-# 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 base qw(PublicInbox::Lock);
use PublicInbox::Spawn qw(spawn);
-use PublicInbox::MID qw(mids mid_mime mid2path);
+use PublicInbox::MID qw(mids mid2path);
use PublicInbox::Address;
use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
use PublicInbox::ContentId qw(content_digest);
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,
my $git_dir = $git->{git_dir};
my @cmd = ('git', "--git-dir=$git_dir", qw(fast-import
--quiet --done --date-format=raw));
- my $rdr = { 0 => fileno($out_r), 1 => fileno($in_w) };
+ my $rdr = { 0 => $out_r, 1 => $in_w };
my $pid = spawn(\@cmd, undef, $rdr);
die "spawn fast-import failed: $!" unless defined $pid;
$out_w->autoflush(1);
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 = '';
my $env = { GIT_INDEX_FILE => $index };
run_die([@cmd, qw(read-tree -m -v -i), $self->{ref}], $env);
}
- run_die([@cmd, 'update-server-info'], undef);
- ($self->{path_type} eq '2/38') and eval {
+ run_die([@cmd, 'update-server-info']);
+ my $ibx = $self->{-inbox};
+ ($ibx && $self->{path_type} eq '2/38') and eval {
require PublicInbox::SearchIdx;
- my $inbox = $self->{inbox} || $git_dir;
- my $s = PublicInbox::SearchIdx->new($inbox);
+ my $s = PublicInbox::SearchIdx->new($ibx);
$s->index_sync({ ref => $self->{ref} });
};
- eval { run_die([@cmd, qw(gc --auto)], undef) } if $do_gc;
+ eval { run_die([@cmd, qw(gc --auto)]) } if $do_gc;
}
sub barrier {
"$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));
}
my $blob = $self->{mark}++;
- my $str = $mime->as_string;
- my $n = length($str);
+ my $raw_email = $mime->{-public_inbox_raw} // $mime->as_string;
+ my $n = length($raw_email);
$self->{bytes_added} += $n;
print $w "blob\nmark :$blob\ndata ", $n, "\n" or wfail;
- print $w $str, "\n" or wfail;
+ 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, \$str ];
+ $self->{last_object} = [ $oid, $n, \$raw_email ];
}
my $ref = $self->{ref};
my $commit = $self->{mark}++;
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 $self->{out} or return;
sub atfork_child {
my ($self) = @_;
foreach my $f (qw(in out)) {
+ next unless defined($self->{$f});
close $self->{$f} or die "failed to close import[$f]: $!\n";
}
}
"$dt.$b64" . '@z';
}
-sub clean_purge_buffer {
- my ($oids, $buf) = @_;
- my $cmt_msg = 'purged '.join(' ',@$oids)."\n";
+sub rewrite_commit ($$$$) {
+ my ($self, $oids, $buf, $mime) = @_;
+ my ($name, $email, $at, $ct, $subject);
+ if ($mime) {
+ ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime);
+ } else {
+ $name = $email = '';
+ $subject = 'purged '.join(' ', @$oids);
+ }
@$oids = ();
-
+ $subject .= "\n";
foreach my $i (0..$#$buf) {
my $l = $buf->[$i];
- if ($l =~ /^author .* (\d+ [\+-]?\d+)$/) {
- $buf->[$i] = "author <> $1\n";
- } elsif ($l =~ /^data (\d+)/) {
- $buf->[$i++] = "data " . length($cmt_msg) . "\n";
- $buf->[$i] = $cmt_msg;
+ if ($l =~ /^author .* ([0-9]+ [\+-]?[0-9]+)$/) {
+ $at //= $1;
+ $buf->[$i] = "author $name <$email> $at\n";
+ } elsif ($l =~ /^committer .* ([0-9]+ [\+-]?[0-9]+)$/) {
+ $ct //= $1;
+ $buf->[$i] = "committer $self->{ident} $ct\n";
+ } elsif ($l =~ /^data ([0-9]+)/) {
