canalhandia/preflight.sh

#!/usr/bin/env bash
# Pre-flight harness for a Canalhandia deploy.
#
# Every check below is READ-ONLY. It never restarts the server, never writes to
# the plugins directory, and never touches the world. Run it after staging a
# jar and before asking Crafty to restart: a red line here is a crash-on-boot
# you get to fix while the server is still up.
#
# Usage:  ./preflight.sh [path/to/new.jar]
#         (defaults to target/Canalhandia-1.0.0.jar)

set -uo pipefail

JAR="${1:-target/Canalhandia-1.0.0.jar}"
NS=minecraft
SERVER_ID=6e39a8b2-300b-42d6-8139-f397c23e461b
PLUGINS="/crafty/servers/${SERVER_ID}/plugins"
K="microk8s kubectl -n ${NS}"

fail=0
pass() { printf '  \033[32mOK\033[0m   %s\n' "$1"; }
warn() { printf '  \033[33mWARN\033[0m %s\n' "$1"; }
bad()  { printf '  \033[31mFAIL\033[0m %s\n' "$1"; fail=$((fail + 1)); }
head() { printf '\n\033[1m%s\033[0m\n' "$1"; }

CRAFTY=$($K get pods -l app=crafty-controller -o jsonpath='{.items[0].metadata.name}' 2>/dev/null)
if [ -z "$CRAFTY" ]; then
  CRAFTY=$($K get pods --no-headers 2>/dev/null | awk '/^crafty-controller/ {print $1; exit}')
fi

head "1. Local build"

if [ ! -f "$JAR" ]; then
  bad "jar not found: $JAR"
else
  pass "jar present: $JAR ($(stat -c%s "$JAR") bytes)"
  # A jar that does not open is a jar the server will refuse at boot.
  if unzip -t "$JAR" >/dev/null 2>&1; then
    pass "jar archive is intact"
  else
    bad "jar archive is corrupt (unzip -t failed)"
  fi
  # plugin.yml is the only file Bukkit truly requires; without it the plugin is
  # skipped silently and nothing in the deploy takes effect.
  if unzip -p "$JAR" plugin.yml >/dev/null 2>&1; then
    pass "plugin.yml present in jar"
  else
    bad "plugin.yml MISSING from jar — the plugin would not load at all"
  fi
  # Every command the code registers must exist in plugin.yml, or register()
  # logs a warning and the command silently does nothing in game.
  missing=""
  for cmd in canalhandia curiosidade adivinha enquete ranking reagir reacoes \
             palpite votar legal wow top f ia iap errado; do
    unzip -p "$JAR" plugin.yml 2>/dev/null | grep -qE "^  ${cmd}:" || missing="$missing $cmd"
  done
  if [ -z "$missing" ]; then
    pass "all 16 commands declared in plugin.yml"
  else
    bad "commands missing from plugin.yml:$missing"
  fi
  # config.yml ships defaults; a jar without it means saveDefaultConfig() writes
  # nothing and every setting silently falls back to the hardcoded default.
  if unzip -p "$JAR" config.yml >/dev/null 2>&1; then
    pass "config.yml present in jar"
  else
    bad "config.yml MISSING from jar"
  fi
fi

head "2. Tests"
if [ -d target/surefire-reports ]; then
  tests=$(grep -ho 'tests="[0-9]*"' target/surefire-reports/*.xml 2>/dev/null |
          grep -o '[0-9]*' | paste -sd+ | bc)
  bads=$(grep -ho 'failures="[0-9]*"\|errors="[0-9]*"' target/surefire-reports/*.xml 2>/dev/null |
         grep -o '[0-9]*' | paste -sd+ | bc)
  if [ "${bads:-1}" = "0" ]; then
    pass "${tests} tests, 0 failures/errors"
  else
    bad "${bads} test failures/errors — run mvn test"
  fi
else
  warn "no surefire reports; run the test suite before deploying"
fi

head "3. Cluster"
if [ -z "$CRAFTY" ]; then
  bad "crafty-controller pod not found in namespace ${NS}"
else
  pass "crafty pod: $CRAFTY"
  if $K exec "$CRAFTY" -- test -d "$PLUGINS" 2>/dev/null; then
    pass "plugins directory reachable"
  else
    bad "cannot reach $PLUGINS"
  fi
fi

