Made use of taxize conditional, as it is now orphaned.

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: occCite
 Type: Package
 Title: Querying and Managing Large Biodiversity Occurrence Datasets
-Version: 0.5.7
+Version: 0.5.8
 Authors@R: c(
   person(given = "Hannah L.", family = "Owens", ,"[email protected]", role=c("aut","cre"),
     comment = c(ORCID = "0000-0003-0071-1745")),
@@ -38,7 +38,8 @@ Suggests:
     ape,
     bit64,
     knitr,
-    httr
+    httr,
+    taxize
 Imports:
     bib2df,
     BIEN,
@@ -47,7 +48,6 @@ Imports:
     lubridate,
     methods,
     rgbif (>= 3.1),
-    taxize,
     stringr,
     stats,
     leaflet,
@@ -61,4 +61,4 @@ Imports:
     DBI,
     waffle
 VignetteBuilder: knitr, rmarkdown
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2

NEWS.md

@@ -1,3 +1,8 @@
+# occCite 0.5.8
+
+* Moved `taxize` package to `Suggests`, as it is now orphaned.
+* `studyTaxonList()` allows user to skip taxonomic rectification, which relies on functions from `taxize` package. `studyTaxonList()` automatically skips taxonomic rectification if `taxize` is unavailable.
+
 # occCite 0.5.7
 
 * Fixed warning in `occCitation()` when getting GBIF citations

R/taxonRectification.R

@@ -10,6 +10,11 @@
 #' \code{\link[taxize]{gnr_resolve}}. See the
 #' \href{http://gni.globalnames.org/}{Global Names List} for more information.
 #'
+#' @param skipTaxize If \code{skipTaxize = TRUE}, occCite will skip taxonomic
+#'  rectification using taxize, which has been orphaned on CRAN. Setting this
+#'  option to `TRUE` will result in a check for the taxize package before taxonomic
+#'  rectification is attempted.
+#'
 #' @return A string with the closest match according to
 #' \code{\link[taxize]{gnr_resolve}}, and a list of taxonomic data sources that
 #' contain the matching name.
@@ -22,77 +27,109 @@
 #' )
 #' @export
 #'
-taxonRectification <- function(taxName = NULL, datasources = NULL) {
 
-  # Checks for source connectivity
-  tryCatch(
-    expr = sources <- taxize::gnr_datasources(),
-    error = function(e) {
-      message(paste("GNR server unreachable; please try again later. \n"))
-    }
-  )
+taxonRectification <- function(taxName = NULL, datasources = NULL,
+                               skipTaxize = FALSE) {
 
-  if (!exists("sources")) {
-    return(invisible(NULL))
+  if (!is.logical(skipTaxize)) {
+    warning(paste0(
+      "You have not used a logical operator to\n",
+      "specify whether occCite should skip taxize-\n",
+      "based taxonomic rectification."
+    ))
+    return(NULL)
+  }
+
+  if(!skipTaxize){
+    if(!requireNamespace("taxize", quietly = TRUE)){
+      warning(paste0("Package taxize unavailable. Skipping taxonomic rectification."))
+      skipTaxize <- TRUE
+    }
   }
 
-  # Are user-input databases included in data sources for Global Names Resolver?
-  if (!is.null(datasources)) {
-    for (db in datasources) {
-      notInDB <- character()
-      if (!(db %in% sources$title)) {
-        notInDB <- append(notInDB, db)
+  if(skipTaxize){
+    resolvedNames <- data.frame(taxName, taxName, "Not rectified.")
+    colnames(resolvedNames) <- c(
+      "Input Name",
+      "Best Match",
+      "Searched Taxonomic Databases w/ Matches"
+    )
+    resolvedNames <- as.data.frame(resolvedNames)
+
+    return(resolvedNames)
+
+
+  } else{
+    # Checks for source connectivity
+    tryCatch(
+      expr = sources <- taxize::gnr_datasources(),
+      error = function(e) {
+        message(paste("GNR server unreachable; please try again later. \n"))
+      }
+    )
+
+    if (!exists("sources")) {
+      return(invisible(NULL))
+    }
+
+    # Are user-input databases included in data sources for Global Names Resolver?
+    if (!is.null(datasources)) {
+      for (db in datasources) {
+        notInDB <- character()
+        if (!(db %in% sources$title)) {
+          notInDB <- append(notInDB, db)
+        }
       }
+      if (length(notInDB) != 0) {
+        warning(paste0(
+          "Following sources not found in\n",
+          "Global Names Index source list: ",
+          paste(notInDB, collapse = ", ")
+        ))
+      }
+      # Remove invalid sources from datasources
+      datasources <- datasources[!datasources %in% notInDB]
     }
-    if (length(notInDB) != 0) {
+
+    # Populating vector of data sources if no valid sources are supplied
+    if (length(datasources) == 0) {
       warning(paste0(
-        "Following sources not found in\n",
-        "Global Names Index source list: ",
-        paste(notInDB, collapse = ", ")
+        "No valid taxonomic data sources supplied.\n",
+        "Populating default list from all available sources."
       ))
+      datasources <- sources$title
     }
-    # Remove invalid sources from datasources
-    datasources <- datasources[!datasources %in% notInDB]
-  }
-
-  # Populating vector of data sources if no valid sources are supplied
-  if (length(datasources) == 0) {
-    warning(paste0(
-      "No valid taxonomic data sources supplied.\n",
-      "Populating default list from all available sources."
-    ))
-    datasources <- sources$title
-  }
 
