From df976e14db1eb31985483bd7a8a681bc2473c9af Mon Sep 17 00:00:00 2001
From: Henrique Sposito <henrique.sposito@graduateinstitute.ch>
Date: Fri, 23 Aug 2024 18:09:06 +0200
Subject: [PATCH] More fixes to sentence splitting when annotating texts

---
 R/text_tools.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/R/text_tools.R b/R/text_tools.R
index d8bec43..5c09aff 100644
--- a/R/text_tools.R
+++ b/R/text_tools.R
@@ -328,7 +328,7 @@ read_pdf <- function(path) {
 annotate_text <- function(v, level = "words") {
   doc_id <- sentence_id <- token_id <- token <- pos <- tag <- lemma <- entity <- NULL
   suppressWarnings(spacyr::spacy_initialize(model = "en_core_web_sm"))
-  v <- stringr::str_replace_all(v, "\\.\\,|\\. \\,|\\,\\.|\\, \\.", ".")
+  v <- stringr::str_replace_all(v, "\\.\\,|\\. \\,|\\,\\.|\\, \\.|\\.\\\n\\,", ".")
   parse <- spacyr::spacy_parse(v, tag = TRUE)
   suppressWarnings(spacyr::spacy_finalize())
   if (level == "sentences" | level == "sentence") {