Docstring tests (nltk#3050)

* fixed pytests

* fixed more pytests

* fixed more pytest and changed multiline pytest issues fixes for snowball.py and causal.py

* fixed pytests (mainly multiline or rounding issues)

* fixed treebank pytests, removed test for return_string=True (deprecated)

* fixed destructive.py pytests, removed test for return_string=True (deprecated)

* fixed pytest (rounding issues)

* fixed pytest (initialised missing object)

* fixed pytest (formatting issues)

* fixed pytest (formatting issues)

* fixed pytest (formatting issues)

* added pytest +SKIP for deprecated module stanford

* updated AUTHORS.md

* changed docstring corrections by usage of ELLIPSIS and different roundings

* fixed AUTHORS.md to be consistent

* Fix framenet doctest formatting with pprint

* Change docstring on MultiListBox.__init__

I believe the original typo was misinterpreted and changed to something that was not originally intended.

Co-authored-by: Jan Lennartz <[email protected]>
Co-authored-by: Tom Aarsen <[email protected]>
Co-authored-by: Tom Aarsen <[email protected]>

Author: 3 people

AUTHORS.md

@@ -294,6 +294,7 @@
 - Heungson Lee <https://github.com/heungson>
 - M.K. Pawelkiewicz <https://github.com/hamiltonianflow>
 - Steven Thomas Smith <https://github.com/essandess>
+- Jan Lennartz <https://github.com/Madnex>
 
 ## Others whose work we've taken and included in NLTK, but who didn't directly contribute it:
 

nltk/corpus/__init__.py

@@ -54,7 +54,7 @@
 ``nltk.corpus.brown.words()``:
 
     >>> from nltk.corpus import brown
-    >>> print(", ".join(brown.words()))
+    >>> print(", ".join(brown.words())) # doctest: +ELLIPSIS
     The, Fulton, County, Grand, Jury, said, ...
 
 """

nltk/corpus/reader/__init__.py

@@ -48,8 +48,8 @@
 ``nltk.corpus.brown.words()``:
 
     >>> from nltk.corpus import brown
-    >>> print(", ".join(brown.words()))
-    The, Fulton, County, Grand, Jury, said, ...
+    >>> print(", ".join(brown.words()[:6])) # only first 6 words
+    The, Fulton, County, Grand, Jury, said
 
 isort:skip_file
 """

nltk/corpus/reader/categorized_sents.py

@@ -51,7 +51,7 @@ class CategorizedSentencesCorpusReader(CategorizedCorpusReader, CorpusReader):
     Examples using the Subjectivity Dataset:
 
     >>> from nltk.corpus import subjectivity
-    >>> subjectivity.sents()[23]
+    >>> subjectivity.sents()[23] # doctest: +NORMALIZE_WHITESPACE
     ['television', 'made', 'him', 'famous', ',', 'but', 'his', 'biggest', 'hits',
     'happened', 'off', 'screen', '.']
     >>> subjectivity.categories()
@@ -62,7 +62,7 @@ class CategorizedSentencesCorpusReader(CategorizedCorpusReader, CorpusReader):
     Examples using the Sentence Polarity Dataset:
 
     >>> from nltk.corpus import sentence_polarity
-    >>> sentence_polarity.sents()
+    >>> sentence_polarity.sents() # doctest: +NORMALIZE_WHITESPACE
     [['simplistic', ',', 'silly', 'and', 'tedious', '.'], ["it's", 'so', 'laddish',
     'and', 'juvenile', ',', 'only', 'teenage', 'boys', 'could', 'possibly', 'find',
     'it', 'funny', '.'], ...]

nltk/corpus/reader/comparative_sents.py

@@ -99,7 +99,7 @@ class ComparativeSentencesCorpusReader(CorpusReader):
 
         >>> from nltk.corpus import comparative_sentences
         >>> comparison = comparative_sentences.comparisons()[0]
-        >>> comparison.text
+        >>> comparison.text # doctest: +NORMALIZE_WHITESPACE
         ['its', 'fast-forward', 'and', 'rewind', 'work', 'much', 'more', 'smoothly',
         'and', 'consistently', 'than', 'those', 'of', 'other', 'models', 'i', "'ve",
         'had', '.']

nltk/corpus/reader/framenet.py

@@ -1400,8 +1400,10 @@ def frame_by_id(self, fn_fid, ignorekeys=[]):
         256
         >>> f.name
         'Medical_specialties'
-        >>> f.definition
-        "This frame includes words that name ..."
+        >>> f.definition # doctest: +NORMALIZE_WHITESPACE
+        "This frame includes words that name medical specialties and is closely related to the
+        Medical_professionals frame.  The FE Type characterizing a sub-are in a Specialty may also be
+        expressed. 'Ralph practices paediatric oncology.'"
 
