#
# Used for displaying the HTML web interface.
@@ -6,6 +6,7 @@
package PublicInbox::View;
use strict;
use warnings;
+use bytes (); # only for bytes::length
use PublicInbox::MsgTime qw(msg_datestamp);
use PublicInbox::Hval qw/ascii_html obfuscate_addrs/;
use PublicInbox::Linkify;
@@ -14,9 +15,11 @@ use PublicInbox::MsgIter;
use PublicInbox::Address;
use PublicInbox::WwwStream;
use PublicInbox::Reply;
+use PublicInbox::ViewDiff qw(flush_diff);
require POSIX;
use Time::Local qw(timegm);
-
+use PublicInbox::SearchMsg qw(subject_normalized);
+use constant COLS => 72;
use constant INDENT => ' ';
use constant TCHILD => '` ';
sub th_pfx ($) { $_[0] == 0 ? '' : TCHILD };
@@ -27,7 +30,7 @@ sub msg_html {
my ($ctx, $mime, $more, $smsg) = @_;
my $hdr = $mime->header_obj;
my $ibx = $ctx->{-inbox};
- my $obfs_ibx = $ctx->{-obfs_ibx} = $ibx->{obfuscate} ? $ibx : undef;
+ $ctx->{-obfs_ibx} = $ibx->{obfuscate} ? $ibx : undef;
my $tip = _msg_html_prepare($hdr, $ctx, $more, 0);
my $end = 2;
PublicInbox::WwwStream->response($ctx, 200, sub {
@@ -35,7 +38,7 @@ sub msg_html {
if ($nr == 1) {
# $more cannot be true w/o $smsg being defined:
my $upfx = $more ? '../'.mid_escape($smsg->mid).'/' : '';
- $tip . multipart_text_as_html($mime, $upfx, $obfs_ibx) .
+ $tip . multipart_text_as_html($mime, $upfx, $ctx) .
'
'
} elsif ($more && @$more) {
++$end;
@@ -60,12 +63,12 @@ sub msg_page {
my $ibx = $ctx->{-inbox};
my ($first, $more);
my $smsg;
- if (my $srch = $ibx->search) {
+ if (my $over = $ibx->over) {
my ($id, $prev);
- $smsg = $srch->next_by_mid($mid, \$id, \$prev);
+ $smsg = $over->next_by_mid($mid, \$id, \$prev);
$first = $ibx->msg_by_smsg($smsg) if $smsg;
if ($first) {
- my $next = $srch->next_by_mid($mid, \$id, \$prev);
+ my $next = $over->next_by_mid($mid, \$id, \$prev);
$more = [ $id, $prev, $next ] if $next;
}
return unless $first;
@@ -80,15 +83,15 @@ sub msg_html_more {
my $str = eval {
my ($id, $prev, $smsg) = @$more;
my $mid = $ctx->{mid};
- $smsg = $ctx->{-inbox}->smsg_mime($smsg);
- my $next = $ctx->{srch}->next_by_mid($mid, \$id, \$prev);
+ my $ibx = $ctx->{-inbox};
+ $smsg = $ibx->smsg_mime($smsg);
+ my $next = $ibx->over->next_by_mid($mid, \$id, \$prev);
@$more = $next ? ($id, $prev, $next) : ();
if ($smsg) {
my $mime = $smsg->{mime};
my $upfx = '../' . mid_escape($smsg->mid) . '/';
_msg_html_prepare($mime->header_obj, $ctx, $more, $nr) .
- multipart_text_as_html($mime, $upfx,
- $ctx->{-obfs_ibx}) .
+ multipart_text_as_html($mime, $upfx, $ctx) .
'
'
} else {
'';
@@ -118,6 +121,9 @@ sub msg_reply {
my ($arg, $link, $reply_to_all) =
PublicInbox::Reply::mailto_arg_link($ibx, $hdr);
+ if (ref($arg) eq 'SCALAR') {
+ return ''.ascii_html($$arg).'
