use PublicInbox::MID qw(mid_mime mid2path);
use PublicInbox::Address;
use PublicInbox::ContentId qw(content_id);
+use Date::Parse qw(str2time);
+use Time::Zone qw(tz_offset);
sub new {
my ($class, $git, $name, $email, $ibx) = @_;
inbox => $ibx,
path_type => '2/38', # or 'v2'
ssoma_lock => 1, # disable for v2
+ bytes_added => 0,
}, $class
}
chomp($self->{tip} = $git->qx(qw(rev-parse --revs-only), $self->{ref}));
my @cmd = ('git', "--git-dir=$git_dir", qw(fast-import
- --quiet --done --date-format=rfc2822));
+ --quiet --done --date-format=raw));
my $rdr = { 0 => fileno($out_r), 1 => fileno($in_w) };
my $pid = spawn(\@cmd, undef, $rdr);
die "spawn fast-import failed: $!" unless defined $pid;
sub wfail () { die "write to fast-import failed: $!" }
-sub now2822 () {
- my @t = gmtime(time);
- my $day = qw(Sun Mon Tue Wed Thu Fri Sat)[$t[6]];
- my $mon = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec)[$t[4]];
-
- sprintf('%s, %2d %s %d %02d:%02d:%02d +0000',
- $day, $t[3], $mon, $t[5] + 1900, $t[2], $t[1], $t[0]);
-}
+sub now_raw () { time . ' +0000' }
sub norm_body ($) {
my ($mime) = @_;
(undef, $cur);
}
+# used for v2 (maybe)
+sub checkpoint {
+ my ($self) = @_;
+ return unless $self->{pid};
+ print { $self->{out} } "checkpoint\n" or wfail;
+ undef;
+}
+
+# used for v2
+sub get_mark {
+ my ($self, $mark) = @_;
+ die "not active\n" unless $self->{pid};
+ my ($r, $w) = $self->gfi_start;
+ print $w "get-mark $mark\n" or wfail;
+ defined(my $oid = <$r>) or die "get-mark failed, need git 2.6.0+\n";
+ $oid;
+}
+
# returns undef on non-existent
-# ('MISMATCH', msg) on mismatch
-# (:MARK, msg) on success
+# ('MISMATCH', Email::MIME) on mismatch
+# (:MARK, Email::MIME) on success
#
# For v2 inboxes, the content_id is returned instead of the msg
# v2 callers should check with Xapian before calling this as
print $w "reset $ref\n" or wfail;
}
my $ident = $self->{ident};
- my $now = now2822();
+ my $now = now_raw();
$msg ||= 'rm';
my $len = length($msg) + 1;
print $w "commit $ref\nmark :$commit\n",
(($self->{tip} = ":$commit"), $cur);
}
+sub parse_date ($) {
+ my ($mime) = @_;
+ my $hdr = $mime->header_obj;
+ my $date = $hdr->header_raw('Date');
+ my ($ts, $zone);
+ my $mid = $hdr->header_raw('Message-ID');
+ if ($date) {
+ $ts = eval { str2time($date) };
+ if ($@) {
+ warn "bad Date: $date in $mid: $@\n";
+ } elsif ($date =~ /\s+([\+\-]\d+)\s*\z/) {
+ $zone = $1;
+ }
+ }
+ unless ($ts) {
+ my @recvd = $hdr->header_raw('Received');
+ foreach my $r (@recvd) {
+ $zone = undef;
+ $r =~ /\s*(\d+\s+[[:alpha:]]+\s+\d{2,4}\s+
+ \d+\D\d+(?:\D\d+)\s+([\+\-]\d+))/osx or next;
+ $zone = $2;
+ $ts = eval { str2time($1) } and last;
+ warn "no date in Received: $r\n";
+ }
+ }
+ $zone ||= '+0000';
+ # "-1200" is the furthest westermost zone offset,
+ # but git fast-import is liberal so we use "-1400"
+ if ($zone >= 1400 || $zone <= -1400) {
+ warn "bogus TZ offset: $zone, ignoring and assuming +0000\n";
