diff options
Diffstat (limited to 'lib/PublicInbox/View.pm')
| -rw-r--r-- | lib/PublicInbox/View.pm | 552 |
1 files changed, 297 insertions, 255 deletions
diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm index 26094082..44e1f2a8 100644 --- a/lib/PublicInbox/View.pm +++ b/lib/PublicInbox/View.pm @@ -7,6 +7,7 @@ package PublicInbox::View; use strict; use v5.10.1; use List::Util qw(max); +use Text::Wrap qw(wrap); # stdlib, we need Perl 5.6+ for $huge use PublicInbox::MsgTime qw(msg_datestamp); use PublicInbox::Hval qw(ascii_html obfuscate_addrs prurl mid_href ts2str fmt_ts); @@ -19,6 +20,7 @@ use PublicInbox::WwwStream qw(html_oneshot); 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); use PublicInbox::ContentHash qw(content_hash); @@ -36,14 +38,12 @@ sub msg_page_i { : $ctx->gone('over'); $ctx->{mhref} = ($ctx->{nr} || $ctx->{smsg}) ? "../${\mid_href($smsg->{mid})}/" : ''; - my $obuf = $ctx->{obuf} = _msg_page_prepare_obuf($eml, $ctx); - if (length($$obuf)) { - multipart_text_as_html($eml, $ctx); - $$obuf .= '</pre><hr>'; + if (_msg_page_prepare($eml, $ctx, $smsg->{ts})) { + $eml->each_part(\&add_text_body, $ctx, 1); + print { $ctx->{zfh} } '</pre><hr>'; } - delete $ctx->{obuf}; - $$obuf .= html_footer($ctx, $ctx->{first_hdr}) if !$ctx->{smsg}; - $$obuf; + html_footer($ctx, $ctx->{first_hdr}) if !$ctx->{smsg}; + ''; # XXX TODO cleanup } else { # called by WwwStream::async_next or getline $ctx->{smsg}; # may be undef } @@ -56,14 +56,12 @@ sub no_over_html ($) { my $eml = PublicInbox::Eml->new($bref); $ctx->{mhref} = ''; PublicInbox::WwwStream::init($ctx); - my $obuf = $ctx->{obuf} = _msg_page_prepare_obuf($eml, $ctx); - if (length($$obuf)) { - multipart_text_as_html($eml, $ctx); - $$obuf .= '</pre><hr>'; + if (_msg_page_prepare($eml, $ctx)) { # sets {-title_html} + $eml->each_part(\&add_text_body, $ctx, 1); + print { $ctx->{zfh} } '</pre><hr>'; } - delete $ctx->{obuf}; - eval { $$obuf .= html_footer($ctx, $eml) }; - html_oneshot($ctx, 200, $obuf); + html_footer($ctx, $eml); + $ctx->html_done; } # public functions: (unstable) @@ -82,7 +80,8 @@ sub msg_page { # allow user to easily browse the range around this message if # they have ->over $ctx->{-t_max} = $smsg->{ts}; - PublicInbox::WwwStream::aresponse($ctx, 200, \&msg_page_i); + $ctx->{-spfx} = '../' if $ibx->{-repo_objs}; + PublicInbox::WwwStream::aresponse($ctx, \&msg_page_i); } # /$INBOX/$MESSAGE_ID/#R @@ -184,6 +183,59 @@ sub nr_to_s ($$$) { $nr == 1 ? "$nr $singular" : "$nr $plural"; } +sub addr2urlmap ($) { + my ($ctx) = @_; + # cache makes a huge difference with /[tT] and large threads + my $key = PublicInbox::Git::host_prefix_url($ctx->{env}, ''); + my $ent = $ctx->{www}->{pi_cfg}->{-addr2urlmap}->{$key} // do { + my $by_addr = $ctx->{www}->{pi_cfg}->{-by_addr}; + my (%addr2url, $url); + while (my ($addr, $ibx) = each %$by_addr) { + $url = $ibx->base_url // $ibx->base_url($ctx->{env}); + $addr2url{$addr} = ascii_html($url) if defined $url; + } + # don't allow attackers to randomly change Host: headers + # and OOM us if the server handles all hostnames: + my $tmp = $ctx->{www}->{pi_cfg}->{-addr2urlmap}; + my @k = keys %$tmp; # random order + delete @$tmp{@k[0..3]} if scalar(@k) > 7; + my $re = join('|', map { quotemeta } keys %addr2url); + $tmp->{$key} = [ qr/\b($re)\b/i, \%addr2url ]; + }; + @$ent; +} + +sub to_cc_html ($$$$) { + my ($ctx, $eml, $field, $t) = @_; + my @vals = $eml->header($field) or return ('', 0); + my (undef, $addr2url) = addr2urlmap($ctx); + my $pairs = PublicInbox::Address::pairs(join(', ', @vals)); + my ($len, $line_len, $html) = (0, 0, ''); + my ($pair, $url); + my ($cur_ibx, $env) = @$ctx{qw(ibx env)}; + # avoid excessive ascii_html calls (already hot in profiles): + my @html = split /\n/, ascii_html(join("\n", map { + $_->[0] // (split(/\@/, $_->[1]))[0]; # addr user if no name + } @$pairs)); + for my $n (@html) { + $pair = shift @$pairs; + if ($line_len) { # 9 = display width of ",\t": + if ($line_len + length($n) > COLS - 9) { + $html .