Merge remote-tracking branch 'nltk/twitter' into twitter

nltk/corpus/__init__.py

@@ -201,7 +201,7 @@ treebank_chunk = LazyCorpusLoader(
 treebank_raw = LazyCorpusLoader(
     'treebank/raw', PlaintextCorpusReader, r'wsj_.*', encoding='ISO-8859-2')
 tweets = LazyCorpusLoader(
-    'tweets', TwitterCorpusReader)
+    'twitter', TwitterCorpusReader, '.*\.json')
 udhr = LazyCorpusLoader(
     'udhr', UdhrCorpusReader)
 udhr2 = LazyCorpusLoader(

nltk/corpus/reader/bnc.py

@@ -22,7 +22,7 @@ class BNCCorpusReader(XMLCorpusReader):
     http://www.ota.ox.ac.uk/desc/2554
 
     If you extracted the archive to a directory called `BNC`, then you can
-    instantiate the reder as::
+    instantiate the reader as::
 
         BNCCorpusReader(root='BNC/Texts/', fileids=r'[A-K]/\w*/\w*\.xml')
 

nltk/corpus/reader/tweets.py

@@ -26,6 +26,21 @@ class TwitterCorpusReader(CorpusReader):
 
     Individual Tweets can be tokenized using the default tokenizer, or by a
     custom tokenizer specified as a parameter to the constructor.
+
+    Construct a new Tweet corpus reader for a set of documents
+    located at the given root directory.
+
+    If you made your own tweet collection in a directory called
+    `twitter-files`, then you can initialise the reader as::
+
+        >>> reader = TwitterCorpusReader(root='twitter-files', '.*\.json') # doctest: +SKIP
+
+    The recommended approach is to use this directory as the value of the
+    environmental variable `TWITTER`, and then invoke the reader as::
+
+        >>> root = os.environ['TWITTER']
+        >>> reader = TwitterCorpusReader(root, '.*\.json') # doctest: +SKIP
+
     """
 
     CorpusView = StreamBackedCorpusView
@@ -33,15 +48,10 @@ class TwitterCorpusReader(CorpusReader):
     The corpus view class used by this reader.
     """
 
-    def __init__(self, root, fileids,
+    def __init__(self, root,
                  word_tokenizer=TweetTokenizer(),
                  encoding='utf8'):
         """
-        Construct a new Tweet corpus reader for a set of documents
-        located at the given root directory.  Example usage:
-
-            >>> root = os.environ['TWITTER']
-            >>> reader = TwitterCorpusReader(root, '.*\.json') # doctest: +SKIP
 
         :param root: The root directory for this corpus.
 

nltk/twitter/__init__.py

@@ -13,6 +13,14 @@ This package contains classes for retrieving Tweet documents using the
 Twitter API.
 
 """
+try:
+    from twython import Twython, TwythonStreamer
+except ImportError as err:
+    import textwrap
+    MSG = """The NLTK twitterclient module requires the Twython package. See\
+    https://twython.readthedocs.org/ for installation instructions."""
+    err.msg = textwrap.fill(MSG)
+    raise
 
 from nltk.twitter.util import credsfromfile
 from nltk.twitter.twitterclient import Streamer, Query, Twitter, TweetViewer,\

nltk/twitter/twitter_demo.py

@@ -192,8 +192,9 @@ def corpusreader_demo():
 
     """
     from nltk.corpus import TwitterCorpusReader
-    root = os.environ['TWITTER']
-    reader = TwitterCorpusReader(root, '1k_sample.json')
+    #root = os.environ['TWITTER']
+    #reader = TwitterCorpusReader(root, '1k_sample.json')
+    reader = TwitterCorpusReader('twitter', 'tweets.20150417.json')
     print()
     print("Complete tweet documents")
     print(SPACER)
@@ -214,7 +215,7 @@ def corpusreader_demo():
 
 
 ALL = range(12)
-DEMOS = ALL[9:10]
+DEMOS = ALL[11:]
 
 
 if __name__ == "__main__":