Source Code for Module nltk.corpus.reader.wordlist

 1  # Natural Language Toolkit: Word List Corpus Reader 
 2  # 
 3  # Copyright (C) 2001-2011 NLTK Project 
 4  # Author: Steven Bird <sb@ldc.upenn.edu> 
 5  #         Edward Loper <edloper@gradient.cis.upenn.edu> 
 6  # URL: <http://www.nltk.org/> 
 7  # For license information, see LICENSE.TXT 
 8   
 9  from nltk.tokenize import line_tokenize 
10   
11  from util import * 
12  from api import * 
13   
14 -class WordListCorpusReader(CorpusReader): 
15      """ 
16      List of words, one per line.  Blank lines are ignored. 
17      """ 
18 -    def words(self, fileids=None): 
19          return line_tokenize(self.raw(fileids)) 
20   
21 -    def raw(self, fileids=None): 
22          if fileids is None: fileids = self._fileids 
23          elif isinstance(fileids, basestring): fileids = [fileids] 
24          return concat([self.open(f).read() for f in fileids]) 
25   
26   
27 -class SwadeshCorpusReader(WordListCorpusReader): 
28 -    def entries(self, fileids=None): 
29          """ 
30          @return: a tuple of words for the specified fileids. 
31          """ 
32          if not fileids: 
33              fileids = self.fileids() 
34   
35          wordlists = [self.words(f) for f in fileids] 
36          return zip(*wordlists) 
37