pep8 formatting fix

piskvorky · Nov 30, 2015 · 602c0c7 · 602c0c7
1 parent b8224fe
commit 602c0c7
Showing 1 changed file with 9 additions and 6 deletions.
diff --git a/gensim/corpora/wikicorpus.py b/gensim/corpora/wikicorpus.py
@@ -180,9 +180,10 @@ def get_namespace(tag):
     return namespace
 _get_namespace = get_namespace
 
+
 def extract_pages(f, filter_namespaces=False):
     """
-    Extract pages from MediaWiki database dump.
+    Extract pages from a MediaWiki database dump = open file-like object `f`.
 
     Return an iterable over (str, str, str) which generates (title, content, pageid) triplets.
 
@@ -224,6 +225,7 @@ def extract_pages(f, filter_namespaces=False):
             elem.clear()
 _extract_pages = extract_pages  # for backward compatibility
 
+
 def process_article(args):
     """
     Parse a wikipedia article, returning its content as a list of tokens
@@ -293,7 +295,7 @@ def get_texts(self):
         # is dumb and would load the entire input into RAM at once...
         ignore_namespaces = 'Wikipedia Category File Portal Template MediaWiki User Help Book Draft'.split()
         for group in utils.chunkize(texts, chunksize=10 * self.processes, maxsize=1):
-            for tokens, title, pageid in pool.imap(process_article, group): # chunksize=10):
+            for tokens, title, pageid in pool.imap(process_article, group):  # chunksize=10):
                 articles_all += 1
                 positions_all += len(tokens)
                 # article redirects and short stubs are pruned here
@@ -307,8 +309,9 @@ def get_texts(self):
                     yield tokens
         pool.terminate()
 
-        logger.info("finished iterating over Wikipedia corpus of %i documents with %i positions"
-            " (total %i articles, %i positions before pruning articles shorter than %i words)" %
-            (articles, positions, articles_all, positions_all, ARTICLE_MIN_WORDS))
-        self.length = articles # cache corpus length
+        logger.info(
+            "finished iterating over Wikipedia corpus of %i documents with %i positions"
+            " (total %i articles, %i positions before pruning articles shorter than %i words)",
+            articles, positions, articles_all, positions_all, ARTICLE_MIN_WORDS)
+        self.length = articles  # cache corpus length
 # endclass WikiCorpus