X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/f8e5f031c04122d65d1066077be3920ae95518ae..993a8cd64b2913a6d1c42f094c37c6c2d66d2332:/librarian/__init__.py?ds=sidebyside diff --git a/librarian/__init__.py b/librarian/__init__.py index 5997a4e..dbdad5b 100644 --- a/librarian/__init__.py +++ b/librarian/__init__.py @@ -1,14 +1,10 @@ # -*- coding: utf-8 -*- -# exception classes - +# +# This file is part of Librarian, licensed under GNU Affero GPLv3 or later. +# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information. +# 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." + pass class ValidationError(Exception): pass @@ -26,7 +22,7 @@ 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 @@ -53,7 +49,7 @@ 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'], @@ -73,16 +69,33 @@ 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 +\ - u'\n\n'; \ No newline at end of file + 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)