@ $attr";
if ($nr_c) {
- my $cmid = $children->[0]->{id};
+ my $cmid = $children->[0]->{mid};
$rv .= $pad . $mapping->{$cmid}->[0];
if ($nr_c > 2) {
my $s = ($nr_c - 1). ' more replies';
$rv .= pad_link($cmid, $level + 1, $s);
} elsif (my $cn = $children->[1]) {
- $rv .= $pad . $mapping->{$cn->{id}}->[0];
+ $rv .= $pad . $mapping->{$cn->{mid}}->[0];
}
}
my $next = $siblings->[$idx+1] if $siblings && $idx >= 0;
if ($next) {
- my $nmid = $next->{id};
+ my $nmid = $next->{mid};
$rv .= $pad . $mapping->{$nmid}->[0];
my $nnext = $nr_s - $idx;
if ($nnext > 2) {
my $s = ($nnext - 1).' subsequent siblings';
$rv .= pad_link($nmid, $level, $s);
} elsif (my $nn = $siblings->[$idx + 2]) {
- $rv .= $pad . $mapping->{$nn->{id}}->[0];
+ $rv .= $pad . $mapping->{$nn->{mid}}->[0];
}
}
$rv .= $pad ."$s_s, $s_c; $ctx->{s_nr}\n";
@@ -379,7 +367,7 @@ sub walk_thread ($$$) {
sub pre_thread { # walk_thread callback
my ($ctx, $level, $node, $idx) = @_;
- $ctx->{mapping}->{$node->{id}} = [ '', $node, $idx, $level ];
+ $ctx->{mapping}->{$node->{mid}} = [ '', $node, $idx, $level ];
skel_dump($ctx, $level, $node);
}
@@ -398,8 +386,8 @@ sub stream_thread_i { # PublicInbox::WwwStream::getline callback
my $node = shift @$q or next;
my $cl = $level + 1;
unshift @$q, map { ($cl, $_) } @{$node->{children}};
- if (my $smsg = $ctx->{-inbox}->smsg_mime($node->{smsg})) {
- return thread_index_entry($ctx, $level, $smsg);
+ if ($ctx->{-inbox}->smsg_mime($node)) {
+ return thread_index_entry($ctx, $level, $node);
} else {
return ghost_index_entry($ctx, $level, $node);
}
@@ -417,12 +405,12 @@ sub stream_thread ($$) {
my $node = shift @q or next;
my $cl = $level + 1;
unshift @q, map { ($cl, $_) } @{$node->{children}};
- $smsg = $ibx->smsg_mime($node->{smsg}) and last;
+ $smsg = $ibx->smsg_mime($node) and last;
}
return missing_thread($ctx) unless $smsg;
$ctx->{-obfs_ibx} = $ibx->{obfuscate} ? $ibx : undef;
- $ctx->{-title_html} = ascii_html($smsg->subject);
+ $ctx->{-title_html} = ascii_html($smsg->{subject});
$ctx->{-html_tip} = thread_index_entry($ctx, $level, $smsg);
$ctx->{-queue} = \@q;
PublicInbox::WwwStream->response($ctx, 200, \&stream_thread_i);
@@ -468,7 +456,7 @@ sub thread_html {
$smsg = $ibx->smsg_mime($m) and last;
}
return missing_thread($ctx) unless $smsg;
- $ctx->{-title_html} = ascii_html($smsg->subject);
+ $ctx->{-title_html} = ascii_html($smsg->{subject});
$ctx->{-html_tip} = ''.index_entry($smsg, $ctx, scalar @$msgs);
$ctx->{msgs} = $msgs;
PublicInbox::WwwStream->response($ctx, 200, \&thread_html_i);
@@ -486,38 +474,22 @@ sub thread_html_i { # PublicInbox::WwwStream::getline callback
}
sub multipart_text_as_html {
- my (undef, $mhref, $ctx) = @_; # $mime = $_[0]
- $ctx->{mhref} = $mhref;
+ # ($mime, $ctx) = @_; # each_part may do "$_[0] = undef"
# scan through all parts, looking for displayable text
- msg_iter($_[0], \&add_text_body, $ctx, 1);
-}
-
-sub flush_quote {
- my ($s, $l, $quot) = @_;
-
- my $rv = $l->to_html($$quot);
-
- # we use a here to allow users to specify their own
- # color for quoted text
- $$quot = undef;
- $$s .= qq() . $rv . ''
+ $_[0]->each_part(\&add_text_body, $_[1], 1);
}
sub attach_link ($$$$;$) {
my ($ctx, $ct, $p, $fn, $err) = @_;
- my ($part, $depth, @idx) = @$p;
- my $nl = $idx[-1] > 1 ? "\n" : '';
- my $idx = join('.', @idx);
+ my ($part, $depth, $idx) = @$p;
+ my $nl = substr($idx, -2) eq '.1' ? '' : "\n"; # like join("\n", ...)
