-# Copyright (C) 2016-2018 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)
use warnings;
use PublicInbox::Git;
use PublicInbox::MID qw(mid2path);
-use PublicInbox::MIME;
+use PublicInbox::Eml;
# Long-running "git-cat-file --batch" processes won't notice
# unlinked packs, so we need to restart those processes occasionally.
my $cleanup_avail = -1; # 0, or 1
my $have_devel_peek;
my $CLEANUP = {}; # string(inbox) -> inbox
+
+sub git_cleanup ($) {
+ my ($self) = @_;
+ my $git = $self->{git} or return;
+ $git->cleanup;
+}
+
sub cleanup_task () {
$cleanup_timer = undef;
my $next = {};
for my $ibx (values %$CLEANUP) {
my $again;
if ($have_devel_peek) {
- foreach my $f (qw(mm search over)) {
+ 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;
# refcnt is zero when tmp is out-of-scope
}
}
- if (my $git = $ibx->{git}) {
- $again = $git->cleanup;
- }
+ git_cleanup($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->{over} || $ibx->{mm} ||
- $ibx->{search});
+ $again ||= !!$ibx->{search};
}
$next->{"$ibx"} = $ibx if $again;
}
}
sub cleanup_possible () {
- # no need to require EvCleanup, here, if it were enabled another
+ # no need to require DS, here, if it were enabled another
# module would've require'd it, already
- eval { PublicInbox::EvCleanup::enabled() } or return 0;
+ eval { PublicInbox::DS::in_loop() } or return 0;
eval {
require Devel::Peek; # needs separate package in Fedora
my ($self) = @_;
$cleanup_avail = cleanup_possible() if $cleanup_avail < 0;
return if $cleanup_avail != 1;
- $cleanup_timer ||= PublicInbox::EvCleanup::later(*cleanup_task);
+ $cleanup_timer //= PublicInbox::DS::later(\&cleanup_task);
$CLEANUP->{"$self"} = $self;
}
sub _set_limiter ($$$) {
my ($self, $pi_config, $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/) {
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};
+ my $dir = $opts->{inboxdir};
if (defined $dir && -f "$dir/inbox.lock") {
$opts->{version} = 2;
}
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} // 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
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};
_cleanup_later($self);
};
}
-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};
+ return if $self->version < 2;
+ my $cur = $self->{-max_git_epoch};
my $changed = git($self)->alternates_changed;
- if (!defined($part) || $changed) {
- $self->git->cleanup if $changed;
- my $gits = "$self->{mainrepo}/git";
+ 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(\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 {
my ($self) = @_;
$self->{mm} ||= eval {
require PublicInbox::Msgmap;
- _cleanup_later($self);
- my $dir = $self->{mainrepo};
- if (($self->{version} || 1) >= 2) {
+ my $dir = $self->{inboxdir};
+ if ($self->version >= 2) {
PublicInbox::Msgmap->new_file("$dir/msgmap.sqlite3");
} else {
PublicInbox::Msgmap->new($dir);
};
}
-sub search ($;$) {
- my ($self, $over_only) = @_;
+sub search ($;$$) {
+ my ($self, $over_only, $ctx) = @_;
my $srch = $self->{search} ||= eval {
_cleanup_later($self);
require PublicInbox::Search;
- PublicInbox::Search->new($self, $self->{altid});
+ PublicInbox::Search->new($self);
+ };
+ ($over_only || eval { $srch->xdb }) ? $srch : do {
+ $ctx and $ctx->{env}->{'psgi.errors'}->print(<<EOF);
+`$self->{name}' search went away unexpectedly
+EOF
+ undef;
};
- ($over_only || eval { $srch->xdb }) ? $srch : undef;
}
-sub over ($) {
- my ($self) = @_;
- my $srch = search($self, 1) or return;
- $self->{over} ||= eval {
- my $over = $srch->{over_ro};
- $over->dbh_new; # may fail
+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;
- }
+ };
}
sub try_cat {
$rv;
}
-sub description {
- my ($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;
- $desc = '($INBOX_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, $s);
+ scalar(@urls) ? \@urls : undef
+ }) // [];
}
sub base_url {
- my ($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) {
+ 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 {
# 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;
};
$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;
+ $self->git->cat_file($blob);
}
-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($$) {
- my ($self, $mid) = @_;
- my $mm = mm($self) or return;
- $mm->num_for($mid);
+sub smsg_eml {
+ my ($self, $smsg) = @_;
+ my $bref = msg_by_smsg($self, $smsg) or return;
+ my $eml = PublicInbox::Eml->new($bref);
+ $smsg->populate($eml) unless exists($smsg->{num}); # v1 w/o SQLite
+ $eml;
}
sub smsg_by_mid ($$) {
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::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:
+ defined(my $num = $mm->num_for($mid)) or 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 ($$;$) {
- my ($self, $mid, $ref) = @_;
-
- over($self) or
- return msg_by_path($self, mid2path($mid), $ref);
-
+sub msg_by_mid ($$) {
+ 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, $before) = @_;
- over($self)->recent($opts, $after, $before);
+ $self->over->recent($opts, $after, $before);
}
sub modified {
my ($self) = @_;
- if (my $over = over($self)) {
+ if (my $over = $self->over) {
my $msgs = $over->recent({limit => 1});
if (my $smsg = $msgs->[0]) {
return $smsg->{ts};
git($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} = $obj;
+}
+
+sub unsubscribe_unlock {
+ my ($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 $@;
+ }
+}
+
+sub uidvalidity { $_[0]->{uidvalidity} //= $_[0]->mm->created_at }
+
+sub eidx_key { $_[0]->{newsgroup} // $_[0]->{inboxdir} }
+
1;