#!/usr/bin/env bash
#
# JbTecWiz Support Centre -- generated fix script
#
# Fault : Docker breaks the host network, or containers cannot resolve names
# Fix   : Give containers a resolver they can reach
# Source: https://jbtecwiz.com/support/lnx-ctr-network
#
# Run as     : Root shell
# Expect     : 25 minutes
# Risk       : medium
# Reversible : yes
#
# WHEN THIS IS THE RIGHT FIX
#   Containers resolve nothing, or only external names.
#
# HOW TO UNDO IT
#   Remove the dns keys from daemon.json and restart Docker.
#
# Walks the fix one step at a time and asks before each. Steps with no
# command are yours to do -- it prints those and waits. DRYRUN=1 prints
# without executing; UNATTENDED=1 does not ask.
#
# --------------------------------------------------------------------
# NO WARRANTY - USE AT YOUR OWN RISK
#
# This script is provided by JbTecWiz as-is and with no warranty of any
# kind, express or implied. You run it entirely at your own risk.
#
# JbTecWiz accepts no liability for any loss or damage arising from its
# use, including but not limited to data loss, downtime, or configuration
# changes that turn out to be wrong for your system.
#
# You are responsible for reading this script before running it, for
# satisfying yourself that it suits the machine in front of you, and for
# having a working backup first. Some steps cannot be undone.
# --------------------------------------------------------------------

set -uo pipefail
DRYRUN="${DRYRUN:-0}"
UNATTENDED="${UNATTENDED:-0}"
failed=0

if [ "$(id -u)" -ne 0 ]; then
  echo "  This fix is documented as needing root. Re-run with sudo." >&2
  exit 3
fi

rule() { printf "\n%s\n" "$(printf '-%.0s' $(seq 1 70))"; if [ $# -gt 0 ]; then echo "$1"; fi; }
prose() { echo "$1" | fold -s -w 74 | sed "s/^/  /"; }

# Returns 0 when the caller should run the command, 1 when it should not.
# A manual step always returns 1 -- there is nothing for the caller to run.
step() {  # step <n> <do> <why> <manual|cmd> [command lines...]
  local n="$1" dotext="$2" why="$3" mode="$4"; shift 4
  rule "  Step $n of 5"
  prose "$dotext"
  if [ -n "$why" ]; then echo; prose "$why"; fi
  if [ "$mode" = "manual" ]; then
    echo; echo "  -> Do this yourself, then press Enter to carry on."
    if [ "$UNATTENDED" = "0" ] && [ "$DRYRUN" = "0" ]; then read -r _; fi
    return 1
  fi
  echo; printf "    %s\n" "$@"; echo
  if [ "$DRYRUN" = "1" ]; then echo "  (dry run -- not executed)"; return 1; fi
  if [ "$UNATTENDED" = "0" ]; then
    read -r -p "  Run this step? [Y]es / [S]kip / [Q]uit " a
    case "$a" in
      [Qq]*) echo "  Stopped at your request."; exit 0 ;;
      [Ss]*) echo "  Skipped."; return 1 ;;
    esac
  fi
  return 0
}

rule
echo "  Docker breaks the host network, or containers cannot resolve names"
echo "  Give containers a resolver they can reach"
echo
echo "  Risk: medium   Reversible   25 minutes"
echo
prose 'No warranty. Use at your own risk - JbTecWiz accepts no liability. Read it before you run it, and have a backup.'
rule
echo
if [ "$UNATTENDED" = "0" ] && [ "$DRYRUN" = "0" ]; then
  read -r -p "  Ready? [y/N] " go
  case "$go" in [Yy]*) ;; *) echo "  Nothing was changed."; exit 0;; esac
fi

if step 1 'See what the container was given.' '' cmd 'docker run --rm alpine cat /etc/resolv.conf' 'cat /etc/resolv.conf'; then
  docker run --rm alpine cat /etc/resolv.conf
  cat /etc/resolv.conf
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 1 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 2 'If the host'\''s resolv.conf points at 127.0.0.53, Docker substitutes public resolvers -- which cannot resolve internal names.' 'This is why a container can reach the internet and not the company'\''s own DNS. The loopback stub resolver is meaningless inside the container'\''s namespace, so Docker silently swaps in 8.8.8.8.' cmd 'resolvectl status | head -20'; then
  resolvectl status | head -20
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 2 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 3 'Set real resolvers for the daemon.' '' cmd 'sudo tee -a /etc/docker/daemon.json >/dev/null <<'\''EOF'\''' '{' '  "dns": ["10.0.0.10", "10.0.0.11"],' '  "dns-search": ["example.local"]' '}' 'EOF' 'sudo systemctl restart docker'; then
  sudo tee -a /etc/docker/daemon.json >/dev/null <<'EOF'
  {
    "dns": ["10.0.0.10", "10.0.0.11"],
    "dns-search": ["example.local"]
  }
  EOF
  sudo systemctl restart docker
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 3 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 4 'Remember that container-to-container name resolution only works on a user-defined network, not on the default bridge.' 'This surprises people constantly: containers on the default bridge cannot resolve each other by name at all. Creating a network is the fix, and it takes one command.' cmd 'docker network create appnet' 'docker run -d --name db --network appnet postgres:16' 'docker run --rm --network appnet alpine nslookup db'; then
  docker network create appnet
  docker run -d --name db --network appnet postgres:16
  docker run --rm --network appnet alpine nslookup db
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 4 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 5 'Check the daemon.json is valid JSON -- two separate objects appended will stop Docker starting.' '' cmd 'python3 -m json.tool < /etc/docker/daemon.json'; then
  python3 -m json.tool < /etc/docker/daemon.json
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 5 failed. The rest of the fix may depend on it." >&2
  fi
fi

rule "  Confirm it worked"
prose 'A container resolves both internal and external names.'
if [ "$DRYRUN" = "0" ]; then
  docker run --rm alpine sh -c 'nslookup fileserver.example.local; nslookup google.com'
fi

rule
if [ "$failed" -gt 0 ]; then
  echo "  Finished with $failed failed step(s)."
  echo "  Read the full write-up at https://jbtecwiz.com/support/lnx-ctr-network"
else
  echo "  Finished."
fi
echo
prose 'To undo: Remove the dns keys from daemon.json and restart Docker.'
rule