[ 
https://issues.apache.org/jira/browse/HIVE-21240?focusedWorklogId=230307&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-230307
 ]

ASF GitHub Bot logged work on HIVE-21240:
-----------------------------------------

                Author: ASF GitHub Bot
            Created on: 19/Apr/19 23:00
            Start Date: 19/Apr/19 23:00
    Worklog Time Spent: 10m 
      Work Description: b-slim commented on pull request #530: HIVE-21240: JSON 
SerDe Deserialize Re-Write
URL: https://github.com/apache/hive/pull/530#discussion_r277108929
 
 

 ##########
 File path: 
serde/src/java/org/apache/hadoop/hive/serde2/json/HiveJsonReader.java
 ##########
 @@ -0,0 +1,532 @@
+/*
+ * 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.hadoop.hive.serde2.json;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.nio.charset.StandardCharsets;
+import java.time.ZoneId;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.EnumSet;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.Iterator;
+import java.util.LinkedHashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Map.Entry;
+import java.util.Set;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+import org.apache.commons.lang3.tuple.ImmutablePair;
+import org.apache.commons.lang3.tuple.Pair;
+import org.apache.hadoop.hive.common.type.Date;
+import org.apache.hadoop.hive.common.type.HiveChar;
+import org.apache.hadoop.hive.common.type.HiveDecimal;
+import org.apache.hadoop.hive.common.type.HiveVarchar;
+import org.apache.hadoop.hive.common.type.Timestamp;
+import org.apache.hadoop.hive.common.type.TimestampTZ;
+import org.apache.hadoop.hive.serde2.SerDeException;
+import org.apache.hadoop.hive.serde2.objectinspector.ListObjectInspector;
+import org.apache.hadoop.hive.serde2.objectinspector.MapObjectInspector;
+import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
+import org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector;
+import org.apache.hadoop.hive.serde2.objectinspector.StructField;
+import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector;
+import 
org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;
+import org.apache.hadoop.hive.serde2.typeinfo.BaseCharTypeInfo;
+import org.apache.hadoop.hive.serde2.typeinfo.PrimitiveTypeInfo;
+import org.apache.hadoop.hive.serde2.typeinfo.TimestampLocalTZTypeInfo;
+import org.apache.hive.common.util.TimestampParser;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.fasterxml.jackson.databind.JsonNode;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.fasterxml.jackson.databind.node.JsonNodeType;
+import com.fasterxml.jackson.databind.node.TextNode;
+import com.google.common.base.Preconditions;
+
+/**
+ * This class converts JSON strings into Java or Hive Primitive objects.
+ *
+ * Support types are:<br/>
+ * <br/>
+ * <table border="1">
+ * <tr>
+ * <th>JSON Type</th>
+ * <th>Java Type</th>
+ * <th>Notes</th>
+ * </tr>
+ * <tr>
+ * <td>Object</td>
+ * <td>java.util.List</td>
+ * <td>Each element may be different type
+ * </tr>
+ * <tr>
+ * <td>Array</td>
+ * <td>java.util.List</td>
+ * <td>Each element is same type</td>
+ * </tr>
+ * <tr>
+ * <td>Map</td>
+ * <td>java.util.Map</td>
+ * <td>Keys must be same primitive type; every value is the same type</td>
+ * </tr>
+ * </table>
+ */
+public class HiveJsonReader {
+
+  private static final Logger LOG =
+      LoggerFactory.getLogger(HiveJsonReader.class);
+
+  private final Map<Pair<StructObjectInspector, String>, StructField> 
discoveredFields =
+      new HashMap<>();
+
+  private final Set<Pair<StructObjectInspector, String>> 
discoveredUnknownFields =
+      new HashSet<>();
+
+  private final EnumSet<Feature> features = EnumSet.noneOf(Feature.class);
+
+  private final ObjectMapper objectMapper;
+
+  private final TimestampParser tsParser;
+  private BinaryEncoding binaryEncoding;
+  private final ObjectInspector oi;
+
+  /**
+   * Enumeration that defines all on/off features for this reader.
+   */
+  public enum Feature {
+    COL_INDEX_PARSING, PRIMITIVE_TO_WRITABLE, IGNORE_UKNOWN_FIELDS
+  }
+
+  /**
+   * Constructor with default the Hive default timestamp parser.
+   *
+   * @param oi ObjectInspector for all the fields in the JSON object
+   */
+  public HiveJsonReader(ObjectInspector oi) {
+    this(oi, new TimestampParser());
+  }
+
+  /**
+   * Constructor with default the Hive default timestamp parser.
+   *
+   * @param oi ObjectInspector info for all the fields in the JSON object
+   * @param tsParser Custom timestamp parser
+   */
+  public HiveJsonReader(ObjectInspector oi, TimestampParser tsParser) {
+    this.binaryEncoding = BinaryEncoding.BASE64;
+    this.tsParser = tsParser;
+    this.oi = oi;
+    this.objectMapper = new ObjectMapper();
+  }
+
+  /**
+   * Parse text containing a complete JSON object.
+   *
+   * @param text The text to parse
+   * @return A List of Objects, one for each field in the JSON object
+   * @throws IOException Unable to parse the JSON text
+   * @throws SerDeException The SerDe is not configured correctly
+   */
+  public Object parseStruct(final String text)
+      throws IOException, SerDeException {
+    Preconditions.checkNotNull(text);
+    Preconditions.checkState(this.oi != null);
+    final JsonNode rootNode = this.objectMapper.reader().readTree(text);
+    return visitNode(rootNode, this.oi);
+  }
+
+  /**
+   * Parse text containing a complete JSON object.
+   *
+   * @param in The InputStream to read the text from
+   * @return A List of Objects, one for each field in the JSON object
+   * @throws IOException Unable to parse the JSON text
+   * @throws SerDeException The SerDe is not configured correctly
+   */
+  public Object parseStruct(final InputStream in)
+      throws IOException, SerDeException {
+    Preconditions.checkNotNull(in);
+    Preconditions.checkState(this.oi != null);
+    final JsonNode rootNode = this.objectMapper.reader().readTree(in);
+    return visitNode(rootNode, this.oi);
+  }
+
+  /**
+   * Visit a node and parse it based on the provided ObjectInspector.
+   *
+   * @param rootNode The root node to process
+   * @param oi The ObjectInspector to use
+   * @return The value in this node (may be a complex type if nested)
 
