X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FInbox.pm;h=da81fb67ad22efa8248c208a2d65629512153bbe;hb=23af251dd607c4e75ab1e68063f2c885c48cc035;hp=0d28dd04023e95338e456c8ac2f7403f71bcca12;hpb=b241b1ac6f8b0b47c69dad47716ac9b184e4c098;p=public-inbox.git

diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm
index 0d28dd04..da81fb67 100644
--- a/lib/PublicInbox/Inbox.pm
+++ b/lib/PublicInbox/Inbox.pm
@@ -1,79 +1,63 @@
-# Copyright (C) 2016-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 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 v5.10.1;
 use PublicInbox::Git;
 use PublicInbox::MID qw(mid2path);
-use Devel::Peek qw(SvREFCNT);
-use PublicInbox::MIME;
-use POSIX qw(strftime);
-
-my $cleanup_timer;
-eval {
-	$cleanup_timer = 'disabled';
-	require PublicInbox::EvCleanup;
-	$cleanup_timer = undef; # OK if we get here
-};
-my $cleanup_broken = $@;
-
-my $CLEANUP = {}; # string(inbox) -> inbox
-sub cleanup_task () {
-	$cleanup_timer = undef;
-	my $next = {};
-	for my $ibx (values %$CLEANUP) {
-		my $again;
-		foreach my $f (qw(mm search)) {
-			delete $ibx->{$f} if SvREFCNT($ibx->{$f}) == 1;
-		}
-		my $expire = time - 60;
-		if (my $git = $ibx->{git}) {
-			$again = $git->cleanup($expire);
-		}
-		if (my $gits = $ibx->{-repo_objs}) {
-			foreach my $git (@$gits) {
-				$again = 1 if $git->cleanup($expire);
-			}
-		}
-		$again ||= !!($ibx->{mm} || $ibx->{search});
-		$next->{"$ibx"} = $ibx if $again;
+use PublicInbox::Eml;
+use List::Util qw(max);
+use Carp qw(croak);
+
+# returns true if further checking is required
+sub check_inodes ($) {
+	for (qw(over mm)) { $_[0]->{$_}->check_inodes if $_[0]->{$_} }
+}
+
+sub do_cleanup {
+	my ($ibx) = @_;
+	my $live;
+	if (defined $ibx->{git}) {
+		$live = $ibx->isa(__PACKAGE__) ? $ibx->{git}->cleanup(1)
+					: $ibx->{git}->cleanup_if_unlinked;
+		delete($ibx->{git}) unless $live;
+	}
+	if ($live) {
+		check_inodes($ibx);
+	} else {
+		delete(@$ibx{qw(over mm description cloneurl
+				-imap_url -nntp_url)});
+	}
+	my $srch = $ibx->{search} // $ibx;
+	delete @$srch{qw(xdb qp)};
+	for my $git (@{$ibx->{-repo_objs} // []}) {
+		$live = 1 if $git->cleanup(1);
 	}
-	$CLEANUP = $next;
+	PublicInbox::DS::add_uniq_timer($ibx+0, 5, \&do_cleanup, $ibx) if $live;
 }
 
 sub _cleanup_later ($) {
-	my ($self) = @_;
-	return if $cleanup_broken;
-	return unless PublicInbox::EvCleanup::enabled();
-	$cleanup_timer ||= PublicInbox::EvCleanup::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\d+\z/;
-	}
-	$opts->{$field} = $val || $default;
+	# no need to require DS, here, if it were enabled another
+	# module would've require'd it, already
+	eval { PublicInbox::DS::in_loop() } and
+		PublicInbox::DS::add_uniq_timer($_[0]+0, 30, \&do_cleanup, @_)
 }
 
