X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FInbox.pm;h=07e8b5b754071de5c8264d9e95034469e45b1128;hb=ff2db829115a5db9cc4d046b4a9018cfba4ca6c0;hp=dc186b731da8a41bd231ba9edc9594b1642566e0;hpb=70caf43a131fc5bdf7104f82f2acee9d5353d6a8;p=public-inbox.git

diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm
index dc186b73..07e8b5b7 100644
--- a/lib/PublicInbox/Inbox.pm
+++ b/lib/PublicInbox/Inbox.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2016-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2019 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)
@@ -7,47 +7,65 @@ use strict;
 use warnings;
 use PublicInbox::Git;
 use PublicInbox::MID qw(mid2path);
-use Devel::Peek qw(SvREFCNT);
 use PublicInbox::MIME;
-use POSIX qw(strftime);
 
+# 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;
-eval {
-	$cleanup_timer = 'disabled';
-	require PublicInbox::EvCleanup;
-	$cleanup_timer = undef; # OK if we get here
-};
-my $cleanup_broken = $@;
-
+my $cleanup_avail = -1; # 0, or 1
+my $have_devel_peek;
 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;
+		if ($have_devel_peek) {
+			foreach my $f (qw(mm search over)) {
+				# 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
+			}
 		}
-		my $expire = time - 60;
 		if (my $git = $ibx->{git}) {
-			$again = $git->cleanup($expire);
+			$again = $git->cleanup;
 		}
 		if (my $gits = $ibx->{-repo_objs}) {
 			foreach my $git (@$gits) {
-				$again = 1 if $git->cleanup($expire);
+				$again = 1 if $git->cleanup;
 			}
 		}
-		$again ||= !!($ibx->{mm} || $ibx->{search});
+		if ($have_devel_peek) {
+			$again ||= !!($ibx->{over} || $ibx->{mm} ||
+			              $ibx->{search});
+		}
 		$next->{"$ibx"} = $ibx if $again;
 	}
 	$CLEANUP = $next;
 }
 
+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
+		$have_devel_peek = 1;
+	};
+	1;
+}
+
 sub _cleanup_later ($) {
 	my ($self) = @_;
-	return if $cleanup_broken;
-	return unless PublicInbox::EvCleanup::enabled();
-	$cleanup_timer ||= PublicInbox::EvCleanup::later(*cleanup_task);
+	$cleanup_avail = cleanup_possible() if $cleanup_avail < 0;
+	return if $cleanup_avail != 1;
+	$cleanup_timer ||= PublicInbox::DS::later(*cleanup_task);
 	$CLEANUP->{"$self"} = $self;
 }
 
@@ -56,7 +74,7 @@ sub _set_uint ($$$) {
 	my $val = $opts->{$field};
 	if (defined $val) {
 		$val = $val->[-1] if ref($val) eq 'ARRAY';
-		$val = undef if $val !~ /\A\d+\z/;
+		$val = undef if $val !~ /\A[0-9]+\z/;
 	}
 	$opts->{$field} = $val || $default;
 }
@@ -69,7 +87,7 @@ sub _set_limiter ($$$) {
 		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 ($val =~ /\A[a-z][a-z0-9]*\z/) {
@@ -91,7 +109,7 @@ sub new {
 	_set_limiter($opts, $pi_config, 'httpbackend');
 	_set_uint($opts, 'feedmax', 25);
 	$opts->{nntpserver} ||= $pi_config->{'publicinbox.nntpserver'};
-	my $dir = $opts->{mainrepo};
+	my $dir = $opts->{inboxdir};
 	if (defined $dir && -f "$dir/inbox.lock") {
 		$opts->{version} = 2;
 	}
@@ -107,11 +125,11 @@ sub new {
 	bless $opts, $class;
 }
 
-sub git_part {
-	my ($self, $part) = @_;
+sub git_epoch {
+	my ($self, $epoch) = @_;
 	($self->{version} || 1) == 2 or return;
-	$self->{"$part.git"} ||= eval {
-		my $git_dir = "$self->{mainrepo}/git/$part.git";
+	$self->{"$epoch.git"} ||= eval {
+		my $git_dir = "$self->{inboxdir}/git/$epoch.git";
 		my $g = PublicInbox::Git->new($git_dir);
 		$g->{-httpbackend_limiter} = $self->{-httpbackend_limiter};
 		# no cleanup needed, we never cat-file off this, only clone
@@ -122,7 +140,7 @@ sub git_part {
 sub git {
 	my ($self) = @_;
 	$self->{git} ||= eval {
-		my $git_dir = $self->{mainrepo};
+		my $git_dir = $self->{inboxdir};
 		$git_dir .= '/all.git' if (($self->{version} || 1) == 2);
 		my $g = PublicInbox::Git->new($git_dir);
 		$g->{-httpbackend_limiter} = $self->{-httpbackend_limiter};
@@ -131,27 +149,27 @@ sub git {
 	};
 }
 
