xiaoxia-saas/scripts/ci/validate_code_quality.sh

#!/bin/bash
# CI Validate: 代码质量与安全扫描（并行Job 1/3）
# 包含：密钥扫描、格式检查、安全扫描、依赖漏洞、死代码检测、脚本语法校验
set -eu

echo "=== CI Validate: 代码质量与安全扫描 ==="

# --- 密钥检测 ---
echo ""
echo "=== [1/6] Secret detection (detect-secrets) ==="
python3 -m pip install -q detect-secrets
detect-secrets --version

detect-secrets scan \
  --all-files \
  --exclude-files '(^|/)(tests|test|e2e|__tests__|spec|docs|node_modules|site-packages|migrations|alembic|.gitea|.git|.pytest_cache|.next|dist|build)/' \
  --exclude-files '\.(md|rst|txt|lock|example|sample|min\.js|min\.css|spec\.ts|test\.ts|test\.py)$' \
  --exclude-files '(package-lock|yarn\.lock|poetry\.lock|Pipfile\.lock)$' \
  --disable-plugin Base64HighEntropyString \
  --disable-plugin HexHighEntropyString \
  --disable-plugin BasicAuthDetector \
  --disable-plugin KeywordDetector \
  --disable-plugin IPPublicDetector \
  > /tmp/secrets-scan.json 2>&1

FOUND=$(python3 -c "
import json
try:
    with open('/tmp/secrets-scan.json') as f:
        data = json.load(f)
    results = data.get('results', {})
    total = sum(len(v) for v in results.values())
    print(total)
except Exception:
    print('error')
")

echo "Secrets detected: $FOUND"
if [ "$FOUND" != "0" ] && [ "$FOUND" != "error" ]; then
  echo ""
  echo "=== Secret details ==="
  python3 -c "
import json
with open('/tmp/secrets-scan.json') as f:
    data = json.load(f)
for fpath, items in data.get('results', {}).items():
    for item in items:
        line = item.get('line_number', '?')
        stype = item.get('type', '?')
        hashed = item.get('hashed_secret', '')[:16]
        print(f'  {fpath}:{line} [{stype}] {hashed}...')
"
  echo ""
  echo "ERROR: Potential secrets detected in code!"
  exit 1
fi
echo "✅ Secret scan passed"

# --- 增量/全量模式判断 ---
echo ""
echo "=== [2/6] Code quality checks ==="
SCAN_MODE="full"
CHANGED_PY_FILES=""

if [ "${GITHUB_EVENT_NAME:-}" = "pull_request" ] && [ -n "${GITHUB_REF_NAME:-}" ] && [ -n "${GITHUB_TOKEN:-}" ]; then
  PR_NUMBER=$(echo "$GITHUB_REF" | sed 's|refs/pull/||; s|/.*||')
  API_URL="${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/pulls/${PR_NUMBER}/files?limit=100"
  set +e
  RESPONSE=$(curl -s -w "\n%{http_code}" -H "Authorization: token ${GITHUB_TOKEN}" "$API_URL")
  HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
  BODY=$(echo "$RESPONSE" | sed '$d')
  set -e
  if [ "$HTTP_CODE" = "200" ]; then
    CHANGED_PY_FILES=$(echo "$BODY" | python3 -c "
import json, sys
try:
    files = json.load(sys.stdin)
    py_files = [f['filename'] for f in files if f['filename'].endswith('.py') and f['status'] != 'removed']
    print(' '.join(py_files))
except Exception:
    print('')
")
    # 新增文件(added)强制全量检查，防止增量漏检
    ADDED_PY_FILES=$(echo "$BODY" | python3 -c "
import json, sys
try:
    files = json.load(sys.stdin)
    added = [f['filename'] for f in files if f['filename'].endswith('.py') and f['status'] == 'added']
    print(' '.join(added))
except Exception:
    print('')
")
    MODIFIED_PY_FILES=$(echo "$BODY" | python3 -c "
import json, sys
try:
    files = json.load(sys.stdin)
    modified = [f['filename'] for f in files if f['filename'].endswith('.py') and f['status'] not in ('removed', 'added')]
    print(' '.join(modified))
except Exception:
    print('')
")
    if [ -n "$CHANGED_PY_FILES" ]; then
      SCAN_MODE="incremental"
      echo "Incremental mode: $(echo "$CHANGED_PY_FILES" | wc -w) Python files changed"
    else
      SCAN_MODE="skip_py"
      echo "No Python files changed in this PR"
    fi
  else
    echo "WARN: API returned HTTP $HTTP_CODE, falling back to full scan"
  fi
else
  echo "Full scan mode (not a PR event)"
fi

