X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLEI.pm;h=0da26a32825755c7f3534d2c50b9c70e04fc06f0;hb=7d2e572aca7297ea2015d2b6e7c71b672521ec82;hp=28e5365ad6b8bf75d302b8472941e50561446187;hpb=e01fe4f05196b56775fffffe23572ec648b14ec6;p=public-inbox.git

diff --git a/lib/PublicInbox/LEI.pm b/lib/PublicInbox/LEI.pm
index 28e5365a..0da26a32 100644
--- a/lib/PublicInbox/LEI.pm
+++ b/lib/PublicInbox/LEI.pm
@@ -27,7 +27,7 @@ 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));
@@ -83,7 +83,7 @@ sub rel2abs ($$) {
 	File::Spec->rel2abs($p, $pwd);
 }
 
-sub _store_path ($) {
+sub store_path ($) {
 	my ($self) = @_;
 	rel2abs($self, ($self->{env}->{XDG_DATA_HOME} //
 		($self->{env}->{HOME} // '/nonexistent').'/.local/share')
@@ -97,6 +97,22 @@ 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) = @_;
+	$self->{ale} //= do {
+		require PublicInbox::LeiALE;
+		PublicInbox::LeiALE->new(cache_dir($self).
+					'/all_locals_ever.git');
+	};
+}
+
 sub index_opt {
 	# TODO: drop underscore variants everywhere, they're undocumented
 	qw(fsync|sync! jobs|j=i indexlevel|L=s compact
@@ -108,10 +124,12 @@ sub index_opt {
 # 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 threads|t augment|a
+'q' => [ '--stdin|SEARCH_TERMS...', 'search for messages matching terms',
+	'stdin|', # /|\z/ must be first for lone dash
+	qw(save-as=s output|mfolder|o=s format|f=s dedupe|d=s threads|t+
 	sort|s=s reverse|r offset=i remote! local! external! pretty
-	include|I=s@ exclude=s@ only=s@ jobs|j=s globoff|g stdin|
+	include|I=s@ exclude=s@ only=s@ jobs|j=s globoff|g augment|a
+	import-remote! import-before! lock=s@ rsyncable
 	alert=s@ mua=s no-torsocks torsocks=s verbose|v+ quiet|q C=s@),
 	PublicInbox::LeiQuery::curl_opt(), opt_dash('limit|n=i', '[0-9]+') ],
 
@@ -131,7 +149,7 @@ our %CMD = ( # sorted in order of importance/use:
 	qw(prune quiet|q C=s@) ],
 
 'ls-query' => [ '[FILTER...]', 'list saved search queries',
-		qw(name-only format|f=s z C=s@) ],
+		qw(name-only format|f=s C=s@) ],
 'rm-query' => [ 'QUERY_NAME', 'remove a saved search', qw(C=s@) ],
 'mv-query' => [ qw(OLD_NAME NEW_NAME), 'rename a saved search', qw(C=s@) ],
 
@@ -171,19 +189,22 @@ our %CMD = ( # sorted in order of importance/use:
 '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! C=s@),
+	lock=s@ in-format|F=s kw|keywords|flags! C=s@),
 	],
 '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 quiet|q
-	kw|keywords|flags! C=s@),
+	lock=s@ kw|keywords|flags! C=s@),
 	],
+'p2q' => [ 'FILE|COMMIT_OID|--stdin',
+	"use a patch to generate a query for `lei q --stdin'",
+	qw(stdin| want|w=s@ uri debug) ],
 'config' => [ '[...]', sub {
 		'git-config(1) wrapper for '._config_path($_[0]);
 	}, qw(config-file|system|global|file|f=s), # for conflict detection
 	 qw(C=s@), pass_through('git config') ],
 'init' => [ '[DIRNAME]', sub {
-	"initialize storage, default: "._store_path($_[0]);
+	"initialize storage, default: ".store_path($_[0]);
 	}, qw(quiet|q C=s@) ],
 'daemon-kill' => [ '[-SIGNAL]', 'signal the lei-daemon',
 	# "-C DIR" conflicts with -CHLD, here, and chdir makes no sense, here
@@ -217,22 +238,30 @@ my %OPTDESC = (
 'help|h' => 'show this built-in help',
 '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)' ],
+
 'globoff|g' => "do not match locations using '*?' wildcards ".
 		"and\xa0'[]'\x{a0}ranges",
 'verbose|v+' => 'be more verbose',
+'external!' => 'do not use externals',
 'solve!' => 'do not attempt to reconstruct blobs from emails',
 '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'],
+'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	threads|t' => 'display entire thread a message belongs to',
-'q	threads|t' =>
+'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,<any command>',
 	'run command(s) or perform ops when done writing to output ' .
 	'(default: ":WINCH,:bell" with --mua and Maildir/IMAP output, ' .
@@ -246,17 +275,11 @@ my %OPTDESC = (
 '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',
@@ -270,23 +293,22 @@ 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-query' => $ls_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)'],
@@ -326,7 +348,7 @@ my %CONFIG_KEYS = (
 	'leistore.dir' => 'top-level storage location',
 );
 
-my @WQ_KEYS = qw(lxs l2m imp mrr cnv); # internal workers
+my @WQ_KEYS = qw(lxs l2m imp mrr cnv p2q); # internal workers
 
