mirror of
https://github.com/kevinveenbirkenbach/computer-playbook.git
synced 2025-03-29 04:23:34 +01:00
80 lines
3.3 KiB
Python
80 lines
3.3 KiB
Python
import os
|
|
import re
|
|
from sphinx.util import logging
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
# Set the maximum heading level to include (e.g., include headings up to H3)
|
|
MAX_HEADING_LEVEL = 3
|
|
|
|
def extract_headings_from_file(filepath, max_level=MAX_HEADING_LEVEL):
|
|
"""
|
|
Extract Markdown headings (up to max_level) from the file at filepath.
|
|
Skips fenced code blocks.
|
|
"""
|
|
headings = []
|
|
try:
|
|
with open(filepath, 'r', encoding='utf-8') as f:
|
|
in_code_block = False
|
|
for line in f:
|
|
# Toggle fenced code block state if a line starts with ```
|
|
if line.strip().startswith("```"):
|
|
in_code_block = not in_code_block
|
|
continue
|
|
if in_code_block:
|
|
continue
|
|
# Match Markdown headings: one or more '#' followed by a space and the title.
|
|
match = re.match(r'^(#{1,})\s+(.*)$', line)
|
|
if match:
|
|
level = len(match.group(1))
|
|
if level <= max_level:
|
|
heading_text = match.group(2).strip()
|
|
# Create a simple slug for the anchor by:
|
|
# - converting to lowercase
|
|
# - replacing spaces with hyphens
|
|
# - removing non-alphanumeric characters (except hyphens)
|
|
anchor = re.sub(r'\s+', '-', heading_text.lower())
|
|
anchor = re.sub(r'[^a-z0-9\-]', '', anchor)
|
|
headings.append({'level': level, 'text': heading_text, 'anchor': anchor})
|
|
except Exception as e:
|
|
logger.warning(f"Error reading {filepath}: {e}")
|
|
return headings
|
|
|
|
def add_local_md_headings(app, pagename, templatename, context, doctree):
|
|
"""
|
|
For every Markdown file in the same directory as the current page,
|
|
extract its headings and add them to the context.
|
|
"""
|
|
srcdir = app.srcdir
|
|
# Determine the directory of the current page (e.g., "directory/file" → "directory")
|
|
directory = os.path.dirname(pagename)
|
|
abs_dir = os.path.join(srcdir, directory)
|
|
if not os.path.isdir(abs_dir):
|
|
logger.warning(f"Directory {abs_dir} not found for page {pagename}.")
|
|
context['local_md_headings'] = []
|
|
return
|
|
|
|
local_md_headings = []
|
|
for file in os.listdir(abs_dir):
|
|
if file.endswith('.md'):
|
|
# Optionally, you may choose to skip the current file:
|
|
# if file == os.path.basename(pagename):
|
|
# continue
|
|
filepath = os.path.join(abs_dir, file)
|
|
headings = extract_headings_from_file(filepath)
|
|
for heading in headings:
|
|
# Build a full link: if there is a directory, include it in the path.
|
|
file_link = os.path.join(directory, file) if directory else file
|
|
full_link = file_link + '#' + heading['anchor']
|
|
local_md_headings.append({
|
|
'level': heading['level'],
|
|
'text': heading['text'],
|
|
'link': full_link
|
|
})
|
|
context['local_md_headings'] = local_md_headings
|
|
|
|
def setup(app):
|
|
# Connect our handler to the "html-page-context" event.
|
|
app.connect('html-page-context', add_local_md_headings)
|
|
return {'version': '0.1', 'parallel_read_safe': True}
|