#!/usr/bin/env bash
# dry-run-publish.sh
# Pre-flight a Confluence storage body before posting. Runs:
#   - format sanity (storage XHTML, no wiki markup, no markdown fences)
#   - secret / PII grep (BLOCKER)
#   - macro sanity (every {code} / {plantuml} / panel is in storage form)
#   - PlantUML parse (if plantuml on $PATH)
#   - size sanity (over 300 lines needs justification header)
#
# Usage:
#   bash scripts/dry-run-publish.sh <draft.xml>
#
# Exit codes:
#   0 = ready to post
#   1 = REVISE (MAJOR or MINOR issues found)
#   2 = BLOCK (BLOCKER issues found)

set -u

if [[ $# -lt 1 ]]; then
  echo "Usage: $0 <draft.xml>" >&2
  exit 1
fi

DRAFT="$1"

if [[ ! -f "$DRAFT" ]]; then
  echo "Draft not found: $DRAFT" >&2
  exit 2
fi

BLOCK=0
MAJOR=0
MINOR=0

note_block() { echo "  [BLOCK]  $1"; BLOCK=1; }
note_major() { echo "  [MAJOR]  $1"; MAJOR=1; }
note_minor() { echo "  [MINOR]  $1"; MINOR=1; }

echo "Pre-flight: $DRAFT"
echo "------------------------------------"

# 1. Format sanity
if head -3 "$DRAFT" | grep -q '^---$'; then
  note_block "Markdown front-matter detected -- storage body must not contain --- fences."
fi

if grep -qE '\{code:' "$DRAFT"; then
  note_major "Wiki code-block syntax detected. Use <ac:structured-macro ac:name=\"code\">."
fi
if grep -qE '\{info:' "$DRAFT" || grep -qE '\{note:' "$DRAFT" || grep -qE '\{warning:' "$DRAFT"; then
  note_major "Wiki panel syntax detected. Use <ac:structured-macro ac:name=\"info|note|warning\">."
fi
if grep -qE '\{plantuml' "$DRAFT"; then
  if ! grep -qE '<ac:structured-macro ac:name="plantuml"' "$DRAFT"; then
    note_major "{plantuml} found but not wrapped in <ac:structured-macro ac:name=\"plantuml\">."
  fi
fi

if grep -qE '^#{1,6} ' "$DRAFT"; then
  note_major "Markdown heading detected (# / ## / ###). Use <h1> / <h2> / <h3>."
fi
if grep -qE '^[[:space:]]*```' "$DRAFT"; then
  note_major "Markdown code fence (\`\`\`) detected. Use <ac:structured-macro ac:name=\"code\">."
fi

# 2. Secrets / PII
SECRET_PATTERNS=(
  'AKIA[0-9A-Z]{16}'
  'ghp_[A-Za-z0-9]{30,}'
  'glpat-[A-Za-z0-9_-]{20,}'
  'xox[baprs]-[A-Za-z0-9-]{10,}'
  'sk-[A-Za-z0-9]{40,}'
  'ATATT[A-Za-z0-9]{30,}'
  '-----BEGIN [A-Z ]+PRIVATE KEY-----'
)

for pat in "${SECRET_PATTERNS[@]}"; do
  if grep -qE "$pat" "$DRAFT" 2>/dev/null; then
    note_block "Secret pattern matched: $pat -- scrub before posting."
  fi
done

if grep -qE "Netcracker/Projects/NDO/knowledge" "$DRAFT"; then
  note_block "Body references the local mirror path. Use the public BASS URL."
fi

# 3. Macro sanity
PLANTUML_COUNT=$(grep -cE '<ac:structured-macro ac:name="plantuml"' "$DRAFT" || true)
PLANTUML_COUNT=$(printf '%d' "${PLANTUML_COUNT:-0}" 2>/dev/null || echo 0)
CODE_COUNT=$(grep -cE '<ac:structured-macro ac:name="code"' "$DRAFT" || true)
CODE_COUNT=$(printf '%d' "${CODE_COUNT:-0}" 2>/dev/null || echo 0)

if [[ $PLANTUML_COUNT -gt 0 ]]; then
  if grep -B2 'ac:name="plantuml"' "$DRAFT" | grep -qE '<ac:structured-macro ac:name="(info|note|warning|tip|code)"'; then
    note_major "PlantUML macro appears inside a panel or code block. Move to body root."
  fi
fi

if [[ $CODE_COUNT -gt 0 ]]; then
  if ! grep -q 'ac:parameter ac:name="language"' "$DRAFT"; then
    note_major "{code} block has no language parameter."
  fi
fi

if [[ $PLANTUML_COUNT -gt 0 ]] && command -v plantuml >/dev/null 2>&1; then
  TMPDIR_PRE=$(mktemp -d)
  awk '
    /<ac:structured-macro ac:name="plantuml"/{flag=1; next}
    /<\/ac:structured-macro>/{flag=0}
    flag && /<ac:plain-text-body><!\[CDATA\[/{capture=1; next}
    flag && capture && /\]\]><\/ac:plain-text-body>/{capture=0; next}
    flag && capture{print}
  ' "$DRAFT" > "$TMPDIR_PRE/all.puml"
  if [[ -s "$TMPDIR_PRE/all.puml" ]]; then
    if ! plantuml -tpng -checkonly -failfast2 "$TMPDIR_PRE/all.puml" >/dev/null 2>&1; then
      note_major "PlantUML syntax check failed. Run plantuml -tpng locally on the extracted body."
    fi
  fi
  rm -rf "$TMPDIR_PRE"
fi

# 4. Size
LINES=$(wc -l < "$DRAFT")
if [[ $LINES -gt 300 ]]; then
  if ! head -5 "$DRAFT" | grep -qiE 'justify|long|expanded'; then
    note_major "Body is $LINES lines (>300) and no justification header is present."
  fi
fi

# 5. Image alt text
if grep -qE '<ac:image' "$DRAFT"; then
  if ! grep -q 'ac:alt' "$DRAFT"; then
    note_major "<ac:image> without ac:alt."
  fi
fi

echo "------------------------------------"
if [[ $BLOCK -eq 1 ]]; then
  echo "BLOCK -- secret, format, or path issue. Fix and re-run."
  exit 2
elif [[ $MAJOR -eq 1 ]]; then
  echo "REVISE -- major issues found. Fix and re-run."
  exit 1
elif [[ $MINOR -eq 1 ]]; then
  echo "PASS (with minor notes) -- ready to post."
  exit 0
else
  echo "PASS -- ready to post."
  exit 0
fi