use Email::MIME::ContentType qw/parse_content_type/;
use PublicInbox::Hval;
use PublicInbox::MID qw/mid_clean mid_compress mid2path/;
-use Digest::SHA;
+use Digest::SHA qw/sha1_hex/;
+my $SALT = rand;
require POSIX;
# TODO: make these constants tunable
use constant MAX_TRUNC_LEN => 72;
use constant PRE_WRAP => "<pre\nstyle=\"white-space:pre-wrap\">";
use constant T_ANCHOR => '#u';
+use constant INDENT => ' ';
*ascii_html = *PublicInbox::Hval::ascii_html;
PRE_WRAP . multipart_text_as_html($mime, $full_pfx) . '</pre>';
}
+sub in_reply_to {
+ my ($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 $1;
+ }
+ undef;
+}
+
# this is already inside a <pre>
sub index_entry {
my ($fh, $mime, $level, $state) = @_;
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;
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, $t_anchor);
- if (defined $irt) {
- $anchor_idx = anchor_for($irt);
- $anchor = $seen->{$anchor_idx};
- $t_anchor = T_ANCHOR;
- } else {
- $t_anchor = '';
- }
+ my $irt = in_reply_to($header_obj);
+ my $parent_anchor = $seen->{anchor_for($irt)} if defined $irt;
+
if ($srch) {
- $subj = "<a\nhref=\"${path}t/$href/#u\">$subj</a>";
+ my $t = $ctx->{flat} ? 'T' : 't';
+ $subj = "<a\nhref=\"${path}$href/$t/#u\">$subj</a>";
}
if ($root_anchor && $root_anchor eq $id) {
$subj = "<u\nid=\"u\">$subj</u>";
}
- my $ts = $mime->header('X-PI-TS');
- unless (defined $ts) {
- $ts = msg_timestamp($mime);
- }
- $ts = POSIX::strftime('%Y-%m-%d %H:%M', gmtime($ts));
-
+ my $ts = _msg_date($mime);
my $rv = "<table\nsummary=l$level><tr>";
if ($level) {
- $rv .= '<td><pre>' . (' ' x $level) . '</pre></td>';
+ $rv .= '<td><pre>' . (INDENT x $level) . '</pre></td>';
}
$rv .= "<td\nid=s$midx>" . PRE_WRAP;
$rv .= "<b\nid=\"$id\">$subj</b>\n";
$fh->write($rv .= "\n\n");
my ($fhref, $more_ref);
- my $mhref = "${path}m/$href/";
- if ($level > 0) {
- $fhref = "${path}f/$href/";
+ my $mhref = "${path}$href/";
+
+ # show full messages at level == 0 in threaded view
+ if ($level > 0 || ($ctx->{flat} && $root_anchor ne $id)) {
+ $fhref = "${path}$href/f/";
$more_ref = \$more;
}
# scan through all parts, looking for displayable text
});
$mime->body_set('');
- my $txt = "${path}m/$href/raw";
+ my $txt = "${path}$href/raw";
$rv = "\n<a\nhref=\"$mhref\">$more</a> <a\nhref=\"$txt\">raw</a> ";
$rv .= html_footer($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}m/$v/";
- $seen->{$anchor_idx} = $anchor;
+ $parent_anchor = "${path}$v/";
}
- $rv .= " <a\nhref=\"$anchor\">parent</a>";
+ $rv .= " <a\nhref=\"$parent_anchor\">parent</a>";
}
-
if ($srch) {
- $rv .= " <a\nhref=\"${path}t/$href/$t_anchor\">" .
- "threadlink</a>";
+ if ($ctx->{flat}) {
+ $rv .= " [<a\nhref=\"${path}$href/t/#u\">threaded</a>" .
+ "|<b>flat</b>]";
+ } else {
+ $rv .= " [<b>threaded</b>|" .
+ "<a\nhref=\"${path}$href/T/#u\">flat</a>]";
+ }
}
$fh->write($rv .= '</pre></td></tr></table>');
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 $next = "<a\nid=\"s$final_anchor\">";
$next .= $final_anchor == 1 ? 'only message in' : 'end of';
- $next .= " thread</a>, back to <a\nhref=\"../../\">index</a>\n";
- $next .= "download: <a\nhref=\"mbox.gz\">mbox.gz</a>\n\n";
- $fh->write("<hr />" . PRE_WRAP . $next . $foot .