';
+ }
# mailto: link only works if address obfuscation is disabled
if ($link) {
@@ -164,6 +170,24 @@ sub in_reply_to {
$refs->[-1];
}
+sub fold_addresses ($) {
+ return $_[0] if length($_[0]) <= COLS;
+ # try to fold on commas after non-word chars before $lim chars,
+ # Try to get the "," preceeded by ">" or ")", but avoid folding
+ # on the comma where somebody uses "Lastname, Firstname".
+ # We also try to keep the last and penultimate addresses in
+ # the list on the same line if possible, hence the extra \z
+ # Fall back to folding on spaces at $lim + 1 chars
+ my $lim = COLS - 8; # 8 = "\t" display width
+ my $too_long = $lim + 1;
+ $_[0] =~ s/\s*\z//s; # Email::Simple doesn't strip trailing spaces
+ $_[0] = join("\n\t",
+ ($_[0] =~ /(.{0,$lim}\W(?:,|\z)|
+ .{1,$lim}(?:,|\z)|
+ .{1,$lim}|
+ .{$too_long,}?)(?:\s|\z)/xgo));
+}
+
sub _hdr_names_html ($$) {
my ($hdr, $field) = @_;
my $val = $hdr->header($field) or return '';
@@ -179,7 +203,6 @@ sub nr_to_s ($$$) {
# this is already inside a
sub index_entry {
my ($smsg, $ctx, $more) = @_;
- my $srch = $ctx->{srch};
my $subj = $smsg->subject;
my $mid_raw = $smsg->mid;
my $id = id_compress($mid_raw, 1);
@@ -189,6 +212,7 @@ sub index_entry {
my $irt;
my $obfs_ibx = $ctx->{-obfs_ibx};
+ $subj = '(no subject)' if $subj eq '';
my $rv = "* ";
$subj = ''.ascii_html($subj).'';
obfuscate_addrs($obfs_ibx, $subj) if $obfs_ibx;
@@ -196,23 +220,37 @@ sub index_entry {
$rv .= $subj . "\n";
$rv .= _th_index_lite($mid_raw, \$irt, $id, $ctx);
my @tocc;
- my $mime = $smsg->{mime};
+ 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 $hdr = $mime->header_obj;
- foreach my $f (qw(To Cc)) {
- my $dst = _hdr_names_html($hdr, $f);
- if ($dst ne '') {
- obfuscate_addrs($obfs_ibx, $dst) if $obfs_ibx;
- push @tocc, "$f: $dst";
- }
- }
my $from = _hdr_names_html($hdr, 'From');
obfuscate_addrs($obfs_ibx, $from) if $obfs_ibx;
- $rv .= "From: $from @ ".fmt_ts($smsg->ds)." UTC";
+ $rv .= "From: $from @ ".fmt_ts($ds)." UTC";
my $upfx = $ctx->{-upfx};
my $mhref = $upfx . mid_escape($mid_raw) . '/';
$rv .= qq{ (permalink / };
$rv .= qq{raw)\n};
- $rv .= ' '.join('; +', @tocc) . "\n" if @tocc;
+ my $to = fold_addresses(_hdr_names_html($hdr, 'To'));
+ my $cc = fold_addresses(_hdr_names_html($hdr, 'Cc'));
+ my ($tlen, $clen) = (length($to), length($cc));
+ my $to_cc = '';
+ if (($tlen + $clen) > COLS) {
+ $to_cc .= ' To: '.$to."\n" if $tlen;
+ $to_cc .= ' Cc: '.$cc."\n" if $clen;
+ } else {
+ if ($tlen) {
+ $to_cc .= ' To: '.$to;
+ $to_cc .= '; +Cc: '.$cc if $clen;
+ } else {
+ $to_cc .= ' Cc: '.$cc if $clen;
+ }
+ $to_cc .= "\n";
+ }
+ obfuscate_addrs($obfs_ibx, $to_cc) if $obfs_ibx;
+ $rv .= $to_cc;
my $mapping = $ctx->{mapping};
if (!$mapping && (defined($irt) || defined($irt = in_reply_to($hdr)))) {
@@ -224,7 +262,8 @@ sub index_entry {
$rv .= "\n";
# scan through all parts, looking for displayable text
- msg_iter($mime, sub { $rv .= add_text_body($mhref, $obfs_ibx, $_[0]) });
+ my $ibx = $ctx->{-inbox};
+ msg_iter($mime, sub { $rv .= add_text_body($mhref, $ctx, $_[0]) });
# add the footer
$rv .= "\n^ ".
