Test for removed records, switch to R CMD CHECK workflow for tests, use default testthat setup

.Rbuildignore

@@ -1,3 +1,4 @@
 ^LICENSE\.md$
 ^.*\.Rproj$
 ^\.Rproj\.user$
+^\.github$

.github/.gitignore

@@ -0,0 +1 @@
+*.html

.github/workflows/R-CMD-check.yaml

@@ -0,0 +1,47 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+
+name: R-CMD-check.yaml
+
+permissions: read-all
+
+jobs:
+  R-CMD-check:
+    runs-on: ${{ matrix.config.os }}
+
+    name: ${{ matrix.config.os }} (${{ matrix.config.r }})
+
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - {os: ubuntu-latest,   r: 'release'}
+
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      R_KEEP_PKG_SOURCE: yes
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: r-lib/actions/setup-pandoc@v2
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          r-version: ${{ matrix.config.r }}
+          http-user-agent: ${{ matrix.config.http-user-agent }}
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::rcmdcheck
+          needs: check
+
+      - uses: r-lib/actions/check-r-package@v2
+        with:
+          upload-snapshots: true
+          build_args: 'c("--no-manual","--compact-vignettes=gs+qpdf")'

.github/workflows/testing.yaml

@@ -55,5 +55,6 @@ jobs:
         run: |
           devtools::install(quick = TRUE)
           library(rato.occurrences)
-          source("tests/test_dwc_occurrence.R")
+          library(testthat)
+          testthat::test_dir("tests/testthat/")
         shell: Rscript {0}

DESCRIPTION

@@ -45,3 +45,5 @@ Depends:
     R (>= 2.10)
 LazyData: true
 Config/testthat/edition: 3
+Suggests: 
+    lubridate

NAMESPACE

@@ -1,7 +1,9 @@
 # Generated by roxygen2: do not edit by hand
 
 export("%>%")
+export(get_current)
 export(get_objects)
+export(get_reference)
 export(get_token)
 export(list_object_ids)
 export(set_dwc_order)

R/data.R

@@ -4,5 +4,5 @@
 #' to be included in this dataset. Checks are run against this list to detect
 #' when new species are added.
 #'
-#' @format ## `species` A vector with over 30 species names.
+#' @format `species` A vector with over 30 species names.
 "species"

R/get_current.R

@@ -0,0 +1,34 @@
+#' Get the version of the dataset as currently present locally. Called current
+#' in tests.
+#'
+#' This version might be different from the reference dataset [get_reference()]
+#' if new data was fetched and mapped but not yet published to Github. For
+#' example during an automatic publishing run, or while a new verion of the
+#' dataset is still in review.
+#'
+#' @return A data.frame with DwC mapping of the dataset, as present on the repo.
+#' @export
+#'
+#' @examplesIf interactive()
+#' get_current()
+get_current <- function() {
+
+  # `occurrence.csv` is stored in inst/data/processed/occurrence.csv, everything
+  # stored in inst is placed into the package root after installing. Thus in
+  # data/processed/occurrence.csv, but when directly navigating the repo, the
+  # file still remains in inst.
+
+  data_object_path <-
+    system.file("data/processed", package = "rato.occurrences")
+
+  # Make sure data_object_path exists
+  assertthat::assert_that(
+    dir.exists(data_object_path)
+  )
+
+  readr::read_csv(
+    file.path(data_object_path, "occurrence.csv"),
+    show_col_types = FALSE,
+    progress = FALSE
+  )
+}

