searchmsg: remove locale-dependency for ->date

[public-inbox.git] / lib / PublicInbox / SearchMsg.pm

diff --git a/lib/PublicInbox/SearchMsg.pm b/lib/PublicInbox/SearchMsg.pm
index 93be747507bc7c7589afcad39758a3d10dfa7d33..4c65fbe01a20fb15f36d10b3d1b3dd0cc85c6896 100644 (file)
--- a/lib/PublicInbox/SearchMsg.pm
+++ b/lib/PublicInbox/SearchMsg.pm
@@ -1,5 +1,5 @@
-# Copyright (C) 2015 all contributors <meta@public-inbox.org>
-# License: GPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2015-2016 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 # based on notmuch, but with no concept of folders, files or flags
 #
 # Wraps a document inside our Xapian search index.
@@ -7,16 +7,10 @@ package PublicInbox::SearchMsg;
 use strict;
 use warnings;
 use Search::Xapian;
-use Email::Address qw//;
-use Email::Simple qw//;
-use POSIX qw//;
 use Date::Parse qw/str2time/;
 use PublicInbox::MID qw/mid_clean/;
-use Encode qw/find_encoding/;
-my $enc_utf8 = find_encoding('UTF-8');
+use PublicInbox::Address;
 our $PFX2TERM_RE = undef;
-use constant EPOCH_822 => 'Thu, 01 Jan 1970 00:00:00 +0000';
-use POSIX qw(strftime);
 
 sub new {
        my ($class, $mime) = @_;
@@ -38,10 +32,10 @@ sub get_val ($$) {
 
 sub load_doc {
        my ($class, $doc) = @_;
-       my $data = $doc->get_data;
+       my $data = $doc->get_data or return;
        my $ts = get_val($doc, &PublicInbox::Search::TS);
-       $data = $enc_utf8->decode($data);
-       my ($subj, $from, $refs, $to, $cc) = split(/\n/, $data);
+       utf8::decode($data);
+       my ($subj, $from, $refs, $to, $cc, $blob) = split(/\n/, $data);
        bless {
                doc => $doc,
                subject => $subj,
@@ -50,6 +44,7 @@ sub load_doc {
                references => $refs,
                to => $to,
                cc => $cc,
+               blob => $blob,
        }, $class;
 }
 
@@ -66,7 +61,8 @@ sub __hdr ($$) {
        my $mime = $self->{mime} or return;
        $val = $mime->header($field);
        $val = '' unless defined $val;
-       $val =~ tr/\t\r\n/ /;
+       $val =~ tr/\n/ /;
+       $val =~ tr/\r//d;
        $self->{$field} = $val;
 }
 
@@ -74,22 +70,29 @@ sub subject ($) { __hdr($_[0], 'subject') }
 sub to ($) { __hdr($_[0], 'to') }
 sub cc ($) { __hdr($_[0], 'cc') }
 
+# no strftime, that is locale-dependent
+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 ($) {
        my ($self) = @_;
        my $date = __hdr($self, 'date');
        return $date if defined $date;
        my $ts = $self->{ts};
        return unless defined $ts;
-       $self->{date} = strftime('%a, %d %b %Y %T %z', gmtime($ts));
+       my ($sec, $min, $hour, $mday, $mon, $year, $wday) = gmtime($ts);
+       $self->{date} = "$DoW[$wday], ".
+                       sprintf("%02d $MoY[$mon] %04d %02d:%02d:%02d +0000",
+                               $mday, $year+1900, $hour, $min, $sec);
+
 }
 
 sub from ($) {
        my ($self) = @_;
        my $from = __hdr($self, 'from');
        if (defined $from && !defined $self->{from_name}) {
-               $from =~ tr/\t\r\n/ /;
-               my @from = Email::Address->parse($from);
-               $self->{from_name} = $from[0]->name;
+               my @n = PublicInbox::Address::names($from);
+               $self->{from_name} = join(', ', @n);
        }
        $from;
 }
@@ -108,9 +111,11 @@ sub ts {
 }
 
 sub to_doc_data {
-       my ($self) = @_;
-       join("\n", $self->subject, $self->from, $self->references,
-               $self->to, $self->cc);
+       my ($self, $blob) = @_;
+       my @rows = ($self->subject, $self->from, $self->references,
+                       $self->to, $self->cc);
+       push @rows, $blob if defined $blob;
+       join("\n", @rows);
 }
 
 sub references {
@@ -144,38 +149,6 @@ sub ensure_metadata {
        }
 }
 
-# for threading only
-sub mini_mime {
-       my ($self) = @_;
-       $self->ensure_metadata;
-       my @hs = (
-               'Subject' => $self->subject,
-               'X-PI-From' => $self->from_name,
-       );
-
-       my @h = (
-               # prevent Email::Simple::Creator from running,
-               # this header is useless for threading as we use X-PI-TS
-               # for sorting and display:
-               'Date' => EPOCH_822,
-               'Message-ID' => "<$self->{mid}>",
-               'X-PI-TS' => $self->ts,
-       );
-       if (my $refs = $self->{references}) {
-               push @h, References => $refs;
-       }
-       my $mime = Email::MIME->create(header_str => \@hs, header => \@h);
-       my $h = $mime->header_obj;
-
-       # set these headers manually since Encode::encode('MIME-Q', ...)
-       # will add spaces to long values when using header_str above.
-
-       # drop useless headers Email::MIME set for us
-       $h->header_set('Date');
-       $h->header_set('MIME-Version');
-       $mime;
-}
-
 sub mid ($;$) {
        my ($self, $mid) = @_;
 
@@ -189,11 +162,15 @@ sub mid ($;$) {
        }
 }
 
-sub _extract_mid {
-       my ($self) = @_;
+sub _extract_mid { mid_clean(mid_mime($_[0]->mime)) }
 
-       my $mid = $self->mime->header('Message-ID');
-       defined $mid ? mid_clean($mid) : $mid;
+sub blob {
+       my ($self, $x40) = @_;
+       if (defined $x40) {
+               $self->{blob} = $x40;
+       } else {
+               $self->{blob};
+       }
 }
 
 sub mime {