X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FView.pm;h=4d6f44e0bdc8dca7b1b9da9fa88bb3349b6e74da;hb=52a02a813a46940530183ede4d4cc7028290cd8f;hp=9b62ed3c3d954d76ab173c4c32bd561b85c62b30;hpb=d0147582e289fdd4cdd84e91d8b0f8ae9c230124;p=public-inbox.git diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm index 9b62ed3c..4d6f44e0 100644 --- a/lib/PublicInbox/View.pm +++ b/lib/PublicInbox/View.pm @@ -17,6 +17,7 @@ use PublicInbox::Address; 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); @@ -56,7 +57,7 @@ sub msg_page { } 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); @@ -65,7 +66,7 @@ sub msg_page { $ctx->{mhref} = $next ? '../'.mid_href($smsg->{mid}).'/' : ''; multipart_text_as_html($mime, $ctx); $ctx->{-html_tip} = (${delete $ctx->{obuf}} .= '
-sub index_entry { - my ($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}; @@ -200,12 +200,12 @@ sub index_entry { $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"; @@ -243,7 +243,7 @@ sub index_entry { # 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 @@ -322,7 +322,7 @@ sub _th_index_lite { my $s_s = nr_to_s($nr_s, 'sibling', 'siblings'); my $s_c = nr_to_s($nr_c, 'reply', 'replies'); $attr =~ s!\n\z!\n!s; - $attr =~ s! !!s; # no point in duplicating subject + $attr =~ s! (?:" )?!!s; # no point in dup subject $attr =~ s!]+>([^<]+)!$1!s; # no point linking to self $rv .= "@ $attr"; if ($nr_c) { @@ -371,10 +371,10 @@ sub pre_thread { # walk_thread callback 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); - $beg . '' . index_entry($smsg, $ctx, 0) . '' . $end; + $beg . '' . eml_entry($ctx, $smsg, $eml, 0) . '' . $end; } sub stream_thread_i { # PublicInbox::WwwStream::getline callback @@ -386,8 +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 ($ctx->{-inbox}->smsg_mime($node)) { - return thread_index_entry($ctx, $level, $node); + if (my $eml = $ctx->{-inbox}->smsg_eml($node)) { + return thread_eml_entry($ctx, $level, $node, $eml); } else { return ghost_index_entry($ctx, $level, $node); } @@ -399,21 +399,21 @@ sub stream_thread ($$) { 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) 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); + PublicInbox::WwwStream::response($ctx, 200, \&stream_thread_i); } # /$INBOX/$MESSAGE_ID/t/ @@ -451,40 +451,59 @@ sub thread_html { 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} = ''.index_entry($smsg, $ctx, scalar @$msgs); + $ctx->{-html_tip} = ''.eml_entry($ctx, $smsg, $eml, scalar @$msgs); $ctx->{msgs} = $msgs; - PublicInbox::WwwStream->response($ctx, 200, \&thread_html_i); + PublicInbox::WwwStream::response($ctx, 200, \&thread_html_i); } sub thread_html_i { # PublicInbox::WwwStream::getline callback 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); + $$rv .= "$h: $v\n"; + } + } } sub attach_link ($$$$;$) { my ($ctx, $ct, $p, $fn, $err) = @_; - my ($part, $depth, @idx) = @$p; - my $nl = $idx[-1] > 1 ? "\n" : ''; - my $idx = join('.', @idx); + my ($part, $depth, $idx) = @$p; + + # Eml iteration clobbers multipart ->{bdy}, so do not offer + # downloads for 0-byte multipart attachments + return unless $part->{bdy}; + + my $nl = $idx eq '1' ? '' : "\n"; # like join("\n", ...) my $size = bytes::length($part->body); # hide attributes normally, unless we want to aid users in @@ -512,20 +531,30 @@ EOF $desc = ascii_html($desc); $$rv .= ($desc eq '') ? "$ts --]" : "$desc --]\n[-- $ts --]"; $$rv .= "\n"; + + submsg_hdr($ctx, $part) if $part->{is_submsg}; + undef; } -sub add_text_body { # callback for msg_iter +sub add_text_body { # callback for each_part my ($p, $ctx) = @_; my $upfx = $ctx->{mhref}; my $ibx = $ctx->{-inbox}; - # $p - from msg_iter: [ Email::MIME, depth, @idx ] - my ($part, $depth, @idx) = @$p; + my $l = $ctx->{-linkify} //= PublicInbox::Linkify->new; + # $p - from each_part: [ Email::MIME-like, depth, $idx ] + my ($part, $depth, $idx) = @$p; my $ct = $part->content_type || 'text/plain'; my $fn = $part->filename; my ($s, $err) = msg_part_text($part, $ct); return attach_link($ctx, $ct, $p, $fn) unless defined $s; + my $rv = $ctx->{obuf}; + if ($part->{is_submsg}) { + submsg_hdr($ctx, $part); + $$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; @@ -536,11 +565,15 @@ sub add_text_body { # callback for msg_iter # 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 $spfx; @@ -568,13 +601,11 @@ sub add_text_body { # callback for msg_iter # split off quoted and unquoted blocks: my @sections = PublicInbox::MsgIter::split_quotes($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 here to allow users to specify @@ -1096,6 +1127,7 @@ sub dump_topics { 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); @@ -1181,7 +1213,7 @@ sub index_topics { if (@$msgs) { walk_thread(thread_results($ctx, $msgs), $ctx, \&acc_topic); } - PublicInbox::WwwStream->response($ctx, dump_topics($ctx), \&index_nav); + PublicInbox::WwwStream::response($ctx, dump_topics($ctx), \&index_nav); } sub thread_adj_level {