Source Code for Module nltk.corpus.reader.wordlist

 1  # Natural Language Toolkit: Word List Corpus Reader 
 2  # 
 3  # Copyright (C) 2001-2008 NLTK Project 
 4  # Author: Steven Bird <[email protected]> 
 5  #         Edward Loper <[email protected]> 
 6  # URL: <http://nltk.org> 
 7  # For license information, see LICENSE.TXT 
 8   
 9  from nltk.corpus.reader.util import * 
10  from nltk.corpus.reader.api import * 
11  from nltk.internals import deprecated 
12  from nltk.tokenize import line_tokenize 
13   
14 -class WordListCorpusReader(CorpusReader): 
15      """ 
16      List of words, one per line.  Blank lines are ignored. 
17      """ 
18 -    def words(self, files=None): 
19          return line_tokenize(self.raw(files)) 
20   
21 -    def raw(self, files=None): 
22          if files is None: files = self._files 
23          elif isinstance(files, basestring): files = [files] 
24          return concat([self.open(f).read() for f in files]) 
25   
26      #{ Deprecated since 0.8 
27      @deprecated("Use .raw() or .words() instead.") 
28 -    def read(self, items=None, format='listed'): 
29          if format == 'raw': return self.raw(items) 
30          if format == 'listed': return self.words(items) 
31          raise ValueError('bad format %r' % format) 
32      @deprecated("Use .words() instead.") 
33 -    def listed(self, items=None): 
34          return self.words(items) 
35      #} 
36