jnatkins

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>

  <!-- Replace the group ID with your group ID -->
  <groupId>com.mycompany.hadoopproject</groupId>
  <!-- Replace the artifact ID with the name of your project -->
  <artifactId>my-hadoop-project</artifactId>
  <version>1.0-SNAPSHOT</version>
  <packaging>jar</packaging>

jnatkins

{
   "retweeted_status": {
      "contributors": null,
      "text": "#Crowdsourcing – drivers already generate traffic data for your smartphone to suggest alternative routes when a road is clogged. #bigdata",
      "geo": null,
      "retweeted": false,
      "in_reply_to_screen_name": null,
      "truncated": false,
      "entities": {
         "urls": [],

jnatkins

created_at                        entities                                                                                                                 text                                                                                                                                            user
Mon Sep 10 21:19:23 +0000 2012    {"urls":[],"user_mentions":[{"screen_name":"ScottOstby","name":"Scott Ostby"}],"hashtags":[{"text":"Crowdsourcing"}]}    RT @ScottOstby: #Crowdsourcing – drivers already generate traffic data for your smartphone to suggest alternative routes when a road is  ...    {"screen_name":"ParvezJugon","name":"Parvez Jugon","friends_count":299,"followers_count":70,"statuses_count":1294,"verified":false,"utc_offset":null,"time_zone":null}

jnatkins

package com.cloudera.nile.etl;

import java.io.IOException;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Iterator;
import java.util.TimeZone;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

jnatkins

package org.kiji.examples.importers;

import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.util.Bytes;

jnatkins

package org.kiji.examples.importers;

import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Delete;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Put;