msgtime: assume +0000 if TZ missing when using Date::Parse

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

diff --git a/lib/PublicInbox/MsgTime.pm b/lib/PublicInbox/MsgTime.pm
index 479aaa4ecf132f5176d49ce54db6171769872666..8703d7bc0a78293dbe4735e34c5a339ad8cffb6c 100644 (file)
--- a/lib/PublicInbox/MsgTime.pm
+++ b/lib/PublicInbox/MsgTime.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2018-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # Various date/time-related functions
@@ -38,7 +38,7 @@ sub str2date_zone ($) {
        if ($date =~ /(?:[A-Za-z]+,?\s+)? # day-of-week
                        ([0-9]+),?\s+  # dd
                        ([A-Za-z]+)\s+ # mon
-                       ([0-9]{2,})\s+ # YYYY or YY (or YYY :P)
+                       ([0-9]{2,4})\s+ # YYYY or YY (or YYY :P)
                        ([0-9]+)[:\.] # HH:
                                ((?:[0-9]{2})|(?:\s?[0-9])) # MM
                                (?:[:\.]((?:[0-9]{2})|(?:\s?[0-9])))? # :SS
@@ -67,6 +67,10 @@ sub str2date_zone ($) {
 
                $ts = timegm($ss // 0, $mm, $hh, $dd, $mon, $yyyy);
 
+               # 4-digit dates in non-spam from 1900s and 1910s exist in
+               # lore archives
+               return if $ts < 0;
+
                # Compute the time offset from [+-]HHMM
                $tz //= 0;
                my ($tz_hh, $tz_mm);
@@ -100,7 +104,8 @@ sub str2date_zone ($) {
                # off is the time zone offset in seconds from GMT
                my ($ss,$mm,$hh,$day,$month,$year,$off) =
                                        Date::Parse::strptime($date);
-               return undef unless(defined $off);
+               return unless defined($year);
+               $off //= 0;
 
                # Compute the time zone from offset
                my $sign = ($off < 0) ? '-' : '+';