zwitschi
9f0a216c5e
- Created index.html template for the homepage with service cards and partner logos. - Added page_from_md.html template for rendering pages from markdown. - Developed services.html template detailing various services offered. - Implemented tests for link handling in markdown, ensuring external links open in new tabs and internal links function correctly. - Enhanced markdown parser tests to validate heading extraction, content rendering, and link safety. - Introduced utility tests for template rendering, HTML minification, and JavaScript minification. Co-authored-by: Copilot <copilot@github.com>
352 lines
8.8 KiB
Python
352 lines
8.8 KiB
Python
import textwrap
|
|
import pytest
|
|
from bs4 import BeautifulSoup
|
|
from markdown import Markdown
|
|
from xml.etree.ElementTree import Element, SubElement
|
|
from lib.markdown_parser import (
|
|
HeadingCollector,
|
|
HeadingExtension,
|
|
build_component_structure,
|
|
markdown_to_html_lines,
|
|
parse_markdown_file,
|
|
)
|
|
|
|
|
|
def test_h4_creates_card_details():
|
|
md = textwrap.dedent("""
|
|
# Page Title
|
|
|
|
## Section One
|
|
|
|
### Card One
|
|
Card intro paragraph.
|
|
|
|
#### Detail A
|
|
Detail content line 1.
|
|
- item 1
|
|
- item 2
|
|
|
|
#### Detail B
|
|
Another detail paragraph with [a link](https://example.com).
|
|
""")
|
|
|
|
page = build_component_structure(md, "test.md")
|
|
|
|
assert page['title'] == 'Page Title'
|
|
assert len(page['sections']) == 1
|
|
section = page['sections'][0]
|
|
assert section['title'] == 'Section One'
|
|
assert len(section['cards']) == 1
|
|
card = section['cards'][0]
|
|
assert card['title'] == 'Card One'
|
|
# content should include the intro paragraph converted to HTML
|
|
assert 'Card intro paragraph' in card['content']
|
|
# details should be present
|
|
assert 'details' in card
|
|
assert len(card['details']) == 2
|
|
assert card['details'][0]['title'] == 'Detail A'
|
|
assert 'item 1' in card['details'][0]['content']
|
|
assert card['details'][1]['title'] == 'Detail B'
|
|
assert 'https://example.com' in card['details'][1]['content']
|
|
|
|
|
|
def test_section_content_preserves_lists_before_first_card():
|
|
md = textwrap.dedent("""
|
|
# Title
|
|
|
|
## Section One
|
|
|
|
- Item A
|
|
- Item B
|
|
|
|
### Card Title
|
|
Card body
|
|
""")
|
|
|
|
page = build_component_structure(md, "test.md")
|
|
|
|
section = page['sections'][0]
|
|
assert '<ul>' in section['content']
|
|
assert '<li>Item A</li>' in section['content']
|
|
assert section['cards'][0]['title'] == 'Card Title'
|
|
|
|
|
|
def test_card_content_keeps_lists_when_section_changes():
|
|
md = textwrap.dedent("""
|
|
# Title
|
|
|
|
## Section One
|
|
|
|
### Card One
|
|
- First
|
|
- Second
|
|
|
|
## Section Two
|
|
Details
|
|
""")
|
|
|
|
page = build_component_structure(md, "test.md")
|
|
|
|
first_section = page['sections'][0]
|
|
card = first_section['cards'][0]
|
|
assert '<ul>' in card['content']
|
|
assert '<li>First</li>' in card['content']
|
|
|
|
|
|
def test_card_body_renders_list_items():
|
|
md = textwrap.dedent("""
|
|
# Title
|
|
|
|
## Section
|
|
|
|
### Card
|
|
- Alpha
|
|
- Beta
|
|
- Gamma
|
|
""")
|
|
|
|
page = build_component_structure(md, "test.md")
|
|
|
|
card = page['sections'][0]['cards'][0]
|
|
assert '<ul>' in card['content']
|
|
assert '<li>Alpha</li>' in card['content']
|
|
assert '<li>Gamma</li>' in card['content']
|
|
|
|
|
|
def test_external_links_add_target_attributes():
|
|
md = textwrap.dedent("""
|
|
# Title
|
|
|
|
## Section
|
|
|
|
Visit [Example](https://example.com) now.