= ",\n\t"; + $len += $line_len; + $line_len = 0; + } else { + $html .= ', '; + $line_len += 2; + } + } + $line_len += length($n); + $url = $addr2url->{lc($pair->[1] // '')}; + $html .= $url ? qq(<a\nhref="$url$t">$n</a>) : $n; + } + ($html, $len + $line_len); +} + # Displays the text of of the message for /$INBOX/$MSGID/[Tt]/ endpoint # this is already inside a <pre> sub eml_entry { @@ -208,7 +260,8 @@ sub eml_entry { 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 ($t, undef) = delete @$smsg{qw(ts blob)}; + $t = $t ? '?t='.ts2str($t) : ''; my $from = _hdr_names_html($eml, 'From'); obfuscate_addrs($obfs_ibx, $from) if $obfs_ibx; @@ -217,9 +270,8 @@ sub eml_entry { my $mhref = $upfx . mid_href($mid_raw) . '/'; $rv .= qq{ (<a\nhref="$mhref">permalink</a> / }; $rv .= qq{<a\nhref="${mhref}raw">raw</a>)\n}; - my $to = fold_addresses(_hdr_names_html($eml, 'To')); - my $cc = fold_addresses(_hdr_names_html($eml, 'Cc')); - my ($tlen, $clen) = (length($to), length($cc)); + my ($to, $tlen) = to_cc_html($ctx, $eml, 'To', $t); + my ($cc, $clen) = to_cc_html($ctx, $eml, 'Cc', $t); my $to_cc = ''; if (($tlen + $clen) > COLS) { $to_cc .= ' To: '.$to."\n" if $tlen; @@ -242,20 +294,22 @@ sub eml_entry { my $html = ascii_html($irt); $rv .= qq(In-Reply-To: <<a\nhref="$href">$html</a>>\n) } - $rv .= "\n"; + say { $ctx->zfh } $rv; # scan through all parts, looking for displayable text $ctx->{mhref} = $mhref; - $ctx->{obuf} = \$rv; - $eml->each_part(\&add_text_body, $ctx, 1); - delete $ctx->{obuf}; + $ctx->{changed_href} = "#e$id"; # for diffstat "files? changed," + $eml->each_part(\&add_text_body, $ctx, 1); # expensive # add the footer - $rv .= "\n<a\nhref=#$id_m\nid=e$id>^</a> ". + $rv = "\n<a\nhref=#$id_m\nid=e$id>^</a> ". "<a\nhref=\"$mhref\">permalink</a>" . " <a\nhref=\"${mhref}raw\">raw</a>" . " <a\nhref=\"${mhref}#R\">reply</a>"; + delete($ctx->{-qry}) and + $rv .= qq[ <a\nhref="${mhref}#related">related</a>]; + my $hr; if (defined(my $pct = $smsg->{pct})) { # used by SearchView.pm $rv .= "\t[relevance $pct%]"; @@ -300,8 +354,7 @@ sub _th_index_lite { my $rv = ''; my $mapping = $ctx->{mapping} or return $rv; my $pad = ' '; - my $mid_map = $mapping->{$mid_raw}; - defined $mid_map or + my $mid_map = $mapping->{$mid_raw} // return 'public-inbox BUG: '.ascii_html($mid_raw).' not mapped'; my ($attr, $node, $idx, $level) = @$mid_map; my $children = $node->{children}; @@ -333,10 +386,10 @@ 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!</b>\n!s; + chop $attr; # remove "\n" $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"; + $rv .= "<b>@ $attr</b>\n"; if ($nr_c) { my $cmid = $children->[0] ? $children->[0]->{mid} : undef; $rv .= $pad . _skel_hdr($mapping, $cmid); @@ -386,7 +439,9 @@ sub pre_thread { # walk_thread callback sub thread_eml_entry { my ($ctx, $eml) = @_; my ($beg, $end) = thread_adj_level($ctx, $ctx->{level}); - $beg . '<pre>' . eml_entry($ctx, $eml) . '</pre>' . $end; + print { $ctx->zfh } $beg, '<pre>'; + print { $ctx->{zfh} } eml_entry($ctx, $eml), '</pre>'; + $end; } sub next_in_queue ($$) { @@ -413,15 +468,15 @@ sub stream_thread_i { # PublicInbox::WwwStream::getline callback if (!