if [ "$SCAN_MODE" = "incremental" ]; then
  # 防御性过滤
  EXISTING_PY_FILES=""
  for f in $CHANGED_PY_FILES; do
    if [ -f "$f" ]; then
      if [ -z "$EXISTING_PY_FILES" ]; then
        EXISTING_PY_FILES="$f"
      else
        EXISTING_PY_FILES="$EXISTING_PY_FILES $f"
      fi
    fi
  done
  CHANGED_PY_FILES="$EXISTING_PY_FILES"

  python3 -m compileall -q $CHANGED_PY_FILES
  python3 -m black --check --fast $CHANGED_PY_FILES
  python3 -m isort --check-only $CHANGED_PY_FILES
  RUFF_FILES=$(echo "$CHANGED_PY_FILES" | tr ' ' '\n' | grep -v '^scripts/' | grep -v '^$' | xargs)
  if [ -n "$RUFF_FILES" ]; then
    python3 -m ruff check $RUFF_FILES --statistics
  else
    echo "No ruff-checkable files changed, skipping"
  fi
elif [ "$SCAN_MODE" = "skip_py" ]; then
  echo "No Python files changed - skipping Python lint checks"
else
  echo "Full scan mode"
  python3 -m compileall -q alembic apps packages tests scripts
  python3 -m black --check --fast alembic apps packages tests scripts
  python3 -m isort --check-only alembic apps packages tests scripts
  python3 -m ruff check apps packages tests --statistics
fi
echo "✅ Code quality checks passed"

# --- Bandit 安全扫描（仅告警） ---
echo ""
echo "=== [3/6] Security scan (bandit, advisory only) ==="
set +e
bandit -r apps packages -q -ll
BANDIT_EXIT=$?
set -e
if [ "$BANDIT_EXIT" -ne 0 ]; then
  echo "⚠️  Bandit found security issues (advisory mode - not blocking CI)"
else
  echo "✅ Bandit security scan passed"
fi

# --- Pip-audit 依赖漏洞扫描（仅告警） ---
echo ""
echo "=== [4/6] Python dependency vulnerability scan (pip-audit, advisory only) ==="
python3 -m pip install -q pip-audit
pip-audit --version
EXIT_CODE=0
for req_file in requirements.txt requirements-base.txt requirements-dev.txt; do
  if [ -f "$req_file" ]; then
    echo "--- Scanning $req_file ---"
    pip-audit -r "$req_file" --desc on 2>&1 | head -40 || EXIT_CODE=$?
    echo ""
  fi
done
echo "pip-audit scan completed (advisory mode - warnings only, not blocking CI)"

# --- Vulture 死代码检测（仅告警） ---
echo ""
echo "=== [5/6] Dead code detection (vulture, advisory only) ==="
set +e
python3 -m pip install -q vulture
vulture --version
echo "告警模式，不阻断CI。置信度>=90%建议尽快确认。"
echo ""
vulture apps packages scripts \
  --exclude "tests,test,migrations,.gitea,docs,node_modules,site-packages,*/test_*.py,*/conftest.py" \
  --min-confidence 70 \
  2>&1 | sort -t'(' -k2 -rn | head -80
echo ""
echo "=== vulture scan summary ==="
echo "发现潜在死代码（可能包含框架装饰器注册的函数，为误报）"
echo "建议：定期人工审查高置信度（>=90%）条目"
set -e

# --- CI脚本语法校验 ---
echo ""
echo "=== [6/6] CI & shell scripts syntax validation ==="
SYNTAX_ERROR=0
# 检查所有 CI shell 脚本
for script in scripts/ci/*.sh; do
  if [ -f "$script" ]; then
    if ! bash -n "$script" 2>&1; then
      echo "❌ 语法错误: $script"
      SYNTAX_ERROR=1
    fi
  fi
done
# 检查所有 CI Python 脚本语法
for script in scripts/ci/*.py; do
  if [ -f "$script" ]; then
    if ! python3 -m py_compile "$script" 2>&1; then
      echo "❌ Python语法错误: $script"
      SYNTAX_ERROR=1
    fi
  fi
done
# 检查 .gitea/workflows 下的脚本（如果有）
for script in .gitea/workflows/*.sh; do
  if [ -f "$script" ]; then
    if ! bash -n "$script" 2>&1; then
      echo "❌ 语法错误: $script"
      SYNTAX_ERROR=1
    fi
  fi
done
if [ "$SYNTAX_ERROR" -ne 0 ]; then
  echo "❌ CI脚本语法校验失败，见上方错误"
  exit 1
fi
echo "✅ All CI scripts syntax OK"

echo ""
echo "=== CI Validate: 代码质量与安全扫描 全部通过 ✅ ==="