X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FInbox.pm;h=3b5ac970d07cf43af6d86b656d92606f108cefc9;hb=53c1b42f1f8bf5b50acbf25cbe77e70ca15d5c77;hp=23b77213b7a9d1b3adf4b8598ddca22035dea4a3;hpb=2c972f3d70caf99488fff300341450e48be6ebf1;p=public-inbox.git

diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm
index 23b77213..3b5ac970 100644
--- a/lib/PublicInbox/Inbox.pm
+++ b/lib/PublicInbox/Inbox.pm
@@ -1,62 +1,102 @@
-# Copyright (C) 2016 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # Represents a public-inbox (which may have multiple mailing addresses)
 package PublicInbox::Inbox;
 use strict;
 use warnings;
-use Scalar::Util qw(weaken isweak);
 use PublicInbox::Git;
 use PublicInbox::MID qw(mid2path);
+use PublicInbox::Eml;
 
-my $weakt;
-eval {
-	$weakt = 'disabled';
-	require PublicInbox::EvCleanup;
-	$weakt = undef; # OK if we get here
-};
+# Long-running "git-cat-file --batch" processes won't notice
+# unlinked packs, so we need to restart those processes occasionally.
+# Xapian and SQLite file handles are mostly stable, but sometimes an
+# admin will attempt to replace them atomically after compact/vacuum
+# and we need to be prepared for that.
+my $cleanup_timer;
+my $cleanup_avail = -1; # 0, or 1
+my $have_devel_peek;
+my $CLEANUP = {}; # string(inbox) -> inbox
 
-my $WEAKEN = {}; # string(inbox) -> inbox
-sub weaken_task () {
-	$weakt = undef;
-	_weaken_fields($_) for values %$WEAKEN;
-	$WEAKEN = {};
+sub git_cleanup ($) {
+	my ($self) = @_;
+	my $git = $self->{git} or return;
+	$git->cleanup;
 }
 
-sub _weaken_later ($) {
-	my ($self) = @_;
-	$weakt ||= PublicInbox::EvCleanup::later(*weaken_task);
-	$WEAKEN->{"$self"} = $self;
+sub cleanup_task () {
+	$cleanup_timer = undef;
+	my $next = {};
+	for my $ibx (values %$CLEANUP) {
+		my $again;
+		if ($have_devel_peek) {
+			foreach my $f (qw(search)) {
+				# we bump refcnt by assigning tmp, here:
+				my $tmp = $ibx->{$f} or next;
+				next if Devel::Peek::SvREFCNT($tmp) > 2;
+				delete $ibx->{$f};
+				# refcnt is zero when tmp is out-of-scope
+			}
+		}
+		git_cleanup($ibx);
+		if (my $gits = $ibx->{-repo_objs}) {
+			foreach my $git (@$gits) {
+				$again = 1 if $git->cleanup;
+			}
+		}
+		check_inodes($ibx);
+		if ($have_devel_peek) {
+			$again ||= !!$ibx->{search};
+		}
+		$next->{"$ibx"} = $ibx if $again;
+	}
+	$CLEANUP = $next;
 }
 
-sub new {
-	my ($class, $opts) = @_;
-	my $v = $opts->{address} ||= 'public-inbox@example.com';
-	my $p = $opts->{-primary_address} = ref($v) eq 'ARRAY' ? $v->[0] : $v;
-	$opts->{domain} = ($p =~ /\@(\S+)\z/) ? $1 : 'localhost';
-	weaken($opts->{-pi_config});
-	bless $opts, $class;
+sub cleanup_possible () {
+	# no need to require DS, here, if it were enabled another
+	# module would've require'd it, already
+	eval { PublicInbox::DS::in_loop() } or return 0;
+
+	eval {
+		require Devel::Peek; # needs separate package in Fedora
+		$have_devel_peek = 1;
+	};
+	1;
 }
 
-sub _weaken_fields {
+sub _cleanup_later ($) {
 	my ($self) = @_;
-	foreach my $f (qw(git mm search)) {
-		isweak($self->{$f}) or weaken($self->{$f});
+	$cleanup_avail = cleanup_possible() if $cleanup_avail < 0;
+	return if $cleanup_avail != 1;
+	$cleanup_timer ||= PublicInbox::DS::later(*cleanup_task);
+	$CLEANUP->{"$self"} = $self;
+}
+
+sub _set_uint ($$$) {
+	my ($opts, $field, $default) = @_;
+	my $val = $opts->{$field};
+	if (defined $val) {
+		$val = $val->[-1] if ref($val) eq 'ARRAY';
+		$val = undef if $val !~ /\A[0-9]+\z/;
 	}
+	$opts->{$field} = $val || $default;
 }
 
