import: fall back to Sender for extracting name and email

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

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 1a2698a75d609aea4162075e312a791f1c9041c0..664bec6910e5f4d70c6c10e21a1ff2de2da6bd09 100644 (file)
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -12,8 +12,7 @@ use PublicInbox::Spawn qw(spawn);
 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);
+use PublicInbox::MsgTime qw(msg_timestamp);
 
 sub new {
        my ($class, $git, $name, $email, $ibx) = @_;
@@ -204,39 +203,47 @@ sub remove {
 
 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 = $1;
+       my ($ts, $zone) = msg_timestamp($mime->header_obj);
+       $ts = 0 if $ts < 0; # git uses unsigned times
+       "$ts $zone";
+}
+
+sub extract_author_info ($) {
+       my ($mime) = @_;
+
+       my $sender = '';
+       my $from = $mime->header('From');
+       my ($email) = PublicInbox::Address::emails($from);
+       my ($name) = PublicInbox::Address::names($from);
+       if (!defined($name) || !defined($email)) {
+               $sender = $mime->header('Sender');
+               if (!defined($name)) {
+                       ($name) = PublicInbox::Address::names($sender);
                }
-       }
-       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: $r\n";
+               if (!defined($email)) {
+                       ($email) = PublicInbox::Address::emails($sender);
                }
        }
-       $zone ||= '+0000';
-       # "-1200" is the furthest westermost zone offset,
-       # but git fast-import is liberal so we use "-1400"
-       if ($zone >= 1400 || $zone <= -1400) {
-               warn "bogus TZ offset: $zone, ignoring and assuming +0000\n";
-               $zone = '+0000';
+       if (defined $email) {
+               # quiet down wide character warnings with utf8::encode
+               utf8::encode($email);
+       } else {
+               $email = '';
+               warn "no email in From: $from or Sender: $sender\n";
        }
-       $ts = time unless defined $ts;
-       $ts = 0 if $ts < 0; # git uses unsigned times
-       "$ts $zone";
+
+       # 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 or Sender: $sender\n";
+       }
+       ($name, $email);
 }
 
 # returns undef on duplicate
@@ -244,10 +251,7 @@ sub parse_date ($) {
 sub add {
        my ($self, $mime, $check_cb) = @_; # mime = Email::MIME
 
-       my $from = $mime->header('From');
-       my ($email) = PublicInbox::Address::emails($from);
-       my ($name) = PublicInbox::Address::names($from);
-
+       my ($name, $email) = extract_author_info($mime);
        my $date_raw = parse_date($mime);
        my $subject = $mime->header('Subject');
        $subject = '(no subject)' unless defined $subject;
@@ -280,14 +284,12 @@ sub add {
        $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 ($self->{want_object_id}) {
-               chomp($self->{last_object_id} = $self->get_mark(":$blob"));
-               $self->{last_object_size} = $n;
+       if ($self->{want_object_info}) {
+               chomp(my $oid = $self->get_mark(":$blob"));
+               $self->{last_object} = [ $oid, $n, \$str ];
        }
-
        my $ref = $self->{ref};
        my $commit = $self->{mark}++;
        my $parent = $tip =~ /\A:/ ? $tip : undef;
@@ -296,25 +298,6 @@ sub add {
                print $w "reset $ref\n" or wfail;
        }
 
-       # 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);
        print $w "commit $ref\nmark :$commit\n",
                "author $name <$email> $date_raw\n",
@@ -374,6 +357,13 @@ sub done {
        close $lockfh or die "close lock failed: $!";
 }
 
+sub atfork_child {
+       my ($self) = @_;
+       foreach my $f (qw(in out)) {
+               close $self->{$f} or die "failed to close import[$f]: $!\n";
+       }
+}
+
 1;
 __END__
 =pod