1 # -*- coding: utf-8 -*-
3 # This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
4 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
6 class ParseError(Exception):
9 class ValidationError(Exception):
12 class NoDublinCore(ValidationError):
15 class XMLNamespace(object):
16 '''A handy structure to repsent names in an XML namespace.'''
18 def __init__(self, uri):
21 def __call__(self, tag):
22 return '{%s}%s' % (self.uri, tag)
24 def __contains__(self, tag):
25 return tag.startswith('{' + str(self) + '}')
28 return 'XMLNamespace(%r)' % self.uri
31 return '%s' % self.uri
33 class EmptyNamespace(XMLNamespace):
35 super(EmptyNamespace, self).__init__('')
37 def __call__(self, tag):
40 # some common namespaces we use
41 RDFNS = XMLNamespace('http://www.w3.org/1999/02/22-rdf-syntax-ns#')
42 DCNS = XMLNamespace('http://purl.org/dc/elements/1.1/')
43 XINS = XMLNamespace("http://www.w3.org/2001/XInclude")
44 XHTMLNS = XMLNamespace("http://www.w3.org/1999/xhtml")
46 WLNS = EmptyNamespace()
48 import lxml.etree as etree
51 DEFAULT_BOOKINFO = dcparser.BookInfo(
52 { RDFNS('about'): u'http://wiki.wolnepodreczniki.pl/Lektury:Template'}, \
53 { DCNS('creator'): [u'Some, Author'],
54 DCNS('title'): [u'Some Title'],
55 DCNS('subject.period'): [u'Unknown'],
56 DCNS('subject.type'): [u'Unknown'],
57 DCNS('subject.genre'): [u'Unknown'],
58 DCNS('date'): ['1970-01-01'],
59 # DCNS('date'): [creation_date],
60 DCNS('publisher'): [u"Fundacja Nowoczesna Polska"],
62 [u"""Publikacja zrealizowana w ramach projektu
63 Wolne Lektury (http://wolnelektury.pl). Reprodukcja cyfrowa
64 wykonana przez Bibliotekę Narodową z egzemplarza
65 pochodzącego ze zbiorów BN."""],
66 DCNS('identifier.url'):
67 [u"http://wolnelektury.pl/katalog/lektura/template"],
69 [u"Domena publiczna - zm. [OPIS STANU PRAWNEGO TEKSTU]"] })
71 def xinclude_forURI(uri):
72 e = etree.Element(XINS("include"))
74 return etree.tostring(e, encoding=unicode)
76 def wrap_text(ocrtext, creation_date, bookinfo=DEFAULT_BOOKINFO):
77 """Wrap the text within the minimal XML structure with a DC template."""
78 bookinfo.created_at = creation_date
80 dcstring = etree.tostring(bookinfo.to_etree(), \
81 method='xml', encoding=unicode, pretty_print=True)
83 return u'<utwor>\n' + dcstring + u'\n<plain-text>\n' + ocrtext + \
84 u'\n</plain-text>\n</utwor>';
87 def serialize_raw(element):
88 b = u'' + (element.text or '')
90 for child in element.iterchildren():
91 e = etree.tostring(child, method='xml', encoding=unicode, pretty_print=True)
100 def serialize_children(element, format='raw'):
101 return SERIALIZERS[format](element)