 sub _set_limiter ($$$) {
-	my ($self, $git, $pfx) = @_;
+	my ($self, $pi_config, $pfx) = @_;
 	my $lkey = "-${pfx}_limiter";
-	$git->{$lkey} = $self->{$lkey} ||= eval {
+	$self->{$lkey} ||= do {
+		# full key is: publicinbox.$NAME.httpbackendmax
 		my $mkey = $pfx.'max';
 		my $val = $self->{$mkey} or return;
 		my $lim;
-		if ($val =~ /\A\d+\z/) {
+		if ($val =~ /\A[0-9]+\z/) {
 			require PublicInbox::Qspawn;
 			$lim = PublicInbox::Qspawn::Limiter->new($val);
 		} elsif ($val =~ /\A[a-z][a-z0-9]*\z/) {
-			$lim = $self->{-pi_config}->limiter($val);
+			$lim = $pi_config->limiter($val);
 			warn "$mkey limiter=$val not found\n" if !$lim;
 		} else {
 			warn "$mkey limiter=$val not understood\n";
@@ -65,29 +105,113 @@ sub _set_limiter ($$$) {
 	}
 }
 
+sub new {
+	my ($class, $opts) = @_;
+	my $v = $opts->{address} ||= [ 'public-inbox@example.com' ];
+	my $p = $opts->{-primary_address} = ref($v) eq 'ARRAY' ? $v->[0] : $v;
+	$opts->{domain} = ($p =~ /\@(\S+)\z/) ? $1 : 'localhost';
+	my $pi_config = delete $opts->{-pi_config};
+	_set_limiter($opts, $pi_config, 'httpbackend');
+	_set_uint($opts, 'feedmax', 25);
+	$opts->{nntpserver} ||= $pi_config->{'publicinbox.nntpserver'};
+	my $dir = $opts->{inboxdir};
+	if (defined $dir && -f "$dir/inbox.lock") {
+		$opts->{version} = 2;
+	}
+
+	# allow any combination of multi-line or comma-delimited hide entries
+	my $hide = {};
+	if (defined(my $h = $opts->{hide})) {
+		foreach my $v (@$h) {
+			$hide->{$_} = 1 foreach (split(/\s*,\s*/, $v));
+		}
+		$opts->{-hide} = $hide;
+	}
+	bless $opts, $class;
+}
+
+sub version { $_[0]->{version} // 1 }
+
+sub git_epoch {
+	my ($self, $epoch) = @_;
+	$self->version == 2 or return;
+	$self->{"$epoch.git"} ||= do {
+		my $git_dir = "$self->{inboxdir}/git/$epoch.git";
+		my $g = PublicInbox::Git->new($git_dir);
+		$g->{-httpbackend_limiter} = $self->{-httpbackend_limiter};
+		# no cleanup needed, we never cat-file off this, only clone
+		$g;
+	};
+}
+
 sub git {
 	my ($self) = @_;
-	$self->{git} ||= eval {
-		_weaken_later($self);
-		my $g = PublicInbox::Git->new($self->{mainrepo});
-		_set_limiter($self, $g, 'httpbackend');
+	$self->{git} ||= do {
+		my $git_dir = $self->{inboxdir};
+		$git_dir .= '/all.git' if $self->version == 2;
+		my $g = PublicInbox::Git->new($git_dir);
+		$g->{-httpbackend_limiter} = $self->{-httpbackend_limiter};
+		_cleanup_later($self);
 		$g;
 	};
 }
 
+sub max_git_epoch {
+	my ($self) = @_;
+	return if $self->version < 2;
+	my $cur = $self->{-max_git_epoch};
+	my $changed = git($self)->alternates_changed;
+	if (!defined($cur) || $changed) {
+		git_cleanup($self) if $changed;
+		my $gits = "$self->{inboxdir}/git";
+		if (opendir my $dh, $gits) {
+			my $max = -1;
+			while (defined(my $git_dir = readdir($dh))) {
+				$git_dir =~ m!\A([0-9]+)\.git\z! or next;
+				$max = $1 if $1 > $max;
+			}
+			$cur = $self->{-max_git_epoch} = $max if $max >= 0;
+		} else {
+			warn "opendir $gits failed: $!\n";
+		}
+	}
+	$cur;
+}
+
 sub mm {
 	my ($self) = @_;
 	$self->{mm} ||= eval {
-		_weaken_later($self);
-		PublicInbox::Msgmap->new($self->{mainrepo});
+		require PublicInbox::Msgmap;
+		my $dir = $self->{inboxdir};
+		if ($self->version >= 2) {
+			PublicInbox::Msgmap->new_file("$dir/msgmap.sqlite3");
+		} else {
+			PublicInbox::Msgmap->new($dir);
+		}
 	};
 }
 
