Support tidysq sequences

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

@@ -1,9 +1,25 @@
-# NOTE: This workflow is overkill for most R packages
-# check-standard.yaml is likely a better choice
-# usethis::use_github_action("check-standard") will install it.
-#
-# For help debugging build failures open an issue on the RStudio community with the 'github-actions' tag.
-# https://community.rstudio.com/new-topic?category=Package%20development&tags=github-actions
+# Read more about GitHub actions the features of this GitHub Actions workflow
+## at https://lcolladotor.github.io/biocthis/articles/biocthis.html#use_bioc_github_action
+##
+## For more details, check the biocthis developer notes vignette at
+## https://lcolladotor.github.io/biocthis/articles/biocthis_dev_notes.html
+##
+## You can add this workflow to other packages using:
+## > biocthis::use_bioc_github_action()
+##
+## Using GitHub Actions exposes you to many details about how R packages are
+## compiled and installed in several operating system.s
+### If you need help, please follow the steps listed at
+## https://github.com/r-lib/actions#where-to-find-help
+##
+## If you found an issue specific to biocthis's GHA workflow, please report it
+## with the information that will make it easier for others to help you.
+## Thank you!
+
+## Acronyms:
+## * GHA: GitHub Action
+## * OS: operating system
+
 on:
   push:
     branches:
@@ -14,64 +30,181 @@ on:
       - main
       - master
 
-name: R-CMD-check
+name: R-CMD-check-bioc
+
+## These environment variables control whether to run GHA code later on that is
+## specific to testthat, covr, and pkgdown.
+##
+## If you need to clear the cache of packages, update the number inside
+## cache-version as discussed at https://github.com/r-lib/actions/issues/86.
+## Note that you can always run a GHA test without the cache by using the word
+## "/nocache" in the commit message.
+env:
+  has_testthat: 'true'
+  run_covr: 'true'
+  run_pkgdown: 'true'
+  has_RUnit: 'false'
+  cache-version: 'cache-v1'
 
 jobs:
-  R-CMD-check:
+  build-check:
     runs-on: ${{ matrix.config.os }}
-
     name: ${{ matrix.config.os }} (${{ matrix.config.r }})
+    container: ${{ matrix.config.cont }}
+    ## Environment variables unique to this job.
 
     strategy:
       fail-fast: false
       matrix:
         config:
-          - {os: macOS-latest, r: 'release'}
-          - {os: windows-latest, r: 'release'}
-          - {os: ubuntu-latest, r: 'release'}
-
+          - { os: ubuntu-latest, r: '4.0', bioc: '3.12', cont: "bioconductor/bioconductor_docker:RELEASE_3_12", rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest" }
+          - { os: macOS-latest, r: '4.0', bioc: '3.12'}
+          - { os: windows-latest, r: '4.0', bioc: '3.12'}
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
       RSPM: ${{ matrix.config.rspm }}
+      NOT_CRAN: true
+      TZ: UTC
+      GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
 
     steps:
-      - uses: actions/checkout@v2
+      ## to avoid conversion of configure.ac
+      - name: Configure git
+        run: git config --global core.autocrlf false
 
-      - uses: r-lib/actions/setup-r@v1
+      ## Set the R library to the directory matching the
+      ## R packages cache step further below when running on Docker (Linux).
+      - name: Set R Library home on Linux
+        if: runner.os == 'Linux'
+        run: |
+          mkdir /__w/_temp/Library
+          echo ".libPaths('/__w/_temp/Library')" > ~/.Rprofile
+      ## Most of these steps are the same as the ones in
+      ## https://github.com/r-lib/actions/blob/master/examples/check -standard.yaml
+      ## If they update their steps, we will also need to update ours.
+      - name: Checkout Repository
+        uses: actions/checkout@v2
+
+      ## R is already included in the Bioconductor docker images
+      - name: Setup R from r-lib
+        if: runner.os != 'Linux'
+        uses: r-lib/actions/setup-r@master
         with:
           r-version: ${{ matrix.config.r }}
-          http-user-agent: ${{ matrix.config.http-user-agent }}
 
