Merge pull request nltk#1598 from chmeyer/fix/CHUNK_TAG_PATTERN

Fix/chunk tag pattern

nltk/chunk/regexp.py

@@ -831,7 +831,7 @@ def __repr__(self):
 # this should probably be made more strict than it is -- e.g., it
 # currently accepts 'foo'.
 CHUNK_TAG_PATTERN = re.compile(r'^((%s|<%s>)*)$' %
-                                ('[^\{\}<>]+',
+                                ('([^\{\}<>]|\{\d+,?\d*\}|\{\d*,?\d+\})+',
                                  '[^\{\}<>]+'))
 
 def tag_pattern2re_pattern(tag_pattern):

nltk/test/unit/test_chunk.py

@@ -0,0 +1,49 @@
+# -*- coding: utf-8 -*-
+from __future__ import absolute_import, unicode_literals
+import unittest
+
+from nltk import RegexpParser
+
+class TestChunkRule(unittest.TestCase):
+
+    def test_tag_pattern2re_pattern_quantifier(self):
+        """Test for bug https://github.com/nltk/nltk/issues/1597
+    
+        Ensures that curly bracket quantifiers can be used inside a chunk rule.
+        This type of quantifier has been used for the supplementary example
+        in http://www.nltk.org/book/ch07.html#exploring-text-corpora.
+        """    
+        sent = [('The', 'AT'), ('September-October', 'NP'), ('term', 'NN'), ('jury', 'NN'), ('had', 'HVD'), ('been', 'BEN'), ('charged', 'VBN'), ('by', 'IN'), ('Fulton', 'NP-TL'), ('Superior', 'JJ-TL'), ('Court', 'NN-TL'), ('Judge', 'NN-TL'), ('Durwood', 'NP'), ('Pye', 'NP'), ('to', 'TO'), ('investigate', 'VB'), ('reports', 'NNS'), ('of', 'IN'), ('possible', 'JJ'), ('``', '``'), ('irregularities', 'NNS'), ("''", "''"), ('in', 'IN'), ('the', 'AT'), ('hard-fought', 'JJ'), ('primary', 'NN'), ('which', 'WDT'), ('was', 'BEDZ'), ('won', 'VBN'), ('by', 'IN'), ('Mayor-nominate', 'NN-TL'), ('Ivan', 'NP'), ('Allen', 'NP'), ('Jr.', 'NP'), ('.', '.')] # source: brown corpus
+        cp = RegexpParser('CHUNK: {<N.*>{4,}}')
+        tree = cp.parse(sent)
+        assert tree.pformat() == """(S
+  The/AT
+  September-October/NP
+  term/NN
+  jury/NN
+  had/HVD
+  been/BEN
+  charged/VBN
+  by/IN
+  Fulton/NP-TL
+  Superior/JJ-TL
+  (CHUNK Court/NN-TL Judge/NN-TL Durwood/NP Pye/NP)
+  to/TO
+  investigate/VB
+  reports/NNS
+  of/IN
+  possible/JJ
+  ``/``
+  irregularities/NNS
+  ''/''
+  in/IN
+  the/AT
+  hard-fought/JJ
+  primary/NN
+  which/WDT
+  was/BEDZ
+  won/VBN
+  by/IN
+  (CHUNK Mayor-nominate/NN-TL Ivan/NP Allen/NP Jr./NP)
+  ./.)"""
+