Example usage for org.apache.hadoop.mapred TextInputFormat subclass-usage

Introduction

In this page you can find the example usage for org.apache.hadoop.mapred TextInputFormat subclass-usage.

Usage

From source file BigDataFinal.XmlInputFormat.java

/**
 * Reads records that are delimited by a specifc begin/end tag.
 */
public class XmlInputFormat extends TextInputFormat {

    public static final String START_TAG_KEY = "xmlinput.start";

From source file cascading.clojure.NullByteTextInputFormat.java

public class NullByteTextInputFormat extends TextInputFormat {
    private static final Log log = LogFactory.getLog(NullByteTextInputFormat.class);

    @Override
    public RecordReader<LongWritable, Text> getRecordReader(InputSplit inputSplit, JobConf jobConf,
            Reporter reporter) throws IOException {

From source file cascading.clojure.TaggedInputFormat.java

/**
 * Reads records that are delimited by taginput.start and taginput.end
 */
public class TaggedInputFormat extends TextInputFormat {
    private static final Log log = LogFactory.getLog(TaggedInputFormat.class);

From source file com.dataiku.hive.storage.XMLHiveInputFormat.java

/**
 * Reads records that are delimited by a specfic begin/end tag.
 */
public class XMLHiveInputFormat extends TextInputFormat {

    public static final String TAG_KEY = "xml.tag";

From source file com.hadoop.mapred.DeprecatedLzoTextInputFormat.java

/**
 * This class conforms to the old (org.apache.hadoop.mapred.*) hadoop API style 
 * which is deprecated but still required in places.  Streaming, for example, 
 * does a check that the given input format is a descendant of 
 * org.apache.hadoop.mapred.InputFormat, which any InputFormat-derived class
 * from the new API fails.  In order for streaming to work, you must use

From source file com.ibm.spss.hive.serde2.xml.XmlInputFormat.java

/**
 * Reads records that are delimited by a specific begin/end tag.
 */
public class XmlInputFormat extends TextInputFormat {

    public static final String START_TAG_KEY = "xmlinput.start";

From source file com.pagerank.hadoop.job1.xmlinputformatter.XmlInputFormat.java

/**
 * Reads records that are delimited by a specific begin/end tag.
 */
public class XmlInputFormat extends TextInputFormat {

    public static final String START_TAG_KEY = "xmlinput.start";

From source file com.thinkbiganalytics.inputformat.hadoop.mapred.OmnitureDataFileInputFormat.java

/**
 * A tool for Hadoop eco system that makes it easier to parse Omniture Click Stream data.
 * It consists of custom input format and line reader. Works identically to TextInputFormat except for
 * the fact that it uses a EscapedLineReader which gets around Omniture's pesky escaped tabs and newlines.
 * For more information about format, please refer to Omniture Documentation at
 * https://marketing.adobe.com/resources/help/en_US/sc/clickstream/analytics_clickstream.pdf.

From source file edu.umd.cloud9.collection.XMLInputFormatOld.java

/**
 * A simple {@link org.apache.hadoop.mapred.InputFormat} for XML documents ({@code
 * org.apache.hadoop.mapred} API). The class recognizes begin-of-document and end-of-document tags
 * only: everything between those delimiting tags is returned in an uninterpreted {@code Text}
 * object.
 *

From source file fr.alma.pagerank.job1.XmlInputFormat.java

/**
* Reads records that are delimited by a specific begin/end tag.
*/
public class XmlInputFormat extends TextInputFormat {

    public static final String START_TAG_KEY = "xmlinput.start";