X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FView.pm;h=fa96cca337d87f9113425a209c5b78aafa2b6dfa;hp=f4f6da1128cb7591c971baa6483a73deea52c16e;hb=4eee5af6011cc8cdefb66c9729952c7eff5c0b0b;hpb=a5968dc059f655a9ac62f1b8bf0bed2b90080b02

diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm
index f4f6da11..fa96cca3 100644
--- a/lib/PublicInbox/View.pm
+++ b/lib/PublicInbox/View.pm
@@ -5,8 +5,7 @@
 # See Documentation/design_www.txt for this.
 package PublicInbox::View;
 use strict;
-use warnings;
-use bytes (); # only for bytes::length
+use v5.10.1;
 use List::Util qw(max);
 use PublicInbox::MsgTime qw(msg_datestamp);
 use PublicInbox::Hval qw(ascii_html obfuscate_addrs prurl mid_href
@@ -22,6 +21,7 @@ use PublicInbox::ViewDiff qw(flush_diff);
 use PublicInbox::Eml;
 use Time::Local qw(timegm);
 use PublicInbox::Smsg qw(subject_normalized);
+use PublicInbox::ContentHash qw(content_hash);
 use constant COLS => 72;
 use constant INDENT => '  ';
 use constant TCHILD => '` ';
@@ -31,13 +31,17 @@ sub msg_page_i {
 	my ($ctx, $eml) = @_;
 	if ($eml) { # called by WwwStream::async_eml or getline
 		my $smsg = $ctx->{smsg};
-		$ctx->{smsg} = $ctx->{over}->next_by_mid(@{$ctx->{next_arg}});
+		my $over = $ctx->{ibx}->over;
+		$ctx->{smsg} = $over ? $over->next_by_mid(@{$ctx->{next_arg}})
+				: $ctx->gone('over');
 		$ctx->{mhref} = ($ctx->{nr} || $ctx->{smsg}) ?
 				"../${\mid_href($smsg->{mid})}/" : '';
 		my $obuf = $ctx->{obuf} = _msg_page_prepare_obuf($eml, $ctx);
-		multipart_text_as_html($eml, $ctx);
+		if (length($$obuf)) {
+			multipart_text_as_html($eml, $ctx);
+			$$obuf .= '</pre><hr>';
+		}
 		delete $ctx->{obuf};
-		$$obuf .= '</pre><hr>';
 		$$obuf .= html_footer($ctx, $ctx->{first_hdr}) if !$ctx->{smsg};
 		$$obuf;
 	} else { # called by WwwStream::async_next or getline
@@ -53,9 +57,11 @@ sub no_over_html ($) {
 	$ctx->{mhref} = '';
 	PublicInbox::WwwStream::init($ctx);
 	my $obuf = $ctx->{obuf} = _msg_page_prepare_obuf($eml, $ctx);
-	multipart_text_as_html($eml, $ctx);
+	if (length($$obuf)) {
+		multipart_text_as_html($eml, $ctx);
+		$$obuf .= '</pre><hr>';
+	}
 	delete $ctx->{obuf};
-	$$obuf .= '</pre><hr>';
 	eval { $$obuf .= html_footer($ctx, $eml) };
 	html_oneshot($ctx, 200, $obuf);
 }
@@ -66,7 +72,7 @@ sub msg_page {
 	my ($ctx) = @_;
 	my $ibx = $ctx->{ibx};
 	$ctx->{-obfs_ibx} = $ibx->{obfuscate} ? $ibx : undef;
-	my $over = $ctx->{over} = $ibx->over or return no_over_html($ctx);
+	my $over = $ibx->over or return no_over_html($ctx);
 	my ($id, $prev);
 	my $next_arg = $ctx->{next_arg} = [ $ctx->{mid}, \$id, \$prev ];
 
@@ -136,6 +142,9 @@ $info
   <a
 href="$se_url">$se_url</a>
 $link</pre>
+
+  Be sure your reply has a <b>Subject:</b> header at the top and a blank line
+  before the message body.
 EOF
 }
 
