nltk 3.2__zip → 3.3__zip

nltk-3.3/nltk/test/unit/test_tokenize.py

@@ -0,0 +1,168 @@
+# -*- coding: utf-8 -*-
+"""
+Unit tests for nltk.tokenize.
+See also nltk/test/tokenize.doctest
+"""
+
+from __future__ import unicode_literals
+from nltk.tokenize import TweetTokenizer, StanfordSegmenter, TreebankWordTokenizer
+from nose import SkipTest
+import unittest
+import os
+
+
+class TestTokenize(unittest.TestCase):
+
+    def test_tweet_tokenizer(self):
+        """
+        Test TweetTokenizer using words with special and accented characters.
+        """
+
+        tokenizer = TweetTokenizer(strip_handles=True, reduce_len=True)
+        s9 = "@myke: Let's test these words: resumé España München français"
+        tokens = tokenizer.tokenize(s9)
+        expected = [':', "Let's", 'test', 'these', 'words', ':', 'resumé',
+                    'España', 'München', 'français']
+        self.assertEqual(tokens, expected)
+
+    def test_stanford_segmenter_arabic(self):
+        """
+        Test the Stanford Word Segmenter for Arabic (default config)
+        """
+        try:
+            seg = StanfordSegmenter()
+            seg.default_config('ar')
+            sent = u'يبحث علم الحاسوب استخدام الحوسبة بجميع اشكالها لحل المشكلات'
+            segmented_sent = seg.segment(sent.split())
+            assert segmented_sent.split() == ['يبحث', 'علم', 'الحاسوب', 'استخدام',
+                                              'الحوسبة', 'ب', 'جميع', 'اشكال',
+                                              'ها', 'ل', 'حل', 'المشكلات']
+        except LookupError as e:
+            raise SkipTest(str(e))
+
+    def test_stanford_segmenter_chinese(self):
+        """
+        Test the Stanford Word Segmenter for Chinese (default config)
+        """
+        try:
+            seg = StanfordSegmenter()
+            seg.default_config('zh')
+            sent = u"这是斯坦福中文分词器测试"
+            segmented_sent = seg.segment(sent.split())
+            assert segmented_sent.split() == ['这', '是', '斯坦福',
+                                              '中文', '分词器', '测试']
+        except LookupError as e:
+            raise SkipTest(str(e))
+
+    def test_phone_tokenizer(self):
+        """
+        Test a string that resembles a phone number but contains a newline
+        """
+
+        # Should be recognized as a phone number, albeit one with multiple spaces
+        tokenizer = TweetTokenizer()
+        test1 = "(393)  928 -3010"
+        expected = ['(393)  928 -3010']
+        result = tokenizer.tokenize(test1)
+        self.assertEqual(result, expected)
+
+        # Due to newline, first three elements aren't part of a phone number;
+        # fourth is
+        test2= "(393)\n928 -3010"
+        expected = ['(', '393', ')', "928 -3010"]
+        result = tokenizer.tokenize(test2)
+        self.assertEqual(result, expected)
+
+    def test_remove_handle(self):
+        """
+        Test remove_handle() from casual.py with specially crafted edge cases
+        """
+
+        tokenizer = TweetTokenizer(strip_handles=True)
+
+        # Simple example. Handles with just numbers should be allowed
+        test1 = "@twitter hello @twi_tter_. hi @12345 @123news"
+        expected = ['hello', '.', 'hi']
+        result = tokenizer.tokenize(test1)
+        self.assertEqual(result, expected)
+
+        # Handles are allowed to follow any of the following characters
+        test2 = "@n`@n~@n(@n)@n-@n=@n+@n\\@n|@n[@n]@n{@n}@n;@n:@n'@n\"@n/@n?@n.@n,@n<@n>@n @n\n@n ñ@n.ü@n.ç@n."
+        expected = ['`', '~', '(', ')', '-', '=', '+', '\\', '|', '[', ']', '{', '}', ';', ':', "'", '"', '/', '?', '.', ',', '<', '>', 'ñ', '.', 'ü', '.', 'ç', '.']
