# -*- coding: utf-8 -*-
#
# This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
-# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
+# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
#
-class ParseError(Exception):
-
- def __init__(self, cause, message=None):
- self.cause = cause
+import re
+import urllib
+from .utils import XMLNamespace
+
+
+class UnicodeException(Exception):
+ def __str__(self):
+ """ Dirty workaround for Python Unicode handling problems. """
+ return unicode(self).encode('utf-8')
+
+ def __unicode__(self):
+ """ Dirty workaround for Python Unicode handling problems. """
+ args = self.args[0] if len(self.args) == 1 else self.args
try:
- self.message = message or self.cause.message
- except:
- self.message = "No message."
+ message = unicode(args)
+ except UnicodeDecodeError:
+ message = unicode(args, encoding='utf-8', errors='ignore')
+ return message
-class ValidationError(Exception):
- pass
-class NoDublinCore(ValidationError):
+class ParseError(UnicodeException):
pass
-class XMLNamespace(object):
- '''A handy structure to repsent names in an XML namespace.'''
- def __init__(self, uri):
- self.uri = uri
+class ValidationError(UnicodeException):
+ pass
- def __call__(self, tag):
- return '{%s}%s' % (self.uri, tag)
- def __contains__(self, tag):
- return tag.startswith('{'+str(self)+'}')
+# was deleted, but still used???
+class NoDublinCore(ValidationError):
+ pass
+
- def __repr__(self):
- return 'XMLNamespace(%r)' % self.uri
+class BuildError(Exception):
+ pass
- def __str__(self):
- return '%s' % self.uri
class EmptyNamespace(XMLNamespace):
def __init__(self):
DCNS = XMLNamespace('http://purl.org/dc/elements/1.1/')
XINS = XMLNamespace("http://www.w3.org/2001/XInclude")
XHTMLNS = XMLNamespace("http://www.w3.org/1999/xhtml")
+NCXNS = XMLNamespace("http://www.daisy.org/z3986/2005/ncx/")
+OPFNS = XMLNamespace("http://www.idpf.org/2007/opf")
+
+SSTNS = XMLNamespace('http://nowoczesnapolska.org.pl/sst#')
+
+
+class WLURI(object):
+ """Represents a WL URI. Extracts slug from it."""
+ slug = None
+
+ example = 'http://wolnelektury.pl/katalog/lektura/template/'
+ _re_wl_uri = re.compile(r'http://(www\.)?wolnelektury.pl/katalog/lektura/(?P<slug>[-a-z0-9]+)/?$')
+
+ def __init__(self, uri):
+ uri = unicode(uri)
+ self.uri = uri
+ self.slug = uri.rstrip('/').rsplit('/', 1)[-1]
+
+ @classmethod
+ def strict(cls, uri):
+ match = cls._re_wl_uri.match(uri)
+ if not match:
+ raise ValidationError(u'Invalid URI (%s). Should match: %s' % (
+ uri, cls._re_wl_uri.pattern))
+ return cls(uri)
+
+ @classmethod
+ def from_slug(cls, slug):
+ """Contructs an URI from slug.
+
+ >>> WLURI.from_slug('a-slug').uri
+ u'http://wolnelektury.pl/katalog/lektura/a-slug/'
+
+ """
+ uri = 'http://wolnelektury.pl/katalog/lektura/%s/' % slug
+ return cls(uri)
+
+ def __unicode__(self):
+ return self.uri
+
+ def __str__(self):
+ return self.uri
+
+ def __eq__(self, other):
+ return self.slug == other.slug
+
-WLNS = EmptyNamespace()
-
-import lxml.etree as etree
-import dcparser
-
-DEFAULT_BOOKINFO = dcparser.BookInfo(
- { RDFNS('about'): u'http://wiki.wolnepodreczniki.pl/Lektury:Template'},\
- { DCNS('creator'): [u'Some, Author'],
- DCNS('title'): [u'Some Title'],
- DCNS('subject.period'): [u'Unknown'],
- DCNS('subject.type'): [u'Unknown'],
- DCNS('subject.genre'): [u'Unknown'],
- DCNS('date'): ['1970-01-01'],
- # DCNS('date'): [creation_date],
- DCNS('publisher'): [u"Fundacja Nowoczesna Polska"],
- DCNS('description'):
- [u"""Publikacja zrealizowana w ramach projektu
- Wolne Lektury (http://wolnelektury.pl). Reprodukcja cyfrowa
- wykonana przez Bibliotekę Narodową z egzemplarza
- pochodzącego ze zbiorów BN."""],
- DCNS('identifier.url'):
- [u"http://wolnelektury.pl/katalog/lektura/template"],
- DCNS('rights'):
- [u"Domena publiczna - zm. [OPIS STANU PRAWNEGO TEKSTU]"] })
-
-def xinclude_forURI(uri):
- e = etree.Element( XINS("include") )
- e.set("href", uri)
- return etree.tostring(e, encoding=unicode)
-
-def wrap_text(ocrtext, creation_date, bookinfo=DEFAULT_BOOKINFO):
- """Wrap the text within the minimal XML structure with a DC template."""
- bookinfo.created_at = creation_date
-
- dcstring = etree.tostring(bookinfo.to_etree(),\
- method='xml', encoding=unicode, pretty_print=True)
-
- return u'<utwor>\n' + dcstring + u'\n<plain-text>\n' + ocrtext +\
- u'\n</plain-text>\n</utwor>';
-
-
-def serialize_raw(element):
- b = u'' + (element.text or '')
-
- for child in element.iterchildren():
- e = etree.tostring(child, method='xml', encoding=unicode, pretty_print=True)
- b += e
-
- return b
-
-SERIALIZERS = {
- 'raw': serialize_raw,
-}
-
-def serialize_children(element, format='raw'):
- return SERIALIZERS[format](element)
+class URLOpener(urllib.FancyURLopener):
+ version = 'FNP Librarian (http://git.nowoczesnapolska.org.pl/?p=librarian.git)'
+urllib._urlopener = URLOpener()
fnp / librarian.git / blobdiff