+ $next .= " thread</a>, back to <a\nhref=\"../../\">index</a>";
+ if ($flat) {
+ $next .= " [<a\nhref=\"../t/#u\">threaded</a>|<b>flat</b>]";
+ } else {
+ $next .= " [<b>threaded</b>|<a\nhref=\"../T/#u\">flat</a>]";
+ }
+ $next .= "\ndownload thread: <a\nhref=\"../t.mbox.gz\">mbox.gz</a>";
+ $next .= " / follow: <a\nhref=\"../t.atom\">Atom feed</a>";
+ $cb->write("<hr />" . PRE_WRAP . $next . "\n\n". $foot .
"</pre></body></html>");
- $fh->close;
+ $cb->close;
}
sub index_walk {
[\@:\w\.-]+/
?[\@\w\+\&\?\.\%\;/#=-]*)!x;
-sub linkify {
- # no newlines added here since it'd break the splitting we do
- # to fold quotes
- $_[0] =~ s!$LINK_RE!<a\nhref="$1">$1</a>!g;
+sub linkify_1 {
+ my ($link_map, $s) = @_;
+ $s =~ s!$LINK_RE!
+ my $url = $1;
+ # salt this, as this could be exploited to show
+ # links in the HTML which don't show up in the raw mail.
+ my $key = sha1_hex($url . $SALT);
+ $link_map->{$key} = $url;
+ 'PI-LINK-'. $key;
+ !ge;
+ $s;
+}
+
+sub linkify_2 {
+ my ($link_map, $s) = @_;
+
+ # Added "PI-LINK-" prefix to avoid false-positives on git commits
+ $s =~ s!\bPI-LINK-([a-f0-9]{40})\b!
+ my $key = $1;
+ my $url = $link_map->{$key};
+ if (defined $url) {
+ $url = ascii_html($url);
+ "<a\nhref=\"$url\">$url</a>";
+ } else {
+ # false positive or somebody tried to mess with us
+ $key;
+ }
+ !ge;
+ $s;
}
sub flush_quote {
if ($full_pfx) {
if (!$final && scalar(@$quot) <= MAX_INLINE_QUOTED) {
# show quote inline
- my $rv = join('', map { linkify($_); $_ } @$quot);
+ my %l;
+ my $rv = join('', map { linkify_1(\%l, $_) } @$quot);
@$quot = ();
- return $rv;
+ $rv = ascii_html($rv);
+ return linkify_2(\%l, $rv);
}
# show a short snippet of quoted text and link to full version:
- @$quot = map { s/^(?:>\s*)+//gm; $_ } @$quot;
+ @$quot = map { s/^(?:>\s*)+//gm; $_ } @$quot;
my $cur = join(' ', @$quot);
@$quot = split(/\s+/, $cur);
$cur = '';
} while (@$quot && length($cur) < MAX_TRUNC_LEN);
@$quot = ();
$cur =~ s/ \z/ .../s;
+ $cur = ascii_html($cur);
my $nr = ++$$n;
"> [<a\nhref=\"$full_pfx#q${part_nr}_$nr\">$cur</a>]\n";
} else {
# show everything in the full version with anchor from
# short version (see above)
my $nr = ++$$n;
- my $rv = "<a\nid=q${part_nr}_$nr></a>";
- $rv .= join('', map { linkify($_); $_ } @$quot);
+ my $rv = "";
+ my %l;
+ $rv .= join('', map { linkify_1(\%l, $_) } @$quot);
@$quot = ();
- $rv;
+ $rv = ascii_html($rv);
+ "<a\nid=q${part_nr}_$nr></a>" . linkify_2(\%l, $rv);
}
}
my $s = $part->body;
$part->body_set('');
$s = $enc->decode($s);
- $s = ascii_html($s);
my @lines = split(/^/m, $s);
$s = '';
my @quot;
while (defined(my $cur = shift @lines)) {
- if ($cur !~ /^>/) {
+ if ($cur !~ /^>/) {
# show the previously buffered quote inline
if (scalar @quot) {
$s .= flush_quote(\@quot, \$n, $$part_nr,
}
# regular line, OK
- linkify($cur);
- $s .= $cur;
+ my %l;
+ $cur = linkify_1(\%l, $cur);
+ $cur = ascii_html($cur);
+ $s .= linkify_2(\%l, $cur);
} else {
push @quot, $cur;
}
} elsif ($h eq 'Subject') {
$title[0] = $v->as_html;
if ($srch) {
- $rv .= "$h: <a\nid=\"t\"\n" .
