xiaoxia-saas/tests/unit/test_path_security.py

"""路径安全校验工具单元测试 — 路径遍历防护."""

from __future__ import annotations

import os
import sys
import tempfile
import unittest
from pathlib import Path

sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "apps", "worker"))

from video_processing.path_security import (  # noqa: E402
    PathSecurityError,
    get_allowed_local_dirs,
    is_in_allowed_dirs,
    is_path_safe,
    safe_resolve_path,
    sanitize_filename,
    validate_local_schema_path,
)


class TestSafeResolvePath(unittest.TestCase):
    """安全路径解析测试."""

    def setUp(self):
        self.tmpdir = tempfile.mkdtemp()

    def tearDown(self):
        import shutil

        shutil.rmtree(self.tmpdir, ignore_errors=True)

    # ── 正常路径 ─────────────────────────────────────────────────────────

    def test_simple_relative_path(self):
        """简单相对路径应该正常解析."""
        result = safe_resolve_path("test.mp4", self.tmpdir)
        self.assertEqual(result.name, "test.mp4")
        self.assertTrue(str(result).startswith(self.tmpdir))

    def test_subdirectory_path(self):
        """子目录路径应该正常解析."""
        result = safe_resolve_path("sub/dir/file.mp4", self.tmpdir)
        self.assertTrue(str(result).startswith(self.tmpdir))
        self.assertIn("sub/dir/file.mp4", str(result).replace("\\", "/"))

    def test_dot_slash_path(self):
        """./ 开头的路径应该正常解析."""
        result = safe_resolve_path("./test.mp4", self.tmpdir)
        self.assertEqual(result.name, "test.mp4")

    # ── 路径遍历防护 ─────────────────────────────────────────────────────

    def test_parent_traversal_rejected(self):
        """../ 路径遍历应该被拒绝."""
        with self.assertRaises(PathSecurityError):
            safe_resolve_path("../etc/passwd", self.tmpdir)

    def test_multiple_parent_traversal_rejected(self):
        """多级 ../ 遍历应该被拒绝."""
        with self.assertRaises(PathSecurityError):
            safe_resolve_path("../../etc/passwd", self.tmpdir)

    def test_mixed_traversal_rejected(self):
        """混合路径遍历应该被拒绝."""
        with self.assertRaises(PathSecurityError):
            safe_resolve_path("./sub/../../etc/shadow", self.tmpdir)

    def test_absolute_path_rejected(self):
        """绝对路径（超出基目录）应该被拒绝."""
        with self.assertRaises(PathSecurityError):
            safe_resolve_path("/etc/passwd", self.tmpdir)

    # ── 空字节注入 ───────────────────────────────────────────────────────

    def test_null_byte_rejected(self):
        """空字节注入应该被拒绝."""
        with self.assertRaises(PathSecurityError):
            safe_resolve_path("test\x00.mp4", self.tmpdir)

    # ── 空路径 ──────────────────────────────────────────────────────────

    def test_empty_path_rejected(self):
        """空路径应该被拒绝."""
        with self.assertRaises(PathSecurityError):
            safe_resolve_path("", self.tmpdir)

    def test_none_path_rejected(self):
        """None 路径应该被拒绝."""
        with self.assertRaises(PathSecurityError):
            safe_resolve_path(None, self.tmpdir)  # type: ignore

    def test_whitespace_path_rejected(self):
        """空白路径应该被拒绝."""
        with self.assertRaises(PathSecurityError):
            safe_resolve_path("   ", self.tmpdir)

    # ── 路径长度 ────────────────────────────────────────────────────────

    def test_too_long_path_rejected(self):
        """超长路径应该被拒绝."""
        long_path = "a" * 5000 + ".mp4"
        with self.assertRaises(PathSecurityError):
            safe_resolve_path(long_path, self.tmpdir)

    # ── 系统路径防护 ─────────────────────────────────────────────────────

    def test_proc_path_rejected_when_absolute(self):
        """/proc/ 路径在绝对路径模式下应该被拒绝（因为超出基目录）."""
        with self.assertRaises(PathSecurityError):
            safe_resolve_path("/proc/self/environ", self.tmpdir)

