vepetkov

# Parse the whole git history and show files larger than 1Mb (2^20 b)
git rev-list --objects --all |
  git cat-file --batch-check='%(objecttype) %(objectname) %(objectsize) %(rest)' |
  sed -n 's/^blob //p' |
  awk '$2 >= 2^20' |
  sort --numeric-sort --key=2 |
  cut -c 1-12,41- |
  $(command -v gnumfmt || echo numfmt) --field=2 --to=iec-i --suffix=B --padding=7 --round=nearest

vepetkov

# Store in ~/.config/direnv/direnvrc to run for all folders automatically
# check if VENV is loaded
if [[ -z "${VIRTUAL_ENV_PROMPT}" ]] ; then
    if [ ! -d ".venv" ] ; then
        echo "Installing virtualenv for $(python -V)"
        python -m venv .venv
    fi
    echo "Activating $(python -V) virtualenv from .venv"
    source .venv/bin/activate
fi

vepetkov

# Test SMTP with STARTTLS
openssl s_client -showcerts -connect smtp.office365.com:587 -servername smtp.office365.com -starttls smtp

# Test IMAP with SSL/TLS
openssl s_client -showcerts -connect outlook.office365.com:993 -servername outlook.office365.com

# Test POP3 with SSL/TLS
openssl s_client -showcerts -connect outlook.office365.com:995 -servername outlook.office365.com

vepetkov

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import argparse
import tarfile
import json


def get_tar_metadata(file_name):
    tar = tarfile.open(file_name, encoding="iso8859-1")

vepetkov

import os
import snowflake.connector

ctx = snowflake.connector.connect(
    authenticator="snowflake",
    user=os.getenv("SNOWSQL_USER"),
    password=os.getenv("SNOWSQL_PWD"),
    account=os.getenv("SNOWSQL_ACCOUNT"),
    warehouse=os.getenv("SNOWSQL_WAREHOUSE")
    )

vepetkov

# Get the Hive Symlinks
aws s3 ls s3://<BUCKET>/hive/  --recursive | awk '{print "s3://<BUCKET>/"$4}' 

# Delete all data files for the selected Hive partition
aws s3 cp s3://<BUCKET>/hive/dt=2019-07-24-00-00/symlink.txt - | xargs -I {} sh -c 'aws s3 rm {}'

vepetkov

import pandas as pd
import pyarrow.orc as orc

file0 = open('/hive/warehouse/000000_0', 'rb')
data0 = orc.ORCFile(file0)
df0 = data0.read(columns=['_col10', '_col50']).to_pandas()
df0.describe()

vepetkov

# Unzip in-place (i.e. in the folder containing the file and not the current one)
find . -type f -name "*.zip" | xargs -P4 -I fileName sh -c 'unzip -o -d "$(dirname "fileName")" "fileName" && rm "fileName"'

# Gzip all CSV extracted from the ZIP files
find . -type f -name *.csv -print0 | xargs -0 -n1 -P4 gzip

vepetkov

# Concatenate the Root and SubCA certs from DigiCert 
# to get the full certification chain
cat DigiCert_Global_Root_CA.pem DigiCertSHA2SecureServerCA.pem > DigiCertCA_Chain.pem

# Generate a new key store from the signed cert, the private key
openssl pkcs12 -export \
    -in my_cert_signed.crt 
    -inkey my_cert_key.pem 
    -chain -CAfile DigiCertCA_Chain.pem \
    -name "my_cert" -out my_cert.keystore.p12

vepetkov

# Get the requested resources for all pods by container

kubectl get pods -ao jsonpath='{range .items[*]}{@.metadata.name}{"\n"}{range @.spec.containers[*]}{"\t"}{@.name}{" cpu:"}{@.resources.requests.cpu}{" mem:"}{@.resources.requests.memory}{"\n"}{end}{end}'