replace most uses of PublicInbox::MIME with Eml

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

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 68dc0c7e83c1b223796ee171200d879065e1add2..98aa7785efb1815f985fffe56b70aad772bca206 100644 (file)
--- 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 = $mime->header('Subject');
@@ -274,8 +275,8 @@ sub git_timestamp {
        "$ts $zone";
 }
 
-sub extract_cmt_info ($) {
-       my ($mime) = @_;
+sub extract_cmt_info ($;$) {
+       my ($mime, $smsg) = @_;
 
        my $sender = '';
        my $from = $mime->header('From');
@@ -325,6 +326,10 @@ sub extract_cmt_info ($) {
        utf8::encode($subject);
        my $at = git_timestamp(my @at = msg_datestamp($hdr));
        my $ct = git_timestamp(my @ct = msg_timestamp($hdr));
+       if ($smsg) {
+               $smsg->{ds} = $at[0];
+               $smsg->{ts} = $ct[0];
+       }
        ($name, $email, $at, $ct, $subject);
 }
 
@@ -350,7 +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;
@@ -370,9 +375,9 @@ sub clean_tree_v2 ($$$) {
 # returns undef on duplicate
 # returns the :MARK of the most recent commit
 sub add {
-       my ($self, $mime, $check_cb) = @_; # mime = Email::MIME
+       my ($self, $mime, $check_cb, $smsg) = @_; # mime = Email::MIME
 
-       my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime);
+       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') {
@@ -402,9 +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 = $self->{mark}++;
@@ -435,14 +441,31 @@ sub run_die ($;$$) {
        $? == 0 or die join(' ', @$cmd) . " failed: $?\n";
 }
 
+my @INIT_FILES = ('HEAD' => "ref: refs/heads/master\n",
+               'description' => <<EOD,
+Unnamed repository; edit this file 'description' to name the repository.
+EOD
+               'config' => <<EOC);
+[core]
+       repositoryFormatVersion = 0
+       filemode = true
+       bare = true
+[repack]
+       writeBitmaps = true
+EOC
+
 sub init_bare {
-       my ($dir) = @_;
-       my @cmd = (qw(git init --bare -q), $dir);
-       run_die(\@cmd);
-       # set a reasonable default:
-       @cmd = (qw/git config/, "--file=$dir/config",
-               'repack.writeBitmaps', 'true');
-       run_die(\@cmd);
+       my ($dir) = @_; # or self
+       $dir = $dir->{git}->{git_dir} if ref($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 {