$ghost_ok) { # first non-ghost $ctx->{-title_html} = ascii_html($smsg->{subject}); - $ctx->zmore($ctx->html_top); + print { $ctx->zfh } $ctx->html_top; } return $smsg; } # buffer the ghost entry and loop - $ctx->zmore(ghost_index_entry($ctx, $lvl, $smsg)); + print { $ctx->zfh } ghost_index_entry($ctx, $lvl, $smsg) } else { # all done - $ctx->zmore(join('', thread_adj_level($ctx, 0))); - $ctx->zmore(${delete($ctx->{skel})}); + print { $ctx->zfh } thread_adj_level($ctx, 0), + ${delete($ctx->{skel})}; return; } } @@ -430,7 +485,7 @@ sub stream_thread_i { # PublicInbox::WwwStream::getline callback sub stream_thread ($$) { my ($rootset, $ctx) = @_; @{$ctx->{-queue}} = map { (0, $_) } @$rootset; - PublicInbox::WwwStream::aresponse($ctx, 200, \&stream_thread_i); + PublicInbox::WwwStream::aresponse($ctx, \&stream_thread_i); } # /$INBOX/$MSGID/t/ and /$INBOX/$MSGID/T/ @@ -441,10 +496,11 @@ sub thread_html { my $ibx = $ctx->{ibx}; my ($nr, $msgs) = $ibx->over->get_thread($mid); return missing_thread($ctx) if $nr == 0; + $ctx->{-spfx} = '../../' if $ibx->{-repo_objs}; # link $INBOX_DIR/description text to "index_topics" view around # the newest message in this thread - my $t = ts2str($ctx->{-t_max} = max(map { delete $_->{ts} } @$msgs)); + my $t = ts2str($ctx->{-t_max} = max(map { $_->{ts} } @$msgs)); my $t_fmt = fmt_ts($ctx->{-t_max}); my $skel = '<hr><pre>'; @@ -481,7 +537,7 @@ EOF # flat display: lazy load the full message from smsg $ctx->{msgs} = $msgs; $ctx->{-html_tip} = '<pre>'; - PublicInbox::WwwStream::aresponse($ctx, 200, \&thread_html_i); + PublicInbox::WwwStream::aresponse($ctx, \&thread_html_i); } sub thread_html_i { # PublicInbox::WwwStream::getline callback @@ -490,7 +546,7 @@ sub thread_html_i { # PublicInbox::WwwStream::getline callback my $smsg = $ctx->{smsg}; if (exists $ctx->{-html_tip}) { $ctx->{-title_html} = ascii_html($smsg->{subject}); - $ctx->zmore($ctx->html_top); + print { $ctx->zfh } $ctx->html_top; } return eml_entry($ctx, $eml); } else { @@ -498,31 +554,19 @@ sub thread_html_i { # PublicInbox::WwwStream::getline callback return $smsg if exists($smsg->{blob}); } my $skel = delete($ctx->{skel}) or return; # all done - $ctx->zmore($$skel); + print { $ctx->zfh } $$skel; undef; } } -sub multipart_text_as_html { - # ($mime, $ctx) = @_; # each_part may do "$_[0] = undef" - - # scan through all parts, looking for displayable text - $_[0]->each_part(\&add_text_body, $_[1], 1); -} - sub submsg_hdr ($$) { my ($ctx, $eml) = @_; - my $obfs_ibx = $ctx->{-obfs_ibx}; - my $rv = $ctx->{obuf}; - $$rv .= "\n"; + my $s = "\n"; for my $h (qw(From To Cc Subject Date Message-ID X-Alt-Message-ID)) { - my @v = $eml->header($h); - for my $v (@v) { - obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx; - $v = ascii_html($v); - $$rv .= "$h: $v\n"; - } + $s .= "$h: $_\n" for $eml->header($h); } + obfuscate_addrs($ctx->{-obfs_ibx}, $s) if $ctx->{-obfs_ibx}; + ascii_html($s); } sub attach_link ($$$$;$) { @@ -533,7 +577,6 @@ sub attach_link ($$$$;$) { # downloads for 0-byte multipart attachments return unless $part->{bdy}; - my $nl = $idx eq '1' ? '' : "\n"; # like join("\n", ...) my $size = length($part->body); delete $part->{bdy}; # save memory @@ -549,23 +592,17 @@ sub attach_link ($$$$;$) { } else { $sfn = 'a.bin'; } - my $rv = $ctx->{obuf}; - $$rv .= qq($nl<a\nhref="$ctx->{mhref}$idx-$sfn">); - if ($err) { - $$rv .= <<EOF; + my $rv = $idx eq '1' ? '' : "\n"; # like join("\n", ...) + $rv .= qq(<a\nhref="$ctx->{mhref}$idx-$sfn">); + $rv .= <<EOF if $err; [-- Warning: decoded text below may be mangled, UTF-8 assumed --] EOF - } - $$rv .