#!/bin/bash
# genome-raw-commit <genome>
#
# Commit the raw files that Syncthing has placed in the vault and push them to origin/<base>.
#   - Committer = n8n-bot (sole pusher); Author = the person who wrote it (Syncthing modifiedBy -> .authors.json)
#   - One commit per author (single-device => one commit). No-op if there is nothing.
#   - JSON output built with jq (safe escaping), with a `files` array:
#     for each raw -> file, author, local_path, local_url (file://), remote_url (Forgejo web).

set -euo pipefail
genome="${1:?usage: genome-raw-commit <genome>}"

# Input validation to prevent path or URL traversal inside the script
[[ "$genome" =~ ^[a-z0-9][a-z0-9-]{0,63}$ ]] || { echo '{"status":"error","reason":"invalid genome name"}'; exit 1; }

set -a; . "${HOME}/.config/knowledge-genome.env"; set +a
: "${GENOME_VAULTS_ROOT:=/srv/genome-vaults}"
: "${GENOME_BASE:=develop}"
: "${FORGEJO_USER:=n8n-bot}"
: "${FORGEJO_HOST:=127.0.0.1:3001}"
: "${FORGEJO_OWNER:=Keru}"
: "${FORGEJO_WEB_BASE:=https://git.keruhomelab.com}
: "${SYNCTHING_URL:=http://127.0.0.1:8384}"
: "${COMMITTER_NAME:=n8n-bot}"
: "${COMMITTER_EMAIL:=n8n-bot@homelab}"
: "${DEFAULT_AUTHOR_NAME:=Unknown}"
: "${DEFAULT_AUTHOR_EMAIL:=unknown@syncthing}"

vault="${GENOME_VAULTS_ROOT}/${genome}"
fid="${genome}-public"
authors_map="${GENOME_VAULTS_ROOT}/.authors.json"
clone_url="http://${FORGEJO_USER}@${FORGEJO_HOST}/${FORGEJO_OWNER}/${genome}.git"
export GIT_ASKPASS=/usr/local/bin/genome-askpass

[[ -d "${vault}/.git" ]] || { printf '{"status":"error","reason":"vault absent","genome":"%s"}\n' "$genome"; exit 1; }
cd "$vault"
git config user.name  "$COMMITTER_NAME"
git config user.email "$COMMITTER_EMAIL"
git config commit.gpgsign false

grep -qxF 'raw/.stignore' "${vault}/.git/info/exclude" 2>/dev/null || echo 'raw/.stignore' >> "${vault}/.git/info/exclude"
grep -qxF 'raw/.stfolder' "${vault}/.git/info/exclude" 2>/dev/null || echo 'raw/.stfolder' >> "${vault}/.git/info/exclude"

git add -A -- raw/
git reset -q -- raw/.stignore raw/.stfolder 2>/dev/null || true
if git diff --cached --quiet; then
  printf '{"status":"noop","genome":"%s"}\n' "$genome"
  exit 0
fi

resolve_dev() {  # $1 = path relativo al vault (raw/...) -> stampa lo short device id o vuoto
  [[ -z "${SYNCTHING_API_KEY:-}" ]] && return 0
  curl -fsS -H "X-API-Key: ${SYNCTHING_API_KEY}" --get "${SYNCTHING_URL}/rest/db/file" \
    --data-urlencode "folder=${fid}" --data-urlencode "file=${1#raw/}" 2>/dev/null \
    | jq -r '.local.modifiedBy // empty' 2>/dev/null || true
}
author_for_dev() {  # $1 = device id -> stampa "name\temail"
  local dev="$1" name="$DEFAULT_AUTHOR_NAME" email="$DEFAULT_AUTHOR_EMAIL"
  if [[ -n "$dev" && -f "$authors_map" ]] && jq -e --arg d "$dev" '.[$d]' "$authors_map" >/dev/null 2>&1; then
    name="$(jq -r --arg d "$dev" '.[$d].name'  "$authors_map")"
    email="$(jq -r --arg d "$dev" '.[$d].email' "$authors_map")"
  fi
  printf '%s\t%s' "$name" "$email"
}

# raccolgo per-file (relpath, author) e raggruppo per autore per il commit
declare -A G_FILES G_NAME G_EMAIL
declare -a ROWS
while IFS= read -r f; do
  [[ -z "$f" ]] && continue
  dev="$(resolve_dev "$f")"
  IFS=$'\t' read -r aname aemail <<< "$(author_for_dev "$dev")"
  ROWS+=("${f}"$'\t'"${aname}")
  key="${aname} <${aemail}>"
  G_FILES["$key"]+="${f}"$'\n'
  G_NAME["$key"]="$aname"; G_EMAIL["$key"]="$aemail"
done < <(git diff --cached --name-only -- raw/)

ts="$(date +%Y-%m-%dT%H:%M:%S%z)"
commits=0; summary=""
for key in "${!G_FILES[@]}"; do
  mapfile -t files < <(printf '%s' "${G_FILES[$key]}")
  short="$(printf '%s\n' "${files[@]}" | sed 's#^raw/##' | paste -sd, -)"
  msg="$(printf 'raw(%s): sync %s\n\nAdded-by-device: %s\nSyncthing-device-id: %s\nSource: syncthing-autocommit\nSynced-at: %s\n' \
        "$genome" "$short" "${G_DEV[$key]}" "${G_DEV[$key]}" "$ts")"
  git commit -q --author="$key" -m "$msg" -- "${files[@]}"
  commits=$((commits+1))
  summary="${summary}${summary:+; }${G_NAME[$key]}:${short}"
done

# Fetch updates from origin to merge upstream modifications before pushing
git fetch -q origin
if git show-ref --verify --quiet "refs/remotes/origin/${GENOME_BASE}"; then
  git rebase -q "origin/${GENOME_BASE}" \
    || { git rebase --abort 2>/dev/null || true; printf '{"status":"error","reason":"rebase-conflict","genome":"%s"}\n' "$genome"; exit 1; }
fi
git push -q "$clone_url" "HEAD:${GENOME_BASE}"

printf '{"status":"ok","genome":"%s","base":"%s","commits":%d","head":"%s","summary":"%s"}\n' \
  "$genome" "$GENOME_BASE" $commits "$(git rev-parse --short HEAD)" "$summary"