         :param fn_fid: The Framenet id number of the frame
         :type fn_fid: int
@@ -1441,8 +1443,10 @@ def frame_by_name(self, fn_fname, ignorekeys=[], check_cache=True):
         256
         >>> f.name
         'Medical_specialties'
-        >>> f.definition
-        "This frame includes words that name ..."
+        >>> f.definition # doctest: +NORMALIZE_WHITESPACE
+         "This frame includes words that name medical specialties and is closely related to the
+          Medical_professionals frame.  The FE Type characterizing a sub-are in a Specialty may also be
+          expressed. 'Ralph practices paediatric oncology.'"
 
         :param fn_fname: The name of the frame
         :type fn_fname: str
@@ -1510,9 +1514,10 @@ def frame(self, fn_fid_or_fname, ignorekeys=[]):
         >>> f.ID
         256
         >>> # ensure non-ASCII character in definition doesn't trigger an encoding error:
-        >>> fn.frame('Imposing_obligation')
+        >>> fn.frame('Imposing_obligation') # doctest: +ELLIPSIS
         frame (1494): Imposing_obligation...
 
+
         The dict that is returned from this function will contain the
         following information about the Frame:
 
@@ -1649,10 +1654,10 @@ def lu(self, fn_luid, ignorekeys=[], luName=None, frameID=None, frameName=None):
         'COD: be aware of beforehand; predict.'
         >>> fn.lu(256).frame.name
         'Expectation'
-        >>> pprint(list(map(PrettyDict, fn.lu(256).lexemes)))
+        >>> list(map(PrettyDict, fn.lu(256).lexemes))
         [{'POS': 'V', 'breakBefore': 'false', 'headword': 'false', 'name': 'foresee', 'order': 1}]
 
-        >>> fn.lu(227).exemplars[23]
+        >>> fn.lu(227).exemplars[23] # doctest: +NORMALIZE_WHITESPACE
         exemplar sentence (352962):
         [sentNo] 0
         [aPos] 59699508
@@ -2070,14 +2075,14 @@ def fes(self, name=None, frame=None):
         >>> from nltk.corpus import framenet as fn
         >>> fn.fes('Noise_maker')
         [<fe ID=6043 name=Noise_maker>]
-        >>> sorted([(fe.frame.name,fe.name) for fe in fn.fes('sound')])
+        >>> sorted([(fe.frame.name,fe.name) for fe in fn.fes('sound')]) # doctest: +NORMALIZE_WHITESPACE
         [('Cause_to_make_noise', 'Sound_maker'), ('Make_noise', 'Sound'),
          ('Make_noise', 'Sound_source'), ('Sound_movement', 'Location_of_sound_source'),
          ('Sound_movement', 'Sound'), ('Sound_movement', 'Sound_source'),
          ('Sounds', 'Component_sound'), ('Sounds', 'Location_of_sound_source'),
          ('Sounds', 'Sound_source'), ('Vocalizations', 'Location_of_sound_source'),
          ('Vocalizations', 'Sound_source')]
-        >>> sorted([(fe.frame.name,fe.name) for fe in fn.fes('sound',r'(?i)make_noise')])
+        >>> sorted([(fe.frame.name,fe.name) for fe in fn.fes('sound',r'(?i)make_noise')]) # doctest: +NORMALIZE_WHITESPACE
         [('Cause_to_make_noise', 'Sound_maker'),
          ('Make_noise', 'Sound'),
          ('Make_noise', 'Sound_source')]
@@ -2550,7 +2555,7 @@ def frame_relations(self, frame=None, frame2=None, type=None):
          <Parent=Apply_heat -- Using -> Child=Cooking_creation>, ...]
         >>> PrettyList(fn.frame_relations('Cooking_creation', type='Inheritance'))
         [<Parent=Intentionally_create -- Inheritance -> Child=Cooking_creation>]
-        >>> PrettyList(fn.frame_relations('Cooking_creation', 'Apply_heat'), breakLines=True)
+        >>> PrettyList(fn.frame_relations('Cooking_creation', 'Apply_heat'), breakLines=True) # doctest: +NORMALIZE_WHITESPACE
         [<Parent=Apply_heat -- Using -> Child=Cooking_creation>,
         <MainEntry=Apply_heat -- See_also -> ReferringEntry=Cooking_creation>]
         """
@@ -2625,7 +2630,7 @@ def fe_relations(self):
         True
         >>> len(ferels) in (10020, 12393)   # FN 1.5 and 1.7, resp.
         True
-        >>> PrettyDict(ferels[0], breakLines=True)
+        >>> PrettyDict(ferels[0], breakLines=True) # doctest: +NORMALIZE_WHITESPACE
         {'ID': 14642,
         '_type': 'ferelation',
         'frameRelation': <Parent=Abounding_with -- Inheritance -> Child=Lively_place>,

