some cleaning
[librarian.git] / scripts / book2partner
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3 #
4 # This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
5 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.  
6 #
7 import os.path
8 import optparse
9 from copy import deepcopy
10 from lxml import etree
11
12 from librarian import epub, DirDocProvider, ParseError, cover
13 from librarian.dcparser import BookInfo
14
15
16 def utf_trunc(text, limit):
17     """ truncates text to at most `limit' bytes in utf-8 """
18     if text is None:
19         return text
20     orig_text = text
21     if len(text.encode('utf-8')) > limit:
22         newlimit = limit - 3
23         while len(text.encode('utf-8')) > newlimit:
24             text = text[:(newlimit - len(text.encode('utf-8'))) / 4]
25         text += '...'
26     return text
27
28
29 def virtualo(filenames, output_dir, verbose):
30     xml = etree.fromstring("""<?xml version="1.0" encoding="utf-8"?>
31         <products xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"></products>""")
32     product = etree.fromstring("""<product>
33             <publisherProductId></publisherProductId>
34             <title></title>
35             <info></info>
36             <description></description>
37             <authors>
38                 <author>
39                     <names>Jan</names>
40                     <lastName>Kowalski</lastName>
41                 </author>
42             </authors>
43             <price>0.0</price>
44             <language>PL</language>
45         </product>""")
46
47     try:
48         for main_input in input_filenames:
49             if options.verbose:
50                 print main_input
51             path, fname = os.path.realpath(main_input).rsplit('/', 1)
52             provider = DirDocProvider(path)
53             slug, ext = os.path.splitext(fname)
54
55             outfile_dir = os.path.join(output_dir, slug)
56             os.makedirs(os.path.join(output_dir, slug))
57
58             info = BookInfo.from_file(main_input)
59
60             product_elem = deepcopy(product)
61             product_elem[0].text = utf_trunc(slug, 100)
62             product_elem[1].text = utf_trunc(info.title, 255)
63             product_elem[2].text = utf_trunc(info.description, 255)
64             product_elem[3].text = utf_trunc(info.source_name, 3000)
65             product_elem[4][0][0].text = utf_trunc(u' '.join(info.author.first_names), 100)
66             product_elem[4][0][1].text = utf_trunc(info.author.last_name, 100)
67             xml.append(product_elem)
68
69             cover.virtualo_cover(
70                 u' '.join(info.author.first_names + (info.author.last_name,)), 
71                 info.title
72                 ).save(os.path.join(outfile_dir, slug+'.jpg'))
73             outfile = os.path.join(outfile_dir, '1.epub')
74             outfile_sample = os.path.join(outfile_dir, '1.sample.epub')
75             epub.transform(provider, file_path=main_input, output_file=outfile)
76             epub.transform(provider, file_path=main_input, output_file=outfile_sample, sample=25)
77     except ParseError, e:
78         print '%(file)s:%(name)s:%(message)s' % {
79             'file': main_input,
80             'name': e.__class__.__name__,
81             'message': e.message
82         }
83
84     xml_file = open(os.path.join(output_dir, 'import_products.xml'), 'w')
85     xml_file.write(etree.tostring(xml, pretty_print=True, encoding=unicode).encode('utf-8'))
86     xml_file.close()
87
88
89
90
91 if __name__ == '__main__':
92     # Parse commandline arguments
93     usage = """Usage: %prog [options] SOURCE [SOURCE...]
94     Prepare SOURCE files for a partner."""
95
96     parser = optparse.OptionParser(usage=usage)
97
98     parser.add_option('-v', '--verbose', action='store_true', dest='verbose', default=False,
99         help='print status messages to stdout')
100     parser.add_option('-O', '--output-dir', dest='output_dir', metavar='DIR', default='',
101                       help='specifies the directory for output')
102     parser.add_option('--virtualo', action='store_true', dest='virtualo', default=False,
103                       help='prepare files for Virtualo API')
104
105     options, input_filenames = parser.parse_args()
106
107     if len(input_filenames) < 1:
108         parser.print_help()
109         exit(1)
110
111     if options.virtualo:
112         virtualo(input_filenames, options.output_dir, options.verbose)