#!/usr/bin/env bash
# Branch, PR body, and commit contract checker.
# v2: exits 1 on violation. Consumers that want warn-only set
# continue-on-error: true on the job (or stay on @v1).
set -euo pipefail

BRANCH="${HEAD_BRANCH:-}"
TITLE="${PR_TITLE:-}"
AUTHOR="${PR_AUTHOR:-}"
BODY="${PR_BODY:-}"
BASE="${BASE_SHA:-}"
HEAD="${HEAD_SHA:-}"

# Gitea renders HTML comments as hidden. Validate the visible body so required
# tracking and attribution cannot exist only in comment source.
VISIBLE_BODY=$(printf '%s\n' "${BODY}" | awk '
  {
    line=$0
    fence_pos=1
    while (fence_pos <= 3 && substr(line, fence_pos, 1) == " ") fence_pos++
    fence_char=substr(line, fence_pos, 1)
    fence_run=0
    if (fence_char == "`" || fence_char == "~") {
      while (substr(line, fence_pos + fence_run, 1) == fence_char) fence_run++
    }
    if (in_fence) {
      print line
      if (fence_char == active_fence_char && fence_run >= active_fence_run) in_fence=0
      next
    }
    if (fence_run >= 3) {
      in_fence=1
      active_fence_char=fence_char
      active_fence_run=fence_run
      print line
      next
    }

    visible=""
    pos=1
    while (pos <= length(line)) {
      if (in_comment) {
        rest=substr(line, pos)
        comment_end=index(rest, "-->")
        if (comment_end == 0) {
          pos=length(line) + 1
          break
        }
        visible=visible " "
        pos += comment_end + 2
        in_comment=0
        continue
      }

      if (substr(line, pos, 1) == "`") {
        ticks=1
        while (substr(line, pos + ticks, 1) == "`") ticks++
        close_pos=pos + ticks
        found_close=0
        while (close_pos <= length(line)) {
          if (substr(line, close_pos - 1, 1) != "`" &&
              substr(line, close_pos, ticks) == substr(line, pos, ticks) &&
              substr(line, close_pos + ticks, 1) != "`") {
            found_close=1
            break
          }
          close_pos++
        }
        if (found_close) {
          visible=visible substr(line, pos, close_pos + ticks - pos)
          pos=close_pos + ticks
          continue
        }
      }

      if (substr(line, pos, 4) == "<!--") {
        visible=visible " "
        in_comment=1
        pos += 4
        continue
      }
      visible=visible substr(line, pos, 1)
      pos++
    }
    print visible
  }
')

# Break-glass: dfritz is exempt from all naming checks.
if [ "${AUTHOR}" = "dfritz" ]; then
  echo "check-naming: dfritz break-glass — exempt"
  exit 0
fi

FAILED=0
BRANCH_KIND="invalid"
BRANCH_BUG=""

# ---- branch form ----
# <role>/bug-<id>/<kebab>
if echo "${BRANCH}" | grep -qE "^(dev|ux|ops|security|perf|architect|support)/bug-[a-z0-9]+/[a-z0-9][a-z0-9-]*$"; then
  BRANCH_KIND="role-bug"
  BRANCH_BUG=$(echo "${BRANCH}" | sed -E 's|^[^/]+/(bug-[a-z0-9]+)/.*|\1|')
# chore/<kebab>
elif echo "${BRANCH}" | grep -qE "^chore/[a-z0-9][a-z0-9-]*$"; then
  BRANCH_KIND="chore"
else
  echo "FAIL[check-naming]: branch '${BRANCH}' does not match convention"
  echo "  expected: <role>/bug-<id>/<kebab>  (role: dev|ux|ops|security|perf|architect|support)"
  echo "         or: chore/<kebab>"
  FAILED=1
fi

# ---- title form ----
TITLE_BUG=""
if echo "${TITLE}" | grep -qE "^\[bug-[a-z0-9]+\] ."; then
  TITLE_BUG=$(echo "${TITLE}" | sed -E 's|^\[(bug-[a-z0-9]+)\].*|\1|')
fi

