fix #60

JuliaText · Mar 19, 2021 · d181905 · d181905
1 parent c924822
commit d181905
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/src/sentences/sentence_splitting.jl b/src/sentences/sentence_splitting.jl
@@ -120,7 +120,8 @@ function postproc_splits(sentences::AbstractString)
     sentences = replace(sentences, r"(\bMs\.)\n" => s"\1 ")
     sentences = replace(sentences, r"(\bMrs\.)\n" => s"\1 ")
 
-
+    # no sentence break in between two words with no punctuation
+    sentences=replace(sentences,r"([a-zA-Z0-9])\n([a-zA-Z0-9])"=>s"\1 \2")
 
 
     # possible TODO: filter excessively long / short sentences