R/get_reference.R

@@ -0,0 +1,62 @@
+#' Get the version of the dataset as published on Github, called reference in
+#' tests
+#'
+#' This version might be different from the one on GBIF, as the IPT only fetches
+#' the data from GITHUB periodically (once a week) and not necessarily in phase
+#' with the updates on Github.
+#'
+#' @return A data.frame with DwC mapping of the dataset, as currently published
+#'   on Github.
+#' @export
+#'
+#' @examplesIf interactive()
+#' get_reference()
+get_reference <- function() {
+  github_csv_url <-
+    paste0(
+      "https://raw.githubusercontent.com/riparias/rato-occurrences/main/",
+      "inst/data/processed/occurrence.csv"
+    )
+
+  httr2::request(github_csv_url) %>%
+    httr2::req_retry() %>%
+    httr2::req_cache(path = tempdir(), max_age = 600) %>%
+    httr2::req_perform() %>%
+    httr2::resp_body_raw() %>%
+    rawToChar() %>%
+    readr::read_csv(show_col_types = FALSE,
+                    progress = FALSE,
+                    col_types = 
+                      readr::cols(
+                        occurrenceID = readr::col_character(),
+                        occurrenceStatus = readr::col_character(),
+                        eventID = readr::col_double(),
+                        scientificName = readr::col_character(),
+                        eventDate = readr::col_datetime(format = ""),
+                        organismQuantity = readr::col_double(),
+                        organismQuantityType = readr::col_character(),
+                        samplingProtocol = readr::col_character(),
+                        samplingEffort = readr::col_character(),
+                        municipality = readr::col_character(),
+                        verbatimLatitude = readr::col_double(),
+                        verbatimLongitude = readr::col_double(),
+                        verbatimCoordinateSystem = readr::col_character(),
+                        verbatimSRS = readr::col_character(),
+                        decimalLatitude = readr::col_double(),
+                        decimalLongitude = readr::col_double(),
+                        coordinateUncertaintyInMeters = readr::col_double(),
+                        countryCode = readr::col_character(),
+                        geodeticDatum = readr::col_character(),
+                        type = readr::col_character(),
+                        language = readr::col_character(),
+                        license = readr::col_character(),
+                        rightsHolder = readr::col_character(),
+                        datasetID = readr::col_character(),
+                        institutionCode = readr::col_character(),
+                        datasetName = readr::col_character(),
+                        basisOfRecord = readr::col_character(),
+                        recordedBy = readr::col_character(),
+                        kingdom = readr::col_character(),
+                        taxonRank = readr::col_character()
+                      ))
+}

R/set_dwc_order.R

@@ -20,19 +20,19 @@ set_dwc_order <- function(x){
   assertthat::assert_that(is.data.frame(x))
   dplyr::relocate(
     x,
-    occurrenceID,
-    occurrenceStatus,
-    eventID,
-    scientificName,
-    eventDate,
+    "occurrenceID",
+    "occurrenceStatus",
+    "eventID",
+    "scientificName",
+    "eventDate",
     dplyr::starts_with("organism"),
     dplyr::starts_with("sampling"),
-    municipality,
+    "municipality",
     dplyr::starts_with("verbatim"),
     dplyr::starts_with("decimal"),
-    coordinateUncertaintyInMeters,
-    countryCode,
-    geodeticDatum
+    "coordinateUncertaintyInMeters",
+    "countryCode",
+    "geodeticDatum"
 
   )
 }

README.md

@@ -1,6 +1,9 @@
+<!-- badges: start -->
 [![funding](https://img.shields.io/static/v1?label=published+through&message=LIFE+RIPARIAS&labelColor=00a58d&color=ffffff)](https://www.riparias.be/)
 [![fetch-data](https://github.com/riparias/rato-occurrences/actions/workflows/fetch-data.yaml/badge.svg)](https://github.com/riparias/rato-occurrences/actions/workflows/fetch-data.yaml)
 [![mapping and testing](https://github.com/riparias/rato-occurrences/actions/workflows/mapping_and_testing.yaml/badge.svg)](https://github.com/riparias/rato-occurrences/actions/workflows/mapping_and_testing.yaml)
+[![R-CMD-check](https://github.com/riparias/rato-occurrences/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/riparias/rato-occurrences/actions/workflows/R-CMD-check.yaml)
+<!-- badges: end -->
 
 ## Rationale