Merge pull request #66 from stitam/wf

Revert "Disable GitHub workflows"

.Rbuildignore

@@ -14,4 +14,4 @@ README.Rmd
 /cache/
 
 # scripts that are not part of the package
-scripts/
+scripts

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

@@ -0,0 +1,50 @@
+# Workflow derived from
+# https://github.com/r-lib/actions/blob/v2-branch/examples/check-standard.yaml
+
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+
+name: R-CMD-check
+
+jobs:
+  R-CMD-check:
+    runs-on: ${{ matrix.config.os }}
+
+    name: ${{ matrix.config.os }} (${{ matrix.config.r }})
+
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - {os: macos-latest,   r: 'release'}
+          - {os: windows-latest, r: 'release'}
+          - {os: ubuntu-latest,   r: 'devel', http-user-agent: 'release'}
+          - {os: ubuntu-latest,   r: 'release'}
+          - {os: ubuntu-latest,   r: 'oldrel-1'}
+
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      R_KEEP_PKG_SOURCE: yes
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - 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

.github/workflows/check-pkgdown.yml

@@ -0,0 +1,33 @@
+on:
+    push:
+      branches:
+        - master
+    pull_request:
+      branches:
+        - master
+
+name: check-pkgdown
+
+jobs:
+    check_pkgdown:
+      runs-on: ubuntu-22.04
+
+      env:
+        GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+
+      steps:
+        - uses: actions/checkout@v3
+        - uses: r-lib/actions/setup-r@v2
+          with:
+            r-version: 'release'
+        - uses: r-lib/actions/setup-r-dependencies@v2
+          with:
+            extra-packages: any::devtools, any::pkgdown
+
+        - name: Install dependencies
+          run: devtools::install_github("https://github.com/ropensci-org/rotemplate")
+          shell: Rscript {0}
+
+        - name: Check pkgdown
+          run: pkgdown::check_pkgdown()
+          shell: Rscript {0}

.github/workflows/test-coverage.yaml

@@ -0,0 +1,51 @@
+# Workflow copied from 
+https://github.com/r-lib/actions/blob/v2-branch/examples/test-coverage.yaml
+
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+
+name: test-coverage
+
+jobs:
+  test-coverage:
+    runs-on: ubuntu-latest
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::covr
+          needs: coverage
+
+      - name: Test coverage
+        run: |
+          covr::codecov(
+            quiet = FALSE,
+            clean = FALSE,
+            install_path = file.path(Sys.getenv("RUNNER_TEMP"), "package")
+          )
+        shell: Rscript {0}
+
+      - name: Show testthat output
+        if: always()
+        run: |
+          ## --------------------------------------------------------------------
+          find ${{ runner.temp }}/package -name 'testthat.Rout*' -exec cat '{}' \; || true
+        shell: bash
+
+      - name: Upload test results
+        if: failure()
+        uses: actions/upload-artifact@v3
+        with:
+          name: coverage-test-failures
+          path: ${{ runner.temp }}/package

DESCRIPTION

@@ -11,12 +11,13 @@ Maintainer: Tamas Stirling <[email protected]>
 License: MIT + file LICENSE
 Encoding: UTF-8
 LazyData: true
+Depends:
+    R (>= 3.5.0)
 Imports:
     curl,
     dplyr,
     httr,
     jsonlite,
-    plyr,
     rentrez,
     stringi,
     stringr,

NAMESPACE

@@ -12,7 +12,6 @@ export(ncbi_link_uid)
 export(ncbi_parse)
 export(ncbi_parse_assembly_xml)
 export(ncbi_parse_biosample_txt)
-export(parse_gb_header)
 export(parse_report)
 importFrom(curl,curl_download)
 importFrom(curl,handle_setopt)

R/ncbi_get_meta.R

@@ -13,6 +13,8 @@
 #' API queries?
 #' @param parse logical; should the function attempt to parse the output into a
 #' tibble?
+#' @param mc_cores integer; number of cores to use for parallel processing. Only
+#' used if \code{parse = TRUE}.
 #' @param verbose logical; Should verbose messages be printed to console?
 #' @return If \code{parse = FALSE} the function will return an object of class
 #' \code{ncbi_meta}, which is a character vector with some extra information
@@ -42,6 +44,7 @@ ncbi_get_meta <- function(
     batch_size = 100,
     use_history = TRUE,
     parse = TRUE,
+    mc_cores = NULL,
     verbose = getOption("verbose")
   ) {
   if ("ncbi_uid" %in% class(query)) {
@@ -159,7 +162,7 @@ ncbi_get_meta <- function(
     if (verbose) {
       message("Attempting to parse retrieved metadata.")
     }
-    res_parsed <- ncbi_parse(meta = res, verbose = verbose)
+    res_parsed <- ncbi_parse(meta = res, mc_cores = mc_cores, verbose = verbose)
     if (all("data.frame" %in% class(res_parsed))) {
       out <- dplyr::bind_rows(res_parsed)
       if (verbose) message("Done.")