+        result = tokenizer.tokenize(test2)
+        self.assertEqual(result, expected)
+
+
+        # Handles are NOT allowed to follow any of the following characters
+        test3 = "a@n j@n z@n A@n L@n Z@n 1@n 4@n 7@n 9@n 0@n _@n !@n @@n #@n $@n %@n &@n *@n"
+        expected = ['a', '@n', 'j', '@n', 'z', '@n', 'A', '@n', 'L', '@n', 'Z', '@n', '1', '@n', '4', '@n', '7', '@n', '9', '@n', '0', '@n', '_', '@n', '!', '@n', '@', '@n', '#', '@n', '$', '@n', '%', '@n', '&', '@n', '*', '@n']
+        result = tokenizer.tokenize(test3)
+        self.assertEqual(result, expected)
+
+
+        # Handles are allowed to precede the following characters
+        test4 = "@n!a @n#a @n$a @n%a @n&a @n*a"
+        expected = ['!', 'a', '#', 'a', '$', 'a', '%', 'a', '&', 'a', '*', 'a']
+        result = tokenizer.tokenize(test4)
+        self.assertEqual(result, expected)
+
+
+        # Tests interactions with special symbols and multiple @
+        test5 = "@n!@n @n#@n @n$@n @n%@n @n&@n @n*@n @n@n @@n @n@@n @n_@n @n7@n @nj@n"
+        expected = ['!', '@n', '#', '@n', '$', '@n', '%', '@n', '&', '@n', '*', '@n', '@n', '@n', '@', '@n', '@n', '@', '@n', '@n_', '@n', '@n7', '@n', '@nj', '@n']
+        result = tokenizer.tokenize(test5)
+        self.assertEqual(result, expected)
+
+
+        # Tests that handles can have a max length of 20
+        test6 = "@abcdefghijklmnopqrstuvwxyz @abcdefghijklmnopqrst1234 @abcdefghijklmnopqrst_ @abcdefghijklmnopqrstendofhandle"
+        expected = ['uvwxyz', '1234', '_', 'endofhandle']
+        result = tokenizer.tokenize(test6)
+        self.assertEqual(result, expected)
+
+
+        # Edge case where an @ comes directly after a long handle
+        test7 = "@abcdefghijklmnopqrstu@abcde @abcdefghijklmnopqrst@abcde @abcdefghijklmnopqrst_@abcde @abcdefghijklmnopqrst5@abcde"
+        expected = ['u', '@abcde', '@abcdefghijklmnopqrst', '@abcde', '_', '@abcde', '5', '@abcde']
+        result = tokenizer.tokenize(test7)
+        self.assertEqual(result, expected)
+
+    def test_treebank_span_tokenizer(self):
+        """
+        Test TreebankWordTokenizer.span_tokenize function
+        """
+
+        tokenizer = TreebankWordTokenizer()
+
+        # Test case in the docstring
+        test1 = "Good muffins cost $3.88\nin New (York).  Please (buy) me\ntwo of them.\n(Thanks)."