-  # Resolving the user-input taxonomic names
-  sourceIDs <- sources$id[sources$title %in% datasources]
-  # Protects from error when gnr_resolve gets complete list of data sources
-  if (nrow(sources) == length(sourceIDs)) {
-    sourceIDs <- NULL
-  }
-  taxonomicDatabaseMatches <- vector("list")
-  temp <- taxize::gnr_resolve(sci = taxName, data_source_ids = sourceIDs)
-  if (nrow(temp) == 0) {
-    bestMatch <- "No match"
-    taxonomicDatabaseMatches <- "No match"
-    warning(paste(taxName,
-      " is not found in any of the taxonomic data sources specified.",
-      sep = ""
-    ))
-  } else {
-    bestMatch <- temp[order(temp$score), ]$matched_name[1]
-    matchingSources <- temp$data_source_title[temp$matched_name == bestMatch]
-    taxonomicDatabaseMatches <- paste(matchingSources, collapse = "; ")
-  }
+    # Resolving the user-input taxonomic names
+    sourceIDs <- sources$id[sources$title %in% datasources]
+    # Protects from error when gnr_resolve gets complete list of data sources
+    if (nrow(sources) == length(sourceIDs)) {
+      sourceIDs <- NULL
+    }
+    taxonomicDatabaseMatches <- vector("list")
+    temp <- taxize::gnr_resolve(sci = taxName, data_source_ids = sourceIDs)
+    if (nrow(temp) == 0) {
+      bestMatch <- "No match"
+      taxonomicDatabaseMatches <- "No match"
+      warning(paste(taxName,
+                    " is not found in any of the taxonomic data sources specified.",
+                    sep = ""
+      ))
+    } else {
+      bestMatch <- temp[order(temp$score), ]$matched_name[1]
+      matchingSources <- temp$data_source_title[temp$matched_name == bestMatch]
+      taxonomicDatabaseMatches <- paste(matchingSources, collapse = "; ")
+    }
 
-  # Building the results table
-  resolvedNames <- data.frame(taxName, bestMatch, taxonomicDatabaseMatches)
-  colnames(resolvedNames) <- c(
-    "Input Name",
-    "Best Match",
-    "Searched Taxonomic Databases w/ Matches"
-  )
-  resolvedNames <- as.data.frame(resolvedNames)
+    # Building the results table
+    resolvedNames <- data.frame(taxName, bestMatch, taxonomicDatabaseMatches)
+    colnames(resolvedNames) <- c(
+      "Input Name",
+      "Best Match",
+      "Searched Taxonomic Databases w/ Matches"
+    )
+    resolvedNames <- as.data.frame(resolvedNames)
 
-  return(resolvedNames)
+    return(resolvedNames)
+  }
 }

README.md

@@ -44,19 +44,19 @@ citation(package = "occCite")
 ```
 
     ## 
-    ## Owens H, Merow C, Maitner B, Kass J, Barve V, Guralnick R (2022).
+    ## Owens H, Merow C, Maitner B, Kass J, Barve V, Guralnick R (2024).
     ## _occCite: Querying and Managing Large Biodiversity Occurrence
     ## Datasets_. doi: 10.5281/zenodo.632770 (URL:
-    ## https://doi.org/10.5281/zenodo.632770), R package version 0.5.7,
+    ## https://doi.org/10.5281/zenodo.632770), R package version 0.5.8,
     ## <URL: https://CRAN.R-project.org/package=occCite>.
     ## 
     ## A BibTeX entry for LaTeX users is
     ## 
     ##   @Manual{,
     ##     title = {occCite: Querying and Managing Large Biodiversity Occurrence Datasets},
     ##     author = {Hannah Owens and Cory Merow and Brian Maitner and Jamie Kass and Vijay Barve and Robert Guralnick},
-    ##     year = {2022},
-    ##     note = {R package version 0.5.7},
+    ##     year = {2024},
+    ##     note = {R package version 0.5.8},
     ##     url = {https://CRAN.R-project.org/package=occCite},
     ##     doi = {10.5281/zenodo.632770},
     ##   }

cran-comments.md

@@ -1,11 +1,8 @@
 ## Update
 This is a package update. In this version, I have:
 
-* Fixed warning in `occCitation()` when getting GBIF citations
-* Updated date formatting using `format()` instead of `as.character()`
-* Updated test files to incorporate rgbif 3.8.0 output changes, make more efficient
-* In occResults, renamed "Dataset", "DatasetKey", and "DataService" to "datasetName", "datasetKey", "dataService", respectively.
-* Made an option for removing package citations.
+* Moved `taxize` package to `Suggests`, as it is now orphaned.
+* `studyTaxonList()` allows user to skip taxonomic rectification, which relies on functions from `taxize` package. `studyTaxonList()` automatically skips taxonomic rectification if `taxize` is unavailable.
 
 ## Test environments
 * local OS X 14.5 install, R 4.3.2 (with and without internet connection)
@@ -14,7 +11,10 @@ This is a package update. In this version, I have:
 * macOS-latest (on GitHub Actions), R 4.4.1
 
 ## R CMD check results
-0 errors | 0 warnings | 0 notes
+0 errors | 0 warnings | 1 notes
+
+Note: Suggests orphaned package: ‘taxize’
+- Use is conditional on presence of package. If taxize is absent, taxonomic rectification is skipped. This is noted in metadata and does not affect downstream processes.
 
 ## Downstream dependencies
 I ran tools::check_packages_in_dir() check on downstream dependencies of