nltk 3.2.1__zip → 3.3__zip

{nltk-3.2.1 → nltk-3.3}/nltk/tag/stanford.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 # Natural Language Toolkit: Interface to the Stanford Part-of-speech and Named-Entity Taggers
 #
-# Copyright (C) 2001-2016 NLTK Project
+# Copyright (C) 2001-2018 NLTK Project
 # Author: Nitin Madnani <nmadnani@ets.org>
 #         Rami Al-Rfou' <ralrfou@cs.stonybrook.edu>
 # URL: <http://nltk.org/>
@@ -10,23 +10,26 @@
 """
 A module for interfacing with the Stanford taggers.
 
-Tagger models need to be downloaded from http://nlp.stanford.edu/software
+Tagger models need to be downloaded from https://nlp.stanford.edu/software
 and the STANFORD_MODELS environment variable set (a colon-separated
 list of paths).
 
 For more details see the documentation for StanfordPOSTagger and StanfordNERTagger.
 """
 
+from abc import abstractmethod
 import os
 import tempfile
 from subprocess import PIPE
 import warnings
 
-from nltk.internals import find_file, find_jar, config_java, java, _java_options, find_jars_within_path
+from six import text_type
+
+from nltk.internals import find_file, find_jar, config_java, java, _java_options
 from nltk.tag.api import TaggerI
-from nltk import compat
 
-_stanford_url = 'http://nlp.stanford.edu/software'
+_stanford_url = 'https://nlp.stanford.edu/software'
+
 
 class StanfordTagger(TaggerI):
     """
@@ -42,33 +45,40 @@ class StanfordTagger(TaggerI):
     _SEPARATOR = ''
     _JAR = ''
 
-    def __init__(self, model_filename, path_to_jar=None, encoding='utf8', verbose=False, java_options='-mx1000m'):
+    def __init__(self, model_filename, path_to_jar=None, encoding='utf8',
+                 verbose=False, java_options='-mx1000m'):
+        # Raise deprecation warning.
+        warnings.warn(str("\nThe StanfordTokenizer will "
+                          "be deprecated in version 3.2.6.\n"
+                          "Please use \033[91mnltk.parse.corenlp.CoreNLPParser\033[0m instead."),
+                      DeprecationWarning, stacklevel=2)
 
         if not self._JAR:
             warnings.warn('The StanfordTagger class is not meant to be '
-                    'instantiated directly. Did you mean StanfordPOSTagger or StanfordNERTagger?')
+                          'instantiated directly. Did you mean '
+                          'StanfordPOSTagger or StanfordNERTagger?')
         self._stanford_jar = find_jar(
                 self._JAR, path_to_jar,
                 searchpath=(), url=_stanford_url,
                 verbose=verbose)
 
         self._stanford_model = find_file(model_filename,
-                env_vars=('STANFORD_MODELS',), verbose=verbose)
-        
-        # Adding logging jar files to classpath 
-        stanford_dir = os.path.split(self._stanford_jar)[0]
-        self._stanford_jar = tuple(find_jars_within_path(stanford_dir))
-        
+                                         env_vars=('STANFORD_MODELS',),
+                                         verbose=verbose)
+
         self._encoding = encoding
         self.java_options = java_options
 
     @property
+    @abstractmethod
     def _cmd(self):
-      raise NotImplementedError
+        """
+        A property that returns the command that will be executed.
+        """
 
     def tag(self, tokens):
-        # This function should return list of tuple rather than list of list 
-        return sum(self.tag_sents([tokens]), []) 
+        # This function should return list of tuple rather than list of list
+        return sum(self.tag_sents([tokens]), [])
 
     def tag_sents(self, sentences):
         encoding = self._encoding
@@ -80,29 +90,29 @@ class StanfordTagger(TaggerI):
 
         cmd = list(self._cmd)
         cmd.extend(['-encoding', encoding])
-        
+
         # Write the actual sentences to the temporary input file
         _input_fh = os.fdopen(_input_fh, 'wb')
         _input = '\n'.join((' '.join(x) for x in sentences))
-        if isinstance(_input, compat.text_type) and encoding:
+        if isinstance(_input, text_type) and encoding:
             _input = _input.encode(encoding)
         _input_fh.write(_input)
         _input_fh.close()
-        
+
         # Run the tagger and get the output
         stanpos_output, _stderr = java(cmd, classpath=self._stanford_jar,
-                                                       stdout=PIPE, stderr=PIPE)
+                                       stdout=PIPE, stderr=PIPE)
         stanpos_output = stanpos_output.decode(encoding)
-        
+
         # Delete the temporary file
-        os.unlink(self._input_file_path) 
+        os.unlink(self._input_file_path)
 
