Merge branch 'master' into async

.github/workflows/R-check.yaml

@@ -14,7 +14,7 @@ jobs:
         config:
         - { os: windows-latest, r: 'release'}
         - { os: macOS-latest, r: 'release'}
-        - {os: ubuntu-latest,   r: 'release'}
+        - { os: ubuntu-latest,   r: 'release'}
 
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
@@ -35,55 +35,9 @@ jobs:
           extra-packages: any::rcmdcheck
           needs: check
 
-      # - name: Install dependencies
-      #  run: |
-      #    install.packages("stringi", type="source")
-      #    remotes::install_deps(dependencies = TRUE)
-      #    remotes::install_cran(c("rcmdcheck", "BiocManager"))
-      #    BiocManager::install("sangerseqR")
-      #  shell: Rscript {0}
-      #
-      # - uses: r-lib/actions/check-r-package@v2
-      #   with:
-      #     upload-snapshots: true
-
-      #- name: Query dependencies
-      #  run: |
-      #    install.packages('remotes')
-      #    saveRDS(remotes::dev_package_deps(dependencies = TRUE), ".github/depends.Rds", version = 2)
-      #    writeLines(sprintf("R-%i.%i", getRversion()$major, getRversion()$minor), ".github/R-version")
-      #  shell: Rscript {0}
-
-      #- name: Cache R packages
-      #  if: runner.os != 'Windows'
-      #  uses: actions/cache@v1
-      #  with:
-      #    path: ${{ env.R_LIBS_USER }}
-      #    key: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-${{ hashFiles('.github/depends.Rds') }}
-      #    restore-keys: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-
-
-      #- name: Install system dependencies
-      #  if: runner.os == 'Linux'
-      #  run: |
-      #    while read -r cmd
-      #    do
-      #      eval sudo $cmd
-      #    done < <(Rscript -e 'writeLines(remotes::system_requirements("ubuntu", "20.04"))')
-
-      # - name: Install system dependencies
-      #   if: runner.os == 'Linux'
-      #   env:
-      #     RHUB_PLATFORM: linux-x86_64-ubuntu-gcc
-      #   run: |
-      #     Rscript -e "remotes::install_github('r-hub/sysreqs')"
-      #     sysreqs=$(Rscript -e "cat(sysreqs::sysreq_commands('DESCRIPTION'))")
-      #     sudo -s eval "$sysreqs"
-
-      # - name: Check
-      #   env:
-      #     _R_CHECK_CRAN_INCOMING_: false
-      #   run: rcmdcheck::rcmdcheck(args = c("--no-manual", "--as-cran"), error_on = "error", check_dir = "check")
-      #   shell: Rscript {0}
+      - uses: r-lib/actions/check-r-package@v2
+        with:
+          upload-snapshots: true
 
       - name: Session info
         run: |
@@ -92,11 +46,6 @@ jobs:
           sessioninfo::session_info(pkgs, include_base = TRUE)
         shell: Rscript {0}
 
-      - name: Show testthat output
-        if: always()
-        run: find check -name 'testthat.Rout*' -exec cat '{}' \; || true
-        shell: bash
-
       - name: Upload check results
         if: failure()
         uses: actions/upload-artifact@master

.gitignore

@@ -1,7 +1,7 @@
 vignettes/cache
-.Rproj
+*.Rproj
 .Rproj.user
 .Rhistory
 revdep/checks.noindex
 revdep/data.sqlite
-revdep/library.noindex
+revdep/library.noindex

DESCRIPTION

@@ -31,7 +31,7 @@ BugReports: https://github.com/ropensci/bold/issues
 LazyData: yes
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.1
+RoxygenNote: 7.2.3
 X-schema.org-applicationCategory: Data Access
 X-schema.org-keywords: biodiversity, barcode, DNA, sequences, fasta
 X-schema.org-isPartOf: https://ropensci.org

NEWS.md

@@ -10,7 +10,7 @@ bold 1.3.0
 
 * Similarly, the now deprecated `bold_identify_parents()` has new argument checks and will throw warnings to not affect existing workflows.
 
-* For `bold_tax_id2()` and `bold_tax_name()`, when querying multiple taxa, if one fails, the loop won't break and will instead throw the API error as a warning. The ouput object will also have 2 new attributes "errors" and "params" that will let you see what errors occured for with request and what parameters were use for the request.
+* For `bold_tax_id2()` and `bold_tax_name()`, when querying multiple taxa, if one fails, the loop won't break and will instead throw the API error as a warning. The output object will also have 2 new attributes "errors" and "params" that will let you see what errors occurred for with request and what parameters were use for the request.
 To make it easy to retrieve these attributes, 3 new functions have been created:
   * `bold_get_attr()` will return a list of the two attributes
   * `bold_get_errors()` will return a list of the errors

R/bold_filter.R

@@ -1,3 +1,6 @@
+if (getRversion() >= "2.15.1") {
+  utils::globalVariables(c("nucleotides", ".I"))
+}
 #' Filter BOLD specimen + sequence data (output of bold_seqspec)
 #'
 #' Picks either shortest or longest sequences, for a given grouping variable

R/bold_identify.R

@@ -19,7 +19,7 @@
 #'  lot of sequences - you are doing a separate query for each one, so it can
 #' take a long time - if you run into errors let us know.
 #'
-#' @section db parmeter options:
+#' @section db parameter options:
 #'
 #' - COX1 Every COI barcode record on BOLD with a minimum sequences
 #'  length of 500bp (warning: unvalidated library and includes records without

