X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FView.pm;h=8969e17576f60de54152ebb2d4502571610801ef;hb=f76f265a851944b5dedcc3be5f3b5224b6ebda89;hp=3d7ba6f5bb235f39eeed0e8911b4149295f9e35d;hpb=cd486277621f00c108a49c4ba3c9fedbef0f70d5;p=public-inbox.git diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm index 3d7ba6f5..8969e175 100644 --- a/lib/PublicInbox/View.pm +++ b/lib/PublicInbox/View.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2014, Eric Wong and all contributors +# Copyright (C) 2014-2015 all contributors # License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt) package PublicInbox::View; use strict; @@ -19,6 +19,7 @@ use constant MAX_INLINE_QUOTED => 12; # half an 80x24 terminal use constant MAX_TRUNC_LEN => 72; use constant PRE_WRAP => ""; use constant T_ANCHOR => '#u'; +use constant INDENT => ' '; *ascii_html = *PublicInbox::Hval::ascii_html; @@ -46,6 +47,19 @@ sub feed_entry { PRE_WRAP . multipart_text_as_html($mime, $full_pfx) . ''; } +sub in_reply_to { + my ($header_obj) = @_; + my $irt = $header_obj->header('In-Reply-To'); + + return mid_clean($irt) if (defined $irt); + + my $refs = $header_obj->header('References'); + if ($refs && $refs =~ /<([^>]+)>\s*\z/s) { + return $1; + } + undef; +} + # this is already inside a
 sub index_entry {
 	my ($fh, $mime, $level, $state) = @_;
@@ -61,7 +75,7 @@ sub index_entry {
 	my $mid_raw = $header_obj->header('Message-ID');
 	my $id = anchor_for($mid_raw);
 	my $seen = $state->{seen};
-	$seen->{$id} = "#$id"; # save the anchor for later
+	$seen->{$id} = "#$id"; # save the anchor for children, later
 
 	my $mid = PublicInbox::Hval->new_msgid($mid_raw);
 	my $from = PublicInbox::Hval->new_oneline($mime->header('From'))->raw;
@@ -71,26 +85,24 @@ sub index_entry {
 	$from = PublicInbox::Hval->new_oneline($from)->as_html;
 	$subj = PublicInbox::Hval->new_oneline($subj)->as_html;
 	my $more = 'permalink';
-	my $root_anchor = $state->{root_anchor};
+	my $root_anchor = $state->{root_anchor} || '';
 	my $path = $root_anchor ? '../../' : '';
 	my $href = $mid->as_href;
-	my $irt = $header_obj->header('In-Reply-To');
-	my ($anchor_idx, $anchor);
-	if (defined $irt) {
-		$anchor_idx = anchor_for($irt);
-		$anchor = $seen->{$anchor_idx};
-	}
+	my $irt = in_reply_to($header_obj);
+	my $parent_anchor = $seen->{anchor_for($irt)} if defined $irt;
+
 	if ($srch) {
-		$subj = "$subj";
+		my $t = $ctx->{flat} ? 'T' : 't';
+		$subj = "$subj";
 	}
-	if ($root_anchor && $root_anchor eq $id) {
+	if ($root_anchor eq $id) {
 		$subj = "$subj";
 	}
 
 	my $ts = _msg_date($mime);
 	my $rv = "";
 	if ($level) {
-		$rv .= '
' . ('  ' x $level) . '
'; + $rv .= '
' . (INDENT x $level) . '
'; } $rv .= "" . PRE_WRAP; $rv .= "$subj\n"; @@ -103,7 +115,9 @@ sub index_entry { my ($fhref, $more_ref); my $mhref = "${path}$href/"; - if ($level > 0) { + + # show full message if it's our root message + if ($root_anchor ne $id) { $fhref = "${path}$href/f/"; $more_ref = \$more; } @@ -118,13 +132,21 @@ sub index_entry { $rv .= html_footer($mime, 0, undef, $ctx); if (defined $irt) { - unless (defined $anchor) { - my $v = PublicInbox::Hval->new_msgid($irt); + unless (defined $parent_anchor) { + my $v = PublicInbox::Hval->new_msgid($irt, 1); $v = $v->as_href; - $anchor = "${path}$v/"; - $seen->{$anchor_idx} = $anchor; + $parent_anchor = "${path}$v/"; + } + $rv .= " parent"; + } + if ($srch) { + if ($ctx->{flat}) { + $rv .= " [threaded" . + "|flat]"; + } else { + $rv .= " [threaded|" . + "flat]"; } - $rv .= " parent"; } $fh->write($rv .= '
