use PublicInbox::WwwStream;
use PublicInbox::Reply;
use PublicInbox::ViewDiff qw(flush_diff);
+use PublicInbox::Eml;
use POSIX qw(strftime);
use Time::Local qw(timegm);
use PublicInbox::Smsg qw(subject_normalized);
} else {
$first = $ibx->msg_by_mid($mid) or return;
}
- my $mime = PublicInbox::MIME->new($first);
+ my $mime = PublicInbox::Eml->new($first);
$ctx->{-obfs_ibx} = $ibx->{obfuscate} ? $ibx : undef;
my $hdr = $ctx->{hdr} = $mime->header_obj;
$ctx->{obuf} = _msg_page_prepare_obuf($hdr, $ctx, 0);
my $ibx = $ctx->{-inbox};
my $next = $ibx->over->next_by_mid($ctx->{mid}, \$id, \$prev);
$ctx->{more} = [ $id, $prev, $next ] if $next;
- $smsg = $ibx->smsg_mime($smsg) or return '';
+ my $eml = $ibx->smsg_eml($smsg) or return '';
$ctx->{mhref} = '../' . mid_href($smsg->{mid}) . '/';
- my $mime = delete $smsg->{mime};
- $ctx->{obuf} = _msg_page_prepare_obuf($mime->header_obj, $ctx, $nr);
- multipart_text_as_html($mime, $ctx);
+ $ctx->{obuf} = _msg_page_prepare_obuf($eml->header_obj, $ctx, $nr);
+ multipart_text_as_html($eml, $ctx);
${delete $ctx->{obuf}} .= '</pre><hr>';
}
sub fold_addresses ($) {
return $_[0] if length($_[0]) <= COLS;
# try to fold on commas after non-word chars before $lim chars,
- # Try to get the "," preceeded by ">" or ")", but avoid folding
+ # Try to get the "," preceded by ">" or ")", but avoid folding
# on the comma where somebody uses "Lastname, Firstname".
# We also try to keep the last and penultimate addresses in
# the list on the same line if possible, hence the extra \z
# human-friendly format
sub fmt_ts ($) { strftime('%Y-%m-%d %k:%M', gmtime($_[0])) }
+# Displays the text of of the message for /$INBOX/$MSGID/[Tt]/ endpoint
# this is already inside a <pre>
-sub index_entry {
- my ($smsg, $ctx, $more) = @_;
- my $subj = $smsg->subject;
- my $mid_raw = $smsg->mid;
+sub eml_entry {
+ my ($ctx, $smsg, $eml, $more) = @_;
+ my $subj = delete $smsg->{subject};
+ my $mid_raw = $smsg->{mid};
my $id = id_compress($mid_raw, 1);
my $id_m = 'm'.$id;
-
my $root_anchor = $ctx->{root_anchor} || '';
my $irt;
my $obfs_ibx = $ctx->{-obfs_ibx};
$rv .= $subj . "\n";
$rv .= _th_index_lite($mid_raw, \$irt, $id, $ctx);
my @tocc;
- my $ds = $smsg->ds; # for v1 non-Xapian/SQLite users
- # deleting {mime} is critical to memory use,
- # the rest of the fields saves about 400K as we iterate across 1K msgs
- my ($mime) = delete @$smsg{qw(mime ds ts blob subject)};
+ my $ds = delete $smsg->{ds}; # for v1 non-Xapian/SQLite users
+
+ # Deleting these fields saves about 400K as we iterate across 1K msgs
+ delete @$smsg{qw(ts blob)};
- my $hdr = $mime->header_obj;
+ my $hdr = $eml->header_obj;
my $from = _hdr_names_html($hdr, 'From');
obfuscate_addrs($obfs_ibx, $from) if $obfs_ibx;
$rv .= "From: $from @ ".fmt_ts($ds)." UTC";
# scan through all parts, looking for displayable text
$ctx->{mhref} = $mhref;
$ctx->{obuf} = \$rv;
- msg_iter($mime, \&add_text_body, $ctx, 1);
+ $eml->each_part(\&add_text_body, $ctx, 1);
delete $ctx->{obuf};
# add the footer
my $nr_c = scalar @$children;
my $nr_s = 0;
my $siblings;
- if (my $smsg = $node->{smsg}) {
- # delete saves about 200KB on a 1K message thread
- if (my $refs = delete $smsg->{references}) {
- ($$irt) = ($refs =~ m/$MID_EXTRACT\z/o);
- }
+ # delete saves about 200KB on a 1K message thread
+ if (my $refs = delete $node->{references}) {
+ ($$irt) = ($refs =~ m/$MID_EXTRACT\z/o);
}
my $irt_map = $mapping->{$$irt} if defined $$irt;
if (defined $irt_map) {
$rv .= $pad . $irt_map->[0];
if ($idx > 0) {
my $prev = $siblings->[$idx - 1];
- my $pmid = $prev->{id};