|
|
""")
|
|
|
|
page = build_component_structure(md, "test.md")
|
|
|
|
section_html = page['sections'][0]['content']
|
|
soup = BeautifulSoup(section_html, 'html.parser')
|
|
anchor = soup.find('a')
|
|
assert anchor is not None
|
|
assert anchor['href'] == 'https://example.com'
|
|
assert anchor.get('target') == '_blank'
|
|
assert anchor.get('rel') == ['noopener', 'noreferrer']
|
|
|
|
|
|
def test_unsafe_links_are_neutralized():
|
|
md = textwrap.dedent("""
|
|
# Title
|
|
|
|
## Section
|
|
|
|
[Bad](javascript:alert('xss'))
|
|
""")
|
|
|
|
page = build_component_structure(md, "test.md")
|
|
|
|
section_html = page['sections'][0]['content']
|
|
soup = BeautifulSoup(section_html, 'html.parser')
|
|
anchor = soup.find('a')
|
|
assert anchor is not None
|
|
assert anchor['href'] == '#unsafe'
|
|
assert 'target' not in anchor.attrs
|
|
assert 'rel' not in anchor.attrs
|
|
|
|
|
|
def test_index_page_sections_and_headings_extracted():
|
|
text = """
|
|
# Title
|
|
|
|
Main intro paragraph.
|
|
|
|
## Section 1
|
|
|
|
Section 1 intro.
|
|
|
|
- List item 1 a
|
|
- List item 1 b
|
|
|
|
## Section 2
|
|
|
|
Section 2 intro.
|
|
|
|
- List item 2 a
|
|
- List item 2 b
|
|
|
|
"""
|
|
md = Markdown(extensions=[HeadingExtension()])
|
|
md.convert(text)
|
|
collector = md.treeprocessors['heading_collector']
|
|
headings = [h for h in getattr(collector, 'headings', []) if 'level' in h]
|
|
|
|
assert headings[0]['level'] == 1
|
|
assert headings[0]['text'] == 'Title'
|
|
assert headings[1]['level'] == 2
|
|
assert headings[1]['text'] == 'Section 1'
|
|
assert headings[2]['level'] == 2
|
|
assert headings[2]['text'] == 'Section 2'
|
|
|
|
|
|
def test_index_page_main_intro_extracted():
|
|
text = """
|
|
# Title
|
|
|
|
This is the main introduction paragraph for the index page.
|
|
|
|
## Section 1
|
|
|
|
Section content.
|
|
"""
|
|
md = Markdown(extensions=[HeadingExtension()])
|
|
md.convert(text)
|
|
collector = md.treeprocessors['heading_collector']
|
|
main_intro = getattr(collector, 'main_intro', '')
|
|
|
|
assert 'This is the main introduction paragraph for the index page.' in main_intro
|
|
|
|
|
|
def test_heading_extension_collects_headings_and_lists():
|
|
md = Markdown(extensions=[HeadingExtension()])
|
|
md.convert(textwrap.dedent("""
|
|
# Title
|
|
|
|
## Section with **Bold** and [Link](#target)
|
|
|
|
- Item A
|
|
- [Item B](#b) and more
|
|
"""))
|
|
|
|
collector = md.treeprocessors['heading_collector']
|
|
headings = getattr(collector, 'headings', [])
|
|
|
|
assert headings[0]['level'] == 1
|
|
assert headings[0]['text'] == 'Title'
|
|
assert headings[1]['level'] == 2
|
|
assert headings[1]['text'] == 'Section with Bold and Link'
|
|
list_entry = next(entry for entry in headings if entry.get('type') == 'ul')
|
|
assert list_entry['items'][0] == 'Item A'
|
|
assert 'Item B' in list_entry['items'][1]
|
|
|
|
|
|
def test_heading_collector_extract_text_handles_children():
|
|
collector = HeadingCollector(Markdown())
|
|
parent = Element('p')
|
|
child = SubElement(parent, 'strong')
|
|
child.text = 'Bold'
|
|
child.tail = ' tail'
|
|
nested = SubElement(child, 'em')
|
|
nested.text = 'inner'
|
|
|
|
