Fix some failing doctests

Author: stevenbird

nltk/collections.py

@@ -7,8 +7,6 @@
 
 import bisect
 
-# this unused import is for python 2.7
-from collections import Counter, defaultdict, deque
 from functools import total_ordering
 from itertools import chain, islice
 
@@ -61,7 +59,6 @@ def copy(self):
         return d
 
     def items(self):
-        # returns iterator under python 3 and list under python 2
         return zip(self.keys(), self.values())
 
     def keys(self, data=None, keys=None):
@@ -106,7 +103,6 @@ def update(self, data):
                 self._keys.append(key)
 
     def values(self):
-        # returns iterator under python 3
         return map(self.get, self._keys)
 
 

nltk/corpus/reader/wordnet.py

@@ -588,14 +588,13 @@ def closure(self, rel, depth=-1):
         (from 'animal.n.01' to 'entity.n.01'):
 
         >>> dog = wn.synset('dog.n.01')
-        >>> hyp = lambda s:s.hypernyms()
-        >>> print(list(dog.closure(hyp)))
-        [Synset('canine.n.02'), Synset('domestic_animal.n.01'), Synset('carnivore.n.01'),\
- Synset('animal.n.01'), Synset('placental.n.01'), Synset('organism.n.01'),\
- Synset('mammal.n.01'), Synset('living_thing.n.01'), Synset('vertebrate.n.01'),\
- Synset('whole.n.02'), Synset('chordate.n.01'), Synset('object.n.01'),\
- Synset('physical_entity.n.01'), Synset('entity.n.01')]
-
+        >>> hyp = lambda s:sorted(s.hypernyms())
+        >>> print(sorted(dog.closure(hyp)))
+        [Synset('animal.n.01'), Synset('canine.n.02'), Synset('carnivore.n.01'),\
+Synset('chordate.n.01'), Synset('domestic_animal.n.01'), Synset('entity.n.01'),\
+Synset('living_thing.n.01'), Synset('mammal.n.01'), Synset('object.n.01'),\
+Synset('organism.n.01'), Synset('physical_entity.n.01'), Synset('placental.n.01'),\
+Synset('vertebrate.n.01'), Synset('whole.n.02')]
         UserWarning: Discarded redundant search for Synset('animal.n.01') at depth 7
         """
 
@@ -619,7 +618,7 @@ def tree(self, rel, depth=-1, cut_mark=None):
         >>> from nltk.corpus import wordnet as wn
         >>> from pprint import pprint
         >>> computer = wn.synset('computer.n.01')
-        >>> topic = lambda s:s.topic_domains()
+        >>> topic = lambda s:sorted(s.topic_domains())
         >>> pprint(computer.tree(topic))
         [Synset('computer.n.01'), [Synset('computer_science.n.01')]]
 
@@ -629,7 +628,7 @@ def tree(self, rel, depth=-1, cut_mark=None):
         But keep duplicate branches (from 'animal.n.01' to 'entity.n.01'):
 
         >>> dog = wn.synset('dog.n.01')
-        >>> hyp = lambda s:s.hypernyms()
+        >>> hyp = lambda s:sorted(s.hypernyms())
         >>> pprint(dog.tree(hyp))
         [Synset('dog.n.01'),
          [Synset('canine.n.02'),

nltk/util.py

@@ -353,7 +353,7 @@ def unweighted_minimum_spanning_digraph(tree, children=iter, shapes=None, attr=N
     >>> import nltk
     >>> wn=nltk.corpus.wordnet
     >>> from nltk.util import unweighted_minimum_spanning_digraph as umsd
-    >>> print(umsd(wn.synset('bound.a.01'), lambda s:s.also_sees()))
+    >>> print(umsd(wn.synset('bound.a.01'), lambda s:sorted(s.also_sees())))
     digraph G {
     "Synset('bound.a.01')" -> "Synset('unfree.a.02')";
     "Synset('unfree.a.02')" -> "Synset('confined.a.02')";
@@ -377,7 +377,7 @@ def unweighted_minimum_spanning_digraph(tree, children=iter, shapes=None, attr=N
 ##########################################################################
 
 
-def acyclic_breadth_first(tree, children=iter, maxdepth=-1):
+def acyclic_breadth_first(tree, children=iter, maxdepth=-1, verbose=False):
     """Traverse the nodes of a tree in breadth-first order,
     discarding eventual cycles.
 