+ my $pmid = $prev->{mid};
if ($idx > 2) {
my $s = ($idx - 1). ' preceding siblings ...';
$rv .= pad_link($pmid, $level, $s);
} elsif ($idx == 2) {
- my $ppmid = $siblings->[0]->{id};
+ my $ppmid = $siblings->[0]->{mid};
$rv .= $pad . $mapping->{$ppmid}->[0];
}
$rv .= $pad . $mapping->{$pmid}->[0];
my $s_s = nr_to_s($nr_s, 'sibling', 'siblings');
my $s_c = nr_to_s($nr_c, 'reply', 'replies');
$attr =~ s!\n\z!</b>\n!s;
- $attr =~ s!<a\nhref.*</a> !!s; # no point in duplicating subject
+ $attr =~ s!<a\nhref.*</a> (?:" )?!!s; # no point in dup subject
$attr =~ s!<a\nhref=[^>]+>([^<]+)</a>!$1!s; # no point linking to self
$rv .= "<b>@ $attr";
if ($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 .= $pad ."<a\nhref=#r$id>$s_s, $s_c; $ctx->{s_nr}</a>\n";
sub pre_thread { # walk_thread callback
my ($ctx, $level, $node, $idx) = @_;
- $ctx->{mapping}->{$node->{id}} = [ '', $node, $idx, $level ];
+ $ctx->{mapping}->{$node->{mid}} = [ '', $node, $idx, $level ];
skel_dump($ctx, $level, $node);
}
-sub thread_index_entry {
- my ($ctx, $level, $smsg) = @_;
+sub thread_eml_entry {
+ my ($ctx, $level, $smsg, $eml) = @_;
my ($beg, $end) = thread_adj_level($ctx, $level);
- $beg . '<pre>' . index_entry($smsg, $ctx, 0) . '</pre>' . $end;
+ $beg . '<pre>' . eml_entry($ctx, $smsg, $eml, 0) . '</pre>' . $end;
}
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 (my $eml = $ctx->{-inbox}->smsg_eml($node)) {
+ return thread_eml_entry($ctx, $level, $node, $eml);
} else {
return ghost_index_entry($ctx, $level, $node);
}
my ($rootset, $ctx) = @_;
my $ibx = $ctx->{-inbox};
my @q = map { (0, $_) } @$rootset;
- my ($smsg, $level);
+ my ($smsg, $eml, $level);
while (@q) {
$level = shift @q;
- my $node = shift @q or next;
+ $smsg = shift @q or next;
my $cl = $level + 1;
- unshift @q, map { ($cl, $_) } @{$node->{children}};
- $smsg = $ibx->smsg_mime($node->{smsg}) and last;
+ unshift @q, map { ($cl, $_) } @{$smsg->{children}};
+ $eml = $ibx->smsg_eml($smsg) and last;
}
- return missing_thread($ctx) unless $smsg;
+ return missing_thread($ctx) unless $eml;
$ctx->{-obfs_ibx} = $ibx->{obfuscate} ? $ibx : undef;
$ctx->{-title_html} = ascii_html($smsg->{subject});
- $ctx->{-html_tip} = thread_index_entry($ctx, $level, $smsg);
+ $ctx->{-html_tip} = thread_eml_entry($ctx, $level, $smsg, $eml);
$ctx->{-queue} = \@q;
PublicInbox::WwwStream->response($ctx, 200, \&stream_thread_i);
}
return stream_thread($rootset, $ctx) unless $ctx->{flat};
# flat display: lazy load the full message from smsg
- my $smsg;
- while (my $m = shift @$msgs) {
- $smsg = $ibx->smsg_mime($m) and last;
+ my ($smsg, $eml);
+ while ($smsg = shift @$msgs) {
+ $eml = $ibx->smsg_eml($smsg) and last;
}
return missing_thread($ctx) unless $smsg;
$ctx->{-title_html} = ascii_html($smsg->{subject});
- $ctx->{-html_tip} = '<pre>'.index_entry($smsg, $ctx, scalar @$msgs);
+ $ctx->{-html_tip} = '<pre>'.eml_entry($ctx, $smsg, $eml, scalar @$msgs);
$ctx->{msgs} = $msgs;
PublicInbox::WwwStream->response($ctx, 200, \&thread_html_i);
}
my ($nr, $ctx) = @_;
my $msgs = $ctx->{msgs} or return;
while (my $smsg = shift @$msgs) {
- $ctx->{-inbox}->smsg_mime($smsg) or next;
- return index_entry($smsg, $ctx, scalar @$msgs);
+ my $eml = $ctx->{-inbox}->smsg_eml($smsg) or next;
+ return eml_entry($ctx, $smsg, $eml, scalar @$msgs);
}
my ($skel) = delete @$ctx{qw(skel msgs)};
$$skel;
}
sub multipart_text_as_html {
- # ($mime, $ctx) = @_; # msg_iter will do "$_[0] = undef"
+ # ($mime, $ctx) = @_; # each_part may do "$_[0] = undef"
# scan through all parts, looking for displayable text
- msg_iter($_[0], \&add_text_body, $_[1], 1);
