def generate_id()

in plugins/asfgenid.py [0:0]

• 52 lines of code
• 14 McCabe index (conditional complexity)

def generate_id(content):
    if isinstance(content, pelican.contents.Static):
        return

    # get plugin settings
    asf_genid = content.settings['ASF_GENID']
    # asf_headings setting may be overridden
    asf_headings = content.metadata.get('asf_headings', str(asf_genid['headings']))

    # show active plugins
    if asf_genid['debug']:
        print('asfgenid:\nshow plugins in case one is processing before this one')
        for name in content.settings['PLUGINS']:
            print(f'plugin: {name}')

    # track the id tags
    ids = set()
    # track permalinks
    permalinks = set()

    # step 1 - fixup html that cmark marks unsafe - move to later?
    if asf_genid['unsafe_tags']:
        fixup_content(content)

    # step 2 - prepare for genid processes
    # parse html content into BeautifulSoup4
    soup = BeautifulSoup(content._content, 'html.parser') # pylint: disable=protected-access
    # page title
    title = content.metadata.get('title', 'Title')
    # assure relative source path is in the metadata
    content.metadata['relative_source_path'] = rel_source_path = content.relative_source_path
    # create breadcrumb html
    content.metadata['breadcrumbs'] = breadcrumbs = make_breadcrumbs(rel_source_path, title)
    # display output path and title
    print(f'{content.relative_source_path} - {title}')
    # if debug display breadcrumb html
    if asf_genid['debug']:
        print(f'    {breadcrumbs}')
    # enhance metadata if done by asfreader
    add_data(content)

    # step 3 - metadata expansion
    if asf_genid['metadata']:
        if asf_genid['debug']:
            print(f'metadata expansion: {content.relative_source_path}')
        for tag in soup.findAll(string=METADATA_RE):
            expand_metadata(tag, content.metadata, asf_genid['debug'])

    # step 4 - find all id attributes already present
    for tag in soup.findAll(id=True):
        unique(tag['id'], ids)
        # don't change existing ids

    # step 5 - find all {#id} and {.class} text and assign attributes
    if asf_genid['elements']:
        if asf_genid['debug']:
            print(f'elementid: {content.relative_source_path}')
        for tag in soup.findAll(string=ELEMENTID_RE):
            elementid_transform(ids, soup, tag, asf_genid['permalinks'], permalinks, asf_genid['debug'])

    # step 6 - find all headings w/o ids already present or assigned with {#id} text
    if asf_headings == 'True':
        if asf_genid['debug']:
            print(f'headings: {content.relative_source_path}')
        # Find heading tags
        HEADING_RE = re.compile(asf_genid['headings_re'])
        for tag in soup.findAll(HEADING_RE, id=False):
            headingid_transform(ids, soup, tag, asf_genid['permalinks'], permalinks)

    # step 7 - find all tables without class
    if asf_genid['tables']:
        if asf_genid['debug']:
            print(f'tables: {content.relative_source_path}')
        for tag in soup.findAll(TABLE_RE, _class=False):
            tag['class'] = 'table'

    # step 8 - find TOC tag and generate Table of Contents
    if asf_genid['toc']:
        tags = soup('p', text='[TOC]')
        if tags:
            generate_toc(content, tags, title, asf_genid['toc_headers'], asf_genid['debug'])

    # step 9 - reset the html content
    content._content = soup.decode(formatter='html')  # pylint: disable=protected-access

    # step 10 - output all of the permalinks created
    if asf_genid['debug']:
        for tag in permalinks:
            print(f'    #{tag}')