Merge pull request #166 from coderbhupendra/master

changed sort according to pyuca rules.
cltk · Mar 5, 2016 · b6c28cc · b6c28cc
2 parents b73a581 + e90222d
commit b6c28cc
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 2 deletions.
diff --git a/cltk/utils/philology.py b/cltk/utils/philology.py
@@ -11,6 +11,7 @@
 from nltk.text import ConcordanceIndex
 from nltk.tokenize.punkt import PunktLanguageVars
 import os
+import pyuca
 
 
 class Philology:
@@ -199,7 +200,8 @@ def return_concordance_all(self, tokens):
         of lists.
         """
 
-        tokens = sorted(tokens)  #! is the list order preserved?
+        coll = pyuca.Collator()
+        tokens = sorted(tokens, key=coll.sort_key)  #! is the list order preserved?
 
         concordance_list = []
         for token in tokens:

diff --git a/setup.py b/setup.py
@@ -28,7 +28,8 @@
                       'regex',
                       'whoosh',
                       'fuzzywuzzy',
-                      'python-Levenshtein'],
+                      'python-Levenshtein',
+                      'pyuca'],
     keywords=['nlp', 'nltk', 'greek', 'latin'],
     license='MIT',
     long_description="The Classical Language Toolkit (CLTK) is a framework for natural language processing for Classical languages.",  # pylint: disable=C0301