- "href=\"../../t/$mid_href/\">";
+ my $p = $full_pfx ? '' : '../';
+ $rv .= "$h: <a\nid=\"t\"\nhref=\"${p}t/#u\">";
$rv .= $v->as_html . "</a>\n";
next;
}
}
$rv .= 'Message-ID: <' . $mid->as_html . '> ';
- my $raw_ref = $full_pfx ? 'raw' : "../../m/$mid_href/raw";
+ my $raw_ref = $full_pfx ? 'raw' : '../raw';
$rv .= "(<a\nhref=\"$raw_ref\">raw</a>)\n";
if ($srch) {
$rv .= "<a\nhref=\"#r\">References: [see below]</a>\n";
}
sub thread_inline {
- my ($dst, $ctx, $cur) = @_;
+ my ($dst, $ctx, $cur, $full_pfx) = @_;
my $srch = $ctx->{srch};
my $mid = mid_compress(mid_clean($cur->header('Message-ID')));
my $res = $srch->get_thread($mid);
my $nr = $res->{total};
+
if ($nr <= 1) {
- $$dst .= "[only message in thread]\n";
- return;
+ $$dst .= "\n[no followups, yet]\n";
+ return (undef, in_reply_to($cur));
}
+ my $upfx = $full_pfx ? '' : '../';
- $$dst .= "roughly $nr messages in thread:\n";
+ $$dst .= "\n\n~$nr messages in thread: ".
+ "(<a\nhref=\"${upfx}t/#u\">expand</a>)\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 => $parent ? mid_compress($parent) : '',
+ parent => $parent,
};
for (thread_results(load_results($res))->rootset) {
- inline_dump($dst, $state, $_, 0);
+ 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: <";
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) {
my $href = "mailto:$to?In-Reply-To=$irt&Cc=${cc}&Subject=$subj";
my $srch = $ctx->{srch} if $ctx;
- my $idx = $standalone ? " <a\nhref=\"../../\">index</a>" : '';
+ my $upfx = $full_pfx ? '../' : '../../';
+ my $idx = $standalone ? " <a\nhref=\"$upfx\">index</a>" : '';
if ($idx && $srch) {
- $mid = mid_compress(mid_clean($mid));
- my $t_anchor = defined $irt ? T_ANCHOR : '';
- $irt = $mime->header('In-Reply-To');
- $idx = " <a\nhref=\"../../t/$mid/$t_anchor\">".
