jbell730
/
anya

import os
import tempfile
import unittest
from datetime import datetime, timezone
from unittest.mock import patch, MagicMock

from services.feeds import looks_like_feed, parse_feed
from services.sources import get_sources
from services.headlines import prepare_headlines
from structs.headline import Headline


RSS_2_0 = """<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel>
<title>Test feed</title>
<item><title>First news story</title><link>https://x/1</link><pubDate>Mon, 14 Sep 2026 12:00:00 GMT</pubDate></item>
<item><title>Second news story</title><link>https://x/2</link></item>
</channel></rss>
"""

ATOM = """<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
<entry><title>Atom story one</title><published>2026-09-14T14:30:00Z</published></entry>
<entry><title>Atom story two</title><updated>2026-09-13T10:00:00Z</updated></entry>
</feed>
"""


class TestLooksLikeFeed(unittest.TestCase):
    def test_rss_and_atom_detected(self):
        self.assertTrue(looks_like_feed(RSS_2_0))
        self.assertTrue(looks_like_feed(ATOM))

    def test_html_not_detected(self):
        self.assertFalse(looks_like_feed("<html><body><a>Story</a></body></html>"))

    def test_empty_not_detected(self):
        self.assertFalse(looks_like_feed(""))
        self.assertFalse(looks_like_feed(None))


class TestParseFeed(unittest.TestCase):
    def test_rss_2_0(self):
        items = parse_feed(RSS_2_0)
        titles = [t for t, _ in items]
        self.assertEqual(titles, ["First news story", "Second news story"])
        self.assertEqual(items[0][1].year, 2026)
        self.assertIsNone(items[1][1])

    def test_atom(self):
        items = parse_feed(ATOM)
        titles = [t for t, _ in items]
        self.assertEqual(titles, ["Atom story one", "Atom story two"])
        self.assertIsNotNone(items[0][1])
        self.assertIsNotNone(items[1][1])

    def test_malformed_returns_empty(self):
        self.assertEqual(parse_feed("not xml at all <<<"), [])


class TestGetSources(unittest.TestCase):
    def test_skips_comments_and_blanks(self):
        path = None
        try:
            with tempfile.NamedTemporaryFile("w", suffix=".txt", delete=False) as f:
                f.write("# a comment\n\nhttps://a.com\n\nhttps://b.com\n# another\n")
                path = f.name
            self.assertEqual(get_sources(path), ["https://a.com", "https://b.com"])
        finally:
            if path:
                os.unlink(path)


class TestFeedDomainNormalization(unittest.TestCase):
    def test_feed_subdomain_stripped(self):
        self.assertEqual(Headline("a", ["a"], "https://feeds.npr.org/1001/rss.xml").domain, "npr.org")
        self.assertEqual(Headline("a", ["a"], "https://rss.nytimes.com/x").domain, "nytimes.com")
        self.assertEqual(Headline("a", ["a"], "https://www.vox.com/rss/index.xml").domain, "vox.com")


class TestPrepareHeadlinesFeed(unittest.TestCase):
    def setUp(self):
        self.stopwords = {"the", "a", "an", "in", "on", "and", "of", "to"}

    @patch("services.headlines.requests.get")
    def test_feed_source_is_parsed(self, mock_get):
        mock_response = MagicMock()
        mock_response.status_code = 200
        mock_response.content = RSS_2_0.encode("utf-8")
        mock_response.text = RSS_2_0
        mock_get.return_value = mock_response

        headlines = prepare_headlines(["https://feeds.bbci.co.uk/news/world/rss.xml"], self.stopwords)

        titles = [h.display_text for h in headlines]
        self.assertEqual(titles, ["First news story", "Second news story"])
        # Domain comes from the feed host, normalized to the outlet.
        self.assertEqual(headlines[0].domain, "bbci.co.uk")
        self.assertIsNotNone(headlines[0].published_at)


if __name__ == "__main__":
    unittest.main()