
my $GLP = Getopt::Long::Parser->new;
$GLP->configure(qw(gnu_getopt no_ignore_case auto_abbrev));
my $GLP_PASS = Getopt::Long::Parser->new;
sub pass_through { $GLP_PASS }
my $OPT;
-sub opt_dash {
+sub opt_dash ($$) {
my ($spec, $re_str) = @_; # 'limit|n=i', '([0-9]+)'
my ($key) = ($spec =~ m/\A([a-z]+)/g);
my $cb = sub { # Getopt::Long "<>" catch-all handler
my ($arg) = @_;
if ($arg =~ /\A-($re_str)\z/) {
$OPT->{$key} = $1;
+ } elsif ($arg eq '--') { # "--" arg separator, ignore first
+ push @{$OPT->{-argv}}, $arg if $OPT->{'--'}++;
+ # lone (single) dash is handled elsewhere
+ } elsif (substr($arg, 0, 1) eq '-') {
+ if ($OPT->{'--'}) {
+ push @{$OPT->{-argv}}, $arg;
+ } else {
+ die "bad argument: $arg\n";
+ }
} else {
- die "bad argument for --$key: $arg\n";
+ push @{$OPT->{-argv}}, $arg;
}
};
- ($spec, '<>' => $cb, $GLP_PASS)
+ ($spec, '<>' => $cb, $GLP_PASS) # for Getopt::Long
}
sub _store_path ($) {
# TODO: generate shell completion + help using %CMD and %OPTDESC
# command => [ positional_args, 1-line description, Getopt::Long option spec ]
our %CMD = ( # sorted in order of importance/use:
-'query' => [ 'SEARCH_TERMS...', 'search for messages matching terms', qw(
- save-as=s output|o=s format|f=s dedupe|d=s thread|t augment|a
- sort|s=s@ reverse|r offset=i remote local! extinbox!
+'q' => [ '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
since|after=s until|before=s), 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') ],
