shiumachi

#!/bin/bash
usage()
{
    echo "hadoop-logaggr.sh [-h] file" >&2
    echo "         -h: help (this message)" >&2
    exit 0
}

TEMP=`getopt h $*`

shiumachi

#!/bin/sh

TMP_DIR=/tmp

HADOOP_BIN_DIR=${HADOOP_MAPRED_HOME}/bin
HADOOP_COMMAND=${HADOOP_BIN_DIR}/hadoop
HADOOP_JAR_COMMAND="${HADOOP_COMMAND} jar"
MAPRED_SHARE_HOME=${HADOOP_MAPRED_HOME}/share/hadoop/mapreduce
HADOOP_EXAMPLE_JAR=${MAPRED_SHARE_HOME}/hadoop*examples*.jar
HADOOP_EXAMPLE_COMMAND="${HADOOP_JAR_COMMAND} ${HADOOP_EXAMPLE_JAR}"

shiumachi

#!/bin/sh

source util.sh

TMP_DIR=/tmp

HADOOP_BIN_DIR=${HADOOP_HOME}/bin
HADOOP_COMMAND=${HADOOP_BIN_DIR}/hadoop
HADOOP_START_HDFS_COMMAND=`which start-dfs.sh`
HADOOP_STOP_HDFS_COMMAND=`which stop-dfs.sh`

shiumachi

#!/bin/bash

usage(){
    printf "%s:\n" "usage" 1>&2
    printf "%s file \n" `basename $0` 1>&2
    printf "  %-15s: help (this message)" "-h" >&2
}


TEMP=`getopt h $*`

shiumachi

#!/bin/bash

usage()
{
    echo "usage: zip_logs.sh [directory] [-prod]" >&2
    exit 0
}
    
TEMP=`getopt :h $*`

shiumachi

#!/bin/sh

HOME_LIB_DIR=${HOME}/lib

# symlink list
HADOOP_SYMLINK=${HOME_LIB_DIR}/hadoop
HBASE_SYMLINK=${HOME_LIB_DIR}/hbase
ZOOKEEPER_SYMLINK=${HOME_LIB_DIR}/zookeeper
HIVE_SYMLINK=${HOME_LIB_DIR}/hive
PIG_SYMLINK=${HOME_LIB_DIR}/pig

shiumachi

#!/usr/bin/python
import hashlib

startKey = 2
endKey = 6
inputNum = 1000
testNum = 100000

def check_bl(bloom, a):
    aa = hashlib.md5(a).hexdigest()[startKey:endKey]

shiumachi

#!/usr/bin/python
# -*- coding: utf-8 -*-
import argparse
import sys

class MyArgParse(object):
    def __init__(self):
        pass

    def sum(self):

shiumachi

#!/bin/sh

# logging stdout/stderr
set -x
exec >> /root/bootstrap-master-init.log 2>&1
date

# Master node identifier
touch /root/kafka-kudu-demo_edge-node.flag

shiumachi

# This script compacts daily based csv files to monthly based parquet file.
# The CSV files should be named like "YYYY-MM-DD.csv" format.
#
# このスクリプトは日付毎のcsvファイルを月毎のparquetファイルに変換します。
# CSVファイルの名前は"YYYY-MM-DD.csv"の形式にしてください。
#

import pandas as pd
import numpy as np
import pyarrow as pa