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）
105 lines
3.5 KiB
Python
105 lines
3.5 KiB
Python
# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
from unittest.mock import patch
|
|
|
|
from src.crawler.readability_extractor import ReadabilityExtractor
|
|
|
|
|
|
class TestReadabilityExtractor:
|
|
@patch("src.crawler.readability_extractor.simple_json_from_html_string")
|
|
def test_extract_article_with_valid_content(self, mock_simple_json):
|
|
# Arrange
|
|
mock_simple_json.return_value = {
|
|
"title": "Test Article",
|
|
"content": "<p>Article content</p>",
|
|
}
|
|
extractor = ReadabilityExtractor()
|
|
|
|
# Act
|
|
article = extractor.extract_article("<html>test</html>")
|
|
|
|
# Assert
|
|
assert article.title == "Test Article"
|
|
assert article.html_content == "<p>Article content</p>"
|
|
|
|
@patch("src.crawler.readability_extractor.simple_json_from_html_string")
|
|
def test_extract_article_with_none_content(self, mock_simple_json):
|
|
# Arrange
|
|
mock_simple_json.return_value = {
|
|
"title": "Test Article",
|
|
"content": None,
|
|
}
|
|
extractor = ReadabilityExtractor()
|
|
|
|
# Act
|
|
article = extractor.extract_article("<html>test</html>")
|
|
|
|
# Assert
|
|
assert article.title == "Test Article"
|
|
assert article.html_content == "<p>No content could be extracted from this page</p>"
|
|
|
|
@patch("src.crawler.readability_extractor.simple_json_from_html_string")
|
|
def test_extract_article_with_empty_content(self, mock_simple_json):
|
|
# Arrange
|
|
mock_simple_json.return_value = {
|
|
"title": "Test Article",
|
|
"content": "",
|
|
}
|
|
extractor = ReadabilityExtractor()
|
|
|
|
# Act
|
|
article = extractor.extract_article("<html>test</html>")
|
|
|
|
# Assert
|
|
assert article.title == "Test Article"
|
|
assert article.html_content == "<p>No content could be extracted from this page</p>"
|
|
|
|
@patch("src.crawler.readability_extractor.simple_json_from_html_string")
|
|
def test_extract_article_with_whitespace_only_content(self, mock_simple_json):
|
|
# Arrange
|
|
mock_simple_json.return_value = {
|
|
"title": "Test Article",
|
|
"content": " \n \t ",
|
|
}
|
|
extractor = ReadabilityExtractor()
|
|
|
|
# Act
|
|
article = extractor.extract_article("<html>test</html>")
|
|
|
|
# Assert
|
|
assert article.title == "Test Article"
|
|
assert article.html_content == "<p>No content could be extracted from this page</p>"
|
|
|
|
@patch("src.crawler.readability_extractor.simple_json_from_html_string")
|
|
def test_extract_article_with_none_title(self, mock_simple_json):
|
|
# Arrange
|
|
mock_simple_json.return_value = {
|
|
"title": None,
|
|
"content": "<p>Article content</p>",
|
|
}
|
|
extractor = ReadabilityExtractor()
|
|
|
|
# Act
|
|
article = extractor.extract_article("<html>test</html>")
|
|
|
|
# Assert
|
|
assert article.title == "Untitled"
|
|
assert article.html_content == "<p>Article content</p>"
|
|
|
|
@patch("src.crawler.readability_extractor.simple_json_from_html_string")
|
|
def test_extract_article_with_empty_title(self, mock_simple_json):
|
|
# Arrange
|
|
mock_simple_json.return_value = {
|
|
"title": "",
|
|
"content": "<p>Article content</p>",
|
|
}
|
|
extractor = ReadabilityExtractor()
|
|
|
|
# Act
|
|
article = extractor.extract_article("<html>test</html>")
|
|
|
|
# Assert
|
|
assert article.title == "Untitled"
|
|
assert article.html_content == "<p>Article content</p>"
|