 Review comment:
   seems like this can return null, can you add annotation plus explanation 
what null means ?
 
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


Issue Time Tracking
-------------------

    Worklog Id:     (was: 230307)
    Time Spent: 1h 20m  (was: 1h 10m)

> JSON SerDe Re-Write
> -------------------
>
>                 Key: HIVE-21240
>                 URL: https://issues.apache.org/jira/browse/HIVE-21240
>             Project: Hive
>          Issue Type: Improvement
>          Components: Serializers/Deserializers
>    Affects Versions: 4.0.0, 3.1.1
>            Reporter: David Mollitor
>            Assignee: David Mollitor
>            Priority: Major
>              Labels: pull-request-available
>             Fix For: 4.0.0
>
>         Attachments: HIVE-21240.1.patch, HIVE-21240.1.patch, 
> HIVE-21240.10.patch, HIVE-21240.11.patch, HIVE-21240.11.patch, 
> HIVE-21240.11.patch, HIVE-21240.11.patch, HIVE-21240.2.patch, 
> HIVE-21240.3.patch, HIVE-21240.4.patch, HIVE-21240.5.patch, 
> HIVE-21240.6.patch, HIVE-21240.7.patch, HIVE-21240.9.patch, 
> HIVE-24240.8.patch, kafka_storage_handler.diff
>
>          Time Spent: 1h 20m
>  Remaining Estimate: 0h
>
> The JSON SerDe has a few issues, I will link them to this JIRA.
> * Use Jackson Tree parser instead of manually parsing
> * Added support for base-64 encoded data (the expected format when using JSON)
> * Added support to skip blank lines (returns all columns as null values)
> * Current JSON parser accepts, but does not apply, custom timestamp formats 
> in most cases
> * Added some unit tests
> * Added cache for column-name to column-index searches, currently O\(n\) for 
> each row processed, for each column in the row



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

Reply via email to