-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 $cur = $self->{-max_git_epoch};
 	my $changed = git($self)->alternates_changed;
-	if (!defined($part) || $changed) {
+	if (!defined($cur) || $changed) {
 		$self->git->cleanup if $changed;
-		my $gits = "$self->{mainrepo}/git";
+		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;
+				$git_dir =~ m!\A([0-9]+)\.git\z! or next;
 				$max = $1 if $1 > $max;
 			}
-			$part = $self->{-max_git_part} = $max if $max >= 0;
+			$cur = $self->{-max_git_epoch} = $max if $max >= 0;
 		} else {
 			warn "opendir $gits failed: $!\n";
 		}
 	}
-	$part;
+	$cur;
 }
 
 sub mm {
@@ -159,7 +177,7 @@ sub mm {
 	$self->{mm} ||= eval {
 		require PublicInbox::Msgmap;
 		_cleanup_later($self);
-		my $dir = $self->{mainrepo};
+		my $dir = $self->{inboxdir};
 		if (($self->{version} || 1) >= 2) {
 			PublicInbox::Msgmap->new_file("$dir/msgmap.sqlite3");
 		} else {
@@ -173,16 +191,19 @@ sub search ($;$) {
 	my $srch = $self->{search} ||= eval {
 		_cleanup_later($self);
 		require PublicInbox::Search;
-		PublicInbox::Search->new($self, $self->{altid});
+		PublicInbox::Search->new($self);
 	};
-	# TODO: lazily load Xapian
-	# return $srch if $over_only || eval { $srch->xdb };
-	# undef;
+	($over_only || eval { $srch->xdb }) ? $srch : undef;
 }
 
 sub over ($) {
-	my $srch = search($_[0], 1) or return;
-	$srch->{over_ro};
+	my ($self) = @_;
+	my $srch = search($self, 1) or return;
+	$self->{over} ||= eval {
+		my $over = $srch->{over_ro};
+		$over->dbh_new; # may fail
+		$over;
+	}
 }
 
 sub try_cat {
@@ -199,11 +220,11 @@ sub description {
 	my ($self) = @_;
 	my $desc = $self->{description};
 	return $desc if defined $desc;
-	$desc = try_cat("$self->{mainrepo}/description");
+	$desc = try_cat("$self->{inboxdir}/description");
 	local $/ = "\n";
 	chomp $desc;
 	$desc =~ s/\s+/ /smg;
-	$desc = '($REPO_DIR/description missing)' if $desc eq '';
+	$desc = '($INBOX_DIR/description missing)' if $desc eq '';
 	$self->{description} = $desc;
 }
 
@@ -211,7 +232,7 @@ sub cloneurl {
 	my ($self) = @_;
 	my $url = $self->{cloneurl};
 	return $url if $url;
-	$url = try_cat("$self->{mainrepo}/cloneurl");
+	$url = try_cat("$self->{inboxdir}/cloneurl");
 	my @url = split(/\s+/s, $url);
 	local $/ = "\n";
 	chomp @url;
@@ -219,26 +240,22 @@ sub cloneurl {
 }
 
 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) {
+		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 {
@@ -276,12 +293,11 @@ sub nntp_url {
 				# 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, $u;
-			}
+
+			# List::Util::uniq requires Perl 5.26+, maybe we
+			# can use it by 2030 or so
+			my %seen;
+			@urls = grep { !$seen{$_}++ } (@urls, @m);
 		}
 		\@urls;
 	};
@@ -290,7 +306,7 @@ sub nntp_url {
 sub nntp_usable {
 	my ($self) = @_;
 	my $ret = mm($self) && over($self);
-	$self->{mm} = $self->{search} = undef;
+	$self->{mm} = $self->{over} = $self->{search} = undef;
 	$ret;
 }