[fix] stoplist: 4 regex corrected

a982e36a · Romain Loth · 2c5405a7 · a982e36a
Commit a982e36a authored Oct 05, 2016 by Romain Loth
Show whitespace changes
Inline Side-by-side

Showing with 4 additions and 5 deletions

list_stop.py gargantext/util/toolchain/list_stop.py +4 -5

No files found.
--- a/gargantext/util/toolchain/list_stop.py
+++ b/gargantext/util/toolchain/list_stop.py
@@ -37,11 +37,10 @@ def is_stop_word(ngram, stop_words=None):
            , "(.*)(différent)(.*)"
            , "(.*)(travers)(.*)"
            # academic stamps
-            , ".*\belsevier\b.*"
+            , ".*elsevier.*"
-            , ".*\bwiley\b.*"
+            , ".*wiley.*"
-            , ".*\bspringer\b.*"
+            , ".*springer.*"
-            , ".*university press\b.*"
+            , ".*university press.*"
-            , ".*\bstudy\b.*"
            # academic terms when alone ~~> usually not informative
            , "hypothes[ie]s$"
            , "analys[ie]s$"