bss/incorporeal-cms
1
0
Fork 0
Code Issues 5 Pull Requests Releases 54 Wiki Activity

use beautifulsoup to parse the description from the first paragraph

Browse Source 
Signed-off-by: Brian S. Stephan <bss@incorporeal.org>
This commit is contained in:
Brian S. Stephan
2026-01-28 14:27:21 -06:00
parent 20673c178a
commit 8238787900
4 changed files with 44 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
tests/test_markdown.py
View File

@@ -134,62 +134,77 @@ def test_request_path_to_breadcrumb_display_patterns():
def test_parse_md_metadata():
"""Test the direct results of parsing a markdown file."""
content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'more-metadata.md'), PAGES_DIR)
content, md, page_name, page_title, page_desc, mtime = parse_md(
os.path.join(PAGES_DIR, 'more-metadata.md'),
PAGES_DIR
)
assert page_name == 'title for the page'
assert page_title == 'title for the page - example.org'
assert page_desc == 'description of this page made even longer'
def test_parse_md_metadata_forced_no_title():
"""Test the direct results of parsing a markdown file."""
content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'forced-no-title.md'), PAGES_DIR)
content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR, 'forced-no-title.md'), PAGES_DIR)
assert page_name == ''
assert page_title == 'example.org'
def test_parse_md_metadata_no_title_so_h1():
"""Test the direct results of parsing a markdown file."""
content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'subdir/index.md'), PAGES_DIR)
content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR, 'subdir/index.md'), PAGES_DIR)
assert page_name == 'another page'
assert page_title == 'another page - example.org'
def test_parse_md_metadata_no_title_or_h1_so_path():
"""Test the direct results of parsing a markdown file."""
content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'no-title-or-h1.md'), PAGES_DIR)
content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR, 'no-title-or-h1.md'), PAGES_DIR)
assert page_name == '/no-title-or-h1'
assert page_title == '/no-title-or-h1 - example.org'
def test_parse_md_metadata_no_title_or_h1_so_path_dir():
"""Test the direct results of parsing a markdown file."""
content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'no-title-subdir/index.md'), PAGES_DIR)
content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR, 'no-title-subdir/index.md'),
PAGES_DIR)
assert page_name == '/no-title-subdir/'
assert page_title == '/no-title-subdir/ - example.org'
def test_parse_md_metadata_no_title_or_h1_so_path_dir_file():
"""Test the direct results of parsing a markdown file."""
content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'no-title-subdir/no-title-or-h1.md'),
PAGES_DIR)
content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR,
'no-title-subdir/no-title-or-h1.md'),
PAGES_DIR)
assert page_name == '/no-title-subdir/no-title-or-h1'
assert page_title == '/no-title-subdir/no-title-or-h1 - example.org'
def test_parse_md_derive_description_from_p():
"""Test that we can get a description from the first paragraph in the file."""
content, md, page_name, page_title, page_desc, mtime = parse_md(
os.path.join(PAGES_DIR, 'rambling.md'),
PAGES_DIR
)
assert page_desc == 'this is a long string of text where I am typing a lot over multiple lines'
def test_parse_md_no_file():
"""Test the direct results of parsing a markdown file."""
with pytest.raises(FileNotFoundError):
content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'nope.md'), PAGES_DIR)
content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR, 'nope.md'), PAGES_DIR)
def test_parse_md_bad_file():
"""Test the direct results of parsing a markdown file."""
with pytest.raises(ValueError):
content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'actually-a-png.md'), PAGES_DIR)
content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR, 'actually-a-png.md'), PAGES_DIR)
def test_md_extension_in_source_link_is_stripped():
"""Test that if a foo.md file link is specified in the Markdown, it is foo in the HTML."""
content, _, _, _, _ = parse_md(os.path.join(PAGES_DIR, 'file-with-md-link.md'), PAGES_DIR)
content, _, _, _, _, _ = parse_md(os.path.join(PAGES_DIR, 'file-with-md-link.md'), PAGES_DIR)
assert '<a href="foo">Foo</a>' in content
assert '<a href="foo#anchor">Anchored Foo</a>' in content
assert '<a href="sub/foo">Sub Foo</a>' in content
@@ -198,7 +213,7 @@ def test_md_extension_in_source_link_is_stripped():
def test_index_in_source_link_is_stripped():
"""Test that if a index.md file link is specified in the Markdown, it is just the dir in the HTML."""
content, _, _, _, _ = parse_md(os.path.join(PAGES_DIR, 'file-with-index.md-link.md'), PAGES_DIR)
content, _, _, _, _, _ = parse_md(os.path.join(PAGES_DIR, 'file-with-index.md-link.md'), PAGES_DIR)
assert '<a href="cool/">Cool</a>' in content
assert '<a href="cool/#anchor">Anchored Cool</a>' in content
assert '<a href=".">This Index</a>' in content