my $size = bytes::length($part->body);
# hide attributes normally, unless we want to aid users in
# spotting MUA problems:
$ct =~ s/;.*// unless $err;
$ct = ascii_html($ct);
- my $desc = $part->header('Content-Description');
- $desc = $fn unless defined $desc;
- $desc = '' unless defined $desc;
my $sfn;
if (defined $fn && $fn =~ /\A$PublicInbox::Hval::FN\z/o) {
$sfn = $fn;
@@ -529,22 +501,25 @@ sub attach_link ($$$$;$) {
my $rv = $ctx->{obuf};
$$rv .= qq($nl{mhref}$idx-$sfn">);
if ($err) {
- $$rv .= "[-- Warning: decoded text below may be mangled --]\n";
+ $$rv .= <header('Content-Description') // $fn // '';
$desc = ascii_html($desc);
$$rv .= ($desc eq '') ? "$ts --]" : "$desc --]\n[-- $ts --]";
$$rv .= "\n";
undef;
}
-sub add_text_body { # callback for msg_iter
+sub add_text_body { # callback for each_part
my ($p, $ctx) = @_;
my $upfx = $ctx->{mhref};
my $ibx = $ctx->{-inbox};
- # $p - from msg_iter: [ Email::MIME, depth, @idx ]
- my ($part, $depth, @idx) = @$p;
+ # $p - from each_part: [ Email::MIME-like, depth, $idx ]
+ my ($part, $depth, $idx) = @$p;
my $ct = $part->content_type || 'text/plain';
my $fn = $part->filename;
my ($s, $err) = msg_part_text($part, $ct);
@@ -554,14 +529,21 @@ sub add_text_body { # callback for msg_iter
# link generation in diffs with the extra '%0D'
$s =~ s/\r\n/\n/sg;
+ # will be escaped to `•' in HTML
+ obfuscate_addrs($ibx, $s, "\x{2022}") if $ibx->{obfuscate};
+
# always support diff-highlighting, but we can't linkify hunk
# headers for solver unless some coderepo are configured:
my $diff;
- if ($s =~ /^(?:diff|---|\+{3}) /ms) {
- # diffstat anchors do not link across attachments or messages:
- $idx[0] = $upfx . $idx[0] if $upfx ne '';
- $ctx->{-apfx} = join('/', @idx);
- $ctx->{-anchors} = {}; # attr => filename
+ if ($s =~ /^--- [^\n]+\n\+{3} [^\n]+\n@@ /ms) {
+ # diffstat anchors do not link across attachments or messages,
+ # -apfx is just a stable prefix for making diffstat anchors
+ # linkable to the first diff hunk w/o crossing attachments
+ $idx =~ tr!.!/!; # compatibility with previous versions
+ $ctx->{-apfx} = $upfx . $idx;
+
+ # do attr => filename mappings for diffstats in git diffs:
+ $ctx->{-anchors} = {} if $s =~ /^diff --git /sm;
$diff = 1;
delete $ctx->{-long_path};
my $spfx;
@@ -587,8 +569,8 @@ sub add_text_body { # callback for msg_iter
$s .= "\n" unless $s =~ /\n\z/s;
# split off quoted and unquoted blocks:
- my @sections = split(/((?:^>[^\n]*\n)+)/sm, $s);
- $s = '';
+ my @sections = PublicInbox::MsgIter::split_quotes($s);
+ undef $s; # free memory
my $rv = $ctx->{obuf};