+        expected = [
+            (0, 4), (5, 12), (13, 17), (18, 19), (19, 23),
+            (24, 26), (27, 30), (31, 32), (32, 36), (36, 37), (37, 38),
+            (40, 46), (47, 48), (48, 51), (51, 52), (53, 55), (56, 59),
+            (60, 62), (63, 68), (69, 70), (70, 76), (76, 77), (77, 78)
+        ]
+        result = list(tokenizer.span_tokenize(test1))
+        self.assertEqual(result, expected)
+
+        # Test case with double quotation
+        test2 = "The DUP is similar to the \"religious right\" in the United States and takes a hardline stance on social issues"
+        expected = [
+            (0, 3), (4, 7), (8, 10), (11, 18), (19, 21), (22, 25), (26, 27),
+            (27, 36), (37, 42), (42, 43), (44, 46), (47, 50), (51, 57), (58, 64),
+            (65, 68), (69, 74), (75, 76), (77, 85), (86, 92), (93, 95), (96, 102),
+            (103, 109)
+        ]
+        result = list(tokenizer.span_tokenize(test2))
+        self.assertEqual(result, expected)
+
+        # Test case with double qoutation as well as converted quotations
+        test3 = "The DUP is similar to the \"religious right\" in the United States and takes a ``hardline'' stance on social issues"
+        expected = [
+            (0, 3), (4, 7), (8, 10), (11, 18), (19, 21), (22, 25), (26, 27),
+            (27, 36), (37, 42), (42, 43), (44, 46), (47, 50), (51, 57), (58, 64),
+            (65, 68), (69, 74), (75, 76), (77, 79), (79, 87), (87, 89), (90, 96),
+            (97, 99), (100, 106), (107, 113)
+        ]
+        result = list(tokenizer.span_tokenize(test3))
+        self.assertEqual(result, expected)

{nltk-3.2 → nltk-3.3}/nltk/test/unit/test_twitter_auth.py

@@ -1,185 +1,185 @@
-# -*- coding: utf-8 -*-
-"""
-Tests for static parts of Twitter package
-"""
-
-import os
-import unittest
-from nose import SkipTest
-
-try:
-    import twython
-except ImportError as e:
-    raise SkipTest("The twython library has not been installed.")
-
-from nltk.twitter import Authenticate
-
-
-class TestCredentials(unittest.TestCase):
-    """
-    Tests that Twitter credentials information from file is handled correctly.
-    """
-
-    def setUp(self):
-        self.subdir = os.path.join(os.path.dirname(__file__), 'files')
-        self.auth = Authenticate()
-        os.environ['TWITTER'] = 'twitter-files'
-
-    def test_environment(self):
-        """
-        Test that environment variable has been read correctly.
-        """
-        fn = os.path.basename(self.auth.creds_subdir)
-        self.assertEqual(fn, os.environ['TWITTER'])
-
-    def test_empty_subdir1(self):
-        """
-        Setting subdir to empty path should raise an error.
-        """
-        try:
-            self.auth.load_creds(subdir='')
-        # raises ValueError (zero length field name in format) for python 2.6
-        # OSError for the rest
-        except OSError:
-            pass
-        except ValueError:
-            pass
-        except Exception as e:
-            self.fail('Unexpected exception thrown: %s' % e)
-        else:
-            self.fail('OSError exception not thrown.')
-
-    def test_empty_subdir2(self):
-        """
-        Setting subdir to `None` should raise an error.
-        """
-        self.auth.creds_subdir = None
-        try:
-            self.auth.load_creds()
-        except ValueError:
-            pass
-        except Exception as e:
-            self.fail('Unexpected exception thrown: %s' % e)
-        else:
-            self.fail('ValueError exception not thrown.')
-
-    def test_missingdir(self):
-        """
-        Setting subdir to nonexistent directory should raise an error.
-        """
-        try:
-            self.auth.load_creds(subdir='/nosuchdir')
-        # raises ValueError (zero length field name in format) for python 2.6
-        # OSError for the rest
-        except OSError:
-            pass
-        except ValueError:
-            pass
-        except Exception as e:
-            self.fail('Unexpected exception thrown: %s' % e)
-        else:
-            self.fail('OSError exception not thrown.')
-
-    def test_missingfile1(self):
-        """
-        Defaults for authentication will fail since 'credentials.txt' not
-        present in default subdir, as read from `os.environ['TWITTER']`.
-        """
-        try:
-            self.auth.load_creds()
-        # raises ValueError (zero length field name in format) for python 2.6
-        # OSError for the rest
-        except OSError:
-            pass
-        except ValueError:
-            pass
-        except Exception as e:
-            self.fail('Unexpected exception thrown: %s' % e)
-        else:
-            self.fail('OSError exception not thrown.')
