SELECT DISTINCT 'DATA' AS DSN,
'MASTER' AS ORG_ID,e.emp_id,
e.emp_name AS EMPLOYEE_NUMBER,
e.emp_firstname AS EMPLOYEE_FIRST_NAME,
e.emp_lastname AS EMPLOYEE_LAST_NAME,
e.emp_val20 AS PAY_STATUS,
(NVL(TO_CHAR(PGT.PAYGRPTYP_NAME),'MASTER')) AS PAY_FREQUENCY,
E.EMP_VAL16 AS PAY_CLASS,
SP.SHFTPAT_NAME AS SHIFT_CODE,
WB.WBU_EMAIL AS EMAIL_ADDR,
(NVL(TO_CHAR( DE.DEPT_NAME),'MASTER')) AS DEPARTMENT,
NULL AS HELD_POSTN,
(NVL(TO_CHAR( J.JOB_NAME),'MASTER')) AS JOB_TITLE,
WB. WBU_NAME AS USER_NAME,
(NVL(TO_CHAR(ET.WBT_ID ),'MASTER')) AS TEAM_CODE,
WT.WBT_NAME AS TEAM_NAME,
WT.WBT_DESC AS TEAM_DESC,
(NVL(TO_CHAR(EB.EMPBDG_BADGE_NUMBER),'MASTER')) AS PERMANENT_BADGE_NO
FROM EMPLOYEE E
LEFT JOIN SHIFT_PATTERN SP
ON E.SHFTPAT_ID =SP.SHFTPAT_ID
LEFT JOIN PAY_GROUP PT
ON E.PAYGRP_ID =PT.PAYGRP_ID
LEFT JOIN PAY_GROUP_TYPE PGT
ON PT.PAYGRPTYP_ID =PGT.PAYGRPTYP_ID
LEFT JOIN EMPLOYEE_BADGE EB
ON E.EMP_ID=EB.EMP_ID
LEFT JOIN EMP_UDF_DATA ED
ON E.EMP_ID=ED.EMP_ID
LEFT JOIN WORKBRAIN_USER WB
ON E.EMP_ID=WB.EMP_ID
LEFT JOIN EMP_DEF_LAB D
ON E.EMP_ID=D.EMP_ID
LEFT JOIN DEPARTMENT DE
ON D.DEPT_ID=DE.DEPT_ID
LEFT JOIN EMPLOYEE_JOB EJ
ON E.EMP_ID=EJ.EMP_ID
LEFT JOIN JOB J
ON EJ.JOB_ID=J.JOB_ID
LEFT JOIN EMPLOYEE_TEAM ET
ON E.EMP_ID=ET.EMP_ID
LEFT JOIN WORKBRAIN_TEAM WT
ON ET.WBT_ID=WT.WBT_ID
LEFT JOIN CALC_GROUP CG
ON E.CALCGRP_ID =CG.CALCGRP_ID
WHERE E.EMP_ID NOT IN (SELECT EMP_ID FROM EMPLOYEE_READER_GROUP)
AND sysdate BETWEEN ET.empt_start_date AND ET.empt_end_date
AND ET.empt_home_team = 'Y'
AND sysdate BETWEEN EJ.EMPJOB_START_DATE AND EJ.EMPJOB_END_DATE
GROUP BY E.EMP_ID,
-- ER.rdrgrp_id,
e.emp_name,
e.emp_lastname,
e.emp_firstname,
e.emp_status,
e.emp_val20,
PGT.PAYGRPTYP_NAME,
E.EMP_VAL16,
e.EMP_VAL18,
EB.EMPBDG_BADGE_NUMBER,
WB.WBU_EMAIL,
DE.DEPT_NAME,
J.JOB_NAME,
SP.SHFTPAT_NAME,
WB. WBU_NAME ,
ET.WBT_ID ,
WT.WBT_NAME,
WT.WBT_DESC;
我想要员工表中的所有数据,所以我使用左连接,但我没有得到员工表中可用的所有行,有些值丢失。请帮我这个。我的员工有43000行但是当我使用它时,我只能获得17000行。我不知道我在哪里滞后。我希望将空列作为主表的正确值。
答案 0 :(得分:1)
你可以整天LEFT加入,你的where子句仍然可以作为过滤器使用。尝试没有where子句,看看你是否得到所有43k。另外,您正在分组可能会折叠行。
答案 1 :(得分:1)
WHERE子句中的这些过滤器将OUTER JOIN转换为INNER JOIN:
AND sysdate BETWEEN ET.empt_start_date AND ET.empt_end_date
AND ET.empt_home_team = 'Y'
AND sysdate BETWEEN EJ.EMPJOB_START_DATE AND EJ.EMPJOB_END_DATE
因为它们排除了测试属性为null的行(这是它们在不匹配的外连接行中的行)。
所以有几种方法。第一种是允许空值,例如
AND ( ET.empt_home_team is null or
( sysdate BETWEEN ET.empt_start_date AND ET.empt_end_date
AND ET.empt_home_team = 'Y' )
)
AND ( EJ.EMPJOB_START_DATE is null
or sysdate BETWEEN EJ.EMPJOB_START_DATE AND EJ.EMPJOB_END_DATE )
第二种是用内联视图替换表格,例如
LEFT JOIN ( select * from EMPLOYEE_TEAM
where sysdate BETWEEN empt_start_date AND empt_end_date
AND empt_home_team = 'Y' ) ET
ON E.EMP_ID=ET.EMP_ID
