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）
71 lines
2.0 KiB
Python
71 lines
2.0 KiB
Python
# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
import src.crawler as crawler_module
|
|
|
|
|
|
def test_crawler_sets_article_url(monkeypatch):
|
|
"""Test that the crawler sets the article.url field correctly."""
|
|
|
|
class DummyArticle:
|
|
def __init__(self):
|
|
self.url = None
|
|
|
|
def to_markdown(self):
|
|
return "# Dummy"
|
|
|
|
class DummyJinaClient:
|
|
def crawl(self, url, return_format=None):
|
|
return "<html>dummy</html>"
|
|
|
|
class DummyReadabilityExtractor:
|
|
def extract_article(self, html):
|
|
return DummyArticle()
|
|
|
|
monkeypatch.setattr("src.crawler.crawler.JinaClient", DummyJinaClient)
|
|
monkeypatch.setattr(
|
|
"src.crawler.crawler.ReadabilityExtractor", DummyReadabilityExtractor
|
|
)
|
|
|
|
crawler = crawler_module.Crawler()
|
|
url = "http://example.com"
|
|
article = crawler.crawl(url)
|
|
assert article.url == url
|
|
assert article.to_markdown() == "# Dummy"
|
|
|
|
|
|
def test_crawler_calls_dependencies(monkeypatch):
|
|
"""Test that Crawler calls JinaClient.crawl and ReadabilityExtractor.extract_article."""
|
|
calls = {}
|
|
|
|
class DummyJinaClient:
|
|
def crawl(self, url, return_format=None):
|
|
calls["jina"] = (url, return_format)
|
|
return "<html>dummy</html>"
|
|
|
|
class DummyReadabilityExtractor:
|
|
def extract_article(self, html):
|
|
calls["extractor"] = html
|
|
|
|
class DummyArticle:
|
|
url = None
|
|
|
|
def to_markdown(self):
|
|
return "# Dummy"
|
|
|
|
return DummyArticle()
|
|
|
|
monkeypatch.setattr("src.crawler.crawler.JinaClient", DummyJinaClient)
|
|
monkeypatch.setattr(
|
|
"src.crawler.crawler.ReadabilityExtractor", DummyReadabilityExtractor
|
|
)
|
|
|
|
crawler = crawler_module.Crawler()
|
|
url = "http://example.com"
|
|
crawler.crawl(url)
|
|
assert "jina" in calls
|
|
assert calls["jina"][0] == url
|
|
assert calls["jina"][1] == "html"
|
|
assert "extractor" in calls
|
|
assert calls["extractor"] == "<html>dummy</html>"
|