@@ -278,7 +317,10 @@ sub _th_index_lite {
my $nr_s = 0;
my $siblings;
if (my $smsg = $node->{smsg}) {
- ($$irt) = (($smsg->{references} || '') =~ m/<([^>]+)>\z/);
+ # delete saves about 200KB on a 1K message thread
+ if (my $refs = delete $smsg->{references}) {
+ ($$irt) = ($refs =~ m/<([^>]+)>\z/);
+ }
}
my $irt_map = $mapping->{$$irt} if defined $$irt;
if (defined $irt_map) {
@@ -336,7 +378,7 @@ sub walk_thread {
while (@q) {
my ($level, $node, $i) = splice(@q, 0, 3);
defined $node or next;
- $cb->($ctx, $level, $node, $i);
+ $cb->($ctx, $level, $node, $i) or return;
++$level;
$i = 0;
unshift @q, map { ($level, $_, $i++) } @{$node->{children}};
@@ -357,7 +399,7 @@ sub thread_index_entry {
sub stream_thread ($$) {
my ($rootset, $ctx) = @_;
- my $inbox = $ctx->{-inbox};
+ my $ibx = $ctx->{-inbox};
my @q = map { (0, $_) } @$rootset;
my $level;
my $smsg;
@@ -366,11 +408,11 @@ sub stream_thread ($$) {
my $node = shift @q or next;
my $cl = $level + 1;
unshift @q, map { ($cl, $_) } @{$node->{children}};
- $smsg = $inbox->smsg_mime($node->{smsg}) and last;
+ $smsg = $ibx->smsg_mime($node->{smsg}) and last;
}
return missing_thread($ctx) unless $smsg;
- $ctx->{-obfs_ibx} = $inbox->{obfuscate} ? $inbox : undef;
+ $ctx->{-obfs_ibx} = $ibx->{obfuscate} ? $ibx : undef;
$ctx->{-title_html} = ascii_html($smsg->subject);
$ctx->{-html_tip} = thread_index_entry($ctx, $level, $smsg);
$smsg = undef;
@@ -381,7 +423,7 @@ sub stream_thread ($$) {
my $node = shift @q or next;
my $cl = $level + 1;
unshift @q, map { ($cl, $_) } @{$node->{children}};
- if ($smsg = $inbox->smsg_mime($node->{smsg})) {
+ if ($smsg = $ibx->smsg_mime($node->{smsg})) {
return thread_index_entry($ctx, $level, $smsg);
} else {
return ghost_index_entry($ctx, $level, $node);
@@ -397,8 +439,8 @@ sub stream_thread ($$) {
sub thread_html {
my ($ctx) = @_;
my $mid = $ctx->{mid};
- my $srch = $ctx->{srch};
- my ($nr, $msgs) = $srch->get_thread($mid);
+ my $ibx = $ctx->{-inbox};
+ my ($nr, $msgs) = $ibx->over->get_thread($mid);
return missing_thread($ctx) if $nr == 0;
my $skel = '
';
$skel .= $nr == 1 ? 'only message in thread' : 'end of thread';
@@ -415,13 +457,13 @@ sub thread_html {
$ctx->{prev_level} = 0;
$ctx->{root_anchor} = anchor_for($mid);
$ctx->{mapping} = {};
- $ctx->{s_nr} = "$nr+ messages in thread";
+ $ctx->{s_nr} = ($nr > 1 ? "$nr+ messages" : 'only message')
+ .' in thread';
my $rootset = thread_results($ctx, $msgs);
# reduce hash lookups in pre_thread->skel_dump
- my $inbox = $ctx->{-inbox};
- $ctx->{-obfs_ibx} = $inbox->{obfuscate} ? $inbox : undef;
+ $ctx->{-obfs_ibx} = $ibx->{obfuscate} ? $ibx : undef;