if (defined($fn) || $depth > 0 || $err) {
# badly-encoded message with $err? tell the world about it!
@@ -598,17 +580,19 @@ sub add_text_body { # callback for msg_iter
my $l = $ctx->{-linkify} //= PublicInbox::Linkify->new;
foreach my $cur (@sections) {
if ($cur =~ /\A>/) {
- flush_quote($rv, $l, \$cur);
+ # we use a here to allow users to specify
+ # their own color for quoted text
+ $$rv .= qq();
+ $$rv .= $l->to_html($cur);
+ $$rv .= '';
} elsif ($diff) {
- flush_diff($rv, $ctx, \$cur);
+ flush_diff($ctx, \$cur);
} else {
# regular lines, OK
$$rv .= $l->to_html($cur);
- $cur = undef;
}
+ undef $cur; # free memory
}
-
- obfuscate_addrs($ibx, $$rv) if $ibx->{obfuscate};
}
sub _msg_page_prepare_obuf {
@@ -631,10 +615,9 @@ sub _msg_page_prepare_obuf {
}
my @title; # (Subject[0], From[0])
for my $v ($hdr->header('From')) {
- $v = PublicInbox::Hval->new($v);
- my @n = PublicInbox::Address::names($v->raw);
+ my @n = PublicInbox::Address::names($v);
+ $v = ascii_html($v);
$title[1] //= ascii_html(join(', ', @n));
- $v = $v->as_html;
if ($obfs_ibx) {
obfuscate_addrs($obfs_ibx, $v);
obfuscate_addrs($obfs_ibx, $title[1]);
@@ -651,16 +634,15 @@ sub _msg_page_prepare_obuf {
}
my @subj = $hdr->header('Subject');
if (@subj) {
- for my $v (@subj) {
+ my $v = ascii_html(shift @subj);
+ obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx;
+ $rv .= 'Subject: ';
+ $rv .= $over ? qq($v\n) : "$v\n";
+ $title[0] = $v;
+ for $v (@subj) { # multi-Subject message :<
$v = ascii_html($v);
obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx;
- $rv .= 'Subject: ';
- if ($over) {
- $rv .= qq($v\n);
- } else {
- $rv .= "$v\n";
- }
- $title[0] //= $v;
+ $rv .= "Subject: $v\n";
}
} else { # dummy anchor for thread skeleton at bottom of page
$rv .= qq() if $over;
@@ -673,8 +655,7 @@ sub _msg_page_prepare_obuf {
}
$ctx->{-title_html} = join(' - ', @title);
if (scalar(@$mids) == 1) { # common case
- my $mid = PublicInbox::Hval->new_msgid($mids->[0]);
- my $mhtml = $mid->as_html;
+ my $mhtml = ascii_html($mids->[0]);
$rv .= "Message-ID: <$mhtml> ";
$rv .= "(raw)\n";
} else {
@@ -690,7 +671,7 @@ sub _msg_page_prepare_obuf {
}
$rv .= _parent_headers($hdr, $over);
$rv .= "\n";
- $ctx->{obuf} = \$rv;
+ \$rv;
}
sub SKEL_EXPAND () {
@@ -752,9 +733,8 @@ sub _parent_headers {
$refs = references($hdr);
my $irt = pop @$refs;
if (defined $irt) {
- my $v = PublicInbox::Hval->new_msgid($irt);
- my $html = $v->as_html;
- my $href = $v->{href};
+ my $html = ascii_html($irt);
+ my $href = mid_href($irt);
$rv .= "In-Reply-To: <";
$rv .= "$html>\n";
}
@@ -774,9 +754,8 @@ sub _parent_headers {
# returns a string buffer via ->getline
sub html_footer {
- my ($ctx) = @_;
+ my ($ctx, $hdr) = @_;
my $ibx = $ctx->{-inbox};
- my $hdr = delete $ctx->{hdr};
my $upfx = '../';