-'add-extinbox' => [ 'URL_OR_PATHNAME',
+'add-external' => [ 'URL_OR_PATHNAME',
'add/set priority of a publicinbox|extindex for extra matches',
- qw(prio=i) ],
-'ls-extinbox' => [ '[FILTER...]', 'list publicinbox|extindex locations',
- qw(format|f=s z local remote) ],
-'forget-extinbox' => [ '{URL_OR_PATHNAME|--prune}',
+ qw(boost=i quiet|q) ],
+'ls-external' => [ '[FILTER...]', 'list publicinbox|extindex locations',
+ qw(format|f=s z|0 local remote quiet|q) ],
+'forget-external' => [ '{URL_OR_PATHNAME|--prune}',
'exclude further results from a publicinbox|extindex',
- qw(prune) ],
+ qw(prune quiet|q) ],
'ls-query' => [ '[FILTER...]', 'list saved search queries',
qw(name-only format|f=s z) ],
'set/unset flags on message(s) from stdin',
qw(stdin| oid=s exact by-mid|mid:s) ],
'forget' => [ '[--stdin|--oid=OID|--by-mid=MID]',
- 'exclude message(s) on stdin from query results',
+ "exclude message(s) on stdin from `q' search results",
qw(stdin| oid=s exact by-mid|mid:s quiet|q) ],
'purge-mailsource' => [ '{URL_OR_PATHNAME|--all}',
# code repos are used for `show' to solve blobs from patch mails
'add-coderepo' => [ 'PATHNAME', 'add or set priority of a git code repo',
- qw(prio=i) ],
+ qw(boost=i) ],
'ls-coderepo' => [ '[FILTER_TERMS...]',
'list known code repos', qw(format|f=s z) ],
'forget-coderepo' => [ 'PATHNAME',
'daemon-kill' => [ '[-SIGNAL]', 'signal the lei-daemon',
opt_dash('signal|s=s', '[0-9]+|(?:[A-Z][A-Z0-9]+)') ],
'daemon-pid' => [ '', 'show the PID of the lei-daemon' ],
-'daemon-env' => [ '[NAME=VALUE...]', 'set, unset, or show daemon environment',
- qw(clear| unset|u=s@ z|0) ],
'help' => [ '[SUBCOMMAND]', 'show help' ],
# XXX do we need this?
'type=s' => [ 'any|mid|git', 'disambiguate type' ],
-'dedupe|d=s' => ['STRAT|content|oid|mid',
+'dedupe|d=s' => ['STRAT|content|oid|mid|none',
'deduplication strategy'],
'show thread|t' => 'display entire thread a message belongs to',
-'query thread|t' =>
+'q thread|t' =>
'return all messages in the same thread as the actual match(es)',
'augment|a' => 'augment --output destination instead of clobbering',
'message/object output format' ],
'mark format|f=s' => $stdin_formats,
'forget format|f=s' => $stdin_formats,
-'query format|f=s' => [ 'OUT|maildir|mboxrd|mboxcl2|mboxcl|html|oid',
+'q format|f=s' => [ 'OUT|maildir|mboxrd|mboxcl2|mboxcl|html|oid|json',
'specify output format, default depends on --output'],
'ls-query format|f=s' => $ls_format,
-'ls-extinbox format|f=s' => $ls_format,
+'ls-external format|f=s' => $ls_format,
'limit|n=i@' => ['NUM', 'limit on number of matches (default: 10000)' ],
'offset=i' => ['OFF', 'search result offset (default: 0)'],
-'sort|s=s@' => [ 'VAL|internaldate,date,relevance,docid',
+'sort|s=s' => [ 'VAL|received,relevance,docid',
"order of results `--output'-dependent"],
+'reverse|r' => [ 'reverse search results' ], # like sort(1)
-'prio=i' => 'priority of query source',
+'boost=i' => 'increase/decrease priority of results (default: 0)',
'local' => 'limit operations to the local filesystem',
'local!' => 'exclude results from the local filesystem',
'by-mid|mid:s' => [ 'MID', 'match only by Message-ID, ignoring contents' ],
'jobs:i' => 'set parallelism level',
-# xargs, env, use "-0", git(1) uses "-z". Should we support z|0 everywhere?
-'z' => 'use NUL \\0 instead of newline (CR) to delimit lines',