'); @@ -139,33 +161,46 @@ sub thread_html { sub emit_thread_html { my ($cb, $ctx, $foot, $srch) = @_; - my $mid = mid_compress($ctx->{mid}); + my $mid = $ctx->{mid}; my $res = $srch->get_thread($mid); my $msgs = load_results($res); my $nr = scalar @$msgs; - return missing_thread($cb) if $nr == 0; - my $fh = $cb->([200,['Content-Type'=>'text/html; charset=UTF-8']]); - my $th = thread_results($msgs); + return missing_thread($cb, $ctx) if $nr == 0; + my $flat = $ctx->{flat}; + my $orig_cb = $cb; + my $seen = {}; my $state = { ctx => $ctx, - seen => {}, + seen => $seen, root_anchor => anchor_for($mid), anchor_idx => 0, }; - { - require PublicInbox::GitCatFile; - my $git = PublicInbox::GitCatFile->new($ctx->{git_dir}); - thread_entry($fh, $git, $state, $_, 0) for $th->rootset; + + require PublicInbox::GitCatFile; + my $git = PublicInbox::GitCatFile->new($ctx->{git_dir}); + if ($flat) { + pre_anchor_entry($seen, $_) for (@$msgs); + __thread_entry(\$cb, $git, $state, $_, 0) for (@$msgs); + } else { + my $th = thread_results($msgs); + thread_entry(\$cb, $git, $state, $_, 0) for $th->rootset; } + $git = undef; + Email::Address->purge_cache; + + # there could be a race due to a message being deleted in git + # but still being in the Xapian index: + return missing_thread($cb, $ctx) if ($orig_cb eq $cb); + my $final_anchor = $state->{anchor_idx}; my $next = ""; $next .= $final_anchor == 1 ? 'only message in' : 'end of'; - $next .= " thread, back to index\n"; - $next .= "download: mbox.gz"; - $next .= " / Atom feed\n\n"; - $fh->write("
" . PRE_WRAP . $next . $foot . + $next .= " thread, back to index"; + $next .= "\ndownload thread: mbox.gz"; + $next .= " / follow: Atom feed"; + $cb->write("
" . PRE_WRAP . $next . "\n\n". $foot . ""); - $fh->close; + $cb->close; } sub index_walk { @@ -216,7 +251,7 @@ sub multipart_text_as_html { # scan through all parts, looking for displayable text $mime->walk_parts(sub { my ($part) = @_; - $rv .= add_text_body($enc, $part, \$part_nr, $full_pfx); + $rv .= add_text_body($enc, $part, \$part_nr, $full_pfx, 1); }); $mime->body_set(''); $rv; @@ -268,7 +303,7 @@ sub linkify_2 { } sub flush_quote { - my ($quot, $n, $part_nr, $full_pfx, $final) = @_; + my ($quot, $n, $part_nr, $full_pfx, $final, $do_anchor) = @_; if ($full_pfx) { if (!$final && scalar(@$quot) <= MAX_INLINE_QUOTED) { @@ -302,18 +337,18 @@ sub flush_quote { } else { # show everything in the full version with anchor from # short version (see above) - my $nr = ++$$n; - my $rv = ""; my %l; - $rv .= join('', map { linkify_1(\%l, $_) } @$quot); + my $rv .= join('', map { linkify_1(\%l, $_) } @$quot); @$quot = (); $rv = ascii_html($rv); + return linkify_2(\%l, $rv) unless $do_anchor; + my $nr = ++$$n; "" . linkify_2(\%l, $rv); } } sub add_text_body { - my ($enc_msg, $part, $part_nr, $full_pfx) = @_; + my ($enc_msg, $part, $part_nr, $full_pfx, $do_anchor) = @_; return '' if $part->subparts; my $ct = $part->content_type; @@ -343,7 +378,7 @@ sub add_text_body { # show the previously buffered quote inline if (scalar @quot) { $s .= flush_quote(\@quot, \$n, $$part_nr, - $full_pfx, 0); + $full_pfx, 0, $do_anchor); } # regular line, OK @@ -355,7 +390,10 @@ sub add_text_body { push @quot, $cur; } } - $s .= flush_quote(\@quot, \$n, $$part_nr, $full_pfx, 1) if scalar @quot; + if (scalar @quot) { + $s .= flush_quote(\@quot, \$n, $$part_nr, $full_pfx, 1, + $do_anchor); + } $s .= "\n" unless $s =~ /\n\z/s; ++$$part_nr; $s; @@ -407,37 +445,42 @@ sub headers_to_html_header { sub thread_inline { my ($dst, $ctx, $cur, $full_pfx) = @_; my $srch = $ctx->{srch}; - my $mid = mid_compress(mid_clean($cur->header('Message-ID'))); + my $mid = mid_clean($cur->header('Message-ID')); my $res = $srch->get_thread($mid); my $nr = $res->{total}; if ($nr <= 1) { $$dst .