xiaoxia-saas/scripts/ci/run_validate.sh

#!/bin/bash
# CI Validate Job 主脚本：代码质量全量检查
# 包含：密钥扫描、格式检查、类型检查、安全扫描、依赖漏洞检查、死代码检测、Alembic迁移验证
set -eu

echo "=== CI Validate: 开始全量代码质量检查 ==="

# --- 密钥检测 ---
echo ""
echo "=== [1/8] 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 "=== [2/8] 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('')
")
    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
  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 "$CHANGED_PY_FILES" | tr ' ' '\n' | grep -v '^scripts/' | tr '\n' ' ')
  if [ -n "$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"

# --- Mypy 类型检查 ---
echo ""
echo "=== [3/8] Type check (mypy) ==="
bash scripts/ci/mypy_check.sh
echo "✅ Mypy type check passed"

# --- Bandit 安全扫描 ---
echo ""
echo "=== [4/8] Security scan (bandit) ==="
bandit -r apps packages -q -ll
echo "✅ Bandit security scan passed"

# --- Pip-audit 依赖漏洞扫描（仅告警） ---
echo ""
echo "=== [5/8] 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 "=== [6/8] 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

# --- Release 脚本语法校验 ---
echo ""
echo "=== [7/8] Release scripts syntax validation ==="
bash -n scripts/backup_postgres.sh
bash -n scripts/restore_postgres_plan.sh
bash -n scripts/init_production_env.sh
echo "✅ Release scripts syntax OK"

# --- Alembic 迁移验证 ---
echo ""
echo "=== [8/8] Alembic migrations validation (with isolated PG) ==="
PG_CONTAINER=ci-pg-validate-${GITHUB_RUN_ID:-$$}
docker rm -f "$PG_CONTAINER" 2>/dev/null || true
docker run -d --name "$PG_CONTAINER" \
  --shm-size=256m \
  -e POSTGRES_USER=postgres \
  -e POSTGRES_PASSWORD=postgres \
  -e POSTGRES_DB=xiaoxia_saas \
  -P \
  --health-cmd "pg_isready -U postgres" \
  --health-interval 3s \
  --health-timeout 3s \
  --health-retries 20 \
  postgres:16-alpine

# 等待PG容器内部ready
for i in $(seq 1 30); do
  if docker inspect --format='{{.State.Health.Status}}' "$PG_CONTAINER" 2>/dev/null | grep -q healthy; then
    echo "PostgreSQL container is healthy"
    break
  fi
  echo "Waiting for PostgreSQL... ($i/30)"
  sleep 2
done
docker inspect --format='{{.State.Health.Status}}' "$PG_CONTAINER" | grep -q healthy

# 获取两种连接方式
PG_MAPPED_PORT=$(docker port "$PG_CONTAINER" 5432/tcp | cut -d: -f2)
PG_CONTAINER_IP=$(docker inspect --format='{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$PG_CONTAINER")
echo "Mapped port: $PG_MAPPED_PORT, Container IP: $PG_CONTAINER_IP"

# 双模式探测：先试端口映射，再试容器IP，哪个通就用哪个
PG_HOST=""
PG_PORT=""
for mode in "mapped:127.0.0.1:$PG_MAPPED_PORT" "container:$PG_CONTAINER_IP:5432"; do
  MODE_NAME=$(echo "$mode" | cut -d: -f1)
  TEST_HOST=$(echo "$mode" | cut -d: -f2)
  TEST_PORT=$(echo "$mode" | cut -d: -f3)
  echo "Testing $MODE_NAME mode ($TEST_HOST:$TEST_PORT)..."
  for i in $(seq 1 15); do
    if python3 -c "import socket; s=socket.socket(); s.settimeout(2); s.connect(('$TEST_HOST', $TEST_PORT)); s.close()" 2>/dev/null; then
      PG_HOST="$TEST_HOST"
      PG_PORT="$TEST_PORT"
      echo "✅ $MODE_NAME mode works: $TEST_HOST:$TEST_PORT"
      break 2
    fi
    sleep 2
  done
  echo "❌ $MODE_NAME mode failed after 15 attempts, trying next..."
done

if [ -z "$PG_HOST" ]; then
  echo "ERROR: 无法通过任何方式连接到PostgreSQL容器"
  echo "端口映射和容器IP两种方式均失败，可能是当前runner的Docker网络配置异常"
  exit 1
fi

echo "Using PostgreSQL: $PG_HOST:$PG_PORT"
export DATABASE_URL="postgresql+psycopg://postgres:postgres@$PG_HOST:$PG_PORT/xiaoxia_saas"

PYTHONPATH="$PWD/apps/api:$PWD" python3 -m alembic upgrade head
echo "✅ Alembic migrations applied successfully"
docker rm -f "$PG_CONTAINER" 2>/dev/null || true

echo ""
echo "=== CI Validate: 所有检查通过 ✅ ==="