+# 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',
-# note: no "--ignore-environment" / "-i" support like env(1) since that
-# is one-shot and this is for a persistent daemon:
-'clear|' => 'clear the daemon environment',
-'unset|u=s@' => ['NAME',
- 'unset matching NAME, may be specified multiple times'],
-
'signal|s=s' => [ 'SIG', 'signal to send lei-daemon (default: TERM)' ],
); # %OPTDESC
sub x_it ($$) { # pronounced "exit"
my ($self, $code) = @_;
+ $self->{1}->autoflush(1); # make sure client sees stdout before exit
if (my $sig = ($code & 127)) {
kill($sig, $self->{pid} // $$);
} else {
sub puts ($;@) { print { shift->{1} } map { "$_\n" } @_ }
-sub emit {
- my ($self, $channel) = @_; # $buf = $_[2]
- print { $self->{$channel} } $_[2] or die "print FD[$channel]: $!";
-}
+sub out ($;@) { print { shift->{1} } @_ }
-sub err {
- my ($self, $buf) = @_;
- $buf .= "\n" unless $buf =~ /\n\z/s;
- emit($self, 2, $buf);
+sub err ($;@) {
+ print { shift->{2} } @_, (substr($_[-1], -1, 1) eq "\n" ? () : "\n");
}
-sub qerr { $_[0]->{opt}->{quiet} or err(@_) }
+sub qerr ($;@) { $_[0]->{opt}->{quiet} or err(shift, @_) }
sub fail ($$;$) {
my ($self, $buf, $exit_code) = @_;
$msg .= $rhs;
$msg .= "\n";
}
- my $channel = $errmsg ? 2 : 1;
- emit($self, $channel, $msg);
+ print { $self->{$errmsg ? 2 : 1} } $msg;
x_it($self, $errmsg ? 1 << 8 : 0); # stderr => failure
undef;
}
return _help($self, "bad arguments or options for $cmd");
return _help($self) if $OPT->{help};
+ push @$argv, @{$OPT->{-argv}} if defined($OPT->{-argv});
+
# "-" aliases "stdin" or "clear"
$OPT->{$lone_dash} = ${$OPT->{$lone_dash}} if defined $lone_dash;
}
last if $err;
}
- # warn "inf=$inf ".scalar(@$argv). ' '.scalar(@args)."\n";
if (!$inf && scalar(@$argv) > scalar(@args)) {
$err //= 'too many arguments';
}
sub dispatch {
my ($self, $cmd, @argv) = @_;
- local $SIG{__WARN__} = sub { err($self, "@_") };
+ local $SIG{__WARN__} = sub { err($self, @_) };
return _help($self, 'no command given') unless defined($cmd);
my $func = "lei_$cmd";
$func =~ tr/-/_/;
my $cfg = _lei_cfg($self, $creat);
$cfg->{-lei_store} //= do {
require PublicInbox::LeiStore;
- PublicInbox::SearchIdx::load_xapian_writable();
- defined(my $dir = $cfg->{'leistore.dir'}) or return;
+ my $dir = $cfg->{'leistore.dir'};
+ $dir //= _store_path($self->{env}) if $creat;
+ return unless $dir;
PublicInbox::LeiStore->new($dir, { creat => $creat });
};
}
my ($self, @argv) = @_;
}
-sub lei_query {
- my ($self, @argv) = @_;
-}
-
sub lei_mark {
my ($self, @argv) = @_;
}
my $cfg = _lei_cfg($self, 1);
my $cmd = [ qw(git config -f), $cfg->{'-f'}, @argv ];
my %rdr = map { $_ => $self->{$_} } (0..2);
- require PublicInbox::Import;
- PublicInbox::Import::run_die($cmd, $env, \%rdr);
+ run_die($cmd, $env, \%rdr);
}
sub lei_init {
$dir //= _store_path($env);
$dir = File::Spec->rel2abs($dir, $env->{PWD}); # PWD is symlink-aware
my @cur = stat($cur) if defined($cur);
- $cur = File::Spec->canonpath($cur) if $cur;
+ $cur = File::Spec->canonpath($cur // $dir);
my @dir = stat($dir);
my $exists = "I: leistore.dir=$cur already initialized" if @dir;
if (@cur) {
return qerr($self, $exists);
}
-sub lei_daemon_pid { emit($_[0], 1, "$$\n") }
+sub lei_daemon_pid { puts shift, $$ }
sub lei_daemon_kill {
my ($self) = @_;
