discord_bot/tests/test_spec_news.py

"""Unit coverage for SPEC-013 news digest + memory + tool (NEWS-01..12)."""

import tempfile
import unittest
from pathlib import Path
from unittest.mock import AsyncMock

from fjerkroa_bot.news import (
    GET_NEWS_TOOL,
    NewsFetcher,
    NewsPoster,
    load_seen,
    parse_feed,
    query_news,
    render_digest,
    save_seen,
)
from fjerkroa_bot.openai_responder import OpenAIResponder
from fjerkroa_bot.persistence import PersistentStore

CONFIG = {"openai-token": "t", "model": "m", "system": "s", "history-limit": 5}

RSS = b"""<?xml version="1.0"?><rss><channel>
<item><title>Game X released</title><link>https://ex.com/x</link></item>
<item><title>Patch Y notes</title><link>https://ex.com/y</link></item>
</channel></rss>"""

ATOM = b"""<?xml version="1.0"?><feed xmlns="http://www.w3.org/2005/Atom">
<entry><title>Atom headline</title><link href="https://ex.com/a"/></entry>
</feed>"""


class TestParse(unittest.TestCase):
    def test_rss(self):
        """NEWS-01: RSS items parsed with title + link."""
        items = parse_feed(RSS, "Src")
        self.assertEqual([i["title"] for i in items], ["Game X released", "Patch Y notes"])
        self.assertEqual(items[0]["link"], "https://ex.com/x")
        self.assertEqual(items[0]["source"], "Src")

    def test_atom(self):
        """NEWS-01: Atom entries parsed with href link."""
        items = parse_feed(ATOM, "A")
        self.assertEqual(items[0]["title"], "Atom headline")
        self.assertEqual(items[0]["link"], "https://ex.com/a")

    def test_malformed_never_raises(self):
        """NEWS-01: garbage XML returns [] without raising."""
        self.assertEqual(parse_feed(b"<not xml", "bad"), [])
        self.assertEqual(parse_feed(b"", "empty"), [])


class TestDigest(unittest.TestCase):
    def test_sanitized_and_capped(self):
        """NEWS-02: headlines sanitized, item count capped."""
        items = [{"title": "@everyone big news \x00", "link": "", "source": "S"} for _ in range(20)]
        digest = render_digest(items, max_items=5)
        self.assertEqual(digest.count("\n"), 4)  # 5 lines
        self.assertNotIn("@everyone", digest)
        self.assertNotIn("\x00", digest)


class TestCollect(unittest.IsolatedAsyncioTestCase):
    async def test_ssrf_skip_and_dedup(self):
        """NEWS-03: guarded feed skipped, dup titles dropped, bad fetch survived."""

        def guard(url):
            return "refused" if "internal" in url else None

        async def fetch(url):
            if "boom" in url:
                raise ValueError("boom")
            return RSS  # same content from two feeds -> dedup

        fetcher = NewsFetcher(guard, fetch)
        feeds = [
            ("https://a.com/feed", "A"),
            ("https://internal/feed", "Internal"),  # SSRF-skipped
            ("https://boom.com/feed", "Boom"),  # fetch fails
            ("https://b.com/feed", "B"),  # same RSS -> dup titles dropped
        ]
        items = await fetcher.collect(feeds, per_feed=5)
        titles = [i["title"] for i in items]
        self.assertEqual(titles, ["Game X released", "Patch Y notes"])  # deduped, internal+boom skipped

    async def test_per_feed_limit(self):
        """NEWS-03: per-feed cap honored."""
        fetcher = NewsFetcher(lambda u: None, AsyncMock(return_value=RSS))
        items = await fetcher.collect([("https://a.com", "A")], per_feed=1)
        self.assertEqual(len(items), 1)


class TestPoster(unittest.IsolatedAsyncioTestCase):
    def poster(self, posts):
        async def fetch(url):
            return RSS

        async def post(hook, content):
            posts.append((hook, content))

        return NewsPoster(lambda u: None, fetch, post)

    async def test_posts_unseen_then_dedups(self):
        """NEWS-04: unseen items post to the mapped webhook; re-run posts nothing."""
        posts = []
        poster = self.poster(posts)
        feeds = [("https://a.com/feed", "PS", "news")]
        hooks = {"news": "https://discord.com/api/webhooks/x"}
        posted, seen = await poster.run_post(feeds, hooks, set(), per_feed=5, max_per_run=8, seed_only=False)
        self.assertEqual(posted, 2)
        self.assertIn("PS", posts[0][1])
        self.assertIn("https://discord.com/api/webhooks/x", posts[0][0])
        # re-run with the accumulated seen -> nothing new
        posts.clear()
        posted2, _ = await poster.run_post(feeds, hooks, seen, per_feed=5, max_per_run=8, seed_only=False)
        self.assertEqual(posted2, 0)
        self.assertEqual(posts, [])

