Spring batch 在SpringBatch中,如何在ItemReader之后处理逻辑上相关的行? 脚本
为了简单起见,假设我有一个ItemReader,它返回我25行Spring batch 在SpringBatch中,如何在ItemReader之后处理逻辑上相关的行? 脚本,spring-batch,Spring Batch,为了简单起见,假设我有一个ItemReader,它返回我25行 前10行属于学生A 接下来的5个属于学生B 剩下的10个属于学生C 我想将它们逻辑地聚合在一起,比如说通过studentId,然后将它们展平,最终每个学生一行。 问题 如果我理解正确,将提交间隔设置为5将执行以下操作: 将5行发送给处理器(处理器将聚合它们或执行我告诉它的任何业务逻辑) 处理后将写入5行 然后,它将在接下来的5行中再次执行此操作,以此类推 如果这是真的,那么在接下来的五年中,我将不得不检查已经编写的代码,将它们汇总到
<?xml version="1.0" encoding="UTF-8"?>
<beans xmlns="http://www.springframework.org/schema/beans"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:batch="http://www.springframework.org/schema/batch"
xsi:schemaLocation="http://www.springframework.org/schema/batch http://www.springframework.org/schema/batch/spring-batch-2.1.xsd
http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans-3.0.xsd">
<description>Example job to get you started. It provides a skeleton for a typical batch application.</description>
<batch:job id="job1">
<batch:step id="step1" >
<batch:tasklet transaction-manager="transactionManager" start-limit="100" >
<batch:chunk reader="attendanceItemReader"
processor="attendanceProcessor"
writer="attendanceItemWriter"
commit-interval="10"
/>
</batch:tasklet>
</batch:step>
</batch:job>
<bean id="attendanceItemReader" class="org.springframework.batch.item.database.JdbcCursorItemReader">
<property name="dataSource">
<ref bean="sourceDataSource"/>
</property>
<property name="sql"
value="select s.student_name ,s.student_id ,fas.attendance_days ,fas.attendance_value from K12INTEL_DW.ftbl_attendance_stumonabssum fas inner join k12intel_dw.dtbl_students s on fas.student_key = s.student_key inner join K12INTEL_DW.dtbl_schools ds on fas.school_key = ds.school_key inner join k12intel_dw.dtbl_school_dates dsd on fas.school_dates_key = dsd.school_dates_key where dsd.rolling_local_school_yr_number = 0 and ds.school_code = ? and s.student_activity_indicator = 'Active' and fas.LOCAL_GRADING_PERIOD = 'G1' and s.student_current_grade_level = 'Gr 9' order by s.student_id"/>
<property name="preparedStatementSetter" ref="attendanceStatementSetter"/>
<property name="rowMapper" ref="attendanceRowMapper"/>
</bean>
<bean id="attendanceStatementSetter" class="edu.kdc.visioncards.preparedstatements.AttendanceStatementSetter"/>
<bean id="attendanceRowMapper" class="edu.kdc.visioncards.rowmapper.AttendanceRowMapper"/>
<bean id="attendanceProcessor" class="edu.kdc.visioncards.AttendanceProcessor" />
<bean id="attendanceItemWriter" class="org.springframework.batch.item.file.FlatFileItemWriter">
<property name="resource" value="file:target/outputs/passthrough.txt"/>
<property name="lineAggregator">
<bean class="org.springframework.batch.item.file.transform.PassThroughLineAggregator" />
</property>
</bean>
</beans>
还有一个划船制图器
package edu.kdc.visioncards.rowmapper;
import java.sql.ResultSet;
import java.sql.SQLException;
