X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/215503e15ca9d6d1e8a053f7bfa359af1af102f3..f8442984a021793164661a54ec84ae9caaf9862b:/librarian/__init__.py?ds=inline diff --git a/librarian/__init__.py b/librarian/__init__.py old mode 100755 new mode 100644 index 34c493b..5b6981d --- a/librarian/__init__.py +++ b/librarian/__init__.py @@ -1,34 +1,18 @@ # -*- coding: utf-8 -*- # -# This file is part of Librarian. +# This file is part of Librarian, licensed under GNU Affero GPLv3 or later. +# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information. # -# Copyright © 2008,2009,2010 Fundacja Nowoczesna Polska -# -# For full list of contributors see AUTHORS file. -# -# This program is free software: you can redistribute it and/or modify -# it under the terms of the GNU Affero General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU Affero General Public License for more details. -# -# You should have received a copy of the GNU Affero General Public License -# along with this program. If not, see . -# -# exception classes +import os class ParseError(Exception): - - def __init__(self, cause, message=None): - self.cause = cause - try: - self.message = message or self.cause.message - except: - self.message = "No message." + def __str__(self): + """ Dirty workaround for Python Unicode handling problems. """ + return self.message.message + + def __unicode__(self): + """ Dirty workaround for Python Unicode handling problems. """ + return self.message.message class ValidationError(Exception): pass @@ -46,7 +30,7 @@ class XMLNamespace(object): return '{%s}%s' % (self.uri, tag) def __contains__(self, tag): - return tag.startswith('{'+str(self)+'}') + return tag.startswith('{' + str(self) + '}') def __repr__(self): return 'XMLNamespace(%r)' % self.uri @@ -66,14 +50,43 @@ RDFNS = XMLNamespace('http://www.w3.org/1999/02/22-rdf-syntax-ns#') 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") WLNS = EmptyNamespace() + +class DocProvider(object): + """ Base class for a repository of XML files. + Used for generating joined files, like EPUBs + """ + + def by_slug(self, slug): + raise NotImplemented + + def __getitem__(self, slug): + return self.by_slug(slug) + + def by_uri(self, uri): + return self.by_slug(uri.rsplit('/', 1)[1]) + + +class DirDocProvider(DocProvider): + """ Serve docs from a directory of files in form .xml """ + + def __init__(self, dir): + self.dir = dir + self.files = {} + + def by_slug(self, slug): + return open(os.path.join(self.dir, '%s.xml' % slug)) + + import lxml.etree as etree import dcparser DEFAULT_BOOKINFO = dcparser.BookInfo( - { RDFNS('about'): u'http://wiki.wolnepodreczniki.pl/Lektury:Template'},\ + { RDFNS('about'): u'http://wiki.wolnepodreczniki.pl/Lektury:Template'}, \ { DCNS('creator'): [u'Some, Author'], DCNS('title'): [u'Some Title'], DCNS('subject.period'): [u'Unknown'], @@ -93,18 +106,18 @@ DEFAULT_BOOKINFO = dcparser.BookInfo( [u"Domena publiczna - zm. [OPIS STANU PRAWNEGO TEKSTU]"] }) def xinclude_forURI(uri): - e = etree.Element( XINS("include") ) + 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(),\ + + dcstring = etree.tostring(bookinfo.to_etree(), \ method='xml', encoding=unicode, pretty_print=True) - return u'\n' + dcstring + u'\n\n' + ocrtext +\ + return u'\n' + dcstring + u'\n\n' + ocrtext + \ u'\n\n'; @@ -117,13 +130,13 @@ def serialize_raw(element): return b -from wl_light import serialize_nl - - SERIALIZERS = { 'raw': serialize_raw, - 'nl': serialize_nl, } def serialize_children(element, format='raw'): return SERIALIZERS[format](element) + +def get_resource(path): + return os.path.join(os.path.dirname(__file__), path) +