还没有完成,主要是hive没有配置好。。。。。。。。程序的清洗已经做得差不多了,之前一直有出现数组溢出的情况,主要原因是我还没有理解mapreduce的工作模式。代码如下:
import java.lang.String; import java.io.IOException; import java.util.*; import java.text.SimpleDateFormat; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import org.apache.hadoop.util.GenericOptionsParser; import org.apache.hadoop.io.NullWritable; public class Namecount { public static final SimpleDateFormat FORMAT = new SimpleDateFormat("d/MMM/yyyy:HH:mm:ss", Locale.ENGLISH); //原时间格式 public static final SimpleDateFormat dateformat1 = new SimpleDateFormat("yyyy-MM-dd");//现时间格式 private Date parseDateFormat(String string) { //转换时间格式 Date parse = null; try { parse = FORMAT.parse(string); } catch (Exception e) { e.printStackTrace(); } return parse; } public String[] parse(String line) { public static ArrayList<String> ip = new ArrayList<String>(); public static ArrayList<String> date = new ArrayList<String>(); public static ArrayList<String> day = new ArrayList<String>(); public static ArrayList<Long> traffic = new ArrayList<Long>(); public static ArrayList<String> type = new ArrayList<String>(); public static ArrayList<String> id = new ArrayList<String>(); return new String[] { ip, time, url, status, traffic }; } private String parseTraffic(String line) { //流量 final String trim = line.substring(line.lastIndexOf("\"") + 1) .trim(); String traffic = trim.split(" ")[1]; return traffic; } private String parseStatus(String line) { //状态 final String trim = line.substring(line.lastIndexOf("\"") + 1) .trim(); String status = trim.split(" ")[0]; return status; } private String parseURL(String line) { //url final int first = line.indexOf("\""); final int last = line.lastIndexOf("\""); String url = line.substring(first + 1, last); return url; } private String parseTime(String line) { //时间 final int first = line.indexOf("["); final int last = line.indexOf("+0800]"); String time = line.substring(first + 1, last).trim(); Date date = parseDateFormat(time); return dateformat1.format(date); } private String parseIP(String line) { //ip String ip = line.split("- -")[0].trim(); return ip; } public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> { public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { // 将输入的纯文本文件的数据转化成String Text outputValue = new Text(); String line = value.toString(); Namecount aa=new Namecount(); StringTokenizer tokenizerArticle = new StringTokenizer(line, "\n"); // 分别对每一行进行处理 while (tokenizerArticle.hasMoreElements()) { // 每行按空格划分 String stra=tokenizerArticle.nextToken().toString(); String [] Newstr=aa.parse(stra); if (Newstr[2].startsWith("GET /")) { //过滤开头字符串 Newstr[2] = Newstr[2].substring("GET /".length()); } else if (Newstr[2].startsWith("POST /")) { Newstr[2] = Newstr[2].substring("POST /".length()); } if (Newstr[2].endsWith(" HTTP/1.1")) { //过滤结尾字符串 Newstr[2] = Newstr[2].substring(0, Newstr[2].length() - " HTTP/1.1".length()); } String[] words = Newstr[2].split("/"); if(words.length==4){ outputValue.set(Newstr[0] + "\t" + Newstr[1] + "\t" + words[0]+"\t"+words[1]+"\t"+words[2]+"\t"+words[3]+"\t"+"0"); context.write(outputValue,new IntWritable(1)); } } } } public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> { // 实现reduce函数 public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { int sum = 0; Iterator<IntWritable> iterator = values.iterator(); while (iterator.hasNext()) { sum += iterator.next().get(); } context.write(key, new IntWritable(sum)); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); conf.set("mapred.jar","Namecount.jar"); String[] ioArgs = new String[] { "name", "name_out" }; String[] otherArgs = new GenericOptionsParser(conf, ioArgs).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: Score Average <in> <out>"); System.exit(2); } Job job = new Job(conf, "name_goods_count"); job.setJarByClass(Namecount.class); // 设置Map、Combine和Reduce处理类 job.setMapperClass(Map.class); job.setCombinerClass(Reduce.class); job.setReducerClass(Reduce.class); // 设置输出类型 job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); // 将输入的数据集分割成小数据块splites,提供一个RecordReder的实现 job.setInputFormatClass(TextInputFormat.class); // 提供一个RecordWriter的实现,负责数据输出 job.setOutputFormatClass(TextOutputFormat.class); // 设置输入和输出目录 Path in=new Path("hdfs://localhost:9000/mymapreduce3/123/12345.txt"); Path out=new Path("hdfs://localhost:9000/mymapreduce3/out"); FileInputFormat.addInputPath(job,in); FileOutputFormat.setOutputPath(job,out); }
如此,还有一点小错误,明天应该可以完成生于部分以及导入hive了
原文:https://www.cnblogs.com/jyt123/p/11852158.html