-
-    def test_missingfile2(self):
-        """
-        Credentials file 'foobar' cannot be found in default subdir.
-        """
-        try:
-            self.auth.load_creds(creds_file='foobar')
-        # raises ValueError (zero length field name in format) for python 2.6
-        # OSError for the rest
-        except OSError:
-            pass
-        except ValueError:
-            pass
-        except Exception as e:
-            self.fail('Unexpected exception thrown: %s' % e)
-        else:
-            self.fail('OSError exception not thrown.')
-
-    def test_incomplete_file(self):
-        """
-        Credentials file 'bad_oauth1-1.txt' is incomplete
-        """
-        try:
-            self.auth.load_creds(creds_file='bad_oauth1-1.txt',
-                                 subdir=self.subdir)
-        except ValueError:
-            pass
-        except Exception as e:
-            self.fail('Unexpected exception thrown: %s' % e)
-        else:
-            self.fail('ValueError exception not thrown.')
-
-    def test_malformed_file1(self):
-        """
-        First key in credentials file 'bad_oauth1-2.txt' is ill-formed
-        """
-        try:
-            self.auth.load_creds(creds_file='bad_oauth1-2.txt',
-                                 subdir=self.subdir)
-        except ValueError:
-            pass
-        except Exception as e:
-            self.fail('Unexpected exception thrown: %s' % e)
-        else:
-            self.fail('ValueError exception not thrown.')
-
-    def test_malformed_file2(self):
-        """
-        First key in credentials file 'bad_oauth1-2.txt' is ill-formed
-        """
-        try:
-            self.auth.load_creds(creds_file='bad_oauth1-3.txt',
-                                 subdir=self.subdir)
-        except ValueError:
-            pass
-        except Exception as e:
-            self.fail('Unexpected exception thrown: %s' % e)
-        else:
-            self.fail('ValueError exception not thrown.')
-
-    def test_correct_path(self):
-        """
-        Path to default credentials file is well-formed, given specified
-        subdir.
-        """
-        self.auth.load_creds(subdir=self.subdir)
-        self.auth.creds_fullpath = os.path.join(self.subdir, self.auth.creds_file)
-
-    def test_correct_file1(self):
-        """
-        Default credentials file is identified
-        """
-        self.auth.load_creds(subdir=self.subdir)
-        self.assertEqual(self.auth.creds_file, 'credentials.txt')
-
-    def test_correct_file2(self):
-        """
-        Default credentials file has been read correctluy
-        """
-        oauth = self.auth.load_creds(subdir=self.subdir)
-        self.assertEqual(oauth['app_key'], 'a')
-
-
-if __name__ == '__main__':
-    unittest.main()
-
+# -*- coding: utf-8 -*-
+"""
+Tests for static parts of Twitter package
+"""
+
+import os
+import unittest
+from nose import SkipTest
+
+try:
+    import twython
+except ImportError as e:
+    raise SkipTest("The twython library has not been installed.")
+
+from nltk.twitter import Authenticate
+
+
+class TestCredentials(unittest.TestCase):
+    """
+    Tests that Twitter credentials information from file is handled correctly.
+    """
+
+    def setUp(self):
+        self.subdir = os.path.join(os.path.dirname(__file__), 'files')
+        self.auth = Authenticate()
+        os.environ['TWITTER'] = 'twitter-files'
+
+    def test_environment(self):
+        """
+        Test that environment variable has been read correctly.
+        """
+        fn = os.path.basename(self.auth.creds_subdir)
+        self.assertEqual(fn, os.environ['TWITTER'])
+
+    def test_empty_subdir1(self):
+        """
+        Setting subdir to empty path should raise an error.
+        """
+        try:
+            self.auth.load_creds(subdir='')
+        # raises ValueError (zero length field name in format) for python 2.6
+        # OSError for the rest
+        except OSError:
+            pass
+        except ValueError:
+            pass
+        except Exception as e:
+            self.fail('Unexpected exception thrown: %s' % e)
+        else:
+            self.fail('OSError exception not thrown.')
