gyli

function vpn {
  if [ $1 = "c" ]; then
    /opt/cisco/anyconnect/bin/vpn connect "vpn.example.com";
  elif [ $1 = "d" ]; then
    /opt/cisco/anyconnect/bin/vpn disconnect;
    kill $(ps aux | grep "[C]isco AnyConnect Secure Mobility Client" | awk '{print $2}') 2>/dev/null;
  elif [ $1 = "k" ]; then
    kill $(ps aux | grep "[C]isco AnyConnect Secure Mobility Client" | awk '{print $2}') 2>/dev/null;
    kill -9 $(ps aux | grep "[/]opt/cisco/anyconnect/bin/vpn connect" | awk '{print $2}') 2>/dev/null;
  fi

gyli

template = """head{var1}middle{var2{nested}}end"""

def parenthetic_contents(string):
    """Generate parenthesized contents in string as pairs (level, contents)."""
    stack = []
    for i, c in enumerate(string):
        if c == '{':
            stack.append(i)
        elif c == '}' and stack:
            start = stack.pop()

gyli

# Once brew upgraded Python, packages installed through pipx might need to be reinstalled
rm -rf ~/.local/pipx/shared/
pipx reinstall-all

gyli

import re

example = """Ann,Bob,Cat(Tom,Max),Dave"""

re.split(r',(?![^\(\)]*\))', example)

# Output:
# ['Ann', 'Bob', 'Cat(Tom,Max)', 'Dave']

gyli

import csv


class CustomCSVReader:
    _CSV_DEFAULT_PARS = {
        "delimiter": ",",
        "doublequote": True,
        "escapechar": None,
        "lineterminator": "\r\n",
        "quotechar": '"',

gyli

  def CopyObjectRecursively(
      s3client: AmazonS3Client,
      sourcePath: String,
      targetPath: String,
      includeSourceBucketInTargetPath: Boolean = false): Unit = {

    val sourceURI: AmazonS3URI = new AmazonS3URI(sourcePath)
    val targetURI: AmazonS3URI = new AmazonS3URI(targetPath)

    val sourceBucket = sourceURI.getBucket()

gyli

# https://www.elastic.co/guide/en/elasticsearch/reference/7.0/indices-split-index.html
# Parameter number_of_routing_shards is used for splitting index in Elasticsearch
# Since ES 7.0, it has default value, which is designed to split by factors of 2 up to a maximum of 1024 shards.
# However, depending on the original number of primary shards, the default value might not be the best choice, 
# since it might not provide the most possibles the shards could be split to.

# For example, if the current primary shard number is 5, es would give number_of_routing_shards 650 as default value,
# and it allows the index to be split to 10, 20, 40, 80, 160, 320 or 640.
# However, assuming the maximum shard number is still 1024, set number_of_routing_shards to 900 would give the splitting 
# more options: 5, 10, 15, 20, 25, 30, 45, 50, 60, 75, 90, 100, 150, 180, 225, 300, 450, 900

gyli

import multiprocessing
import time


class WorkerPool:
    def __init__(self, worker_number):
        self.worker_number = worker_number
        self.pool = [multiprocessing.Process()] * worker_number

    def run(self, target, args=None, sleep_time=1):

gyli

import pandas as pd
import multiprocessing as mp
import traceback


def processing_chunk(chunk):
    for row in chunk.iterrows():
        pass
    time.sleep(5)

gyli

def join_nullable(l: List[str], sep: str) -> str:
    """
    Filter out None in a list and join the remaining strings.
    Example:
        Input: l=['a', None, 'c'], sep=' '
        Output: 'a c'
    :param l: list of strings
    :param sep: separator
    """
    return sep.join(filter(lambda i: bool(i), l))