Files
姚章浩 693cd952cd feat(asset): 清理被截断的结尾图片引用,修复整单 502
仓库首次入库(此前仅存在于本地工作区与测试服构建产物中,未上传)。

改动(src/knowledge_adapter/asset_content_processor.py):
- 新增 _TRUNCATED_TRAILING_MARKDOWN_RESOURCE_IMAGE 规则,清除 chunk 末尾被截断的
  ![](resource://xxxx 残片(WeKnora 分块在图片引用中间截断时产生,旧逻辑无法匹配完整引用,
  残留 resource:// 触发 ContentProcessingError,导致整单 502)
- 回归测试 tests/test_asset_content_processor.py::
  test_truncated_trailing_markdown_resource_image_is_removed

验证证据:
- 测试服 120.76.217.51,镜像 knowledge-adapter-service:reviewed-test-aeab4b5fca2d
  (release aeab4b5fca2d8661):KB d015d05c-25c8-4d63-b2ab-e8590d3c2dfb 5 个查询全部
  http=200、records=5、残留 resource:// = 0;KB b9dacd62 无退化;容器日志无 error/exception
- 本地:pytest 141 项全通过、ruff 全通过
- 该文件与 258c31e0fe07fd08 源码的差异经逐文件 md5 比对,为唯一变更文件
2026-09-16 10:01:27 +08:00

111 lines
3.1 KiB
Python

import pytest
from knowledge_adapter.resource_locator import (
InvalidResourceLocator,
InvalidResourceReference,
parse_oss_object_key,
parse_resource_reference,
)
VALID_HANDLE = "AbCdEfGhIjKlMnOpQrSt_1"
def test_parse_resource_reference_accepts_only_canonical_handle() -> None:
assert parse_resource_reference(f"resource://{VALID_HANDLE}") == VALID_HANDLE
invalid_values = [
"resource://short",
"resource://AbCdEfGhIjKlMnOpQrSt/1",
"resource://AbCdEfGhIjKlMnOpQrSt%1",
"https://example.com/image.png",
"http://example.com/image.png",
]
for value in invalid_values:
with pytest.raises(InvalidResourceReference):
parse_resource_reference(value)
def test_parse_oss_object_key_accepts_matching_wrapped_locator() -> None:
object_key = parse_oss_object_key(
provider="oss",
physical_path=(
"storage://backend-test/"
"oss://private-assets/weknora/10008/assets/image.png"
),
storage_backend_id="backend-test",
expected_storage_backend_id="backend-test",
expected_bucket="private-assets",
)
assert object_key == "weknora/10008/assets/image.png"
@pytest.mark.parametrize(
("provider", "physical_path", "storage_backend_id"),
[
(
"oss",
"storage://backend-test/oss://private-assets/../secret.png",
"backend-test",
),
(
"oss",
"storage://backend-test/oss://private-assets//absolute.png",
"backend-test",
),
(
"oss",
"storage://backend-test/oss://private-assets/folder\\image.png",
"backend-test",
),
(
"oss",
"storage://backend-test/oss://private-assets/image.png\x00ignored",
"backend-test",
),
(
"oss",
"storage://backend-test/oss://private-assets/image.png?signature=bad",
"backend-test",
),
(
"cos",
"storage://backend-test/oss://private-assets/image.png",
"backend-test",
),
(
"oss",
"storage://other/oss://private-assets/image.png",
"backend-test",
),
(
"oss",
"storage://backend-test/oss://other-bucket/image.png",
"backend-test",
),
(
"oss",
"https://example.com/image.png",
"backend-test",
),
(
"oss",
"storage://backend-test/oss://private-assets/" + ("x" * 1024),
"backend-test",
),
],
)
def test_parse_oss_object_key_rejects_locator_outside_fixed_boundary(
provider: str,
physical_path: str,
storage_backend_id: str,
) -> None:
with pytest.raises(InvalidResourceLocator):
parse_oss_object_key(
provider=provider,
physical_path=physical_path,
storage_backend_id=storage_backend_id,
expected_storage_backend_id="backend-test",
expected_bucket="private-assets",
)