X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/07fdba2c7fe8e11b6867712d47bdd608e88c29fb..167d19bdfe76a77754d2e14a80ac0c25c725c379:/librarian/__init__.py diff --git a/librarian/__init__.py b/librarian/__init__.py index e69de29..0074ee9 100644 --- a/librarian/__init__.py +++ b/librarian/__init__.py @@ -0,0 +1,132 @@ +# -*- 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. +# +import os + +class ParseError(Exception): + pass + +class ValidationError(Exception): + pass + +class NoDublinCore(ValidationError): + pass + +class XMLNamespace(object): + '''A handy structure to repsent names in an XML namespace.''' + + def __init__(self, uri): + self.uri = uri + + def __call__(self, tag): + return '{%s}%s' % (self.uri, tag) + + def __contains__(self, tag): + return tag.startswith('{' + str(self) + '}') + + def __repr__(self): + return 'XMLNamespace(%r)' % self.uri + + def __str__(self): + return '%s' % self.uri + +class EmptyNamespace(XMLNamespace): + def __init__(self): + super(EmptyNamespace, self).__init__('') + + def __call__(self, tag): + return tag + +# some common namespaces we use +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'}, \ + { 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'\n' + dcstring + u'\n\n' + ocrtext + \ + u'\n\n'; + + +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)