librarian/partners.py

   1 # -*- coding: utf-8 -*-
   2 #
   3 # This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
   4 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
   5 #
   6
   7 """
   8 Classes for packaging ebooks for some old partners.
   9 These should be removed from librarian to separate package,
  10 along with custom cover images etc.
  11
  12 New partners shouldn't be added here, but in the partners repository.
  13 """
  14 from __future__ import print_function, unicode_literals
  15
  16 from librarian import packagers, cover
  17 from .util import makedirs
  18
  19
  20 class GandalfEpub(packagers.EpubPackager):
  21     cover = cover.GandalfCover
  22
  23
  24 class GandalfPdf(packagers.PdfPackager):
  25     cover = cover.GandalfCover
  26
  27
  28 class BookotekaEpub(packagers.EpubPackager):
  29     cover = cover.BookotekaCover
  30
  31
  32 class PrestigioEpub(packagers.EpubPackager):
  33     cover = cover.PrestigioCover
  34     flags = ('less-advertising',)
  35
  36
  37 class PrestigioPdf(packagers.PdfPackager):
  38     cover = cover.PrestigioCover
  39     flags = ('less-advertising',)
  40
  41
  42 class Virtualo(packagers.Packager):
  43     @staticmethod
  44     def utf_trunc(text, limit):
  45         """ truncates text to at most `limit' bytes in utf-8 """
  46         if text is None:
  47             return text
  48         if len(text.encode('utf-8')) > limit:
  49             newlimit = limit - 3
  50             while len(text.encode('utf-8')) > newlimit:
  51                 text = text[:(newlimit - len(text.encode('utf-8'))) / 4]
  52             text += '...'
  53         return text
  54
  55     @classmethod
  56     def prepare(cls, input_filenames, output_dir='', verbose=False):
  57         from lxml import etree
  58         from librarian import DirDocProvider, ParseError
  59         from librarian.parser import WLDocument
  60         from copy import deepcopy
  61         import os.path
  62
  63         xml = etree.fromstring("""<?xml version="1.0" encoding="utf-8"?>
  64             <products xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"></products>""")
  65         product = etree.fromstring("""<product>
  66                 <publisherProductId></publisherProductId>
  67                 <title></title>
  68                 <info></info>
  69                 <description></description>
  70                 <authors>
  71                     <author>
  72                         <names>Jan</names>
  73                         <lastName>Kowalski</lastName>
  74                     </author>
  75                 </authors>
  76                 <price>0.0</price>
  77                 <language>PL</language>
  78             </product>""")
  79
  80         try:
  81             for main_input in input_filenames:
  82                 if verbose:
  83                     print(main_input)
  84                 path, fname = os.path.realpath(main_input).rsplit('/', 1)
  85                 provider = DirDocProvider(path)
  86                 slug, ext = os.path.splitext(fname)
  87
  88                 outfile_dir = os.path.join(output_dir, slug)
  89                 makedirs(os.path.join(output_dir, slug))
  90
  91                 doc = WLDocument.from_file(main_input, provider=provider)
  92                 info = doc.book_info
  93
  94                 product_elem = deepcopy(product)
  95                 product_elem[0].text = cls.utf_trunc(slug, 100)
  96                 product_elem[1].text = cls.utf_trunc(info.title, 255)
  97                 product_elem[2].text = cls.utf_trunc(info.description, 255)
  98                 product_elem[3].text = cls.utf_trunc(info.source_name, 3000)
  99                 product_elem[4][0][0].text = cls.utf_trunc(u' '.join(info.author.first_names), 100)
 100                 product_elem[4][0][1].text = cls.utf_trunc(info.author.last_name, 100)
 101                 xml.append(product_elem)
 102
 103                 cover.VirtualoCover(info).save(os.path.join(outfile_dir, slug+'.jpg'))
 104                 outfile = os.path.join(outfile_dir, '1.epub')
 105                 outfile_sample = os.path.join(outfile_dir, '1.sample.epub')
 106                 doc.save_output_file(doc.as_epub(), output_path=outfile)
 107                 doc.save_output_file(doc.as_epub(doc, sample=25), output_path=outfile_sample)
 108                 outfile = os.path.join(outfile_dir, '1.mobi')
 109                 outfile_sample = os.path.join(outfile_dir, '1.sample.mobi')
 110                 doc.save_output_file(doc.as_mobi(cover=cover.VirtualoCover), output_path=outfile)
 111                 doc.save_output_file(
 112                     doc.as_mobi(doc, cover=cover.VirtualoCover, sample=25),
 113                     output_path=outfile_sample)
 114         except ParseError as e:
 115             print('%(file)s:%(name)s:%(message)s' % {
 116                 'file': main_input,
 117                 'name': e.__class__.__name__,
 118                 'message': e.message
 119             })
 120
 121         xml_file = open(os.path.join(output_dir, 'import_products.xml'), 'w')
 122         xml_file.write(etree.tostring(xml, pretty_print=True, encoding='unicode').encode('utf-8'))
 123         xml_file.close()