Multiple changes to fix R CMD check

.Rbuildignore

@@ -6,10 +6,9 @@
 .github
 
 # README files
-README.Rmd
+README.html
 README.md
+README.Rmd
 
-# Local directories
-
-cache/
-inst/
+# knitr and R markdown default cache directories
+/cache/

.github/workflows/test-coverage.yaml

@@ -1,29 +1,51 @@
+# Workflow copied from 
+https://github.com/r-lib/actions/blob/v2-branch/examples/test-coverage.yaml
+
 on:
   push:
-    branches:
-      - master
+    branches: [main, master]
   pull_request:
-    branches:
-      - master
+    branches: [main, master]
 
 name: test-coverage
 
 jobs:
   test-coverage:
-    runs-on: macOS-latest
+    runs-on: ubuntu-latest
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+
     steps:
       - uses: actions/checkout@v3
+
       - uses: r-lib/actions/setup-r@v2
         with:
-          r-version: 'release'
+          use-public-rspm: true
 
-      - name: Install dependencies
-        run: |
-          install.packages(c("remotes", "rcmdcheck"))
-          remotes::install_deps(dependencies = TRUE)
-          remotes::install_cran("covr")
-        shell: Rscript {0}
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::covr
+          needs: coverage
 
       - name: Test coverage
-        run: covr::codecov()
+        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

.gitignore

@@ -37,8 +37,4 @@ vignettes/*.pdf
 
 # R Environment Variables
 .Renviron
-
-# Local directories
-
-cache/
-inst/
+inst/doc

DESCRIPTION

@@ -1,13 +1,32 @@
 Package: webseq
 Type: Package
-Title: This package collects R functions for working with sequence databases like NCBI, ENA, MGnify
+Title: Access data from biological sequence databases like NCBI, ENA, MGnify
+Description: This package interacts with online biological sequence databases.
+    It provides functions to search for sequences, convert identifiers and
+    download sequences and associated metadata.
 Version: 0.1
 Date: 2022-01-05
 Author: Tamas Stirling
 Maintainer: Tamas Stirling <[email protected]>
-Description: TBA
-License: TBD
+License: MIT + file LICENSE
 Encoding: UTF-8
 LazyData: true
+Imports:
+    curl,
+    dplyr,
+    genbankr,
+    httr,
+    jsonlite,
+    plyr,
+    rentrez,
+    stringi,
+    stringr,
+    tibble,
+    XML
+Suggests:
+    knitr,
+    rmarkdown,
+    testthat
 RoxygenNote: 7.2.3
+VignetteBuilder: knitr
 Config/testthat/edition: 3

LICENSE

@@ -0,0 +1,2 @@
+YEAR: 2023
+COPYRIGHT HOLDER: Tamás Stirling

R/flag_files.R

@@ -47,7 +47,7 @@ flag_files <- function(filenames) {
       if (nrow(cr) == 1) {
         df$keep[i] = TRUE 
       } else {
-        cr <- cr[order(cr$source, cr$version, decreasing = c(TRUE, TRUE)),]
+        cr <- cr[order(cr$source, cr$version, decreasing = TRUE),]
         cr$keep[1] <- TRUE
         cr$keep[2:nrow(cr)] <- FALSE
         df$keep[cr$row] <- cr$keep

R/mgnify_instance.R

@@ -1,3 +1,15 @@
+#' Search for a specific entry in MGnify
+#' 
+#' This function can be used for searching MGnify using an identifier.
+#' @param query character; the indentifier
+#' @param from character; the api which contains this identifier. See
+#' \code{mgnify_endpoints()} for a list of possible apis. 
+#' @return a list
+#' @examples
+#' \dontrun{
+#' # look up an assembly
+#' mgnify_instance("ERZ477576", from = "assemblies")
+#' }
 #' @export
 mgnify_instance <- function(query, from) {
   query <- utils::URLencode(query)

R/mgnify_list.R

@@ -1,5 +1,14 @@
 #' Retrieve a list of instances from MGnify
-#' @param sleep character; 
+#' 
+#' This function retrieves a list of identifiers to look up with other
+#' functions.
+#' @param query character; what to look for.
+#' @param from character; API. See \code{"mgnify_endpoints()"}.
+#' @param from_id character; more precise filtering for the API.
+#' @param page numeric; the API's response is paginated this tells the API which
+#' page to return. If \code{NULL}, the function will return all pages.
+#' @param sleep character; number of seconds to sleep before requesting the next
+#' page.
 #' @param verbose logical; should verbose messages be printed to console?
 #' @examples
 #' \dontrun{

