[
https://issues.apache.org/jira/browse/NIFI-4731?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16474503#comment-16474503
]
ASF GitHub Bot commented on NIFI-4731:
--------------------------------------
Github user zenfenan commented on a diff in the pull request:
https://github.com/apache/nifi/pull/2682#discussion_r188032966
--- Diff:
nifi-nar-bundles/nifi-gcp-bundle/nifi-gcp-processors/src/main/java/org/apache/nifi/processors/gcp/bigquery/PutBigQueryStream.java
---
@@ -0,0 +1,360 @@
+/*
+ * 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.nifi.processors.gcp.bigquery;
+
+import com.google.cloud.bigquery.BigQuery;
+import com.google.cloud.bigquery.BigQueryError;
+import com.google.cloud.bigquery.InsertAllRequest;
+import com.google.cloud.bigquery.InsertAllResponse;
+import com.google.cloud.bigquery.JobInfo;
+import com.google.cloud.bigquery.Schema;
+import com.google.cloud.bigquery.StandardTableDefinition;
+import com.google.cloud.bigquery.Table;
+import com.google.cloud.bigquery.TableId;
+import com.google.cloud.bigquery.TableInfo;
+import com.google.common.collect.ImmutableList;
+import com.google.gson.Gson;
+import com.google.gson.reflect.TypeToken;
+import java.io.IOException;
+import java.io.InputStreamReader;
+import java.lang.reflect.Type;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Map.Entry;
+import java.util.Set;
+import java.util.concurrent.TimeUnit;
+import org.apache.nifi.annotation.behavior.InputRequirement;
+import org.apache.nifi.annotation.behavior.WritesAttribute;
+import org.apache.nifi.annotation.behavior.WritesAttributes;
+import org.apache.nifi.annotation.documentation.CapabilityDescription;
+import org.apache.nifi.annotation.documentation.Tags;
+import org.apache.nifi.annotation.lifecycle.OnScheduled;
+import org.apache.nifi.annotation.lifecycle.OnStopped;
+import org.apache.nifi.components.PropertyDescriptor;
+import org.apache.nifi.expression.ExpressionLanguageScope;
+import org.apache.nifi.flowfile.FlowFile;
+import org.apache.nifi.processor.DataUnit;
+import org.apache.nifi.processor.ProcessContext;
+import org.apache.nifi.processor.ProcessSession;
+import org.apache.nifi.processor.Relationship;
+import org.apache.nifi.processor.exception.ProcessException;
+import org.apache.nifi.processor.util.StandardValidators;
+
+/**
+ *
+ */
+
+@InputRequirement(InputRequirement.Requirement.INPUT_REQUIRED)
+@Tags({"google", "google cloud", "bq", "bigquery"})
+@CapabilityDescription("Streams flow files to a Google BigQuery table.")
+
+@WritesAttributes({
+ @WritesAttribute(attribute = BigQueryAttributes.DATASET_ATTR,
description = BigQueryAttributes.DATASET_DESC),
+ @WritesAttribute(attribute = BigQueryAttributes.TABLE_NAME_ATTR,
description = BigQueryAttributes.TABLE_NAME_DESC),
+ @WritesAttribute(attribute = BigQueryAttributes.TABLE_SCHEMA_ATTR,
description = BigQueryAttributes.TABLE_SCHEMA_DESC),
+ @WritesAttribute(attribute = BigQueryAttributes.BATCH_SIZE_ATTR,
description = BigQueryAttributes.BATCH_SIZE_DESC),
+ @WritesAttribute(attribute = BigQueryAttributes.MAX_ROW_SIZE_ATTR,
description = BigQueryAttributes.MAX_ROW_SIZE_DESC),
+ @WritesAttribute(attribute =
BigQueryAttributes.CREATE_DISPOSITION_ATTR, description =
BigQueryAttributes.CREATE_DISPOSITION_DESC),
+ @WritesAttribute(attribute =
BigQueryAttributes.TABLE_CACHE_RESET_ATTR, description =
BigQueryAttributes.TABLE_CACHE_RESET_DESC),
+ @WritesAttribute(attribute = BigQueryAttributes.JOB_ERROR_MSG_ATTR,
description = BigQueryAttributes.JOB_ERROR_MSG_DESC),
+ @WritesAttribute(attribute = BigQueryAttributes.JOB_ERROR_REASON_ATTR,
description = BigQueryAttributes.JOB_ERROR_REASON_DESC),
+ @WritesAttribute(attribute =
BigQueryAttributes.JOB_ERROR_LOCATION_ATTR, description =
BigQueryAttributes.JOB_ERROR_LOCATION_DESC)
+})
+
+public class PutBigQueryStream extends AbstractBigQueryProcessor {
+ public static final Relationship REL_ROW_TOO_BIG =
+ new Relationship.Builder().name("row_too_big")
+ .description("FlowFiles are routed to this relationship if
the row size is too big.")
+ .build();
+
+ public static final PropertyDescriptor DATASET = new PropertyDescriptor
+ .Builder().name(BigQueryAttributes.DATASET_ATTR)
+ .displayName("Dataset")
+ .description(BigQueryAttributes.DATASET_DESC)
+ .required(true)
+ .defaultValue("${" + BigQueryAttributes.DATASET_ATTR + "}")
+
.expressionLanguageSupported(ExpressionLanguageScope.FLOWFILE_ATTRIBUTES)
+ .addValidator(StandardValidators.NON_EMPTY_EL_VALIDATOR)
+ .build();
+
+ public static final PropertyDescriptor TABLE_NAME = new
PropertyDescriptor
+ .Builder().name(BigQueryAttributes.TABLE_NAME_ATTR)
+ .displayName("Table Name")
+ .description(BigQueryAttributes.TABLE_NAME_DESC)
+ .required(true)
+ .defaultValue("${" + BigQueryAttributes.TABLE_NAME_ATTR + "}")
+
.expressionLanguageSupported(ExpressionLanguageScope.FLOWFILE_ATTRIBUTES)
+ .addValidator(StandardValidators.NON_EMPTY_EL_VALIDATOR)
+ .build();
+
+ public static final PropertyDescriptor TABLE_SCHEMA = new
PropertyDescriptor
--- End diff --
I think `TABLE_SCHEMA`, `DATASET`, `TABLE_NAME` can be moved to the
`AbstractBigQueryProcessor`
> BigQuery processors
> -------------------
>
> Key: NIFI-4731
> URL: https://issues.apache.org/jira/browse/NIFI-4731
> Project: Apache NiFi
> Issue Type: New Feature
> Components: Extensions
> Reporter: Mikhail Sosonkin
> Priority: Major
>
> NIFI should have processors for putting data into BigQuery (Streaming and
> Batch).
> Initial working processors can be found this repository:
> https://github.com/nologic/nifi/tree/NIFI-4731/nifi-nar-bundles/nifi-gcp-bundle/nifi-gcp-processors/src/main/java/org/apache/nifi/processors/gcp/bigquery
> I'd like to get them into Nifi proper.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
