Added documentation for WikiCorpus metadata. Fix #1161 (#1163)

piskvorky · Feb 24, 2017 · 5571e99 · 5571e99
1 parent c971411
commit 5571e99
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 0 deletions.
diff --git a/gensim/corpora/indexedcorpus.py b/gensim/corpora/indexedcorpus.py
@@ -69,6 +69,7 @@ def serialize(serializer, fname, corpus, id2word=None, index_fname=None, progres
            each saved document,
         * the `docbyoffset(offset)` method, which returns a document
           positioned at `offset` bytes within the persistent storage (file).
+        * metadata if set to true will ensure that serialize will write out article titles to a pickle file.
 
         Example:
 

diff --git a/gensim/corpora/wikicorpus.py b/gensim/corpora/wikicorpus.py
@@ -266,6 +266,7 @@ def __init__(self, fname, processes=None, lemmatize=utils.has_pattern(), diction
         If `pattern` package is installed, use fancier shallow parsing to get
         token lemmas. Otherwise, use simple regexp tokenization. You can override
         this automatic logic by forcing the `lemmatize` parameter explicitly.
+        self.metadata if set to true will ensure that serialize will write out article titles to a pickle file.
 
         """
         self.fname = fname