From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 4/8] view: cleanup topic accumulation and dumping
Date: Sat, 15 Feb 2020 09:46:36 +0000 [thread overview]
Message-ID: <20200215094640.19425-5-e@yhbt.net> (raw)
In-Reply-To: <20200215094640.19425-1-e@yhbt.net>
Avoid needlessly normalizing the subject when dumping, since
it's pushed into the @$topic array during accumulation in
normalized form.
We can also safely treat $smsg as a hashref and avoid
calling "->ds" as a method since we know we've got that
loaded via Over||Search and won't have to use Email::MIME
header lookup methods.
---
lib/PublicInbox/View.pm | 41 +++++++++++++++++++----------------------
1 file changed, 19 insertions(+), 22 deletions(-)
diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm
index f0446723..e586b068 100644
--- a/lib/PublicInbox/View.pm
+++ b/lib/PublicInbox/View.pm
@@ -1039,35 +1039,32 @@ sub sort_ds {
sub acc_topic { # walk_thread callback
my ($ctx, $level, $node) = @_;
my $mid = $node->{id};
- my $x = $node->{smsg} || $ctx->{-inbox}->smsg_by_mid($mid);
- my ($subj, $ds);
- my $topic;
- if ($x) {
- $subj = $x->subject;
- $subj = subject_normalized($subj);
+ my $smsg = $node->{smsg} // $ctx->{-inbox}->smsg_by_mid($mid);
+ if ($smsg) {
+ my $subj = subject_normalized($smsg->subject);
$subj = '(no subject)' if $subj eq '';
- $ds = $x->ds;
- if ($level == 0) {
- $topic = [ $ds, 1, { $subj => $mid }, $subj ];
+ my $ds = $smsg->{ds};
+ if ($level == 0) { # new, top-level topic
+ my $topic = [ $ds, 1, { $subj => $mid }, $subj ];
$ctx->{-cur_topic} = $topic;
push @{$ctx->{order}}, $topic;
return 1;
}
- $topic = $ctx->{-cur_topic}; # should never be undef
+ # continue existing topic
+ my $topic = $ctx->{-cur_topic}; # should never be undef
$topic->[0] = $ds if $ds > $topic->[0];
- $topic->[1]++;
+ $topic->[1]++; # bump N+ message counter
my $seen = $topic->[2];
if (scalar(@$topic) == 3) { # parent was a ghost
push @$topic, $subj;
- } elsif (!$seen->{$subj}) {
- push @$topic, $level, $subj;
+ } elsif (!defined($seen->{$subj})) {
+ push @$topic, $level, $subj; # @extra messages
}
$seen->{$subj} = $mid; # latest for subject
} else { # ghost message
return 1 if $level != 0; # ignore child ghosts
- $topic = [ -666, 0, {} ];
- $ctx->{-cur_topic} = $topic;
+ my $topic = $ctx->{-cur_topic} = [ -666, 0, {} ];
push @{$ctx->{order}}, $topic;
}
1;
@@ -1087,7 +1084,7 @@ sub dump_topics {
# sort by recency, this allows new posts to "bump" old topics...
foreach my $topic (sort { $b->[0] <=> $a->[0] } @$order) {
- my ($ds, $n, $seen, $top_subj, @ex) = @$topic;
+ my ($ds, $n, $seen, $top_subj, @extra) = @$topic;
@$topic = ();
next unless defined $top_subj; # ghost topic
my $mid = delete $seen->{$top_subj};
@@ -1111,19 +1108,19 @@ sub dump_topics {
my $atom = qq(<a\nhref="$href/t.atom">Atom</a>);
my $s = "<a\nhref=\"$href/T/$anchor\">$top_subj</a>\n" .
" $ds UTC $n - $mbox / $atom\n";
- for (my $i = 0; $i < scalar(@ex); $i += 2) {
- my $level = $ex[$i];
- my $subj = $ex[$i + 1];
+ for (my $i = 0; $i < scalar(@extra); $i += 2) {
+ my $level = $extra[$i];
+ my $subj = $extra[$i + 1]; # already normalized
$mid = delete $seen->{$subj};
- my @subj = split(/ /, subject_normalized($subj));
+ my @subj = split(/ /, $subj);
my @next_prev = @subj; # full copy
my $omit = dedupe_subject($prev_subj, \@subj, ' "');
$prev_subj = \@next_prev;
- $subj = ascii_html(join(' ', @subj));
+ $subj = ascii_html($subj);
obfuscate_addrs($obfs_ibx, $subj) if $obfs_ibx;
$href = mid_escape($mid);
$s .= indent_for($level) . TCHILD;
- $s .= "<a\nhref=\"$href/T/#u\">$subj</a>$omit\n";
+ $s .= qq(<a\nhref="$href/T/#u">$subj</a>$omit\n);
}
push @out, $s;
}
next prev parent reply other threads:[~2020-02-15 9:46 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-15 9:46 [PATCH 0/8] some view cleanups and minor bugfixes Eric Wong
2020-02-15 9:46 ` [PATCH 1/8] view: remove mhref arg from multipart_text_as_html Eric Wong
2020-02-15 9:46 ` [PATCH 2/8] view: single id="t" for multi-Subject messages Eric Wong
2020-02-15 9:46 ` [PATCH 3/8] view: dump_topics: better naming of top Subject Eric Wong
2020-02-15 9:46 ` Eric Wong [this message]
2020-02-15 9:46 ` [PATCH 5/8] view,searchview: avoid smsg method calls when using SQLite/Xapian Eric Wong
2020-02-15 9:46 ` [PATCH 6/8] view: escape Subject HTML directly Eric Wong
2020-02-15 9:46 ` [PATCH 7/8] view: escape ampersand in Message-IDs Eric Wong
2020-02-15 9:46 ` [PATCH 8/8] view: remove last Hval->new caller Eric Wong
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://public-inbox.org/README
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200215094640.19425-5-e@yhbt.net \
--to=e@yhbt.net \
--cc=meta@public-inbox.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).