1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
|
# Copyright (C) 2015-2021 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
#
# A small/skeleton/slim representation of a message.
# This used to be "SearchMsg", but we split out overview
# indexing into over.sqlite3 so it's not just "search". There
# may be many of these objects loaded in memory at once for
# large threads in our WWW UI and the NNTP range responses.
package PublicInbox::Smsg;
use strict;
use v5.10.1;
use parent qw(Exporter);
our @EXPORT_OK = qw(subject_normalized);
use PublicInbox::MID qw(mids references);
use PublicInbox::Address;
use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
sub oidbin { pack('H*', $_[0]->{blob}) }
sub to_doc_data {
my ($self) = @_;
join("\n",
$self->{subject},
$self->{from},
$self->{references} // '',
$self->{to},
$self->{cc},
$self->{blob},
$self->{mid},
$self->{bytes} // '',
$self->{lines} // ''
);
}
sub load_from_data ($$) {
my ($self) = $_[0]; # data = $_[1]
utf8::decode($_[1]);
(
$self->{subject},
$self->{from},
$self->{references},
# To: and Cc: are stored to optimize HDR/XHDR in NNTP since
# some NNTP clients will use that for message displays.
# NNTP only, and only stored in Over(view), not Xapian
$self->{to},
$self->{cc},
$self->{blob},
$self->{mid},
# NNTP only
$self->{bytes},
$self->{lines}
) = split(/\n/, $_[1]);
}
sub psgi_cull ($) {
my ($self) = @_;
# drop NNTP-only fields which aren't relevant to PSGI results:
# saves ~80K on a 200 item search result:
# TODO: we may need to keep some of these for JMAP...
my ($f) = delete @$self{qw(from tid to cc bytes lines)};
# ghosts don't have ->{from}
$self->{from_name} = join(', ', PublicInbox::Address::names($f // ''));
$self;
}
sub parse_references ($$$) {
my ($smsg, $hdr, $mids) = @_;
my $refs = references($hdr);
push(@$refs, @$mids) if scalar(@$mids) > 1;
return $refs if scalar(@$refs) == 0;
# prevent circular references here:
my %seen = ( ($smsg->{mid} // '') => 1 );
my @keep;
foreach my $ref (@$refs) {
if (length($ref) > PublicInbox::MID::MAX_MID_SIZE) {
warn "References: <$ref> too long, ignoring\n";
next;
}
$seen{$ref} //= push(@keep, $ref);
}
$smsg->{references} = '<'.join('> <', @keep).'>' if @keep;
\@keep;
}
# used for v2, Import and v1 non-SQLite WWW code paths
sub populate {
my ($self, $hdr, $sync) = @_;
for my $f (qw(From To Cc Subject)) {
my @all = $hdr->header($f);
my $val = join(', ', @all);
$val =~ tr/\r//d;
# MIME decoding can create NULs, replace them with spaces
# to protect git and NNTP clients
$val =~ tr/\0\t\n/ /;
# rare: in case headers have wide chars (not RFC2047-encoded)
utf8::decode($val);
# lower-case fields for read-only stuff
$self->{lc($f)} = $val;
# Capitalized From/Subject for git-fast-import
next if $f eq 'To' || $f eq 'Cc';
if (scalar(@all) > 1) {
$val = $all[0];
$val =~ tr/\r//d;
$val =~ tr/\0\t\n/ /;
}
$self->{$f} = $val if $val ne '';
}
$sync //= {};
my @ds = msg_datestamp($hdr, $sync->{autime} // $self->{ds});
my @ts = msg_timestamp($hdr, $sync->{cotime} // $self->{ts});
$self->{-ds} = \@ds;
$self->{-ts} = \@ts;
$self->{ds} //= $ds[0]; # no zone
$self->{ts} //= $ts[0];
$self->{mid} //= mids($hdr)->[0];
}
# no strftime, that is locale-dependent and not for RFC822
my @DoW = qw(Sun Mon Tue Wed Thu Fri Sat);
my @MoY = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
sub date ($) { # for NNTP
my ($self) = @_;
my $ds = $self->{ds};
return unless defined $ds;
my ($sec, $min, $hour, $mday, $mon, $year, $wday) = gmtime($ds);
"$DoW[$wday], " . sprintf("%02d $MoY[$mon] %04d %02d:%02d:%02d +0000",
$mday, $year+1900, $hour, $min, $sec);
}
sub internaldate { # for IMAP
my ($self) = @_;
my ($sec, $min, $hour, $mday, $mon, $year) = gmtime($self->{ts} // 0);
sprintf("%02d-$MoY[$mon]-%04d %02d:%02d:%02d +0000",
$mday, $year+1900, $hour, $min, $sec);
}
our $REPLY_RE = qr/^re:\s+/i;
# TODO: see RFC 5256 sec 2.1 "Base Subject" and evaluate compatibility
# w/ existing indices...
sub subject_normalized ($) {
my ($subj) = @_;
$subj =~ s/\A\s+//s; # no leading space
$subj =~ s/\s+\z//s; # no trailing space
$subj =~ s/\s+/ /gs; # no redundant spaces
$subj =~ s/\.+\z//; # no trailing '.'
$subj =~ s/$REPLY_RE//igo; # remove reply prefix
$subj;
}
# returns the number of bytes to add if given a non-CRLF arg
sub crlf_adjust ($) {
if (index($_[0], "\r\n") < 0) {
# common case is LF-only, every \n needs an \r;
# so favor a cheap tr// over an expensive m//g
$_[0] =~ tr/\n/\n/;
} else { # count number of '\n' w/o '\r', expensive:
scalar(my @n = ($_[0] =~ m/(?<!\r)\n/g));
}
}
sub set_bytes { $_[0]->{bytes} = $_[2] + crlf_adjust($_[1]) }
1;
|