         # Return java configurations to their default values
         config_java(options=default_options, verbose=False)
-                
+
         return self.parse_output(stanpos_output, sentences)
 
-    def parse_output(self, text, sentences = None):
+    def parse_output(self, text, sentences=None):
         # Output the tagged sentences
         tagged_sentences = []
         for tagged_sentence in text.strip().split("\n"):
@@ -113,6 +123,7 @@ class StanfordTagger(TaggerI):
             tagged_sentences.append(sentence)
         return tagged_sentences
 
+
 class StanfordPOSTagger(StanfordTagger):
     """
     A class for pos tagging with Stanford Tagger. The input is the paths to:
@@ -124,11 +135,10 @@ class StanfordPOSTagger(StanfordTagger):
     Example:
 
         >>> from nltk.tag import StanfordPOSTagger
-        >>> st = StanfordPOSTagger('english-bidirectional-distsim.tagger') # doctest: +SKIP
-        >>> st.tag('What is the airspeed of an unladen swallow ?'.split()) # doctest: +SKIP
+        >>> st = StanfordPOSTagger('english-bidirectional-distsim.tagger')
+        >>> st.tag('What is the airspeed of an unladen swallow ?'.split())
         [('What', 'WP'), ('is', 'VBZ'), ('the', 'DT'), ('airspeed', 'NN'), ('of', 'IN'), ('an', 'DT'), ('unladen', 'JJ'), ('swallow', 'VB'), ('?', '.')]
     """
-
     _SEPARATOR = '_'
     _JAR = 'stanford-postagger.jar'
 
@@ -139,7 +149,9 @@ class StanfordPOSTagger(StanfordTagger):
     def _cmd(self):
         return ['edu.stanford.nlp.tagger.maxent.MaxentTagger',
                 '-model', self._stanford_model, '-textFile',
-                self._input_file_path, '-tokenize', 'false','-outputFormatOptions', 'keepEmptySentences']
+                self._input_file_path, '-tokenize', 'false',
+                '-outputFormatOptions', 'keepEmptySentences']
+
 
 class StanfordNERTagger(StanfordTagger):
     """
@@ -169,28 +181,39 @@ class StanfordNERTagger(StanfordTagger):
 
     @property
     def _cmd(self):
-        # Adding -tokenizerFactory edu.stanford.nlp.process.WhitespaceTokenizer -tokenizerOptions tokenizeNLs=false for not using stanford Tokenizer  
+        # Adding -tokenizerFactory edu.stanford.nlp.process.WhitespaceTokenizer -tokenizerOptions tokenizeNLs=false for not using stanford Tokenizer
         return ['edu.stanford.nlp.ie.crf.CRFClassifier',
                 '-loadClassifier', self._stanford_model, '-textFile',
-                self._input_file_path, '-outputFormat', self._FORMAT, '-tokenizerFactory', 'edu.stanford.nlp.process.WhitespaceTokenizer', '-tokenizerOptions','\"tokenizeNLs=false\"']
+                self._input_file_path, '-outputFormat', self._FORMAT,
+                '-tokenizerFactory',
+                'edu.stanford.nlp.process.WhitespaceTokenizer',
+                '-tokenizerOptions', '\"tokenizeNLs=false\"']
 
     def parse_output(self, text, sentences):
         if self._FORMAT == 'slashTags':
-            # Joint together to a big list    
+            # Joint together to a big list
             tagged_sentences = []
             for tagged_sentence in text.strip().split("\n"):
                 for tagged_word in tagged_sentence.strip().split():
                     word_tags = tagged_word.strip().split(self._SEPARATOR)
-                    tagged_sentences.append((''.join(word_tags[:-1]), word_tags[-1]))
-                
+                    tagged_sentences.append((''.join(word_tags[:-1]),
+                                             word_tags[-1]))
+
             # Separate it according to the input
             result = []
-            start = 0 
+            start = 0
             for sent in sentences:
                 result.append(tagged_sentences[start:start + len(sent)])
-                start += len(sent);
-            return result 
+                start += len(sent)
+            return result
 
         raise NotImplementedError
 
+def setup_module(module):
+    from nose import SkipTest
 
+    try:
+        StanfordPOSTagger('english-bidirectional-distsim.tagger')
+    except LookupError:
+        raise SkipTest('Doctests from nltk.tag.stanford are skipped because one \
+                       of the stanford jars cannot be found.')

