Fix for issue #1009

gensim/corpora/wikicorpus.py

@@ -258,7 +258,7 @@ class WikiCorpus(TextCorpus):
     >>> MmCorpus.serialize('wiki_en_vocab200k.mm', wiki) # another 8h, creates a file in MatrixMarket format plus file with id->word
 
     """
-    def __init__(self, fname, processes=None, lemmatize=utils.has_pattern(), dictionary=None, filter_namespaces=('0',)):
+    def __init__(self, fname, processes=None, lemmatize=True, dictionary=None, filter_namespaces=('0',)):
         """
         Initialize the corpus. Unless a dictionary is provided, this scans the
         corpus once, to determine its vocabulary.
@@ -274,7 +274,16 @@ def __init__(self, fname, processes=None, lemmatize=utils.has_pattern(), diction
         if processes is None:
             processes = max(1, multiprocessing.cpu_count() - 1)
         self.processes = processes
-        self.lemmatize = lemmatize
+        # if the user has set lemmatize flag as True, check if installed
+        if lemmatize == True:
+            try:
+                from pattern.en import parse
+                self.lemmatize = True
+            except ImportError:
+                self.lemmatize = False
+                warnings.warn("Pattern library is not installed, falling back to regexp based lemmatization.")
+        else:
+            self.lemmatize = False
         if dictionary is None:
             self.dictionary = Dictionary(self.get_texts())
         else:

gensim/utils.py

@@ -80,7 +80,6 @@ def smart_open(fname, mode='rb'):
 RE_HTML_ENTITY = re.compile(r'&(#?)([xX]?)(\w{1,8});', re.UNICODE)
 
 
-
 def synchronous(tlockname):
     """
     A decorator to place an instance-based lock around a method.
@@ -1003,19 +1002,6 @@ def pyro_daemon(name, obj, random_suffix=False, ip=None, port=None, ns_conf={}):
             daemon.requestLoop()
 
 
-def has_pattern():
-    """
-    Function to check if there is installed pattern library
-    """
-    pattern = False
-    try:
-        from pattern.en import parse
-        pattern = True
-    except ImportError:
-        warnings.warn("Pattern library is not installed, lemmatization won't be available.")
-    return pattern
-
-
 def lemmatize(content, allowed_tags=re.compile('(NN|VB|JJ|RB)'), light=False,
         stopwords=frozenset(), min_length=2, max_length=15):
     """
@@ -1037,10 +1023,10 @@ def lemmatize(content, allowed_tags=re.compile('(NN|VB|JJ|RB)'), light=False,
     ['rank/NN', 'study/VB', 'hard/RB']
 
     """
-    if not has_pattern():
-        raise ImportError("Pattern library is not installed. Pattern library is needed in order  \
-         to use lemmatize function")
-    from pattern.en import parse
+    try:
+        from pattern.en import parse
+    except ImportError:
+        warnings.warn("Pattern library is not installed, lemmatization won't be available.")
 
     if light:
         import warnings