import org.springframework.jdbc.core.RowMapper;
import edu.kdc.visioncards.dto.AttendanceDTO;
public class AttendanceRowMapper<T> implements RowMapper<AttendanceDTO> {
public static final String STUDENT_NAME = "STUDENT_NAME";
public static final String STUDENT_ID = "STUDENT_ID";
public static final String ATTENDANCE_DAYS = "ATTENDANCE_DAYS";
public static final String ATTENDANCE_VALUE = "ATTENDANCE_VALUE";
public AttendanceDTO mapRow(ResultSet rs, int rowNum) throws SQLException {
AttendanceDTO dto = new AttendanceDTO();
dto.setStudentId(rs.getString(STUDENT_ID));
dto.setStudentName(rs.getString(STUDENT_NAME));
dto.setAttDays(rs.getInt(ATTENDANCE_DAYS));
dto.setAttValue(rs.getInt(ATTENDANCE_VALUE));
return dto;
}
}
包edu.kdc.visioncards.rowmapper;
导入java.sql.ResultSet;
导入java.sql.SQLException;
导入org.springframework.jdbc.core.RowMapper;
导入edu.kdc.visioncards.dto.AttendanceDTO;
公共类owmapper实现了RowMapper{
公共静态最终字符串STUDENT\u NAME=“STUDENT\u NAME”;
公共静态最终字符串STUDENT\u ID=“STUDENT\u ID”;
公共静态最终字符串考勤天数=“考勤天数”;
公共静态最终字符串考勤值=“考勤值”;
公共AttendanceDTO mapRow(结果集rs,int rowNum)引发SQLException{
AttendanceDTO dto=新AttendanceDTO();
dto.setStudentId(rs.getString(STUDENT_ID));
dto.setStudentName(rs.getString(学生名称));
dto.setAttDays(rs.getInt(出勤日));
dto.setAttValue(rs.getInt(考勤值));
返回dto;
}
}
我的处理器
package edu.kdc.visioncards;
import java.util.HashMap;
import java.util.Map;
import org.springframework.batch.item.ItemProcessor;
import edu.kdc.visioncards.dto.AttendanceDTO;
public class AttendanceProcessor implements ItemProcessor<AttendanceDTO, Map<Integer, AttendanceDTO>> {
private Map<Integer, AttendanceDTO> map = new HashMap<Integer, AttendanceDTO>();
public Map<Integer, AttendanceDTO> process(AttendanceDTO dto) throws Exception {
if(map.containsKey(new Integer(dto.getStudentId()))){
AttendanceDTO attDto = (AttendanceDTO)map.get(new Integer(dto.getStudentId()));
attDto.setAttDays(attDto.getAttDays() + dto.getAttDays());
attDto.setAttValue(attDto.getAttValue() + dto.getAttValue());
}else{
map.put(new Integer(dto.getStudentId()), dto);
}
return map;
}
}
包edu.kdc.visioncards;
导入java.util.HashMap;
导入java.util.Map;
导入org.springframework.batch.item.ItemProcessor;
导入edu.kdc.visioncards.dto.AttendanceDTO;
公共类AttendanceProcessor实现ItemProcessor{
私有映射映射=新的HashMap();
公共映射进程(AttendanceDTO dto)引发异常{
if(map.containsKey(新整数(dto.getStudentId())){
AttendanceDTO attDto=(AttendanceDTO)map.get(新整数(dto.getStudentId());
attDto.setAttDays(attDto.getAttDays()+dto.getAttDays());
attDto.setAttValue(attDto.getAttValue()+dto.getAttValue());
}否则{
put(新整数(dto.getStudentId()),dto);
}
返回图;
}
}
我对上面代码的关注
在处理器中,我创建了一个HashMap,在处理行时,我检查映射中是否已经有该学生,如果没有,我将其添加。如果它已经在那里,我抓取它,得到我感兴趣的值,并将它们添加到我当前正在处理的行中
之后,Spring批处理框架根据我的配置写入一个文件
我的问题如下:
基本上,您讨论的是具有更改ID(1)的批处理,其中批处理必须跟踪更改 对于spring/spring批次,我们讨论:
- ItemWriter,用于检查项目列表中的id更改
- 更改前,项目存储在临时数据存储(2)(列表、地图等)中,不会被写出
- 当id更改时,聚合/扁平化业务代码在数据存储中的项目上运行,并且应该写入一个项目,现在数据存储可以用于具有下一个id的下一个项目
