diabetesprevalence data #10

.Rbuildignore

@@ -5,7 +5,6 @@
 ^\.travis.yml
 ^\_pkgdown.yml
 ^LICENSE
-^data/.
 ^vignettes/.
 ^logo.png
 ^BioMathlogo.svg

R/data.R

@@ -0,0 +1,8 @@
+#' 5002 publications on diabetes prevalence
+#'
+#' A dataset containing 5002 publications exported from a Citavi project.
+#'
+#' @format A data frame with 5002 rows and 25 variables.
+#' @usage data(diabetesprevalence)
+"diabetesprevalence"
+

R/detect_language.R

@@ -12,14 +12,15 @@
 #'
 #' @details
 #' `r lifecycle::badge("experimental")` \cr
-#' Currently this only works for files that were generated while Citavi
-#' was set to "English" so that column names are "Short Title" etc.
+#' The underyling core function determining the language is \code{textcat::textcat()}.
 #'
 #' @examples
-#' path <- example_xlsx("3dupsin5refs.xlsx")
-#' read_Citavi_xlsx(path) %>%
-#'    detect_language() %>%
-#'    dplyr::select(Title, Abstract, det_lang, det_lang_wanted)
+#' CitDat <- CitaviR::diabetesprevalence %>%
+#'   dplyr::slice(1952:1955, 4390:4393)
+#'
+#' CitDat %>%
+#'   detect_language() %>%
+#'   dplyr::select(Abstract, det_lang, det_lang_wanted)
 #'
 #' @return A tibble containing at least one additional column: \code{det_lang}.
 #' @importFrom textcat textcat
@@ -29,6 +30,18 @@
 #'
 detect_language <- function (CitDat, fieldsToDetectIn = c("Abstract"), wantedLanguage = c("english")) {
 
+  # stop if empty arguments -------------------------------------------
+  if (is.null(all_of(fieldsToDetectIn))) {
+    stop("'fieldsToDetectIn' must not be NULL/NA.")
+  }
+
+
+  # check if fieldsToDetectIn are present -----------------------------------
+  if (!all_of(fieldsToDetectIn %in% names(CitDat))) {
+    stop(paste("Could not be found in dataset column names:\n",
+               fieldsToDetectIn[fieldsToDetectIn %not_in% names(CitDat)]))
+  }
+
 
   # collapse fieldsToDetectIn -----------------------------------------------
   CitDat <- CitDat %>%

_pkgdown.yml

@@ -51,7 +51,8 @@ reference:
   - read_Citavi_xlsx
   - write_Citavi_xlsx
 
-- title: Utility
+- title: Utility & Data
   contents:
   - '`%not_in%`'
   - example_xlsx
+  - diabetesprevalence

data-raw/diabetesprevalence.R

@@ -0,0 +1,12 @@
+suppressWarnings(
+  diabetesprevalence <-
+    CitaviR::read_Citavi_xlsx(
+      path = "data-raw/diabetesprevalence.xlsx",
+      keepMarksCols = TRUE,
+      useYearDerived = TRUE,
+      setSuggestedColOrder = TRUE,
+      setSuggestedColTypes = TRUE
+    )
+)
+
+usethis::use_data(diabetesprevalence, overwrite = TRUE, internal = FALSE)