PLAIN_TITLE=$(printf '%s\n' "${TITLE}" | sed -E 's/^\[bug-[a-z0-9]+\][[:space:]]+//')
if printf '%s\n' "${PLAIN_TITLE}" | grep -qE '^(build|chore|ci|docs|feat|fix|perf|refactor|revert|style|test)(\([^)]*\))?!?:[[:space:]]'; then
  echo "FAIL[check-naming]: title must be a plain-language imperative without Conventional Commit syntax"
  FAILED=1
fi

if [ "${BRANCH_KIND}" = "role-bug" ]; then
  if [ -z "${TITLE_BUG}" ]; then
    echo "FAIL[check-naming]: title must lead with [${BRANCH_BUG}]"
    echo "  have: ${TITLE}"
    echo "  want: [${BRANCH_BUG}] ${TITLE}"
    FAILED=1
  elif [ "${TITLE_BUG}" != "${BRANCH_BUG}" ]; then
    echo "FAIL[check-naming]: bug-id mismatch — branch carries '${BRANCH_BUG}' but title carries '${TITLE_BUG}'"
    FAILED=1
  fi

  tracking=$(printf '%s\n' "${VISIBLE_BODY}" | awk '
    /^## Tracking[[:space:]]*$/ { in_section=1; next }
    /^## / && in_section { exit }
    in_section { print }
  ')
  if [ -z "${tracking}" ]; then
    echo "FAIL[check-naming]: PR body must contain a non-empty ## Tracking section"
    FAILED=1
  else
    if ! printf '%s\n' "${tracking}" | grep -qE "(^|[[:space:]])Fixes[[:space:]]+${BRANCH_BUG}([^a-z0-9]|$)"; then
      echo "FAIL[check-naming]: ## Tracking must contain the literal token 'Fixes ${BRANCH_BUG}'"
      FAILED=1
    fi
    if ! printf '%s\n' "${tracking}" | grep -Fq "https://agenthub.fritzlab.net/${BRANCH_BUG}"; then
      echo "FAIL[check-naming]: ## Tracking must link https://agenthub.fritzlab.net/${BRANCH_BUG}"
      FAILED=1
    fi
  fi

elif [ "${BRANCH_KIND}" = "chore" ] && [ -n "${TITLE_BUG}" ]; then
  echo "FAIL[check-naming]: chore branch should not carry a [bug-id] title prefix"
  FAILED=1
fi

if [ "${BRANCH_KIND}" != "invalid" ]; then
  attribution=$(printf '%s\n' "${VISIBLE_BODY}" | awk '
    /^## Attribution[[:space:]]*$/ { in_section=1; next }
    /^## / && in_section { exit }
    in_section { print }
  ')
  watermark_re='^[-*]?[[:space:]]*Authored-By: .+ \(.+\) <noreply@[[:alnum:].-]+>$'
  if ! printf '%s\n' "${attribution}" | grep -qE "${watermark_re}"; then
    echo "FAIL[check-naming]: ## Attribution must contain an Authored-By product/model watermark"
    FAILED=1
  fi

  if ! printf '%s\n%s\n' "${BASE}" "${HEAD}" | grep -qEv '^[0-9a-f]{40,64}$'; then
    for revision in "${BASE}" "${HEAD}"; do
      if ! git cat-file -e "${revision}^{commit}" 2>/dev/null; then
        echo "FAIL[check-naming]: base-sha and head-sha must name available commits"
        FAILED=1
        break
      fi
    done
    if git cat-file -e "${BASE}^{commit}" 2>/dev/null && git cat-file -e "${HEAD}^{commit}" 2>/dev/null; then
      commit_count=0
      while IFS= read -r commit; do
        [ -n "${commit}" ] || continue
        commit_count=$((commit_count + 1))
        message=$(git log -1 --format=%B "${commit}")
        if ! printf '%s\n' "${message}" | awk '
          { line[NR]=$0 }
          END {
            n=NR
            while (n > 0 && line[n] == "") n--
            if (n < 3 || line[n-1] != "" || line[n] !~ /^Authored-By: .+ \(.+\) <noreply@[[:alnum:].-]+>$/) exit 1
          }
        '; then
          echo "FAIL[check-naming]: commit ${commit} must end with an Authored-By product/model trailer"
          FAILED=1
        fi
      done < <(git rev-list --reverse "${BASE}..${HEAD}" 2>/dev/null)
      if [ "${commit_count}" -eq 0 ]; then
        echo "FAIL[check-naming]: base-sha..head-sha contains no PR commits"
        FAILED=1
      fi
    fi
  else
    echo "FAIL[check-naming]: base-sha and head-sha must be lowercase hexadecimal commit SHAs"
    FAILED=1
  fi
fi

if [ "${FAILED}" -eq 0 ]; then
  echo "check-naming: ok"
fi

exit "${FAILED}"