kill($sig, $$) or fail($self, "kill($sig, $$): $!");
}
-sub lei_daemon_env {
- my ($self, @argv) = @_;
- my $opt = $self->{opt};
- if (defined $opt->{clear}) {
- %ENV = ();
- } elsif (my $u = $opt->{unset}) {
- delete @ENV{@$u};
- }
- if (@argv) {
- %ENV = (%ENV, map { split(/=/, $_, 2) } @argv);
- } elsif (!defined($opt->{clear}) && !$opt->{unset}) {
- my $eor = $opt->{z} ? "\0" : "\n";
- my $buf = '';
- while (my ($k, $v) = each %ENV) { $buf .= "$k=$v$eor" }
- emit($self, 1, $buf)
- }
-}
-
sub lei_help { _help($_[0]) }
# Shell completion helper. Used by lei-completion.bash and hopefully
my ($self, @argv) = @_;
my %rdr = map { $_ => $self->{$_} } (0..2);
my $pid = spawn(['git', @argv], $self->{env}, \%rdr);
- PublicInbox::DS::dwaitpid($pid, \&reap_exec, $self);
+ dwaitpid($pid, \&reap_exec, $self);
+}
+
+# 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);
+ chomp(my $pager = <$fh> // '');
+ close($fh) or warn "`git var PAGER' error: \$?=$?";
+ return if $pager eq 'cat' || $pager eq '';
+ $env->{LESS} //= 'FRX';
+ $env->{LV} //= '-c';
+ $env->{COLUMNS} //= 80; # TODO TIOCGWINSZ
+ $env->{MORE} //= 'FRX' if $^O eq 'freebsd';
+ pipe(my ($r, $w)) or return warn "pipe: $!";
+ my $rdr = { 0 => $r, 1 => $self->{1}, 2 => $self->{2} };
+ $self->{1} = $w;
+ $self->{2} = $w if -t $self->{2};
+ my $pid = spawn([$pager], $env, $rdr);
+ dwaitpid($pid, undef, $self->{sock});
+ $env->{GIT_PAGER_IN_USE} = 'true'; # we may spawn git
}
sub accept_dispatch { # Listener {post_accept} callback
my $self = bless { sock => $sock }, __PACKAGE__;
vec(my $rin = '', fileno($sock), 1) = 1;
# `say $sock' triggers "die" in lei(1)
- for my $i (0..2) {
- if (select(my $rout = $rin, undef, undef, 1)) {
- my $fd = IO::FDPass::recv(fileno($sock));
- if ($fd >= 0) {
- my $rdr = ($fd == 0 ? '<&=' : '>&=');
+ my $buf;
+ if (select(my $rout = $rin, undef, undef, 1)) {
+ my @fds = $recv_cmd->($sock, $buf, 4096 * 33); # >MAX_ARG_STRLEN
+ if (scalar(@fds) == 3) {
+ my $i = 0;
+ for my $rdr (qw(<&= >&= >&=)) {
+ my $fd = shift(@fds);
if (open(my $fh, $rdr, $fd)) {
- $self->{$i} = $fh;
- } else {
+ $self->{$i++} = $fh;
+ } else {
say $sock "open($rdr$fd) (FD=$i): $!";
return;
}
- } else {
- say $sock "recv FD=$i: $!";
- return;
}
} else {
- say $sock "timed out waiting to recv FD=$i";
+ say $sock "recv_cmd failed: $!";
return;
}
+ } else {
+ say $sock "timed out waiting to recv FDs";
+ return;
}
- # $ARGV_STR = join("]\0[", @ARGV);
- # $ENV_STR = join('', map { "$_=$ENV{$_}\0" } keys %ENV);
- # $line = "$$\0\0>$ARGV_STR\0\0>$ENV_STR\0\0";
- my ($client_pid, $argv, $env) = do {
- local $/ = "\0\0\0"; # yes, 3 NULs at EOL, not 2
- chomp(my $line = <$sock>);
- split(/\0\0>/, $line, 3);
- };
- my %env = map { split(/=/, $_, 2) } split(/\0/, $env);
+ $self->{2}->autoflush(1); # keep stdout buffered until x_it|DESTROY
+ # $ENV_STR = join('', map { "\0$_=$ENV{$_}" } keys %ENV);
+ # $buf = "$$\0$argc\0".join("\0", @ARGV).$ENV_STR."\0\0";
+ if (substr($buf, -2, 2, '') ne "\0\0") { # s/\0\0\z//
+ say $sock "request command truncated";
+ return;
+ }
+ my ($client_pid, $argc, @argv) = split(/\0/, $buf, -1);
+ undef $buf;
+ my %env = map { split(/=/, $_, 2) } splice(@argv, $argc);
if (chdir($env{PWD})) {
+ local %ENV = %env;
$self->{env} = \%env;
- $self->{pid} = $client_pid;
- eval { dispatch($self, split(/\]\0\[/, $argv)) };
