diff options
Diffstat (limited to 'lib/PublicInbox/Inbox.pm')
-rw-r--r-- | lib/PublicInbox/Inbox.pm | 123 |
1 files changed, 60 insertions, 63 deletions
diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm index b7b71268..dd689221 100644 --- a/lib/PublicInbox/Inbox.pm +++ b/lib/PublicInbox/Inbox.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2016-2021 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) @@ -10,32 +10,22 @@ use PublicInbox::MID qw(mid2path); use PublicInbox::Eml; use List::Util qw(max); use Carp qw(croak); +use PublicInbox::Compat qw(uniqstr); -# returns true if further checking is required +# in case DBs get replaced (Xapcmd does it for v1) sub check_inodes ($) { for (qw(over mm)) { $_[0]->{$_}->check_inodes if $_[0]->{$_} } } +# search/over/mm hold onto FDs and description+cloneurl may get updated. +# creating long-lived allocations in the same phase as short-lived +# allocations also leads to fragmentation, so we don't want some stuff +# living too long. 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} // $ibx; + my ($srch) = delete @$ibx{qw(search over mm description cloneurl)}; + $srch //= $ibx; # extsearch delete @$srch{qw(xdb qp)}; - for my $git (@{$ibx->{-repo_objs} // []}) { - $live = 1 if $git->cleanup(1); - } - PublicInbox::DS::add_uniq_timer($ibx+0, 5, \&do_cleanup, $ibx) if $live; } sub _cleanup_later ($) { @@ -48,14 +38,14 @@ sub _cleanup_later ($) { sub _set_limiter ($$$) { my ($self, $pi_cfg, $pfx) = @_; my $lkey = "-${pfx}_limiter"; - $self->{$lkey} ||= do { + $self->{$lkey} //= do { # full key is: publicinbox.$NAME.httpbackendmax my $mkey = $pfx.'max'; my $val = $self->{$mkey} or return; my $lim; if ($val =~ /\A[0-9]+\z/) { - require PublicInbox::Qspawn; - $lim = PublicInbox::Qspawn::Limiter->new($val); + require PublicInbox::Limiter; + $lim = PublicInbox::Limiter->new($val); } elsif ($val =~ /\A[a-z][a-z0-9]*\z/) { $lim = $pi_cfg->limiter($val); warn "$mkey limiter=$val not found\n" if !$lim; @@ -80,12 +70,8 @@ sub new { 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; + for $v (@{delete($opts->{hide}) // []}) { + $opts->{-'hide_'.$_} = 1 for split(/\s*,\s*/, $v); } bless $opts, $class; } @@ -115,7 +101,6 @@ sub git { my $g = PublicInbox::Git->new($git_dir); my $lim = $self->{-httpbackend_limiter}; $g->{-httpbackend_limiter} = $lim if $lim; - _cleanup_later($self); $g; }; } @@ -181,33 +166,18 @@ sub over { } // ($req ? croak("E: $@") : undef); } -sub try_cat { - my ($path) = @_; - open(my $fh, '<', $path) or return ''; - local $/; - <$fh> // ''; -} - -sub cat_desc ($) { - my $desc = try_cat($_[0]); - local $/ = "\n"; - chomp $desc; - utf8::decode($desc); - $desc =~ s/\s+/ /smg; - $desc eq '' ? undef : $desc; -} - sub description { my ($self) = @_; - ($self->{description} //= cat_desc("$self->{inboxdir}/description")) // + ($self->{description} //= + PublicInbox::Git::cat_desc("$self->{inboxdir}/description")) // '($INBOX_DIR/description missing)'; } sub cloneurl { my ($self) = @_; $self->{cloneurl} // do { - my $s = try_cat("$self->{inboxdir}/cloneurl"); - my @urls = split(/\s+/s, $s); + my @urls = split(/\s+/s, + PublicInbox::IO::try_cat "$self->{inboxdir}/cloneurl"); scalar(@urls) ? ($self->{cloneurl} = \@urls) : undef; } // []; } @@ -220,7 +190,8 @@ sub base_url { $url .= '/' if $url !~ m!/\z!; return $url .