From 4cdd4f46eceb961a90ec60fd3577996f1ecafe97 Mon Sep 17 00:00:00 2001
From: Kate W <magpiedin@gmail.com>
Date: Tue, 12 Nov 2019 13:25:12 -0600
Subject: [PATCH] merge consecutive line-breaks

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

diff --git a/ocrMangle.R b/ocrMangle.R
index c62e106..c3d911f 100644
--- a/ocrMangle.R
+++ b/ocrMangle.R
@@ -37,7 +37,7 @@ for (i in 1:NROW(imagelist)) {
   
   # include filename & count of lines in row
   imagesOCR$image[i] <- imagelist[i]
-  imagesOCR$line_count[i] <- str_count(ocrText, "\n")
+  imagesOCR$line_count[i] <- str_count(ocrText, "\n+")
   
   # show progress
   print(paste(i, " - ", Sys.time()))
@@ -50,7 +50,7 @@ ocrText <- separate(imagesOCR, text,
                     into = paste0("Line", 
                                   seq(1:max(imagesOCR$line_count, na.rm = T))),
                     # into = seq(1:20),  # if need consistent NCOL
-                    sep = "\n",
+                    sep = "(\n)+",
                     extra = "merge", fill = "right")