about summary refs log tree commit homepage
path: root/scripts
diff options
context:
space:
mode:
authorEric Wong (Contractor, The Linux Foundation) <e@80x24.org>2018-02-20 21:00:21 +0000
committerEric Wong (Contractor, The Linux Foundation) <e@80x24.org>2018-02-20 21:00:21 +0000
commitfeabfb1809b911fc97538282234c8b1f087ddb6a (patch)
tree8fc484f46f1c2c191ccb0a72fcbebfcad38bc115 /scripts
parentb42bbc915750cf2f0c559514041ba3f5d1a44a12 (diff)
downloadpublic-inbox-feabfb1809b911fc97538282234c8b1f087ddb6a.tar.gz
This is too slow, currently.  Working with only 2017 LKML
archives:

         git-only: ~1 minute
     git + SQLite: ~12 minutes
git+Xapian+SQlite: ~45 minutes

So yes, it looks like we'll need to parallelize Xapian indexing,
at least.
Diffstat (limited to 'scripts')
-rw-r--r--scripts/import_vger_from_mbox3
1 files changed, 3 insertions, 0 deletions
diff --git a/scripts/import_vger_from_mbox b/scripts/import_vger_from_mbox
index c45dc4ee..d30e8a30 100644
--- a/scripts/import_vger_from_mbox
+++ b/scripts/import_vger_from_mbox
@@ -7,6 +7,7 @@ use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/;
 use Date::Parse qw/str2time/;
 use Email::MIME;
 $Email::MIME::ContentType::STRICT_PARAMS = 0; # user input is imperfect
+use PublicInbox::Inbox;
 use PublicInbox::V2Writable;
 my $usage = "usage: $0 NAME EMAIL DIR <MBOX\n";
 my $dry_run;
@@ -18,8 +19,10 @@ my $mainrepo = shift or die $usage; # /path/to/v2/repo
 my $v2ibx = {
         mainrepo => $mainrepo,
         name => $name,
+        version => 2,
         -primary_address => $email,
 };
+$v2ibx = PublicInbox::Inbox->new($v2ibx);
 my $im = $dry_run ? undef : PublicInbox::V2Writable->new($v2ibx, 1);
 binmode STDIN;
 my $msg = '';