+ $buf->[$i++] = "data " . length($subject) . "\n";
+ $buf->[$i] = $subject;
last;
}
}
}
-sub purge_oids {
- my ($self, $purge) = @_;
- my $tmp = "refs/heads/purge-".((keys %$purge)[0]);
+# returns the new commit OID if a replacement was done
+# returns undef if nothing was done
+sub replace_oids {
+ my ($self, $mime, $replace_map) = @_; # oid => raw string
+ my $tmp = "refs/heads/replace-".((keys %$replace_map)[0]);
my $old = $self->{'ref'};
my $git = $self->{git};
my @export = (qw(fast-export --no-data --use-done-feature), $old);
- my ($rd, $pid) = $git->popen(@export);
+ my $rd = $git->popen(@export);
my ($r, $w) = $self->gfi_start;
my @buf;
- my $npurge = 0;
+ my $nreplace = 0;
my @oids;
my ($done, $mark);
my $tree = $self->{-tree};
@buf = ();
}
push @buf, "commit $tmp\n";
- } elsif (/^data (\d+)/) {
+ } elsif (/^data ([0-9]+)/) {
# only commit message, so $len is small:
my $len = $1; # + 1 for trailing "\n"
push @buf, $_;
push @buf, $buf;
} elsif (/^M 100644 ([a-f0-9]+) (\w+)/) {
my ($oid, $path) = ($1, $2);
- if ($purge->{$oid}) {
+ $tree->{$path} = 1;
+ my $sref = $replace_map->{$oid};
+ if (defined $sref) {
push @oids, $oid;
- delete $tree->{$path};
+ my $n = length($$sref);
+ push @buf, "M 100644 inline $path\ndata $n\n";
+ push @buf, $$sref; # hope CoW works...
+ push @buf, "\n";
} else {
- $tree->{$path} = 1;
push @buf, $_;
}
} elsif (/^D (\w+)/) {
push @buf, $_ if $tree->{$path};
} elsif ($_ eq "\n") {
if (@oids) {
- my $out = join('', @buf);
- $out =~ s/^/# /sgm;
- warn "purge rewriting\n", $out, "\n";
- clean_purge_buffer(\@oids, \@buf);
- $npurge++;
+ if (!$mime) {
+ my $out = join('', @buf);
+ $out =~ s/^/# /sgm;
+ warn "purge rewriting\n", $out, "\n";
+ }
+ rewrite_commit($self, \@oids, \@buf, $mime);
+ $nreplace++;
}
$w->print(@buf, "\n") or wfail;
@buf = ();
} elsif ($_ 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;
}
die 'done\n not seen from fast-export' unless $done;
- chomp(my $cmt = $self->get_mark(":$mark")) if $npurge;
+ chomp(my $cmt = $self->get_mark(":$mark")) if $nreplace;
$self->{nchg} = 0; # prevent _update_git_info until update-ref:
$self->done;
my @git = ('git', "--git-dir=$git->{git_dir}");
- run_die([@git, qw(update-ref), $old, $tmp]) if $npurge;
+ run_die([@git, qw(update-ref), $old, $tmp]) if $nreplace;
run_die([@git, qw(update-ref -d), $tmp]);
- return if $npurge == 0;
+ return if $nreplace == 0;
+
+ run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all --quiet)]);
- run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all)]);
+ # check that old OIDs are gone
my $err = 0;
- foreach my $oid (keys %$purge) {
+ foreach my $oid (keys %$replace_map) {
my @info = $git->check($oid);
if (@info) {
- warn "$oid not purged\n";
+ warn "$oid not replaced\n";
$err++;
}
}
_update_git_info($self, 0);
- die "Failed to purge $err object(s)\n" if $err;
+ die "Failed to replace $err object(s)\n" if $err;
$cmt;
}
=head1 NAME
-PublicInbox::Import - message importer for public-inbox
+PublicInbox::Import - message importer for public-inbox v1 inboxes
=head1 VERSION
version 1.0
-=head1 SYNOPSYS
+=head1 SYNOPSIS
use Email::MIME;
use PublicInbox::Git;
=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.