my $skel = " index";
my $rv = '';
@@ -788,17 +767,17 @@ sub html_footer {
$next = $prev = ' ';
if (my $n = $ctx->{next_msg}) {
- $n = PublicInbox::Hval->new_msgid($n)->{href};
+ $n = mid_href($n);
$next = "next";
}
my $u;
my $par = $ctx->{parent_msg};
if ($par) {
- $u = PublicInbox::Hval->new_msgid($par)->{href};
+ $u = mid_href($par);
$u = "$upfx$u/";
}
if (my $p = $ctx->{prev_msg}) {
- $prev = PublicInbox::Hval->new_msgid($p)->{href};
+ $prev = mid_href($p);
if ($p && $par && $p eq $par) {
$prev = "prev parent';
@@ -820,9 +799,9 @@ sub html_footer {
}
sub linkify_ref_no_over {
- my $v = PublicInbox::Hval->new_msgid($_[0]);
- my $html = $v->as_html;
- my $href = $v->{href};
+ my ($mid) = @_;
+ my $href = mid_href($mid);
+ my $html = ascii_html($mid);
"<$html>";
}
@@ -834,9 +813,8 @@ sub anchor_for {
sub ghost_parent {
my ($upfx, $mid) = @_;
- $mid = PublicInbox::Hval->new_msgid($mid);
- my $href = $mid->{href};
- my $html = $mid->as_html;
+ my $href = mid_href($mid);
+ my $html = ascii_html($mid);
qq{[parent not found: <$html>]};
}
@@ -848,7 +826,7 @@ sub indent_for {
sub find_mid_root {
my ($ctx, $level, $node, $idx) = @_;
++$ctx->{root_idx} if $level == 0;
- if ($node->{id} eq $ctx->{mid}) {
+ if ($node->{mid} eq $ctx->{mid}) {
$ctx->{found_mid_at} = $ctx->{root_idx};
return 0;
}
@@ -905,25 +883,25 @@ sub missing_thread {
sub dedupe_subject {
my ($prev_subj, $subj, $val) = @_;
- my $omit = ''; # '"' denotes identical text omitted
+ my $omit; # '"' denotes identical text omitted
my (@prev_pop, @curr_pop);
while (@$prev_subj && @$subj && $subj->[-1] eq $prev_subj->[-1]) {
push(@prev_pop, pop(@$prev_subj));
push(@curr_pop, pop(@$subj));
- $omit ||= $val;
+ $omit //= $val;
}
pop @$subj if @$subj && $subj->[-1] =~ /^re:\s*/i;
if (scalar(@curr_pop) == 1) {
- $omit = '';
+ $omit = undef;
push @$prev_subj, @prev_pop;
push @$subj, @curr_pop;
}
- $omit;
+ $omit // '';
}
sub skel_dump { # walk_thread callback
- my ($ctx, $level, $node) = @_;
- my $smsg = $node->{smsg} or return _skel_ghost($ctx, $level, $node);
+ my ($ctx, $level, $smsg) = @_;
+ $smsg->{blob} or return _skel_ghost($ctx, $level, $smsg);
my $skel = $ctx->{skel};
my $cur = $ctx->{cur};
@@ -933,7 +911,7 @@ sub skel_dump { # walk_thread callback
$$skel .= delete($ctx->{sl_note}) || '';
}
- my $f = ascii_html($smsg->from_name);
+ my $f = ascii_html($smsg->{from_name});
my $obfs_ibx = $ctx->{-obfs_ibx};
obfuscate_addrs($obfs_ibx, $f) if $obfs_ibx;
@@ -972,7 +950,7 @@ sub skel_dump { # walk_thread callback
# Subject is never undef, this mail was loaded from
# our Xapian which would've resulted in '' if it were
# really missing (and Filter rejects empty subjects)
- my @subj = split(/ /, subject_normalized($smsg->subject));
+ my @subj = split(/ /, subject_normalized($smsg->{subject}));