= "[-- Attachment #$idx: "; - my $ts = "Type: $ct, Size: $size bytes"; + $rv .= "[-- Attachment #$idx: "; my $desc = $part->header('Content-Description') // $fn // ''; - $desc = ascii_html($desc); - $$rv .= ($desc eq '') ? "$ts --]" : "$desc --]\n[-- $ts --]"; - $$rv .= "</a>\n"; - - submsg_hdr($ctx, $part) if $part->{is_submsg}; - - undef; + $rv .= ascii_html($desc)." --]\n[-- " if $desc ne ''; + $rv .= "Type: $ct, Size: $size bytes --]</a>\n"; + $rv .= submsg_hdr($ctx, $part) if $part->{is_submsg}; + $rv; } sub add_text_body { # callback for each_part @@ -578,13 +615,9 @@ sub add_text_body { # callback for each_part 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); - $$rv .= "\n"; - } + my $zfh = $ctx->zfh; + $s // return print $zfh (attach_link($ctx, $ct, $p, $fn) // ''); + say $zfh submsg_hdr($ctx, $part) if $part->{is_submsg}; # makes no difference to browsers, and don't screw up filename # link generation in diffs with the extra '%0D' @@ -607,24 +640,6 @@ sub add_text_body { # callback for each_part $ctx->{-anchors} = {} if $s =~ /^diff --git /sm; $diff = 1; delete $ctx->{-long_path}; - my $spfx; - # absolute URL (Atom feeds) - if ($ibx->{coderepo}) { - if (index($upfx, '//') >= 0) { - $spfx = $upfx; - $spfx =~ s!/([^/]*)/\z!/!; - } else { - my $n_slash = $upfx =~ tr!/!/!; - if ($n_slash == 0) { - $spfx = '../'; - } elsif ($n_slash == 1) { - $spfx = ''; - } else { # nslash == 2 - $spfx = '../../'; - } - } - } - $ctx->{-spfx} = $spfx; }; # split off quoted and unquoted blocks: @@ -632,110 +647,122 @@ sub add_text_body { # callback for each_part undef $s; # free memory if (defined($fn) || ($depth > 0 && !$part->{is_submsg}) || $err) { # badly-encoded message with $err? tell the world about it! - attach_link($ctx, $ct, $p, $fn, $err); - $$rv .= "\n"; + say $zfh attach_link($ctx, $ct, $p, $fn, $err); } delete $part->{bdy}; # save memory - foreach my $cur (@sections) { + for my $cur (@sections) { # $cur may be huge if ($cur =~ /\A>/) { # we use a <span> here to allow users to specify # their own color for quoted text - $$rv .= qq(<span\nclass="q">); - $$rv .= $l->to_html($cur); - $$rv .= '</span>'; + print $zfh qq(<span\nclass="q">), + $l->to_html($cur), '</span>'; } elsif ($diff) { flush_diff($ctx, \$cur); - } else { - # regular lines, OK - $$rv .= $l->to_html($cur); + } else { # regular lines, OK + print $zfh $l->to_html($cur); } undef $cur; # free memory } } -sub _msg_page_prepare_obuf { - my ($eml, $ctx) = @_; - my $over = $ctx->{ibx}->over; - my $obfs_ibx = $ctx->{-obfs_ibx}; - my $rv = ''; +sub _msg_page_prepare { + my ($eml, $ctx, $ts) = @_; + my $have_over = !!$ctx->{ibx}->over; my $mids = mids_for_index($eml); my $nr = $ctx->{nr}++; if ($nr) { # unlikely if ($ctx->{chash} eq content_hash($eml)) { warn "W: BUG? @$mids not deduplicated properly\n"; - return \$rv; + return; } - $rv .= -"<pre>WARNING: multiple messages have this Message-ID\n</pre>"; - $rv .= '<pre>'; + $ctx->{-html_tip} = +qq[<pre>WARNING: multiple messages have this Message-ID (<a +href="d/">diff</a>)</pre><pre>]; } else { $ctx->{first_hdr} = $eml->header_obj; $ctx->{chash} = content_hash($eml) if $ctx->{smsg}; # reused MID - $rv .= "<pre\nid=b>"; # anchor for body start + $ctx->{-html_tip} = "<pre\nid=b>"; # anchor for body start } - $ctx->{-upfx} = '../' if $over; + $ctx->{-upfx} = '../'; my @title; # (Subject[0], From[0]) + my $hbuf = ''; for my $v ($eml->header('From')) { my @n = PublicInbox::Address::names($v); - $v = ascii_html($v); - $title[1] //= ascii_html(join(', ', @n)); - if ($obfs_ibx) { - obfuscate_addrs($obfs_ibx, $v); - obfuscate_addrs($obfs_ibx, $title[1]); - } - $rv .