From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,AWL,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id 9B462200A6 for ; Tue, 27 Oct 2020 07:55:01 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Subject: [PATCH 48/52] extsearch: wire up remaining Inbox-like methods for WWW Date: Tue, 27 Oct 2020 07:54:49 +0000 Message-Id: <20201027075453.19163-49-e@80x24.org> In-Reply-To: <20201027075453.19163-1-e@80x24.org> References: <20201027075453.19163-1-e@80x24.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: This lets us pretend an ExtSearch object is an Inbox object in most of the existing WWW code. --- lib/PublicInbox/Config.pm | 12 +++++++++ lib/PublicInbox/ExtSearch.pm | 25 ++++++++++++++++++ lib/PublicInbox/Inbox.pm | 51 ++++++++++++++++++------------------ lib/PublicInbox/WWW.pm | 3 ++- 4 files changed, 64 insertions(+), 27 deletions(-) diff --git a/lib/PublicInbox/Config.pm b/lib/PublicInbox/Config.pm index d57c361a..d425cc9b 100644 --- a/lib/PublicInbox/Config.pm +++ b/lib/PublicInbox/Config.pm @@ -89,6 +89,11 @@ sub lookup_name ($$) { $self->{-by_name}->{$name} // _fill($self, "publicinbox.$name"); } +sub lookup_ei { + my ($self, $name) = @_; + $self->{-ei_by_name}->{$name} //= _fill_ei($self, "eindex.$name"); +} + sub each_inbox { my ($self, $cb, @arg) = @_; # may auto-vivify if config file is non-existent: @@ -457,6 +462,13 @@ EOF $ibx } +sub _fill_ei ($$) { + my ($self, $pfx) = @_; + require PublicInbox::ExtSearch; + my $d = $self->{"$pfx.topdir"}; + defined($d) && -d $d ? PublicInbox::ExtSearch->new($d) : undef; +} + sub urlmatch { my ($self, $key, $url) = @_; state $urlmatch_broken; # requires git 1.8.5 diff --git a/lib/PublicInbox/ExtSearch.pm b/lib/PublicInbox/ExtSearch.pm index 3e8ca82c..66c99eaa 100644 --- a/lib/PublicInbox/ExtSearch.pm +++ b/lib/PublicInbox/ExtSearch.pm @@ -3,6 +3,7 @@ # Read-only external (detached) index for cross inbox search. # This is a read-only counterpart to PublicInbox::ExtSearchIdx +# and behaves like PublicInbox::Inbox AND PublicInbox::Search package PublicInbox::ExtSearch; use strict; use v5.10.1; @@ -21,6 +22,8 @@ sub new { }, __PACKAGE__; } +sub search { $_[0] } # self + # overrides PublicInbox::Search::_xdb sub _xdb { my ($self) = @_; @@ -38,7 +41,29 @@ sub git { $self->{git} //= PublicInbox::Git->new("$self->{topdir}/ALL.git"); } +sub mm { undef } + +sub altid_map { {} } + +sub description { + my ($self) = @_; + ($self->{description} //= + PublicInbox::Inbox::cat_desc("$self->{topdir}/description")) // + '$EINDEX_DIR/description missing'; +} + +sub cloneurl { [] } # TODO + +sub base_url { 'https://example.com/TODO/' } +sub nntp_url { [] } + no warnings 'once'; *smsg_eml = \&PublicInbox::Inbox::smsg_eml; +*smsg_by_mid = \&PublicInbox::Inbox::smsg_by_mid; +*msg_by_mid = \&PublicInbox::Inbox::msg_by_mid; +*modified = \&PublicInbox::Inbox::modified; +*recent = \&PublicInbox::Inbox::recent; + +*max_git_epoch = *nntp_usable = *msg_by_path = \&mm; # undef 1; diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm index cd5c098a..1d18cdf1 100644 --- a/lib/PublicInbox/Inbox.pm +++ b/lib/PublicInbox/Inbox.pm @@ -225,16 +225,19 @@ sub try_cat { $rv; } +sub cat_desc ($) { + 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} //= 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)'; + ($self->{description} //= cat_desc("$self->{inboxdir}/description")) // + '($INBOX_DIR/description missing)'; } sub cloneurl { @@ -342,39 +345,35 @@ sub smsg_eml { $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); + 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 ($$) { my ($self, $mid) = @_; - - over($self) or - return msg_by_path($self, mid2path($mid)); - my $smsg = smsg_by_mid($self, $mid); - $smsg ? msg_by_smsg($self, $smsg) : undef; + $smsg ? msg_by_smsg($self, $smsg) : msg_by_path($self, mid2path($mid)); } sub recent { my ($self, $opts, $after, $before) = @_; - over($self)->recent($opts, $after, $before); + $self->over->recent($opts, $after, $before); } sub modified { my ($self) = @_; - if (my $over = over($self)) { + if (my $over = $self->over) { my $msgs = $over->recent({limit => 1}); if (my $smsg = $msgs->[0]) { return $smsg->{ts}; diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm index e3b589cb..cdbcff1e 100644 --- a/lib/PublicInbox/WWW.pm +++ b/lib/PublicInbox/WWW.pm @@ -210,7 +210,8 @@ sub news_cgit_fallback ($) { # returns undef if valid, array ref response if invalid sub invalid_inbox ($$) { my ($ctx, $inbox) = @_; - my $ibx = $ctx->{www}->{pi_config}->lookup_name($inbox); + my $ibx = $ctx->{www}->{pi_config}->lookup_name($inbox) // + $ctx->{www}->{pi_config}->lookup_ei($inbox); if (defined $ibx) { $ctx->{-inbox} = $ibx; return;