    async def test_seed_run_posts_nothing(self):
        """NEWS-05: seed_only marks items seen without posting."""
        posts = []
        poster = self.poster(posts)
        feeds = [("https://a.com/feed", "PS", "news")]
        posted, seen = await poster.run_post(feeds, {"news": "h"}, set(), 5, 8, seed_only=True)
        self.assertEqual(posted, 0)
        self.assertEqual(posts, [])
        self.assertEqual(len(seen), 2)  # both marked seen

    async def test_max_per_run_caps(self):
        """NEWS-05: max-per-run caps posts; extras stay seen (not re-posted next run)."""
        posts = []
        poster = self.poster(posts)
        feeds = [("https://a.com/feed", "PS", "news")]
        posted, seen = await poster.run_post(feeds, {"news": "h"}, set(), per_feed=5, max_per_run=1, seed_only=False)
        self.assertEqual(posted, 1)
        self.assertEqual(len(seen), 2)  # both seen, only one posted

    async def test_failures_survived(self):
        """NEWS-06: SSRF-skip, fetch fail, missing webhook, post error each survive."""
        posts = []

        async def fetch(url):
            if "boom" in url:
                raise ValueError("boom")
            return RSS

        async def post(hook, content):
            if hook == "bad":
                raise RuntimeError("post failed")
            posts.append((hook, content))

        def guard(url):
            return "refused" if "internal" in url else None

        poster = NewsPoster(guard, fetch, post)
        feeds = [
            ("https://internal/feed", "I", "news"),  # SSRF-skipped
            ("https://boom.com/feed", "B", "news"),  # fetch fails
            ("https://ok.com/feed", "OK", "nowhere"),  # no webhook for channel
            ("https://ok2.com/feed", "OK2", "news"),  # webhook raises
        ]
        posted, seen = await poster.run_post(feeds, {"news": "bad"}, set(), 5, 8, seed_only=False)
        self.assertEqual(posted, 0)  # everything failed/skipped, no crash


class TestSeenState(unittest.TestCase):
    def test_roundtrip_and_seed_detection(self):
        """NEWS-05: missing state -> (empty, existed=False); saved state reloads."""
        import tempfile
        from pathlib import Path

        with tempfile.TemporaryDirectory() as tmp:
            path = str(Path(tmp) / "state.json")
            seen, existed = load_seen(path)
            self.assertEqual((seen, existed), (set(), False))
            save_seen(path, {"a", "b", "c"}, cap=5000)
            reloaded, existed2 = load_seen(path)
            self.assertEqual(reloaded, {"a", "b", "c"})
            self.assertTrue(existed2)

    def test_cap_bounds_state(self):
        """NEWS-05: save keeps at most `cap` keys."""
        import json

        with tempfile.TemporaryDirectory() as tmp:
            path = str(Path(tmp) / "state.json")
            save_seen(path, {f"k{i}" for i in range(100)}, cap=10)
            self.assertEqual(len(json.load(open(path))), 10)


RSS_DESC = b"""<?xml version="1.0"?><rss><channel>
<item><title>Storm hits coast</title><link>https://ex.com/s</link>
<description>&lt;p&gt;Heavy &lt;b&gt;wind&lt;/b&gt;   expected&lt;/p&gt;</description></item>
</channel></rss>"""

ATOM_SUM = b"""<?xml version="1.0"?><feed xmlns="http://www.w3.org/2005/Atom">
<entry><title>Atom T</title><link href="https://ex.com/a"/><summary>Short  gist  here</summary></entry>
</feed>"""


class TestSummaries(unittest.TestCase):
    def test_rss_description_stripped(self):
        """NEWS-07: RSS description parsed, HTML stripped, entities unescaped, whitespace collapsed."""
        items = parse_feed(RSS_DESC, "S")
        self.assertEqual(items[0]["summary"], "Heavy wind expected")

    def test_atom_summary(self):
        """NEWS-07: Atom summary collapsed to clean text."""
        items = parse_feed(ATOM_SUM, "A")
        self.assertEqual(items[0]["summary"], "Short gist here")

    def test_missing_description_is_empty(self):
        """NEWS-07: no description -> empty summary, never an error."""
        self.assertEqual(parse_feed(RSS, "S")[0]["summary"], "")

    def test_digest_carries_summary(self):
        """NEWS-08: digest appends the sanitized capped summary; zero cap = title only."""
        items = [{"title": "T", "link": "https://ex.com/x", "source": "NRK", "summary": "the gist of it"}]
        digest = render_digest(items, 10, 100)
        self.assertIn("[NRK]", digest)
        self.assertIn("the gist of it", digest)
        self.assertNotIn("the gist", render_digest(items, 10, 0))  # zero cap -> title only


