deleted stale nltk_data files

nltk_data/__init__.py

-# Natural Language Toolkit (NLTK) Package for building models 
-#
-# Copyright (C) 2001-2011 NLTK Project
-# Authors: Steven Bird <sb@csse.unimelb.edu.au>
-#          Edward Loper <edloper@gradient.cis.upenn.edu>
-# URL: <http://www.nltk.org/>
-# For license information, see LICENSE.TXT
-
-"""
-A package for building the models distributed with NLTK.
-"""
-

nltk_data/samples/polish-lat2.txt

-Pruska Biblioteka Państwowa. Jej dawne zbiory znane pod nazwą
-"Berlinka" to skarb kultury i sztuki niemieckiej. Przewiezione przez
-Niemców pod koniec II wojny światowej na Dolny Śląsk, zostały
-odnalezione po 1945 r. na terytorium Polski. Trafiły do Biblioteki
-Jagiellońskiej w Krakowie, obejmują ponad 500 tys. zabytkowych
-archiwaliów, m.in. manuskrypty Goethego, Mozarta, Beethovena, Bacha.

nltk_data/samples/sinorama-gb.xml

-<?xml version="1.0" encoding="gb2312" ?>
-
-<sent>
-è˹
-
-In some cases, cats were valued above humans.
-</sent>

nltk_data/samples/sinorama-utf8.xml

-<?xml version="1.0" encoding="utf-8" ?>
-<doc>
-<sent>
-甚至猫以人贵
-
-In some cases, cats were valued above humans.
-</sent>
-</doc>

nltk_data/tagsets.py

-# Natural Language Toolkit (NLTK) Package for Tagset Tables
-#
-# Copyright (C) 2001-2011 NLTK Project
-# Authors: Steven Bird <sb@csse.unimelb.edu.au>
-# URL: <http://www.nltk.org/>
-# For license information, see LICENSE.TXT
-
-"""
-A package for building the Tagset Tables distributed with NLTK
-"""
-
-import re
-import pickle
-
-from tagset_data import *
-
-RECORD_SEP = "   *"
-FIELD_SEP = " - "
-
-TAGSETS = {'upenn_tagset': upenn_tagset,
-           'brown_tagset': brown_tagset,
-           'claws5_tagset': claws5_tagset}
-
-def load_tagset(s):
-    tagset = {}
-    entries = s.split(RECORD_SEP)
-    for entry in entries:
-        if FIELD_SEP in entry:
-            entry = re.sub(r'(?m)\s+', ' ', entry)
-            _, tag, defn, examples = entry.split(FIELD_SEP, 3)
-            if tag not in tagset:
-                tagset[tag] = (defn, examples)
-            else:
-                raise ValueError, "Duplicate tag: %s" % tag
-    return tagset
-
-def build_tagsets():
-    for tagset in TAGSETS:
-        print "Building", tagset 
-        output = open(tagset + ".pickle", "w")
-        tagset_dict = load_tagset(TAGSETS[tagset])
-        pickle.dump(tagset_dict, output)
-        output.close()
-    
-if __name__ == '__main__':
-    build_tagsets()