kb-skills/tests/test_zhihu_metadata/test_markdown_converter.py

"""Tests for MarkdownConverter in kb_workflow.metadata

Tests cover:
- Normal image conversion
- Zhihu lazy loading image handling (data-actualsrc)
- Alternative lazy loading (data-original)
- Mixed content with images
"""

import pytest

from kb_workflow.metadata.markdown_converter import MarkdownConverter


class TestMarkdownConverterImages:
    """Tests for image handling in MarkdownConverter"""

    def test_normal_image_conversion(self):
        """Test that normal images are converted correctly"""
        html = '<img src="https://example.com/image.jpg" alt="test">'
        converter = MarkdownConverter()
        result = converter.convert(html)
        assert "![test](https://example.com/image.jpg)" in result

    def test_zhihu_lazy_load_image_with_data_actualsrc(self):
        """Test that Zhihu lazy loading images use data-actualsrc"""
        html = '''<img src="data:image/svg+xml;utf8,<svg></svg>"
                   data-actualsrc="https://pic1.zhimg.com/v2-real-image_b.jpg">'''
        converter = MarkdownConverter()
        result = converter.convert(html)
        assert "https://pic1.zhimg.com/v2-real-image_b.jpg" in result
        assert "data:image/svg+xml" not in result

    def test_lazy_load_image_with_data_original(self):
        """Test that images with data-original use that URL"""
        html = '''<img src="data:image/svg+xml;..." data-original="https://example.com/original.jpg">'''
        converter = MarkdownConverter()
        result = converter.convert(html)
        assert "https://example.com/original.jpg" in result
        assert "data:image/svg+xml" not in result

    def test_data_actualsrc_priority_over_data_original(self):
        """Test that data-actualsrc takes priority over data-original"""
        html = '''<img src="data:image/svg+xml;..."
                   data-actualsrc="https://example.com/actual.jpg"
                   data-original="https://example.com/original.jpg">'''
        converter = MarkdownConverter()
        result = converter.convert(html)
        assert "https://example.com/actual.jpg" in result
        assert "https://example.com/original.jpg" not in result

    def test_normal_image_not_modified(self):
        """Test that normal images with http(s) src are not modified"""
        html = '<img src="https://example.com/normal.jpg">'
        converter = MarkdownConverter()
        result = converter.convert(html)
        assert "https://example.com/normal.jpg" in result

    def test_mixed_content_with_images(self):
        """Test conversion of mixed content with text and images"""
        html = '''
        <div class="RichText">
            <p>First paragraph.</p>
            <figure>
                <img src="data:image/svg+xml;..." data-actualsrc="https://pic.zhimg.com/image1.jpg">
            </figure>
            <p>Second paragraph.</p>
            <img src="https://example.com/normal.jpg">
        </div>
        '''
        converter = MarkdownConverter()
        result = converter.convert(html)

        # Check text content
        assert "First paragraph" in result
        assert "Second paragraph" in result

        # Check lazy loaded image
        assert "https://pic.zhimg.com/image1.jpg" in result

        # Check normal image
        assert "https://example.com/normal.jpg" in result

        # Ensure no SVG placeholders in result
        assert "data:image/svg+xml" not in result

    def test_figure_with_caption(self):
        """Test that figure elements with captions are handled correctly"""
        html = '''
        <figure>
            <img src="data:image/svg+xml;..." data-actualsrc="https://pic.zhimg.com/fig.jpg">
            <figcaption>Image caption</figcaption>
        </figure>
        '''
        converter = MarkdownConverter()
        result = converter.convert(html)

        assert "https://pic.zhimg.com/fig.jpg" in result
        assert "Image caption" in result

    def test_noscript_images_not_duplicated(self):
        """Test that images inside noscript tags don't cause duplicates

        Zhihu HTML structure includes noscript fallback images:
        <figure><img data-actualsrc=...><noscript><img src=...></noscript></figure>

        After fixing lazy-load, both imgs would have real URLs, causing duplicates.
        The fix removes noscript tags before processing.
        """
        html = '''
        <figure>
            <img src="data:image/svg+xml;..." data-actualsrc="https://pic.zhimg.com/test.jpg">
            <noscript>
                <img src="https://pic.zhimg.com/test.jpg">
            </noscript>
        </figure>
        '''
        converter = MarkdownConverter()
        result = converter.convert(html)

        # Should appear exactly once, not twice
        assert result.count("zhimg.com") == 1
        assert "https://pic.zhimg.com/test.jpg" in result

    def test_empty_src_with_data_actualsrc(self):
        """Test handling of empty src with data-actualsrc"""
        html = '<img src="" data-actualsrc="https://example.com/fallback.jpg">'
        converter = MarkdownConverter()
        result = converter.convert(html)
        # Empty src is not a data: URI, so it should stay as is
        assert "https://example.com/fallback.jpg" not in result


class TestMarkdownConverterBasicConversion:
    """Tests for basic HTML to Markdown conversion"""

    def test_paragraphs(self):
        """Test paragraph conversion"""
        html = "<p>First</p><p>Second</p>"
        converter = MarkdownConverter()
        result = converter.convert(html)
        assert "First" in result
        assert "Second" in result

    def test_headings(self):
        """Test heading conversion"""
        html = "<h1>Title</h1><h2>Subtitle</h2>"
        converter = MarkdownConverter()
        result = converter.convert(html)
        assert "# Title" in result
        assert "## Subtitle" in result

    def test_links(self):
        """Test link conversion"""
        html = '<a href="https://example.com">Link</a>'
        converter = MarkdownConverter()
        result = converter.convert(html)
        assert "[Link](https://example.com)" in result

    def test_code_blocks(self):
        """Test code block conversion"""
        html = "<pre><code>def hello():\n    print('hello')</code></pre>"
        converter = MarkdownConverter()
        result = converter.convert(html)
        assert "```" in result or "def hello():" in result