iconara

#!/usr/bin/env bash

region=us-east-1
query='SELECT NOW()'
output_location="s3://aws-athena-query-results-1234567890-$region/"

query_execution_id=$(aws athena start-query-execution \
  --region "$region" \
  --query-string "$query" \
  --result-configuration "OutputLocation=$output_location" \

iconara

// this is an attempt to create a synchronous InputStream from a call to
// S3AsyncClient#getObject using a blocking queue.
//
// the purpose is to be able to make many S3 operations asynchronously, but
// at the same time be able to pass off some results to threads and into
// code that expects InputStream or Reader, like a Commons CSV.

public class InputStreamResponseTransformer extends InputStream implements AsyncResponseTransformer<GetObjectResponse, InputStream>, Subscriber<ByteBuffer> {
    private static final ByteBuffer END_MARKER = ByteBuffer.allocate(0);

iconara

#!/usr/bin/env ruby

# This code parses the .csv.metadata files written by Athena and produces a
# structure similar to what you get from the GetQueryResults API call.
#
# I have reverse engineered the format and I'm not sure about all the details,
# but it seems to correspond to the GetQueryResults API call well. Some things,
# like nullability, the difference between name and label, and the schema_name
# and table_name fields, I haven't been able to figure out because they seem
# not to be used, or never takes any other values.

iconara

-- Connection limits by role
SELECT rolname, rolconnlimit
FROM pg_roles
WHERE rolconnlimit <> -1;

-- Change connection limit for a role
ALTER USER $role WITH CONNECTION LIMIT 64;

-- Current activity
SELECT *

iconara

require 'aws-sdk-glue'
require 'aws-sdk-s3'

def split_s3_uri(s3_uri)
  s3_uri.match(%r{\As3://(.+?)/(.+)\z}).to_a.drop(1)
end

database, table_name = ARGV.take(2)

glue = Aws::Glue::Client.new

iconara

-- this creates a schema called "name_of_schema_in_redshift" in Redshift,
-- that works as an alias for the Athena/Glue database "name_of_database_in_glue".
CREATE EXTERNAL SCHEMA name_of_schema_in_redshift
FROM DATA CATALOG
DATABASE 'name_of_database_in_glue'
REGION 'us-east-1'
IAM_ROLE 'arn:aws:iam::456064453472:role/xyz';

iconara

require 'aws-sdk-ec2'

ec2 = Aws::EC2::Client.new

response = ec2.describe_security_groups

puts('digraph securitygroups {')

loop do
  response.security_groups.each do |security_group|

iconara

-- Discovers all partitions of a table if they use Hive's partitioning format (e.g. partition0=abc/partition1=def)
MSCK REPAIR TABLE tablename;

iconara

#!/bin/bash

function log() {
  logger -st "cbck[$$]" "$@"
}

function check_failed() {
  log -p user.err "Check failed: $1"
  exit 1
}

iconara

# Running this script with `ruby -w` will print these warnings:
# .../lib/ruby/1.9/webrick/https.rb:26 warning: javax.net.ssl.SSLPeerUnverifiedException: peer not authenticated
# .../lib/ruby/1.9/webrick/https.rb:27 warning: javax.net.ssl.SSLPeerUnverifiedException: peer not authenticated

require 'webrick'
require 'webrick/https'
require 'net/https'
require 'logger'

def create_root_ca(cn)