R/bold_identify_taxonomy.R

@@ -40,7 +40,7 @@ methods::setMethod(
   definition = function(x, taxOnly = TRUE) {
     b_assert_length(x, len = 0L, name = "x")
     taxOnly <- b_assert_logical(taxOnly, name = "taxOnly")
-    hasID <- vapply(x, \(x) "ID" %in% colnames(x), NA)
+    hasID <- vapply(x, function(x) "ID" %in% colnames(x), NA)
     if (all(!hasID)) {
       stop("no column 'ID' found in x")
     } else {

R/bold_seqspec.R

@@ -74,7 +74,7 @@ bold_seqspec <- function(taxon = NULL, ids = NULL, bin = NULL, container = NULL,
       b_sepFasta(out, format = format)
   }
 }
-#' Seperate sequences (fasta) from `bold_seqspec` output.
+#' Separate sequences (fasta) from `bold_seqspec` output.
 #'
 #' @param x      (object) The output of a `bold_seqspec` call.
 #' @param format (character) The format used in the `bold_seqspec` call. One of 'tsv' (default) or 'xml'.

R/bold_stats.R

@@ -80,7 +80,7 @@ b_simplify_stats <- function(x, dataType) {
     n <- which(vapply(x, inherits, NA, "integer"))
     ov <- vapply(x[-n], `[[`, 0L, "count")
     ov <- as.data.frame(c(x[n],ov))
-    dd <- lapply(x[-n], \(x) {
+    dd <- lapply(x[-n], function(x) {
       y <- x$drill_down
       i <- 0
       while (!is.data.frame(y) && i < 5) {

R/bold_tax_id2.R

@@ -130,7 +130,7 @@ b_process_tax_id <- function(x, ids, types, tree) {
         out <- b_format_tax_id(out, ids = ids)
       } else {
         tmp <-
-          lapply(b_nameself(names(out)), \(id) b_format_tax_id(out[[id]], id))
+          lapply(b_nameself(names(out)), function(id) b_format_tax_id(out[[id]], id))
         out <-
           lapply(b_nameself(types), b_grp_dataTypes_tree, x = tmp)
         if ("basic" %in% names(out) &&

R/bold_trace.R

@@ -130,7 +130,7 @@ bold_read_trace <- function(x){
     else
       `names<-`(x, basename(x))
   }
-  lapply(trace_paths, \(trace_path) {
+  lapply(trace_paths, function(trace_path) {
     if (file.exists(trace_path)) {
       sangerseqR::readsangerseq(trace_path)
     } else {

R/utils.R

@@ -92,7 +92,7 @@ b_parse <- function(res, format, raise = TRUE, cleanData = FALSE, multiple = FAL
   }
 }
 b_cleanData <- function(x, emptyValue = NA){
-  col2clean <- vapply(x, \(x) {
+  col2clean <- vapply(x, function(x) {
     any(b_detect(x, "|", max_count = 1, fixed = TRUE), na.rm = TRUE)
   }, NA)
   col2clean <- which(col2clean, useNames = FALSE)
@@ -161,25 +161,21 @@ b_ennum <- function(x, join_word = "and", quote = FALSE) {
 }
 b_fix_taxonName <- function(x){
   # see issue #84
-  b_replace(
-    x,
-    # check if supposed to:
-    c(
-      # be quoted; keep quoted text
-      " ('[^']*)$",
-      # be in parenthesis; keep parenthesis text
-      " (\\([^\\(]*)$",
-      # end with a dot (there might be more cases, but haven't seen them yet)
-      "( sp(\\. nov)?$)"
-    ),
-    # add :
-    c(
-      # closing quote
-      " $1\\\\$2\\\\'",
-      # closing parenthesis
-      "$1$2)",
-      # end dot
-      "$1"
-    ),
-    vectorize_all = FALSE)
+  # check if supposed to:
+  x <- b_replace(x,
+                 # be quoted; keep quoted text
+                 " ('[^']*)$",
+                 # add closing quote
+                 " \\\\$1\\\\'")
+  x <- b_replace(x,
+                 # be in parenthesis; keep parenthesis text
+                 " (\\([^\\(]*)$",
+                 # add closing parenthesis
+                 " $1)")
+  x <- b_replace(x,
+                 # end with a dot (there might be more cases, but haven't seen them yet)
+                 "( sp(\\. nov)?$)",
+                 # add end dot
+                 "$1.")
+  x
 }

R/utils_assert.R

@@ -72,12 +72,14 @@ b_validate <- function(x, choices, name){
   }
 }
 b_get_db <- function(x){
-  x <- tolower(x)
-  if (b_detect(x, '^pub(lic)?$|_public$'))
+  opts <- list(case_insensitive = TRUE)
+  if (b_detect(x, '^COX[1I]$', opts_regex = opts))
+    "COX1"
+  else if (b_detect(x, '^pub(lic)?$|_public$', opts_regex = opts))
     "COX1_SPECIES_PUBLIC"
-  else if (b_detect(x, '^spe(cies)?$|_species$'))
+  else if (b_detect(x, '^spe(cies)?$|_species$', opts_regex = opts))
     "COX1_SPECIES"
-  else if (b_detect(x, '^(cox1_)?(l640)?bp$'))
+  else if (b_detect(x, '^(cox[1I]_)?(l640)?bp$', opts_regex = opts))
     "COX1_L640bp"
   else
     x