 sub _set_limiter ($$$) {
-	my ($self, $pi_config, $pfx) = @_;
+	my ($self, $pi_cfg, $pfx) = @_;
 	my $lkey = "-${pfx}_limiter";
-	$self->{$lkey} ||= eval {
+	$self->{$lkey} //= do {
 		# full key is: publicinbox.$NAME.httpbackendmax
 		my $mkey = $pfx.'max';
 		my $val = $self->{$mkey} or return;
 		my $lim;
-		if ($val =~ /\A\d+\z/) {
+		if ($val =~ /\A[0-9]+\z/) {
 			require PublicInbox::Qspawn;
 			$lim = PublicInbox::Qspawn::Limiter->new($val);
 		} elsif ($val =~ /\A[a-z][a-z0-9]*\z/) {
-			$lim = $pi_config->limiter($val);
+			$lim = $pi_cfg->limiter($val);
 			warn "$mkey limiter=$val not found\n" if !$lim;
 		} else {
 			warn "$mkey limiter=$val not understood\n";
@@ -84,259 +68,276 @@ sub _set_limiter ($$$) {
 
 sub new {
 	my ($class, $opts) = @_;
-	my $v = $opts->{address} ||= 'public-inbox@example.com';
+	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->{mainrepo};
-	if (defined $dir && -f "$dir/inbox.lock") {
-		$opts->{version} = 2;
+	my $pi_cfg = delete $opts->{-pi_cfg};
+	_set_limiter($opts, $pi_cfg, 'httpbackend');
+	my $fmax = $opts->{feedmax};
+	if (defined($fmax) && $fmax =~ /\A[0-9]+\z/) {
+		$opts->{feedmax} += 0;
+	} else {
+		delete $opts->{feedmax};
+	}
+	# 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 git_part {
-	my ($self, $part) = @_;
-	($self->{version} || 1) == 2 or return;
-	$self->{"$part.git"} ||= eval {
-		my $git_dir = "$self->{mainrepo}/git/$part.git";
+sub version {
+	$_[0]->{version} //= -f "$_[0]->{inboxdir}/inbox.lock" ? 2 : 1
+}
+
+sub git_epoch {
+	my ($self, $epoch) = @_; # v2-only, callers always supply $epoch
+	$self->{"$epoch.git"} //= do {
+		my $git_dir = "$self->{inboxdir}/git/$epoch.git";
+		return unless -d $git_dir;
 		my $g = PublicInbox::Git->new($git_dir);
-		$g->{-httpbackend_limiter} = $self->{-httpbackend_limiter};
-		# no cleanup needed, we never cat-file off this, only clone
+		my $lim = $self->{-httpbackend_limiter};
+		$g->{-httpbackend_limiter} = $lim if $lim;
+		# caller must manually cleanup when done
 		$g;
 	};
 }
 
 sub git {
 	my ($self) = @_;
-	$self->{git} ||= eval {
-		my $git_dir = $self->{mainrepo};
-		$git_dir .= '/all.git' if (($self->{version} || 1) == 2);
+	$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};
+		my $lim = $self->{-httpbackend_limiter};
+		$g->{-httpbackend_limiter} = $lim if $lim;
 		_cleanup_later($self);
 		$g;
 	};
 }
 
-sub max_git_part {
+sub max_git_epoch {
 	my ($self) = @_;
-	my $v = $self->{version};
-	return unless defined($v) && $v == 2;
-	my $part = $self->{-max_git_part};
-	my $changed = git($self)->alternates_changed;
-	if (!defined($part) || $changed) {
-		$self->git->cleanup if $changed;
-		my $gits = "$self->{mainrepo}/git";
+	return if $self->version < 2;
+	my $cur = $self->{-max_git_epoch};
+	my $changed;
+	if (!defined($cur) || ($changed = git($self)->alternates_changed)) {
+		$self->{git}->cleanup 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(\d+)\.git\z! or next;
-				$max = $1 if $1 > $max;
-			}
-			$part = $self->{-max_git_part} = $max if $max >= 0;
-		} else {
-			warn "opendir $gits failed: $!\n";
+			my $max = max(map {
+				substr($_, 0, -4) + 0; # drop ".git" suffix
+			} grep(/\A[0-9]+\.git\z/, readdir($dh))) // return;
+			$cur = $self->{-max_git_epoch} = $max;
 		}
 	}
-	$part;
+	$cur;
 }
 
