Added line to replace multiple whitespace characters in full text by a single regular whitespace

R/dfm_gen.R

@@ -32,7 +32,8 @@ dfm_gen <- function(out,words = '999', text = c("lemmas","full")) {
                         str_replace_na(out$`_source.text`, replacement = " "),
                         sep = " ") %>%
       # Remove html tags
-      str_replace_all("<.*?>", " ")
+      str_replace_all("<.*?>", " ") %>%
+      str_replace_all("\\s+"," ")
   }
   # out$codes <- out$`_source.codes.majorTopic` %>%
   out <- out %>%