X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/648dff98814d2ddeda2f06a8c0e2fb01547fac2a..04cb9d727764da3c0d3ba30783ba25dc828e3899:/lib/librarian/html.py diff --git a/lib/librarian/html.py b/lib/librarian/html.py index ae5efa644..ea71bbb1d 100644 --- a/lib/librarian/html.py +++ b/lib/librarian/html.py @@ -53,6 +53,8 @@ def transform(input_filename, output_filename): doc = etree.parse(doc_file, parser) result = doc.xslt(style) + add_anchors(result.getroot()) + add_table_of_contents(result.getroot()) result.write(output_filename, xml_declaration=True, pretty_print=True, encoding='utf-8') @@ -155,3 +157,60 @@ def extract_fragments(input_filename): return closed_fragments, open_fragments + +def add_anchor(element, number): + anchor = etree.Element('a', href='#f%d' % number) + anchor.set('class', 'anchor') + anchor.text = str(number) + if element.text: + anchor.tail = element.text + element.text = u'' + element.insert(0, anchor) + + anchor_target = etree.Element('a', name='f%d' % number) + element.insert(0, anchor_target) + + +def add_anchors(root): + counter = 1 + for element in root.iterdescendants(): + if element.getparent().tag in 'div' and 'note' in element.getparent().get('class', ''): + continue + if element.getparent().tag in 'blockquote': + continue + + if element.tag == 'p' and 'verse' in element.get('class', ''): + if counter == 1 or counter % 5 == 0: + add_anchor(element, counter) + counter += 1 + elif 'paragraph' in element.get('class', ''): + add_anchor(element, counter) + counter += 1 + + +def add_table_of_contents(root): + sections = [] + + for element in root.iterdescendants(): + if element.tag in ('h2', 'h3'): + if element.tag == 'h3' and len(sections) and sections[-1][0] == 'h2': + sections[-1][2].append((element.tag, ''.join(element.xpath('descendant-or-self::text()')), [])) + else: + sections.append((element.tag, ''.join(element.xpath('descendant-or-self::text()')), [])) + + toc = etree.Element('div') + toc.set('id', 'toc') + toc_header = etree.SubElement(toc, 'h2') + toc_header.text = u'Spis treści' + toc_list = etree.SubElement(toc, 'ol') + + for section, text, subsections in sections: + section_element = etree.SubElement(toc_list, 'li') + section_element.text = text + if len(subsections): + subsection_list = etree.SubElement(section_element, 'ol') + for subsection, text, _ in subsections: + subsection_element = etree.SubElement(subsection_list, 'li') + subsection_element.text = text + root.insert(0, toc) +