R/ncbi_parse.R

@@ -9,7 +9,7 @@
 #' @param db character; the NCBI database from which the data was retrieved.
 #' @param format character; the format of the data set. Currently only
 #' \code{"xml"} is supported.
-#' @param mc_cores integer; number of cores to use for parallel processing.
+#' @param mc_cores integer; Number of cores to use for parallel processing.
 #' @param verbose logical; Should verbose messages be printed to console?
 #' @return a tibble.
 #' @details This function is integrated into \code{ncbi_get_meta()} and is 
@@ -73,11 +73,6 @@ ncbi_parse <- function(
   }
   db <- match.arg(db, choices = c("assembly", "biosample"))
   format <- match.arg(format, choices = c("xml"))
-  if (is.null(mc_cores)) {
-    mc_cores <- max(parallel::detectCores() - 1, 1)
-  } else {
-    mc_cores <- as.integer(mc_cores)
-  }
   f <- get(paste("ncbi_parse", db, format, sep = "_"))
   if (db == "assembly" && format == "xml") {
     out <- f(meta, verbose = verbose)

R/ncbi_parse_biosample_xml.R

@@ -16,11 +16,7 @@ ncbi_parse_biosample_xml <- function(
     if (verbose) message("No BioSample metadata to parse.")
     return(NA_character_)
   }
-  if (is.null(mc_cores)) {
-    mc_cores <- max(parallel::detectCores() - 1, 1)
-  } else {
-    mc_cores <- as.integer(mc_cores)
-  }
+  mc_cores <- get_mc_cores(mc_cores, verbose = verbose)
   biosample_df <- data.frame()
   if (verbose) message("Attempting to parse BioSample XMLs.")
   for (i in seq_along(biosample_xml)) {
@@ -69,14 +65,14 @@ ncbi_parse_biosample_xml <- function(
     }
     if (verbose) message("Successful.")
     out <- dplyr::bind_rows(out)
-    out <- dplyr::relocate(out, biosample_uid)
-    out <- dplyr::relocate(out, biosample, .after = biosample_uid)
+    out <- dplyr::relocate(out, "biosample_uid")
+    out <- dplyr::relocate(out, "biosample", .after = "biosample_uid")
     biosample_df <- dplyr::bind_rows(biosample_df, out)
   }
   out <- tibble::as_tibble(biosample_df)
   out <- out[, order(unname(sapply(out, function(x) sum(is.na(x)))))]
-  out <- dplyr::relocate(out, biosample_uid)
-  out <- dplyr::relocate(out, biosample, .after = biosample_uid)
+  out <- dplyr::relocate(out, "biosample_uid")
+  out <- dplyr::relocate(out, "biosample", .after = "biosample_uid")
   return(out)
 }
 
@@ -138,7 +134,7 @@ ncbi_parse_biosample_xml_entry <- function(x, verbose = getOption("verbose")) {
   }
   if (all(c("geo", "geo_link") %in% names(out)) & nrow(out) == 1) {
     if (grepl(out$geo, out$geo_link)) {
-      out <- dplyr::select(out, -geo_link)
+      out <- dplyr::select(out, -"geo_link")
     }
   }
   if (nrow(out) > 1) {

R/utils.R

@@ -146,3 +146,40 @@ validate_webseq_class <- function(x) {
     testthat::expect_true(attr(x, "db") %in% ncbi_dbs())
   }
 }
+
+#' Get number of processor cores
+#' 
+#' @param mc_cores integer; Number of cores to use for parallel processing.
+#' @param verbose logical; Should verbose messages be printed to console?
+#' @noRd
+get_mc_cores <- function(mc_cores, verbose = getOption("verbose")) {
+  if (is.null(mc_cores)) {
+    if (verbose) message(
+      "Number of cores not specified. Looking at 'Ncpu' option."
+    )
+    mc_cores <- getOption("Ncpu")
+    if (!is.null(mc_cores)) {
+      if (verbose) message("Found.")
+    } else {
+      if (verbose) message(
+        "Not found. Attempting to use all but one cores (at least 1)."
+      )
+      mc_cores <- max(parallel::detectCores() - 1, 1)
+    }
+  }
+  mc_cores <- as.integer(mc_cores)
+  if (!is.integer(mc_cores)) {
+    stop("Number of cores must be an integer.")
+  }
+  if (mc_cores < 1) {
+    stop("Number of cores must be at least 1.")
+  }
+  sys <- Sys.info()
+  if (mc_cores > 1 && sys[["sysname"]] == "Windows") {
+    if (verbose) message(
+      "'mc.cores' > 1 is not supported on Windows."
+    )
+    mc_cores <- 1
+  }
+  return(mc_cores)
+}