-sub search {
-	my ($self) = @_;
-	$self->{search} ||= eval {
-		_weaken_later($self);
-		PublicInbox::Search->new($self->{mainrepo});
+sub search ($;$$) {
+	my ($self, $over_only, $ctx) = @_;
+	my $srch = $self->{search} ||= eval {
+		_cleanup_later($self);
+		require PublicInbox::Search;
+		PublicInbox::Search->new($self);
+	};
+	($over_only || eval { $srch->xdb }) ? $srch : do {
+		$ctx and $ctx->{env}->{'psgi.errors'}->print(<<EOF);
+`$self->{name}' search went away unexpectedly
+EOF
+		undef;
+	};
+}
+
+sub over {
+	$_[0]->{over} //= eval {
+		my $srch = search($_[0], 1) or return;
+		my $over = PublicInbox::Over->new("$srch->{xpfx}/over.sqlite3");
+		$over->dbh; # may fail
+		$over;
 	};
 }
 
@@ -103,71 +227,205 @@ sub try_cat {
 
 sub description {
 	my ($self) = @_;
-	my $desc = $self->{description};
-	return $desc if defined $desc;
-	$desc = try_cat("$self->{mainrepo}/description");
-	chomp $desc;
-	$desc =~ s/\s+/ /smg;
-	$desc = '($GIT_DIR/description missing)' if $desc eq '';
-	$self->{description} = $desc;
+	($self->{description} //= do {
+		my $desc = try_cat("$self->{inboxdir}/description");
+		local $/ = "\n";
+		chomp $desc;
+		utf8::decode($desc);
+		$desc =~ s/\s+/ /smg;
+		$desc eq '' ? undef : $desc;
+	}) // '($INBOX_DIR/description missing)';
 }
 
 sub cloneurl {
 	my ($self) = @_;
-	my $url = $self->{cloneurl};
-	return $url if $url;
-	$url = try_cat("$self->{mainrepo}/cloneurl");
-	my @url = split(/\s+/s, $url);
-	chomp @url;
-	$self->{cloneurl} = \@url;
+	($self->{cloneurl} //= do {
+		my $s = try_cat("$self->{inboxdir}/cloneurl");
+		my @urls = split(/\s+/s, $s);
+		scalar(@urls) ? \@urls : undef
+	}) // [];
 }
 
 sub base_url {
-	my ($self, $env) = @_;
-	if ($env) { # PSGI env
-		my $scheme = $env->{'psgi.url_scheme'};
-		my $host_port = $env->{HTTP_HOST} ||
-			"$env->{SERVER_NAME}:$env->{SERVER_PORT}";
-		my $url = "$scheme://$host_port". ($env->{SCRIPT_NAME} || '/');
+	my ($self, $env) = @_; # env - PSGI env
+	if ($env) {
+		my $url = PublicInbox::Git::host_prefix_url($env, '');
 		# for mount in Plack::Builder
 		$url .= '/' if $url !~ m!/\z!;
-		$url .= $self->{name} . '/';
-	} else {
-		# either called from a non-PSGI environment (e.g. NNTP/POP3)
-		$self->{-base_url} ||= do {
-			my $url = $self->{url} or return undef;
-			# expand protocol-relative URLs to HTTPS if we're
-			# not inside a web server
-			$url = "https:$url" if $url =~ m!\A//!;
-			$url .= '/' if $url !~ m!/\z!;
-			$url;
-		};
+		return $url .= $self->{name} . '/';
 	}
+	# called from a non-PSGI environment (e.g. NNTP/POP3):
+	$self->{-base_url} ||= do {
+		my $url = $self->{url}->[0] or return undef;
+		# expand protocol-relative URLs to HTTPS if we're
+		# not inside a web server
+		$url = "https:$url" if $url =~ m!\A//!;
+		$url .= '/' if $url !~ m!/\z!;
+		$url;
+	};
+}
+
+sub nntp_url {
+	my ($self) = @_;
+	$self->{-nntp_url} ||= do {
+		# no checking for nntp_usable here, we can point entirely
+		# to non-local servers or users run by a different user
+		my $ns = $self->{nntpserver};
+		my $group = $self->{newsgroup};
+		my @urls;
+		if ($ns && $group) {
+			$ns = [ $ns ] if ref($ns) ne 'ARRAY';
+			@urls = map {
+				my $u = m!\Anntps?://! ? $_ : "nntp://$_";
+				$u .= '/' if $u !~ m!/\z!;
+				$u.$group;
+			} @$ns;
+		}
+
+		my $mirrors = $self->{nntpmirror};
+		if ($mirrors) {
+			my @m;
+			foreach (@$mirrors) {
+				my $u = m!\Anntps?://! ? $_ : "nntp://$_";
+				if ($u =~ m!\Anntps?://[^/]+/?\z!) {
+					if ($group) {
+						$u .= '/' if $u !~ m!/\z!;
+						$u .= $group;
+					} else {
+						warn
+"publicinbox.$self->{name}.nntpmirror=$_ missing newsgroup name\n";
+					}
+				}
+				# else: allow full URLs like:
+				# nntp://news.example.com/alt.example
+				push @m, $u;
+			}
+
+			# List::Util::uniq requires Perl 5.26+, maybe we
+			# can use it by 2030 or so
+			my %seen;
+			@urls = grep { !$seen{$_}++ } (@urls, @m);
+		}
+		\@urls;
+	};
 }
 