class NewsStoreBase(unittest.TestCase):
    def setUp(self):
        self.tmp = tempfile.TemporaryDirectory()
        self.addCleanup(self.tmp.cleanup)
        self.store = PersistentStore(Path(self.tmp.name) / "bot.db")


class TestNewsStore(NewsStoreBase):
    def test_dedup_and_rolling_window(self):
        """NEWS-09: items deduped by link; prune keeps the newest N."""
        first = [
            {"title": "A", "link": "L1", "source": "S", "summary": "sa"},
            {"title": "B", "link": "L2", "source": "S", "summary": "sb"},
        ]
        self.assertEqual(self.store.add_news_items(first), 2)
        self.assertEqual(self.store.add_news_items([dict(first[0])]), 0)  # dup link ignored
        self.assertEqual(self.store.news_count(), 2)
        self.store.prune_news(1)
        self.assertEqual(self.store.news_count(), 1)
        self.assertEqual(self.store.recent_news(5)[0]["title"], "B")  # newest survives

    def test_dedup_by_title_when_no_link(self):
        """NEWS-09: linkless items dedup on title."""
        self.store.add_news_items([{"title": "Same", "link": "", "source": "S", "summary": ""}])
        self.store.add_news_items([{"title": "Same", "link": "", "source": "S", "summary": ""}])
        self.assertEqual(self.store.news_count(), 1)


class TestQueryNews(NewsStoreBase):
    def seed(self):
        self.store.add_news_items(
            [
                {"title": "Nordland storm", "link": "L1", "source": "Nordland", "summary": "strong wind on the coast"},
                {"title": "Oslo budget", "link": "L2", "source": "NRK", "summary": "@everyone spending plan"},
                {"title": "Sport result", "link": "L3", "source": "Sport", "summary": "the match ended"},
            ]
        )

    def test_topic_filter(self):
        """NEWS-11: topic keywords must appear in title or summary."""
        self.seed()
        res = query_news(self.store, topic="storm")
        self.assertEqual([r["title"] for r in res["results"]], ["Nordland storm"])

    def test_topic_matches_source_label(self):
        """NEWS-11: topic also matches the source label, so 'Nordland' finds regional items."""
        self.store.add_news_items([{"title": "Ferry delayed", "link": "LX", "source": "Nordland", "summary": "boat late"}])
        res = query_news(self.store, topic="Nordland")
        self.assertTrue(any(r["link"] == "LX" for r in res["results"]))  # matched via source, not title/summary

    def test_source_filter_and_sanitize(self):
        """NEWS-11: source narrows results; title/summary are sanitized."""
        self.seed()
        res = query_news(self.store, source="NRK")
        self.assertTrue(res["results"] and all(r["source"] == "NRK" for r in res["results"]))
        self.assertNotIn("@everyone", res["results"][0]["summary"])

    def test_limit_clamped_and_no_store(self):
        """NEWS-11: limit clamps to 1..30; a missing store returns an error."""
        self.seed()
        self.assertLessEqual(len(query_news(self.store, limit=999)["results"]), 30)
        self.assertGreaterEqual(len(query_news(self.store, limit=0)["results"]), 1)
        self.assertIn("error", query_news(None))


class TestNewsTool(unittest.IsolatedAsyncioTestCase):
    def setUp(self):
        self.tmp = tempfile.TemporaryDirectory()
        self.addCleanup(self.tmp.cleanup)

    def _responder(self, **extra):
        cfg = dict(CONFIG, **{"history-directory": self.tmp.name}, **extra)
        return OpenAIResponder(cfg, "chat")

    def test_tool_offered_needs_flag_and_store(self):
        """NEWS-10: get_news offered only with enable-news-tool AND a store."""
        no_store = OpenAIResponder(dict(CONFIG, **{"enable-news-tool": True}), "chat")
        self.assertIsNone(no_store.store)
        self.assertNotIn("get_news", [f["name"] for f in no_store._available_tools()])
        flag_off = self._responder()
        self.assertNotIn("get_news", [f["name"] for f in flag_off._available_tools()])
        on = self._responder(**{"enable-news-tool": True})
        self.assertIn("get_news", [f["name"] for f in on._available_tools()])
        self.assertEqual(GET_NEWS_TOOL["name"], "get_news")

    async def test_dispatch_caps_news(self):
        """NEWS-12: over news-daily-per-user, get_news refuses without querying."""
        responder = self._responder(**{"enable-news-tool": True, "news-daily-per-user": 2})
        responder.store.add_news_items([{"title": "x", "link": "l", "source": "s", "summary": "y"}])
        for _ in range(2):
            self.assertIn("results", await responder._dispatch_tool("get_news", {}, "alice"))
        blocked = await responder._dispatch_tool("get_news", {}, "alice")
        self.assertIn("error", blocked)