-sub mm {
+sub mm_file {
 	my ($self) = @_;
-	$self->{mm} ||= eval {
+	my $d = $self->{inboxdir};
+	($self->version >= 2 ? $d : "$d/public-inbox").'/msgmap.sqlite3';
+}
+
+sub mm {
+	my ($self, $req) = @_;
+	$self->{mm} //= eval {
 		require PublicInbox::Msgmap;
 		_cleanup_later($self);
-		my $dir = $self->{mainrepo};
-		if (($self->{version} || 1) >= 2) {
-			PublicInbox::Msgmap->new_file("$dir/msgmap.sqlite3");
-		} else {
-			PublicInbox::Msgmap->new($dir);
-		}
-	};
+		PublicInbox::Msgmap->new_file($self);
+	} // ($req ? croak("E: $@") : undef);
 }
 
 sub search {
 	my ($self) = @_;
-	$self->{search} ||= eval {
+	$self->{search} // eval {
 		_cleanup_later($self);
-		PublicInbox::Search->new($self, $self->{altid});
+		require PublicInbox::Search;
+		my $srch = PublicInbox::Search->new($self);
+		(eval { $srch->xdb }) ? ($self->{search} = $srch) : undef;
 	};
 }
 
+# isrch is preferred for read-only interfaces if available since it
+# reduces kernel cache and FD overhead
+sub isrch { $_[0]->{isrch} // search($_[0]) }
+
+sub over {
+	my ($self, $req) = @_;
+	$self->{over} // eval {
+		my $srch = $self->{search} // do {
+			require PublicInbox::Search;
+			PublicInbox::Search->new($self);
+		};
+		_cleanup_later($self);
+		my $over = PublicInbox::Over->new("$srch->{xpfx}/over.sqlite3");
+		$over->dbh; # may fail
+		$self->{over} = $over;
+	} // ($req ? croak("E: $@") : undef);
+}
+
 sub try_cat {
 	my ($path) = @_;
-	my $rv = '';
-	if (open(my $fh, '<', $path)) {
-		local $/;
-		$rv = <$fh>;
-	}
-	$rv;
+	open(my $fh, '<', $path) or return '';
+	local $/;
+	<$fh> // '';
 }
 
-sub description {
-	my ($self) = @_;
-	my $desc = $self->{description};
-	return $desc if defined $desc;
-	$desc = try_cat("$self->{mainrepo}/description");
+sub cat_desc ($) {
+	my $desc = try_cat($_[0]);
 	local $/ = "\n";
 	chomp $desc;
+	utf8::decode($desc);
 	$desc =~ s/\s+/ /smg;
-	$desc = '($REPO_DIR/description missing)' if $desc eq '';
-	$self->{description} = $desc;
+	$desc eq '' ? undef : $desc;
+}
+
+sub description {
+	my ($self) = @_;
+	($self->{description} //= cat_desc("$self->{inboxdir}/description")) //
+		'($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);
-	local $/ = "\n";
-	chomp @url;
-	$self->{cloneurl} = \@url;
+	$self->{cloneurl} // do {
+		my $s = try_cat("$self->{inboxdir}/cloneurl");
+		my @urls = split(/\s+/s, $s);
+		scalar(@urls) ? ($self->{cloneurl} = \@urls) : undef;
+	} // [];
 }
 