 sub nntp_usable {
 	my ($self) = @_;
-	my $ret = $self->mm && $self->search;
-	$self->{mm} = $self->{search} = undef;
+	my $ret = mm($self) && over($self);
+	$self->{mm} = $self->{over} = $self->{search} = undef;
 	$ret;
 }
 
-sub msg_by_path ($$;$) {
-	my ($self, $path, $ref) = @_;
-	# TODO: allow other refs:
-	my $str = git($self)->cat_file('HEAD:'.$path, $ref);
-	$$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s if $str;
-	$str;
+# for v1 users w/o SQLite only
+sub msg_by_path ($$) {
+	my ($self, $path) = @_;
+	git($self)->cat_file('HEAD:'.$path);
+}
+
+sub msg_by_smsg ($$) {
+	my ($self, $smsg) = @_;
+
+	# ghosts may have undef smsg (from SearchThread.node) or
+	# no {blob} field
+	return unless defined $smsg;
+	defined(my $blob = $smsg->{blob}) or return;
+
+	git($self)->cat_file($blob);
 }
 
-sub path_check {
-	my ($self, $path) = @_;
-	git($self)->check('HEAD:'.$path);
+sub smsg_eml {
+	my ($self, $smsg) = @_;
+	my $bref = msg_by_smsg($self, $smsg) or return;
+	my $eml = PublicInbox::Eml->new($bref);
+	$smsg->populate($eml) unless exists($smsg->{num}); # v1 w/o SQLite
+	$eml;
+}
+
+sub mid2num($$) {
+	my ($self, $mid) = @_;
+	my $mm = mm($self) or return;
+	$mm->num_for($mid);
+}
+
+sub smsg_by_mid ($$) {
+	my ($self, $mid) = @_;
+	my $over = over($self) or return;
+	# favor the Message-ID we used for the NNTP article number:
+	defined(my $num = mid2num($self, $mid)) or return;
+	my $smsg = $over->get_art($num) or return;
+	PublicInbox::Smsg::psgi_cull($smsg);
+}
+
+sub msg_by_mid ($$) {
+	my ($self, $mid) = @_;
+
+	over($self) or
+		return msg_by_path($self, mid2path($mid));
+
+	my $smsg = smsg_by_mid($self, $mid);
+	$smsg ? msg_by_smsg($self, $smsg) : undef;
+}
+
+sub recent {
+	my ($self, $opts, $after, $before) = @_;
+	over($self)->recent($opts, $after, $before);
+}
+
+sub modified {
+	my ($self) = @_;
+	if (my $over = over($self)) {
+		my $msgs = $over->recent({limit => 1});
+		if (my $smsg = $msgs->[0]) {
+			return $smsg->{ts};
+		}
+		return time;
+	}
+	git($self)->modified; # v1
+}
+
+# returns prefix => pathname mapping
+# (pathname is NOT public, but prefix is used for Xapian queries)
+sub altid_map ($) {
+	my ($self) = @_;
+	$self->{-altid_map} //= eval {
+		require PublicInbox::AltId;
+		my $altid = $self->{altid} or return {};
+		my %h = map {;
+			my $x = PublicInbox::AltId->new($self, $_);
+			"$x->{prefix}" => $x->{filename}
+		} @$altid;
+		\%h;
+	} // {};
+}
+
+# $obj must respond to ->on_inbox_unlock, which takes Inbox ($self) as an arg
+sub subscribe_unlock {
+	my ($self, $ident, $obj) = @_;
+	$self->{unlock_subs}->{$ident} = $obj;
 }
 
-sub msg_by_mid ($$;$) {
-	my ($self, $mid, $ref) = @_;
-	msg_by_path($self, mid2path($mid), $ref);
+sub unsubscribe_unlock {
+	my ($self, $ident) = @_;
+	delete $self->{unlock_subs}->{$ident};
+}
+
+sub check_inodes ($) {
+	my ($self) = @_;
+	for (qw(over mm)) { # TODO: search
+		$self->{$_}->check_inodes if $self->{$_};
+	}
+}
+
+# called by inotify
+sub on_unlock {
+	my ($self) = @_;
+	check_inodes($self);
+	my $subs = $self->{unlock_subs} or return;
+	for (values %$subs) {
+		eval { $_->on_inbox_unlock($self) };
+		warn "E: $@ ($self->{inboxdir})\n" if $@;
+	}
 }
 
 1;