hawq-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From tzolov <...@git.apache.org>
Subject [GitHub] incubator-hawq pull request: HAWQ-178: Add JSON plugin support in ...
Date Tue, 02 Feb 2016 02:10:06 GMT
Github user tzolov commented on a diff in the pull request:

    https://github.com/apache/incubator-hawq/pull/302#discussion_r51513424
  
    --- Diff: pxf/pxf-json/src/main/java/org/apache/hawq/pxf/plugins/json/JsonRecordReader.java
---
    @@ -0,0 +1,166 @@
    +package org.apache.hawq.pxf.plugins.json;
    +
    +/*
    + * 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.
    + */
    +
    +import static org.apache.commons.lang3.StringUtils.isEmpty;
    +
    +import java.io.BufferedInputStream;
    +import java.io.IOException;
    +import java.security.InvalidParameterException;
    +
    +import org.apache.commons.logging.Log;
    +import org.apache.commons.logging.LogFactory;
    +import org.apache.hadoop.fs.FSDataInputStream;
    +import org.apache.hadoop.fs.FileSystem;
    +import org.apache.hadoop.fs.Path;
    +import org.apache.hadoop.io.LongWritable;
    +import org.apache.hadoop.io.Text;
    +import org.apache.hadoop.mapred.FileSplit;
    +import org.apache.hadoop.mapred.JobConf;
    +import org.apache.hadoop.mapred.RecordReader;
    +import org.apache.hawq.pxf.api.Fragment;
    +
    +/**
    + * {@link RecordReader} implementation that can read multiline JSON objects.
    + */
    +public class JsonRecordReader implements RecordReader<LongWritable, Text> {
    +
    +	private static final Log LOG = LogFactory.getLog(JsonRecordReader.class);
    +
    +	public static final String RECORD_IDENTIFIER = "json.input.format.record.identifier";
    +
    +	private JsonStreamReader streamReader = null;
    +	private long start = 0, end = 0;
    +	private float toRead = 0;
    +	private String identifier = null;
    +
    +	/**
    +	 * @param conf
    +	 *            Hadoop context
    +	 * @param split
    +	 *            HDFS Split as defined by the {@link Fragment}.
    +	 * @throws IOException
    +	 */
    +	public JsonRecordReader(JobConf conf, FileSplit split) throws IOException {
    +		LOG.debug("JsonRecordReader constructor called.  Conf is " + conf + ". Split is " +
split);
    +		this.identifier = conf.get(RECORD_IDENTIFIER);
    +		LOG.debug("Identifier is " + this.identifier);
    +
    +		if (isEmpty(this.identifier)) {
    +			throw new InvalidParameterException(RECORD_IDENTIFIER + " is not set.");
    +		} else {
    +			LOG.debug("Initializing JsonRecordReader with identifier " + identifier);
    +		}
    +
    +		// get relevant data
    +		Path file = split.getPath();
    +
    +		LOG.debug("File is " + file);
    +
    +		start = split.getStart();
    +		end = start + split.getLength();
    +		toRead = end - start;
    +		LOG.debug("FileSystem is " + FileSystem.get(conf));
    +
    +		FSDataInputStream strm = FileSystem.get(conf).open(file);
    +
    +		LOG.debug("Retrieved file stream ");
    +
    +		if (start != 0) {
    +			strm.seek(start);
    +		}
    +
    +		streamReader = new JsonStreamReader(identifier, new BufferedInputStream(strm));
    +
    +		LOG.debug("Reader is " + streamReader);
    +	}
    +
    +	/*
    +	 * {@inheritDoc}
    +	 */
    +	@Override
    +	public boolean next(LongWritable key, Text value) throws IOException {
    +
    +		boolean retval = false;
    +		boolean keepGoing = false;
    +		do {
    +			// Exit condition (end of block/file)
    +			if (streamReader.getBytesRead() >= (end - start)) {
    +				return false;
    +			}
    +
    +			keepGoing = false;
    +			String record = streamReader.getJsonRecord();
    +			if (record != null) {
    +				if (JsonUtil.decodeLineToJsonNode(record) == null) {
    --- End diff --
    
    Did this and removed the JsonUtil all together. Parsing logic is moved directly in the
resolver. Also i think it is better to log an error in case of malformed json object but to
continue the processing (e.g. no exception is thrown)


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

Mime
View raw message