R/ncbi_download_genome.R

@@ -39,7 +39,7 @@ ncbi_download_genome <- function(accession,
     }
     if (verbose) message(x, ". ", appendLF = FALSE)
     Sys.sleep(stats::runif(1,0.2,0.5))
-    assembly_uid <- try(ncbi_get_uid(x, db = "assembly"), silent = TRUE)
+    assembly_uid <- try(get_uid(x, db = "assembly"), silent = TRUE)
     if (inherits(assembly_uid, "try-error")) {
       if (verbose) message("Failed. Webservice temporarily down.")
       return(NA)

R/ncbi_meta_biosample.R

@@ -10,11 +10,11 @@
 #' @examples
 #' \dontrun{
 #' # Sample metadata from BioSample ID
-#' biosample_uid <- ncbi_get_uid("SAMN02714232", db = "biosample")
+#' biosample_uid <- get_uid("SAMN02714232", db = "biosample")
 #' ncbi_meta(biosample_uid)
 #' 
 #' # Sample metadata from assembly accession 
-#' assembly_uid <- ncbi_get_uid("GCF_000695855.3")
+#' assembly_uid <- get_uid("GCF_000695855.3")
 #' biosample_uid <- ncbi_link_uids(assembly_uid, from = "assembly", to = "biosample")
 #' ncbi_meta_biosample(biosample_uid)
 #' }

R/ncbi_meta_sra.R

@@ -1,7 +1,7 @@
 #function currently used to get run id from sra_uid
 ncbi_meta_sra <- function(sra) {
   init <- substr(sra, 1, 3)
-  sra_uid <- ncbi_get_uid(sra, db = "sra")
+  sra_uid <- get_uid(sra, db = "sra")
   res <- rentrez::entrez_fetch(
     db = "sra", id = sra_uid, rettype = "docsum", retmode = "json")
   cont <- jsonlite::fromJSON(res)$result[[2]]$runs

tests/testthat.R

@@ -0,0 +1,3 @@
+library('testthat')
+library('webseq')
+test_check("webseq")

vignettes/ncbi.Rmd

@@ -9,6 +9,10 @@ vignette: >
   \usepackage[utf8]{inputenc}
 ---
 
+```{r}
+library(webseq)
+```
+
 ## Download genome assemblies
 
 Download genbank file for GCF_003007635.1.
@@ -18,13 +22,13 @@ https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/003/007/635/
 
 Let's download GCF_003007635.1_ASM300763v1_genomic.gbff.gz!
 
-```{r}
+```{r, eval = FALSE}
 ncbi_download_genome("GCF_003007635.1", type = "genomic.gbff")
 ```
 
 If we try to download it again, the function will indicate that the file is already downloaded.
 
-```{r}
+```{r, eval = FALSE}
 ncbi_download_genome("GCF_003007635.1", type = "genomic.gbff")
 ```
 
@@ -35,25 +39,29 @@ Let's download some metadata for this assembly!
 First, get the Assembly UID of the assembly, which is the internal identifier of the assembly within the NCBI Assembly database.
 
 ```{r}
-assembly_uid <- ncbi_get_uid("GCF_003007635.1", db = "assembly")
+assembly_uid <- get_uid("GCF_003007635.1", db = "assembly")
+assembly_uid
 ```
 
 Next, collect some assembly metadata.
 
 ```{r}
-assembly_meta <- ncbi_meta_assembly(assembly_uid$uid)
+assembly_meta <- get_meta(assembly_uid$uid, db = "assembly")
+assembly_meta
 ```
 
 Using this metadata we can find the BioSample ID associated with the assembly. Let's use this ID to get the BioSample UID of the sample within the NCBI BioSample database.
 
 ```{r}
-biosample_uid <- ncbi_get_uid(assembly_meta$biosample, db = "biosample")
+biosample_uid <- get_uid(assembly_meta$biosample, db = "biosample")
+biosample_uid
 ```
 
 And then get the metadata itself
 
 ```{r}
-biosample_meta <- ncbi_meta_biosample(biosample_uid$uid)
+biosample_meta <- get_meta(biosample_uid$uid, db = "biosample")
+biosample_meta
 ```
 
 ## Parse metadata files
@@ -69,7 +77,7 @@ upper right corner -> send to -> file -> format = xml -> create file
 
 Download the file and then parse it.
 
-```{r}
+```{r, eval = FALSE}
 ncbi_parse_assembly_xml("assembly_summary.xml")
 ```
 
@@ -82,6 +90,6 @@ upper right corner -> send to -> file -> format = full (text) -> create file
 
 Download the file and then parse it.
 
-```{r}
+```{r, eval = FALSE}
 ncbi_parse_biosample_txt("biosample_summary.txt")
 ```