@@ -397,17 +397,18 @@ def acyclic_breadth_first(tree, children=iter, maxdepth=-1):
                     if child not in traversed:
                         queue.append((child, depth + 1))
                     else:
-                        warnings.warn(
-                            "Discarded redundant search for {} at depth {}".format(
-                                child, depth + 1
-                            ),
-                            stacklevel=2,
-                        )
+                        if verbose:
+                            warnings.warn(
+                                "Discarded redundant search for {} at depth {}".format(
+                                    child, depth + 1
+                                ),
+                                stacklevel=2,
+                            )
             except TypeError:
                 pass
 
 
-def acyclic_depth_first(tree, children=iter, depth=-1, cut_mark=None, traversed=None):
+def acyclic_depth_first(tree, children=iter, depth=-1, cut_mark=None, traversed=None, verbose=False):
     """Traverse the nodes of a tree in depth-first order,
     discarding eventual cycles within any branch,
     adding cut_mark (when specified) if cycles were truncated.
@@ -422,7 +423,7 @@ def acyclic_depth_first(tree, children=iter, depth=-1, cut_mark=None, traversed=
     >>> from nltk.util import acyclic_depth_first as acyclic_tree
     >>> wn=nltk.corpus.wordnet
     >>> from pprint import pprint
-    >>> pprint(acyclic_tree(wn.synset('dog.n.01'), lambda s:s.hypernyms(),cut_mark='...'))
+    >>> pprint(acyclic_tree(wn.synset('dog.n.01'), lambda s:sorted(s.hypernyms()),cut_mark='...'))
     [Synset('dog.n.01'),
      [Synset('canine.n.02'),
       [Synset('carnivore.n.01'),
@@ -454,12 +455,13 @@ def acyclic_depth_first(tree, children=iter, depth=-1, cut_mark=None, traversed=
                         )
                     ]
                 else:
-                    warnings.warn(
-                        "Discarded redundant search for {} at depth {}".format(
-                            child, depth - 1
-                        ),
-                        stacklevel=3,
-                    )
+                    if verbose:
+                        warnings.warn(
+                            "Discarded redundant search for {} at depth {}".format(
+                                child, depth - 1
+                            ),
+                            stacklevel=3,
+                        )
                     if cut_mark:
                         out_tree += [f"Cycle({child},{depth - 1},{cut_mark})"]
         except TypeError:
@@ -470,7 +472,7 @@ def acyclic_depth_first(tree, children=iter, depth=-1, cut_mark=None, traversed=
 
 
 def acyclic_branches_depth_first(
-    tree, children=iter, depth=-1, cut_mark=None, traversed=None
+    tree, children=iter, depth=-1, cut_mark=None, traversed=None, verbose=False
 ):
     """Traverse the nodes of a tree in depth-first order,
     discarding eventual cycles within the same branch,
@@ -488,7 +490,7 @@ def acyclic_branches_depth_first(
     >>> from nltk.util import acyclic_branches_depth_first as tree
     >>> wn=nltk.corpus.wordnet
     >>> from pprint import pprint
-    >>> pprint(tree(wn.synset('certified.a.01'), lambda s:s.also_sees(), cut_mark='...', depth=4))
+    >>> pprint(tree(wn.synset('certified.a.01'), lambda s:sorted(s.also_sees()), cut_mark='...', depth=4))
     [Synset('certified.a.01'),
      [Synset('authorized.a.01'),
       [Synset('lawful.a.01'),
@@ -527,12 +529,13 @@ def acyclic_branches_depth_first(
                         )
                     ]
                 else:
-                    warnings.warn(
-                        "Discarded redundant search for {} at depth {}".format(
-                            child, depth - 1
-                        ),
-                        stacklevel=3,
-                    )
+                    if verbose:
+                        warnings.warn(
+                            "Discarded redundant search for {} at depth {}".format(
+                                child, depth - 1
+                            ),
+                            stacklevel=3,
+                        )
                     if cut_mark:
                         out_tree += [f"Cycle({child},{depth - 1},{cut_mark})"]
         except TypeError:
@@ -563,7 +566,7 @@ def unweighted_minimum_spanning_dict(tree, children=iter):
     >>> from nltk.corpus import wordnet as wn
     >>> from nltk.util import unweighted_minimum_spanning_dict as umsd
     >>> from pprint import pprint
-    >>> pprint(umsd(wn.synset('bound.a.01'), lambda s:s.also_sees()))
+    >>> pprint(umsd(wn.synset('bound.a.01'), lambda s:sorted(s.also_sees())))
     {Synset('bound.a.01'): [Synset('unfree.a.02')],
      Synset('classified.a.02'): [],
      Synset('confined.a.02'): [],
@@ -605,7 +608,7 @@ def unweighted_minimum_spanning_tree(tree, children=iter):
     >>> from nltk.util import unweighted_minimum_spanning_tree as mst
     >>> wn=nltk.corpus.wordnet
     >>> from pprint import pprint
-    >>> pprint(mst(wn.synset('bound.a.01'), lambda s:s.also_sees()))
+    >>> pprint(mst(wn.synset('bound.a.01'), lambda s:sorted(s.also_sees())))
     [Synset('bound.a.01'),
      [Synset('unfree.a.02'),
       [Synset('confined.a.02')],