Sankar sankars

## find_class_jar.sh
find . -name *.jar -exec grep -Hsli SparkJavaTxExecBoot {} \;

## failed_mappings.sql
select
POR_OBJECTNAME as MAPPING_NAME,
POR_REQUESTTYPE as JOB_TYPE,
DATEADD(SECOND,POR_STARTTIME/1000,'19700101 00:00') AS MAPPING_START_TIME,
POR_MESSAGE as ERROR_MESSAGE,
POR_LOGFILENAME as LOG_FILE,
POR_SERVICENAME as DIS_NAME,
POR_EXECUTINGNODENAME as NODE_NAME
from PO_REQUESTSTAT
where POR_MESSAGE IS NOT NULL

## tbl_stats.sql
SELECT d.NAME AS DB_NAME, t. TBL_NAME, COUNT(1) AS COL_COUNT, tp.PARAM_VALUE AS ROW_COUNT
FROM hive.TBLS t
 JOIN hive.DBS d
 ON t.DB_ID = d.DB_ID
 JOIN hive.SDS s
 ON t.SD_ID = s.SD_ID
 JOIN hive.COLUMNS_V2 c
 ON s.CD_ID = c.CD_ID
 JOIN hive.TABLE_PARAMS tp
 ON t.TBL_ID = tp.TBL_ID

## replicate_database_schema.sh
SRC_DB_NAME="src"; TGT_DB_NAME="tgt"; for Table in $HiveTables; do ; hive -e "CREATE TABLE $TGT_DB_NAME.$Table LIKE $SRC_DB_NAME.$Table;"; done;

## ansible_jstack
ansible *149.102 -m shell -a 'sudo -u infabdm /opt/openjdk/jdk-13.0.2/bin/jstack -l -e $(ps aux | grep -i "Blaze_Grid_Manager" | egrep -v "grep|bash" | awk '"'"'{print $2}'"'"') > /root/jstack_app1.log'

## tpch.m
let
    Source = Odbc.DataSource("dsn=TPCH", [HierarchicalNavigation=true]),
    TPCH_Schema = Source{[Name="TPCH",Kind="Schema"]}[Data],
    REGION_Table = TPCH_Schema{[Name="REGION",Kind="Table"]}[Data]
in
    REGION_Table

## tcpdump.sh

tcpdump -i any -G 3600 -w /data/tcpdump/dump-%m-%d-%H.pcap net 10.2.132.0/24 &

## hive_export_import.sh

#!/bin/sh

SRC_DB_NAME="src"

TGT_DB_NAME="tgt"

EXPORT_DIR="/tmp"

HiveTables=$(hive -e "use $SRC_DB_NAME;show tables;" 2>/dev/null | egrep -v "WARN|^$|^Logging|^OK|^Time\ taken")

## sentry_permission_analysis.sql


SELECT  r.ROLE_NAME,g.GROUP_NAME
FROM DC_CDH_SENTRY.SENTRY_ROLE_GROUP_MAP m
INNER JOIN DC_CDH_SENTRY.SENTRY_GROUP g ON m.GROUP_ID = g.GROUP_ID
INNER JOIN DC_CDH_SENTRY.SENTRY_ROLE r ON r.ROLE_ID = m.ROLE_ID
ORDER BY r.ROLE_NAME,g.GROUP_NAME


## install_superset.sh
### Install Superset(0.28.1)

conda create -n superset python=3.6

conda activate superset

pip install pandas==0.23.4

pip install flask==1.0.0
	select
	POR_OBJECTNAME as MAPPING_NAME,
	POR_REQUESTTYPE as JOB_TYPE,
	DATEADD(SECOND,POR_STARTTIME/1000,'19700101 00:00') AS MAPPING_START_TIME,
	POR_MESSAGE as ERROR_MESSAGE,
	POR_LOGFILENAME as LOG_FILE,
	POR_SERVICENAME as DIS_NAME,
	POR_EXECUTINGNODENAME as NODE_NAME
	from PO_REQUESTSTAT
	where POR_MESSAGE IS NOT NULL
	SELECT d.NAME AS DB_NAME, t. TBL_NAME, COUNT(1) AS COL_COUNT, tp.PARAM_VALUE AS ROW_COUNT
	FROM hive.TBLS t
	JOIN hive.DBS d
	ON t.DB_ID = d.DB_ID
	JOIN hive.SDS s
	ON t.SD_ID = s.SD_ID
	JOIN hive.COLUMNS_V2 c
	ON s.CD_ID = c.CD_ID
	JOIN hive.TABLE_PARAMS tp
	ON t.TBL_ID = tp.TBL_ID
	let
	Source = Odbc.DataSource("dsn=TPCH", [HierarchicalNavigation=true]),
	TPCH_Schema = Source{[Name="TPCH",Kind="Schema"]}[Data],
	REGION_Table = TPCH_Schema{[Name="REGION",Kind="Table"]}[Data]
	in
	REGION_Table

	tcpdump -i any -G 3600 -w /data/tcpdump/dump-%m-%d-%H.pcap net 10.2.132.0/24 &

	#!/bin/sh

	SRC_DB_NAME="src"

	TGT_DB_NAME="tgt"

	EXPORT_DIR="/tmp"

	HiveTables=$(hive -e "use $SRC_DB_NAME;show tables;" 2>/dev/null \| egrep -v "WARN\|^$\|^Logging\|^OK\|^Time\ taken")


	SELECT r.ROLE_NAME,g.GROUP_NAME
	FROM DC_CDH_SENTRY.SENTRY_ROLE_GROUP_MAP m
	INNER JOIN DC_CDH_SENTRY.SENTRY_GROUP g ON m.GROUP_ID = g.GROUP_ID
	INNER JOIN DC_CDH_SENTRY.SENTRY_ROLE r ON r.ROLE_ID = m.ROLE_ID
	ORDER BY r.ROLE_NAME,g.GROUP_NAME
	### Install Superset(0.28.1)

	conda create -n superset python=3.6

	conda activate superset

	pip install pandas==0.23.4

	pip install flask==1.0.0