Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
added a script to backfill/update suggest data
- Loading branch information
Showing
1 changed file
with
118 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,118 @@ | ||
package MetaCPAN::Script::Suggest; | ||
|
||
use strict; | ||
use warnings; | ||
|
||
use Moose; | ||
|
||
use DateTime (); | ||
use Log::Contextual qw( :log ); | ||
use MetaCPAN::Types qw( Bool Int ); | ||
|
||
with 'MetaCPAN::Role::Script', 'MooseX::Getopt'; | ||
|
||
has age => ( | ||
is => 'ro', | ||
isa => Int, | ||
default => 1, | ||
documentation => 'number of days back to cover.', | ||
); | ||
|
||
has all => ( | ||
is => 'ro', | ||
isa => Bool, | ||
default => 0, | ||
documentation => 'update all records', | ||
); | ||
|
||
sub run { | ||
my $self = shift; | ||
|
||
if ( $self->all ) { | ||
my $dt = DateTime->new( year => 1994, month => 1 ); | ||
my $end_time = DateTime->now->add( months => 1 ); | ||
|
||
while ( $dt < $end_time ) { | ||
my $gte = $dt->strftime("%Y-%m"); | ||
$dt->add( months => 1 ); | ||
my $lt = $dt->strftime("%Y-%m"); | ||
|
||
my $range = +{ range => { date => { gte => $gte, lt => $lt } } }; | ||
log_info {"updating suggest data for month: $gte"}; | ||
$self->_update_slice($range); | ||
} | ||
} | ||
else { | ||
my $gte = DateTime->now()->subtract( days => $self->age ) | ||
->strftime("%Y-%m-%d"); | ||
my $range = +{ range => { date => { gte => $gte } } }; | ||
log_info {"updating suggest data since: $gte "}; | ||
$self->_update_slice($range); | ||
} | ||
|
||
log_info {"done."}; | ||
} | ||
|
||
sub _update_slice { | ||
my ( $self, $range ) = @_; | ||
|
||
my $files = $self->es->scroll_helper( | ||
index => $self->index->name, | ||
type => 'file', | ||
search_type => 'scan', | ||
scroll => '5m', | ||
fields => [qw< id documentation >], | ||
size => 500, | ||
body => { | ||
query => { | ||
bool => { | ||
must => [ | ||
{ exists => { field => "documentation" } }, $range | ||
], | ||
} | ||
} | ||
}, | ||
); | ||
|
||
my $bulk = $self->es->bulk_helper( | ||
index => $self->index->name, | ||
type => 'file', | ||
max_count => 250, | ||
timeout => '5m', | ||
); | ||
|
||
while ( my $file = $files->next ) { | ||
my $documentation = $file->{fields}{documentation}[0]; | ||
my $weight = 1000 - length($documentation); | ||
$weight = 0 if $weight < 0; | ||
|
||
$bulk->update( | ||
{ | ||
id => $file->{fields}{id}[0], | ||
doc => { | ||
suggest => { | ||
input => [$documentation], | ||
payload => { doc_name => $documentation }, | ||
weight => $weight, | ||
} | ||
}, | ||
} | ||
); | ||
} | ||
|
||
$bulk->flush; | ||
} | ||
|
||
__PACKAGE__->meta->make_immutable; | ||
1; | ||
|
||
__END__ | ||
=head1 SYNOPSIS | ||
# bin/metacpan suggest | ||
=head1 DESCRIPTION | ||
After importing releases from CPAN, this script will set the suggest | ||
field for autocompletion searches. |