    # ── 扩展名校验 ───────────────────────────────────────────────────────

    def test_extension_whitelist_pass(self):
        """白名单内的扩展名应该通过."""
        result = safe_resolve_path(
            "test.mp4",
            self.tmpdir,
            allowed_extensions={".mp4", ".mov"},
        )
        self.assertEqual(result.suffix.lower(), ".mp4")

    def test_extension_whitelist_reject(self):
        """白名单外的扩展名应该被拒绝."""
        with self.assertRaises(PathSecurityError):
            safe_resolve_path(
                "test.exe",
                self.tmpdir,
                allowed_extensions={".mp4", ".mov"},
            )


class TestLocalSchemaPath(unittest.TestCase):
    """local:// schema 路径测试."""

    def setUp(self):
        self.tmpdir = tempfile.mkdtemp()

    def tearDown(self):
        import shutil

        shutil.rmtree(self.tmpdir, ignore_errors=True)

    def test_valid_local_schema(self):
        """有效的 local:// 相对路径应该通过."""
        # 创建测试文件
        test_file = Path(self.tmpdir) / "test.mp4"
        test_file.touch()

        result = validate_local_schema_path("local://test.mp4", self.tmpdir)
        self.assertTrue(result.exists())

    def test_local_schema_absolute_rejected(self):
        """local:// + 绝对路径应该被拒绝."""
        with self.assertRaises(PathSecurityError):
            validate_local_schema_path("local:///etc/passwd", self.tmpdir)

    def test_local_schema_traversal_rejected(self):
        """local:// + 路径遍历应该被拒绝."""
        with self.assertRaises(PathSecurityError):
            validate_local_schema_path("local://../etc/passwd", self.tmpdir)

    def test_non_local_schema_rejected(self):
        """非 local:// 开头的路径应该被拒绝."""
        with self.assertRaises(PathSecurityError):
            validate_local_schema_path("http://example.com/test", self.tmpdir)


class TestSanitizeFilename(unittest.TestCase):
    """文件名清理测试."""

    def test_normal_filename(self):
        """正常文件名应该保持不变."""
        self.assertEqual(sanitize_filename("video.mp4"), "video.mp4")

    def test_path_separators_removed(self):
        """路径分隔符应该被替换."""
        self.assertNotIn("/", sanitize_filename("../path/to/file.mp4"))
        self.assertNotIn("\\", sanitize_filename("..\\path\\file.mp4"))

    def test_leading_dots_removed(self):
        """开头的点应该被移除."""
        result = sanitize_filename(".hidden")
        self.assertFalse(result.startswith("."))
        self.assertEqual(result, "hidden")

    def test_multiple_leading_dots_removed(self):
        """多个开头的点应该全部被移除."""
        result = sanitize_filename("...hidden")
        self.assertFalse(result.startswith("."))

    def test_empty_filename_default(self):
        """空文件名应该返回 unnamed."""
        self.assertEqual(sanitize_filename(""), "unnamed")

    def test_special_chars_removed(self):
        """特殊字符应该被替换."""
        result = sanitize_filename('file<name>:"test|?*.mp4')
        self.assertNotIn("<", result)
        self.assertNotIn(">", result)
        self.assertNotIn(":", result)
        self.assertNotIn('"', result)
        self.assertNotIn("|", result)
        self.assertNotIn("?", result)
        self.assertNotIn("*", result)

    def test_chinese_filename_preserved(self):
        """中文文件名应该保留."""
        result = sanitize_filename("视频素材.mp4")
        self.assertIn("视频素材", result)

    def test_long_filename_truncated(self):
        """超长文件名应该被截断."""
        long_name = "a" * 300 + ".mp4"
        result = sanitize_filename(long_name)
        self.assertLessEqual(len(result), 255)
        self.assertTrue(result.endswith(".mp4"))


class TestAllowedDirs(unittest.TestCase):
    """允许目录配置测试."""

    def test_get_allowed_dirs_returns_list(self):
        """get_allowed_local_dirs 应该返回列表."""
        dirs = get_allowed_local_dirs()
        self.assertIsInstance(dirs, list)

    def test_is_in_allowed_dirs_tmp(self):
        """/tmp 应该在默认允许目录内."""
        self.assertTrue(is_in_allowed_dirs("/tmp/test.mp4"))

    def test_is_path_safe_convenience(self):
        """is_path_safe 便捷函数应该正常工作."""
        with tempfile.TemporaryDirectory() as tmpdir:
            self.assertTrue(is_path_safe("test.mp4", tmpdir))
            self.assertFalse(is_path_safe("../etc/passwd", tmpdir))


if __name__ == "__main__":
    unittest.main()