# -*- coding: utf-8 -*-
#
-# This file is part of Librarian.
-#
-# Copyright © 2008,2009,2010 Fundacja Nowoczesna Polska <fundacja@nowoczesnapolska.org.pl>
-#
-# 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 <http://www.gnu.org/licenses/>.
+# This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
+# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
#
from librarian import ValidationError, NoDublinCore, ParseError
from librarian import RDFNS
self.edoc = edoc
root_elem = edoc.getroot()
-
+
dc_path = './/' + RDFNS('RDF')
-
+
if root_elem.tag != 'utwor':
raise ValidationError("Invalid root element. Found '%s', should be 'utwor'" % root_elem.tag)
if self.rdf_elem is None:
raise NoDublinCore('Document has no DublinCore - which is required.')
-
+
self.book_info = dcparser.BookInfo.from_element(self.rdf_elem)
else:
self.book_info = None
-
+
@classmethod
- def from_string(cls, xml, swap_endlines=False, parse_dublincore=True):
- return cls.from_file(StringIO(xml), swap_endlines, parse_dublincore=parse_dublincore)
+ def from_string(cls, xml, *args, **kwargs):
+ return cls.from_file(StringIO(xml), *args, **kwargs)
@classmethod
def from_file(cls, xmlfile, swap_endlines=False, parse_dublincore=True):
if not isinstance(data, unicode):
data = data.decode('utf-8')
- if swap_endlines:
- data = cls.LINE_SWAP_EXPR.sub(u'<br />\n', data)
-
+ data = data.replace(u'\ufeff', '')
+
try:
parser = etree.XMLParser(remove_blank_text=False)
- return cls(etree.parse(StringIO(data), parser), parse_dublincore=parse_dublincore)
+ tree = etree.parse(StringIO(data.encode('utf-8')), parser)
+
+ if swap_endlines:
+ cls.swap_endlines(tree)
+
+ return cls(tree, parse_dublincore=parse_dublincore)
except (ExpatError, XMLSyntaxError, XSLTApplyError), e:
- raise ParseError(e)
+ raise ParseError(e)
+
+ @classmethod
+ def swap_endlines(cls, tree):
+ # only swap inside stanzas
+ for elem in tree.iter('strofa'):
+ for child in list(elem):
+ if child.tail:
+ chunks = cls.LINE_SWAP_EXPR.split(child.tail)
+ ins_index = elem.index(child) + 1
+ while len(chunks) > 1:
+ ins = etree.Element('br')
+ ins.tail = chunks.pop()
+ elem.insert(ins_index, ins)
+ child.tail = chunks.pop(0)
+ if elem.text:
+ chunks = cls.LINE_SWAP_EXPR.split(elem.text)
+ while len(chunks) > 1:
+ ins = etree.Element('br')
+ ins.tail = chunks.pop()
+ elem.insert(0, ins)
+ elem.text = chunks.pop(0)
def chunk(self, path):
- # convert the path to XPath
+ # convert the path to XPath
expr = self.path_to_xpath(path)
elems = self.edoc.xpath(expr)
if len(elems) == 0:
return None
- else:
+ else:
return elems[0]
def path_to_xpath(self, path):
except Exception, e:
unmerged.append( repr( (key, xpath, e) ) )
- return unmerged
\ No newline at end of file
+ return unmerged
+
+ def clean_ed_note(self):
+ """ deletes forbidden tags from nota_red """
+
+ for node in self.edoc.xpath('|'.join('//nota_red//%s' % tag for tag in
+ ('pa', 'pe', 'pr', 'pt', 'begin', 'end', 'motyw'))):
+ tail = node.tail
+ node.clear()
+ node.tag = 'span'
+ node.tail = tail
fnp / librarian.git / blobdiff