沃巴蒂
ff22ed3a8b
本次同步 09-12 至 09-28 的代码变更，主要内容： 新增功能 - 修改密码：后端新增 ChangePasswordRequest DTO 与UserController/UserService 对应接口，前端新增 ChangePasswordDialog 并在 Header 接入入口 - 文件预览组件重构：file-preview 目录拆分出 VideoPreview（支持 blobUrl 直传）、 ImagePreview、AudioPreview，index.tsx 统一调度各类型预览器 - 新增 my_ops 算子模块：markitdown_parser、mineru_pdf_parser、text_quality_evaluator - 新增 tools/minio-file-server MinIO 文件服务 功能增强 - 数据清洗：cleaning_task_service/scheduler/routes 重构， data_juicer_executor 与 wrapper 增强，OperatorTable/LogsTable/TaskDetail 同步调整 - 数据标注：annotation sync.py、project.py 接口与schema 更新 - 数据采集、算子市场、首页与菜单路由相关页面调整 - DataJuicer 算子接入（useOperatorOperations、dj_ops_schema） 结构调整 - deepflow/ 更名为 deep-flow/（419 个文件重命名） - 新增 helm 部署编排、GitHub Actions 之外的自建镜像构建脚本 未纳入本次提交 - scripts-backup/、runtime/python-executor-backup/、components_backup/（备份目录） - *.backup*、__pycache__ 产物 - zh_core_web_sm-3.8.0-py3-none-any.whl（46MB 构建产物） - DataX/（内嵌独立仓库，远程亦未收录其源码）
134 lines
4.1 KiB
Python
134 lines
4.1 KiB
Python
import json
|
|
from unittest.mock import Mock, patch
|
|
|
|
from src.tools.crawl import crawl_tool
|
|
|
|
|
|
class TestCrawlTool:
|
|
@patch("src.tools.crawl.Crawler")
|
|
def test_crawl_tool_success(self, mock_crawler_class):
|
|
# Arrange
|
|
mock_crawler = Mock()
|
|
mock_article = Mock()
|
|
mock_article.to_markdown.return_value = (
|
|
"# Test Article\nThis is test content." * 100
|
|
)
|
|
mock_crawler.crawl.return_value = mock_article
|
|
mock_crawler_class.return_value = mock_crawler
|
|
|
|
url = "https://example.com"
|
|
|
|
# Act
|
|
result = crawl_tool(url)
|
|
|
|
# Assert
|
|
assert isinstance(result, str)
|
|
result_dict = json.loads(result)
|
|
assert result_dict["url"] == url
|
|
assert "crawled_content" in result_dict
|
|
assert len(result_dict["crawled_content"]) <= 1000
|
|
mock_crawler_class.assert_called_once()
|
|
mock_crawler.crawl.assert_called_once_with(url)
|
|
mock_article.to_markdown.assert_called_once()
|
|
|
|
@patch("src.tools.crawl.Crawler")
|
|
def test_crawl_tool_short_content(self, mock_crawler_class):
|
|
# Arrange
|
|
mock_crawler = Mock()
|
|
mock_article = Mock()
|
|
short_content = "Short content"
|
|
mock_article.to_markdown.return_value = short_content
|
|
mock_crawler.crawl.return_value = mock_article
|
|
mock_crawler_class.return_value = mock_crawler
|
|
|
|
url = "https://example.com"
|
|
|
|
# Act
|
|
result = crawl_tool(url)
|
|
|
|
# Assert
|
|
result_dict = json.loads(result)
|
|
assert result_dict["crawled_content"] == short_content
|
|
|
|
@patch("src.tools.crawl.Crawler")
|
|
@patch("src.tools.crawl.logger")
|
|
def test_crawl_tool_crawler_exception(self, mock_logger, mock_crawler_class):
|
|
# Arrange
|
|
mock_crawler = Mock()
|
|
mock_crawler.crawl.side_effect = Exception("Network error")
|
|
mock_crawler_class.return_value = mock_crawler
|
|
|
|
url = "https://example.com"
|
|
|
|
# Act
|
|
result = crawl_tool(url)
|
|
|
|
# Assert
|
|
assert isinstance(result, str)
|
|
assert "Failed to crawl" in result
|
|
assert "Network error" in result
|
|
mock_logger.error.assert_called_once()
|
|
|
|
@patch("src.tools.crawl.Crawler")
|
|
@patch("src.tools.crawl.logger")
|
|
def test_crawl_tool_crawler_instantiation_exception(
|
|
self, mock_logger, mock_crawler_class
|
|
):
|
|
# Arrange
|
|
mock_crawler_class.side_effect = Exception("Crawler init error")
|
|
|
|
url = "https://example.com"
|
|
|
|
# Act
|
|
result = crawl_tool(url)
|
|
|
|
# Assert
|
|
assert isinstance(result, str)
|
|
assert "Failed to crawl" in result
|
|
assert "Crawler init error" in result
|
|
mock_logger.error.assert_called_once()
|
|
|
|
@patch("src.tools.crawl.Crawler")
|
|
@patch("src.tools.crawl.logger")
|
|
def test_crawl_tool_markdown_conversion_exception(
|
|
self, mock_logger, mock_crawler_class
|
|
):
|
|
# Arrange
|
|
mock_crawler = Mock()
|
|
mock_article = Mock()
|
|
mock_article.to_markdown.side_effect = Exception("Markdown conversion error")
|
|
mock_crawler.crawl.return_value = mock_article
|
|
mock_crawler_class.return_value = mock_crawler
|
|
|
|
url = "https://example.com"
|
|
|
|
# Act
|
|
result = crawl_tool(url)
|
|
|
|
# Assert
|
|
assert isinstance(result, str)
|
|
assert "Failed to crawl" in result
|
|
assert "Markdown conversion error" in result
|
|
mock_logger.error.assert_called_once()
|
|
|
|
@patch("src.tools.crawl.Crawler")
|
|
def test_crawl_tool_with_none_content(self, mock_crawler_class):
|
|
# Arrange
|
|
mock_crawler = Mock()
|
|
mock_article = Mock()
|
|
mock_article.to_markdown.return_value = "# Article\n\n*No content available*\n"
|
|
mock_crawler.crawl.return_value = mock_article
|
|
mock_crawler_class.return_value = mock_crawler
|
|
|
|
url = "https://example.com"
|
|
|
|
# Act
|
|
result = crawl_tool(url)
|
|
|
|
# Assert
|
|
assert isinstance(result, str)
|
|
result_dict = json.loads(result)
|
|
assert result_dict["url"] == url
|
|
assert "crawled_content" in result_dict
|
|
assert "No content available" in result_dict["crawled_content"]
|