#!/usr/bin/env bash
#
# JbTecWiz Support Centre -- generated fix script
#
# Fault : Name resolution fails but the network is up
# Fix   : Fix systemd-resolved's upstream
# Source: https://jbtecwiz.com/support/lnx-dns-resolve
#
# Run as     : Shell as root
# Expect     : 20 minutes
# Risk       : low
# Reversible : yes
#
# WHEN THIS IS THE RIGHT FIX
#   resolv.conf points at 127.0.0.53. The real configuration is not in
#   that file.
#
# HOW TO UNDO IT
#   sudo resolvectl revert eth0 undoes runtime changes to that interface.
#
# 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

# - THIS SCRIPT WILL NOT RUN UNTIL YOU EDIT IT -
cat >&2 <<'EOF'

  This script needs editing before it can run.
  Replace each of these with a real value:
    example.com   (a placeholder domain)

  Then delete this block near the top of the script.

EOF
exit 2

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 $n of 6"
  prose "$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 "  Name resolution fails but the network is up"
echo "  Fix systemd-resolved'\''s upstream"
echo
echo "  Risk: low   Reversible   20 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 'Ask resolved what it is actually using per interface.' 'Editing /etc/resolv.conf on a resolved system is pointless -- it is generated, and your edit is overwritten on the next network change. This command shows the configuration that matters.' cmd 'resolvectl status'; then
  resolvectl status
  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 'Test resolution through the stub and directly, to separate the two.' '' cmd 'resolvectl query example.com' 'dig +short example.com @1.1.1.1'; then
  resolvectl query example.com
  dig +short example.com @1.1.1.1
  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 'If the upstream is empty or wrong, set it on the interface.' '' cmd 'sudo resolvectl dns eth0 10.0.0.10 10.0.0.11' 'sudo resolvectl domain eth0 example.local'; then
  sudo resolvectl dns eth0 10.0.0.10 10.0.0.11
  sudo resolvectl domain eth0 example.local
  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 'Make it permanent in the network configuration rather than at runtime. On Ubuntu with netplan:' '' cmd 'sudo nano /etc/netplan/01-netcfg.yaml' 'sudo netplan apply'; then
  sudo nano /etc/netplan/01-netcfg.yaml
  sudo netplan apply
  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 'Flush the cache and re-test.' '' cmd 'sudo resolvectl flush-caches' 'getent hosts example.com'; then
  sudo resolvectl flush-caches
  getent hosts example.com
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 5 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 6 'Confirm the symlink is intact -- a VPN client that replaced it with a static file causes intermittent failures.' '' cmd 'ls -l /etc/resolv.conf'; then
  ls -l /etc/resolv.conf
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 6 failed. The rest of the fix may depend on it." >&2
  fi
fi

rule "  Confirm it worked"
prose 'Names resolve and resolvectl shows the expected servers.'
if [ "$DRYRUN" = "0" ]; then
  resolvectl status | grep -A3 'Current DNS'
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-dns-resolve"
else
  echo "  Finished."
fi
echo
prose 'To undo: sudo resolvectl revert eth0 undoes runtime changes to that interface.'
rule