Merge branch 'develop' into twitter

nltk/internals.py

@@ -592,6 +592,23 @@ def find_jar_iter(name_pattern, path_to_jar=None, env_vars=(),
                                 print('[Found %s: %s]' % (name_pattern, cp))
                             yielded = True
                             yield cp
+                    # The case where user put directory containing the jar file in the classpath 
+                    if os.path.isdir(cp):
+                        if not is_regex:
+                            if os.path.isfile(os.path.join(cp,name_pattern)):
+                                if verbose:
+                                    print('[Found %s: %s]' % (name_pattern, cp))
+                                yielded = True
+                                yield os.path.join(cp,name_pattern)
+                        else:
+                            # Look for file using regular expression 
+                            for file_name in os.listdir(cp):
+                                if re.match(name_pattern,file_name):
+                                    if verbose:
+                                        print('[Found %s: %s]' % (name_pattern, os.path.join(cp,file_name)))
+                                    yielded = True
+                                    yield os.path.join(cp,file_name)
+                                
             else:
                 jar_env = os.environ[env_var]
                 jar_iter = ((os.path.join(jar_env, path_to_jar) for path_to_jar in os.listdir(jar_env))

nltk/parse/dependencygraph.py

@@ -465,7 +465,7 @@ class DependencyGraph(object):
         for n in nx_nodelist:
             self.nx_labels[n] = self.nodes[n]['word']
 
-        g = NX.XDiGraph()
+        g = NX.MultiDiGraph()
         g.add_nodes_from(nx_nodelist)
         g.add_edges_from(nx_edgelist)
 
@@ -552,13 +552,11 @@ def cycle_finding_demo():
     dg = DependencyGraph(treebank_data)
     print(dg.contains_cycle())
     cyclic_dg = DependencyGraph()
-    top = {'word': None, 'deps': [1], 'rel': 'TOP', 'address': 0}
-    child1 = {'word': None, 'deps': [2], 'rel': 'NTOP', 'address': 1}
-    child2 = {'word': None, 'deps': [4], 'rel': 'NTOP', 'address': 2}
-    child3 = {'word': None, 'deps': [1], 'rel': 'NTOP', 'address': 3}
-    child4 = {'word': None, 'deps': [3], 'rel': 'NTOP', 'address': 4}
-    cyclic_dg.nodelist = [top, child1, child2, child3, child4]
-    cyclic_dg.root = top
+    cyclic_dg.add_node({'word': None, 'deps': [1], 'rel': 'TOP', 'address': 0})
+    cyclic_dg.add_node({'word': None, 'deps': [2], 'rel': 'NTOP', 'address': 1})
+    cyclic_dg.add_node({'word': None, 'deps': [4], 'rel': 'NTOP', 'address': 2})
+    cyclic_dg.add_node({'word': None, 'deps': [1], 'rel': 'NTOP', 'address': 3})
+    cyclic_dg.add_node({'word': None, 'deps': [3], 'rel': 'NTOP', 'address': 4})
     print(cyclic_dg.contains_cycle())
 
 treebank_data = """Pierre  NNP     2       NMOD

nltk/tag/__init__.py

@@ -83,7 +83,7 @@ from nltk.data import load
 # Standard treebank POS tagger
 _POS_TAGGER = 'taggers/maxent_treebank_pos_tagger/english.pickle'
 
-def pos_tag(tokens):
+def pos_tag(tokens, tagset=None):
     """
     Use NLTK's currently recommended part of speech tagger to
     tag the given list of tokens.
@@ -101,6 +101,8 @@ def pos_tag(tokens):
     :rtype: list(tuple(str, str))
     """
     tagger = load(_POS_TAGGER)
+    if tagset:
+        return [(token, map_tag('en-ptb', tagset, tag)) for (token, tag) in tagger.tag(tokens)]
     return tagger.tag(tokens)
 
 def pos_tag_sents(sentences):

nltk/tag/crf.py

@@ -24,7 +24,7 @@ class CRFTagger(TaggerI):
     """
     A module for POS tagging using CRFSuite https://pypi.python.org/pypi/python-crfsuite
     
-    >>> from nltk.tag.crf import CRFTagger
+    >>> from nltk.tag import CRFTagger
     >>> ct = CRFTagger()
  
     >>> train_data = [[('University','Noun'), ('is','Verb'), ('a','Det'), ('good','Adj'), ('place','Noun')],

nltk/tag/hunpos.py

@@ -33,7 +33,7 @@ class HunposTagger(TaggerI):
 
     Example:
 
-        >>> from nltk.tag.hunpos import HunposTagger
+        >>> from nltk.tag import HunposTagger
         >>> ht = HunposTagger('en_wsj.model')
         >>> ht.tag('What is the airspeed of an unladen swallow ?'.split())
         [('What', 'WP'), ('is', 'VBZ'), ('the', 'DT'), ('airspeed', 'NN'), ('of', 'IN'), ('an', 'DT'), ('unladen', 'NN'), ('swallow', 'VB'), ('?', '.')]