 sub base_url {
-	my ($self, $env) = @_;
-	my $scheme;
-	if ($env && ($scheme = $env->{'psgi.url_scheme'})) { # PSGI env
-		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 && $env->{'psgi.url_scheme'}) {
+		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):
+	my $url = $self->{url} // return undef;
+	$url = $url->[0] // return undef;
+	# expand protocol-relative URLs to HTTPS if we're
+	# not inside a web server
+	substr($url, 0, 0, 'https:') if substr($url, 0, 2) eq '//';
+	$url .= '/' if substr($url, -1, 1) ne '/';
+	$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";
-					}
+# imapserver, nntpserver, and pop3server configs are used here:
+sub _x_url ($$$) {
+	my ($self, $x, $ctx) = @_; # $x is "imap", "nntp", or "pop3"
+	# no checking for nntp_usable here, we can point entirely
+	# to non-local servers or users run by a different user
+	my $ns = $self->{"${x}server"} //
+	       $ctx->{www}->{pi_cfg}->get_all("publicinbox.${x}server");
+	my $group = $self->{newsgroup};
+	my @urls;
+	if ($ns && $group) {
+		@urls = map {
+			my $u = m!\A${x}s?://! ? $_ : "$x://$_";
+			$u .= '/' if $u !~ m!/\z!;
+			$u.$group;
+		} @$ns;
+	}
+	if (my $mirrors = $self->{"${x}mirror"}) {
+		my @m;
+		for (@$mirrors) {
+			my $u = m!\A${x}s?://! ? $_ : "$x://$_";
+			if ($u =~ m!\A${x}s?://[^/]+/?\z!) {
+				if ($group) {
+					$u .= '/' if $u !~ m!/\z!;
+					$u .= $group;
+				} else { # n.b. IMAP and POP3 use "newsgroup"
+					warn <<EOM;
+publicinbox.$self->{name}.${x}mirror=$_ missing newsgroup name
+EOM
 				}
-				# else: allow full URLs like:
-				# nntp://news.example.com/alt.example
-				push @m, $u;
-			}
-			my %seen = map { $_ => 1 } @urls;
-			foreach my $u (@m) {
-				next if $seen{$u};
-				$seen{$u} = 1;
-				push @urls, $u;
 			}
+			# else: allow full URLs like:
+			# nntp://news.example.com/alt.example
+			push @m, $u;
 		}
-		\@urls;
-	};
+
+		# List::Util::uniq requires Perl 5.26+, maybe we
+		# can use it by 2030 or so
+		my %seen;
+		@urls = grep { !$seen{$_}++ } (@urls, @m);
+	}
+	\@urls;
 }
 
+# my ($self, $ctx) = @_;
+sub imap_url { $_[0]->{-imap_url} //= _x_url($_[0], 'imap', $_[1]) }
+sub nntp_url { $_[0]->{-nntp_url} //= _x_url($_[0], 'nntp', $_[1]) }
+sub pop3_url { $_[0]->{-pop3_url} //= _x_url($_[0], 'pop3', $_[1]) }
+
 sub nntp_usable {
 	my ($self) = @_;
-	my $ret = $self->mm && $self->search;
-	$self->{mm} = $self->{search} = undef;
+	my $ret = mm($self) && over($self);
+	delete @$self{qw(mm over search)};
 	$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 ($$;$) {
-	my ($self, $smsg, $ref) = @_;
+sub msg_by_smsg ($$) {
+	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;
-
-	my $str = git($self)->cat_file($blob, $ref);
-	$$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s if $str;
-	$str;
+	$smsg // return;
+	$self->git->cat_file($smsg->{blob} // return);
 }
 
