0.9.4

Fix for dawg node id

.gitignore

@@ -9,4 +9,5 @@ sampledawg.py
 dist
 lexpy.egg-info
 build
-.venv
+.venv
+dawg_sample.py

README.md

@@ -43,6 +43,7 @@ Lexpy version `0.9.3` is recommended and it supports both Python 2 and Python 3.
 | Search using wildcard expression                                                                                              	| `search('a?b*')`                          	| `search('a?b*)`                           	|
 | Search for prefix matches                                                                                                     	| `search_with_prefix('bar')`               	| `search_with_prefix('bar')`               	|
 | Search for similar words within  given edit distance. Here, the notion of edit distance  is same as Levenshtein distance (LD) 	| `search_within_distance('apble', dist=1)` 	| `search_within_distance('apble', dist=1)` 	|
+| Get the number of nodes in the automaton 	| `len(trie)` 	| `len(dawg)` 	|
 
 
 # Examples
@@ -100,7 +101,7 @@ with open('/path/to/file.txt', 'r') as infile:
 1. Check if exists using the `in` operator
 
 ```python
-print 'ampyx' in trie
+print('ampyx' in trie)
 True
 ```
 

lexpy/__init__.py

@@ -1,4 +1,4 @@
-
+__version__ = "0.9.4"
 
 
 

lexpy/dawg.py

@@ -47,8 +47,9 @@ def add(self, word):
         for letter in word[common_prefix_index:]:
             _id = self._id + 1
             node.add_child(letter, _id)
-            self.__unchecked_nodes.append((node, letter, node[letter]))
-            node = node[letter]
+            self.__unchecked_nodes.append((node, letter, node.children[letter]))
+            node = node.children[letter]
+            self._id = _id
 
         node.eow = True
         self._num_of_words += 1
@@ -61,7 +62,7 @@ def _reduce(self, to):
         for i in range(len(self.__unchecked_nodes)-1, to-1, -1):
             (parent, letter, child) = self.__unchecked_nodes[i]
             if child in self.__minimized_nodes:
-                parent.children[letter] = child
+                parent.children[letter] = self.__minimized_nodes[child]
             else:
                 self.__minimized_nodes[child] = child
             self.__unchecked_nodes.pop()

setup.py

@@ -4,6 +4,8 @@
 
 from setuptools import setup, find_packages
 
+from lexpy import __version__
+
 LONG_DESCRIPTION = 'A lexicon is a data-structure which stores a set of words. ' \
                    'The difference between a dictionary and a lexicon is that in a lexicon there are no values associated with the words. ' \
                    'A lexicon is similar to a list of words or a set, but the internal representation is different and optimized for faster searches(of words, prefixes and wildcard patterns). ' \
@@ -18,7 +20,7 @@
 DESCRIPTION = ('Python package for lexicon.')
 LICENSE = 'GNU GPLv3'
 URL = 'https://github.com/aosingh/lexpy'
-VERSION = '0.9.3'
+VERSION = __version__
 
 PACKAGES = ['lexpy']
 
@@ -33,10 +35,10 @@
     'Topic :: Text Processing :: Indexing',
     'License :: OSI Approved :: GNU General Public License v3 (GPLv3)',
     'Programming Language :: Python :: 2.7',
-    'Programming Language :: Python :: 3.3',
-    'Programming Language :: Python :: 3.4',
     'Programming Language :: Python :: 3.5',
     'Programming Language :: Python :: 3.6',
+    'Programming Language :: Python :: 3.7',
+    'Programming Language :: Python :: 3.8',
     'Operating System :: POSIX :: Linux',
     'Operating System :: Unix',
     'Operating System :: Microsoft :: Windows',