+ $_[0]->each_part(\&add_text_body, $_[1], 1);
+}
+
+sub submsg_hdr ($$) {
+ my ($ctx, $eml) = @_;
+ my $obfs_ibx = $ctx->{-obfs_ibx};
+ my $rv = $ctx->{obuf};
+ $$rv .= "\n";
+ for my $h (qw(From To Cc Subject Date Message-ID X-Alt-Message-ID)) {
+ my @v = $eml->header($h);
+ for my $v (@v) {
+ obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx;
+ $v = ascii_html($v);
+ $$rv .= "$h: $v\n";
+ }
+ }
}
sub attach_link ($$$$;$) {
my ($ctx, $ct, $p, $fn, $err) = @_;
- my ($part, $depth, @idx) = @$p;
- my $nl = $idx[-1] > 1 ? "\n" : '';
- my $idx = join('.', @idx);
+ my ($part, $depth, $idx) = @$p;
+
+ # Eml iteration clobbers multipart ->{bdy}, so do not offer
+ # downloads for 0-byte multipart attachments
+ return unless $part->{bdy};
+
+ my $nl = $idx eq '1' ? '' : "\n"; # like join("\n", ...)
my $size = bytes::length($part->body);
# hide attributes normally, unless we want to aid users in
$desc = ascii_html($desc);
$$rv .= ($desc eq '') ? "$ts --]" : "$desc --]\n[-- $ts --]";
$$rv .= "</a>\n";
+
+ submsg_hdr($ctx, $part) if $part->{is_submsg};
+
undef;
}
-sub add_text_body { # callback for msg_iter
+sub add_text_body { # callback for each_part
my ($p, $ctx) = @_;
my $upfx = $ctx->{mhref};
my $ibx = $ctx->{-inbox};
- # $p - from msg_iter: [ Email::MIME, depth, @idx ]
- my ($part, $depth, @idx) = @$p;
+ my $l = $ctx->{-linkify} //= PublicInbox::Linkify->new;
+ # $p - from each_part: [ Email::MIME-like, depth, $idx ]
+ my ($part, $depth, $idx) = @$p;
my $ct = $part->content_type || 'text/plain';
my $fn = $part->filename;
my ($s, $err) = msg_part_text($part, $ct);
return attach_link($ctx, $ct, $p, $fn) unless defined $s;
+ my $rv = $ctx->{obuf};
+ if ($part->{is_submsg}) {
+ submsg_hdr($ctx, $part);
+ $$rv .= "\n";
+ }
+
# makes no difference to browsers, and don't screw up filename
# 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 $spfx;
# split off quoted and unquoted blocks:
my @sections = PublicInbox::MsgIter::split_quotes($s);
undef $s; # free memory
- my $rv = $ctx->{obuf};
- if (defined($fn) || $depth > 0 || $err) {
+ if (defined($fn) || ($depth > 0 && !$part->{is_submsg}) || $err) {
# badly-encoded message with $err? tell the world about it!
attach_link($ctx, $ct, $p, $fn, $err);
$$rv .= "\n";
}
- my $l = $ctx->{-linkify} //= PublicInbox::Linkify->new;
foreach my $cur (@sections) {
if ($cur =~ /\A>/) {
# we use a <span> here to allow users to specify
}
undef $cur; # free memory
}
-
- obfuscate_addrs($ibx, $$rv) if $ibx->{obfuscate};
}
sub _msg_page_prepare_obuf {
sub find_mid_root {
my ($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} = $ctx->{root_idx};
return 0;
}
}
sub skel_dump { # walk_thread callback
- my ($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 = $ctx->{cur};
sub _skel_ghost {
my ($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);
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 $smsg = $node->{smsg} // $ctx->{-inbox}->smsg_by_mid($mid);
- if ($smsg) {
+ my ($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 '';
my $ds = $smsg->{ds};
my @next_prev = @subj; # full copy
my $omit = dedupe_subject($prev_subj, \@subj, ' "');
$prev_subj = \@next_prev;
+ $subj = join(' ', @subj);
$subj = ascii_html($subj);
obfuscate_addrs($obfs_ibx, $subj) if $obfs_ibx;
$href = mid_href($mid);
sub ghost_index_entry {
my ($ctx, $level, $node) = @_;
my ($beg, $end) = thread_adj_level($ctx, $level);
- $beg . '<pre>'. ghost_parent($ctx->{-upfx}, $node->{id})
+ $beg . '<pre>'. ghost_parent($ctx->{-upfx}, $node->{mid})
. '</pre>' . $end;
}