= "From: $v\n" if $v ne ''; + $title[1] //= join(', ', @n); + $hbuf .= "From: $v\n" if $v ne ''; } - foreach my $h (qw(To Cc)) { + for my $h (qw(To Cc)) { for my $v ($eml->header($h)) { fold_addresses($v); - $v = ascii_html($v); - obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx; - $rv .= "$h: $v\n" if $v ne ''; + $hbuf .= "$h: $v\n" if $v ne ''; } } my @subj = $eml->header('Subject'); - if (@subj) { - my $v = ascii_html(shift @subj); - obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx; - $rv .= 'Subject: '; - $rv .= $over ? qq(<a\nhref="#r"\nid=t>$v</a>\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: $v\n"; - } - } else { # dummy anchor for thread skeleton at bottom of page - $rv .= qq(<a\nhref="#r"\nid=t></a>) if $over; - $title[0] = '(no subject)'; + $hbuf .= "Subject: $_\n" for @subj; + $title[0] = $subj[0] // '(no subject)'; + $hbuf .= "Date: $_\n" for $eml->header('Date'); + $hbuf = ascii_html($hbuf); + my $t = $ts ? '?t='.ts2str($ts) : ''; + my ($re, $addr2url) = addr2urlmap($ctx); + $hbuf =~ s!$re!qq(<a\nhref=").$addr2url->{lc $1}.qq($t">$1</a>)!sge; + $ctx->{-title_html} = ascii_html(join(' - ', @title)); + if (my $obfs_ibx = $ctx->{-obfs_ibx}) { + obfuscate_addrs($obfs_ibx, $hbuf); + obfuscate_addrs($obfs_ibx, $ctx->{-title_html}); } - for my $v ($eml->header('Date')) { - $v = ascii_html($v); - obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx; # possible :P - $rv .= qq{Date: $v\t<a\nhref="#r">[thread overview]</a>\n}; - } - if (!$nr) { # first (and only) message, common case - $ctx->{-title_html} = join(' - ', @title); - $rv = $ctx->html_top . $rv; + + # [thread overview] link is typically added after Date, + # but added after Subject, or even nothing. + if ($have_over) { + chop $hbuf; # drop "\n", or noop if $rv eq '' + $hbuf .= qq{\t<a\nhref="#r">[thread overview]</a>\n}; + $hbuf =~ s!^Subject:\x20(.*?)(\n[A-Z]|\z) + !Subject: <a\nhref="#r"\nid=t>$1</a>$2!msx or + $hbuf .= qq(<a\nhref="#r\nid=t></a>); } if (scalar(@$mids) == 1) { # common case - my $mhtml = ascii_html($mids->[0]); - $rv .= "Message-ID: <$mhtml> "; - $rv .= "(<a\nhref=\"raw\">raw</a>)\n"; + my $x = ascii_html($mids->[0]); + $hbuf .= qq[Message-ID: <$x> (<a href="raw">raw</a>)\n]; + } + if (!$nr) { # first (and only) message, common case + print { $ctx->zfh } $ctx->html_top, $hbuf; } else { + delete $ctx->{-title_html}; + print { $ctx->zfh } $ctx->{-html_tip}, $hbuf; + } + $ctx->{-linkify} //= PublicInbox::Linkify->new; + $hbuf = ''; + if (scalar(@$mids) != 1) { # unlikely, but it happens :< # X-Alt-Message-ID can happen if a message is injected from # public-inbox-nntpd because of multiple Message-ID headers. - my $lnk = PublicInbox::Linkify->new; - my $s = ''; for my $h (qw(Message-ID X-Alt-Message-ID)) { - $s .= "$h: $_\n" for ($eml->header_raw($h)); + $hbuf .= "$h: $_\n" for ($eml->header_raw($h)); } - $lnk->linkify_mids('..', \$s, 1); - $rv .= $s; + $ctx->{-linkify}->linkify_mids('..', \$hbuf, 1); # escapes HTML + print { $ctx->{zfh} } $hbuf; + $hbuf = ''; } - $rv .= _parent_headers($eml, $over); - $rv .= "\n"; - \$rv; + my @irt = $eml->header_raw('In-Reply-To'); + my $refs; + if (@irt) { # ("so-and-so's message of $DATE") added by some MUAs + for (grep(/=\?/, @irt)) { + s/(=\?.*)\z/PublicInbox::Eml::mhdr_decode $1/se; + } + } else { + $refs = references($eml); + $irt[0] = pop(@$refs) if scalar @$refs; + } + $hbuf .= "In-Reply-To: $_\n" for @irt; + + # do not display References: if search is present, + # we show the thread skeleton at the bottom, instead. + if (!$have_over) { + $refs //= references($eml); + $hbuf .