-# Copyright (C) 2016-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
#
# git fast-import-based ssoma-mda MDA replacement
-# This is only ever run by public-inbox-mda and public-inbox-learn,
-# not the WWW or NNTP code which only requires read-only access.
+# This is only ever run by public-inbox-mda, public-inbox-learn
+# and public-inbox-watch. Not the WWW or NNTP code which only
+# requires read-only access.
package PublicInbox::Import;
use strict;
use warnings;
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,
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 $buf = '';
run_die([@cmd, 'update-server-info'], undef);
($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 $do_gc;
"$ts $zone";
}
-sub extract_author_info ($) {
+sub extract_cmt_info ($) {
my ($mime) = @_;
my $sender = '';
$name = '';
warn "no name in From: $from or Sender: $sender\n";
}
- ($name, $email);
+
+ my $hdr = $mime->header_obj;
+
+ my $subject = $hdr->header('Subject');
+ $subject = '(no subject)' unless defined $subject;
+ # Mime decoding can create nulls replace them with spaces to protect git
+ $subject =~ tr/\0/ /;
+ utf8::encode($subject);
+ my $at = git_timestamp(my @at = msg_datestamp($hdr));
+ my $ct = git_timestamp(my @ct = msg_timestamp($hdr));
+ ($name, $email, $at, $ct, $subject);
}
# kill potentially confusing/misleading headers
sub add {
my ($self, $mime, $check_cb) = @_; # mime = Email::MIME
- my ($name, $email) = extract_author_info($mime);
- my $hdr = $mime->header_obj;
- my @at = msg_datestamp($hdr);
- 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 $subject;
+ my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime);
my $path_type = $self->{path_type};
-
my $path;
if ($path_type eq '2/38') {
$path = mid2path(v1_mid0($mime));
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;
+ "author $name <$email> $at\n",
+ "committer $self->{ident} $ct\n" or wfail;
print $w "data ", (length($subject) + 1), "\n",
$subject, "\n\n" or wfail;
if ($tip ne '') {
$? == 0 or die join(' ', @$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;
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;
my $old = $self->{'ref'};
my $git = $self->{git};
my @export = (qw(fast-export --no-data --use-done-feature), $old);
- my ($rd, $pid) = $git->popen(@export);
+ my $rd = $git->popen(@export);
my ($r, $w) = $self->gfi_start;
my @buf;
my $npurge = 0;
@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, $_;
push @buf, $buf;
} elsif (/^M 100644 ([a-f0-9]+) (\w+)/) {
my ($oid, $path) = ($1, $2);
+ $tree->{$path} = 1;
if ($purge->{$oid}) {
push @oids, $oid;
- delete $tree->{$path};
+ my $cmd = "M 100644 inline $path\ndata 0\n\n";
+ push @buf, $cmd;
} else {
- $tree->{$path} = 1;
push @buf, $_;
}
} elsif (/^D (\w+)/) {
@buf = ();
} elsif ($_ eq "done\n") {
$done = 1;
- } elsif (/^mark :(\d+)$/) {
+ } elsif (/^mark :([0-9]+)$/) {
push @buf, $_;
$mark = $1;
} else {
push @buf, $_;
}
}
+ close $rd or die "close fast-export failed: $?";
if (@buf) {
$w->print(@buf) or wfail;
}
=head1 NAME
-PublicInbox::Import - message importer for public-inbox
+PublicInbox::Import - message importer for public-inbox v1 inboxes
=head1 VERSION
=head1 DESCRIPTION
An importer and remover for public-inboxes which takes L<Email::MIME>
-messages as input and stores them in a ssoma repository as
-documented in L<https://ssoma.public-inbox.org/ssoma_repository.txt>,
+messages as input and stores them in a git repository as
+documented in L<https://public-inbox.org/public-inbox-v1-format.txt>,
except it does not allow duplicate Message-IDs.
It requires L<git(1)> and L<git-fast-import(1)> to be installed.