= "\n[no followups, yet]\n"; - return; + return (undef, in_reply_to($cur)); } my $upfx = $full_pfx ? '' : '../'; $$dst .= "\n\n~$nr messages in thread: ". "(expand)\n"; my $subj = $srch->subject_path($cur->header('Subject')); + my $parent = in_reply_to($cur); my $state = { seen => { $subj => 1 }, srch => $srch, cur => $mid, + parent_cmp => defined $parent ? $parent : '', + parent => $parent, + prev_attr => '', + prev_level => 0, }; for (thread_results(load_results($res))->rootset) { inline_dump($dst, $state, $upfx, $_, 0); } - $state->{next_msg}; + ($state->{next_msg}, $state->{parent}); } sub _parent_headers_nosrch { my ($header_obj) = @_; my $rv = ''; - my $irt = $header_obj->header('In-Reply-To'); + my $irt = in_reply_to($header_obj); if (defined $irt) { - my $v = PublicInbox::Hval->new_msgid($irt); + my $v = PublicInbox::Hval->new_msgid($irt, 1); my $html = $v->as_html; my $href = $v->as_href; $rv .= "In-Reply-To: <"; @@ -448,13 +491,13 @@ sub _parent_headers_nosrch { if ($refs) { # avoid redundant URLs wasting bandwidth my %seen; - $seen{mid_clean($irt)} = 1 if defined $irt; + $seen{$irt} = 1 if defined $irt; my @refs; my @raw_refs = ($refs =~ /<([^>]+)>/g); foreach my $ref (@raw_refs) { next if $seen{$ref}; $seen{$ref} = 1; - push @refs, linkify_ref($ref); + push @refs, linkify_ref_nosrch($ref); } if (@refs) { @@ -495,14 +538,13 @@ sub html_footer { my $srch = $ctx->{srch} if $ctx; my $upfx = $full_pfx ? '../' : '../../'; - my $idx = $standalone ? "index" : ''; + my $idx = $standalone ? " index" : ''; if ($idx && $srch) { - my $next = thread_inline(\$idx, $ctx, $mime, $full_pfx); - $irt = $mime->header('In-Reply-To'); - if (defined $irt) { - $irt = PublicInbox::Hval->new_msgid($irt); - $irt = $irt->as_href; - $irt = "parent "; + my ($next, $p) = thread_inline(\$idx, $ctx, $mime, $full_pfx); + if (defined $p) { + $p = PublicInbox::Hval->new_oneline($p); + $p = $p->as_href; + $irt = "parent "; } else { $irt = ' ' x length('parent '); } @@ -518,8 +560,8 @@ sub html_footer { "$irtreply' . $idx; } -sub linkify_ref { - my $v = PublicInbox::Hval->new_msgid($_[0]); +sub linkify_ref_nosrch { + my $v = PublicInbox::Hval->new_msgid($_[0], 1); my $html = $v->as_html; my $href = $v->as_href; "<$html>"; @@ -535,29 +577,76 @@ sub anchor_for { } sub thread_html_head { - my ($mime) = @_; + my ($cb, $mime) = @_; + $$cb = $$cb->([200, ['Content-Type'=> 'text/html; charset=UTF-8']]); + my $s = PublicInbox::Hval->new_oneline($mime->header('Subject')); $s = $s->as_html; - "$s"; + $$cb->write("$s"); +} + +sub pre_anchor_entry { + my ($seen, $mime) = @_; + my $id = anchor_for($mime->header('Message-ID')); + $seen->{$id} = "#$id"; # save the anchor for children, later +} + +sub ghost_parent { + my ($upfx, $mid) = @_; + # 'subject dummy' is used internally by Mail::Thread + return '[no common parent]' if ($mid eq 'subject dummy'); + + $mid = PublicInbox::Hval->new_msgid($mid); + my $href = $mid->as_href; + my $html = $mid->as_html; + qq{[parent not found: <$html>]}; +} + +sub __thread_entry { + my ($cb, $git, $state, $mime, $level) = @_; + + # lazy load the full message from mini_mime: + $mime = eval { + my $path = mid2path(mid_clean($mime->header('Message-ID'))); + Email::MIME->new($git->cat_file('HEAD:'.