src/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(
  64             """<?xml version="1.0" encoding="utf-8"?>
  65             <products xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">"""
  66             "</products>"
  67         )
  68         product = etree.fromstring("""<product>
  69                 <publisherProductId></publisherProductId>
  70                 <title></title>
  71                 <info></info>
  72                 <description></description>
  73                 <authors>
  74                     <author>
  75                         <names>Jan</names>
  76                         <lastName>Kowalski</lastName>
  77                     </author>
  78                 </authors>
  79                 <price>0.0</price>
  80                 <language>PL</language>
  81             </product>""")
  82
  83         try:
  84             for main_input in input_filenames:
  85                 if verbose:
  86                     print(main_input)
  87                 path, fname = os.path.realpath(main_input).rsplit('/', 1)
  88                 provider = DirDocProvider(path)
  89                 slug, ext = os.path.splitext(fname)
  90
  91                 outfile_dir = os.path.join(output_dir, slug)
  92                 makedirs(os.path.join(output_dir, slug))
  93
  94                 doc = WLDocument.from_file(main_input, provider=provider)
  95                 info = doc.book_info
  96
  97                 product_elem = deepcopy(product)
  98                 product_elem[0].text = cls.utf_trunc(slug, 100)
  99                 product_elem[1].text = cls.utf_trunc(info.title, 255)
 100                 product_elem[2].text = cls.utf_trunc(info.description, 255)
 101                 product_elem[3].text = cls.utf_trunc(info.source_name, 3000)
 102                 product_elem[4][0][0].text = cls.utf_trunc(
 103                     u' '.join(info.author.first_names), 100
 104                 )
 105                 product_elem[4][0][1].text = cls.utf_trunc(
 106                     info.author.last_name, 100
 107                 )
 108                 xml.append(product_elem)
 109
 110                 cover.VirtualoCover(info).save(
 111                     os.path.join(outfile_dir, slug+'.jpg')
 112                 )
 113                 outfile = os.path.join(outfile_dir, '1.epub')
 114                 outfile_sample = os.path.join(outfile_dir, '1.sample.epub')
 115                 doc.save_output_file(doc.as_epub(), output_path=outfile)
 116                 doc.save_output_file(doc.as_epub(doc, sample=25),
 117                                      output_path=outfile_sample)
 118                 outfile = os.path.join(outfile_dir, '1.mobi')
 119                 outfile_sample = os.path.join(outfile_dir, '1.sample.mobi')
 120                 doc.save_output_file(doc.as_mobi(cover=cover.VirtualoCover),
 121                                      output_path=outfile)
 122                 doc.save_output_file(
 123                     doc.as_mobi(doc, cover=cover.VirtualoCover, sample=25),
 124                     output_path=outfile_sample)
 125         except ParseError as e:
 126             print('%(file)s:%(name)s:%(message)s' % {
 127                 'file': main_input,
 128                 'name': e.__class__.__name__,
 129                 'message': e.message
 130             })
 131
 132         with open(os.path.join(
 133                     output_dir, 'import_products.xml'
 134                 ), 'w') as xml_file:
 135             xml_file.write(
 136                 etree.tostring(
 137                     xml, pretty_print=True, encoding='unicode'
 138                 ).encode('utf-8')
 139             )
 140         xml_file.close()