Release version 4.2.0 (#769)

---------

Co-authored-by: Elizabeth Wenk <ehwenk@gmail.com>
Co-authored-by: yangsophieee <sophie.yang917@gmail.com>
Co-authored-by: Sophie Yang <78716301+yangsophieee@users.noreply.github.com>
Co-authored-by: David Coleman <50344360+dcol2804@users.noreply.github.com>
Co-authored-by: GillianKowalick <z5242422@ad.unsw.edu.au>
Co-authored-by: GillianKowalick <85142592+GillianKowalick@users.noreply.github.com>
Co-authored-by: Becca-90 <z3378134@ad.unsw.edu.au>

R/setup.R

@@ -38,10 +38,11 @@ metadata_create_template <- function(dataset_id,
   out$source$primary["key"] = dataset_id
   out$source$primary["bibtype"] = "Article"
 
+  collectors <- c("last_name", "given_name", "ORCID", "affiliation")
+
   out$contributors <- out$contributors$elements
-  out$contributors$data_collectors[c(exclude, "notes")] <- NULL
-  out$contributors$data_collectors[] <- "unknown"
-  out$contributors$data_collectors <- list(out$contributors$data_collectors)
+  out$contributors$data_collectors <- list(out$contributors$data_collectors$elements[collectors])
+  out$contributors$data_collectors[[1]][] <- "unknown"
   out$contributors[c("assistants", "austraits_curators")] <- "unknown"
 
   out$dataset <- out$dataset$values[c("data_is_long_format", "custom_R_code", "collection_date", "taxon_name", "location_name",
@@ -245,11 +246,11 @@ metadata_add_locations <- function(dataset_id, location_data) {
   location_name <- metadata_user_select_column("location_name", names(location_data))
 
   # From remaining variables, choose those to keep
-  location_sub <- dplyr::select(location_data, -!!location_name)
+  location_sub <- dplyr::select(dplyr::all_of(c("location_data"), -!!location_name))
   keep <- metadata_user_select_names(paste("Indicate all columns you wish to keep as distinct location_properties in ", dataset_id), names(location_sub))
 
   # Save and notify
-  metadata$locations <- dplyr::select(location_data, tidyr::one_of(keep)) %>%
+  metadata$locations <- dplyr::select(dplyr::all_of(c("location_data"), tidyr::one_of(keep))) %>%
             split(location_data[[location_name]]) %>% lapply(as.list)
 
   cat(sprintf("Following locations added to metadata for %s: %s\n\twith variables %s.\n\tPlease complete information in %s.\n\n", dataset_id, crayon::red(paste(names( metadata$locations), collapse = ", ")), crayon::red(paste(keep, collapse = ", ")), dataset_id %>% metadata_path_dataset_id()))
@@ -593,16 +594,44 @@ metadata_add_taxonomic_change <- function(dataset_id, find, replace, reason, tax
 #' @return yml file with multiple taxonmic updates added
 #' @export
 metadata_add_taxonomic_changes_list <- function(dataset_id, taxonomic_updates) {
-  
-  # read metadata
+
+  # Read metadata
   metadata <- read_metadata_dataset(dataset_id)
-
-  #read in dataframe of taxonomic changes, split into single-row lists, and add to metadata file
-  metadata$taxonomic_updates <- 
-    taxonomic_updates %>%
-    dplyr::group_split(.data$find) %>% lapply(as.list)
-
-  # write metadata
+
+  if (!all(is.na(metadata[["taxonomic_updates"]]))) {
+
+    existing_updates <- metadata[["taxonomic_updates"]] %>% util_list_to_df2()
+    already_exist <- c()
+
+    for (i in seq_len(nrow(taxonomic_updates))) {
+      # Check if the taxonomic update already exists
+      if (taxonomic_updates[i,]$find %in% existing_updates$find) {
+        # Overwrite existing taxonomic update if TRUE
+        existing_updates[which(existing_updates$find == taxonomic_updates[i,]$find),] <- taxonomic_updates[i,]
+        already_exist <- c(already_exist, taxonomic_updates[i,]$find)
+      } else {
+        # Otherwise, bind to end of existing taxonomic updates
+        existing_updates <- existing_updates %>% bind_rows(taxonomic_updates[i,])
+      }
+    }
+
+    if (length(already_exist) > 0) {
+      message(
+        sprintf(
+          green("%s") %+% red(" already exist(s) in `taxonomic_updates` and is being overwritten"),
+          paste(already_exist, collapse = ", ")
+      ))
+    }
+    # Write new taxonomic updates to metadata
+    metadata$taxonomic_updates <- existing_updates %>% dplyr::group_split(.data$find) %>% lapply(as.list)
+  } else {
+
+    # Read in dataframe of taxonomic changes, split into single-row lists, and add to metadata file
+    metadata$taxonomic_updates <- taxonomic_updates %>% dplyr::group_split(.data$find) %>% lapply(as.list)
+
+  }
+
+  # Write metadata
   write_metadata_dataset(metadata, dataset_id)
 }
 
