DATA
6de0bf9f5b
Vendored deer-flow upstream (bytedance/deer-flow) plus prompt-injection hardening: - New deerflow.security package: content_delimiter, html_cleaner, sanitizer (8 layers — invisible chars, control chars, symbols, NFC, PUA, tag chars, horizontal whitespace collapse with newline/tab preservation, length cap) - New deerflow.community.searx package: web_search, web_fetch, image_search backed by a private SearX instance, every external string sanitized and wrapped in <<<EXTERNAL_UNTRUSTED_CONTENT>>> delimiters - All native community web providers (ddg_search, tavily, exa, firecrawl, jina_ai, infoquest, image_search) replaced with hard-fail stubs that raise NativeWebToolDisabledError at import time, so a misconfigured tool.use path fails loud rather than silently falling back to unsanitized output - Native client back-doors (jina_client.py, infoquest_client.py) stubbed too - Native-tool tests quarantined under tests/_disabled_native/ (collect_ignore_glob via local conftest.py) - Sanitizer Layer 7 fix: only collapse horizontal whitespace, preserve newlines and tabs so list/table structure survives - Hardened runtime config.yaml references only the searx-backed tools - Factory overlay (backend/) kept in sync with deer-flow tree as a reference / source See HARDENING.md for the full audit trail and verification steps.
56 lines
1.9 KiB
Python
56 lines
1.9 KiB
Python
"""Tests for readability extraction fallback behavior."""
|
|
|
|
import subprocess
|
|
|
|
import pytest
|
|
|
|
from deerflow.utils.readability import ReadabilityExtractor
|
|
|
|
|
|
def test_extract_article_falls_back_when_readability_js_fails(monkeypatch):
|
|
"""When Node-based readability fails, extraction should fall back to Python mode."""
|
|
|
|
calls: list[bool] = []
|
|
|
|
def _fake_simple_json_from_html_string(html: str, use_readability: bool = False):
|
|
calls.append(use_readability)
|
|
if use_readability:
|
|
raise subprocess.CalledProcessError(
|
|
returncode=1,
|
|
cmd=["node", "ExtractArticle.js"],
|
|
stderr="boom",
|
|
)
|
|
return {"title": "Fallback Title", "content": "<p>Fallback Content</p>"}
|
|
|
|
monkeypatch.setattr(
|
|
"deerflow.utils.readability.simple_json_from_html_string",
|
|
_fake_simple_json_from_html_string,
|
|
)
|
|
|
|
article = ReadabilityExtractor().extract_article("<html><body>test</body></html>")
|
|
|
|
assert calls == [True, False]
|
|
assert article.title == "Fallback Title"
|
|
assert article.html_content == "<p>Fallback Content</p>"
|
|
|
|
|
|
def test_extract_article_re_raises_unexpected_exception(monkeypatch):
|
|
"""Unexpected errors should be surfaced instead of silently falling back."""
|
|
|
|
calls: list[bool] = []
|
|
|
|
def _fake_simple_json_from_html_string(html: str, use_readability: bool = False):
|
|
calls.append(use_readability)
|
|
if use_readability:
|
|
raise RuntimeError("unexpected parser failure")
|
|
return {"title": "Should Not Reach Fallback", "content": "<p>Fallback</p>"}
|
|
|
|
monkeypatch.setattr(
|
|
"deerflow.utils.readability.simple_json_from_html_string",
|
|
_fake_simple_json_from_html_string,
|
|
)
|
|
|
|
with pytest.raises(RuntimeError, match="unexpected parser failure"):
|
|
ReadabilityExtractor().extract_article("<html><body>test</body></html>")
|
|
assert calls == [True]
|