= 'References: <'.join(">\n\t<", @$refs).">\n" if @$refs; + } + $ctx->{-linkify}->linkify_mids('..', \$hbuf); # escapes HTML + say { $ctx->{zfh} } $hbuf; + 1; } sub SKEL_EXPAND () { @@ -772,7 +799,6 @@ sub thread_skel ($$$) { # when multiple Subject: headers are present, so we follow suit: my $subj = $hdr->header('Subject') // ''; $subj = '(no subject)' if $subj eq ''; - $ctx->{prev_subj} = [ split(/ /, subject_normalized($subj)) ]; $ctx->{cur} = $mid; $ctx->{prev_attr} = ''; $ctx->{prev_level} = 0; @@ -785,54 +811,47 @@ sub thread_skel ($$$) { $ctx->{parent_msg} = $parent; } -sub _parent_headers { - my ($hdr, $over) = @_; - my $rv = ''; - my @irt = $hdr->header_raw('In-Reply-To'); - my $refs; - if (@irt) { - my $lnk = PublicInbox::Linkify->new; - $rv .= "In-Reply-To: $_\n" for @irt; - $lnk->linkify_mids('..', \$rv); - } else { - $refs = references($hdr); - my $irt = pop @$refs; - if (defined $irt) { - my $html = ascii_html($irt); - my $href = mid_href($irt); - $rv .= "In-Reply-To: <"; - $rv .= "<a\nhref=\"../$href/\">$html</a>>\n"; - } - } - - # do not display References: if search is present, - # we show the thread skeleton at the bottom, instead. - return $rv if $over; - - $refs //= references($hdr); - if (@$refs) { - @$refs = map { linkify_ref_no_over($_) } @$refs; - $rv .= 'References: '. join("\n\t", @$refs) . "\n"; - } - $rv; -} - -# returns a string buffer +# writes to zbuf sub html_footer { my ($ctx, $hdr) = @_; - my $ibx = $ctx->{ibx}; my $upfx = '../'; - my $skel; - my $rv = '<pre>'; - if ($ibx->over) { + my (@related, $skel); + my $foot = '<pre>'; + my $qry = delete $ctx->{-qry}; + if ($qry && $ctx->{ibx}->isrch) { + my $q = ''; # search for either ancestor or descendent patches + for (@{$qry->{dfpre}}, @{$qry->{dfpost}}) { + chop if length > 7; # include 1 abbrev "older" patches + $q .= "dfblob:$_ "; + } + chop $q; # omit trailing SP + local $Text::Wrap::columns = COLS; + local $Text::Wrap::huge = 'overflow'; + $q = wrap('', '', $q); + my $rows = ($q =~ tr/\n/\n/) + 1; + $q = ascii_html($q); + $related[0] = <<EOM; +<form id=related +action=$upfx +><pre>find likely ancestor, descendant, or conflicting patches for <a +href=#t>this message</a>: +<textarea name=q cols=${\COLS} rows=$rows>$q</textarea> +<input type=submit value=search +/>\t(<a href=${upfx}_/text/help/#search>help</a>)</pre></form> +EOM + # TODO: related codesearch + # my $csrchv = $ctx->{ibx}->{-csrch} // []; + # push @related, '<pre>'.ascii_html(Dumper($csrchv)).'</pre>'; + } + if ($ctx->{ibx}->over) { my $t = ts2str($ctx->{-t_max}); my $t_fmt = fmt_ts($ctx->{-t_max}); - $skel .= <<EOF; - other threads:[<a + my $fallback = @related ? "\t" : "<a id=related>\t</a>"; + $skel = <<EOF; +${fallback}other threads:[<a href="$upfx?t=$t">~$t_fmt UTC</a>|<a href="$upfx">newest</a>] EOF - thread_skel(\$skel, $ctx, $hdr); my ($next, $prev); my $parent = ' '; @@ -840,43 +859,32 @@ EOF if (my $n = $ctx->{next_msg}) { $n = mid_href($n); - $next = "<a\nhref=\"$upfx$n/\"\nrel=next>next</a>"; + $next = qq(<a\nhref="$upfx$n/"\nrel=next>next</a>); } - my $u; my $par = $ctx->{parent_msg}; - if ($par) { - $u = mid_href($par); - $u = "$upfx$u/"; - } + my $u = $par ? $upfx.mid_href($par).'/' : undef; if (my $p = $ctx->{prev_msg}) { $prev = mid_href($p); if ($p && $par && $p eq $par) { - $prev = "<a\nhref=\"$upfx$prev/\"\n" . + $prev = qq(<a\nhref="$upfx$prev/"\n) . 'rel=prev>prev parent</a>'; $parent = ''; } else { - $prev = "<a\nhref=\"$upfx$prev/\"\n" . + $prev = qq(<a\nhref="$upfx$prev/"\n) . 