+
+    def test_empty_subdir2(self):
+        """
+        Setting subdir to `None` should raise an error.
+        """
+        self.auth.creds_subdir = None
+        try:
+            self.auth.load_creds()
+        except ValueError:
+            pass
+        except Exception as e:
+            self.fail('Unexpected exception thrown: %s' % e)
+        else:
+            self.fail('ValueError exception not thrown.')
+
+    def test_missingdir(self):
+        """
+        Setting subdir to nonexistent directory should raise an error.
+        """
+        try:
+            self.auth.load_creds(subdir='/nosuchdir')
+        # raises ValueError (zero length field name in format) for python 2.6
+        # OSError for the rest
+        except OSError:
+            pass
+        except ValueError:
+            pass
+        except Exception as e:
+            self.fail('Unexpected exception thrown: %s' % e)
+        else:
+            self.fail('OSError exception not thrown.')
+
+    def test_missingfile1(self):
+        """
+        Defaults for authentication will fail since 'credentials.txt' not
+        present in default subdir, as read from `os.environ['TWITTER']`.
+        """
+        try:
+            self.auth.load_creds()
+        # raises ValueError (zero length field name in format) for python 2.6
+        # OSError for the rest
+        except OSError:
+            pass
+        except ValueError:
+            pass
+        except Exception as e:
+            self.fail('Unexpected exception thrown: %s' % e)
+        else:
+            self.fail('OSError exception not thrown.')
+
+    def test_missingfile2(self):
+        """
+        Credentials file 'foobar' cannot be found in default subdir.
+        """
+        try:
+            self.auth.load_creds(creds_file='foobar')
+        # raises ValueError (zero length field name in format) for python 2.6
+        # OSError for the rest
+        except OSError:
+            pass
+        except ValueError:
+            pass
+        except Exception as e:
+            self.fail('Unexpected exception thrown: %s' % e)
+        else:
+            self.fail('OSError exception not thrown.')
+
+    def test_incomplete_file(self):
+        """
+        Credentials file 'bad_oauth1-1.txt' is incomplete
+        """
+        try:
+            self.auth.load_creds(creds_file='bad_oauth1-1.txt',
+                                 subdir=self.subdir)
+        except ValueError:
+            pass
+        except Exception as e:
+            self.fail('Unexpected exception thrown: %s' % e)
+        else:
+            self.fail('ValueError exception not thrown.')
+
+    def test_malformed_file1(self):
+        """
+        First key in credentials file 'bad_oauth1-2.txt' is ill-formed
+        """
+        try:
+            self.auth.load_creds(creds_file='bad_oauth1-2.txt',
+                                 subdir=self.subdir)
+        except ValueError:
+            pass
+        except Exception as e:
+            self.fail('Unexpected exception thrown: %s' % e)
+        else:
+            self.fail('ValueError exception not thrown.')
+
+    def test_malformed_file2(self):
+        """
+        First key in credentials file 'bad_oauth1-2.txt' is ill-formed
+        """
+        try:
+            self.auth.load_creds(creds_file='bad_oauth1-3.txt',
+                                 subdir=self.subdir)
+        except ValueError:
+            pass
+        except Exception as e:
+            self.fail('Unexpected exception thrown: %s' % e)
+        else:
+            self.fail('ValueError exception not thrown.')
+
+    def test_correct_path(self):
+        """
+        Path to default credentials file is well-formed, given specified
+        subdir.
