mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-03 06:12:14 +08:00
975b344ca7
* fix: resolve issue #651 - crawl error with None content handling Fixed issue #651 by adding comprehensive null-safety checks and error handling to the crawl system. The fix prevents the ‘TypeError: Incoming markup is of an invalid type: None’ crash by: 1. Validating HTTP responses from Jina API 2. Handling None/empty content at extraction stage 3. Adding fallback handling in Article markdown/message conversion 4. Improving error diagnostics with detailed logging 5. Adding 16 new tests with 100% coverage for critical paths * Update src/crawler/readability_extractor.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/crawler/article.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
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"]
|