Merge branch 'parseri' into test

nltk/downloader.py

@@ -840,8 +840,11 @@ class Downloader(object):
             for i, child_id in enumerate(collection.children):
                 if child_id in self._packages:
                     collection.children[i] = self._packages[child_id]
-                if child_id in self._collections:
+                elif child_id in self._collections:
                     collection.children[i] = self._collections[child_id]
+                else:
+                    print('removing collection member with no package: {}'.format(child_id))
+                    del collection.children[i]
 
         # Fill in collection.packages for each collection.
         for collection in self._collections.values():

nltk/parse/pchart.py

@@ -212,7 +212,7 @@ class BottomUpProbabilisticChartParser(ParserI):
         # Initialize the chart.
         for edge in bu_init.apply(chart, grammar):
             if self._trace > 1:
-                print('  %-50s [%s]' % (chart.pp_edge(edge,width=2),
+                print('  %-50s [%s]' % (chart.pretty_format_edge(edge,width=2),
                                         edge.prob()))
             queue.append(edge)
 
@@ -227,7 +227,7 @@ class BottomUpProbabilisticChartParser(ParserI):
             # Get the best edge.
             edge = queue.pop()
             if self._trace > 0:
-                print('  %-50s [%s]' % (chart.pp_edge(edge,width=2),
+                print('  %-50s [%s]' % (chart.pretty_format_edge(edge,width=2),
                                         edge.prob()))
 
             # Apply BU & FR to it.
@@ -294,7 +294,7 @@ class BottomUpProbabilisticChartParser(ParserI):
             split = len(queue)-self.beam_size
             if self._trace > 2:
                 for edge in queue[:split]:
-                    print('  %-50s [DISCARDED]' % chart.pp_edge(edge,2))
+                    print('  %-50s [DISCARDED]' % chart.pretty_format_edge(edge,2))
             del queue[:split]
 
 class InsideChartParser(BottomUpProbabilisticChartParser):

nltk/parse/stanford.py

@@ -73,7 +73,7 @@ class StanfordParser(ParserI):
 
     def __init__(self, path_to_jar=None, path_to_models_jar=None,
                  model_path='edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz',
-                 encoding='UTF-8', verbose=False, java_options='-mx1000m'):
+                 encoding='utf8', verbose=False, java_options='-mx1000m'):
 
         self._stanford_jar = find_jar(
             self._JAR, path_to_jar,

nltk/tag/stanford.py

@@ -36,7 +36,7 @@ class StanfordTagger(TaggerI):
     _SEPARATOR = ''
     _JAR = ''
 
-    def __init__(self, path_to_model, path_to_jar=None, encoding='ascii', verbose=False, java_options='-mx1000m'):
+    def __init__(self, path_to_model, path_to_jar=None, encoding='utf8', verbose=False, java_options='-mx1000m'):
 
         if not self._JAR:
             warnings.warn('The StanfordTagger class is not meant to be '

nltk/tokenize/stanford.py

@@ -36,7 +36,7 @@ class StanfordTokenizer(TokenizerI):
 
     _JAR = 'stanford-postagger.jar'
 
-    def __init__(self, path_to_jar=None, encoding='UTF-8', options=None, verbose=False, java_options='-mx1000m'):
+    def __init__(self, path_to_jar=None, encoding='utf8', options=None, verbose=False, java_options='-mx1000m'):
         self._stanford_jar = find_jar(
             self._JAR, path_to_jar,
             env_vars=('STANFORD_POSTAGGER',),