src/sources/document.py

   1 import os
   2 from librarian import RDFNS, DCNS
   3 from lxml import etree
   4 from datetime import date
   5 from . import ocr
   6 from django.conf import settings
   7
   8
   9 def build_document_texts(book):
  10     texts = []
  11     for builder in text_builders:
  12         root = etree.Element('utwor')
  13         # add meta
  14         add_rdf(root, book)
  15
  16         # add master
  17         master = etree.SubElement(root, 'powiesc')
  18
  19         for book_source in book.booksource_set.all():
  20             for page in book_source.get_ocr_files():
  21                 builder(master, page)
  22
  23         texts.append(etree.tostring(root, encoding='unicode', pretty_print=True))
  24     return texts
  25
  26
  27 text_builders = [
  28     ocr.add_page_to_master,
  29     ocr.add_page_to_master_as_stanzas,
  30     ocr.add_page_to_master_as_p,
  31 ]
  32
  33
  34 def add_rdf(root, book):
  35     # TODO: to librarian
  36     rdf = etree.SubElement(root, RDFNS('RDF'))
  37     desc = etree.SubElement(rdf, RDFNS('Description'), **{})
  38
  39     # author
  40     for author in book.authors.all():
  41         etree.SubElement(desc, DCNS('creator')).text = f'{author.last_name_pl}, {author.first_name_pl}'
  42     # translator
  43     for tr in book.translators.all():
  44         etree.SubElement(desc, DCNS('contributor.translator')).text = f'{tr.last_name_pl}, {tr.first_name_pl}'
  45     # title
  46     etree.SubElement(desc, DCNS('title')).text = book.title
  47     # created_at
  48     etree.SubElement(desc, DCNS('date')).text = date.today().isoformat()
  49     # date.pd
  50     etree.SubElement(desc, DCNS('date.pd')).text = str(book.pd_year)
  51     #publisher
  52     etree.SubElement(desc, DCNS('publisher')). text = 'Fundacja Wolne Lektury'
  53     #language
  54     etree.SubElement(desc, DCNS('language')).text = book.language # 3to2?
  55     #description
  56     #source_name
  57     # TODO: allow multiple source meta entries.
  58     sources = []
  59     for book_source in book.booksource_set.all():
  60         sources.append(book_source.source.name)
  61     etree.SubElement(desc, DCNS('source')).text = ';\n '.join(sources)
  62     #url
  63     etree.SubElement(desc, DCNS('identifier.url')).text = f'https://wolnelektury.pl/katalog/lektura/{book.slug}/'
  64     #license?
  65     #license_description?
  66     etree.SubElement(desc, DCNS('rights')).text = ''
  67     #epochs
  68     for tag in book.epochs.all():
  69         etree.SubElement(desc, DCNS('subject.period')).text = tag.name
  70     #kinds
  71     for tag in book.kinds.all():
  72         etree.SubElement(desc, DCNS('subject.type')).text = tag.name
  73     #genres
  74     for tag in book.genres.all():
  75         etree.SubElement(desc, DCNS('subject.genre')).text = tag.name
  76
  77