Last active
April 20, 2017 06:28
-
-
Save karronoli/e1fe69baead725e3813bdddec2b27a52 to your computer and use it in GitHub Desktop.
Import MySQL record to Elasticsearch index with japanese mappinng example.
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
requires 'DBI', '1.636'; | |
requires 'DBD::mysql', '4.042'; | |
requires 'Search::Elasticsearch', '2.03'; |
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
=head1 NAME | |
Import MySQL record to Elasticsearch index with japanese mappinng example. | |
=cut | |
use strict; | |
use warnings; | |
use utf8; | |
use Data::Dumper; | |
use Encode; | |
use Unicode::Normalize; | |
use DBI; | |
use DBD::mysql; | |
use Search::Elasticsearch; | |
use constant | |
{DATABASE => 'mydatabase', | |
DB_HOST => 'localhost', | |
DB_PORT => 3006, | |
DB_USER => 'myuser', | |
DB_PASS => 'mypassword', | |
DB_TABLE => 'mytable', | |
SQL_TEMPLATE => 'select id, name, created_at from %s', # mytable, | |
ES_INDEX => 'myindex', | |
ES_STOPTAGS => ["接続詞","助詞","助詞-格助詞","助詞-格助詞-一般","助詞-格助詞-引用","助詞-格助詞-連語","助詞-接続助詞","助詞-係助詞","助詞-副助詞","助詞-間投助詞","助詞-並立助詞","助詞-終助詞","助詞-副助詞/並立助詞/終助詞","助詞-連体化","助詞-副詞化","助詞-特殊","助動詞","記号","記号-一般","記号-読点","記号-句点","記号-空白","記号-括弧開","記号-括弧閉","その他-間投","フィラー","非言語音"]}; | |
my $dbh = DBI->connect(sprintf('DBI:mysql:%s:%s:%d', DATABASE, DB_HOST, DB_PORT), | |
DB_USER, DB_PASS) | |
or die "cannot connect to MySQL: $DBI::errstr"; | |
my $sth = $dbh->prepare(sprintf(SQL_TEMPLATE, DB_TABLE)) or die $dbh->errstr; | |
$sth->execute or die $dbh->errstr; | |
my @row; | |
while (my @tmp = $sth->fetchrow_array) { | |
push @row, [map {decode_utf8($_)} @tmp]; | |
} | |
$sth->finish; | |
$dbh->disconnect; | |
# elasticsearch-plugin install analysis-kuromoji | |
# elasticsearch-plugin install org.codelibs:elasticsearch-analysis-kuromoji-neologd:5.2.1 | |
my %mappings = | |
(items => | |
{properties => {name => | |
{type => 'text', | |
analyzer => 'japanese'}, | |
created_at => {type => 'date'}}}); | |
my %settings = | |
(index => | |
{analysis => | |
{filter => | |
{pos_filter => | |
{type => 'kuromoji_part_of_speech', | |
stoptags => ES_STOPTAGS}}, | |
tokenizer => {kuromoji => | |
{type => 'kuromoji_tokenizer', | |
mode => 'search'}}, | |
analyzer => {japanese => | |
{type => 'custom', | |
tokenizer => 'kuromoji', | |
filter => ['pos_filter']}}}}); | |
my $es = Search::Elasticsearch->new(); | |
eval { | |
$es->indices->delete(index => ES_INDEX); | |
}; | |
warn $@ if $@; | |
$es->indices->create(index => ES_INDEX, | |
body => {mappings => \%mappings, | |
settings => \%settings}); | |
my $bulk = $es->bulk_helper(index => ES_INDEX, type => DB_TABLE); | |
for my $row (@row) { | |
my ($id, $name, $created_at) = ($row->[0], NFKC($row->[1]), $row->[2]); | |
$bulk->index({id => $id, | |
source => {name => $name, | |
created_at => $created_at}}); | |
} | |
$bulk->flush; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment