yumao
e2f609a027
候选池按独立事件拉取，白名单过滤低质源，同事件与 tech 主题去重后按展示上限打包。 Co-authored-by: Cursor <cursoragent@cursor.com>
294 lines
11 KiB
Python
294 lines
11 KiB
Python
"""Research 时讯质量：可信源、同事件去重、tech 主题过滤、国内配额。"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
import unittest
|
||
from pathlib import Path
|
||
from unittest import mock
|
||
|
||
from daily.news.research_quality import (
|
||
build_deduped_candidate_pool,
|
||
dedupe_same_event,
|
||
filter_tech_against_items,
|
||
is_cn_item,
|
||
is_trusted_item,
|
||
pack_with_cn_quota,
|
||
post_process_research_news,
|
||
research_cn_min,
|
||
)
|
||
|
||
|
||
def _item(
|
||
title: str,
|
||
link: str,
|
||
*,
|
||
source_name: str = "",
|
||
desc_short: str = "",
|
||
region: str | None = None,
|
||
) -> dict:
|
||
row = {
|
||
"title": title,
|
||
"link": link,
|
||
"source_name": source_name,
|
||
"desc_short": desc_short,
|
||
"summary_plain": desc_short,
|
||
"published_fmt": "",
|
||
}
|
||
if region is not None:
|
||
row["region"] = region
|
||
return row
|
||
|
||
|
||
class TestTrustedAndCn(unittest.TestCase):
|
||
def test_trusted_official_and_authority(self):
|
||
self.assertTrue(
|
||
is_trusted_item(_item("x", "https://openai.com/blog/x", source_name="OpenAI"))
|
||
)
|
||
self.assertTrue(
|
||
is_trusted_item(_item("x", "https://techcrunch.com/a", source_name="TechCrunch"))
|
||
)
|
||
self.assertTrue(
|
||
is_trusted_item(_item("x", "https://www.qbitai.com/a", source_name="量子位"))
|
||
)
|
||
|
||
def test_rejects_low_quality(self):
|
||
self.assertFalse(
|
||
is_trusted_item(
|
||
_item("x", "https://wap.stockstar.com/detail/IG1", source_name="证券之星")
|
||
)
|
||
)
|
||
self.assertFalse(
|
||
is_trusted_item(_item("x", "https://random-blog.xyz/a", source_name="Unknown"))
|
||
)
|
||
self.assertFalse(
|
||
is_trusted_item(
|
||
_item("x", "https://www.techtimes.com/articles/1.htm", source_name="TechTimes")
|
||
)
|
||
)
|
||
|
||
def test_trusted_cn_majors_and_engadget(self):
|
||
self.assertTrue(
|
||
is_trusted_item(_item("x", "https://www.yicai.com/news/1.html", source_name="第一财经"))
|
||
)
|
||
self.assertTrue(
|
||
is_trusted_item(
|
||
_item("x", "https://www.news.cn/world/20260729/a/c.html", source_name="新华网")
|
||
)
|
||
)
|
||
self.assertTrue(
|
||
is_trusted_item(
|
||
_item("x", "https://www.engadget.com/2225849/google/", source_name="Engadget")
|
||
)
|
||
)
|
||
|
||
def test_cn_by_whitelist_region_and_cn_tld(self):
|
||
self.assertTrue(is_cn_item(_item("x", "https://www.qbitai.com/a", source_name="量子位")))
|
||
self.assertTrue(
|
||
is_cn_item(_item("x", "https://techcrunch.com/a", source_name="TechCrunch", region="cn"))
|
||
)
|
||
self.assertTrue(is_cn_item(_item("x", "https://news.example.cn/a", source_name="X")))
|
||
self.assertFalse(is_cn_item(_item("x", "https://techcrunch.com/a", source_name="TechCrunch")))
|
||
|
||
|
||
class TestSameEventAndTech(unittest.TestCase):
|
||
def test_petition_cluster_keeps_one(self):
|
||
items = [
|
||
_item(
|
||
"OpenAI, Anthropic scientists ask U.S. for tools to pace AI development",
|
||
"https://www.nbcnews.com/tech/a",
|
||
source_name="NBC News",
|
||
desc_short="超千名前沿实验室员工联名，吁美政府支持控制 AI 研发节奏",
|
||
),
|
||
_item(
|
||
"Sam Altman is ready to decelerate",
|
||
"https://techcrunch.com/2026/07/28/sam-altman-is-ready-to-decelerate/",
|
||
source_name="TechCrunch",
|
||
desc_short="奥特曼称或需控制 AI 发展速度，并支持员工联名请愿",
|
||
),
|
||
]
|
||
out = dedupe_same_event(items)
|
||
self.assertEqual(len(out), 1)
|
||
|
||
def test_distinct_clusters_kept(self):
|
||
items = [
|
||
_item(
|
||
"Sam Altman is ready to decelerate",
|
||
"https://techcrunch.com/a",
|
||
source_name="TechCrunch",
|
||
desc_short="奥特曼称或需控制 AI 发展速度",
|
||
),
|
||
_item(
|
||
"OpenAI’s agent siege forced rebuild at Hugging Face",
|
||
"https://www.theregister.com/ai/a",
|
||
source_name="The Register",
|
||
desc_short="Hugging Face 因 OpenAI 智能体入侵重建基础设施",
|
||
),
|
||
]
|
||
out = dedupe_same_event(items)
|
||
self.assertEqual(len(out), 2)
|
||
|
||
def test_tech_drops_kimi_adapt_when_items_have_kimi_open_source(self):
|
||
items = [
|
||
_item(
|
||
"Moonshot Open-Sources Kimi K3",
|
||
"https://www.caixinglobal.com/a",
|
||
source_name="Caixin",
|
||
desc_short="月之暗面开放 Kimi K3 权重与技术报告",
|
||
)
|
||
]
|
||
tech = [
|
||
_item(
|
||
"moonshotai/Kimi-K3 · Hugging Face",
|
||
"https://huggingface.co/moonshotai/Kimi-K3",
|
||
source_name="Hugging Face",
|
||
desc_short="Kimi K3 开源权重上线",
|
||
),
|
||
_item(
|
||
"华为官宣昇腾 Day0 支持 Kimi K3",
|
||
"https://www.ithome.com/0/982/615.htm",
|
||
source_name="IT之家",
|
||
desc_short="昇腾宣布适配 Kimi K3 训练与推理",
|
||
),
|
||
_item(
|
||
"MCP Specification 2026-07-28",
|
||
"https://blog.modelcontextprotocol.io/posts/2026-07-28/",
|
||
source_name="MCP Blog",
|
||
desc_short="MCP 正式发布新规范",
|
||
),
|
||
]
|
||
kept = filter_tech_against_items(tech, items)
|
||
self.assertEqual(len(kept), 1)
|
||
self.assertIn("MCP", kept[0]["title"])
|
||
|
||
|
||
class TestDedupedCandidatePool(unittest.TestCase):
|
||
def test_pool_is_unique_events_after_fetch(self):
|
||
items = [
|
||
_item(
|
||
"OpenAI, Anthropic scientists ask U.S. for tools to pace AI development",
|
||
"https://www.nbcnews.com/tech/a",
|
||
source_name="NBC News",
|
||
desc_short="超千名前沿实验室员工联名，吁美政府支持控制 AI 研发节奏",
|
||
),
|
||
_item(
|
||
"Sam Altman is ready to decelerate",
|
||
"https://techcrunch.com/2026/07/28/sam-altman-is-ready-to-decelerate/",
|
||
source_name="TechCrunch",
|
||
desc_short="奥特曼称或需控制 AI 发展速度，并支持员工联名请愿",
|
||
),
|
||
_item(
|
||
"junk",
|
||
"https://wap.stockstar.com/detail/1",
|
||
source_name="证券之星",
|
||
desc_short="营销稿",
|
||
),
|
||
]
|
||
pool, tech = build_deduped_candidate_pool(items, [])
|
||
self.assertEqual(tech, [])
|
||
self.assertEqual(len(pool), 1)
|
||
self.assertTrue(all(is_trusted_item(i) for i in pool))
|
||
|
||
|
||
class TestCnQuota(unittest.TestCase):
|
||
def test_cn_min_default_30_percent(self):
|
||
with mock.patch.dict("os.environ", {"DAILY_WECOM_AI_NEWS_CN_MIN": "0"}, clear=False):
|
||
self.assertEqual(research_cn_min(10), 3)
|
||
with mock.patch.dict("os.environ", {"DAILY_WECOM_AI_NEWS_CN_MIN": "4"}, clear=False):
|
||
self.assertEqual(research_cn_min(10), 4)
|
||
|
||
def test_pack_reserves_cn_slots(self):
|
||
items = [
|
||
_item("I1", "https://techcrunch.com/1", source_name="TechCrunch", desc_short="国际1"),
|
||
_item("I2", "https://techcrunch.com/2", source_name="TechCrunch", desc_short="国际2"),
|
||
_item("I3", "https://techcrunch.com/3", source_name="TechCrunch", desc_short="国际3"),
|
||
_item("C1", "https://www.qbitai.com/1", source_name="量子位", desc_short="国内1"),
|
||
_item("C2", "https://www.36kr.com/1", source_name="36氪", desc_short="国内2"),
|
||
_item("C3", "https://www.jiqizhixin.com/1", source_name="机器之心", desc_short="国内3"),
|
||
]
|
||
out = pack_with_cn_quota(items, limit=5, min_cn=3)
|
||
self.assertEqual(len(out), 5)
|
||
self.assertGreaterEqual(sum(1 for i in out if is_cn_item(i)), 3)
|
||
|
||
|
||
class TestPostProcessIntegration(unittest.TestCase):
|
||
def test_sample_day_filters_stockstar_and_dedupes(self):
|
||
sample = Path(__file__).resolve().parents[1] / "output" / "2026-07-29.ai-news-research.json"
|
||
if not sample.exists():
|
||
self.skipTest("sample research json missing")
|
||
raw = json.loads(sample.read_text(encoding="utf-8"))
|
||
items = [
|
||
_item(
|
||
r["title"],
|
||
r["link"],
|
||
source_name=r.get("source_name", ""),
|
||
desc_short=r.get("desc_short", ""),
|
||
)
|
||
for r in raw["items"]
|
||
]
|
||
tech = [
|
||
_item(
|
||
r["title"],
|
||
r["link"],
|
||
source_name=r.get("source_name", ""),
|
||
desc_short=r.get("desc_short", ""),
|
||
)
|
||
for r in raw["tech_items"]
|
||
]
|
||
out_items, out_tech = post_process_research_news(
|
||
items, tech, limit=10, tech_limit=5, min_cn=3
|
||
)
|
||
links = {i["link"] for i in out_items + out_tech}
|
||
self.assertTrue(all("stockstar" not in link for link in links))
|
||
# 联名/减速同簇只留一条
|
||
petitionish = [
|
||
i
|
||
for i in out_items
|
||
if "decelerat" in i["title"].lower()
|
||
or "联名" in (i.get("desc_short") or "")
|
||
or "pace AI" in i["title"]
|
||
]
|
||
self.assertLessEqual(len(petitionish), 1)
|
||
# Kimi 适配不应再堆在 tech
|
||
kimi_tech = [t for t in out_tech if "kimi" in (t["title"] + t.get("desc_short", "")).lower()]
|
||
self.assertEqual(kimi_tech, [])
|
||
|
||
def test_sample_2026_07_30_keeps_cn_majors(self):
|
||
sample = Path(__file__).resolve().parents[1] / "output" / "2026-07-30.ai-news-research.json"
|
||
if not sample.exists():
|
||
self.skipTest("sample research json missing")
|
||
raw = json.loads(sample.read_text(encoding="utf-8"))
|
||
items = [
|
||
_item(
|
||
r["title"],
|
||
r["link"],
|
||
source_name=r.get("source_name", ""),
|
||
desc_short=r.get("desc_short", ""),
|
||
region=r.get("region"),
|
||
)
|
||
for r in raw["items"]
|
||
]
|
||
tech = [
|
||
_item(
|
||
r["title"],
|
||
r["link"],
|
||
source_name=r.get("source_name", ""),
|
||
desc_short=r.get("desc_short", ""),
|
||
region=r.get("region"),
|
||
)
|
||
for r in raw["tech_items"]
|
||
]
|
||
out_items, out_tech = post_process_research_news(
|
||
items, tech, limit=10, tech_limit=5, min_cn=3
|
||
)
|
||
# 不应再被白名单误杀成只剩 1 条
|
||
self.assertGreaterEqual(len(out_items) + len(out_tech), 4)
|
||
self.assertGreaterEqual(sum(1 for i in out_items if is_cn_item(i)), 2)
|
||
hosts = " ".join(i["link"] for i in out_items + out_tech)
|
||
self.assertNotIn("techtimes.com", hosts)
|
||
self.assertTrue("yicai.com" in hosts or "news.cn" in hosts)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
unittest.main()
|