#!/usr/bin/env bash

# Creates a file containing the names of all files in a specific bucket.
#
# e.g. aws-list-deep-glacier-files my-deep-glacier images image_list
#
# You'll need the aws cli tools. Download them from https://docs.aws.amazon.com/cli/latest/userguide/getting-started-install.html
#
# If you see an error like along the lines of "'charmap' codec can't encode
# character '\u200e' in position 42: character maps to <undefined>" then that
# means a filename has a Unicode codepoint and the dumb aws Python code is
# trying to read it using your system's locale, which is very likely not set to
# use the Windows UTF-8 beta feature. This is an ongoing issue in this tool
# that goes back to 2013!!! There's no way to fix it using environment
# variables, at least nothing worked for me. The fix provided by the devs is
# heavy handed: you change your system locale to use UTF-8... This has
# consequences though like breaking legacy apps that don't have Unicode support
# and I'm sure other weird things will happen, such as file corruption. Anyway,
# if you're getting this charmap error then I suggest changing your system
# locale, run this again, then switch back to your previous locale. If you
# don't get the canonical file name then you won't be able to restore it.
#
# You can enable the UTF-8 locale with:
#
# win+r -> intl.cpl -> Administrative tab -> Change system locale -> Beta: Use Unicode UTF-8 box.
#

if which tput >/dev/null 2>&1; then
    ncolors=$(tput colors)
fi
if [ -t 1 ] && [ -n "$ncolors" ] && [ "$ncolors" -ge 8 ]; then
    RED="$(tput setaf 1)"
    GREEN="$(tput setaf 2)"
    YELLOW="$(tput setaf 3)"
    BLUE="$(tput setaf 4)"
    MAGENTA="$(tput setaf 5)"
    CYAN="$(tput setaf 6)"
    BOLD="$(tput bold)"
    NORMAL="$(tput sgr0)"
else
    RED=""
    GREEN=""
    YELLOW=""
    BLUE=""
    MAGENTA=""
    CYAN=""
    BOLD=""
    NORMAL=""
fi

error() {
    printf "${BOLD}${RED}$1${NORMAL}\n"
}

abort() {
  error "\nAborting...\n"
  exit 1
}

set -e

bucket="$1"
path="$2"
output_file="$3"

if [[ $bucket == "" || $path == "" || $output_file == "" ]]; then
    error "Usage: aws-list-deep-glacier-files <bucket-name> <path-in-bucket> <output-file>"
    exit 1
fi

aws s3api list-objects-v2 --bucket $bucket --prefix $path --query "Contents[?StorageClass=='DEEP_ARCHIVE']" --output text | LC_ALL=C awk '{print substr($0, index($0, $2))}' | awk '{NF-=3};3' > "$output_file"