{nltk-3.2.1 → nltk-3.3}/nltk/tag/tnt.py

@@ -1,6 +1,6 @@
 # Natural Language Toolkit: TnT Tagger
 #
-# Copyright (C) 2001-2016 NLTK Project
+# Copyright (C) 2001-2018 NLTK Project
 # Author: Sam Huston <sjh900@gmail.com>
 #
 # URL: <http://nltk.org/>
@@ -357,30 +357,24 @@ class TnT(TaggerI):
         # if word is known
         # compute the set of possible tags
         # and their associated log probabilities
-        if word in self._wd.conditions():
+        if word in self._wd:
             self.known += 1
 
             for (history, curr_sent_logprob) in current_states:
                 logprobs = []
 
                 for t in self._wd[word].keys():
-                    p_uni = self._uni.freq((t,C))
-                    p_bi = self._bi[history[-1]].freq((t,C))
-                    p_tri = self._tri[tuple(history[-2:])].freq((t,C))
-                    p_wd = self._wd[word][t] / self._uni[(t,C)]
+                    tC = (t,C)
+                    p_uni = self._uni.freq(tC)
+                    p_bi = self._bi[history[-1]].freq(tC)
+                    p_tri = self._tri[tuple(history[-2:])].freq(tC)
+                    p_wd = self._wd[word][t] / self._uni[tC]
                     p = self._l1 *p_uni + self._l2 *p_bi + self._l3 *p_tri
                     p2 = log(p, 2) + log(p_wd, 2)
 
-                    logprobs.append(((t,C), p2))
-
-
-                # compute the result of appending each tag to this history
-                for (tag, logprob) in logprobs:
-                    new_states.append((history + [tag],
-                                       curr_sent_logprob + logprob))
-
-
-
+                    # compute the result of appending each tag to this history
+                    new_states.append((history + [tC],
+                                       curr_sent_logprob + p2))
 
         # otherwise a new word, set of possible tags is unknown
         else:
@@ -398,7 +392,7 @@ class TnT(TaggerI):
                 tag = ('Unk',C)
 
             # otherwise apply the unknown word tagger
-            else :
+            else:
                 [(_w, t)] = list(self._unk.tag([word]))
                 tag = (t,C)
 
@@ -407,8 +401,6 @@ class TnT(TaggerI):
 
             new_states = current_states
 
-
-
         # now have computed a set of possible new_states
 
         # sort states by log prob
@@ -420,7 +412,6 @@ class TnT(TaggerI):
         if len(new_states) > self._N:
             new_states = new_states[:self._N]
 
-
         # compute the tags for the rest of the sentence
         # return the best list of tags for the sentence
         return self._tagword(sent, new_states)

{nltk-3.2.1 → nltk-3.3}/nltk/tag/util.py

@@ -1,6 +1,6 @@
 # Natural Language Toolkit: Tagger Utilities
 #
-# Copyright (C) 2001-2016 NLTK Project
+# Copyright (C) 2001-2018 NLTK Project
 # Author: Edward Loper <edloper@gmail.com>
 #         Steven Bird <stevenbird1@gmail.com>
 # URL: <http://nltk.org/>

{nltk-3.2.1 → nltk-3.3}/nltk/tbl/__init__.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 # Natural Language Toolkit: Transformation-based learning
 #
-# Copyright (C) 2001-2016 NLTK Project
+# Copyright (C) 2001-2018 NLTK Project
 # Author: Marcus Uneson <marcus.uneson@gmail.com>
 #   based on previous (nltk2) version by
 #   Christopher Maloof, Edward Loper, Steven Bird

