restricted matching of wordnet tab files so the non-data ones are ignored; added…

restricted matching of wordnet tab files so the non-data ones are ignored; added "fra" to wn.langs() doctest

nltk/corpus/__init__.py

@@ -206,7 +206,7 @@ webtext = LazyCorpusLoader(
     'webtext', PlaintextCorpusReader, r'(?!README|\.).*\.txt', encoding='ISO-8859-2')
 wordnet = LazyCorpusLoader(
     'wordnet', WordNetCorpusReader,
-    LazyCorpusLoader('omw', CorpusReader, r'(?!\.).*\.tab'))
+    LazyCorpusLoader('omw', CorpusReader, r'.*/wn-data-.*\.tab', encoding='utf8'))
 wordnet_ic = LazyCorpusLoader(
     'wordnet_ic', WordNetICCorpusReader, '.*\.dat')
 words = LazyCorpusLoader(

nltk/test/wordnet.doctest

@@ -47,9 +47,9 @@ A synset is identified with a 3-part name of the form: word.pos.nn:
 The WordNet corpus reader gives access to the Open Multilingual
 WordNet, using ISO-639 language codes.
 
-    >>> wn.langs()
+    >>> sorted(wn.langs())
     [u'als', u'arb', u'cat', u'cmn', u'dan', u'eng', u'eus', u'fas',
-    u'fin', u'fre', u'glg', u'heb', u'ind', u'ita', u'jpn', u'nno',
+    u'fin', u'fra', u'fre', u'glg', u'heb', u'ind', u'ita', u'jpn', u'nno',
     u'nob', u'pol', u'por', u'spa', u'tha', u'zsm']
     >>> wn.synsets('犬', lang='jpn')
     [Synset('dog.n.01'), Synset('spy.n.01')]