- 这个概念需要一个阅读器,它告诉步骤“我筋疲力尽”,以便正确地刷新项目末尾(文件/数据库)上的临时数据存储
@覆盖
因为你改变了你的问题,我添加了一个新的答案
如果学生已排序,则不需要列表/映射,您可以在处理器上仅使用一个studentObject来保持“当前”并在其上聚合,直到有一个新的(读取:id更改)
如果学生没有被排序,你将永远不知道某个特定的学生何时“完成”,你将不得不把所有的学生放在一张地图上,直到完整的阅读顺序结束后才能写
注意:
- 处理器需要知道读卡器何时耗尽
- 任何提交率和“id”概念都很难让它正常工作如果你聚合的项目在某种程度上是相同的,那么处理器就无法知道当前处理的项目是否是最后一个
- 基本上,用例要么在读者级别完全解决,要么在作者级别解决(参见其他答案)
private SimpleItem currentItem;
私人分步执行分步执行;
@凌驾
公共SimpleItem进程(SimpleItem newItem)引发异常{
SimpleItem returnItem=null;
如果(currentItem==null){
currentItem=newSimpleItem(newItem.getId(),newItem.getValue());
}else if(currentItem.getId()==new
package edu.kdc.visioncards;
import java.util.HashMap;
import java.util.Map;
import org.springframework.batch.item.ItemProcessor;
import edu.kdc.visioncards.dto.AttendanceDTO;
public class AttendanceProcessor implements ItemProcessor<AttendanceDTO, Map<Integer, AttendanceDTO>> {
private Map<Integer, AttendanceDTO> map = new HashMap<Integer, AttendanceDTO>();
public Map<Integer, AttendanceDTO> process(AttendanceDTO dto) throws Exception {
if(map.containsKey(new Integer(dto.getStudentId()))){
AttendanceDTO attDto = (AttendanceDTO)map.get(new Integer(dto.getStudentId()));
attDto.setAttDays(attDto.getAttDays() + dto.getAttDays());
attDto.setAttValue(attDto.getAttValue() + dto.getAttValue());
}else{
map.put(new Integer(dto.getStudentId()), dto);
}
return map;
}
}
import java.sql.ResultSet;
import java.sql.SQLException;
import org.springframework.batch.item.ReaderNotOpenException;
import org.springframework.batch.item.database.JdbcCursorItemReader;
import org.springframework.jdbc.core.RowMapper;
/**
* A JdbcCursorItemReader that uses a {@link CollectingRowMapper}.
* Like the superclass this reader is not thread-safe.
*
* @author Pino Navato
**/
public class CollectingJdbcCursorItemReader<T> extends JdbcCursorItemReader<T> {
private CollectingRowMapper<T> rowMapper;
private boolean firstRead = true;
/**
* Accepts a {@link CollectingRowMapper} only.
**/
@Override
public void setRowMapper(RowMapper<T> rowMapper) {
this.rowMapper = (CollectingRowMapper<T>)rowMapper;
super.setRowMapper(rowMapper);
}
/**
* Read next row and map it to item.
**/
@Override
protected T doRead() throws Exception {
if (rs == null) {
throw new ReaderNotOpenException("Reader must be open before it can be read.");
}
try {
if (firstRead) {
if (!rs.next()) { //Subsequent calls to next() will be executed by rowMapper
return null;
}
firstRead = false;
} else if (!rowMapper.hasNext()) {
return null;
}
T item = readCursor(rs, getCurrentItemCount());
return item;
}
catch (SQLException se) {
throw getExceptionTranslator().translate("Attempt to process next row failed", getSql(), se);
}
}
@Override
protected T readCursor(ResultSet rs, int currentRow) throws SQLException {
T result = super.readCursor(rs, currentRow);
setCurrentItemCount(rs.getRow());
return result;
}
}