{nltk-3.2.1 → nltk-3.3}/nltk/tbl/demo.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 # Natural Language Toolkit: Transformation-based learning
 #
-# Copyright (C) 2001-2016 NLTK Project
+# Copyright (C) 2001-2018 NLTK Project
 # Author: Marcus Uneson <marcus.uneson@gmail.com>
 #   based on previous (nltk2) version by
 #   Christopher Maloof, Edward Loper, Steven Bird

{nltk-3.2.1 → nltk-3.3}/nltk/tbl/erroranalysis.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 # Natural Language Toolkit: Transformation-based learning
 #
-# Copyright (C) 2001-2016 NLTK Project
+# Copyright (C) 2001-2018 NLTK Project
 # Author: Marcus Uneson <marcus.uneson@gmail.com>
 #   based on previous (nltk2) version by
 #   Christopher Maloof, Edward Loper, Steven Bird

{nltk-3.2.1 → nltk-3.3}/nltk/tbl/feature.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 # Natural Language Toolkit: Transformation-based learning
 #
-# Copyright (C) 2001-2016 NLTK Project
+# Copyright (C) 2001-2018 NLTK Project
 # Author: Marcus Uneson <marcus.uneson@gmail.com>
 #   based on previous (nltk2) version by
 #   Christopher Maloof, Edward Loper, Steven Bird
@@ -9,8 +9,11 @@
 # For license information, see  LICENSE.TXT
 
 from __future__ import division, print_function, unicode_literals
+from abc import ABCMeta, abstractmethod
+from six import add_metaclass
 
 
+@add_metaclass(ABCMeta)
 class Feature(object):
     """
     An abstract base class for Features. A Feature is a combination of
@@ -29,9 +32,6 @@ class Feature(object):
     to the classname.
 
     """
-    # !!FOR_FUTURE: when targeting python3 only, consider @abc.abstractmethod
-    # and metaclass=abc.ABCMeta rather than NotImplementedError
-    # http://julien.danjou.info/blog/2013/guide-python-static-class-abstract-methods
 
     json_tag = 'nltk.tbl.Feature'
     PROPERTY_NAME = None
@@ -245,6 +245,7 @@ class Feature(object):
         return self < other or self == other
 
     @staticmethod
+    @abstractmethod
     def extract_property(tokens, index):
         """
         Any subclass of Feature must define static method extract_property(tokens, index)
@@ -256,6 +257,3 @@ class Feature(object):
         :return: feature value
         :rtype: any (but usually scalar)
         """
-        raise NotImplementedError
-
-

{nltk-3.2.1 → nltk-3.3}/nltk/tbl/rule.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 # Natural Language Toolkit: Transformation-based learning
 #
-# Copyright (C) 2001-2016 NLTK Project
+# Copyright (C) 2001-2018 NLTK Project
 # Author: Marcus Uneson <marcus.uneson@gmail.com>
 #   based on previous (nltk2) version by
 #   Christopher Maloof, Edward Loper, Steven Bird
@@ -9,15 +9,17 @@
 # For license information, see  LICENSE.TXT
 
 from __future__ import print_function
+from abc import ABCMeta, abstractmethod
+from six import add_metaclass
 
 from nltk.compat import python_2_unicode_compatible, unicode_repr
 from nltk import jsontags
 
+
 ######################################################################
 # Tag Rules
 ######################################################################
-
-
+@add_metaclass(ABCMeta)
 class TagRule(object):
     """
     An interface for tag transformations on a tagged corpus, as
@@ -71,6 +73,7 @@ class TagRule(object):
 
         return change
 
+    @abstractmethod
     def applies(self, tokens, index):
         """
         :return: True if the rule would change the tag of
@@ -81,7 +84,6 @@ class TagRule(object):
         :param index: The index to check
         :type index: int
         """
-        raise NotImplementedError
 
     # Rules must be comparable and hashable for the algorithm to work
     def __eq__(self, other):
@@ -317,5 +319,3 @@ class Rule(TagRule):
             condition_to_str(f, v) for (f, v) in self._conditions
         )
         return replacement + conditions
-
-