walk_thread($rootset, $ctx, *pre_thread);
$skel .= '
';
@@ -430,7 +472,7 @@ sub thread_html {
# flat display: lazy load the full message from smsg
my $smsg;
while (my $m = shift @$msgs) {
- $smsg = $inbox->smsg_mime($m) and last;
+ $smsg = $ibx->smsg_mime($m) and last;
}
return missing_thread($ctx) unless $smsg;
$ctx->{-title_html} = ascii_html($smsg->subject);
@@ -440,7 +482,7 @@ sub thread_html {
return unless $msgs;
$smsg = undef;
while (my $m = shift @$msgs) {
- $smsg = $inbox->smsg_mime($m) and last;
+ $smsg = $ibx->smsg_mime($m) and last;
}
return index_entry($smsg, $ctx, scalar @$msgs) if $smsg;
$msgs = undef;
@@ -449,11 +491,11 @@ sub thread_html {
}
sub multipart_text_as_html {
- my ($mime, $upfx, $obfs_ibx) = @_;
+ my ($mime, $upfx, $ctx) = @_;
my $rv = "";
# scan through all parts, looking for displayable text
- msg_iter($mime, sub { $rv .= add_text_body($upfx, $obfs_ibx, $_[0]) });
+ msg_iter($mime, sub { $rv .= add_text_body($upfx, $ctx, $_[0]) });
$rv;
}
@@ -462,12 +504,12 @@ sub flush_quote {
# show everything in the full version with anchor from
# short version (see above)
- my $rv = $l->linkify_1(join('', @$quot));
- @$quot = ();
+ my $rv = $l->linkify_1($$quot);
# we use a here to allow users to specify their own
# color for quoted text
$rv = $l->linkify_2(ascii_html($rv));
+ $$quot = undef;
$$s .= qq() . $rv . ''
}
@@ -486,7 +528,7 @@ sub attach_link ($$$$;$) {
$desc = $fn unless defined $desc;
$desc = '' unless defined $desc;
my $sfn;
- if (defined $fn && $fn =~ /\A[[:alnum:]][\w\.-]+[[:alnum:]]\z/) {
+ if (defined $fn && $fn =~ /\A$PublicInbox::Hval::FN\z/o) {
$sfn = $fn;
} elsif ($ct eq 'text/plain') {
$sfn = 'a.txt';
@@ -506,74 +548,85 @@ sub attach_link ($$$$;$) {
}
sub add_text_body {
- my ($upfx, $obfs_ibx, $p) = @_;
+ my ($upfx, $ctx, $p) = @_;
+ my $ibx = $ctx->{-inbox};
+ my $obfs_ibx = $ibx->{obfuscate} ? $ibx : undef;
# $p - from msg_iter: [ Email::MIME, depth, @idx ]
- my ($part, $depth) = @$p; # attachment @idx is unused
+ my ($part, $depth, @idx) = @$p;
my $ct = $part->content_type || 'text/plain';
my $fn = $part->filename;
-
- if ($ct =~ m!\btext/x?html\b!i) {
- return attach_link($upfx, $ct, $p, $fn);
- }
-
- my $s = eval { $part->body_str };
-
- # badly-encoded message? tell the world about it!
- my $err = $@;
- if ($err) {
- if ($ct =~ m!\btext/plain\b!i) {
- # Try to assume UTF-8 because Alpine seems to
- # do wacky things and set charset=X-UNKNOWN
- $part->charset_set('UTF-8');
- $s = eval { $part->body_str };
-
- # If forcing charset=UTF-8 failed,
- # attach_link will warn further down...
