[
https://issues.apache.org/jira/browse/METRON-283?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15838577#comment-15838577
]
ASF GitHub Bot commented on METRON-283:
---------------------------------------
Github user justinleet commented on a diff in the pull request:
https://github.com/apache/incubator-metron/pull/421#discussion_r97877931
--- Diff:
metron-platform/metron-enrichment/src/main/java/org/apache/metron/enrichment/adapters/geo/GeoLiteDatabase.java
---
@@ -0,0 +1,184 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.metron.enrichment.adapters.geo;
+
+import com.maxmind.db.CHMCache;
+import com.maxmind.geoip2.DatabaseReader;
+import com.maxmind.geoip2.exception.GeoIp2Exception;
+import com.maxmind.geoip2.model.CityResponse;
+import com.maxmind.geoip2.record.City;
+import com.maxmind.geoip2.record.Country;
+import com.maxmind.geoip2.record.Location;
+import com.maxmind.geoip2.record.Postal;
+import org.apache.commons.validator.routines.InetAddressValidator;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.net.InetAddress;
+import java.net.UnknownHostException;
+import java.util.HashMap;
+import java.util.Map;
+import java.util.Optional;
+import java.util.concurrent.locks.Lock;
+import java.util.concurrent.locks.ReentrantReadWriteLock;
+import java.util.zip.GZIPInputStream;
+
+public enum GeoLiteDatabase {
+ INSTANCE;
+
+ protected static final Logger LOG =
LoggerFactory.getLogger(GeoLiteDatabase.class);
+ public static final String GEO_HDFS_FILE = "geo.hdfs.file";
+ public static final String GEO_HDFS_FILE_DEFAULT =
"/apps/metron/geo/default/GeoLite2-City.mmdb.gz";
+
+ private static ReentrantReadWriteLock lock = new
ReentrantReadWriteLock();
+ private static final Lock readLock = lock.readLock();
+ private static final Lock writeLock = lock.writeLock();
+ private static InetAddressValidator ipvalidator = new
InetAddressValidator();
+ private static volatile String hdfsLoc = GEO_HDFS_FILE_DEFAULT;
+ private static DatabaseReader reader = null;
+
+ public synchronized void updateIfNecessary(Map<String, Object>
globalConfig) {
+ // Reload database if necessary (file changes on HDFS)
+ LOG.trace("[Metron] Determining if GeoIpDatabase update required");
+ String hdfsFile = GEO_HDFS_FILE_DEFAULT;
+ if (globalConfig != null) {
+ hdfsFile = (String) globalConfig.getOrDefault(GEO_HDFS_FILE,
GEO_HDFS_FILE_DEFAULT);
+ }
+
+ // Always update if we don't have a DatabaseReader
+ if (reader == null || !hdfsLoc.equals(hdfsFile)) {
--- End diff --
`UpdateIfNecessary` is actually synchronized, so it's already locked.
Given that updates are rare and this is only run on global configs being
updated, impact will be very low (since it's called very rarely).
> Migrate Geo Enrichment outside of MySQL
> ---------------------------------------
>
> Key: METRON-283
> URL: https://issues.apache.org/jira/browse/METRON-283
> Project: Metron
> Issue Type: Improvement
> Reporter: James Sirota
> Assignee: Justin Leet
> Priority: Minor
>
> We need to migrate our enrichment SQL store from MySQL to Phoenix or some
> other SQL on Hbase library. Or alternatively come up with a way to do this
> without using SQL. This way we don't have a dependency on MySQL and there is
> one less thing that we need to install on our platform
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