{nltk-3.2.1 → nltk-3.3}/nltk/tbl/template.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 # Natural Language Toolkit: Transformation-based learning
 #
-# Copyright (C) 2001-2016 NLTK Project
+# Copyright (C) 2001-2018 NLTK Project
 # Author: Marcus Uneson <marcus.uneson@gmail.com>
 #   based on previous (nltk2) version by
 #   Christopher Maloof, Edward Loper, Steven Bird
@@ -9,19 +9,21 @@
 # For license information, see  LICENSE.TXT
 
 from __future__ import print_function
+from abc import ABCMeta, abstractmethod
+from six import add_metaclass
 import itertools as it
 from nltk.tbl.feature import Feature
+from nltk.tbl.rule import Rule
 
 
+@add_metaclass(ABCMeta)
 class BrillTemplateI(object):
     """
     An interface for generating lists of transformational rules that
     apply at given sentence positions.  ``BrillTemplateI`` is used by
     ``Brill`` training algorithms to generate candidate rules.
     """
-    #!!FOR_FUTURE: when targeting python3 only, consider @abc.abstractmethod
-    # and metaclass=abc.ABCMeta rather than NotImplementedError
-    #http://julien.danjou.info/blog/2013/guide-python-static-class-abstract-methods
+    @abstractmethod
     def applicable_rules(self, tokens, i, correctTag):
         """
         Return a list of the transformational rules that would correct
@@ -41,8 +43,8 @@ class BrillTemplateI(object):
         :type correctTag: any
         :rtype: list(BrillRule)
         """
-        raise NotImplementedError
 
+    @abstractmethod
     def get_neighborhood(self, token, index):
         """
         Returns the set of indices *i* such that
@@ -57,10 +59,6 @@ class BrillTemplateI(object):
         :type index: int
         :rtype: set
         """
-        raise NotImplementedError
-
-
-from nltk.tbl.rule import Rule
 
 
 class Template(BrillTemplateI):
@@ -75,8 +73,8 @@ class Template(BrillTemplateI):
       - are applicable to the given token.
     """
     ALLTEMPLATES = []
-    #record a unique id of form "001", for each template created
-#    _ids = it.count(0)
+    # record a unique id of form "001", for each template created
+    # _ids = it.count(0)
 
     def __init__(self, *features):
 
@@ -129,9 +127,9 @@ class Template(BrillTemplateI):
         :type features: list of Features
         :param features: the features to build this Template on
         """
-        #determine the calling form: either
-        #Template(Feature, args1, [args2, ...)]
-        #Template(Feature1(args),  Feature2(args), ...)
+        # determine the calling form: either
+        # Template(Feature, args1, [args2, ...)]
+        # Template(Feature1(args),  Feature2(args), ...)
         if all(isinstance(f, Feature) for f in features):
             self._features = features
         elif issubclass(features[0], Feature) and all(isinstance(a, tuple) for a in features[1:]):
@@ -267,13 +265,13 @@ class Template(BrillTemplateI):
 
         """
         def nonempty_powerset(xs): #xs is a list
-            #itertools docnonempty_powerset([1,2,3]) --> (1,) (2,) (3,) (1,2) (1,3) (2,3) (1,2,3)
+            # itertools docnonempty_powerset([1,2,3]) --> (1,) (2,) (3,) (1,2) (1,3) (2,3) (1,2,3)
 
-            #find the correct tuple given combinations, one of {None, k, (k1,k2)}
+            # find the correct tuple given combinations, one of {None, k, (k1,k2)}
             k = combinations #for brevity
-            combrange = ((1, len(xs)+1) if k is None else     #n over 1 .. n over n (all non-empty combinations)
-                         (k, k+1) if isinstance(k, int) else  #n over k (only
-                         (k[0], k[1]+1))                      #n over k1, n over k1+1... n over k2
+            combrange = ((1, len(xs)+1) if k is None else     # n over 1 .. n over n (all non-empty combinations)
+                         (k, k+1) if isinstance(k, int) else  # n over k (only
+                         (k[0], k[1]+1))                      # n over k1, n over k1+1... n over k2
             return it.chain.from_iterable(it.combinations(xs, r)
                                           for r in range(*combrange))
         seentemplates = set()
@@ -281,7 +279,7 @@ class Template(BrillTemplateI):
             for pick in it.product(*picks):
                 if any(i != j and x.issuperset(y)
                        for (i, x) in enumerate(pick)
-                       for (j,y) in enumerate(pick)):
+                       for (j, y) in enumerate(pick)):
                     continue
                 if skipintersecting and any(i != j and x.intersects(y)
                                             for (i, x) in enumerate(pick)
@@ -303,6 +301,3 @@ class Template(BrillTemplateI):
     @classmethod
     def _poptemplate(cls):
         return cls.ALLTEMPLATES.pop() if cls.ALLTEMPLATES else None
-
-
-

