From 563c864091f82dc1108bdb9e2ab279048627337d Mon Sep 17 00:00:00 2001
From: AG Damsbo <agdamsbo@pm.me>
Date: Fri, 14 Apr 2023 11:46:09 +0200
Subject: [PATCH] a new helper function has been introduced to help matching
 form names when special characters are in use.

---
 R/REDCap_split.r       |  8 ++++++--
 R/read_redcap_tables.R |  5 ++---
 R/utils.r              | 19 +++++++++++++++++--
 3 files changed, 25 insertions(+), 7 deletions(-)

diff --git a/R/REDCap_split.r b/R/REDCap_split.r
index f2d3497..5bd5b04 100644
--- a/R/REDCap_split.r
+++ b/R/REDCap_split.r
@@ -88,13 +88,17 @@ REDCap_split <- function(records,
   # Process user input
   records  <- process_user_input(records)
   metadata <-
-    as.data.frame(process_user_input(metadata)) # See issue #12
+    as.data.frame(process_user_input(metadata))
+
+  # Process repeat instrument names to match the redcap naming
+  records$redcap_repeat_instrument <- clean_redcap_name(records$redcap_repeat_instrument)
+
 
   # Get the variable names in the dataset
   vars_in_data <- names(records)
 
   # Match arg for forms
-  forms <- match.arg(forms)
+  forms <- match.arg(forms, c("repeating", "all"))
 
   # Check to see if there were any repeating instruments
   if (forms == "repeating" &&
diff --git a/R/read_redcap_tables.R b/R/read_redcap_tables.R
index 7841a36..9664d91 100644
--- a/R/read_redcap_tables.R
+++ b/R/read_redcap_tables.R
@@ -76,8 +76,7 @@ read_redcap_tables <- function(uri,
   # Removes any extra characters other than a-z, 0-9 and "_", to mimic raw
   # instrument names.
   if ("redcap_repeat_instrument" %in% names(d)) {
-    d$redcap_repeat_instrument <-
-    gsub("[^a-z0-9_]", "", gsub(" ", "_", tolower(d$redcap_repeat_instrument)))
+    d$redcap_repeat_instrument <- clean_redcap_name(d$redcap_repeat_instrument)
   }
 
   # Getting metadata
@@ -93,7 +92,7 @@ read_redcap_tables <- function(uri,
   l <- REDCap_split(d,
                     m,
                     forms = split_forms,
-                    primary_table_name = "nonrepeating")
+                    primary_table_name = "")
 
   # Sanitizing split list by removing completely empty rows apart from colnames
   # in "generics"
diff --git a/R/utils.r b/R/utils.r
index b005777..398c639 100644
--- a/R/utils.r
+++ b/R/utils.r
@@ -83,9 +83,24 @@ focused_metadata <- function(metadata, vars_in_data) {
 
 }
 
+#' clean_redcap_name
+#' @description
+#' Stepwise removal on non-alphanumeric characters, trailing white space,
+#' substitutes spaces for underscores and converts to lower case.
+#' Trying to make up for different naming conventions.
+#'
+#' @param x vector or data frame for cleaning
+#'
+#' @return vector or data frame, same format as input
+#' @export
+#'
+clean_redcap_name <- function(x){
 
-
-# function to convert the list of dataframes
+  gsub(" ", "_",
+       gsub("[' ']$","",
+           gsub("[^a-z0-9' '_]", "",
+                tolower(x)
+       )))}
 
 
 #' Sanitize list of data frames