X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FOverIdx.pm;h=fd521bdd1e20a62f5a38e8c5308663b104fadb7f;hb=87678710135973f72722258e171fc00f85c86ec8;hp=62fec0dafb4056118a320ca3fe5ba42030b1fa33;hpb=cfb8d16578e7f2f2e300f9f436205e4a8fc7f322;p=public-inbox.git
diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index 62fec0da..fd521bdd 100644
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2018 all contributors
+# Copyright (C) 2018-2020 all contributors
# License: AGPL-3.0+
# for XOVER, OVER in NNTP, and feeds/homepage/threads in PSGI
@@ -13,14 +13,15 @@ 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::Smsg qw(subject_normalized);
+use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
use Compress::Zlib qw(compress);
use PublicInbox::Search;
sub dbh_new {
my ($self) = @_;
- my $dbh = $self->SUPER::dbh_new;
+ my $dbh = $self->SUPER::dbh_new(1);
$dbh->do('PRAGMA journal_mode = TRUNCATE');
$dbh->do('PRAGMA cache_size = 80000');
create_tables($dbh);
@@ -79,8 +80,15 @@ 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);
+ $$tid_ref = $sth->fetchrow_array; # may be undef
+ }
foreach (qw(over id2num)) {
$dbh->prepare_cached(<<"")->execute($num);
DELETE FROM $_ WHERE num = ?
@@ -223,15 +231,23 @@ sub parse_references ($$$) {
warn "References: <$ref> too long, ignoring\n";
next;
}
- next if $seen{$ref}++;
- push @keep, $ref;
+ push(@keep, $ref) unless $seen{$ref}++;
}
$smsg->{references} = '<'.join('> <', @keep).'>' if @keep;
\@keep;
}
+# normalize subjects so they are suitable as pathnames for URLs
+# XXX: consider for removal
+sub subject_path ($) {
+ my ($subj) = @_;
+ $subj = subject_normalized($subj);
+ $subj =~ s![^a-zA-Z0-9_\.~/\-]+!_!g;
+ lc($subj);
+}
+
sub add_overview {
- my ($self, $mime, $bytes, $num, $oid, $mid0) = @_;
+ my ($self, $mime, $bytes, $num, $oid, $mid0, $times) = @_;
my $lines = $mime->body_raw =~ tr!\n!\n!;
my $smsg = bless {
mime => $mime,
@@ -239,19 +255,22 @@ sub add_overview {
bytes => $bytes,
lines => $lines,
blob => $oid,
- }, 'PublicInbox::SearchMsg';
- my $mids = mids($mime->header_obj);
+ }, 'PublicInbox::Smsg';
+ my $hdr = $mime->header_obj;
+ my $mids = mids_for_index($hdr);
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, $mid0);
utf8::encode($dd);
$dd = compress($dd);
- my $values = [ $smsg->ts, $smsg->ds, $num, $mids, $refs, $xpath, $dd ];
+ my $ds = msg_timestamp($hdr, $times->{autime});
+ my $ts = msg_datestamp($hdr, $times->{cotime});
+ my $values = [ $ts, $ds, $num, $mids, $refs, $xpath, $dd ];
add_over($self, $values);
}
@@ -262,7 +281,7 @@ 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, $mid, ['tid'], sub {
@@ -304,20 +323,35 @@ INSERT INTO id2num (id, num) VALUES (?,?)
}
}
-sub delete_articles {
- my ($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 {