text = collector._extract_text(parent)
|
|
|
|
assert 'Bold' in text
|
|
assert 'tail' in text
|
|
assert 'inner' in text
|
|
|
|
collector.headings = []
|
|
collector._process_element(parent)
|
|
assert collector.headings == []
|
|
|
|
|
|
def test_parse_markdown_file_sets_title_from_filename(tmp_path):
|
|
file_path = tmp_path / 'sample_page.md'
|
|
file_path.write_text('Just text without heading', encoding='utf-8')
|
|
|
|
page = parse_markdown_file(str(file_path))
|
|
|
|
assert page['title'] == 'Sample Page'
|
|
|
|
|
|
def test_parse_markdown_file_missing(tmp_path):
|
|
missing = tmp_path / 'not_there.md'
|
|
|
|
with pytest.raises(FileNotFoundError):
|
|
parse_markdown_file(str(missing))
|
|
|
|
|
|
def test_markdown_to_html_lines_handles_empty_and_blank_links():
|
|
assert markdown_to_html_lines('') == ''
|
|
|
|
html = markdown_to_html_lines(
|
|
'Before [Empty]() and [External](https://example.com)')
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
anchors = soup.find_all('a')
|
|
|
|
assert anchors[0]['href'] == ''
|
|
assert 'target' not in anchors[0].attrs
|
|
assert anchors[1]['target'] == '_blank'
|
|
|
|
|
|
def test_markdown_images_normalize_src_and_alt():
|
|
html = markdown_to_html_lines(
|
|
'')
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
image = soup.find('img')
|
|
|
|
assert image is not None
|
|
assert image['src'] == 'img/it-consulting.svg'
|
|
assert image['alt'] == 'IT Consulting'
|
|
|
|
|
|
def test_markdown_images_add_alt_fallback():
|
|
html = markdown_to_html_lines('')
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
image = soup.find('img')
|
|
|
|
assert image is not None
|
|
assert image['src'] == 'img/logo.svg'
|
|
assert image['alt'] == 'logo'
|
|
|
|
|
|
def test_markdown_heading_with_inline_image_preserves_image():
|
|
html = markdown_to_html_lines('## Heading ')
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
heading = soup.find('h2')
|
|
image = heading.find('img') if heading else None
|
|
|
|
assert heading is not None
|
|
assert heading.get_text(strip=True) == 'Heading'
|
|
assert image is not None
|
|
assert image['src'] == 'img/graphic.svg'
|
|
assert image['alt'] == 'Graphic'
|
|
|
|
|
|
def test_build_component_structure_converts_section_images():
|
|
md = textwrap.dedent("""
|
|
# Title
|
|
|
|
## Section With Visual
|
|
|
|
Intro text before image.
|
|
|
|
|
|
""")
|
|
|
|
page = build_component_structure(md, "section.md")
|
|
section_html = page['sections'][0]['content']
|
|
soup = BeautifulSoup(section_html, 'html.parser')
|
|
image = soup.find('img')
|
|
|
|
assert image is not None
|
|
assert image['src'] == 'img/vision.png'
|
|
assert image['alt'] == 'Vision Diagram'
|
|
|
|
|
|
def test_build_component_structure_preserves_external_image_src():
|
|
md = textwrap.dedent("""
|
|
# Title
|
|
|
|
## Section
|
|
|
|
|
|
""")
|
|
|
|
page = build_component_structure(md, "external.md")
|
|
section_html = page['sections'][0]['content']
|
|
soup = BeautifulSoup(section_html, 'html.parser')
|
|
image = soup.find('img')
|
|
|
|
assert image is not None
|
|
assert image['src'] == 'https://cdn.example.com/logo.svg'
|
|
assert image['alt'] == 'Remote Logo'
|