$path)); + } or return; + + if ($state->{anchor_idx} == 0) { + thread_html_head($cb, $mime, $state); + } + + if (my $ghost = delete $state->{ghost}) { + # n.b. ghost messages may only be parents, not children + foreach my $g (@$ghost) { + $$cb->write("" . + (INDENT x $g->[1]) . "" . + PRE_WRAP . ghost_parent('../', $g->[0]) . + ''); + } + } + index_entry($$cb, $mime, $level, $state); + 1; +} + +sub __ghost_entry { + my ($state, $node, $level) = @_; + my $ghost = $state->{ghost} ||= []; + push @$ghost, [ $node->messageid, $level ]; } sub thread_entry { - my ($fh, $git, $state, $node, $level) = @_; + my ($cb, $git, $state, $node, $level) = @_; return unless $node; if (my $mime = $node->message) { - - # lazy load the full message from mini_mime: - my $path = mid2path(mid_clean($mime->header('Message-ID'))); - $mime = eval { Email::MIME->new($git->cat_file("HEAD:$path")) }; - if ($mime) { - if ($state->{anchor_idx} == 0) { - $fh->write(thread_html_head($mime)); - } - index_entry($fh, $mime, $level, $state); + unless (__thread_entry($cb, $git, $state, $mime, $level)) { + __ghost_entry($state, $node, $level); } + } else { + __ghost_entry($state, $node, $level); } - thread_entry($fh, $git, $state, $node->child, $level + 1); - thread_entry($fh, $git, $state, $node->next, $level); + + thread_entry($cb, $git, $state, $node->child, $level + 1); + thread_entry($cb, $git, $state, $node->next, $level); } sub load_results { @@ -573,22 +662,21 @@ sub msg_timestamp { } sub thread_results { - my ($msgs) = @_; + my ($msgs, $nosubject) = @_; require PublicInbox::Thread; my $th = PublicInbox::Thread->new(@$msgs); - $th->thread; no warnings 'once'; - $th->order(*PublicInbox::Thread::sort_ts); + $Mail::Thread::nosubject = $nosubject; + $th->thread; + $th->order(*sort_ts); $th } sub missing_thread { - my ($cb) = @_; - my $title = 'Thread does not exist'; - $cb->([404, ['Content-Type' => 'text/html']])->write(<$title
$title
-Return to index
-EOF + my ($cb, $ctx) = @_; + require PublicInbox::ExtMsg; + + $cb->(PublicInbox::ExtMsg::ext_msg($ctx)) } sub _msg_date { @@ -599,27 +687,36 @@ sub _msg_date { sub _inline_header { my ($dst, $state, $upfx, $mime, $level) = @_; - my $pfx = ' ' x $level; + my $pfx = INDENT x ($level - 1); + my $dot = $level == 0 ? '' : '` '; my $cur = $state->{cur}; - my $mid = $mime->header('Message-ID'); + my $mid = mid_clean($mime->header('Message-ID')); my $f = $mime->header('X-PI-From'); my $d = _msg_date($mime); - $f = PublicInbox::Hval->new($f); - $d = PublicInbox::Hval->new($d); - $f = $f->as_html; - $d = $d->as_html . ' UTC'; - my $midc = mid_compress(mid_clean($mid)); + $f = PublicInbox::Hval->new($f)->as_html; + $d = PublicInbox::Hval->new($d)->as_html; + my $attr = "$f @ $d"; + $state->{first_level} ||= $level; + if ($attr ne $state->{prev_attr} || $state->{prev_level} > $level) { + $state->{prev_attr} = $attr; + $attr = ' - ' . $attr; + $attr .= ' UTC' if $level >= $state->{first_level}; + } else { + $attr = ''; + } + $state->{prev_level} = $level; + if ($cur) { - if ($cur eq $midc) { + if ($cur eq $mid) { delete $state->{cur}; - $$dst .= "$pfx` ". - "[this message] by $f @ $d\n"; + $$dst .= "$pfx$dot". + "[this message]$attr\n"; return; } } else { - $state->{next_msg} ||= $midc; + $state->{next_msg} ||= $mid; } # Subject is never undef, this mail was loaded from @@ -637,22 +734,145 @@ sub _inline_header { my $m = PublicInbox::Hval->new_msgid($mid); $m = $upfx . '../' . $m->as_href . '/'; if (defined $s) { - $$dst .= "$pfx` $s\n" . - "$pfx $f @ $d\n"; + $$dst .= "$pfx$dot$s$attr\n"; } else { - $$dst .= "$pfx` $f @ $d\n"; + $$dst .