github/deer-flow
1
0
Fork 0
mirror of https://github.com/bytedance/deer-flow.git synced 2026-10-26 13:16:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(harness): initialize Article.url to prevent AttributeError in to_message (#5785)

Browse Source 
* fix(harness): initialize Article.url to prevent AttributeError in to_message

* chore(tests): format test_readability with ruff and unify imports
This commit is contained in:
Chau Vu 2026-09-24 08:43:16 +07:00 committed by GitHub
parent 82ac1612e3
commit 887883a58e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 17 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
backend/packages/harness/deerflow/utils/readability.py
View File

@ -15,9 +15,10 @@ logger = logging.getLogger(__name__)
class Article:
url: str
def __init__(self, title: str, html_content: str):
def __init__(self, title: str, html_content: str, url: str | None = None):
self.title = title
self.html_content = html_content
self.url = url or ""
def to_markdown(self, including_title: bool = True) -> str:
markdown = ""
@ -176,4 +177,4 @@ class ReadabilityExtractor:
if not title or not str(title).strip():
title = "Untitled"
return Article(title=title, html_content=html_content)
return Article(title=title, html_content=html_content, url=url)

15
backend/tests/test_readability.py
View File

@ -4,7 +4,7 @@ import subprocess
import pytest
from deerflow.utils.readability import ReadabilityExtractor
from deerflow.utils.readability import Article, ReadabilityExtractor
def test_extract_article_falls_back_when_readability_js_fails(monkeypatch):
@ -53,3 +53,16 @@ def test_extract_article_re_raises_unexpected_exception(monkeypatch):
with pytest.raises(RuntimeError, match="unexpected parser failure"):
ReadabilityExtractor().extract_article("<html><body>test</body></html>")
assert calls == [True]
def test_article_to_message_with_images():
"""Article.to_message should handle articles containing images without AttributeError."""
# Absolute image URL without source url
art_abs = Article("Test Image", '<img src="https://example.com/pic.png">')
msg_abs = art_abs.to_message()
assert any(block.get("type") == "image_url" and block["image_url"]["url"] == "https://example.com/pic.png" for block in msg_abs)
# Relative image URL with source url
art_rel = Article("Test Relative Image", '<img src="/assets/pic.png">', url="https://example.com/base/")
msg_rel = art_rel.to_message()
assert any(block.get("type") == "image_url" and block["image_url"]["url"] == "https://example.com/assets/pic.png" for block in msg_rel)