From 75c1413bd74b9665a53edad587b7b2c22b2079d0 Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Mon, 4 Mar 2024 15:05:01 +0100
Subject: [PATCH] address comments

---
 R/data_summary.R    | 13 +++++++++----
 man/data_summary.Rd |  2 +-
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/R/data_summary.R b/R/data_summary.R
index bddd360ca..d604b2fb5 100644
--- a/R/data_summary.R
+++ b/R/data_summary.R
@@ -8,7 +8,7 @@
 #' @param by Optional character string, indicating the name of a variable in `x`.
 #' If supplied, the data will be split by this variable and summary statistics
 #' will be computed for each group.
-#' @param include_na Logical, if `TRUE`, missing values are included as a level
+#' @param include_na Logical. If `TRUE`, missing values are included as a level
 #' in the grouping variable. If `FALSE`, missing values are omitted from the
 #' grouping variable.
 #' @param ... One or more named expressions that define the new variable name
@@ -88,19 +88,24 @@ data_summary.data.frame <- function(x, ..., by = NULL, include_na = TRUE) {
   } else {
     # sanity check - is "by" a character string?
     if (!is.character(by)) {
-      insight::format_error("Argument `by` must be a character string, indicating the name of a variable in the data.")
+      insight::format_error("Argument `by` must be a character string indicating the name of variables in the data.")
     }
     # is "by" in the data?
     if (!all(by %in% colnames(x))) {
       by_not_found <- by[!by %in% colnames(x)]
       insight::format_error(
-        paste0("Variable \"", by_not_found, "\" not found in the data."),
+        paste0(
+          "Variable",
+          ifelse(length(by_not_found) > 1, "s ", " "),
+          text_concatenate(by_not_found, enclose = "\""),
+          " not found in the data."
+        ),
         .misspelled_string(colnames(x), by_not_found, "Possibly misspelled?")
       )
     }
     # split data, add NA levels, if requested
     l <- lapply(x[by], function(i) {
-      if (include_na) {
+      if (include_na && anyNA(i)) {
         addNA(i)
       } else {
         i
diff --git a/man/data_summary.Rd b/man/data_summary.Rd
index ba3e6cd46..2c4408618 100644
--- a/man/data_summary.Rd
+++ b/man/data_summary.Rd
@@ -22,7 +22,7 @@ summary function \code{n()} can be used to count the number of observations.}
 If supplied, the data will be split by this variable and summary statistics
 will be computed for each group.}
 
-\item{include_na}{Logical, if \code{TRUE}, missing values are included as a level
+\item{include_na}{Logical. If \code{TRUE}, missing values are included as a level
 in the grouping variable. If \code{FALSE}, missing values are omitted from the
 grouping variable.}
 }