Alexander Leibzon alexanderlz

## alluxio-cleanup.sh
#!/bin/bash

ALLUXIO_CMD=/opt/alluxio/bin/alluxio
echo "using alluxio command at $ALLUXIO_CMD"
SCAN_PATH=$1

#for k in $($ALLUXIO_CMD fs ls -fR $SCAN_PATH  | grep LOST | cut -f2 -d'%' | tr -d ' '); do echo "deleting $k"; $ALLUXIO_CMD fs rm $k;done
$ALLUXIO_CMD fs ls -fR $SCAN_PATH  | grep LOST | cut -f2- -d'%' |  xargs -P 30 -I{} $ALLUXIO_CMD fs rm '{}'

## ubuntu-docking-station-monitor-switch.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                alexanderlz
                / ubuntu-docking-station-monitor-switch.md
            
            
              Last active
              July 31, 2016 12:26
            
              
                Create a helper script that switches monitors when ubuntu laptop docked/undocked
              
          
install arandr
sudo apt-get install arandr


save 2 configurations, one for monitors attached on docking, another for laptop only.
~/.screenlayout/dock.sh
~/.screenlayout/undock.sh


add new udev rule:


## set_cover.py
def greedySetCover(targetSet, subSets):
    if not subSets:
        return None
    probeKey = max(subSets, key=lambda x: len(targetSet.intersection(subSets[x])))
    probeSet = subSets[probeKey]
    #result = set()
    resKeys = set()
    while len(targetSet) > 0:
        #result.update(probeSet)
        targetSet = targetSet.difference(probeSet)

## col_desc.sql
SELECT description FROM pg_catalog.pg_description WHERE objsubid =
        (
            SELECT ordinal_position FROM  information_schema.columns WHERE table_name='YOUR_TABLE_NAME' AND column_name='YOUR_COLUMN_NAME'
        )
        and objoid =
        (
            SELECT oid FROM pg_class WHERE relname = 'YOUR_TABLE_NAME' AND relnamespace =
                        (
                            SELECT oid FROM pg_catalog.pg_namespace WHERE nspname = 'public'
                        )

## lines.py
def fetchLinesByMarker(ffile, lineMarker):
        buff = []
        for ln in ffile:
            if ln.startswith(lineMarker):
                if buff:
                        yield(''.join(buff))
                del(buff[:])
            buff.append(ln)
        yield(''.join(buff))

## find_bad_file_by_block_hdfs.sh
sudo -u hdfs hadoop fsck / -files -blocks | grep BAD_BLOCK_ID -B 5

## CryptoHash.java
package com.hiveextensions.udf;

import java.security.MessageDigest;
import java.security.NoSuchAlgorithmException;

import org.apache.hadoop.hive.ql.exec.UDF;

public final class CryptoHash extends UDF {

  public String evaluate(final String s, final String algorithm) {

## log_diff.sh
diff  <(hadoop fs -ls /user/mapred/ | cut -f4 -d'/' | sort -u) <(hadoop fs -ls /user/mapred/*/*_data/$(date +%Y%m%d)* | cut -f4 -d'/' | sort -u) | grep '<' | cut -f2 -d'<'

## hdfs_list_running_jobs.sh
hadoop job -list | grep job_ | awk 'BEGIN{FS="\t";OFS=","};{print $1,strftime("%H:%M:%S", (systime()-int($3/1000)),1),"\""$4"\"","\""$6"\""}'
	#!/bin/bash

	ALLUXIO_CMD=/opt/alluxio/bin/alluxio
	echo "using alluxio command at $ALLUXIO_CMD"
	SCAN_PATH=$1

	#for k in $($ALLUXIO_CMD fs ls -fR $SCAN_PATH \| grep LOST \| cut -f2 -d'%' \| tr -d ' '); do echo "deleting $k"; $ALLUXIO_CMD fs rm $k;done
	$ALLUXIO_CMD fs ls -fR $SCAN_PATH \| grep LOST \| cut -f2- -d'%' \| xargs -P 30 -I{} $ALLUXIO_CMD fs rm '{}'
	def greedySetCover(targetSet, subSets):
	if not subSets:
	return None
	probeKey = max(subSets, key=lambda x: len(targetSet.intersection(subSets[x])))
	probeSet = subSets[probeKey]
	#result = set()
	resKeys = set()
	while len(targetSet) > 0:
	#result.update(probeSet)
	targetSet = targetSet.difference(probeSet)
	SELECT description FROM pg_catalog.pg_description WHERE objsubid =
	(
	SELECT ordinal_position FROM information_schema.columns WHERE table_name='YOUR_TABLE_NAME' AND column_name='YOUR_COLUMN_NAME'
	)
	and objoid =
	(
	SELECT oid FROM pg_class WHERE relname = 'YOUR_TABLE_NAME' AND relnamespace =
	(
	SELECT oid FROM pg_catalog.pg_namespace WHERE nspname = 'public'
	)
	def fetchLinesByMarker(ffile, lineMarker):
	buff = []
	for ln in ffile:
	if ln.startswith(lineMarker):
	if buff:
	yield(''.join(buff))
	del(buff[:])
	buff.append(ln)
	yield(''.join(buff))
	package com.hiveextensions.udf;

	import java.security.MessageDigest;
	import java.security.NoSuchAlgorithmException;

	import org.apache.hadoop.hive.ql.exec.UDF;

	public final class CryptoHash extends UDF {

	public String evaluate(final String s, final String algorithm) {