hive UDAF之cube
程序员文章站
2022-05-23 15:05:31
...
之前有想实现在hadoop上面自动cube,并计算同比的自动化解决方法。过考虑用UDAF去做但是一直没有去实现,最近项目中需要根据配置自动聚合生成数据,目标结果表格式固定,正好满足自动cube的场景,所以就搞了个demo,还在测试中
package com.taobao.voc.hive.udf; /** * description :对传入的多个维度的所有组合所对应的度量进行汇总 * @param :dim1,dim2 [... ,dim10] , '度量1,度量2,...度量N ' * @return : 返回一个数组,数组的每一个成员即一条返回记录,顺序与输入参数位置一一对应 * @comment :目前的多个度量需要拼成一个字符串,用逗号做分隔符,且是整数 * @author : 松坡 * @version : 1.0 */ import java.util.ArrayList; import java.util.HashMap; import java.util.Map; import org.apache.hadoop.hive.ql.exec.UDAF; import org.apache.hadoop.hive.ql.exec.UDAFEvaluator; public class SumCube extends UDAF { public static class Evaluator implements UDAFEvaluator { private boolean mEmpty; private double mSum; private Long mcount; private ArrayList<String> dim_list = new ArrayList<String>(); private String split_str = "_"; private String sub_split_str = ","; private Map<String, String> hm_out = new HashMap<String, String>(); private Map<String, String> hm_ret = new HashMap<String, String>(); private String[] dim_array; private static int dim_num = 0; private ArrayList<String> ret_al=new ArrayList<String>(); public Evaluator() { super(); init(); } public void init() { mSum = 0; mcount = new Long(0); mEmpty = true; } public static String getAddStr(String src_old, String src_new) { String ret_str = ""; if (src_old == null || src_old.equals("")) { ret_str = src_new; } else { String[] l_old = src_old.split(","); String[] l_new = src_new.split(","); for (int i = 0; i < src_new.split(",").length; i++) { ret_str = ret_str + (Long.parseLong(l_old[i]) + Long .parseLong(l_new[i])) + ","; } ret_str = ret_str.substring(0, ret_str.length() - 1); } return ret_str; } public boolean iterate(String... args) { String in_num = ""; if (args.length > 0) { in_num = args[args.length - 1];//最后一位是需要聚集的参数 dim_array = new String[args.length - 1]; dim_num = args.length - 1; //将字段保存到数组中 for (int a = 0; a < args.length - 1; a++) { dim_array[a] = args[a]; } // dim_array = dim.split(sub_split_str); } //拼接纬度 if (mcount == 0) { StringBuffer sb_tmp = new StringBuffer(); for (int i = 0; i < dim_array.length; i++) { sb_tmp.append(i).append(sub_split_str); } String dim_src = sb_tmp.toString(); dim_list = getDim(dim_src.substring(0, dim_src.length() - 1)); } for (int i = 0; i < dim_list.size(); i++) { StringBuffer sb_tmp_1 = new StringBuffer(); String dim_cube = ""; int num1 = 0; if (dim_list.get(i).contains("ALL")) { sb_tmp_1.append("ALL").append(split_str); } else { sb_tmp_1.append(dim_list.get(i)).append(split_str); for (int j = 0; j < dim_list.get(i).length(); j++) { num1 = Integer.parseInt(dim_list.get(i).substring(j, j + 1)); sb_tmp_1.append(dim_array[num1]).append(sub_split_str); } } dim_cube = sb_tmp_1.toString().substring(0, sb_tmp_1.toString().length() - 1); if (hm_out.containsKey(dim_cube)) { hm_out.put(dim_cube, getAddStr(hm_out.get(dim_cube), in_num)); } else { hm_out.put(dim_cube, in_num); } } mcount++; return true; } public Map<String, String> terminatePartial() { Map<String, String> hm_ext = new HashMap<String,String>(); for (Map.Entry<String, String> entry : hm_out.entrySet()) { String key = entry.getKey().toString(); String val = entry.getValue().toString(); String v=getSrcDim(key,dim_num); hm_ext.put(v, val); } return hm_ext; } public boolean merge(Map<String, String> hm_merge) { for (Map.Entry<String, String> entry : hm_merge.entrySet()) { String key = entry.getKey().toString(); String value = entry.getValue().toString(); if (hm_ret.containsKey(key)) { hm_ret.put(key, getAddStr(hm_ret.get(key), value)); } else { hm_ret.put(key, value); } } return true; } public ArrayList<String> terminate() { for (Map.Entry<String, String> entry : hm_ret.entrySet()) { String key = entry.getKey().toString(); String val = entry.getValue().toString(); ret_al.add(key+val); } return ret_al; } public ArrayList<String> getDim(String dim_src) { String src_in = dim_src; String[] src_in_array = src_in.split(","); ArrayList<String> src_out_array = new ArrayList<String>(); String slipt_str = ","; int j = 0; int flag = 0; int flag2 = 0; String tmp_new = ""; String[] last_item_arry = null; StringBuffer tmp_sb = new StringBuffer(); for (int i = 0; i < src_in_array.length; i++) { tmp_sb = new StringBuffer(); j = i; if (i == 0) { while (j < src_in_array.length) { tmp_sb.append(src_in_array[j]).append(slipt_str); j++; continue; } } else { for (int k = 0; k < last_item_arry.length; k++) { for (int l = k; l < src_in_array.length; l++) { if (last_item_arry[k].contains(src_in_array[l])) { continue; } else { for (int f = 0; f < tmp_sb.toString().split( slipt_str).length; f++) { tmp_new = last_item_arry[k] .concat(src_in_array[l]); flag = 0; for (int d = 0; d < tmp_new.length(); d++) { if (tmp_sb.toString().split(slipt_str)[f] .contains(tmp_new.substring(d, d + 1))) { flag++; flag2 = 1; } } if (flag == tmp_new.length()) { flag2 = flag; break; } } if (flag <= i && flag2 < tmp_new.length()) { tmp_sb.append(last_item_arry[k]) .append(src_in_array[l]) .append(slipt_str); } else { flag2 = 1; } } } } } src_out_array.add(tmp_sb.toString()); last_item_arry = tmp_sb.toString().split(slipt_str); } ArrayList<String> out_array = new ArrayList<String>(); String tmp_str = ""; for (int e = 0; e < src_out_array.size(); e++) { tmp_str = src_out_array.get(e).toString(); for (int w = 0; w < tmp_str.split(slipt_str).length; w++) { out_array.add(tmp_str.split(slipt_str)[w].toString()); } } out_array.add("ALL"); return out_array; } public static String getSrcDim(String arg, int num) { String ret = ""; String tmp1 = ""; String[] tmp2 = new String[1]; String[] tmp3= new String[num]; for(int r1=0;r1<num;r1++){ tmp3[r1]="all"; } if ((!arg.contains("ALL")) ) { tmp1 = arg.split("_")[0]; tmp2= arg.split("_")[1].split(","); int tmp_f=0; for (int r2 = 0; r2 < tmp1.length(); r2++) { tmp_f=(int)tmp1.charAt(r2)-48; tmp3[tmp_f] = tmp2[r2]; } } for(int r3=0;r3<num;r3++){ ret=ret+tmp3[r3]+","; } return ret; } } }
推荐阅读
-
阿里云大数据利器Maxcompute学习之-假如你使用过hive 大数据;云计算
-
【四】hive DDL之create/drop/truncate table
-
【Hive】Apache Hive系列之Hive中表的操作
-
Flink DataStream之Kafka数据写入HDFS,并分区到Hive
-
Flink集成Hive之Hive Catalog与Hive Dialect--以Flink1.12为例
-
hive 中 json 字符串解析之 get_json_object 与 json_tuple
-
大数据测试之Hive和Hbase讲解
-
大数据BigData之Hive load外部数据时做了些什么?
-
大数据BigData之 hive command line 如何 debug?
-
大数据BigData之如何配置hive连接mysql,把mysql作为元数据库?