X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FImport.pm;h=98aa7785efb1815f985fffe56b70aad772bca206;hb=46742d95647c7a80cb2f60d5c134717dd91e22e2;hp=46de09c40792c511b835de6bded17b8c8173a1a9;hpb=08f57606beaa3772aefd7ebde43e615781976678;p=public-inbox.git
diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 46de09c4..98aa7785 100644
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2016-2019 all contributors
+# Copyright (C) 2016-2020 all contributors
# License: AGPL-3.0+
#
# git fast-import-based ssoma-mda MDA replacement
@@ -9,12 +9,13 @@ 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::Spawn qw(spawn popen_rd);
+use PublicInbox::MID qw(mids mid2path);
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 {
@@ -46,8 +47,7 @@ sub gfi_start {
return ($self->{in}, $self->{out}) if $self->{pid};
- my ($in_r, $in_w, $out_r, $out_w);
- pipe($in_r, $in_w) or die "pipe failed: $!";
+ my ($out_r, $out_w);
pipe($out_r, $out_w) or die "pipe failed: $!";
my $git = $self->{git};
@@ -66,9 +66,7 @@ sub gfi_start {
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 $pid = spawn(\@cmd, undef, $rdr);
- die "spawn fast-import failed: $!" unless defined $pid;
+ my ($in_r, $pid) = popen_rd(\@cmd, undef, { 0 => $out_r });
$out_w->autoflush(1);
$self->{in} = $in_r;
$self->{out} = $out_w;
@@ -140,7 +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 = $mime->header('Subject');
@@ -277,8 +275,8 @@ sub git_timestamp {
"$ts $zone";
}
-sub extract_cmt_info ($) {
- my ($mime) = @_;
+sub extract_cmt_info ($;$) {
+ my ($mime, $smsg) = @_;
my $sender = '';
my $from = $mime->header('From');
@@ -296,6 +294,10 @@ sub extract_cmt_info ($) {
}
}
if (defined $email) {
+ # Email::Address::XS may leave quoted '<' in addresses,
+ # which git-fast-import doesn't like
+ $email =~ tr/<>//d;
+
# quiet down wide character warnings with utf8::encode
utf8::encode($email);
} else {
@@ -324,6 +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, $subject);
}
@@ -349,7 +355,7 @@ sub v1_mid0 ($) {
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;
@@ -369,9 +375,9 @@ sub clean_tree_v2 ($$$) {
# returns undef on duplicate
# returns the :MARK of the most recent commit
sub add {
- my ($self, $mime, $check_cb) = @_; # mime = Email::MIME
+ my ($self, $mime, $check_cb, $smsg) = @_; # mime = Email::MIME
- my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime);
+ my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime, $smsg);
my $path_type = $self->{path_type};
my $path;
if ($path_type eq '2/38') {
@@ -401,9 +407,10 @@ sub add {
print $w $raw_email, "\n" or wfail;
# v2: we need this for Xapian
- if ($self->{want_object_info}) {
- my $oid = $self->get_mark(":$blob");
- $self->{last_object} = [ $oid, $n, \$raw_email ];
+ if ($smsg) {
+ $smsg->{blob} = $self->get_mark(":$blob");
+ $smsg->{bytes} = $n;
+ $smsg->{-raw_email} = \$raw_email;
}
my $ref = $self->{ref};
my $commit = $self->{mark}++;
@@ -430,19 +437,35 @@ sub add {
sub run_die ($;$$) {
my ($cmd, $env, $rdr) = @_;
my $pid = spawn($cmd, $env, $rdr);
- defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!";
waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish';
$? == 0 or die join(' ', @$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 {
@@ -623,7 +646,7 @@ PublicInbox::Import - message importer for public-inbox v1 inboxes
version 1.0
-=head1 SYNOPSYS
+=head1 SYNOPSIS
use Email::MIME;
use PublicInbox::Git;