# remove common suffixes from the subject if it matches the previous,
# so we do not show redundant text at the end.
my $prev_subj = $ctx->{prev_subj} || [];
@@ -997,7 +975,7 @@ sub skel_dump { # walk_thread callback
$map->[0] = "$d$end";
$id = "\nid=r".$id;
} else {
- $m = $ctx->{-upfx}.mid_escape($mid).'/';
+ $m = $ctx->{-upfx}.mid_href($mid).'/';
}
$$skel .= $d . "" . $end;
1;
@@ -1006,14 +984,13 @@ sub skel_dump { # walk_thread callback
sub _skel_ghost {
my ($ctx, $level, $node) = @_;
- my $mid = $node->{id};
+ my $mid = $node->{mid};
my $d = ' [not found] ';
$d .= ' ' if exists $ctx->{searchview};
$d .= indent_for($level) . th_pfx($level);
my $upfx = $ctx->{-upfx};
- my $m = PublicInbox::Hval->new_msgid($mid);
- my $href = $upfx . $m->{href} . '/';
- my $html = $m->as_html;
+ my $href = $upfx . mid_href($mid) . '/';
+ my $html = ascii_html($mid);
my $mapping = $ctx->{mapping};
my $map = $mapping->{$mid} if $mapping;
@@ -1030,45 +1007,47 @@ sub _skel_ghost {
sub sort_ds {
[ sort {
- (eval { $a->topmost->{smsg}->ds } || 0) <=>
- (eval { $b->topmost->{smsg}->ds } || 0)
+ (eval { $a->topmost->{ds} } || 0) <=>
+ (eval { $b->topmost->{ds} } || 0)
} @{$_[0]} ];
}
# accumulate recent topics if search is supported
# returns 200 if done, 404 if not
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 ($ctx, $level, $smsg) = @_;
+ my $mid = $smsg->{mid};
+ my $has_blob = $smsg->{blob} // do {
+ if (my $by_mid = $ctx->{-inbox}->smsg_by_mid($mid)) {
+ %$smsg = (%$smsg, %$by_mid);
+ 1;
+ }
+ };
+ if ($has_blob) {
+ 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}}, $topic;
}
1;
@@ -1077,7 +1056,7 @@ sub acc_topic { # walk_thread callback
sub dump_topics {
my ($ctx) = @_;
my $order = delete $ctx->{order}; # [ ds, subj1, subj2, subj3, ... ]
- if (!@$order) {
+ unless ($order) {
$ctx->{-html_tip} = '[No topics in range]
';
return 404;
}
@@ -1088,13 +1067,13 @@ 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, $top, @ex) = @$topic;
+ my ($ds, $n, $seen, $top_subj, @extra) = @$topic;
@$topic = ();
- next unless defined $top; # ghost topic
- my $mid = delete $seen->{$top};
- my $href = mid_escape($mid);
- my $prev_subj = [ split(/ /, $top) ];
- $top = PublicInbox::Hval->new($top)->as_html;
+ next unless defined $top_subj; # ghost topic
+ my $mid = delete $seen->{$top_subj};
+ my $href = mid_href($mid);
+ my $prev_subj = [ split(/ /, $top_subj) ];
+ $top_subj = ascii_html($top_subj);
$ds = fmt_ts($ds);
# $n isn't the total number of posts on the topic,
@@ -1110,21 +1089,22 @@ sub dump_topics {
my $mbox = qq(mbox.gz);
my $atom = qq(Atom);
- my $s = "$top\n" .
+ my $s = "$top_subj\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 = join(' ', @subj);
+ $subj = ascii_html($subj);
obfuscate_addrs($obfs_ibx, $subj) if $obfs_ibx;
- $href = mid_escape($mid);
+ $href = mid_href($mid);
$s .= indent_for($level) . TCHILD;
- $s .= "$subj$omit\n";
+ $s .= qq($subj$omit\n);
}
push @out, $s;
}
@@ -1235,7 +1215,7 @@ sub thread_adj_level {
sub ghost_index_entry {
my ($ctx, $level, $node) = @_;
my ($beg, $end) = thread_adj_level($ctx, $level);
- $beg . ''. ghost_parent($ctx->{-upfx}, $node->{id})
+ $beg . ''. ghost_parent($ctx->{-upfx}, $node->{mid})
. '
' . $end;
}