Add taxonomic coverage and EML version to summary metadata

.Rbuildignore

@@ -3,3 +3,5 @@
 ^.*\.Rproj$
 ^\.Rproj\.user$
 ^\.travis\.yml$
+^LICENSE$
+^inst/Pres$

DESCRIPTION

@@ -8,17 +8,32 @@ Authors@R: c(
   person("Irene", "Steves", comment = "https://github.com/isteves", role = "aut"),
   person("Mitchell", "Maier", email = "[email protected]", role = "aut"))
 Maintainer: Julien Brun <[email protected]>
-Description: Tools to download data and metadata from DataONE (https://www.dataone.org) and load this information in R. 
+Description: Tools to download data and metadata from DataONE (https://www.dataone.org) and load this information in R.
 License: Apache License (== 2.0)
-RoxygenNote: 6.1.1
-Imports: dataone, dplyr, eml2, emld, lubridate, purrr, readr, stats, stringr, tibble, tidyr
-Remotes: cboettig/eml2,
-         cboettig/emld,
-         DataONEorg/rdataone
-Suggests: testthat,
+URL: https://github.com/nceas/metajam
+BugReports: https://github.com/nceas/metajam/issues
+Imports:
+    dataone,
+    dplyr,
+    eml2,
+    emld,
+    lubridate,
+    purrr,
+    readr,
+    stats,
+    stringr,
+    tibble,
+    tidyr
+Remotes:
+    cboettig/eml2,
+    cboettig/emld,
+    DataONEorg/rdataone
+Suggests:
+    testthat,
     knitr,
     rmarkdown,
     udunits2
+Encoding: UTF-8
 VignetteBuilder: knitr
-URL: https://github.com/nceas/metajam
-BugReports: https://github.com/nceas/metajam/issues
+Roxygen: list(markdown = TRUE)
+RoxygenNote: 6.1.1

NAMESPACE

@@ -12,10 +12,12 @@ import(readr)
 import(stringr)
 import(tidyr)
 importFrom(dataone,CNode)
-importFrom(dataone,getSystemMetadata)
 importFrom(dataone,query)
 importFrom(emld,as_emld)
 importFrom(lubridate,ymd_hms)
 importFrom(purrr,"%||%")
 importFrom(stats,setNames)
+importFrom(stringr,str_trim)
 importFrom(tibble,enframe)
+importFrom(utils,URLdecode)
+importFrom(utils,write.csv)

R/check_version.R

@@ -2,73 +2,74 @@
 #'
 #' This function takes an identifier and checks to see if it has been obsoleted.
 #'
-#' @param pid (character) The persistent identifier of a data, metadata, or resource map object on a DataONE member node
-#' @param formatType (character) Optional. The format type to return (DATA, METADATA, RESOURCE)
+#' @param pid (character) The persistent identifier of a data, metadata, or resource map object on a DataONE member node.
+#' @param formatType (character) Optional. The format type to return (DATA, METADATA, RESOURCE).
 #'
-#' @importFrom dataone CNode getSystemMetadata
-#' @import stringr
+#' @return A data.frame of object version PIDs and related information.
+#'
+#' @import dataone
 #' @import dplyr
+#' @import stringr
 #'
 #' @export
 #'
 #' @examples
 #' \dontrun{
 #' # Most data URL's and identifiers work
 #' check_version("https://cn.dataone.org/cn/v2/resolve/urn:uuid:a2834e3e-f453-4c2b-8343-99477662b570")
-#' 
+#'
 #' # Returns a warning if several identifiers are returned:
 #' check_version(
 #'   "https://pasta.lternet.edu/package/data/eml/edi/195/2/51abf1c7a36a33a2a8bb05ccbf8c81c6"
 #'   )
 #' check_version("doi:10.18739/A2ZF6M")
-#' 
+#'
 #' # You can specify a formatType (metadata, data, resource)
 #' check_version("doi:10.18739/A2ZF6M", formatType = "metadata")
-#' 
+#'
 #' # Returns a warning if the identifier has been obsoleted
 #' check_version("doi:10.18739/A2HF7Z", formatType = "metadata")
-#' 
+#'
 #' # Returns an error if no matching identifiers are found
 #' check_version("a_test_pid")
 #' }
-#'
 
-check_version <- function(pid, formatType = NULL){
-  
+check_version <- function(pid, formatType = NULL) {
+
   # check that pid is of type character
   if (!all(is.character(pid), all(nchar(pid) > 0))) {
     stop("Argument 'pids' must be character class with non-zero number of characters.")
   }
-  
-  while(nchar(pid) > 5) {
+
+  while (nchar(pid) > 5) {
     results <- suppressMessages(
       dataone::query(dataone::CNode(),
                      list(q = sprintf('identifier:"%s"', pid),
                           fl = "identifier, dateUploaded, formatType, obsoletedBy, resourceMap"),
                      as = "data.frame")
     )
-    #if results is null or empty dataframe, remove part of the URI 
+    #if results is null or empty dataframe, remove part of the URI
     if (is.null(results) || nrow(results) == 0) {
       pid <- gsub("^[^/=]+[/=]*", "", pid)
-      
+
     } else {
       #what to do if multiple are returned
       break
     }
   }
-  
-  if(nrow(results) == 0){
+
+  if (nrow(results) == 0) {
     stop("No matching identifiers were found.")
   }
-  
+
   # filter out extra types (resource map/etc with similar pid)
-  if(!is.null(formatType)){
+  if (!is.null(formatType)) {
     formatType <- toupper(formatType)
     results <- results[results$formatType == formatType,]
   }
-  
-  if(nrow(results) == 1){
-    if(is.null(results$obsoletedBy) || is.na(results$obsoletedBy)){
+
+  if (nrow(results) == 1) {
+    if (is.null(results$obsoletedBy) || is.na(results$obsoletedBy)) {
       message("\n",
               results$identifier,
               "\nis the latest version for identifier\n",
@@ -79,6 +80,6 @@ check_version <- function(pid, formatType = NULL){
   } else {
     warning("Several identifiers are associated with ", pid)
   }
-  
+
   return(results)
 }