+        """
+        self.auth.load_creds(subdir=self.subdir)
+        self.auth.creds_fullpath = os.path.join(self.subdir, self.auth.creds_file)
+
+    def test_correct_file1(self):
+        """
+        Default credentials file is identified
+        """
+        self.auth.load_creds(subdir=self.subdir)
+        self.assertEqual(self.auth.creds_file, 'credentials.txt')
+
+    def test_correct_file2(self):
+        """
+        Default credentials file has been read correctluy
+        """
+        oauth = self.auth.load_creds(subdir=self.subdir)
+        self.assertEqual(oauth['app_key'], 'a')
+
+
+if __name__ == '__main__':
+    unittest.main()
+

nltk-3.3/nltk/test/unit/test_wordnet.py

@@ -0,0 +1,134 @@
+# -*- coding: utf-8 -*-
+"""
+Unit tests for nltk.corpus.wordnet
+See also nltk/test/wordnet.doctest
+"""
+
+from __future__ import unicode_literals
+from nose import SkipTest
+import unittest
+import os
+
+from nltk.corpus.reader.wordnet import WordNetCorpusReader
+from nltk.corpus import wordnet as wn
+from nltk.corpus import wordnet_ic as wnic
+from nltk.data import find as find_data
+
+
+wn.ensure_loaded()
+S = wn.synset
+L = wn.lemma
+
+class WordnNetDemo(unittest.TestCase):
+
+    def test_retrieve_synset(self):
+        move_synset = S('go.v.21')
+        self.assertEqual(move_synset.name(), "move.v.15")
+        self.assertEqual(move_synset.lemma_names(), ['move', 'go'])
+        self.assertEqual(move_synset.definition(), "have a turn; make one's move in a game")
+        self.assertEqual(move_synset.examples(), ['Can I go now?'])
+
+
+    def test_retrieve_synsets(self):
+        self.assertEqual(sorted(wn.synsets('zap', pos='n')),
+                        [S('zap.n.01')])
+        self.assertEqual(sorted(wn.synsets('zap', pos='v')),
+                        [S('microwave.v.01'), S('nuke.v.01'), S('zap.v.01'), S('zap.v.02')])
+
+    def test_hyperhyponyms(self):
+        # Not every synset as hypernyms()
+        self.assertEqual(S('travel.v.01').hypernyms(), [])
+        self.assertEqual(S('travel.v.02').hypernyms(),
+                        [S('travel.v.03')])
+        self.assertEqual(S('travel.v.03').hypernyms(), [])
+
+        # Test hyper-/hyponyms.
+        self.assertEqual(S('breakfast.n.1').hypernyms(), [S('meal.n.01')])
+        first_five_meal_hypo = [S('banquet.n.02'), S('bite.n.04'), S('breakfast.n.01'), S('brunch.n.01'), S('buffet.n.02')]
+        self.assertEqual(sorted(S('meal.n.1').hyponyms()[:5]), first_five_meal_hypo)
+        self.assertEqual(S('Austen.n.1').instance_hypernyms(), [S('writer.n.01')])
+        first_five_composer_hypo = [S('ambrose.n.01'), S('bach.n.01'), S('barber.n.01'), S('bartok.n.01'), S('beethoven.n.01')]
+        self.assertEqual(S('composer.n.1').instance_hyponyms()[:5], first_five_composer_hypo)
+
+        # Test root hyper-/hyponyms
+        self.assertEqual(S('person.n.01').root_hypernyms(), [S('entity.n.01')])
+        self.assertEqual(S('sail.v.01').root_hypernyms(), [S('travel.v.01')])
+        self.assertEqual(S('fall.v.12').root_hypernyms(), [S('act.v.01'), S('fall.v.17')])
+
+    def test_derivationally_related_forms(self):
+        # Test `derivationally_related_forms()`
+        self.assertEqual(L('zap.v.03.nuke').derivationally_related_forms(),
+                        [L('atomic_warhead.n.01.nuke')])
+        self.assertEqual(L('zap.v.03.atomize').derivationally_related_forms(),
+                        [L('atomization.n.02.atomization')])
+        self.assertEqual(L('zap.v.03.atomise').derivationally_related_forms(),
+                        [L('atomization.n.02.atomisation')])
+        self.assertEqual(L('zap.v.03.zap').derivationally_related_forms(),
+                        [])
+
+    def test_meronyms_holonyms(self):
+        # Test meronyms, holonyms.