= $self->{name} . '/'; } - # called from a non-PSGI environment (e.g. NNTP/POP3): + # called from a non-PSGI environment or cross-inbox environment + # where multiple inboxes can have different domains my $url = $self->{url} // return undef; $url = $url->[0] // return undef; # expand protocol-relative URLs to HTTPS if we're @@ -230,8 +201,9 @@ sub base_url { $url; } +# imapserver, nntpserver configs are used here: sub _x_url ($$$) { - my ($self, $x, $ctx) = @_; # $x is "nntp" or "imap" + my ($self, $x, $ctx) = @_; # $x is "imap" or "nntp" # 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"} // @@ -253,7 +225,7 @@ sub _x_url ($$$) { if ($group) { $u .= '/' if $u !~ m!/\z!; $u .= $group; - } else { # n.b. IMAP uses "newsgroup" + } else { # n.b. IMAP and POP3 use "newsgroup" warn <<EOM; publicinbox.$self->{name}.${x}mirror=$_ missing newsgroup name EOM @@ -263,18 +235,36 @@ EOM # nntp://news.example.com/alt.example push @m, $u; } - - # List::Util::uniq requires Perl 5.26+, maybe we - # can use it by 2030 or so - my %seen; - @urls = grep { !$seen{$_}++ } (@urls, @m); + @urls = uniqstr @urls, @m; } \@urls; } # my ($self, $ctx) = @_; -sub nntp_url { $_[0]->{-nntp_url} //= _x_url($_[0], 'nntp', $_[1]) } sub imap_url { $_[0]->{-imap_url} //= _x_url($_[0], 'imap', $_[1]) } +sub nntp_url { $_[0]->{-nntp_url} //= _x_url($_[0], 'nntp', $_[1]) } + +sub pop3_url { + my ($self, $ctx) = @_; + $self->{-pop3_url} //= do { + my $ps = $self->{'pop3server'} // + $ctx->{www}->{pi_cfg}->get_all('publicinbox.pop3server'); + my $group = $self->{newsgroup}; + my @urls; + ($ps && $group) and + @urls = map { m!\Apop3?s?://! ? $_ : "pop3://$_" } @$ps; + if (my $mi = $self->{'pop3mirror'}) { + my @m = map { m!\Apop3?s?://! ? $_ : "pop3://$_" } @$mi; + @urls = uniqstr @urls, @m; + } + my $n = 0; + for (@urls) { $n += s!/+\z!! } + warn <<EOM if $n; +W: pop3server and/or pop3mirror URLs should not end with trailing slash `/' +EOM + \@urls; + } +} sub nntp_usable { my ($self) = @_; @@ -327,11 +317,6 @@ sub msg_by_mid ($$) { $smsg ? msg_by_smsg($self, $smsg) : msg_by_path($self, mid2path($mid)); } -sub recent { - my ($self, $opts, $after, $before) = @_; - $self->over->recent($opts, $after, $before); -} - sub modified { my ($self) = @_; if (my $over = $self->over) { @@ -373,7 +358,7 @@ sub unsubscribe_unlock { # called by inotify sub on_unlock { my ($self) = @_; - check_inodes($self); + check_inodes($self); # DB files may be replaced while holding lock my $subs = $self->{unlock_subs} or return; for my $obj (values %$subs) { eval { $obj->on_inbox_unlock($self) }; @@ -385,6 +370,16 @@ sub uidvalidity { $_[0]->{uidvalidity} //= eval { $_[0]->mm->created_at } } sub eidx_key { $_[0]->{newsgroup} // $_[0]->{inboxdir} } +# only used by NNTP, so we need ->mm anyways +sub art_min { $_[0]->{-art_min} //= eval { $_[0]->mm(1)->min } } + +# used by IMAP, too, which tries to avoid ->mm (but ->{mm} is likely +# faster since it's smaller iff available) +sub art_max { + $_[0]->{-art_max} //= eval { $_[0]->{mm}->max } // + eval { $_[0]->over(1)->max }; +} + sub mailboxid { # rfc 8474, 8620, 8621 my ($self, $imap_slice) = @_; my $pfx = defined($imap_slice) ? $self->{newsgroup} : $self->{name}; @@ -397,4 +392,6 @@ sub mailboxid { # rfc 8474, 8620, 8621 sprintf('-%x', uidvalidity($self) // 0) } +sub thing_type { 'public inbox' } + 1; |