From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-ASN: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id 6690D1F46C for ; Fri, 29 Nov 2019 12:25:09 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Subject: [PATCH 3/4] msgtime: drop Date::Parse for RFC2822 Date: Fri, 29 Nov 2019 12:25:07 +0000 Message-Id: <20191129122508.7708-4-e@80x24.org> In-Reply-To: <20191129122508.7708-1-e@80x24.org> References: <20191129122508.7708-1-e@80x24.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: Date::Parse is not optimized for RFC2822 dates and isn't packaged on OpenBSD. It's still useful for historical email when email clients were less conformant, but is less relevant for new emails. --- lib/PublicInbox/MsgTime.pm | 118 ++++++++++++++++++++++++++++++++----- t/msgtime.t | 7 +++ 2 files changed, 109 insertions(+), 16 deletions(-) diff --git a/lib/PublicInbox/MsgTime.pm b/lib/PublicInbox/MsgTime.pm index 7dec48ce..479aaa4e 100644 --- a/lib/PublicInbox/MsgTime.pm +++ b/lib/PublicInbox/MsgTime.pm @@ -7,28 +7,117 @@ use strict; use warnings; use base qw(Exporter); our @EXPORT_OK = qw(msg_timestamp msg_datestamp); -use Date::Parse qw(str2time strptime); +use Time::Local qw(timegm); +my @MoY = qw(january february march april may june + july august september october november december); +my %MoY; +@MoY{@MoY} = (0..11); +@MoY{map { substr($_, 0, 3) } @MoY} = (0..11); + +my %OBSOLETE_TZ = ( # RFC2822 4.3 (Obsolete Date and Time) + EST => '-0500', EDT => '-0400', + CST => '-0600', CDT => '-0500', + MST => '-0700', MDT => '-0600', + PST => '-0800', PDT => '-0700', + UT => '+0000', GMT => '+0000', Z => '+0000', + + # RFC2822 states: + # The 1 character military time zones were defined in a non-standard + # way in [RFC822] and are therefore unpredictable in their meaning. +); +my $OBSOLETE_TZ = join('|', keys %OBSOLETE_TZ); sub str2date_zone ($) { my ($date) = @_; + my ($ts, $zone); - my $ts = str2time($date); - return undef unless(defined $ts); + # RFC822 is most likely for email, but we can tolerate an extra comma + # or punctuation as long as all the data is there. + # We'll use '\s' since Unicode spaces won't affect our parsing. + # SpamAssassin ignores commas and redundant spaces, too. + if ($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]+)[:\.] # HH: + ((?:[0-9]{2})|(?:\s?[0-9])) # MM + (?:[:\.]((?:[0-9]{2})|(?:\s?[0-9])))? # :SS + \s+ # a TZ offset is required: + ([\+\-])? # TZ sign + [\+\-]* # I've seen extra "-" e.g. "--500" + ([0-9]+|$OBSOLETE_TZ)(?:\s|$) # TZ offset + /xo) { + my ($dd, $m, $yyyy, $hh, $mm, $ss, $sign, $tz) = + ($1, $2, $3, $4, $5, $6, $7, $8); + # don't accept non-English months + defined(my $mon = $MoY{lc($m)}) or return; - # off is the time zone offset in seconds from GMT - my ($ss,$mm,$hh,$day,$month,$year,$off) = strptime($date); - return undef unless(defined $off); + if (defined(my $off = $OBSOLETE_TZ{$tz})) { + $sign = substr($off, 0, 1); + $tz = substr($off, 1); + } - # Compute the time zone from offset - my $sign = ($off < 0) ? '-' : '+'; - my $hour = abs(int($off / 3600)); - my $min = ($off / 60) % 60; + # Y2K problems: 3-digit years, follow RFC2822 + if (length($yyyy) <= 3) { + $yyyy += 1900; - # deal with weird offsets like '-0420' properly - $min = 60 - $min if ($min && $off < 0); + # and 2-digit years from '09 (2009) (0..49) + $yyyy += 100 if $yyyy < 1950; + } - my $zone = sprintf('%s%02d%02d', $sign, $hour, $min); + $ts = timegm($ss // 0, $mm, $hh, $dd, $mon, $yyyy); + + # Compute the time offset from [+-]HHMM + $tz //= 0; + my ($tz_hh, $tz_mm); + if (length($tz) == 1) { + $tz_hh = $tz; + $tz_mm = 0; + } elsif (length($tz) == 2) { + $tz_hh = 0; + $tz_mm = $tz; + } else { + $tz_hh = $tz; + $tz_hh =~ s/([0-9]{2})\z//; + $tz_mm = $1; + } + while ($tz_mm >= 60) { + $tz_mm -= 60; + $tz_hh += 1; + } + $sign //= '+'; + my $off = $sign . ($tz_mm * 60 + ($tz_hh * 60 * 60)); + $ts -= $off; + $sign = '+' if $off == 0; + $zone = sprintf('%s%02d%02d', $sign, $tz_hh, $tz_mm); + + # Time::Zone and Date::Parse are part of the same distibution, + # and we need Time::Zone to deal with tz names like "EDT" + } elsif (eval { require Date::Parse }) { + $ts = Date::Parse::str2time($date); + return undef unless(defined $ts); + + # off is the time zone offset in seconds from GMT + my ($ss,$mm,$hh,$day,$month,$year,$off) = + Date::Parse::strptime($date); + return undef unless(defined $off); + + # Compute the time zone from offset + my $sign = ($off < 0) ? '-' : '+'; + my $hour = abs(int($off / 3600)); + my $min = ($off / 60) % 60; + + # deal with weird offsets like '-0420' properly + $min = 60 - $min if ($min && $off < 0); + + $zone = sprintf('%s%02d%02d', $sign, $hour, $min); + } else { + warn "Date::Parse missing for non-RFC822 date: $date\n"; + return undef; + } + # Note: we've already applied the offset to $ts at this point, + # but we want to keep "git fsck" happy. # "-1200" is the furthest westermost zone offset, # but git fast-import is liberal so we use "-1400" if ($zone >= 1400 || $zone <= -1400) { @@ -63,9 +152,6 @@ sub msg_date_only ($) { my @date = $hdr->header_raw('Date'); my ($ts); foreach my $d (@date) { - # Y2K problems: 3-digit years - $d =~ s!([A-Za-z]{3}) ([0-9]{3}) ([0-9]{2}:[0-9]{2}:[0-9]{2})! - my $yyyy = $2 + 1900; "$1 $yyyy $3"!e; $ts = eval { str2date_zone($d) } and return $ts; if ($@) { my $mid = $hdr->header_raw('Message-ID'); diff --git a/t/msgtime.t b/t/msgtime.t index cecbb921..1452dc97 100644 --- a/t/msgtime.t +++ b/t/msgtime.t @@ -97,4 +97,11 @@ is_datestamp('Wed, 20 Dec 2006 05:32:58 +0420', [1166577178, '+0420']); is_datestamp('Thu, 14 Dec 2006 00:20:24 +0480', [1166036424, '+0520']); is_datestamp('Thu, 14 Dec 2006 00:20:24 -0480', [1166074824, '-0520']); is_datestamp('Mon, 14 Apr 2014 07:59:01 -0007', [1397462761, '-0007']); + +# obsolete formats described in RFC2822 +for (qw(UT GMT Z)) { + is_datestamp('Fri, 02 Oct 1993 00:00:00 '.$_, [ 749520000, '+0000']); +} +is_datestamp('Fri, 02 Oct 1993 00:00:00 EDT', [ 749534400, '-0400']); + done_testing();