- $s = $part->body if $@;
- } else {
- return attach_link($upfx, $ct, $p, $fn);
+ my ($s, $err) = msg_part_text($part, $ct);
+
+ return attach_link($upfx, $ct, $p, $fn) unless defined $s;
+
+ # 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;
+
+ # 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
+ $ctx->{-diff} = $diff = [];
+ delete $ctx->{-long_path};
+ my $spfx;
+ if ($ibx->{-repo_objs}) {
+ if (index($upfx, '//') >= 0) { # absolute URL (Atom feeds)
+ $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;
+ };
- my @lines = split(/^/m, $s);
+ # 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 = split(/((?:^>[^\n]*\n)+)/sm, $s);
$s = '';
if (defined($fn) || $depth > 0 || $err) {
+ # badly-encoded message with $err? tell the world about it!
$s .= attach_link($upfx, $ct, $p, $fn, $err);
$s .= "\n";
}
- my @quot;
my $l = PublicInbox::Linkify->new;
- foreach my $cur (@lines) {
- if ($cur !~ /^>/) {
- # show the previously buffered quote inline
- flush_quote(\$s, $l, \@quot) if @quot;
-
- # regular line, OK
+ foreach my $cur (@sections) {
+ if ($cur =~ /\A>/) {
+ flush_quote(\$s, $l, \$cur);
+ } elsif ($diff) {
+ @$diff = split(/^/m, $cur);
+ $cur = undef;
+ flush_diff(\$s, $ctx, $l);
+ } else {
+ # regular lines, OK
$l->linkify_1($cur);
$s .= $l->linkify_2(ascii_html($cur));
- } else {
- push @quot, $cur;
+ $cur = undef;
}
}
- if (@quot) { # ugh, top posted
- flush_quote(\$s, $l, \@quot);
- obfuscate_addrs($obfs_ibx, $s) if $obfs_ibx;
- $s;
- } else {
- obfuscate_addrs($obfs_ibx, $s) if $obfs_ibx;
- if ($s =~ /\n\z/s) { # common, last line ends with a newline
- $s;
- } else { # some editors don't do newlines...
- $s .= "\n";
- }
- }
+ obfuscate_addrs($obfs_ibx, $s) if $obfs_ibx;
+ $s;
}
sub _msg_html_prepare {
my ($hdr, $ctx, $more, $nr) = @_;
- my $srch = $ctx->{srch} if $ctx;
my $atom = '';
+ my $over = $ctx->{-inbox}->over;
my $obfs_ibx = $ctx->{-obfs_ibx};
my $rv = '';
my $mids = mids($hdr);
@@ -587,33 +640,47 @@ sub _msg_html_prepare {
} else {
$rv .= '';
}
- if ($srch) {
+ if ($over) {
$ctx->{-upfx} = '../';
}
my @title;
- foreach my $h (qw(From To Cc Subject Date)) {
- my $v = $hdr->header($h);
- defined($v) && ($v ne '') or next;
+ my $v;
+ if (defined($v = $hdr->header('From'))) {
$v = PublicInbox::Hval->new($v);
-
- if ($h eq 'From') {
- my @n = PublicInbox::Address::names($v->raw);
- $title[1] = ascii_html(join(', ', @n));
- obfuscate_addrs($obfs_ibx, $title[1]) if $obfs_ibx;
- } elsif ($h eq 'Subject') {
- $title[0] = $v->as_html;
- if ($srch) {
