nltk 3.2__zip → 3.3__zip

{nltk-3.2 → nltk-3.3}/nltk/test/corpus_fixt.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import
-
+# -*- coding: utf-8 -*-
+from __future__ import absolute_import
+
 from nltk.corpus import teardown_module

{nltk-3.2 → nltk-3.3}/nltk/test/crubadan.doctest

@@ -1,65 +1,65 @@
-.. Copyright (C) 2001-2015 NLTK Project
-.. For license information, see LICENSE.TXT
-
-Crubadan Corpus Reader
-======================
-
-Crubadan is an NLTK corpus reader for ngram files provided
-by the Crubadan project. It supports several languages.
-
-    >>> from nltk.corpus import crubadan
-    >>> crubadan.langs() # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-    ['abk', 'abn',..., 'zpa', 'zul']
-
-----------------------------------------
-Language code mapping and helper methods
-----------------------------------------
-
-The web crawler that generates the 3-gram frequencies works at the
-level of "writing systems" rather than languages. Writing systems
-are assigned internal 2-3 letter codes that require mapping to the
-standard ISO 639-3 codes. For more information, please refer to 
-the README in nltk_data/crubadan folder after installing it.
-
-To translate ISO 639-3 codes to "Crubadan Code":
-
-    >>> crubadan.iso_to_crubadan('eng')
-    'en'
-    >>> crubadan.iso_to_crubadan('fra')
-    'fr'
-    >>> crubadan.iso_to_crubadan('aaa')
-
-In reverse, print ISO 639-3 code if we have the Crubadan Code:
-
-    >>> crubadan.crubadan_to_iso('en')
-    'eng'
-    >>> crubadan.crubadan_to_iso('fr')
-    'fra'
-    >>> crubadan.crubadan_to_iso('aa')
-
----------------------------
-Accessing ngram frequencies
----------------------------
-
-On initialization the reader will create a dictionary of every
-language supported by the Crubadan project, mapping the ISO 639-3
-language code to its corresponding ngram frequency.
-
-You can access individual language FreqDist and the ngrams within them as follows:
-
-    >>> english_fd = crubadan.lang_freq('eng')
-    >>> english_fd['the']
-    728135
-
-Above accesses the FreqDist of English and returns the frequency of the ngram 'the'.
-A ngram that isn't found within the language will return 0:
-
-    >>> english_fd['sometest']
-    0
-
-A language that isn't supported will raise an exception:
-
-    >>> crubadan.lang_freq('elvish')
-    Traceback (most recent call last):
-    ...
-    RuntimeError: Unsupported language.
+.. Copyright (C) 2001-2018 NLTK Project
+.. For license information, see LICENSE.TXT
+
+Crubadan Corpus Reader
+======================
+
+Crubadan is an NLTK corpus reader for ngram files provided
+by the Crubadan project. It supports several languages.
+
+    >>> from nltk.corpus import crubadan
+    >>> crubadan.langs() # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
+    ['abk', 'abn',..., 'zpa', 'zul']
+
+----------------------------------------
+Language code mapping and helper methods
+----------------------------------------
+
+The web crawler that generates the 3-gram frequencies works at the
+level of "writing systems" rather than languages. Writing systems
+are assigned internal 2-3 letter codes that require mapping to the
+standard ISO 639-3 codes. For more information, please refer to 
+the README in nltk_data/crubadan folder after installing it.
+
+To translate ISO 639-3 codes to "Crubadan Code":
+
+    >>> crubadan.iso_to_crubadan('eng')
+    'en'
+    >>> crubadan.iso_to_crubadan('fra')
+    'fr'
+    >>> crubadan.iso_to_crubadan('aaa')
+
+In reverse, print ISO 639-3 code if we have the Crubadan Code:
+
+    >>> crubadan.crubadan_to_iso('en')
+    'eng'
+    >>> crubadan.crubadan_to_iso('fr')
+    'fra'
+    >>> crubadan.crubadan_to_iso('aa')
+
+---------------------------
+Accessing ngram frequencies
+---------------------------
+
+On initialization the reader will create a dictionary of every
+language supported by the Crubadan project, mapping the ISO 639-3
+language code to its corresponding ngram frequency.
+
+You can access individual language FreqDist and the ngrams within them as follows:
+
+    >>> english_fd = crubadan.lang_freq('eng')
+    >>> english_fd['the']
+    728135
+
+Above accesses the FreqDist of English and returns the frequency of the ngram 'the'.
+A ngram that isn't found within the language will return 0:
+
+    >>> english_fd['sometest']
+    0
+
+A language that isn't supported will raise an exception:
+
+    >>> crubadan.lang_freq('elvish')
+    Traceback (most recent call last):
+    ...
+    RuntimeError: Unsupported language.