-sub smsg_mime {
-	my ($self, $smsg, $ref) = @_;
-	if (my $s = msg_by_smsg($self, $smsg, $ref)) {
-		$smsg->{mime} = PublicInbox::MIME->new($s);
-		return $smsg;
-	}
-}
-
-sub mid2num($$) {
-	my ($self, $mid) = @_;
-	my $mm = mm($self) or return;
-	$mm->num_for($mid);
+sub smsg_eml {
+	my ($self, $smsg) = @_;
+	my $bref = msg_by_smsg($self, $smsg) or return;
+	my $eml = PublicInbox::Eml->new($bref);
+	$smsg->{num} // $smsg->populate($eml);
+	$eml;
 }
 
 sub smsg_by_mid ($$) {
 	my ($self, $mid) = @_;
-	my $srch = search($self) or return;
-	# favor the Message-ID we used for the NNTP article number:
-	defined(my $num = mid2num($self, $mid)) or return;
-	my $smsg = $srch->lookup_article($num) or return;
-	PublicInbox::SearchMsg::psgi_cull($smsg);
+	my $over = $self->over or return;
+	my $smsg;
+	if (my $mm = $self->mm) {
+		# favor the Message-ID we used for the NNTP article number:
+		my $num = $mm->num_for($mid) // return;
+		$smsg = $over->get_art($num);
+	} else {
+		my ($id, $prev);
+		$smsg = $over->next_by_mid($mid, \$id, \$prev);
+	}
+	$smsg ? PublicInbox::Smsg::psgi_cull($smsg) : undef;
 }
 
-sub msg_by_mid ($$;$) {
-	my ($self, $mid, $ref) = @_;
-	my $srch = search($self) or
-		return msg_by_path($self, mid2path($mid), $ref);
+sub msg_by_mid ($$) {
+	my ($self, $mid) = @_;
 	my $smsg = smsg_by_mid($self, $mid);
-	$smsg ? msg_by_smsg($self, $smsg, $ref) : undef;
+	$smsg ? msg_by_smsg($self, $smsg) : msg_by_path($self, mid2path($mid));
 }
 
 sub recent {
 	my ($self, $opts, $after, $before) = @_;
-	search($self)->{over_ro}->recent($opts, $after, $before);
+	$self->over->recent($opts, $after, $before);
 }
 
 sub modified {
 	my ($self) = @_;
-	if (my $srch = search($self)) {
-		my $msgs = $srch->{over_ro}->recent({limit => 1});
+	if (my $over = $self->over) {
+		my $msgs = $over->recent({limit => 1});
 		if (my $smsg = $msgs->[0]) {
 			return $smsg->{ts};
 		}
@@ -345,4 +346,57 @@ sub modified {
 	git($self)->modified; # v1
 }
 
+# returns prefix => pathname mapping
+# (pathname is NOT public, but prefix is used for Xapian queries)
+sub altid_map ($) {
+	my ($self) = @_;
+	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} = $obj;
+}
+
+sub unsubscribe_unlock {
+	my ($self, $ident) = @_;
+	delete $self->{unlock_subs}->{$ident};
+}
+
+# called by inotify
+sub on_unlock {
+	my ($self) = @_;
+	check_inodes($self);
+	my $subs = $self->{unlock_subs} or return;
+	for my $obj (values %$subs) {
+		eval { $obj->on_inbox_unlock($self) };
+		warn "E: $@ ($self->{inboxdir})\n" if $@;
+	}
+}
+
+sub uidvalidity { $_[0]->{uidvalidity} //= eval { $_[0]->mm->created_at } }
+
+sub eidx_key { $_[0]->{newsgroup} // $_[0]->{inboxdir} }
+
+sub mailboxid { # rfc 8474, 8620, 8621
+	my ($self, $imap_slice) = @_;
+	my $pfx = defined($imap_slice) ? $self->{newsgroup} : $self->{name};
+	utf8::encode($pfx); # to octets
+	# RFC 8620, 1.2 recommends not starting with dash or digits
+	# "A good solution to these issues is to prefix every id with a single
+	#  alphabetical character."
+	'M'.join('', map { sprintf('%02x', ord) } split(//, $pfx)) .
+		(defined($imap_slice) ? sprintf('-%x', $imap_slice) : '') .
+		sprintf('-%x', uidvalidity($self) // 0)
+}
+
 1;