'rel=prev>prev</a>'; - $parent = " <a\nhref=\"$u\">parent</a>" if $u; + $parent = qq( <a\nhref="$u">parent</a>) if $u; } } elsif ($u) { # unlikely - $parent = " <a\nhref=\"$u\"\nrel=prev>parent</a>"; + $parent = qq( <a\nhref="$u"\nrel=prev>parent</a>); } - $rv .= "$next $prev$parent "; + $foot .= "$next $prev$parent "; } else { # unindexed inboxes w/o over $skel = qq( <a\nhref="$upfx">latest</a>); } - $rv .= qq(<a\nhref="#R">reply</a>); - $rv .= $skel; - $rv .= '</pre>'; - $rv .= msg_reply($ctx, $hdr); -} - -sub linkify_ref_no_over { - my ($mid) = @_; - my $href = mid_href($mid); - my $html = ascii_html($mid); - "<<a\nhref=\"../$href/\">$html</a>>"; + # $skel may be big for big threads, don't append it to $foot + print { $ctx->zfh } $foot, qq(<a\nhref="#R">reply</a>), + $skel, '</pre>', @related, + msg_reply($ctx, $hdr); } sub ghost_parent { @@ -937,8 +945,8 @@ sub thread_results { my $tip = splice(@$rootset, $idx, 1); @$rootset = reverse @$rootset; unshift @$rootset, $tip; - $ctx->{sl_note} = strict_loose_note($nr); } + $ctx->{sl_note} = strict_loose_note($nr); } $rootset } @@ -1074,6 +1082,8 @@ sub _skel_ghost { 1; } +# note: we favor Date: here because git-send-email increments it +# to preserve [PATCH $N/$M] ordering in series (it can't control Received:) sub sort_ds { @{$_[0]} = sort { (eval { $a->topmost->{ds} } || 0) <=> @@ -1095,9 +1105,10 @@ sub acc_topic { # walk_thread callback if ($has_blob) { my $subj = subject_normalized($smsg->{subject}); $subj = '(no subject)' if $subj eq ''; + my $ts = $smsg->{ts}; my $ds = $smsg->{ds}; if ($level == 0) { # new, top-level topic - my $topic = [ $ds, 1, { $subj => $mid }, $subj ]; + my $topic = [ $ts, $ds, 1, { $subj => $mid }, $subj ]; $ctx->{-cur_topic} = $topic; push @{$ctx->{order}}, $topic; return 1; @@ -1105,10 +1116,11 @@ sub acc_topic { # walk_thread callback # continue existing topic my $topic = $ctx->{-cur_topic}; # should never be undef - $topic->[0] = $ds if $ds > $topic->[0]; - $topic->[1]++; # bump N+ message counter - my $seen = $topic->[2]; - if (scalar(@$topic) == 3) { # parent was a ghost + $topic->[0] = $ts if $ts > $topic->[0]; + $topic->[1] = $ds if $ds > $topic->[1]; + $topic->[2]++; # bump N+ message counter + my $seen = $topic->[3]; + if (scalar(@$topic) == 4) { # parent was a ghost push @$topic, $subj; } elsif (!defined($seen->{$subj})) { push @$topic, $level, $subj; # @extra messages @@ -1116,7 +1128,7 @@ sub acc_topic { # walk_thread callback $seen->{$subj} = $mid; # latest for subject } else { # ghost message return 1 if $level != 0; # ignore child ghosts - my $topic = $ctx->{-cur_topic} = [ -666, 0, {} ]; + my $topic = $ctx->{-cur_topic} = [ -666, -666, 0, {} ]; push @{$ctx->{order}}, $topic; } 1; @@ -1131,12 +1143,13 @@ sub dump_topics { } my @out; - my $ibx = $ctx->{ibx}; - my $obfs_ibx = $ibx->{obfuscate} ? $ibx : undef; - + my $obfs_ibx = $ctx->{ibx}->{obfuscate} ? $ctx->{ibx} : undef; + if (my $note = delete $ctx->{t_note}) { + push @out, $note; # "messages from ... to ..." + } # sort by recency, this allows new posts to "bump" old topics... foreach my $topic (sort { $b->[0] <=> $a->[0] } @$order) { - my ($ds, $n, $seen, $top_subj, @extra) = @$topic; + my ($ts, $ds, $n, $seen, $top_subj, @extra) = @$topic; @$topic = (); next unless defined $top_subj; # ghost topic my $mid = delete $seen->{$top_subj}; @@ -1158,9 +1171,9 @@ sub dump_topics { my $s = "<a\nhref=\"$href/T/$anchor\">$top_subj</a>\n" . " $ds UTC $n\n"; - for (my $i = 0; $i < scalar(@extra); $i += 2) { - my $level = $extra[$i]; - my $subj = $extra[$i + 1]; # already normalized + while (@extra) { + my $level = shift @extra; + my $subj = shift @extra; # already normalized $mid = delete $seen->{$subj}; my @subj = split(/ /, $subj); my @next_prev = @subj; # full copy @@ -1192,7 +1205,11 @@ sub pagination_footer ($$) { $next = $next ? "$next | " : ' | '; $prev .