#!/usr/bin/env bash
#
# What is on wj that is not on main, and where each commit belongs.
#
#     tools/wj-status.sh              classify everything unpromoted
#     tools/wj-status.sh --product    print just the promotable SHAs
#
# The second form is meant to be read by a person and then pasted, oldest
# first:
#
#     tools/promote-to-main.sh $(tools/wj-status.sh --product)
#
# HOW A COMMIT IS CLASSIFIED
#
# By a trailer you write at commit time:
#
#     Scope: product     belongs on main, the rest of the world should have it
#     Scope: site        belongs to this site alone, keep it on wj
#
# Intent is the only thing that can actually decide this, and you have it when
# you write the commit, not months later when you are staring at a list of
# subject lines trying to remember.
#
# Where there is no trailer this falls back to paths, but the fallback is
# deliberately weak, and says so. Under ADR-015 the only site-specific home in
# the tree is scripts/site_imports/<site>/ - everything else is meant to be
# product with settings and seed data carrying the differences. So "touches
# only site_imports" is the one confident site verdict available, and anything
# else is reported as UNMARKED rather than guessed into a bucket.
set -euo pipefail

cd "$(git rev-parse --show-toplevel)"

MODE="${1:-report}"

if ! git show-ref --verify --quiet refs/heads/main; then
  echo "ERROR: no main branch here." >&2
  exit 1
fi

RANGE="main..wj"
if ! git rev-parse --verify --quiet refs/heads/wj >/dev/null; then
  echo "ERROR: no wj branch here." >&2
  exit 1
fi

COMMITS="$(git rev-list --reverse "$RANGE")"

if [ -z "$COMMITS" ]; then
  echo "Nothing on wj that main does not have."
  exit 0
fi

classify() {
  local sha="$1"
  local scope
  scope="$(git log -1 --format='%(trailers:key=Scope,valueonly)' "$sha" | tr -d '[:space:]')"
  case "$(printf '%s' "$scope" | tr '[:upper:]' '[:lower:]')" in
    product) echo product; return ;;
    site)    echo site;    return ;;
  esac

  # No trailer. The only confident verdict from paths alone.
  local files outside
  files="$(git show --pretty=format: --name-only "$sha" | sed '/^$/d')"
  outside="$(printf '%s\n' "$files" | grep -v '^scripts/site_imports/' || true)"
  if [ -n "$files" ] && [ -z "$outside" ]; then
    echo site-by-path
  else
    echo unmarked
  fi
}

if [ "$MODE" = "--product" ]; then
  for sha in $COMMITS; do
    if [ "$(classify "$sha")" = "product" ]; then
      printf '%s ' "$sha"
    fi
  done
  echo
  exit 0
fi

product_shas=""
unmarked_count=0

echo "On wj, not on main - oldest first"
echo

for sha in $COMMITS; do
  verdict="$(classify "$sha")"
  subject="$(git log -1 --format='%h %s' "$sha")"
  case "$verdict" in
    product)
      echo "  [PRODUCT ] $subject"
      product_shas="$product_shas $sha"
      ;;
    site)
      echo "  [SITE    ] $subject"
      ;;
    site-by-path)
      echo "  [site?   ] $subject"
      echo "             touches only scripts/site_imports/ - looks site-only, not marked"
      ;;
    *)
      echo "  [UNMARKED] $subject"
      unmarked_count=$((unmarked_count + 1))
      ;;
  esac
done

echo
if [ -n "$product_shas" ]; then
  echo "Marked for main:"
  echo "    tools/promote-to-main.sh$product_shas"
  echo
fi

if [ "$unmarked_count" -gt 0 ]; then
  echo "$unmarked_count commit(s) carry no Scope trailer."
  echo
  echo "That is not a failure - it just means nobody decided yet. Under ADR-015"
  echo "most work is product: site differences are meant to live in settings and"
  echo "seed data, not in a branch. So an unmarked commit is more likely to"
  echo "belong on main than not, and leaving it unmarked is how it ends up"
  echo "stranded here."
  echo
  echo "Mark future ones as you go:"
  echo "    git commit -m \"...\" -m \"Scope: product\""
  echo
  echo "Or decide now and promote the ones that belong:"
  echo "    tools/promote-to-main.sh --dry-run <sha>"
fi