hive映射Elasticsearch时间date类型问题

Posted 2022-12-06 上官沐雪

hive映射Elasticsearch时间date类型问题

hive映射es时间date类型出现问题，需要自定义类读取时间类型，如下：

1.建立hive与es映射表

CREATE EXTERNAL TABLE `hive_es_dt_basic4_20210724_02`(
  `id` string COMMENT 'from deserializer', 
  `country` string COMMENT 'from deserializer', 
  `regstatus` string COMMENT 'from deserializer', 
  `districtcode` string COMMENT 'from deserializer', 
  `opfrom` string COMMENT 'from deserializer', 
  `taxpayeridentifynum` string COMMENT 'from deserializer', 
  `brief` string COMMENT 'from deserializer', 
  `address` string COMMENT 'from deserializer', 
  `brands` string COMMENT 'from deserializer', 
  `updateTime` TIMESTAMP COMMENT 'from deserializer',
  `dataSources` int COMMENT 'from deserializer')
ROW FORMAT SERDE 
  'org.elasticsearch.hadoop.hive.EsSerDe' 
STORED BY 
  'org.elasticsearch.hadoop.hive.EsStorageHandler' 
WITH SERDEPROPERTIES ( 
  'serialization.format'='1')
TBLPROPERTIES (
  'es.index.auto.create'='false', 
  'es.mapping.id'='id', 
'es.mapping.names'='country:country,regStatus:regStatus,districtCode:districtCode,regCapital:regCapital,city:city,emailList:emailList,cityCode:cityCode,regOrg:regOrg,location:location,registerNum:registerNum,smallIndustryCode:smallIndustryCode,from:from,size:size,shortName:shortName,tmName:tmName,bigIndustryCode:bigIndustryCode,provinceCode:provinceCode,createTime:createTime,updateTime:updateTime,dataSources:dataSources', 
  'es.nodes'='ip1,ip2,ip3,ip4,ip5', 
  'es.port'='9200', 
  'es.read.metadata'='true', 
  'es.read.metadata.field'='_metadata', 
  'es.resource'='dt_basic4/dt_basic', 
  'last_modified_by'='root', 
  'es.date.format'='yyyy-MM-dd HH:mm:ss',
  'es.ser.reader.value.class'='com.zhendao.MyESReader',
  'last_modified_time'='1617801697', 
  'transient_lastDdlTime'='1617801697');

参数：
‘es.date.format’=‘yyyy-MM-dd HH:mm:ss’ 定义数据类型格式
‘es.ser.reader.value.class’=‘com.zhendao.MyESReader’ 用自定义类读取es

2.自定义com.zhendao.MyESReader类

package com.zhendao;

import org.apache.hadoop.hive.serde2.io.TimestampWritable;
import org.elasticsearch.hadoop.cfg.Settings;
import org.elasticsearch.hadoop.hive.HiveValueReader;

import javax.xml.bind.DatatypeConverter;
import java.sql.Timestamp;
import java.text.ParseException;
import java.text.ParsePosition;
import java.text.SimpleDateFormat;
import java.util.Date;

public class MyESReader extends HiveValueReader 


    private String dateFormat;
    private static final String DEFALUT_DATE_FORMAT = "yyyy-MM-dd HH:mm:ss";

    @Override
    public void setSettings(Settings settings) 
        super.setSettings(settings);
        dateFormat = settings.getProperty("es.date.format");
    

    @Override
    protected Object parseDate(String value, boolean richDate) 
        if (value != null && value.trim().length() > 11 && DEFALUT_DATE_FORMAT.equalsIgnoreCase(dateFormat)) 
            return (richDate ? new TimestampWritable(new Timestamp(parseDate(value,
                    DEFALUT_DATE_FORMAT).getTime())) : parseString(value));
        
        /**如果没有设置日期格式，通过默认的方式支持，以避免使用新的ValueReader后影响到其它的外部表**/
        return super.parseDate(value, richDate);
    


    private static Date parseDate(String stringDate, String format) 
        if (stringDate == null) 
            return null;
        
        try 
            return parseDate(stringDate, new String[]format);
         catch (ParseException e) 
            return null;
        
    

    public static Date parseDate(String str, String... parsePatterns) throws ParseException 
        return parseDateWithLeniency(str, parsePatterns, true);
    

    private static Date parseDateWithLeniency(
            String str, String[] parsePatterns, boolean lenient) throws ParseException 
        if (str == null || parsePatterns == null) 
            throw new IllegalArgumentException("Date and Patterns must not be null");
        

        SimpleDateFormat parser = new SimpleDateFormat();
        parser.setLenient(lenient);
        ParsePosition pos = new ParsePosition(0);
        for (String parsePattern : parsePatterns) 

            String pattern = parsePattern;

            // LANG-530 - need to make sure 'ZZ' output doesn't get passed to SimpleDateFormat
            if (parsePattern.endsWith("ZZ")) 
                pattern = pattern.substring(0, pattern.length() - 1);
            

            parser.applyPattern(pattern);
            pos.setIndex(0);

            String str2 = str;
            // LANG-530 - need to make sure 'ZZ' output doesn't hit SimpleDateFormat as it will ParseException
            if (parsePattern.endsWith("ZZ")) 
                str2 = str.replaceAll("([-+][0-9][0-9]):([0-9][0-9])$", "$1$2");
            

            Date date = parser.parse(str2, pos);
            if (date != null && pos.getIndex() == str2.length()) 
                return date;
            
        
        throw new ParseException("读取错误: " + str, -1);
    

pom依赖

 <dependencies>
        <dependency>
            <groupId>org.elasticsearch</groupId>
            <artifactId>elasticsearch-hadoop</artifactId>
            <version>6.3.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-exec</artifactId>
            <version>1.2.1</version>
            <exclusions>
                <exclusion>
                    <groupId>org.pentaho</groupId>
                    <artifactId>pentaho-aggdesigner-algorithm</artifactId>
                </exclusion>
            </exclusions>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.4</version>
        </dependency>
    </dependencies>