From f7f6c1aafe347bdb35b0af33bea5a3b25c37da0b Mon Sep 17 00:00:00 2001
From: crcruzr <cristian.alexander.cruz.rodriguez@umontreal.ca>
Date: Tue, 25 Jun 2024 17:35:42 -0400
Subject: [PATCH] minor changes

---
 internals.R | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
 create mode 100644 internals.R

diff --git a/internals.R b/internals.R
new file mode 100644
index 0000000..89c5ac4
--- /dev/null
+++ b/internals.R
@@ -0,0 +1,51 @@
+# Function to clean species list names
+#' @keywords internal
+standardize_names <- function(splist) {
+  fixed1 <- simple_cap(trimws(splist)) # all up
+  fixed2 <- gsub("cf\\.", "", fixed1)
+  fixed3 <- gsub("aff\\.", "", fixed2)
+  fixed4 <- trimws(fixed3) # remove trailing and leading space
+  fixed5 <- gsub("_", " ", fixed4) # change names separated by _ to space
+
+  # Hybrids
+  fixed6 <- gsub("(^x )|( x$)|( x )", " ", fixed5)
+  hybrids <- fixed5 == fixed6
+  if (!all(hybrids)) {
+    sp_hybrids <- splist[!hybrids]
+    warning(paste("The 'x' sign indicating hybrids have been removed in the",
+                  "following names before search:",
+                  paste(paste0("'", sp_hybrids, "'"), collapse = ", ")),
+            immediate. = TRUE, call. = FALSE)
+  }
+  # Merge multiple spaces
+  fixed7 <- gsub("(?<=[\\s])\\s*|^\\s+|\\s+$", "", fixed6, perl = TRUE)
+  return(fixed7)
+}
+
+#' @keywords internal
+simple_cap <- function(x) {
+  # Split each string into words, remove unnecessary white spaces, and convert to lowercase
+  words <- sapply(strsplit(x, "\\s+"), function(words) paste(tolower(words), collapse = " "))
+
+  # Capitalize the first letter of each word
+  capitalized <- sapply(strsplit(words, ""), function(word) {
+    if (length(word) > 0) {
+      word[1] <- toupper(word[1])
+    }
+    paste(word, collapse = "")
+  })
+
+  return(capitalized)
+}
+
+#' @keywords internal
+#'
+find_duplicates <- function(vector) {
+  # Count the frequency of each word
+  word_counts <- table(vector)
+  # Find words with a frequency greater than 1
+  duplicated_words <- names(word_counts[word_counts > 1])
+  return(duplicated_words)
+}
+
+