= "$pfx$dot$f @ $d\n"; } } sub inline_dump { my ($dst, $state, $upfx, $node, $level) = @_; return unless $node; - return if $state->{stopped}; if (my $mime = $node->message) { + my $mid = mid_clean($mime->header('Message-ID')); + if ($mid eq $state->{parent_cmp}) { + $state->{parent} = $mid; + } _inline_header($dst, $state, $upfx, $mime, $level); + } else { + my $dot = $level == 0 ? '' : '` '; + my $pfx = (INDENT x $level) . $dot; + $$dst .= $pfx . ghost_parent($upfx, $node->messageid) . "\n"; } inline_dump($dst, $state, $upfx, $node->child, $level+1); inline_dump($dst, $state, $upfx, $node->next, $level); } +sub sort_ts { + sort { + (eval { $a->topmost->message->header('X-PI-TS') } || 0) <=> + (eval { $b->topmost->message->header('X-PI-TS') } || 0) + } @_; +} + +sub rsort_ts { + sort { + (eval { $b->topmost->message->header('X-PI-TS') } || 0) <=> + (eval { $a->topmost->message->header('X-PI-TS') } || 0) + } @_; +} + +# accumulate recent topics if search is supported +# returns 1 if done, undef if not +sub add_topic { + my ($state, $node, $level) = @_; + return unless $node; + my $child_adjust = 1; + + if (my $x = $node->message) { + $x = $x->header_obj; + my ($topic, $subj); + + $subj = $x->header('Subject'); + $subj = $state->{srch}->subject_normalized($subj); + $topic = $subj; + + # kill "[PATCH v2]" etc. for summarization + $topic =~ s/\A\s*\[[^\]]+\]\s*//g; + $topic = substr($topic, 0, 30); + + if (++$state->{subjs}->{$topic} == 1) { + push @{$state->{order}}, [ $level, $subj, $topic ]; + } + + my $mid = mid_clean($x->header('Message-ID')); + + my $u = $x->header('X-PI-From'); + my $ts = $x->header('X-PI-TS'); + $state->{latest}->{$topic} = [ $mid, $u, $ts ]; + } else { + # ghost message, do not bump level + $child_adjust = 0; + } + + add_topic($state, $node->child, $level + $child_adjust); + add_topic($state, $node->next, $level); +} + +sub dump_topics { + my ($state) = @_; + my $order = $state->{order}; + my $subjs = $state->{subjs}; + my $latest = $state->{latest}; + return "\n[No recent topics]" unless (scalar @$order); + my $dst = ''; + my $pfx; + my $prev = 0; + my $prev_attr = ''; + while (defined(my $info = shift @$order)) { + my ($level, $subj, $topic) = @$info; + my $n = delete $subjs->{$topic}; + my ($mid, $u, $ts) = @{delete $latest->{$topic}}; + $mid = PublicInbox::Hval->new($mid)->as_href; + $subj = PublicInbox::Hval->new($subj)->as_html; + $u = PublicInbox::Hval->new($u)->as_html; + $pfx = INDENT x ($level - 1); + my $nl = $level == $prev ? "\n" : ''; + my $dot = $level == 0 ? '' : '` '; + $dst .= "$nl$pfx$dot$subj\n"; + + my $attr; + $ts = POSIX::strftime('%Y-%m-%d %H:%M', gmtime($ts)); + if ($n == 1) { + $attr = "created by $u @ $ts UTC"; + $n = "\n"; + } else { + # $n isn't the total number of posts on the topic, + # just the number of posts in the current results + # window, so leave it unlabeled + $attr = "updated by $u @ $ts UTC"; + $n = " ($n)\n"; + } + if ($level == 0 || $attr ne $prev_attr) { + $pfx .= INDENT if $level > 0; + $dst .= "$pfx- ". $attr . $n; + $prev_attr = $attr; + } + } + $dst .= ''; +} + +sub emit_index_topics { + my ($state, $fh) = @_; + my $off = $state->{ctx}->{cgi}->param('o'); + $off = 0 unless defined $off; + $state->{order} = []; + $state->{subjs} = {}; + $state->{latest} = {}; + my $max = 25; + my %opts = ( offset => int $off, limit => $max * 4 ); + while (scalar @{$state->{order}} < $max) { + my $res = $state->{srch}->query('', \%opts); + my $nr = scalar @{$res->{msgs}} or last; + + for (rsort_ts(thread_results(load_results($res), 1)->rootset)) { + add_topic($state, $_, 0); + } + $opts{offset} += $nr; + } + + $fh->write(dump_topics($state)); + $opts{offset}; +} + 1;