@@ -254,7 +263,6 @@ sub eml_entry {
 	} elsif ($mapping) {
 		my $nested = 'nested';
 		my $flat = 'flat';
-		my $end = '';
 		if ($ctx->{flat}) {
 			$hr = 1;
 			$flat = "<b>$flat</b>";
@@ -276,8 +284,15 @@ sub eml_entry {
 sub pad_link ($$;$) {
 	my ($mid, $level, $s) = @_;
 	$s ||= '...';
-	my $id = id_compress($mid, 1);
-	(' 'x19).indent_for($level).th_pfx($level)."<a\nhref=#r$id>($s)</a>\n";
+	my $href = defined($mid) ?
+		("<a\nhref=#r".id_compress($mid, 1).">($s)</a>\n") :
+		"($s)\n";
+	(' 'x19).indent_for($level).th_pfx($level).$href;
+}
+
+sub _skel_hdr {
+	# my ($mapping, $mid) = @_;
+	($_[0]->{$_[1] // \'bogus'} // [ "(?)\n" ])->[0];
 }
 
 sub _th_index_lite {
@@ -309,10 +324,11 @@ sub _th_index_lite {
 				my $s = ($idx - 1). ' preceding siblings ...';
 				$rv .= pad_link($pmid, $level, $s);
 			} elsif ($idx == 2) {
-				my $ppmid = $siblings->[0]->{mid};
-				$rv .= $pad . $mapping->{$ppmid}->[0];
+				$rv .= $pad . _skel_hdr($mapping,
+						$siblings->[0] ?
+						$siblings->[0]->{mid} : undef);
 			}
-			$rv .= $pad . $mapping->{$pmid}->[0];
+			$rv .= $pad . _skel_hdr($mapping, $pmid);
 		}
 	}
 	my $s_s = nr_to_s($nr_s, 'sibling', 'siblings');
@@ -322,26 +338,26 @@ sub _th_index_lite {
 	$attr =~ s!<a\nhref=[^>]+>([^<]+)</a>!$1!s; # no point linking to self
 	$rv .= "<b>@ $attr";
 	if ($nr_c) {
-		my $cmid = $children->[0]->{mid};
-		$rv .= $pad . $mapping->{$cmid}->[0];
+		my $cmid = $children->[0] ? $children->[0]->{mid} : undef;
+		$rv .= $pad . _skel_hdr($mapping, $cmid);
 		if ($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->{mid}}->[0];
+			$rv .= $pad . _skel_hdr($mapping, $cn->{mid});
 		}
 	}
 
 	my $next = $siblings->[$idx+1] if $siblings && $idx >= 0;
 	if ($next) {
 		my $nmid = $next->{mid};
-		$rv .= $pad . $mapping->{$nmid}->[0];
+		$rv .= $pad . _skel_hdr($mapping, $nmid);
 		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->{mid}}->[0];
+			$rv .= $pad . _skel_hdr($mapping, $nn->{mid});
 		}
 	}
 	$rv .= $pad ."<a\nhref=#r$id>$s_s, $s_c; $ctx->{s_nr}</a>\n";
@@ -420,6 +436,7 @@ sub stream_thread ($$) {
 # /$INBOX/$MSGID/t/ and /$INBOX/$MSGID/T/
 sub thread_html {
 	my ($ctx) = @_;
+	$ctx->{-upfx} = '../../';
 	my $mid = $ctx->{mid};
 	my $ibx = $ctx->{ibx};
 	my ($nr, $msgs) = $ibx->over->get_thread($mid);
@@ -443,13 +460,12 @@ EOF
 	$skel .= " (download: <a\nhref=\"../t.mbox.gz\">mbox.gz</a>";
 	$skel .= " / follow: <a\nhref=\"../t.atom\">Atom feed</a>)\n";
 	$skel .= "-- links below jump to the message on this page --\n";
-	$ctx->{-upfx} = '../../';
 	$ctx->{cur_level} = 0;
 	$ctx->{skel} = \$skel;
 	$ctx->{prev_attr} = '';
 	$ctx->{prev_level} = 0;
-	$ctx->{root_anchor} = anchor_for($mid);
-	$ctx->{mapping} = {};
+	$ctx->{root_anchor} = 'm' . id_compress($mid, 1);
+	$ctx->{mapping} = {}; # mid -> [ header_summary, node, idx, level ]
 	$ctx->{s_nr} = ($nr > 1 ? "$nr+ messages" : 'only message')
 	               .' in thread';
 
@@ -518,7 +534,8 @@ sub attach_link ($$$$;$) {
 	return unless $part->{bdy};
 
 	my $nl = $idx eq '1' ? '' : "\n"; # like join("\n", ...)
-	my $size = bytes::length($part->body);
+	my $size = length($part->body);
+	delete $part->{bdy}; # save memory
 
 	# hide attributes normally, unless we want to aid users in
 	# spotting MUA problems:
@@ -571,7 +588,7 @@ sub add_text_body { # callback for each_part
 
 	# 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;
+	$s =~ s/\r+\n/\n/sg;
 
 	# will be escaped to `&#8226;' in HTML
 	obfuscate_addrs($ibx, $s, "\x{2022}") if $ibx->{obfuscate};
@@ -610,9 +627,6 @@ sub add_text_body { # callback for each_part
 		$ctx->{-spfx} = $spfx;
 	};
 
