X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FOverIdx.pm;h=189bd21d93bc6731192dd26a333cc79f04b89c3e;hb=e67dc3e9fc73029332a632d022002d3ce80c1306;hp=08f87447bea5a288a6f1c8fa7992bb966e129930;hpb=06cd576bb9b73eb177728fead06de8c3fac8d7a3;p=public-inbox.git diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm index 08f87447..189bd21d 100644 --- a/lib/PublicInbox/OverIdx.pm +++ b/lib/PublicInbox/OverIdx.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2018 all contributors +# Copyright (C) 2018-2019 all contributors # License: AGPL-3.0+ # for XOVER, OVER in NNTP, and feeds/homepage/threads in PSGI @@ -13,8 +13,8 @@ use warnings; use base qw(PublicInbox::Over); use IO::Handle; use DBI qw(:sql_types); # SQL_BLOB -use PublicInbox::MID qw/id_compress mids references/; -use PublicInbox::SearchMsg; +use PublicInbox::MID qw/id_compress mids_for_index references/; +use PublicInbox::SearchMsg qw(subject_normalized); use Compress::Zlib qw(compress); use PublicInbox::Search; @@ -79,8 +79,15 @@ sub mid2id { } sub delete_by_num { - my ($self, $num) = @_; + my ($self, $num, $tid_ref) = @_; my $dbh = $self->{dbh}; + if ($tid_ref) { + my $sth = $dbh->prepare_cached(<<'', undef, 1); +SELECT tid FROM over WHERE num = ? LIMIT 1 + + $sth->execute($num); + $$tid_ref = $sth->fetchrow_array; # may be undef + } foreach (qw(over id2num)) { $dbh->prepare_cached(<<"")->execute($num); DELETE FROM $_ WHERE num = ? @@ -207,8 +214,8 @@ sub link_refs { $tid; } -sub parse_references ($$$$) { - my ($self, $smsg, $mid0, $mids) = @_; +sub parse_references ($$$) { + my ($smsg, $mid0, $mids) = @_; my $mime = $smsg->{mime}; my $hdr = $mime->header_obj; my $refs = references($hdr); @@ -230,6 +237,15 @@ sub parse_references ($$$$) { \@keep; } +# normalize subjects so they are suitable as pathnames for URLs +# XXX: consider for removal +sub subject_path ($) { + my ($subj) = @_; + $subj = subject_normalized($subj); + $subj =~ s![^a-zA-Z0-9_\.~/\-]+!_!g; + lc($subj); +} + sub add_overview { my ($self, $mime, $bytes, $num, $oid, $mid0) = @_; my $lines = $mime->body_raw =~ tr!\n!\n!; @@ -240,12 +256,12 @@ sub add_overview { lines => $lines, blob => $oid, }, 'PublicInbox::SearchMsg'; - my $mids = mids($mime->header_obj); - my $refs = $self->parse_references($smsg, $mid0, $mids); + my $mids = mids_for_index($mime->header_obj); + my $refs = parse_references($smsg, $mid0, $mids); my $subj = $smsg->subject; my $xpath; if ($subj ne '') { - $xpath = PublicInbox::Search::subject_path($subj); + $xpath = subject_path($subj); $xpath = id_compress($xpath); } my $dd = $smsg->to_doc_data($oid, $mid0); @@ -262,7 +278,7 @@ sub add_over { my $vivified = 0; $self->begin_lazy; - $self->delete_by_num($num); + $self->delete_by_num($num, \$old_tid); foreach my $mid (@$mids) { my $v = 0; each_by_mid($self, $mid, ['tid'], sub { @@ -304,20 +320,35 @@ INSERT INTO id2num (id, num) VALUES (?,?) } } -sub delete_articles { - my ($self, $nums) = @_; - my $dbh = $self->connect; - $self->delete_by_num($_) foreach @$nums; -} - +# returns number of removed messages +# $oid may be undef to match only on $mid sub remove_oid { my ($self, $oid, $mid) = @_; + my $nr = 0; $self->begin_lazy; each_by_mid($self, $mid, ['ddd'], sub { my ($smsg) = @_; - $self->delete_by_num($smsg->{num}) if $smsg->{blob} eq $oid; + if (!defined($oid) || $smsg->{blob} eq $oid) { + $self->delete_by_num($smsg->{num}); + $nr++; + } 1; }); + $nr; +} + +sub num_mid0_for_oid { + my ($self, $oid, $mid) = @_; + my ($num, $mid0); + $self->begin_lazy; + each_by_mid($self, $mid, ['ddd'], sub { + my ($smsg) = @_; + my $blob = $smsg->{blob}; + return 1 if (!defined($blob) || $blob ne $oid); # continue; + ($num, $mid0) = ($smsg->{num}, $smsg->{mid}); + 0; # done + }); + ($num, $mid0); } sub create_tables {