michalc

# docker run --rm -it -p 5432:5432 -e POSTGRES_PASSWORD=password postgres:14

import pprint
import threading
import time
from concurrent.futures import ThreadPoolExecutor
from contextlib import contextmanager

import psycopg2
import psycopg2.extras

michalc

# From https://stackoverflow.com/a/68876046/1319998, which is itself inspired by https://stackoverflow.com/a/68814418/1319998

from contextlib import contextmanager
from collections import namedtuple
from ctypes import cdll, byref, string_at, c_char_p, c_int, c_double, c_int64, c_void_p
from ctypes.util import find_library
from sys import platform


def query(db_file, sql, params=()):

michalc

# Deletes objects in bulk using boto3's delete_objects, but using multiple threads to achieve some
# parallelism - in spite of the GIL multiple HTTP requests to S3 should happen at the same time.
# Instead of looping over all keys under the root prefix, it walks the tree of keys of delimiter-
# defined "folders" in a depth-first way, which allows each page to be processed by a separate
# thread as its discovered. Depth-first is done because the depth is limited by the maximum key
# size of 1024 in S3, and so means that there is a limit to the memory used by the algorithm to
# store the next requests to make. This would not be the case with breadth-first because there is
# no limit to how many keys are in any folder.
#
# To do the search in parallel, each bit of work (i.e. an HTTP request to fetch a page of keys

michalc

import json
import os
from urllib.parse import urlparse, parse_qsl

import requests
from rich import box
from rich.console import Console
from rich.table import Table

with open(f'{os.environ["HOME"]}/.cf/config.json') as f:

michalc

import datetime
import hashlib
import hmac
import urllib.parse


def aws_sig_v4_headers(access_key_id, secret_access_key, pre_auth_headers,
                       service, region, host, method, path, query, payload):
    algorithm = 'AWS4-HMAC-SHA256'

michalc

def normalise_environment(key_values):
    ''' Converts denormalised dict of (string -> string) pairs, where the first string
        is treated as a path into a nested list/dictionary structure

        {
            "FOO__1__BAR": "setting-1",
            "FOO__1__BAZ": "setting-2",
            "FOO__2__FOO": "setting-3",
            "FOO__2__BAR": "setting-4",
            "FIZZ": "setting-5",

michalc

import base64
import json

import boto3
from cryptography.hazmat.primitives.ciphers.aead import AESGCM

s3 = boto3.resource('s3')
bucket = s3.Bucket('my-bucket')
kms_client = boto3.client('kms')

michalc

# Often it's claimed that a Zip 2.0 file cannot be bigger than 4GiB
# Here's how to make one that's just under 8GiB
from datetime import datetime
from stream_zip import stream_zip, ZIP_32

now = datetime.now()
perms = 0o600

def files():
    for i in range(0, 0xffff):

michalc

import asyncio
import collections
import contextlib

class Read(asyncio.Future):
    @staticmethod
    def is_compatible(holds):
        return not holds[Write]

class Write(asyncio.Future):

michalc

class MyPipeline(_PipelineV2):
    # Everything is a method so nothing happens on import time for flexibility (although possibly
    # does a bit of discovery magic... need to think about that...)
    # Everything is a _static_ method: nothing on self since things are run on different bits of hardware,
    # and gets any run-time dependencies injected in
    #
    # _PipelineV2 won't actually have any code: other parts of the system will interrogate its
    # subclasses as needed. For example
    # - Code in Data Flow would construct a DAG
    # - The test harness would the run this and upstream pipelines synchronously