tighten up digit matches to ASCII for git output

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

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 7e596abc38b2bc541074f757c560ca33ed64610f..2c4bad92996dde45489c84a590cc4cc94f6ebf59 100644 (file)
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -18,19 +18,22 @@ use PublicInbox::MDA;
 use POSIX qw(strftime);
 
 sub new {
+       # we can't change arg order, this is documented in POD
+       # and external projects may rely on it:
        my ($class, $git, $name, $email, $ibx) = @_;
        my $ref = 'refs/heads/master';
        if ($ibx) {
                $ref = $ibx->{ref_head} || 'refs/heads/master';
                $name ||= $ibx->{name};
                $email ||= $ibx->{-primary_address};
+               $git ||= $ibx->git;
        }
        bless {
                git => $git,
                ident => "$name <$email>",
                mark => 1,
                ref => $ref,
-               inbox => $ibx,
+               -inbox => $ibx,
                path_type => '2/38', # or 'v2'
                lock_path => "$git->{git_dir}/ssoma.lock", # v2 changes this
                bytes_added => 0,
@@ -103,7 +106,7 @@ sub _cat_blob ($$$) {
        local $/ = "\n";
        my $info = <$r>;
        defined $info or die "EOF from fast-import / cat-blob: $!";
-       $info =~ /\A[a-f0-9]{40} blob (\d+)\n\z/ or return;
+       $info =~ /\A[a-f0-9]{40} blob ([0-9]+)\n\z/ or return;
        my $left = $1;
        my $offset = 0;
        my $buf = '';
@@ -178,8 +181,8 @@ sub _update_git_info ($$) {
        run_die([@cmd, 'update-server-info'], undef);
        ($self->{path_type} eq '2/38') and eval {
                require PublicInbox::SearchIdx;
-               my $inbox = $self->{inbox} || $git_dir;
-               my $s = PublicInbox::SearchIdx->new($inbox);
+               my $ibx = $self->{-inbox} || $git_dir;
+               my $s = PublicInbox::SearchIdx->new($ibx);
                $s->index_sync({ ref => $self->{ref} });
        };
        eval { run_die([@cmd, qw(gc --auto)], undef) } if $do_gc;
@@ -364,10 +367,14 @@ sub add {
        my @ct = msg_timestamp($hdr);
        my $author_time_raw = git_timestamp(@at);
        my $commit_time_raw = git_timestamp(@ct);
+
        my $subject = $mime->header('Subject');
        $subject = '(no subject)' unless defined $subject;
-       my $path_type = $self->{path_type};
+       # Mime decoding can create nulls replace them with spaces to protect git
+       $subject =~ tr/\0/ /;
+       utf8::encode($subject);
 
+       my $path_type = $self->{path_type};
        my $path;
        if ($path_type eq '2/38') {
                $path = mid2path(v1_mid0($mime));
@@ -408,9 +415,6 @@ sub add {
                print $w "reset $ref\n" or wfail;
        }
 
-       # Mime decoding can create nulls replace them with spaces to protect git
-       $subject =~ tr/\0/ /;
-       utf8::encode($subject);
        print $w "commit $ref\nmark :$commit\n",
                "author $name <$email> $author_time_raw\n",
                "committer $self->{ident} $commit_time_raw\n" or wfail;
@@ -433,6 +437,16 @@ sub run_die ($;$$) {
        $? == 0 or die join(' ', @$cmd) . " failed: $?\n";
 }
 
+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);
+}
+
 sub done {
        my ($self) = @_;
        my $w = delete $self->{out} or return;
@@ -479,9 +493,9 @@ sub clean_purge_buffer {
 
        foreach my $i (0..$#$buf) {
                my $l = $buf->[$i];
-               if ($l =~ /^author .* (\d+ [\+-]?\d+)$/) {
+               if ($l =~ /^author .* ([0-9]+ [\+-]?[0-9]+)$/) {
                        $buf->[$i] = "author <> $1\n";
-               } elsif ($l =~ /^data (\d+)/) {
+               } elsif ($l =~ /^data ([0-9]+)/) {
                        $buf->[$i++] = "data " . length($cmt_msg) . "\n";
                        $buf->[$i] = $cmt_msg;
                        last;
@@ -511,7 +525,7 @@ sub purge_oids {
                                @buf = ();
                        }
                        push @buf, "commit $tmp\n";
-               } elsif (/^data (\d+)/) {
+               } elsif (/^data ([0-9]+)/) {
                        # only commit message, so $len is small:
                        my $len = $1; # + 1 for trailing "\n"
                        push @buf, $_;
@@ -543,7 +557,7 @@ sub purge_oids {
                        @buf = ();
                } elsif ($_ eq "done\n") {
                        $done = 1;
-               } elsif (/^mark :(\d+)$/) {
+               } elsif (/^mark :([0-9]+)$/) {
                        push @buf, $_;
                        $mark = $1;
                } else {
@@ -586,7 +600,7 @@ __END__
 
 =head1 NAME
 
-PublicInbox::Import - message importer for public-inbox
+PublicInbox::Import - message importer for public-inbox v1 inboxes
 
 =head1 VERSION