Function define_template

wikiextractor/extract.py:1812–1859

Adds a template defined in the :param page:. @see https://en.wikipedia.org/wiki/Help:Template#Noinclude.2C_includeonly.2C_and_onlyinclude

(title, page)

def define_template(title, page):
    """
    Adds a template defined in the :param page:.
    @see https://en.wikipedia.org/wiki/Help:Template#Noinclude.2C_includeonly.2C_and_onlyinclude
    """
    global templates
    global redirects

    # title = normalizeTitle(title)

    # check for redirects
    m = re.match('#REDIRECT.*?\[\[([^\]]*)]]', page[0], re.IGNORECASE)
    if m:
        redirects[title] = m.group(1)  # normalizeTitle(m.group(1))
        return

    text = unescape(''.join(page))

    # We're storing template text for future inclusion, therefore,
    # remove all <noinclude> text and keep all <includeonly> text
    # (but eliminate <includeonly> tags per se).
    # However, if <onlyinclude> ... </onlyinclude> parts are present,
    # then only keep them and discard the rest of the template body.
    # This is because using <onlyinclude> on a text fragment is
    # equivalent to enclosing it in <includeonly> tags **AND**
    # enclosing all the rest of the template body in <noinclude> tags.

    # remove comments
    text = comment.sub('', text)

    # eliminate <noinclude> fragments
    text = reNoinclude.sub('', text)
    # eliminate unterminated <noinclude> elements
    text = re.sub(r'<noinclude\s*>.*$', '', text, flags=re.DOTALL)
    text = re.sub(r'<noinclude/>', '', text)

    onlyincludeAccumulator = ''
    for m in re.finditer('<onlyinclude>(.*?)</onlyinclude>', text, re.DOTALL):
        onlyincludeAccumulator += m.group(1)
    if onlyincludeAccumulator:
        text = onlyincludeAccumulator
    else:
        text = reIncludeonly.sub('', text)

    if text:
        if title in templates and templates[title] != text:
            logging.warn('Redefining: %s', title)
        templates[title] = text