-      - uses: r-lib/actions/setup-pandoc@v1
+      ## pandoc is already included in the Bioconductor docker images
+      - name: Setup pandoc from r-lib
+        if: runner.os != 'Linux'
+        uses: r-lib/actions/setup-pandoc@master
+
+      - name: Install github dependencies
+        run: |
+          Rscript -e "install.packages('remotes')"
+          Rscript -e "remotes::install_github('BioGenies/tidysq')"
 
       - 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'
+        if: "!contains(github.event.head_commit.message, '/nocache') && runner.os != 'Linux'"
         uses: actions/cache@v2
         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-
+          key: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_12-r-4.0-${{ hashFiles('.github/depends.Rds') }}
+          restore-keys: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_12-r-4.0-
 
-      - name: Install system dependencies
+      - name: Cache R packages on Linux
+        if: "!contains(github.event.head_commit.message, '/nocache') && runner.os == 'Linux' "
+        uses: actions/cache@v2
+        with:
+          path: /home/runner/work/_temp/Library
+          key: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_12-r-4.0-${{ hashFiles('.github/depends.Rds') }}
+          restore-keys: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_12-r-4.0-
+
+      - name: Install Linux system dependencies
         if: runner.os == 'Linux'
         run: |
-          while read -r cmd
-          do
-            eval sudo $cmd
-          done < <(Rscript -e 'writeLines(remotes::system_requirements("ubuntu", "16.04"))')
+          sysreqs=$(Rscript -e 'cat("apt-get update -y && apt-get install -y", paste(gsub("apt-get install -y ", "", remotes::system_requirements("ubuntu", "20.04")), collapse = " "))')
+          echo $sysreqs
+          sudo -s eval "$sysreqs"
+      - name: Install macOS system dependencies
+        if: matrix.config.os == 'macOS-latest'
+        run: |
+          mkdir ~/.R
+          touch ~/.R/Makevars
+          echo "CXX_STD = CXX17" > ~/.R/Makevars
+
+          ## Enable installing XML from source if needed
+          brew install libxml2
+          echo "XML_CONFIG=/usr/local/opt/libxml2/bin/xml2-config" >> $GITHUB_ENV
+          ## Required to install magick as noted at
+          ## https://github.com/r-lib/usethis/commit/f1f1e0d10c1ebc75fd4c18fa7e2de4551fd9978f#diff-9bfee71065492f63457918efcd912cf2
+          brew install imagemagick@6
+          ## For textshaping, required by ragg, and required by pkgdown
+          brew install harfbuzz fribidi
+          ## Helps compile RCurl from source; added forced ignoring deps
+          brew uninstall --ignore-dependencies curl
+      - name: Install Windows system dependencies
+        if: runner.os == 'Windows'
+        run: |
+          ## Edit below if you have any Windows system dependencies
+        shell: Rscript {0}
+
+      - name: Install BiocManager
+        run: |
+          message(paste('****', Sys.time(), 'installing BiocManager ****'))
+          remotes::install_cran("BiocManager")
+        shell: Rscript {0}
+
+      - name: Set BiocVersion
+        run: |
+          BiocManager::install(version = "${{ matrix.config.bioc }}", ask = FALSE)
+        shell: Rscript {0}
 
