Merge pull request #1190 from hagberg/pajek-utf8

Pajek utf8

2 files changed, 32 insertions, 4 deletions

diff --git a/networkx/readwrite/pajek.py b/networkx/readwrite/pajek.py
index f284c5e5..d8fdc055 100644
--- a/networkx/readwrite/pajek.py
+++ b/networkx/readwrite/pajek.py
@@ -12,7 +12,7 @@ Format
 See http://vlado.fmf.uni-lj.si/pub/networks/pajek/doc/draweps.htm
 for format information.
 """
-#    Copyright (C) 2008-2011 by
+#    Copyright (C) 2008-2014 by
 #    Aric Hagberg <hagberg@lanl.gov>
 #    Dan Schult <dschult@colgate.edu>
 #    Pieter Swart <swart@lanl.gov>
@@ -20,7 +20,7 @@ for format information.
 #    BSD license.
 import networkx as nx
 from networkx.utils import is_string_like, open_file, make_str
-__author__ = """Aric Hagberg (hagberg@lanl.gov)"""
+__author__ = """Aric Hagberg <aric.hagberg@gmail.com>"""
 __all__ = ['read_pajek', 'parse_pajek', 'generate_pajek', 'write_pajek']
 
 def generate_pajek(G):
@@ -172,7 +172,12 @@ def parse_pajek(lines):
             nodelabels={}
             l,nnodes=l.split()
             for i in range(int(nnodes)):
-                splitline=shlex.split(str(next(lines)))
+                l = next(lines)
+                try:
+                    splitline=[x.decode('utf-8') for x in
+                           shlex.split(make_str(l).encode('utf-8'))]
+                except AttributeError:
+                    splitline = shlex.split(str(l))
                 id,label=splitline[0:2]
                 G.add_node(label)
                 nodelabels[id]=label
@@ -194,7 +199,12 @@ def parse_pajek(lines):
                # switch to directed with multiple arcs for each existing edge
                 G=G.to_directed()
             for l in lines:
-                splitline=shlex.split(str(l))
+                try:
+                    splitline = [x.decode('utf-8') for x in
+                                 shlex.split(make_str(l).encode('utf-8'))]
+                except AttributeError:
+                    splitline = shlex.split(str(l))
+
                 if len(splitline)<2:
                     continue
                 ui,vi=splitline[0:2]
diff --git a/networkx/readwrite/tests/test_pajek.py b/networkx/readwrite/tests/test_pajek.py
index 9e7732f0..70b2d0be 100644
--- a/networkx/readwrite/tests/test_pajek.py
+++ b/networkx/readwrite/tests/test_pajek.py
@@ -57,3 +57,21 @@ class TestPajek(object):
         other_lines = self.data.split('\n')[1:]
         data = line + '\n'.join(other_lines)
         G = parse_pajek(data)
+
+    def test_unicode(self):
+        import io
+        G = nx.Graph()
+        try: # Python 3.x
+            name1 = chr(2344) + chr(123) + chr(6543)
+            name2 = chr(5543) + chr(1543) + chr(324)
+        except ValueError: # Python 2.6+
+            name1 = unichr(2344) + unichr(123) + unichr(6543)
+            name2 = unichr(5543) + unichr(1543) + unichr(324)
+        G.add_edge(name1, 'Radiohead', attr_dict={'foo': name2})
+        fh = io.BytesIO()
+        nx.write_pajek(G,fh)
+        fh.seek(0)
+        H=nx.read_pajek(fh)
+        assert_nodes_equal(G.nodes(), H.nodes())
+        assert_edges_equal(G.edges(), H.edges())
+        assert_equal(G.graph,H.graph)