使用彈性搜索 6.8.0 版
完整的 Hive 作業因單個格式錯誤的 json 記錄而失敗,我嘗試更改 'es.write.rest.error.handler.es.return.default'='PASS/HANDLED' 但沒有運氣
參考:https ://www.elastic.co/guide/en/elasticsearch/hadoop/master/errorhandlers.html
以下是在 Hive 提示符下運行以進行攝取的 DDL 腳本
ADD JAR /home/smrafi/elasticsearch-hadoop-6.8.0/dist/elasticsearch-hadoop-6.8.0.jar;
CREATE external TABLE hive_es_with_handler10( data STRING)
STORED BY 'org.elasticsearch.hadoop.hive.EsStorageHandler'
TBLPROPERTIES('es.resource' = 'test_eshadoop/healthCareProvider','es.nodes' = 'xyzpqr','es.input.json' = 'yes','es.index.auto.create' = 'true','es.write.operation'='upsert',
'es.nodes.wan.only' = 'true','es.port' = '443','es.net.ssl'='true','es.batch.size.entries'='1','es.mapping.id' ='id','es.batch.write.retry.count'='-1',
'es.batch.write.retry.wait'='60s',
'es.write.data.error.handlers' = 'es',
'es.write.rest.error.handler.es.client.nodes' = 'vpc-pid-pre-prod-es-cluster-b7thvqfj3tp45arxl34gge3yyi.us-east-2.es.amazonaws.com',
'es.write.rest.error.handler.es.client.port' = '443',
'es.write.rest.error.handler.es.client.resource'='error_es_index',
'es.write.rest.error.handler.es.return.default'='PASS',
'es.write.rest.error.handler.es.return.error'='PASS');
insert into hive_es_with_handler10 select * from provider;
下面是例外跟蹤,它抱怨錯誤失敗。處理程式索引不存在
Caused by: org.elasticsearch.hadoop.EsHadoopIllegalArgumentException: Could not locate write resource for ES error handler.
at org.elasticsearch.hadoop.util.Assert.hasText(Assert.java:30)
at org.elasticsearch.hadoop.handler.impl.elasticsearch.ElasticsearchHandler.init(ElasticsearchHandler.java:145)
at org.elasticsearch.hadoop.serialization.handler.write.impl.DelegatingErrorHandler.init(DelegatingErrorHandler.java:40)
at org.elasticsearch.hadoop.handler.impl.AbstractHandlerLoader.loadHandlers(AbstractHandlerLoader.java:114)
at org.elasticsearch.hadoop.serialization.bulk.BulkEntryWriter.<init>(BulkEntryWriter.java:56)
at org.elasticsearch.hadoop.rest.RestRepository.lazyInitWriting(RestRepository.java:138)
at org.elasticsearch.hadoop.rest.RestRepository.writeProcessedToIndex(RestRepository.java:185)
at org.elasticsearch.hadoop.hive.EsHiveOutputFormat$EsHiveRecordWriter.write(EsHiveOutputFormat.java:64)
at org.apache.hadoop.hive.ql.exec.FileSinkOperator.process(FileSinkOperator.java:762)
at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:897)
at org.apache.hadoop.hive.ql.exec.SelectOperator.process(SelectOperator.java:95)
at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:897)
at org.apache.hadoop.hive.ql.exec.TableScanOperator.process(TableScanOperator.java:130)
at org.apache.hadoop.hive.ql.exec.MapOperator$MapOpCtx.forward(MapOperator.java:148)
at org.apache.hadoop.hive.ql.exec.MapOperator.process(MapOperator.java:550)
... 9 more
uj5u.com熱心網友回復:
以下是正確收集所有錯誤 json 記錄錯誤的配置,Hive 仍然存在問題,Hive 不支持格式錯誤的 json 記錄請檢查此ElasticSearch hive SerializationError 處理程式
ADD JAR /home/smrafi/elasticsearch-hadoop-6.8.0/dist/elasticsearch-hadoop-6.8.0.jar;
CREATE external TABLE hive_es_with_handler32( data STRING)
STORED BY 'org.elasticsearch.hadoop.hive.EsStorageHandler'
TBLPROPERTIES('es.resource' = 'test_eshadoop/healthCareProvider','es.nodes' = 'xyz','es.input.json' = 'yes','es.index.auto.create' = 'true','es.write.operation'='upsert',
'es.nodes.wan.only' = 'true','es.port' = '443','es.net.ssl'='true','es.batch.size.entries'='1','es.mapping.id' ='id','es.batch.write.retry.count'='-1',
'es.batch.write.retry.wait'='60s',
'es.write.rest.error.handlers' = 'es, ignoreBadRecords',
'es.write.data.error.handlers' = 'log, customLog, badJsonHandler',
'es.write.data.error.handler.customLog' = 'com.xyz.elshandler.CustomLogOnError',
'es.write.data.error.handler.badJsonHandler' = 'com.xyz.elshandler.BadJsonHandler',
'es.write.rest.error.handler.es.client.resource'="error_es_index/error",
'es.write.rest.error.handler.es.return.default'='HANDLED',
'es.write.rest.error.handler.log.logger.name' = 'BulkErrors',
'es.write.data.error.handler.log.logger.name' = 'SerializationErrors',
'es.write.rest.error.handler.ignoreBadRecords' = 'com.xyz.elshandler.IgnoreBadRecordHandler',
'es.write.rest.error.handler.es.return.error'='HANDLED');
轉載請註明出處,本文鏈接:https://www.uj5u.com/qiye/526566.html
下一篇:Logstash無法索引到ES:`action[indices:admin/auto_create]對用戶來說是未經授權的`