= qq[ | <a\nhref="$latest">latest</a>]; } - "<hr><pre>page: $next$prev</pre>"; + my $rv = '<hr><pre id=nav>'; + $rv .= "page: $next$prev\n" if $next || $prev; + $rv .= q{- recent:[<b>subjects (threaded)</b>|<a +href="./topics_new.html">topics (new)</a>|<a +href="./topics_active.html">topics (active)</a>]</pre>}; } sub paginate_recent ($$) { @@ -1207,23 +1224,30 @@ sub paginate_recent ($$) { $t =~ s/\A([0-9]{8,14})-// and $after = str2ts($1); $t =~ /\A([0-9]{8,14})\z/ and $before = str2ts($1); - my $ibx = $ctx->{ibx}; - my $msgs = $ibx->recent($opts, $after, $before); - my $nr = scalar @$msgs; - if ($nr < $lim && defined($after)) { + my $msgs = $ctx->{ibx}->over->recent($opts, $after, $before); + if (defined($after) && scalar(@$msgs) < $lim) { $after = $before = undef; - $msgs = $ibx->recent($opts); - $nr = scalar @$msgs; + $msgs = $ctx->{ibx}->over->recent($opts); } - my $more = $nr == $lim; + my $more = scalar(@$msgs) == $lim; my ($newest, $oldest); - if ($nr) { + if (@$msgs) { $newest = $msgs->[0]->{ts}; $oldest = $msgs->[-1]->{ts}; # if we only had $after, our SQL query in ->recent ordered if ($newest < $oldest) { ($oldest, $newest) = ($newest, $oldest); - $more = 0 if defined($after) && $after < $oldest; + $more = undef if defined($after) && $after < $oldest; + } + if (defined($after // $before)) { + my $n = strftime('%Y-%m-%d %H:%M:%S', gmtime($newest)); + my $o = strftime('%Y-%m-%d %H:%M:%S', gmtime($oldest)); + $ctx->{t_note} = <<EOM; + messages from $o to $n UTC [<a href="#nav">more...</a>] +EOM + my $s = ts2str($newest); + $ctx->{prev_page} = qq[<a\nhref="?t=$s-"\nrel=prev>] . + 'prev (newer)</a>'; } } if (defined($oldest) && $more) { @@ -1231,11 +1255,6 @@ sub paginate_recent ($$) { $ctx->{next_page} = qq[<a\nhref="?t=$s"\nrel=next>] . 'next (older)</a>'; } - if (defined($newest) && (defined($before) || defined($after))) { - my $s = ts2str($newest); - $ctx->{prev_page} = qq[<a\nhref="?t=$s-"\nrel=prev>] . - 'prev (newer)</a>'; - } $msgs; } @@ -1243,11 +1262,8 @@ sub paginate_recent ($$) { sub index_topics { my ($ctx) = @_; my $msgs = paginate_recent($ctx, 200); # 200 is our window - if (@$msgs) { - walk_thread(thread_results($ctx, $msgs), $ctx, \&acc_topic); - } - html_oneshot($ctx, dump_topics($ctx), \pagination_footer($ctx, '.')); - + walk_thread(thread_results($ctx, $msgs), $ctx, \&acc_topic) if @$msgs; + html_oneshot($ctx, dump_topics($ctx), pagination_footer($ctx, '.')); } sub thread_adj_level { @@ -1281,4 +1297,30 @@ sub ghost_index_entry { . '</pre>' . $end; } +# /$INBOX/$MSGID/d/ endpoint +sub diff_msg { + my ($ctx) = @_; + require PublicInbox::MailDiff; + my $ibx = $ctx->{ibx}; + my $over = $ibx->over or return no_over_html($ctx); + my ($id, $prev); + my $md = bless { ctx => $ctx }, 'PublicInbox::MailDiff'; + my $next_arg = $md->{next_arg} = [ $ctx->{mid}, \$id, \$prev ]; + my $smsg = $md->{smsg} = $over->next_by_mid(@$next_arg) or + return; # undef == 404 + $ctx->{-t_max} = $smsg->{ts}; + $ctx->{-upfx} = '../../'; + $ctx->{-apfx} = '//'; # fail on to_attr() + $ctx->{-linkify} = PublicInbox::Linkify->new; + my $mid = ascii_html($smsg->{mid}); + $ctx->{-title_html} = "diff for duplicates of <$mid>"; + PublicInbox::WwwStream::html_init($ctx); + print { $ctx->{zfh} } '<pre>diff for duplicates of <<a href="../">', + $mid, "</a>>\n\n"; + sub { + $ctx->attach($_[0]->([200, delete $ctx->{-res_hdr}])); + $md->begin_mail_diff; + }; +} + 1; |