       - name: Install dependencies
         run: |
-          remotes::install_deps(dependencies = TRUE)
+          ## Try installing the package dependencies in steps. First the local
+          ## dependencies, then any remaining dependencies to avoid the
+          ## issues described at
+          ## https://stat.ethz.ch/pipermail/bioc-devel/2020-April/016675.html
+          ## https://github.com/r-lib/remotes/issues/296
+          ## Ideally, all dependencies should get installed in the first pass.
+          ## Temporary for now due to https://github.com/ropensci/RefManageR/issues/79
+          remotes::install_github("ropensci/bibtex")
+          remotes::install_github("ropensci/RefManageR")
+          remotes::install_github("cboettig/knitcitations")
+          ## Pass #1 at installing dependencies
+          message(paste('****', Sys.time(), 'pass number 1 at installing dependencies: local dependencies ****'))
+          remotes::install_local(dependencies = TRUE, repos = BiocManager::repositories(), build_vignettes = TRUE, upgrade = TRUE)
+          ## Pass #2 at installing dependencies
+          message(paste('****', Sys.time(), 'pass number 2 at installing dependencies: any remaining dependencies ****'))
+          remotes::install_local(dependencies = TRUE, repos = BiocManager::repositories(), build_vignettes = TRUE, upgrade = TRUE)
+          ## For running the checks
+          message(paste('****', Sys.time(), 'installing rcmdcheck and BiocCheck ****'))
           remotes::install_cran("rcmdcheck")
+          BiocManager::install("BiocCheck")
+        shell: Rscript {0}
+
+      - name: Install BiocGenerics
+        if:  env.has_RUnit == 'true'
+        run: |
+          ## Install BiocGenerics
+          BiocManager::install("BiocGenerics")
+        shell: Rscript {0}
+
+      - name: Install covr
+        if: github.ref == 'refs/heads/master' && env.run_covr == 'true' && runner.os == 'Linux'
+        run: |
+          remotes::install_cran("covr")
+        shell: Rscript {0}
+
+      - name: Install pkgdown
+        if: github.ref == 'refs/heads/master' && env.run_pkgdown == 'true' && runner.os == 'Linux'
+        run: |
+          remotes::install_cran("pkgdown")
         shell: Rscript {0}
 
       - name: Session info
@@ -81,32 +214,48 @@ jobs:
           sessioninfo::session_info(pkgs, include_base = TRUE)
         shell: Rscript {0}
 
-      - name: Check
+      - name: Run CMD check
         env:
           _R_CHECK_CRAN_INCOMING_: false
-        run: rcmdcheck::rcmdcheck(args = c("--no-manual", "--as-cran"), error_on = "error", check_dir = "check")
+        run: |
+          rcmdcheck::rcmdcheck(
+              args = c("--no-build-vignettes", "--no-manual", "--timings"),
+              build_args = c("--no-manual", "--no-resave-data"),
+              error_on = "error",
+              check_dir = "check"
+          )
         shell: Rscript {0}
 
-      - name: Show testthat output
-        if: always()
-        run: find check -name 'testthat.Rout*' -exec cat '{}' \; || true
-        shell: bash
+      ## Might need an to add this to the if:  && runner.os == 'Linux'
+      - name: Reveal testthat details
+        if:  env.has_testthat == 'true'
+        run: find . -name testthat.Rout -exec cat '{}' ';'
 
-      - name: Upload check results
-        if: failure()
-        uses: actions/upload-artifact@main
-        with:
-          name: ${{ runner.os }}-r${{ matrix.config.r }}-results
-          path: check
+      - name: Run RUnit tests
+        if:  env.has_RUnit == 'true'
+        run: |
+          BiocGenerics:::testPackage()
+        shell: Rscript {0}
 
-      - name: Install covr
-        if: github.ref == 'refs/heads/master' && env.run_covr == 'true'
+      - name: Run BiocCheck
         run: |
-          remotes::install_cran("covr")
+          BiocCheck::BiocCheck(
+              dir('check', 'tar.gz$', full.names = TRUE),
+              `quit-with-status` = TRUE,
+              `no-check-R-ver` = TRUE,
+              `no-check-bioc-help` = TRUE,
+              `no-check-vignettes` = TRUE,
+              `no-check-man-doc` = TRUE,
+              `no-check-bioc-views` = TRUE
+          )
         shell: Rscript {0}
 
       - name: Test coverage
-        if: github.ref == 'refs/heads/master' && env.run_covr == 'true'
+        if: github.ref == 'refs/heads/master' && env.run_covr == 'true' && runner.os == 'Linux'
         run: |
           covr::codecov()
         shell: Rscript {0}
+
+      - name: Install package
+        if: github.ref == 'refs/heads/master' && env.run_pkgdown == 'true' && runner.os == 'Linux'
+        run: R CMD INSTALL .

