X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=98aa7785efb1815f985fffe56b70aad772bca206;hb=46742d95647c7a80cb2f60d5c134717dd91e22e2;hp=3853ff2b532b1cb3aea0dd47de500260de210fc3;hpb=e5dbf0680cfbfa81bad38457c0430fd260dda682;p=public-inbox.git diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm index 3853ff2b..98aa7785 100644 --- a/lib/PublicInbox/Import.pm +++ b/lib/PublicInbox/Import.pm @@ -15,6 +15,7 @@ use PublicInbox::Address; use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp); use PublicInbox::ContentId qw(content_digest); use PublicInbox::MDA; +use PublicInbox::Eml; use POSIX qw(strftime); sub new { @@ -137,7 +138,7 @@ sub check_remove_v1 { $info =~ m!\A100644 blob ([a-f0-9]{40})\t!s or die "not blob: $info"; my $oid = $1; my $msg = _cat_blob($r, $w, $oid) or die "BUG: cat-blob $1 failed"; - my $cur = PublicInbox::MIME->new($msg); + my $cur = PublicInbox::Eml->new($msg); my $cur_s = $cur->header('Subject'); $cur_s = '' unless defined $cur_s; my $cur_m = $mime->header('Subject'); @@ -275,7 +276,7 @@ sub git_timestamp { } sub extract_cmt_info ($;$) { - my ($mime, $v2w) = @_; + my ($mime, $smsg) = @_; my $sender = ''; my $from = $mime->header('From'); @@ -325,9 +326,9 @@ sub extract_cmt_info ($;$) { utf8::encode($subject); my $at = git_timestamp(my @at = msg_datestamp($hdr)); my $ct = git_timestamp(my @ct = msg_timestamp($hdr)); - if ($v2w) { # set fallbacks in case message had no date - $v2w->{autime} = $at[0]; - $v2w->{cotime} = $ct[0]; + if ($smsg) { + $smsg->{ds} = $at[0]; + $smsg->{ts} = $ct[0]; } ($name, $email, $at, $ct, $subject); } @@ -354,7 +355,7 @@ sub v1_mid0 ($) { my $hdr = $mime->header_obj; my $mids = mids($hdr); - if (!scalar(@$mids)) { # spam often has no Message-Id + if (!scalar(@$mids)) { # spam often has no Message-ID my $mid0 = digest2mid(content_digest($mime), $hdr); append_mid($hdr, $mid0); return $mid0; @@ -374,9 +375,9 @@ sub clean_tree_v2 ($$$) { # returns undef on duplicate # returns the :MARK of the most recent commit sub add { - my ($self, $mime, $check_cb, $v2w) = @_; # mime = Email::MIME + my ($self, $mime, $check_cb, $smsg) = @_; # mime = Email::MIME - my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime, $v2w); + my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime, $smsg); my $path_type = $self->{path_type}; my $path; if ($path_type eq '2/38') { @@ -406,9 +407,10 @@ sub add { print $w $raw_email, "\n" or wfail; # v2: we need this for Xapian - if ($self->{want_object_info}) { - my $oid = $self->get_mark(":$blob"); - $self->{last_object} = [ $oid, $n, \$raw_email ]; + if ($smsg) { + $smsg->{blob} = $self->get_mark(":$blob"); + $smsg->{bytes} = $n; + $smsg->{-raw_email} = \$raw_email; } my $ref = $self->{ref}; my $commit = $self->{mark}++; @@ -439,14 +441,31 @@ sub run_die ($;$$) { $? == 0 or die join(' ', @$cmd) . " failed: $?\n"; } +my @INIT_FILES = ('HEAD' => "ref: refs/heads/master\n", + 'description' => < <{git}->{git_dir} if ref($dir); + require File::Path; + File::Path::mkpath([ map { "$dir/$_" } qw(objects/info refs/heads) ]); + for (my $i = 0; $i < @INIT_FILES; $i++) { + my $f = $dir.'/'.$INIT_FILES[$i++]; + next if -f $f; + open my $fh, '>', $f or die "open $f: $!"; + print $fh $INIT_FILES[$i] or die "print $f: $!"; + close $fh or die "close $f: $!"; + } } sub done {