- $rv .= qq($h: );
- $rv .= $v->as_html . "\n";
- next;
- }
- }
+ my @n = PublicInbox::Address::names($v->raw);
+ $title[1] = ascii_html(join(', ', @n));
$v = $v->as_html;
+ if ($obfs_ibx) {
+ obfuscate_addrs($obfs_ibx, $v);
+ obfuscate_addrs($obfs_ibx, $title[1]);
+ }
+ $rv .= "From: $v\n" if $v ne '';
+ }
+ foreach my $h (qw(To Cc)) {
+ defined($v = $hdr->header($h)) or next;
+ fold_addresses($v);
+ $v = ascii_html($v);
obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx;
- $rv .= "$h: $v\n";
-
+ $rv .= "$h: $v\n" if $v ne '';
+ }
+ if (defined($v = $hdr->header('Subject')) && ($v ne '')) {
+ $v = ascii_html($v);
+ obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx;
+ if ($over) {
+ $rv .= qq(Subject: $v\n);
+ } else {
+ $rv .= "Subject: $v\n";
+ }
+ $title[0] = $v;
+ } else { # dummy anchor for thread skeleton at bottom of page
+ $rv .= qq() if $over;
+ $title[0] = '(no subject)';
+ }
+ if (defined($v = $hdr->header('Date'))) {
+ $v = ascii_html($v);
+ obfuscate_addrs($obfs_ibx, $v) if $obfs_ibx; # possible :P
+ $rv .= "Date: $v\n";
}
- $title[0] ||= '(no subject)';
$ctx->{-title_html} = join(' - ', @title);
foreach (@$mids) {
my $mid = PublicInbox::Hval->new_msgid($_) ;
@@ -629,15 +696,15 @@ sub _msg_html_prepare {
$rv .= "(raw)\n";
}
}
- $rv .= _parent_headers($hdr, $srch);
+ $rv .= _parent_headers($hdr, $over);
$rv .= "\n";
}
sub thread_skel {
my ($dst, $ctx, $hdr, $tpfx) = @_;
- my $srch = $ctx->{srch};
my $mid = mids($hdr)->[0];
- my ($nr, $msgs) = $srch->get_thread($mid);
+ my $ibx = $ctx->{-inbox};
+ my ($nr, $msgs) = $ibx->over->get_thread($mid);
my $expand = qq(expand[flat) .
qq(|nested] ) .
qq(mbox.gz ) .
@@ -662,14 +729,14 @@ sub thread_skel {
my $subj = $hdr->header('Subject');
defined $subj or $subj = '';
- $ctx->{prev_subj} = [ split(/ /, $srch->subject_normalized($subj)) ];
+ $subj = '(no subject)' if $subj eq '';
+ $ctx->{prev_subj} = [ split(/ /, subject_normalized($subj)) ];
$ctx->{cur} = $mid;
$ctx->{prev_attr} = '';
$ctx->{prev_level} = 0;
$ctx->{dst} = $dst;
# reduce hash lookups in skel_dump
- my $ibx = $ctx->{-inbox};
$ctx->{-obfs_ibx} = $ibx->{obfuscate} ? $ibx : undef;
walk_thread(thread_results($ctx, $msgs), $ctx, *skel_dump);
@@ -677,10 +744,11 @@ sub thread_skel {
}
sub _parent_headers {
- my ($hdr, $srch) = @_;
+ my ($hdr, $over) = @_;
my $rv = '';
- my $irt = in_reply_to($hdr);
+ my $refs = references($hdr);
+ my $irt = pop @$refs;
if (defined $irt) {
my $v = PublicInbox::Hval->new_msgid($irt);
my $html = $v->as_html;