CMakeLists.txt

@@ -7,6 +7,8 @@ set(R_LIBRARY "~/R/x86_64-pc-linux-gnu-library/3.6/")
 set(R_INCLUDE "/usr/share/R/include/")
 include_directories(${R_LIBRARY}/Rcpp/include)
 include_directories(${R_LIBRARY}/RcppParallel/include)
+include_directories(${R_LIBRARY}/tidysq/include)
+
 include_directories(${R_INCLUDE})
 
 add_library(seqR

DESCRIPTION

@@ -21,13 +21,15 @@ Imports:
     Rcpp (>= 1.0.4),
     RcppParallel,
     slam,
-    rlang
+    rlang,
+    tidysq
 Depends:
     R(>= 3.6)
 LinkingTo:
     Rcpp,
     RcppParallel,
-    BH
+    BH,
+    tidysq
 SystemRequirements: c++17
 RoxygenNote: 7.1.0
 Encoding: UTF-8

R/RcppExports.R

@@ -22,8 +22,12 @@ NULL
     .Call('_seqR_count_contiguous_kmers_numeric', PACKAGE = 'seqR', sequenceMatrix, alphabet, rcppParams)
 }
 
-.count_contiguous_kmers_list <- function(sq, alphabet, rcppParams) {
-    .Call('_seqR_count_contiguous_kmers_list', PACKAGE = 'seqR', sq, alphabet, rcppParams)
+.count_contiguous_kmers_string_vector <- function(sq, alphabet, rcppParams) {
+    .Call('_seqR_count_contiguous_kmers_string_vector', PACKAGE = 'seqR', sq, alphabet, rcppParams)
+}
+
+.count_contiguous_kmers_tidysq <- function(sq, alphabet, rcppParams) {
+    .Call('_seqR_count_contiguous_kmers_tidysq', PACKAGE = 'seqR', sq, alphabet, rcppParams)
 }
 
 .count_gapped_kmers_string <- function(sequenceMatrix, alphabet, rcppParams) {
@@ -38,7 +42,11 @@ NULL
     .Call('_seqR_count_gapped_kmers_numeric', PACKAGE = 'seqR', sequenceMatrix, alphabet, rcppParams)
 }
 
-.count_gapped_kmers_list <- function(sq, alphabet, rcppParams) {
-    .Call('_seqR_count_gapped_kmers_list', PACKAGE = 'seqR', sq, alphabet, rcppParams)
+.count_gapped_kmers_string_vector <- function(sq, alphabet, rcppParams) {
+    .Call('_seqR_count_gapped_kmers_string_vector', PACKAGE = 'seqR', sq, alphabet, rcppParams)
+}
+
+.count_gapped_kmers_tidysq <- function(sq, alphabet, rcppParams) {
+    .Call('_seqR_count_gapped_kmers_tidysq', PACKAGE = 'seqR', sq, alphabet, rcppParams)
 }
 

R/count_kmers.R

@@ -37,10 +37,6 @@ count_kmers <- function(sequences,
     stop("batch size field must be a positive integer number")
   }
 
-  if(is.vector(sequences)) {
-    sequences <- matrix(data=sequences, nrow=1)
-  }
-
   if(!is_positive_integer(hash_dim) || hash_dim > 8) {
     stop("hash_dim is a single integer number from the range [1, 8]")
   }

R/kmer_functions_provider.R

@@ -7,8 +7,10 @@
 }
 
 .get_kmer_function <- function(sequences) {
-  if (is.list(sequences)) {
-    .kmer_functions_map[["list"]]
+  if(tidysq::is.sq(sequences)) {
+    .kmer_functions_map[["tidysq"]]
+  } else if (is.vector(sequences)) {
+    .kmer_functions_map[["string_vector"]]
   } else if (has_integers_only(sequences)) {
     .kmer_functions_map[["integer"]]
   } else if (is.numeric(sequences)) {
@@ -25,5 +27,6 @@
   "integer" = list(.count_contiguous_kmers_integer_proxy, .count_gapped_kmers_integer_proxy),
   "string" = list(.count_contiguous_kmers_string_proxy, .count_gapped_kmers_string_proxy),
   "numeric" = list(.count_contiguous_kmers_numeric_proxy, .count_gapped_kmers_numeric_proxy),
-  "list" = list(.count_contiguous_kmers_list_proxy, .count_gapped_kmers_list_proxy)
+  "string_vector" = list(.count_contiguous_kmers_string_vector_proxy, .count_gapped_kmers_string_vector_proxy),
+  "tidysq" = list(.count_contiguous_kmers_tidysq_proxy, .count_gapped_kmers_tidysq_proxy)
 )