+ $zone = '+0000';
+ }
+ $ts = time unless defined $ts;
+ $ts = 0 if $ts < 0; # git uses unsigned times
+ "$ts $zone";
+}
+
# returns undef on duplicate
+# returns the :MARK of the most recent commit
sub add {
my ($self, $mime, $check_cb) = @_; # mime = Email::MIME
my $from = $mime->header('From');
my ($email) = PublicInbox::Address::emails($from);
my ($name) = PublicInbox::Address::names($from);
- # git gets confused with:
- # "'A U Thor <u@example.com>' via foo" <foo@example.com>
- # ref:
- # <CAD0k6qSUYANxbjjbE4jTW4EeVwOYgBD=bXkSu=akiYC_CB7Ffw@mail.gmail.com>
- $name =~ tr/<>//d;
- my $date = $mime->header('Date');
+ my $date_raw = parse_date($mime);
my $subject = $mime->header('Subject');
$subject = '(no subject)' unless defined $subject;
my $path_type = $self->{path_type};
$mime = $check_cb->($mime) or return;
}
- $mime = $mime->as_string;
my $blob = $self->{mark}++;
- print $w "blob\nmark :$blob\ndata ", length($mime), "\n" or wfail;
- print $w $mime, "\n" or wfail;
+ my $str = $mime->as_string;
+ my $n = length($str);
+ $self->{bytes_added} += $n;
+ print $w "blob\nmark :$blob\ndata ", $n, "\n" or wfail;
+ print $w $str, "\n" or wfail;
+ $str = undef;
# v2: we need this for Xapian
if ($self->{want_object_id}) {
- print $w "get-mark :$blob\n" or wfail;
- defined(my $object_id = <$r>) or
- die "get-mark failed, need git 2.6.0+\n";
- chomp($self->{last_object_id} = $object_id);
+ chomp($self->{last_object_id} = $self->get_mark(":$blob"));
+ $self->{last_object_size} = $n;
}
my $ref = $self->{ref};
print $w "reset $ref\n" or wfail;
}
- utf8::encode($email);
- utf8::encode($name);
+ # quiet down wide character warnings with utf8::encode
+ if (defined $email) {
+ utf8::encode($email);
+ } else {
+ $email = '';
+ warn "no email in From: $from\n";
+ }
+
+ # git gets confused with:
+ # "'A U Thor <u@example.com>' via foo" <foo@example.com>
+ # ref:
+ # <CAD0k6qSUYANxbjjbE4jTW4EeVwOYgBD=bXkSu=akiYC_CB7Ffw@mail.gmail.com>
+ if (defined $name) {
+ $name =~ tr/<>//d;
+ utf8::encode($name);
+ } else {
+ $name = '';
+ warn "no name in From: $from\n";
+ }
utf8::encode($subject);
- # quiet down wide character warnings:
print $w "commit $ref\nmark :$commit\n",
- "author $name <$email> $date\n",
- "committer $self->{ident} ", now2822(), "\n" or wfail;
+ "author $name <$email> $date_raw\n",
+ "committer $self->{ident} ", now_raw(), "\n" or wfail;
print $w "data ", (length($subject) + 1), "\n",
$subject, "\n\n" or wfail;
if ($tip ne '') {
$self->{tip} = ":$commit";
}
-sub run_die ($$) {
+sub run_die ($;$) {
my ($cmd, $env) = @_;
my $pid = spawn($cmd, $env, undef);
defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!";
}
if ($nchg) {
run_die([@cmd, 'update-server-info'], undef);
- eval {
+ ($self->{path_type} eq '2/38') and eval {
require PublicInbox::SearchIdx;
my $inbox = $self->{inbox} || $git_dir;
my $s = PublicInbox::SearchIdx->new($inbox);