Spring batch学习 (1)

Spring Batch 批处理框架埃森哲和Spring Source研发

主要解决批处理数据的问题，包含并行处理，事务处理机制等。具有健壮性可扩展，和自带的监控功能，并且支持断点和重发。让程序员更加注重于业务实现。

Spring Batch 结构如下

Spring batch学习 (1)

JobRepository ：作业仓库负责job。step执行过程的状态保存

JobLauncher : 作业调度器提供执行job入口

Job : 作业由一个或者多个step组成封装多个批处理操作，每个step可以有自己的上下文存放变量和自己的生命周期。

Step: 作业步 job的一个环节，有多个或者一个step组成job

Tasklet: Step中的具体执行逻辑的动作可循环执行，支持异步和同步适用于不同场景

Chunk :给定的item集合可以定义对chunk的读操作，处理操作，写操作，提交间隔等这是SpringBatch 一个特性

Item:一条数据记录

ItemReader: 从数据源(文件系统队列文件等)读取item

ItemProcessor:在Item写入前进行一些处理比如数据清洗，数据转换，数据校验，数据过滤等。

ItemWrieter :将item批量输出到数据源（文件系统，队列，数据库等）

看下batch的基本配置元素分为两种一种为在内存中。

<?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:p="http://www.springframework.org/schema/p"    
    xmlns:tx="http://www.springframework.org/schema/tx" 
    xmlns:aop="http://www.springframework.org/schema/aop"    
    xmlns:context="http://www.springframework.org/schema/context"    
    xsi:schemaLocation="http://www.springframework.org/schema/beans  
    default-autowire="byName">
    <!--job工厂 不是定时-->
    <bean id="jobRepository" 
        class="org.springframework.batch.core.repository.support.MapJobRepositoryFactoryBean">
    </bean>

  <!--job加载器-->

<bean id="jobLauncher" class="org.springframework.batch.core.launch.support.SimpleJobLauncher"> <property name="jobRepository" ref="jobRepository"/> </bean>
<!--事务管理器-->
 <bean id="transactionManager" class="org.springframework.batch.support.transaction.ResourcelessTransactionManager"/> </beans>

第二种为放在数据库中需要在数据库中建表脚本在spring-batch-core的core包里面。mysql版本如下下一篇文章解释表的作用

-- Autogenerated: do not edit this file

CREATE TABLE BATCH_JOB_INSTANCE  (
    JOB_INSTANCE_ID BIGINT  NOT NULL PRIMARY KEY ,
    VERSION BIGINT ,
    JOB_NAME VARCHAR(100) NOT NULL,
    JOB_KEY VARCHAR(32) NOT NULL,
    constraint JOB_INST_UN unique (JOB_NAME, JOB_KEY)
) ENGINE=InnoDB;

CREATE TABLE BATCH_JOB_EXECUTION  (
    JOB_EXECUTION_ID BIGINT  NOT NULL PRIMARY KEY ,
    VERSION BIGINT  ,
    JOB_INSTANCE_ID BIGINT NOT NULL,
    CREATE_TIME DATETIME NOT NULL,
    START_TIME DATETIME DEFAULT NULL ,
    END_TIME DATETIME DEFAULT NULL ,
    STATUS VARCHAR(10) ,
    EXIT_CODE VARCHAR(100) ,
    EXIT_MESSAGE VARCHAR(2500) ,
    LAST_UPDATED DATETIME,
    constraint JOB_INST_EXEC_FK foreign key (JOB_INSTANCE_ID)
    references BATCH_JOB_INSTANCE(JOB_INSTANCE_ID)
) ENGINE=InnoDB;

CREATE TABLE BATCH_JOB_EXECUTION_PARAMS  (
    JOB_EXECUTION_ID BIGINT NOT NULL ,
    TYPE_CD VARCHAR(6) NOT NULL ,
    KEY_NAME VARCHAR(100) NOT NULL ,
    STRING_VAL VARCHAR(250) ,
    DATE_VAL DATETIME DEFAULT NULL ,
    LONG_VAL BIGINT ,
    DOUBLE_VAL DOUBLE PRECISION ,
    IDENTIFYING CHAR(1) NOT NULL ,
    constraint JOB_EXEC_PARAMS_FK foreign key (JOB_EXECUTION_ID)
    references BATCH_JOB_EXECUTION(JOB_EXECUTION_ID)
) ENGINE=InnoDB;

CREATE TABLE BATCH_STEP_EXECUTION  (
    STEP_EXECUTION_ID BIGINT  NOT NULL PRIMARY KEY ,
    VERSION BIGINT NOT NULL,
    STEP_NAME VARCHAR(100) NOT NULL,
    JOB_EXECUTION_ID BIGINT NOT NULL,
    START_TIME DATETIME NOT NULL ,
    END_TIME DATETIME DEFAULT NULL ,
    STATUS VARCHAR(10) ,
    COMMIT_COUNT BIGINT ,
    READ_COUNT BIGINT ,
    FILTER_COUNT BIGINT ,
    WRITE_COUNT BIGINT ,
    READ_SKIP_COUNT BIGINT ,
    WRITE_SKIP_COUNT BIGINT ,
    PROCESS_SKIP_COUNT BIGINT ,
    ROLLBACK_COUNT BIGINT ,
    EXIT_CODE VARCHAR(100) ,
    EXIT_MESSAGE VARCHAR(2500) ,
    LAST_UPDATED DATETIME,
    constraint JOB_EXEC_STEP_FK foreign key (JOB_EXECUTION_ID)
    references BATCH_JOB_EXECUTION(JOB_EXECUTION_ID)
) ENGINE=InnoDB;

CREATE TABLE BATCH_STEP_EXECUTION_CONTEXT  (
    STEP_EXECUTION_ID BIGINT NOT NULL PRIMARY KEY,
    SHORT_CONTEXT VARCHAR(2500) NOT NULL,
    SERIALIZED_CONTEXT TEXT ,
    constraint STEP_EXEC_CTX_FK foreign key (STEP_EXECUTION_ID)
    references BATCH_STEP_EXECUTION(STEP_EXECUTION_ID)
) ENGINE=InnoDB;

CREATE TABLE BATCH_JOB_EXECUTION_CONTEXT  (
    JOB_EXECUTION_ID BIGINT NOT NULL PRIMARY KEY,
    SHORT_CONTEXT VARCHAR(2500) NOT NULL,
    SERIALIZED_CONTEXT TEXT ,
    constraint JOB_EXEC_CTX_FK foreign key (JOB_EXECUTION_ID)
    references BATCH_JOB_EXECUTION(JOB_EXECUTION_ID)
) ENGINE=InnoDB;

CREATE TABLE BATCH_STEP_EXECUTION_SEQ (ID BIGINT NOT NULL) ENGINE=MYISAM;
INSERT INTO BATCH_STEP_EXECUTION_SEQ values(0);
CREATE TABLE BATCH_JOB_EXECUTION_SEQ (ID BIGINT NOT NULL) ENGINE=MYISAM;
INSERT INTO BATCH_JOB_EXECUTION_SEQ values(0);
CREATE TABLE BATCH_JOB_SEQ (ID BIGINT NOT NULL) ENGINE=MYISAM;
INSERT INTO BATCH_JOB_SEQ values(0);

View Code