+        self.assertEqual(S('dog.n.01').member_holonyms(), [S('canis.n.01'), S('pack.n.06')])
+        self.assertEqual(S('dog.n.01').part_meronyms(), [S('flag.n.07')])
+
+        self.assertEqual(S('faculty.n.2').member_meronyms(),
+                        [S('professor.n.01')])
+        self.assertEqual(S('copilot.n.1').member_holonyms(),
+                        [S('crew.n.01')])
+
+        self.assertEqual(S('table.n.2').part_meronyms(),
+                        [S('leg.n.03'), S('tabletop.n.01'), S('tableware.n.01')])
+        self.assertEqual(S('course.n.7').part_holonyms(),
+                        [S('meal.n.01')])
+
+        self.assertEqual(S('water.n.1').substance_meronyms(),
+                        [S('hydrogen.n.01'), S('oxygen.n.01')])
+        self.assertEqual(S('gin.n.1').substance_holonyms(),
+                        [S('gin_and_it.n.01'), S('gin_and_tonic.n.01'),
+                         S('martini.n.01'), S('pink_lady.n.01')])
+
+    def test_antonyms(self):
+        # Test antonyms.
+        self.assertEqual(L('leader.n.1.leader').antonyms(), [L('follower.n.01.follower')])
+        self.assertEqual(L('increase.v.1.increase').antonyms(), [L('decrease.v.01.decrease')])
+
+
+    def test_misc_relations(self):
+        # Test misc relations.
+        self.assertEqual(S('snore.v.1').entailments(), [S('sleep.v.01')])
+        self.assertEqual(S('heavy.a.1').similar_tos(),
+                        [S('dense.s.03'), S('doughy.s.01'),
+                         S('heavier-than-air.s.01'), S('hefty.s.02'),
+                         S('massive.s.04'), S('non-buoyant.s.01'),
+                         S('ponderous.s.02')])
+        self.assertEqual(S('light.a.1').attributes(), [S('weight.n.01')])
+        self.assertEqual(S('heavy.a.1').attributes(), [S('weight.n.01')])
+
+        # Test pertainyms.
+        self.assertEqual(L('English.a.1.English').pertainyms(),
+                         [L('england.n.01.England')])
+
+    def test_lch(self):
+        # Test LCH.
+        self.assertEqual(S('person.n.01').lowest_common_hypernyms(S('dog.n.01')),
+                         [S('organism.n.01')])
+        self.assertEqual(S('woman.n.01').lowest_common_hypernyms(S('girlfriend.n.02')),
+                         [S('woman.n.01')])
+
+    def test_domains(self):
+        # Test domains.
+        self.assertEqual(S('code.n.03').topic_domains(), [S('computer_science.n.01')])
+        self.assertEqual(S('pukka.a.01').region_domains(), [S('india.n.01')])
+        self.assertEqual(S('freaky.a.01').usage_domains(), [S('slang.n.02')])
+
+    def test_wordnet_similarities(self):
+        # Path based similarities.
+        self.assertAlmostEqual(S('cat.n.01').path_similarity(S('cat.n.01')), 1.0)
+        self.assertAlmostEqual(S('dog.n.01').path_similarity(S('cat.n.01')), 0.2)
+        self.assertAlmostEqual(S('dog.n.01').lch_similarity(S('cat.n.01')), 2.028, places=3)
+        self.assertAlmostEqual(S('dog.n.01').wup_similarity(S('cat.n.01')), 0.8571, places=3)
+        # Information Content similarities.
+        brown_ic = wnic.ic('ic-brown.dat')
+        self.assertAlmostEqual(S('dog.n.01').jcn_similarity(S('cat.n.01'), brown_ic), 0.4497, places=3)
+        semcor_ic = wnic.ic('ic-semcor.dat')
+        self.assertAlmostEqual(S('dog.n.01').lin_similarity(S('cat.n.01'), semcor_ic), 0.8863, places=3)