@@ -691,24 +759,11 @@ sub _parent_headers {
# do not display References: if search is present,
# we show the thread skeleton at the bottom, instead.
- return $rv if $srch;
-
- my $refs = $hdr->header_raw('References');
- if ($refs) {
- # avoid redundant URLs wasting bandwidth
- my %seen;
- $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_nosrch($ref);
- }
+ return $rv if $over;
- if (@refs) {
- $rv .= 'References: '. join("\n\t", @refs) . "\n";
- }
+ if (@$refs) {
+ @$refs = map { linkify_ref_no_over($_) } @$refs;
+ $rv .= 'References: '. join("\n\t", @$refs) . "\n";
}
$rv;
}
@@ -716,12 +771,12 @@ sub _parent_headers {
sub html_footer {
my ($hdr, $standalone, $ctx, $rhref) = @_;
- my $srch = $ctx->{srch} if $ctx;
+ my $ibx = $ctx->{-inbox} if $ctx;
my $upfx = '../';
my $tpfx = '';
my $idx = $standalone ? " index" : '';
my $irt = '';
- if ($idx && $srch) {
+ if ($idx && $ibx->over) {
$idx .= "\n";
thread_skel(\$idx, $ctx, $hdr, $tpfx);
my ($next, $prev);
@@ -761,7 +816,7 @@ sub html_footer {
$irt .= $idx;
}
-sub linkify_ref_nosrch {
+sub linkify_ref_no_over {
my $v = PublicInbox::Hval->new_msgid($_[0]);
my $html = $v->as_html;
my $href = $v->{href};
@@ -787,10 +842,56 @@ sub indent_for {
$level ? INDENT x ($level - 1) : '';
}
+sub find_mid_root {
+ my ($ctx, $level, $node, $idx) = @_;
+ ++$ctx->{root_idx} if $level == 0;
+ if ($node->{id} eq $ctx->{mid}) {
+ $ctx->{found_mid_at} = $ctx->{root_idx};
+ return 0;
+ }
+ 1;
+}
+
+sub strict_loose_note ($) {
+ my ($nr) = @_;
+ my $msg =
+" -- strict thread matches above, loose matches on Subject: below --\n";
+
+ if ($nr > PublicInbox::Over::DEFAULT_LIMIT()) {
+ $msg .=
+" -- use mbox.gz link to download all $nr messages --\n";
+ }
+ $msg;
+}
+
sub thread_results {
my ($ctx, $msgs) = @_;
require PublicInbox::SearchThread;
- PublicInbox::SearchThread::thread($msgs, *sort_ds, $ctx->{-inbox});
+ my $ibx = $ctx->{-inbox};
+ my $rootset = PublicInbox::SearchThread::thread($msgs, *sort_ds, $ibx);
+
+ # FIXME: `tid' is broken on --reindex, so that needs to be fixed
+ # and preserved in the future. This bug is hidden by `sid' matches
+ # in get_thread, so we never noticed it until now. And even when
+ # reindexing is fixed, we'll keep this code until a SCHEMA_VERSION
+ # bump since reindexing is expensive and users may not do it
+
+ # loose threading could've returned too many results,
+ # put the root the message we care about at the top:
+ my $mid = $ctx->{mid};
+ if (defined($mid) && scalar(@$rootset) > 1) {
+ $ctx->{root_idx} = -1;
+ my $nr = scalar @$msgs;
+ walk_thread($rootset, $ctx, *find_mid_root);
+ my $idx = $ctx->{found_mid_at};
+ if (defined($idx) && $idx != 0) {
+ my $tip = splice(@$rootset, $idx, 1);
+ @$rootset = reverse @$rootset;
+ unshift @$rootset, $tip;
+ $ctx->{sl_note} = strict_loose_note($nr);
+ }
+ }
+ $rootset
}
sub missing_thread {
@@ -799,11 +900,6 @@ sub missing_thread {
PublicInbox::ExtMsg::ext_msg($ctx);
}
-sub _msg_date {
- my ($hdr) = @_;
- fmt_ts(msg_datestamp($hdr));
-}
-
sub fmt_ts { POSIX::strftime('%Y-%m-%d %k:%M', gmtime($_[0])) }
sub dedupe_subject {
@@ -833,6 +929,10 @@ sub skel_dump {
my $cur = $ctx->{cur};
my $mid = $smsg->{mid};
+ if ($level == 0 && $ctx->{skel_dump_roots}++) {
+ $$dst .= delete $ctx->{sl_note} || '';
+ }
+
my $f = ascii_html($smsg->from_name);
my $obfs_ibx = $ctx->{-obfs_ibx};
obfuscate_addrs($obfs_ibx, $f) if $obfs_ibx;
@@ -851,7 +951,7 @@ sub skel_dump {
delete $ctx->{cur};
$$dst .= "$d".
