Package nltk_lite :: Package corpora
[hide private]
[frames] | no frames]

Source Code for Package nltk_lite.corpora

 1  # Natural Language Toolkit: Corpus Readers 
 2  # 
 3  # Copyright (C) 2001-2007 University of Pennsylvania 
 4  # Author: Steven Bird <sb@ldc.upenn.edu> 
 5  #         Edward Loper <edloper@gradient.cis.upenn.edu> 
 6  # URL: <http://nltk.sf.net> 
 7  # For license information, see LICENSE.TXT 
 8   
 9  import os, sys 
10   
11 -def set_basedir(path):
12 """ 13 Set the path to the directory where NLTK looks for corpora. 14 15 @type path: C{string} 16 @param path: The path to the directory where NLTK should look for corpora. 17 """ 18 global _BASEDIR 19 _BASEDIR = path
20
21 -def get_basedir():
22 """ 23 @return: The path of the directory where NLTK looks for corpora. 24 @rtype: C{string} 25 """ 26 return _BASEDIR
27 28 # Find a default base directory. 29 if os.environ.has_key('NLTK_LITE_CORPORA'): 30 set_basedir(os.environ['NLTK_LITE_CORPORA']) 31 elif sys.platform.startswith('win'): 32 if os.path.isdir('C:\\corpora'): 33 set_basedir('C:\\corpora') 34 elif os.path.isdir(os.path.join(sys.prefix, 'nltk_lite', 'corpora')): 35 set_basedir(os.path.join(sys.prefix, 'nltk_lite', 'corpora')) 36 elif os.path.isdir(os.path.join(sys.prefix, 'lib', 'nltk_lite', 'corpora')): 37 set_basedir(os.path.join(sys.prefix, 'lib', 'nltk_lite', 'corpora')) 38 elif os.path.isdir(os.path.join(sys.prefix, 'nltk_lite')): 39 set_basedir(os.path.join(sys.prefix, 'nltk_lite')) 40 elif os.path.isdir(os.path.join(sys.prefix, 'lib', 'nltk_lite')): 41 set_basedir(os.path.join(sys.prefix, 'lib', 'nltk_lite')) 42 else: 43 set_basedir('C:\\corpora') 44 elif os.path.isdir('/usr/share/nltk_lite/corpora'): 45 set_basedir('/usr/share/nltk_lite/corpora') 46 elif os.path.isdir('/usr/local/share/nltk_lite/corpora'): 47 set_basedir('/usr/local/share/nltk_lite/corpora') 48 elif os.path.isdir('/usr/share/nltk_lite'): 49 set_basedir('/usr/share/nltk_lite') 50 elif os.path.isdir('/usr/local/share/nltk_lite'): 51 set_basedir('/usr/local/share/nltk_lite') 52 else: 53 set_basedir('/usr/share/nltk_lite/corpora') 54 55 # Access to individual corpus items 56 57 # extract the nth item from iterator i 58 from itertools import islice
59 -def extract(n, i):
60 return list(islice(i, n, n+1))[0]
61