 # pronounced "exit": x_it(1 << 8) => exit(1); x_it(13) => SIGPIPE
 sub x_it ($$) {
@@ -397,26 +419,28 @@ sub fail ($$;$) {
 	undef;
 }
 
-sub check_input_format ($;$$) {
-	my ($self, $files, $opt_key) = @_;
-	$opt_key //= 'format';
+sub check_input_format ($;$) {
+	my ($self, $files) = @_;
+	my $opt_key = 'in-format';
 	my $fmt = $self->{opt}->{$opt_key};
 	if (!$fmt) {
 		my $err = $files ? "regular file(s):\n@$files" : '--stdin';
 		return fail($self, "--$opt_key unset for $err");
 	}
+	require PublicInbox::MboxLock if $files;
+	require PublicInbox::MboxReader;
 	return 1 if $fmt eq 'eml';
 	# XXX: should this handle {gz,bz2,xz}? that's currently in LeiToMail
-	require PublicInbox::MboxReader;
-	PublicInbox::MboxReader->can($fmt) ||
-				fail($self, "--$opt_key=$fmt unrecognized");
+	PublicInbox::MboxReader->can($fmt) or
+		return fail($self, "--$opt_key=$fmt unrecognized");
+	1;
 }
 
 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, $err);
 }
@@ -598,8 +622,10 @@ sub _lei_cfg ($;$) {
 	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);
 	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 ($creat) {
@@ -617,6 +643,10 @@ sub _lei_cfg ($;$) {
 	bless $cfg, 'PublicInbox::Config';
 	$cfg->{-st} = $cur_st;
 	$cfg->{'-f'} = $f;
+	if ($sto && File::Spec->canonpath($sto_dir) eq
+			File::Spec->canonpath($cfg->{'leistore.dir'})) {
+		$cfg->{-lei_store} = $sto;
+	}
 	$self->{cfg} = $PATH2CFG{$f} = $cfg;
 }
 
@@ -626,7 +656,7 @@ sub _lei_store ($;$) {
 	$cfg->{-lei_store} //= do {
 		require PublicInbox::LeiStore;
 		my $dir = $cfg->{'leistore.dir'};
-		$dir //= $creat ? _store_path($self) : return;
+		$dir //= $creat ? store_path($self) : return;
 		PublicInbox::LeiStore->new($dir, { creat => $creat });
 	};
 }
@@ -666,11 +696,16 @@ sub lei_convert {
 	PublicInbox::LeiConvert->call(@_);
 }
 
+sub lei_p2q {
+	require PublicInbox::LeiP2q;
+	PublicInbox::LeiP2q->call(@_);
+}
+
 sub lei_init {
 	my ($self, $dir) = @_;
 	my $cfg = _lei_cfg($self, 1);
 	my $cur = $cfg->{'leistore.dir'};
-	$dir //= _store_path($self);
+	$dir //= store_path($self);
 	$dir = rel2abs($self, $dir);
 	my @cur = stat($cur) if defined($cur);
 	$cur = File::Spec->canonpath($cur // $dir);
@@ -749,7 +784,7 @@ sub lei__complete {
 				my $x = length > 1 ? "--$_" : "-$_";
 				$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);
 	}
@@ -764,7 +799,7 @@ sub lei__complete {
 			# (TODO: completion for external paths)
 			shift(@v) if 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")) {
@@ -847,11 +882,26 @@ sub poke_mua { # forces terminal MUAs to wake up and hopefully notice new mail
 	}
 }
 
+my %path_to_fd = ('/dev/stdin' => 0, '/dev/stdout' => 1, '/dev/stderr' => 2);
+$path_to_fd{"/dev/fd/$_"} = $path_to_fd{"/proc/self/fd/$_"} for (0..2);
+sub fopen {
+	my ($self, $mode, $path) = @_;
+	rel2abs($self, $path);
+	$path =~ tr!/!/!s;
+	if (defined(my $fd = $path_to_fd{$path})) {
+		return $self->{$fd};
+	}
+	if ($path =~ m!\A/(?:dev|proc/self)/fd/[0-9]+\z!) {
+		return fail($self, "cannot open $path from daemon");
+	}
+	open my $fh, $mode, $path or return;
+	$fh;
+}
+
 # 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' || $pager eq '';
@@ -860,6 +910,7 @@ sub start_pager {
 	pipe(my ($r, $wpager)) or return warn "pipe: $!";
 	my $rdr = { 0 => $r, 1 => $self->{1}, 2 => $self->{2} };
 	my $pgr = [ undef, @$rdr{1, 2} ];
+	my $env = $self->{env};
 	if ($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);
@@ -934,7 +985,10 @@ sub dclose {
 		}
 	}
 	close(delete $self->{1}) if $self->{1}; # may reap_compress
-	$self->close if $self->{sock}; # PublicInbox::DS::close
+	if (my $sto = delete $self->{sto}) {
+		$sto->ipc_do('done');
+	}
+	$self->close if $self->{-event_init_done}; # PublicInbox::DS::close
 }
 
 # for long-running results
@@ -974,7 +1028,7 @@ 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)) {