v2writable: preserve timestamps from import

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

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 572e9bb9899fc464671510dc26275d51d6b7ce8c..3853ff2b532b1cb3aea0dd47de500260de210fc3 100644 (file)
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2020 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
@@ -9,7 +9,7 @@ package PublicInbox::Import;
 use strict;
 use warnings;
 use base qw(PublicInbox::Lock);
-use PublicInbox::Spawn qw(spawn);
+use PublicInbox::Spawn qw(spawn popen_rd);
 use PublicInbox::MID qw(mids mid2path);
 use PublicInbox::Address;
 use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
@@ -46,8 +46,7 @@ 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 +65,7 @@ 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 => $out_r, 1 => $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} = $out_w;
@@ -277,8 +274,8 @@ sub git_timestamp {
        "$ts $zone";
 }
 
-sub extract_cmt_info ($) {
-       my ($mime) = @_;
+sub extract_cmt_info ($;$) {
+       my ($mime, $v2w) = @_;
 
        my $sender = '';
        my $from = $mime->header('From');
@@ -296,6 +293,10 @@ sub extract_cmt_info ($) {
                }
        }
        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 +325,10 @@ 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 ($v2w) { # set fallbacks in case message had no date
+               $v2w->{autime} = $at[0];
+               $v2w->{cotime} = $ct[0];
+       }
        ($name, $email, $at, $ct, $subject);
 }
 
@@ -369,9 +374,9 @@ 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, $v2w) = @_; # mime = Email::MIME
 
-       my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime);
+       my ($name, $email, $at, $ct, $subject) = extract_cmt_info($mime, $v2w);
        my $path_type = $self->{path_type};
        my $path;
        if ($path_type eq '2/38') {
@@ -430,7 +435,6 @@ 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";
 }