LEFT JOIN ( select * from EMPLOYEE_JOB
where sysdate BETWEEN EMPJOB_START_DATE AND EMPJOB_END_DATE ) EJ
ON E.EMP_ID=EJ.EMP_ID
哪种方法更适合您取决于数据。测试它们并看到。
答案 2 :(得分:1)
想想你想要的数据。当你LEFT JOIN时,当你真正只需要其中一个表的数据时,你就加入了整个表。我修改了你的一些LEFT JOINS来为此考虑因素。此外,在大型数据集上执行WHERE x NOT IN(SELECT x ....)可能非常慢。我已将其更改为允许优化器更好地工作。它现在执行LEFT JOIN .... WHERE x IS NULL。这应该更快。您对MAXing的计划是什么?这个查询非常复杂。您希望在尝试聚合之前确保获得所需的初始数据。
SELECT 'DATA' AS DSN,
'MASTER' AS ORG_ID,e.emp_id,
e.emp_name AS EMPLOYEE_NUMBER,
e.emp_firstname AS EMPLOYEE_FIRST_NAME,
e.emp_lastname AS EMPLOYEE_LAST_NAME,
e.emp_val20 AS PAY_STATUS,
(NVL(TO_CHAR(ptpgt.PAYGRPTYP_NAME),'MASTER')) AS PAY_FREQUENCY, /* From subquery join */
E.EMP_VAL16 AS PAY_CLASS,
SP.SHFTPAT_NAME AS SHIFT_CODE,
WB.WBU_EMAIL AS EMAIL_ADDR,
(NVL(TO_CHAR( DE.DEPT_NAME),'MASTER')) AS DEPARTMENT,
NULL AS HELD_POSTN,
(NVL(TO_CHAR( eej.JOB_NAME),'MASTER')) AS JOB_TITLE, /* From subquery join */
WB. WBU_NAME AS USER_NAME,
(NVL(TO_CHAR(eet.WBT_ID ),'MASTER')) AS TEAM_CODE, /* From subquery join */
WT.WBT_NAME AS TEAM_NAME,
WT.WBT_DESC AS TEAM_DESC,
(NVL(TO_CHAR(EB.EMPBDG_BADGE_NUMBER),'MASTER')) AS PERMANENT_BADGE_NO
FROM EMPLOYEE E
/* This plus WHERE ERG.EMP_ID IS NULL is the same as the subquery filter. But faster. */
LEFT OUTER JOIN EMPLOYEE_READER_GROUP erg ON e.EMP_ID = ERG.EMP_ID
LEFT JOIN SHIFT_PATTERN SP ON E.SHFTPAT_ID =SP.SHFTPAT_ID
LEFT JOIN (
SELECT PT.EMP_ID,PGT.PAYGRPTYP_NAME
FROM PAY_GROUP PT
INNER JOIN PAY_GROUP_TYPE PGT ON PT.PAYGRPTYP_ID =PGT.PAYGRPTYP_ID
) ptpgt ON E.PAYGRP_ID =ptpgt.PAYGRP_ID
LEFT JOIN EMPLOYEE_BADGE EB ON E.EMP_ID=EB.EMP_ID
LEFT JOIN EMP_UDF_DATA ED ON E.EMP_ID=ED.EMP_ID
LEFT JOIN WORKBRAIN_USER WB ON E.EMP_ID=WB.EMP_ID
LEFT JOIN (
SELECT D.EMP_ID, DE.DEPT_NAME
FROM EMP_DEF_LAB D
INNER JOIN DEPARTMENT DE ON D.DEPT_ID=DE.DEPT_ID
) dde ON E.EMP_ID=dde.EMP_ID
LEFT JOIN (
SELECT EJ.EMP_ID, J.JOB_NAME
FROM EMPLOYEE_JOB EJ
INNER JOIN JOB J ON EJ.JOB_ID=J.JOB_ID
WHERE sysdate BETWEEN EJ.EMPJOB_START_DATE AND EJ.EMPJOB_END_DATE
/*
Doublecheck your date filters. Are they getting the edge dates you need?
BETWEEN makes it easy to miss a date, especially if your fields
are DATETIME datatypes.
USE <=/>= to be a bit clearer.
*/
) eej ON E.EMP_ID=eej.EMP_ID
LEFT JOIN (
SELECT ET.EMP_ID, WBT_ID
FROM EMPLOYEE_TEAM ET
INNER JOIN WORKBRAIN_TEAM WT ON ET.WBT_ID=WT.WBT_ID
WHERE
ET.empt_home_team = 'Y'
AND sysdate BETWEEN ET.empt_start_date AND ET.empt_end_date
/*
Doublecheck your date filters. Are they getting the edge dates you need?
BETWEEN makes it easy to miss a date, especially if your fields
are DATETIME datatypes.
USE <=/>= to be a bit clearer.
*/
) eet ON E.EMP_ID=eet.EMP_ID
LEFT JOIN CALC_GROUP CG ON E.CALCGRP_ID=CG.CALCGRP_ID
WHERE
ERG.EMP_ID IS NULL