[
https://issues.apache.org/jira/browse/FLINK-7243?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16691978#comment-16691978
]
ASF GitHub Bot commented on FLINK-7243:
---------------------------------------
fhueske commented on a change in pull request #6483:
[FLINK-7243][flink-formats] Add parquet input format
URL: https://github.com/apache/flink/pull/6483#discussion_r234608920
##########
File path:
flink-formats/flink-parquet/src/main/java/org/apache/flink/formats/parquet/ParquetRowInputFormat.java
##########
@@ -0,0 +1,87 @@
+/*
+ * 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.flink.formats.parquet;
+
+import org.apache.flink.api.common.typeinfo.SqlTimeTypeInfo;
+import org.apache.flink.api.common.typeinfo.TypeInformation;
+import org.apache.flink.api.java.typeutils.ResultTypeQueryable;
+import org.apache.flink.api.java.typeutils.RowTypeInfo;
+import org.apache.flink.core.fs.Path;
+import org.apache.flink.types.Row;
+
+import org.apache.parquet.schema.MessageType;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.sql.Timestamp;
+
+
+/**
+ * A subclass of {@link ParquetInputFormat} to read from Parquet files and
convert to {@link Row}.
+ * It is mainly used to integrate with table API and batch SQL.
+ */
+public class ParquetRowInputFormat extends ParquetInputFormat<Row> implements
ResultTypeQueryable<Row> {
+ private static final long serialVersionUID = 11L;
+ private static final Logger LOG =
LoggerFactory.getLogger(ParquetRowInputFormat.class);
+ private boolean timeStampRewrite;
+ private RowTypeInfo returnType;
+ private int tsIndex;
+
+ public ParquetRowInputFormat(Path path, MessageType messageType) {
+ super(path, messageType);
+ this.returnType = new RowTypeInfo(getFieldTypes(),
getFieldNames());
+ this.timeStampRewrite = false;
+ }
+
+ @Override
+ public TypeInformation<Row> getProducedType() {
+ return new RowTypeInfo(getFieldTypes(), getFieldNames());
+ }
+
+ @Override
+ protected Row convert(Row row) {
+ if (timeStampRewrite) {
+ row.setField(tsIndex, new Timestamp((long)
row.getField(tsIndex)));
+ }
+ return row;
+ }
+
+ /**
+ * Convert long or double field in parquet schema to
SqlTimeTypeInfo.TIMESTAMP, so that the row return can
+ * be directly used for window aggregation in table API. Rewrite the
time stamp field needs to come with
+ * overriding the convert function.
+
+ * @param fieldName the field needs to change to TIMESTAMP type
+ */
+ public void rewriteTimeStampField(String fieldName) {
+ this.tsIndex = returnType.getFieldIndex(fieldName);
+ if (tsIndex == -1) {
+ throw new RuntimeException(String.format("Fail to
extract timestamp field for row schema: [%s]",
+ returnType.toString()));
+ }
+
Review comment:
Add a check that the found field is actually of type `long` or `double`
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
> Add ParquetInputFormat
> ----------------------
>
> Key: FLINK-7243
> URL: https://issues.apache.org/jira/browse/FLINK-7243
> Project: Flink
> Issue Type: Sub-task
> Components: Table API & SQL
> Reporter: godfrey he
> Assignee: Zhenqiu Huang
> Priority: Major
> Labels: pull-request-available
>
> Add a {{ParquetInputFormat}} to read data from a Apache Parquet file.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