- "threadlink</a>$idx\n\n";
- my $next = thread_inline(\$idx, $ctx, $mime);
- if (defined $irt) {
- $irt = PublicInbox::Hval->new_msgid($irt);
- $irt = $irt->as_href;
- $irt = "<a\nhref=\"../$irt/\">parent</a> ";
+ my ($next, $p) = thread_inline(\$idx, $ctx, $mime, $full_pfx);
+ if (defined $p) {
+ $p = PublicInbox::Hval->new_oneline($p);
+ $p = $p->as_href;
+ $irt = "<a\nhref=\"$upfx$p/\">parent</a> ";
} else {
$irt = ' ' x length('parent ');
}
if ($next) {
- $irt .= "<a\nhref=\"../$next/\">next</a> ";
+ $irt .= "<a\nhref=\"$upfx$next/\">next</a> ";
} else {
$irt .= ' ';
}
"$irt<a\nhref=\"" . ascii_html($href) . '">reply</a>' . $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;
"<<a\nhref=\"../$href/\">$html</a>>";
}
sub thread_html_head {
- my ($mime) = @_;
+ my ($cb, $mime) = @_;
+ $$cb = $$cb->([200, ['Content-Type'=> 'text/html; charset=UTF-8']]);
+
my $s = PublicInbox::Hval->new_oneline($mime->header('Subject'));
$s = $s->as_html;
- "<html><head><title>$s</title></head><body>";
+ $$cb->write("<html><head><title>$s</title></head><body>");
+}
+
+sub pre_anchor_entry {
+ my ($seen, $mime) = @_;
+ my $id = anchor_for($mime->header('Message-ID'));
+ $seen->{$id} = "#$id"; # save the anchor for children, later
+}
+
+sub __thread_entry {
+ my ($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) {
+ my $mid = PublicInbox::Hval->new_msgid($g->[0]);
+ my $pfx = INDENT x $g->[1];
+ my $href = $mid->as_href;
+ my $html = $mid->as_html;
+ $$cb->write("<table><tr><td>$pfx</td><td>" .
+ PRE_WRAP .
+ '[parent not found: <' .
+ qq{<a\nhref="../../$href/">}.
+ "$html</a>>]</pre></td></table>");
+ }
+ }
+ index_entry($$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, $level);
}
sub load_results {
}
sub missing_thread {
- my ($cb) = @_;
- my $title = 'Thread does not exist';
- $cb->([404, ['Content-Type' => 'text/html']])->write(<<EOF);
-<html><head><title>$title</title></head><body><pre>$title
-<a href="../../">Return to index</a></pre></body></html>
-EOF
+ my ($cb, $ctx) = @_;
+ require PublicInbox::ExtMsg;
+
+ $cb->(PublicInbox::ExtMsg::ext_msg($ctx))
+}
+
+sub _msg_date {
+ my ($mime) = @_;
+ my $ts = $mime->header('X-PI-TS') || msg_timestamp($mime);
+ POSIX::strftime('%Y-%m-%d %H:%M', gmtime($ts));
}
sub _inline_header {
- my ($dst, $state, $mime, $level) = @_;
- my $pfx = ' ' x $level;
+ my ($dst, $state, $upfx, $mime, $level) = @_;
+ my $pfx = INDENT x $level;
my $cur = $state->{cur};
my $mid = $mime->header('Message-ID');
my $f = $mime->header('X-PI-From');
- my $d = $mime->header('X-PI-Date');
+ my $d = _msg_date($mime);
$f = PublicInbox::Hval->new($f);
$d = PublicInbox::Hval->new($d);
$f = $f->as_html;
$s = $s->as_html;
}
my $m = PublicInbox::Hval->new_msgid($mid);
- $m = '../' . $m->as_href . '/';
+ $m = $upfx . '../' . $m->as_href . '/';
if (defined $s) {
$$dst .= "$pfx` <a\nhref=\"$m\">$s</a>\n" .
"$pfx $f @ $d\n";
}
sub inline_dump {
- my ($dst, $state, $node, $level) = @_;
+ my ($dst, $state, $upfx, $node, $level) = @_;
return unless $node;
- return if $state->{stopped};
if (my $mime = $node->message) {
- _inline_header($dst, $state, $mime, $level);
+ my $mid = mid_clean($mime->header('Message-ID'));
+ if ($mid eq $state->{parent_cmp}) {
+ $state->{parent} = $mid;
+ }
+ _inline_header($dst, $state, $upfx, $mime, $level);
+ } else {
+ my $pfx = INDENT x $level;
+ my $v = PublicInbox::Hval->new_msgid($node->messageid, 1);
+ my $html = $v->as_html;
+ my $href = $v->as_href;
+ $$dst .= $pfx . '` [parent not found: <' .
+ qq{<a\nhref="$upfx../$href/">}.
+ "$html</a>>]\n";
}
- inline_dump($dst, $state, $node->child, $level+1);
- inline_dump($dst, $state, $node->next, $level);
+ inline_dump($dst, $state, $upfx, $node->child, $level+1);
+ inline_dump($dst, $state, $upfx, $node->next, $level);
}
1;