+ $self->{pid} = $client_pid + 0;
+ eval { dispatch($self, @argv) };
say $sock $@ if $@;
} else {
say $sock "chdir($env{PWD}): $!"; # implicit close
}
}
+# for long-running results
+sub event_step {
+ my ($self) = @_;
+ local %ENV = %{$self->{env}};
+ eval {}; # TODO
+ if ($@) {
+ say { $self->{sock} } $@;
+ $self->close; # PublicInbox::DS::close
+ }
+}
+
sub noop {}
# lei(1) calls this when it can't connect
sub lazy_start {
- my ($path, $errno) = @_;
+ my ($path, $errno, $nfd) = @_;
if ($errno == ECONNREFUSED) {
unlink($path) or die "unlink($path): $!";
} elsif ($errno != ENOENT) {
my @st = stat($path) or die "stat($path): $!";
my $dev_ino_expect = pack('dd', $st[0], $st[1]); # dev+ino
pipe(my ($eof_r, $eof_w)) or die "pipe: $!";
- my $oldset = PublicInbox::Sigfd::block_signals();
- require IO::FDPass;
+ my $oldset = PublicInbox::DS::block_signals();
+ if ($nfd == 1) {
+ require PublicInbox::CmdIPC1;
+ $recv_cmd = PublicInbox::CmdIPC1->can('recv_cmd1');
+ } elsif ($nfd == 4) {
+ $recv_cmd = PublicInbox::Spawn->can('recv_cmd4') // do {
+ require PublicInbox::CmdIPC4;
+ PublicInbox::CmdIPC4->can('recv_cmd4');
+ };
+ }
+ $recv_cmd or die <<"";
+(Socket::MsgHdr || IO::FDPass || Inline::C) missing/unconfigured (nfd=$nfd);
+
require PublicInbox::Listener;
require PublicInbox::EOFpipe;
- (-p STDOUT && -p STDERR) or die "E: stdout+stderr must be pipes\n";
+ (-p STDOUT) or die "E: stdout must be a pipe\n";
open(STDIN, '+<', '/dev/null') or die "redirect stdin failed: $!";
POSIX::setsid() > 0 or die "setsid: $!";
my $pid = fork // die "fork: $!";
USR1 => \&noop,
USR2 => \&noop,
};
- my $sigfd = PublicInbox::Sigfd->new($sig, $SFD_NONBLOCK);
+ my $sigfd = PublicInbox::Sigfd->new($sig, SFD_NONBLOCK);
local %SIG = (%SIG, %$sig) if !$sigfd;
if ($sigfd) { # TODO: use inotify/kqueue to detect unlinked sockets
PublicInbox::DS->SetLoopTimeout(5000);
} else {
# wake up every second to accept signals if we don't
# have signalfd or IO::KQueue:
- PublicInbox::Sigfd::sig_setmask($oldset);
+ PublicInbox::DS::sig_setmask($oldset);
PublicInbox::DS->SetLoopTimeout(1000);
}
PublicInbox::DS->SetPostLoopCallback(sub {
$n; # true: continue, false: stop
});
- # STDIN was redirected to /dev/null above, closing STDOUT and
- # STDERR will cause the calling `lei' client process to finish
- # reading <$daemon> pipe.
- open STDOUT, '>&STDIN' or die "redirect stdout failed: $!";
+ # STDIN was redirected to /dev/null above, closing STDERR and
+ # STDOUT will cause the calling `lei' client process to finish
+ # reading the <$daemon> pipe.
openlog($path, 'pid', 'user');
local $SIG{__WARN__} = sub { syslog('warning', "@_") };
- my $owner_pid = $$;
- my $on_destroy = PublicInbox::OnDestroy->new(sub {
- syslog('crit', "$@") if $@ && $$ == $owner_pid;
+ my $on_destroy = PublicInbox::OnDestroy->new($$, sub {
+ syslog('crit', "$@") if $@;
});
open STDERR, '>&STDIN' or die "redirect stderr failed: $!";
+ open STDOUT, '>&STDIN' or die "redirect stdout failed: $!";
# $daemon pipe to `lei' closed, main loop begins:
PublicInbox::DS->EventLoop;
@$on_destroy = (); # cancel on_destroy if we get here
}, __PACKAGE__), @ARGV);
}
+# ensures stdout hits the FS before sock disconnects so a client
+# can immediately reread it
+sub DESTROY {
+ my ($self) = @_;
+ $self->{1}->autoflush(1);
+}
+
1;