{nltk-3.2.1 → nltk-3.3}/nltk/test/__init__.py

@@ -1,6 +1,6 @@
 # Natural Language Toolkit: Unit Tests
 #
-# Copyright (C) 2001-2016 NLTK Project
+# Copyright (C) 2001-2018 NLTK Project
 # Author: Edward Loper <edloper@gmail.com>
 # URL: <http://nltk.org/>
 # For license information, see LICENSE.TXT

{nltk-3.2.1 → nltk-3.3}/nltk/test/all.py

@@ -10,14 +10,15 @@ import doctest, unittest
 from glob import glob
 import os.path
 
+
 def additional_tests():
-    #print "here-000000000000000"
-    #print "-----", glob(os.path.join(os.path.dirname(__file__), '*.doctest'))
+    # print "here-000000000000000"
+    # print "-----", glob(os.path.join(os.path.dirname(__file__), '*.doctest'))
     dir = os.path.dirname(__file__)
     paths = glob(os.path.join(dir, '*.doctest'))
-    files = [ os.path.basename(path) for path in paths ]
+    files = [os.path.basename(path) for path in paths]
     return unittest.TestSuite(
-        [ doctest.DocFileSuite(file) for file in files ]
-        )
-#if os.path.split(path)[-1] != 'index.rst'
+        [doctest.DocFileSuite(file) for file in files]
+    )
+# if os.path.split(path)[-1] != 'index.rst'
 # skips time-dependent doctest in index.rst

{nltk-3.2.1 → nltk-3.3}/nltk/test/bnc.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
     >>> import os.path

{nltk-3.2.1 → nltk-3.3}/nltk/test/ccg.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ==============================

{nltk-3.2.1 → nltk-3.3}/nltk/test/ccg_semantics.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ==============================================

{nltk-3.2.1 → nltk-3.3}/nltk/test/chat80.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 =======

{nltk-3.2.1 → nltk-3.3}/nltk/test/childes_fixt.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import
 
+
 def setup_module(module):
     from nose import SkipTest
     import nltk.data

{nltk-3.2.1 → nltk-3.3}/nltk/test/chunk.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ==========

{nltk-3.2.1 → nltk-3.3}/nltk/test/classify.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 =============

{nltk-3.2.1 → nltk-3.3}/nltk/test/classify_fixt.py

@@ -1,10 +1,11 @@
 # -*- coding: utf-8 -*-
 from __future__ import absolute_import
 
+
 # most of classify.doctest requires numpy
 def setup_module(module):
     from nose import SkipTest
     try:
         import numpy
     except ImportError:
-        raise SkipTest("classify.doctest requires numpy")
+        raise SkipTest("classify.doctest requires numpy")

nltk-3.3/nltk/test/collections.doctest

@@ -0,0 +1,20 @@
+.. Copyright (C) 2001-2018 NLTK Project
+.. For license information, see LICENSE.TXT
+
+===========
+Collections
+===========
+
+    >>> import nltk
+    >>> from nltk.collections import *
+
+Trie
+----
+
+Trie can be pickled:
+
+    >>> import pickle
+    >>> trie = nltk.collections.Trie(['a'])
+    >>> s = pickle.dumps(trie)
+    >>> pickle.loads(s)
+    {'a': {True: None}}

{nltk-3.2.1 → nltk-3.3}/nltk/test/collocations.doctest

@@ -1,4 +1,4 @@
-.. Copyright (C) 2001-2016 NLTK Project
+.. Copyright (C) 2001-2018 NLTK Project
 .. For license information, see LICENSE.TXT
 
 ==============

{nltk-3.2.1 → nltk-3.3}/nltk/test/compat.doctest

@@ -9,10 +9,6 @@ NLTK comes with a Python 2.x/3.x compatibility layer, nltk.compat
     >>> from nltk import compat
     >>> compat.PY3
     False
-    >>> compat.integer_types
-    (<type 'int'>, <type 'long'>)
-    >>> compat.string_types
-    (<type 'basestring'>,)
     >>> # and so on
 
 @python_2_unicode_compatible