"""Tests for feed parser functionality."""

from pydantic import HttpUrl

from thicket.core.feed_parser import FeedParser
from thicket.models import AtomEntry, FeedMetadata


class TestFeedParser:
    """Test the FeedParser class."""

    def test_init(self):
        """Test parser initialization."""
        parser = FeedParser()
        assert parser.user_agent == "thicket/0.1.0"
        assert "a" in parser.allowed_tags
        assert "href" in parser.allowed_attributes["a"]

    def test_parse_atom_feed(self, sample_atom_feed):
        """Test parsing an Atom feed."""
        parser = FeedParser()
        metadata, entries = parser.parse_feed(sample_atom_feed)

        # Check metadata
        assert isinstance(metadata, FeedMetadata)
        assert metadata.title == "Test Feed"
        assert metadata.author_name == "Test Author"
        assert metadata.author_email == "author@example.com"
        assert metadata.link == HttpUrl("https://example.com/")

        # Check entries
        assert len(entries) == 1
        entry = entries[0]
        assert isinstance(entry, AtomEntry)
        assert entry.title == "Test Entry"
        assert entry.id == "https://example.com/entry/1"
        assert entry.link == HttpUrl("https://example.com/entry/1")
        assert entry.summary == "This is a test entry."
        assert "<p>This is the content of the test entry.</p>" in entry.content

    def test_parse_rss_feed(self, sample_rss_feed):
        """Test parsing an RSS feed."""
        parser = FeedParser()
        metadata, entries = parser.parse_feed(sample_rss_feed)

        # Check metadata
        assert isinstance(metadata, FeedMetadata)
        assert metadata.title == "Test RSS Feed"
        assert metadata.link == HttpUrl("https://example.com/")
        assert metadata.author_email == "editor@example.com"

        # Check entries
        assert len(entries) == 1
        entry = entries[0]
        assert isinstance(entry, AtomEntry)
        assert entry.title == "Test RSS Entry"
        assert entry.id == "https://example.com/rss/entry/1"
        assert entry.summary == "This is a test RSS entry."

    def test_sanitize_entry_id(self):
        """Test entry ID sanitization."""
        parser = FeedParser()

        # Test URL ID
        url_id = "https://example.com/posts/2025/01/test-post"
        sanitized = parser.sanitize_entry_id(url_id)
        assert sanitized == "posts_2025_01_test-post"

        # Test problematic characters
        bad_id = "test/with\\bad:chars|and<more>"
        sanitized = parser.sanitize_entry_id(bad_id)
        assert sanitized == "test_with_bad_chars_and_more_"

        # Test empty ID
        empty_id = ""
        sanitized = parser.sanitize_entry_id(empty_id)
        assert sanitized == "entry"

        # Test very long ID
        long_id = "a" * 300
        sanitized = parser.sanitize_entry_id(long_id)
        assert len(sanitized) == 200

    def test_sanitize_html(self):
        """Test HTML sanitization."""
        parser = FeedParser()

        # Test allowed tags
        safe_html = "<p>This is <strong>safe</strong> HTML</p>"
        sanitized = parser._sanitize_html(safe_html)
        assert sanitized == safe_html

        # Test dangerous tags
        dangerous_html = "<script>alert('xss')</script><p>Safe content</p>"
        sanitized = parser._sanitize_html(dangerous_html)
        assert "<script>" not in sanitized
        assert "<p>Safe content</p>" in sanitized

        # Test attributes
        html_with_attrs = '<a href="https://example.com" onclick="alert()">Link</a>'
        sanitized = parser._sanitize_html(html_with_attrs)
        assert 'href="https://example.com"' in sanitized
        assert "onclick" not in sanitized

    def test_extract_feed_metadata(self):
        """Test feed metadata extraction."""
        parser = FeedParser()

        # Test with feedparser parsed data
        import feedparser

        parsed = feedparser.parse("""<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>Test Feed</title>
  <link href="https://example.com/"/>
  <author>
    <name>Test Author</name>
    <email>author@example.com</email>
    <uri>https://example.com/about</uri>
  </author>
  <logo>https://example.com/logo.png</logo>
  <icon>https://example.com/icon.png</icon>
</feed>""")

        metadata = parser._extract_feed_metadata(parsed.feed)
        assert metadata.title == "Test Feed"
        assert metadata.author_name == "Test Author"
        assert metadata.author_email == "author@example.com"
        assert metadata.author_uri == HttpUrl("https://example.com/about")
        assert metadata.link == HttpUrl("https://example.com/")
        assert metadata.logo == HttpUrl("https://example.com/logo.png")
        assert metadata.icon == HttpUrl("https://example.com/icon.png")