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

use h1-as-title logic while generating breadcrumbs

Browse Source 
Signed-off-by: Brian S. Stephan <bss@incorporeal.org>
This commit is contained in:
Brian S. Stephan
2026-01-28 16:08:41 -06:00
parent ee4215ede2
commit 204e7bc416
2 changed files with 30 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
incorporealcms/markdown.py
View File

@@ -84,6 +84,21 @@ def parse_md(path: str, pages_root: str):
rel_path = os.path.relpath(path, pages_root)
page_name, page_description = _get_metadata_from_parsed_page(md, content, rel_path)
page_title = f'{page_name} - {Config.TITLE_SUFFIX}' if page_name else Config.TITLE_SUFFIX
logger.debug("title (potentially derived): %s", page_title)
return content, md, page_name, page_title, page_description, mtime
def _get_metadata_from_parsed_page(md, content, path: str):
"""Get the page name and description from a Markdown object and/or HTML output of a page.
Args:
md: the parsed Markdown object, potentially including Meta tags
content: the Markdown page content converted to HTML, to run through BeautifulSoup
path: path of the page, to derive the name from as a fallback
"""
soup = BeautifulSoup(content, features='lxml')
# get the page title first from the markdown tags, second from the first h1, last from the path
@@ -93,7 +108,7 @@ def parse_md(path: str, pages_root: str):
elif h1_tag := soup.find('h1'):
page_name = h1_tag.string
elif not page_name:
page_name = instance_resource_path_to_request_path(rel_path)
page_name = instance_resource_path_to_request_path(path)
# get the page description from the markdown tags or first paragraph
page_description = None
@@ -103,10 +118,7 @@ def parse_md(path: str, pages_root: str):
if page_description := p_tag.string:
page_description = page_description.replace('\n', ' ')
page_title = f'{page_name} - {Config.TITLE_SUFFIX}' if page_name else Config.TITLE_SUFFIX
logger.debug("title (potentially derived): %s", page_title)
return content, md, page_name, page_title, page_description, mtime
return page_name, page_description
def handle_markdown_file_path(path: str, pages_root: str) -> str:
@@ -175,9 +187,8 @@ def generate_parent_navs(path, pages_root: str):
try:
with open(os.path.join(pages_root, path), 'r') as entry_file:
entry = entry_file.read()
_ = Markup(md.convert(entry)) # nosec B704
page_name = (" ".join(md.Meta.get('title')) if md.Meta.get('title')
else request_path_to_breadcrumb_display(request_path))
content = Markup(md.convert(entry)) # nosec B704
page_name, _ = _get_metadata_from_parsed_page(md, content, os.path.relpath(path, parent_resource_dir))
return generate_parent_navs(parent_resource_path, pages_root) + [(page_name, request_path)]
except FileNotFoundError:
return generate_parent_navs(parent_resource_path, pages_root) + [(request_path, request_path)]