@@ -813,11 +842,13 @@ build_find_taxon <- function(taxon_name, austraits, original_name = FALSE) {
 
   if (!original_name) {
     data <- data %>%
-      dplyr::select(name = taxon_name, .data$dataset_id) %>%
+      dplyr::select(dplyr::all_of("taxon_name", "dataset_id")) %>%
+      rename(name = taxon_name) %>%
       dplyr::distinct()
   } else {
     data <- data %>%
-      dplyr::select(name = original_name, .data$dataset_id) %>%
+      dplyr::select(dplyr::all_of("original_name", "dataset_id")) %>%
+      dplyr::rename(name = original_name) %>%
       dplyr::distinct()
   }
 

R/testdata.R

@@ -187,7 +187,7 @@ dataset_test_worker <-
       # allow some utf8 characters, those with accents over letters for foreign names
       # list of codes is here: http://www.utf8-chartable.de/
       # note c3 is needed because this is prefix for allowed UTF8 chars
-      exceptions <- c("ÁÅÀÂÄÆÃĀâíåæäãàáíčóöøéèłńl°êÜüùúû±µµ“”‘’-–—≈˜×")
+      exceptions <- c("ÁÅÀÂÄÆÃĀâíåæäãàáíÇčóöøéèłńl°êÜüùúû±µµ“”‘’-–—≈˜×")
 
       is_allowed <- i %in% charToRaw(exceptions)
       ! (is_ascii | is_allowed)
@@ -525,12 +525,14 @@ dataset_test_worker <-
           info = paste0(f, "-value types")
         )
 
-        if(length(value_type_cols) > 0)
-        expect_isin(
-          data[[value_type_cols]] %>% unique(),
-          schema$value_type$values %>% names,
-          info = paste0(f, "-value types columns")
-        )
+        if(length(value_type_cols) > 0){
+          for(v in value_type_cols)
+            expect_isin(
+              data[[v]] %>% unique(),
+              schema$value_type$values %>% names,
+              info = paste(f, v, "- value types columns")
+            )
+        }
 
         # Substitutions
         if (!is.na(metadata[["substitutions"]][1])) {

config/metadata.yml

@@ -1,7 +1,7 @@
 metadata:
   title: 'AusTraits: a curated plant trait database for the Australian flora'
   description: "AusTraits is a transformative database, containing measurements on the traits of Australia's plant taxa, standardised from hundreds of disconnected primary sources. While this repository contains the harmonised data, the raw data and code used to build the resource are also available on the project's GitHub repository,http://traitecoevo.github.io/austraits.build. Further information on the project is available in the associated publication and at the project website https://austraits.org."
-  version: "4.1.0"
+  version: "4.2.0"
   doi: 10.5281/zenodo.3568417
   structure_URI: https://github.com/traitecoevo/austraits.build
   geo_location: