Daniel@0: # Part of DML (Digital Music Laboratory)
Daniel@0: # Copyright 2014-2015 AUTHOR_AFFILIATION
Daniel@0:  
Daniel@0: # This program is free software; you can redistribute it and/or
Daniel@0: # modify it under the terms of the GNU General Public License
Daniel@0: # as published by the Free Software Foundation; either version 2
Daniel@0: # of the License, or (at your option) any later version.
Daniel@0: # 
Daniel@0: # This program is distributed in the hope that it will be useful,
Daniel@0: # but WITHOUT ANY WARRANTY; without even the implied warranty of
Daniel@0: # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
Daniel@0: # GNU General Public License for more details.
Daniel@0: # 
Daniel@0: # You should have received a copy of the GNU General Public
Daniel@0: # License along with this library; if not, write to the Free Software
Daniel@0: # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
Daniel@0: 
Daniel@0: from rdflib import Graph
Daniel@0: from rdflib.plugins.parsers.notation3 import BadSyntax
Daniel@0: import warnings
Daniel@0: import codecs
Daniel@0: import platform
Daniel@0: 
Daniel@0: # Load and parse an n3 file
Daniel@0: def get_rdf_graph_from_n3(n3_file_uri):
Daniel@0: 
Daniel@0:     graph = Graph()
Daniel@0: 
Daniel@0:     try:
Daniel@0:         graph.parse(n3_file_uri, format="n3")
Daniel@0:     except UnicodeDecodeError:
Daniel@0:         
Daniel@0:         n3_file_str = uri2path(n3_file_uri)
Daniel@0:         n3_file_iso = codecs.open(n3_file_str, 'r', "iso-8859-1")
Daniel@0: 
Daniel@0:         # check if n3 is valid and parse
Daniel@0:         # repair if necessary
Daniel@0:         graph = parse_potentially_corrupt_n3(n3_file_iso.read())
Daniel@0: 
Daniel@0:     except (AssertionError, BadSyntax):
Daniel@0: 
Daniel@0:         n3_file_str = uri2path(n3_file_uri)
Daniel@0:         n3_file = open(n3_file_str, 'r')
Daniel@0:         graph = parse_potentially_corrupt_n3(n3_file.read())
Daniel@0: 
Daniel@0:     return graph
Daniel@0: 
Daniel@0: # can parse truncated n3
Daniel@0: def parse_potentially_corrupt_n3(content):
Daniel@0:     feature_graph = Graph()
Daniel@0:     # test if file is complete. 
Daniel@0:     # if not, delete the last corrupted entry
Daniel@0:     if not '.' in content[-4:]:
Daniel@0:         warnings.warn("Incomplete rdf file, ignoring last entry")
Daniel@0:         # we find the last correct event
Daniel@0:         lastentry = content.rfind(':event')
Daniel@0:         feature_graph.parse(data=content[:lastentry], format="n3")
Daniel@0:     else:
Daniel@0:         feature_graph.parse(data=content, format="n3")
Daniel@0: 
Daniel@0:     return feature_graph
Daniel@0: 
Daniel@0: # returns filepath from url
Daniel@0: def uri2path(n3_file_uri):
Daniel@0:     
Daniel@0:     n3_file_uri_str = n3_file_uri.__str__()
Daniel@0:     
Daniel@0:     # Assume that n3_file_uri_str starts with 'file://' - we need to remove that
Daniel@0:     if 'Win' in platform.system():
Daniel@0:         FILE_URI_START_INDEX = 8
Daniel@0:     else:
Daniel@0:         FILE_URI_START_INDEX = 7
Daniel@0:             
Daniel@0:     n3_file_str = n3_file_uri_str[FILE_URI_START_INDEX:len(n3_file_uri_str)]
Daniel@0:     return n3_file_str