-	# some editors don't put trailing newlines at the end:
-	$s .= "\n" unless $s =~ /\n\z/s;
-
 	# split off quoted and unquoted blocks:
 	my @sections = PublicInbox::MsgIter::split_quotes($s);
 	undef $s; # free memory
@@ -621,6 +635,7 @@ sub add_text_body { # callback for each_part
 		attach_link($ctx, $ct, $p, $fn, $err);
 		$$rv .= "\n";
 	}
+	delete $part->{bdy}; # save memory
 	foreach my $cur (@sections) {
 		if ($cur =~ /\A>/) {
 			# we use a <span> here to allow users to specify
@@ -646,13 +661,16 @@ sub _msg_page_prepare_obuf {
 	my $mids = mids_for_index($eml);
 	my $nr = $ctx->{nr}++;
 	if ($nr) { # unlikely
+		if ($ctx->{chash} eq content_hash($eml)) {
+			warn "W: BUG? @$mids not deduplicated properly\n";
+			return \$rv;
+		}
+		$rv .=
+"<pre>WARNING: multiple messages have this Message-ID\n</pre>";
 		$rv .= '<pre>';
 	} else {
 		$ctx->{first_hdr} = $eml->header_obj;
-		if ($ctx->{smsg}) {
-			$rv .=
-"<pre>WARNING: multiple messages have this Message-ID\n</pre>";
-		}
+		$ctx->{chash} = content_hash($eml) if $ctx->{smsg}; # reused MID
 		$rv .= "<pre\nid=b>"; # anchor for body start
 	}
 	$ctx->{-upfx} = '../' if $over;
@@ -694,7 +712,7 @@ sub _msg_page_prepare_obuf {
 	for my $v ($eml->header('Date')) {
 		$v = ascii_html($v);
 		obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx; # possible :P
-		$rv .= "Date: $v\n";
+		$rv .= qq{Date: $v\t<a\nhref="#r">[thread overview]</a>\n};
 	}
 	if (!$nr) { # first (and only) message, common case
 		$ctx->{-title_html} = join(' - ', @title);
@@ -739,7 +757,8 @@ sub thread_skel ($$$) {
 			$$skel .= SKEL_EXPAND."\n ";
 			$$skel .= ghost_parent('../', $parent) . "\n";
 		} else {
-			$$skel .= '[no followups] '.SKEL_EXPAND."\n";
+			$$skel .= "<a\nid=r>[no followups]</a> ".
+					SKEL_EXPAND."\n";
 		}
 		$ctx->{next_msg} = undef;
 		$ctx->{parent_msg} = $parent;
@@ -860,11 +879,6 @@ sub linkify_ref_no_over {
 	"&lt;<a\nhref=\"../$href/\">$html</a>&gt;";
 }
 
-sub anchor_for {
-	my ($msgid) = @_;
-	'm' . id_compress($msgid, 1);
-}
-
 sub ghost_parent {
 	my ($upfx, $mid) = @_;
 
@@ -966,7 +980,7 @@ sub skel_dump { # walk_thread callback
 		$$skel .= delete($ctx->{sl_note}) || '';
 	}
 
-	my $f = ascii_html($smsg->{from_name});
+	my $f = ascii_html(delete $smsg->{from_name});
 	my $obfs_ibx = $ctx->{-obfs_ibx};
 	obfuscate_addrs($obfs_ibx, $f) if $obfs_ibx;
 
@@ -1061,10 +1075,10 @@ sub _skel_ghost {
 }
 
 sub sort_ds {
-	[ sort {
+	@{$_[0]} = sort {
 		(eval { $a->topmost->{ds} } || 0) <=>
 		(eval { $b->topmost->{ds} } || 0)
-	} @{$_[0]} ];
+	} @{$_[0]};
 }
 
 # accumulate recent topics if search is supported
@@ -1142,10 +1156,8 @@ sub dump_topics {
 			$anchor = '#t'; # thread skeleton
 		}
 
-		my $mbox = qq(<a\nhref="$href/t.mbox.gz">mbox.gz</a>);
-		my $atom = qq(<a\nhref="$href/t.atom">Atom</a>);
 		my $s = "<a\nhref=\"$href/T/$anchor\">$top_subj</a>\n" .
-			" $ds UTC $n - $mbox / $atom\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
@@ -1265,7 +1277,7 @@ sub thread_adj_level {
 sub ghost_index_entry {
 	my ($ctx, $level, $node) = @_;
 	my ($beg, $end) = thread_adj_level($ctx,  $level);
-	$beg . '<pre>'. ghost_parent($ctx->{-upfx}, $node->{mid})
+	$beg . '<pre>'. ghost_parent($ctx->{-upfx}, $node->{mid} // '?')
 		. '</pre>' . $end;
 }