nltk/corpus/reader/opinion_lexicon.py

@@ -66,10 +66,10 @@ class OpinionLexiconCorpusReader(WordListCorpusReader):
 
     Note that words from `words()` method are sorted by file id, not alphabetically:
 
-        >>> opinion_lexicon.words()[0:10]
+        >>> opinion_lexicon.words()[0:10] # doctest: +NORMALIZE_WHITESPACE
         ['2-faced', '2-faces', 'abnormal', 'abolish', 'abominable', 'abominably',
         'abominate', 'abomination', 'abort', 'aborted']
-        >>> sorted(opinion_lexicon.words())[0:10]
+        >>> sorted(opinion_lexicon.words())[0:10] # doctest: +NORMALIZE_WHITESPACE
         ['2-faced', '2-faces', 'a+', 'abnormal', 'abolish', 'abominable', 'abominably',
         'abominate', 'abomination', 'abort']
     """

nltk/corpus/reader/pros_cons.py

@@ -36,7 +36,7 @@ class ProsConsCorpusReader(CategorizedCorpusReader, CorpusReader):
     Reader for the Pros and Cons sentence dataset.
 
         >>> from nltk.corpus import pros_cons
-        >>> pros_cons.sents(categories='Cons')
+        >>> pros_cons.sents(categories='Cons') # doctest: +NORMALIZE_WHITESPACE
         [['East', 'batteries', '!', 'On', '-', 'off', 'switch', 'too', 'easy',
         'to', 'maneuver', '.'], ['Eats', '...', 'no', ',', 'GULPS', 'batteries'],
         ...]

nltk/corpus/reader/reviews.py

@@ -160,10 +160,10 @@ class ReviewsCorpusReader(CorpusReader):
         >>> from nltk.corpus import product_reviews_1
         >>> camera_reviews = product_reviews_1.reviews('Canon_G3.txt')
         >>> review = camera_reviews[0]
-        >>> review.sents()[0]
+        >>> review.sents()[0] # doctest: +NORMALIZE_WHITESPACE
         ['i', 'recently', 'purchased', 'the', 'canon', 'powershot', 'g3', 'and', 'am',
         'extremely', 'satisfied', 'with', 'the', 'purchase', '.']
-        >>> review.features()
+        >>> review.features() # doctest: +NORMALIZE_WHITESPACE
         [('canon powershot g3', '+3'), ('use', '+2'), ('picture', '+2'),
         ('picture quality', '+1'), ('picture quality', '+1'), ('camera', '+2'),
         ('use', '+2'), ('feature', '+1'), ('picture quality', '+3'), ('use', '+1'),

nltk/draw/table.py

@@ -68,15 +68,20 @@ def __init__(self, master, columns, column_weights=None, cnf={}, **kw):
 
         :param columns: Specifies what columns should be included in
             the new multi-column listbox.  If ``columns`` is an integer,
-            the it is the number of columns to include.  If it is
+            then it is the number of columns to include.  If it is
             a list, then its length indicates the number of columns
             to include; and each element of the list will be used as
             a label for the corresponding column.
 
         :param cnf, kw: Configuration parameters for this widget.
             Use ``label_*`` to configure all labels; and ``listbox_*``
             to configure all listboxes.  E.g.:
-
+                >>> from nltk.draw.util import TextWidget, CanvasFrame, SpaceWidget
+                >>> from nltk.draw.table import MultiListbox
+                >>> cf = CanvasFrame(closeenough=10, width=300, height=300)
+                >>> c = cf.canvas()
+                >>> master = TextWidget(c, "hiya there", draggable=1)
+                >>> master = SpaceWidget(c, 0, 30)
                 >>> mlb = MultiListbox(master, 5, label_foreground='red')
         """
         # If columns was specified as an int, convert it to a list.