head "4. Staged jar on the server"
if [ -n "$CRAFTY" ] && [ -f "$JAR" ]; then
  local_sum=$(sha256sum "$JAR" | cut -c1-8)
  remote_sum=$($K exec "$CRAFTY" -- sha256sum "$PLUGINS/Canalhandia-1.0.0.jar" 2>/dev/null | cut -c1-8)
  if [ -z "$remote_sum" ]; then
    bad "no Canalhandia jar staged on the server"
  elif [ "$local_sum" = "$remote_sum" ]; then
    pass "staged jar matches the local build (sha $local_sum)"
  else
    bad "staged jar is sha $remote_sum, local build is $local_sum — copy it again"
  fi
  # Ownership: the JVM runs as uid 1000 / gid 0. A root-owned jar is a jar the
  # server cannot read, and the failure looks like "plugin just did not load".
  owner=$($K exec "$CRAFTY" -- stat -c '%u:%g' "$PLUGINS/Canalhandia-1.0.0.jar" 2>/dev/null)
  if [ "$owner" = "1000:0" ]; then
    pass "jar ownership 1000:0"
  else
    bad "jar ownership is '$owner', expected 1000:0 — chown it"
  fi
  # A rollback target must exist before, not after, something goes wrong.
  if $K exec "$CRAFTY" -- sh -c "ls $PLUGINS/Canalhandia-1.0.0.jar.bak-* >/dev/null 2>&1"; then
    pass "rollback jar(s) present"
  else
    bad "no .bak jar to roll back to"
  fi
fi

head "5. Live config"
if [ -n "$CRAFTY" ]; then
  cfg="$PLUGINS/Canalhandia/config.yml"
  if $K exec "$CRAFTY" -- test -f "$cfg" 2>/dev/null; then
    pass "config.yml present on the server"
    # Parsed HERE rather than in the pod: the crafty image has no python, and a
    # config.yml that does not parse is a plugin that disables itself on boot.
    tmp=$(mktemp)
    if $K exec "$CRAFTY" -- cat "$cfg" > "$tmp" 2>/dev/null && [ -s "$tmp" ]; then
      # Pick a parser. "no parser available" must NOT be reported as "invalid":
      # a harness that cries wolf is a harness people learn to ignore.
      if python3 -c "import yaml" 2>/dev/null; then
        yaml_check() { python3 -c "import yaml,sys;yaml.safe_load(open(sys.argv[1]))" "$1"; }
      elif command -v docker >/dev/null 2>&1; then
        yaml_check() { docker run --rm -v "$1":/c.yml:ro python:3.12-slim \
            sh -c "pip install -q pyyaml >/dev/null 2>&1 && python3 -c \
            'import yaml;yaml.safe_load(open(\"/c.yml\"))'"; }
      else
        yaml_check() { return 2; }
      fi
      yaml_check "$tmp" 2>/dev/null
      case $? in
        0) pass "config.yml parses as valid YAML" ;;
        2) warn "no YAML parser available (pip install pyyaml) — not checked" ;;
        *) bad "config.yml on the server is NOT valid YAML — the plugin would fail to load" ;;
      esac
      # The keys this deploy depends on. A missing key is not fatal (Settings
      # has defaults) but it means the merge did not happen as intended.
      for key in "modulos:" "zoacao:" "personalidade:" "contexto-chat:" "estado-servidor:"; do
        if grep -q "$key" "$tmp"; then
          pass "config has ${key%:}"
        else
          warn "config has no '${key%:}' — will fall back to the built-in default"
        fi
      done
    else
      warn "could not read config.yml out of the pod"
    fi
    rm -f "$tmp"
    if $K exec "$CRAFTY" -- sh -c "ls $PLUGINS/Canalhandia/config.yml.bak-* >/dev/null 2>&1"; then
      pass "config backup(s) present"
    else
      bad "no config.yml.bak-* to roll back to"
    fi
  else
    bad "config.yml missing on the server"
  fi
fi

head "6. Server health right now"
if [ -n "$CRAFTY" ]; then
  logf="/crafty/servers/${SERVER_ID}/logs/latest.log"
  # tr -dc keeps digits only: grep -c prints nothing on no-match under some
  # shells, and the stray newline made the numeric test below explode.
  online=$($K exec "$CRAFTY" -- sh -c "grep -c 'joined the game' $logf" 2>/dev/null | tr -dc '0-9')
  pass "log readable (${online:-0} join lines this session)"
  errs=$($K exec "$CRAFTY" -- sh -c "tail -500 $logf | grep -ci 'ERROR\]'" 2>/dev/null | tr -dc '0-9')
  if [ "${errs:-0}" -gt 0 ]; then
    warn "${errs} ERROR lines in the last 500 — read them before restarting"
  else
    pass "no ERROR lines in the last 500"
  fi
fi

printf '\n'
if [ "$fail" -eq 0 ]; then
  printf '\033[32mPRE-FLIGHT CLEAN — safe to restart.\033[0m\n'
  exit 0
fi
printf '\033[31m%d CHECK(S) FAILED — do NOT restart yet.\033[0m\n' "$fail"
exit 1