[FIX] Adding some default stop words.

556ec1c4 · delanoe · 869bd484 · 556ec1c4
Commit 556ec1c4 authored May 10, 2016 by delanoe
Hide whitespace changes
Inline Side-by-side

Showing with 2 additions and 2 deletions

list_stop.py gargantext/util/toolchain/list_stop.py +2 -2

No files found.
--- a/gargantext/util/toolchain/list_stop.py
+++ b/gargantext/util/toolchain/list_stop.py
@@ -27,10 +27,10 @@ def is_stop_word(ngram, stop_words=None):
            # , "(.*)(\.)(.*)"         trop fort (enlève les sigles !)
            , "(.*)(\,)(.*)"
            , "(.*)(< ?/?p ?>)(.*)"       # marques de paragraphes
-            , "(.*)(study)(.*)"
+            , "(.*)(study|elsevier)(.*)"
            , "(.*)\b(xx|xi|xv)\b(.*)"
            , "(.*)(result)(.*)"
-            , "(.*)(année|nombre|moitié)(.*)"
+            , "(.*)(year|année|nombre|moitié)(.*)"
            , "(.*)(temps)(.*)"
            , "(.*)(%)(.*)"
            , "(.*)(\{)(.*)"