From 522c872dbafbf1a15635eab2951bd4a315ad7ecd Mon Sep 17 00:00:00 2001
From: Erik de Vries <erik@devries.pm>
Date: Mon, 4 Mar 2019 14:21:04 +0100
Subject: [PATCH] out_parser: moved cleaning regex to end of pipeline, to
 prevent collissions with other (mandatory) regex cleaning

---
 R/out_parser.R | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/R/out_parser.R b/R/out_parser.R
index fbf8966..7d0b684 100644
--- a/R/out_parser.R
+++ b/R/out_parser.R
@@ -68,10 +68,10 @@ out_parser <- function(out, field, clean = F) {
   ### Old regex, used for duplicate detection:
   # \\S*?[0-9@#$%]+[^\\s!?.,;:]*
   out$merged <- out$merged %>%
-    {if(clean == T) str_replace_all(.,"\\S*?[0-9@#$%]+([^\\s!?.,;:]|[!?.,:;]\\S)*", "")  else . } %>%
     str_replace_all("<.{0,20}?>", " ") %>%
     str_replace_all('(\\. ){2,}', '. ') %>%
     str_replace_all('([!?.])\\.','\\1') %>%
-    str_replace_all("\\s+"," ")
+    str_replace_all("\\s+"," ") %>%
+    {if(clean == T) str_replace_all(.,"\\S*?[0-9@#$%]+([^\\s!?.,;:]|[!?.,:;]\\S)*", "")  else . }
   return(out)
 }