Source Code for Module nltk.corpus.util

 1  # Natural Language Toolkit: Corpus Reader Utility Functions 
 2  # 
 3  # Copyright (C) 2001-2008 NLTK Project 
 4  # Author: Edward Loper <[email protected]> 
 5  # URL: <http://nltk.org> 
 6  # For license information, see LICENSE.TXT 
 7   
 8  ###################################################################### 
 9  #{ Lazy Corpus Loader 
10  ###################################################################### 
11   
12  import re 
13  import nltk 
14   
15  TRY_ZIPFILE_FIRST = False 
16   
17 -class LazyCorpusLoader(object): 
18      """ 
19      A proxy object which is used to stand in for a corpus object 
20      before the corpus is loaded.  This allows NLTK to create an object 
21      for each corpus, but defer the costs associated with loading those 
22      corpora until the first time that they're actually accessed. 
23   
24      The first time this object is accessed in any way, it will load 
25      the corresponding corpus, and transform itself into that corpus 
26      (by modifying its own C{__class__} and C{__dict__} attributes). 
27   
28      If the corpus can not be found, then accessing this object will 
29      raise an exception, displaying installation instructions for the 
30      NLTK data package.  Once they've properly installed the data 
31      package (or modified C{nltk.data.path} to point to its location), 
32      they can then use the corpus object without restarting python. 
33      """ 
34 -    def __init__(self, name, reader_cls, *args, **kwargs): 
35          from nltk.corpus.reader.api import CorpusReader 
36          assert issubclass(reader_cls, CorpusReader) 
37          self.__name = name 
38          self.__reader_cls = reader_cls 
39          self.__args = args 
40          self.__kwargs = kwargs 
41   
42 -    def __load(self): 
43          # Find the corpus root directory. 
44          zip_name = re.sub(r'(([^/]*)(/.*)?)', r'\2.zip/\1/', self.__name) 
45          if TRY_ZIPFILE_FIRST: 
46              try:  
47                  root = nltk.data.find('corpora/%s' % zip_name) 
48              except LookupError: 
49                  raise 
50                  root = nltk.data.find('corpora/%s' % self.__name) 
51          else: 
52              try: 
53                  root = nltk.data.find('corpora/%s' % self.__name) 
54              except LookupError, e: 
55                  try: root = nltk.data.find('corpora/%s' % zip_name) 
56                  except LookupError: raise e 
57   
58          # Load the corpus. 
59          corpus = self.__reader_cls(root, *self.__args, **self.__kwargs) 
60           
61          # This is where the magic happens!  Transform ourselves into 
62          # the corpus by modifying our own __dict__ and __class__ to 
63          # match that of the corpus. 
64          self.__dict__ = corpus.__dict__ 
65          self.__class__ = corpus.__class__ 
66   
67 -    def __getattr__(self, attr): 
68          self.__load() 
69          # This looks circular, but its not, since __load() changes our 
70          # __class__ to something new: 
71          return getattr(self, attr) 
72   
73 -    def __repr__(self): 
74          self.__load() 
75          # This looks circular, but its not, since __load() changes our 
76          # __class__ to something new: 
77          return '%r' % self 
78