"$attr [this message]\n";
- return;
+ return 1;
} else {
$ctx->{prev_msg} = $mid;
}
@@ -862,7 +962,7 @@ sub skel_dump {
# Subject is never undef, this mail was loaded from
# our Xapian which would've resulted in '' if it were
# really missing (and Filter rejects empty subjects)
- my @subj = split(/ /, $ctx->{srch}->subject_normalized($smsg->subject));
+ my @subj = split(/ /, subject_normalized($smsg->subject));
# remove common suffixes from the subject if it matches the previous,
# so we do not show redundant text at the end.
@@ -891,6 +991,7 @@ sub skel_dump {
$m = $ctx->{-upfx}.mid_escape($mid).'/';
}
$$dst .= $d . "" . $end;
+ 1;
}
sub _skel_ghost {
@@ -916,6 +1017,7 @@ sub _skel_ghost {
}
my $dst = $ctx->{dst};
$$dst .= $d;
+ 1;
}
sub sort_ds {
@@ -929,20 +1031,20 @@ sub sort_ds {
# returns 200 if done, 404 if not
sub acc_topic {
my ($ctx, $level, $node) = @_;
- my $srch = $ctx->{srch};
my $mid = $node->{id};
my $x = $node->{smsg} || $ctx->{-inbox}->smsg_by_mid($mid);
my ($subj, $ds);
my $topic;
if ($x) {
$subj = $x->subject;
- $subj = $srch->subject_normalized($subj);
+ $subj = subject_normalized($subj);
+ $subj = '(no subject)' if $subj eq '';
$ds = $x->ds;
if ($level == 0) {
$topic = [ $ds, 1, { $subj => $mid }, $subj ];
$ctx->{-cur_topic} = $topic;
push @{$ctx->{order}}, $topic;
- return;
+ return 1;
}
$topic = $ctx->{-cur_topic}; # should never be undef
@@ -956,11 +1058,12 @@ sub acc_topic {
}
$seen->{$subj} = $mid; # latest for subject
} else { # ghost message
- return if $level != 0; # ignore child ghosts
+ return 1 if $level != 0; # ignore child ghosts
$topic = [ -666, 0, {} ];
$ctx->{-cur_topic} = $topic;
push @{$ctx->{order}}, $topic;
}
+ 1;
}
sub dump_topics {
@@ -974,7 +1077,6 @@ sub dump_topics {
my @out;
my $ibx = $ctx->{-inbox};
my $obfs_ibx = $ibx->{obfuscate} ? $ibx : undef;
- my $srch = $ctx->{srch};
# sort by recency, this allows new posts to "bump" old topics...
foreach my $topic (sort { $b->[0] <=> $a->[0] } @$order) {
@@ -1000,13 +1102,13 @@ sub dump_topics {
my $mbox = qq(mbox.gz);
my $atom = qq(Atom);
- my $s = "$top\n" .
+ my $s = "$top\n" .
" $ds UTC $n - $mbox / $atom\n";
for (my $i = 0; $i < scalar(@ex); $i += 2) {
my $level = $ex[$i];
my $subj = $ex[$i + 1];
$mid = delete $seen->{$subj};
- my @subj = split(/ /, $srch->subject_normalized($subj));
+ my @subj = split(/ /, subject_normalized($subj));
my @next_prev = @subj; # full copy
my $omit = dedupe_subject($prev_subj, \@subj, ' "');
$prev_subj = \@next_prev;
@@ -1058,8 +1160,8 @@ sub paginate_recent ($$) {
# Xapian uses '..' but '-' is perhaps friendier to URL linkifiers
# if only $after exists "YYYYMMDD.." because "." could be skipped
# if interpreted as an end-of-sentence
- $t =~ s/\A(\d{8,14})-// and $after = str2ts($1);
- $t =~ /\A(\d{8,14})\z/ and $before = str2ts($1);
+ $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->{-inbox};
my $msgs = $ibx->recent($opts, $after, $before);