worace

csv2json () {
        ruby -r csv -r json -e 'CSV.new(STDIN, headers: true).each { |r| puts r.to_h.to_json }'
}

worace

import cats.effect.Clock
import cats.effect.{IOApp, Resource, IO, ResourceApp, ExitCode}
import scala.concurrent.duration._
object Dummy extends IOApp {
  val resource = Resource.make(IO(System.currentTimeMillis)){ start =>
    IO.sleep(3.seconds) >> IO.println(s"Exiting -- ${System.currentTimeMillis - start}")
  }

  def run(args: List[String]) = resource.use { ctx =>
    val interruptible = IO.never

worace

-- migrate:up
CREATE OR REPLACE FUNCTION with_stringified_values(input jsonb)
  RETURNS jsonb
  LANGUAGE plpgsql AS
$func$
DECLARE
   _key   text;
   _value text;
   _vals text[] := '{}'::text[];
   _output jsonb := '{}'::jsonb;

worace

class ApacheSpark < Formula
  desc "Engine for large-scale data processing"
  homepage "https://spark.apache.org/"
  url "https://archive.apache.org/dist/spark/spark-2.2.0/spark-2.2.0-bin-hadoop2.7.tgz"
  version "2.2.0"
  sha256 "97fd2cc58e08975d9c4e4ffa8d7f8012c0ac2792bcd9945ce2a561cf937aebcc"
  head "https://github.com/apache/spark.git"

  bottle :unneeded

worace

worace

Geoq - (yet another) GIS command line tool

• Problem - ad-hoc manipulation + inspection of piles of textual GIS data
• Replacing copy-paste workflows
• Most work is already in the terminal, so unix tools are a plus
  • integrate with other tools
  • streaming enables processing large datasets
  • fast startup + executable binaries are nice
  • Easy, cross-platform install (rust)
• README - https://github.com/worace/geoq

worace

worace

worace

worace

Intro: Command Line Tools

• Types of programs: Side-effect-y (mkdir, touch) vs Function-y (cat, grep, wc) -- Produce output
• Basic Unix "contract": Take in text stream and output text stream
• Somewhat janky but works fairly well

Examples

• head - show me first lines of a file