From 37df81b8ff8900b334aef9ed1dbe167fc25c4360 Mon Sep 17 00:00:00 2001
From: Erik de Vries <erik@devries.pm>
Date: Sun, 30 Dec 2018 20:20:38 +0100
Subject: [PATCH] ud_update: fixed merged output field to always contain an
 (extra) dot (period) at the end of the document

---
 R/ud_update.R | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/R/ud_update.R b/R/ud_update.R
index 602101b..a2e6bb0 100644
--- a/R/ud_update.R
+++ b/R/ud_update.R
@@ -42,12 +42,14 @@ ud_update <- function(out, localhost = T, udmodel, es_super = .rs.askForPassword
                       out$`_source.preteaser`,
                       out$`_source.teaser`,
                       out$`_source.text`,
+                      '.',
                       sep = ". ") %>%
     # Remove html tags, and multiple consequent whitespaces
     str_replace_all("<.{0,20}?>", " ") %>%
     str_replace_all('(\\. ){2,}', '. ') %>%
     str_replace_all('([!?.])\\.','\\1') %>%
     str_replace_all("\\s+"," ")
+  # out <- filter(out, nchar(merged) > 1)
   par_proc <- function(row, out, udmodel) {
     doc <- out[row,]
     ud <- as.data.frame(udpipe_annotate(udmodel, x = doc$merged, parser = "default", doc_id = doc$`_id`)) %>%