Merge branch 'master' into frev

Author: ben-schwen

.ci/atime/tests.R

@@ -277,5 +277,14 @@ test.list <- atime::atime_test_list(
     Slow = "73d79edf8ff8c55163e90631072192301056e336",   # Parent of the first commit in the PR (https://github.com/Rdatatable/data.table/commit/8397dc3c993b61a07a81c786ca68c22bc589befc)
     Fast = "8397dc3c993b61a07a81c786ca68c22bc589befc"),  # Commit in the PR (https://github.com/Rdatatable/data.table/pull/7019/commits) that removes inefficiency
 
+  "isoweek improved in #7144" = atime::atime_test(
+    setup = {
+      set.seed(349)
+      x = sample(Sys.Date() - 0:5000, N, replace=TRUE)
+    },
+    expr = data.table::isoweek(x),
+    Slow = "548410d23dd74b625e8ea9aeb1a5d2e9dddd2927",   # Parent of the first commit in the PR (https://github.com/Rdatatable/data.table/commit/548410d23dd74b625e8ea9aeb1a5d2e9dddd2927)
+    Fast = "c0b32a60466bed0e63420ec105bc75c34590865e"),  # Commit in the PR (https://github.com/Rdatatable/data.table/pull/7144/commits) that uses a much faster implementation
+
     tests=extra.test.list)
 # nolint end: undesirable_operator_linter.

.ci/linters/md/news_linter.R …rs/md/news_github_link_mismatch_linter.R.ci/linters/md/news_linter.R renamed to .ci/linters/md/news_github_link_mismatch_linter.R .ci/linters/md/news_linter.R renamed to .ci/linters/md/news_github_link_mismatch_linter.R

@@ -1,32 +1,6 @@
-# ensure that numbered list in each section is in sequence
-check_section_numbering = function(news) {
-  if (!grepl("NEWS", news)) return(invisible())
-  news = readLines(news)
-  # plain '#' catches some examples; 'd' for 'data.table'
-  sections = grep("^#+ [A-Zd]", news)
-  entries = grep("^[0-9]+[.]", news)
-  entry_value = as.integer(gsub("^([0-9]+)[.].*", "\\1", news[entries]))
-  section_id = findInterval(entries, sections)
-
-  any_mismatch = FALSE
-  for (id in unique(section_id)) {
-    section_entries = entry_value[section_id == id]
-    intended_value = seq_along(section_entries)
-    matched = section_entries == intended_value
-    if (all(matched)) next
-    any_mismatch = TRUE
-    section_header = news[sections[id]]
-    cat(sprintf(
-      "In section '%s' (line %d), bad numbering:\n%s\n",
-      section_header, sections[id],
-      paste0("  [", section_entries[!matched], " --> ", intended_value[!matched], "]", collapse="\n")
-    ))
-  }
-  stopifnot("Please fix the NEWS issues above" = !any_mismatch)
-}
-
 # ensure that GitHub link text & URL actually agree
-check_gh_links = function(news) {
+news_github_link_mismatch_linter = function(news) {
+  if (!grepl("NEWS", news)) return(invisible())
   news = readLines(news)
   gh_links_info = gregexpr(
     "\\[#(?<md_number>[0-9]+)\\]\\(https://github.com/Rdatatable/data.table/(?<link_type>[^/]+)/(?<link_number>[0-9]+)\\)",

.ci/linters/md/news_section_numbering_linter.R

@@ -0,0 +1,26 @@
+# ensure that numbered list in each section is in sequence
+news_section_numbering_linter = function(news) {
+  if (!grepl("NEWS", news)) return(invisible())
+  news = readLines(news)
+  # plain '#' catches some examples; 'd' for 'data.table'
+  sections = grep("^#+ [A-Zd]", news)
+  entries = grep("^[0-9]+[.]", news)
+  entry_value = as.integer(gsub("^([0-9]+)[.].*", "\\1", news[entries]))
+  section_id = findInterval(entries, sections)
+
+  any_mismatch = FALSE
+  for (id in unique(section_id)) {
+    section_entries = entry_value[section_id == id]
+    intended_value = seq_along(section_entries)
+    matched = section_entries == intended_value
+    if (all(matched)) next
+    any_mismatch = TRUE
+    section_header = news[sections[id]]
+    cat(sprintf(
+      "In section '%s' (line %d), bad numbering:\n%s\n",
+      section_header, sections[id],
+      paste0("  [", section_entries[!matched], " --> ", intended_value[!matched], "]", collapse="\n")
+    ))
+  }
+  stopifnot("Please fix the NEWS issues above" = !any_mismatch)
+}

.ci/linters/md/heading_id_linter.R …/linters/md/vignette_heading_id_linter.R.ci/linters/md/heading_id_linter.R renamed to .ci/linters/md/vignette_heading_id_linter.R .ci/linters/md/heading_id_linter.R renamed to .ci/linters/md/vignette_heading_id_linter.R

@@ -1,6 +1,6 @@
 # ensure that ids are limited to alphanumerics and dashes
 # (in particular, dots and underscores break the links)
-check_header_ids = function(md) {
+vignette_heading_id_linter = function(md) {
   if (!grepl('[.]Rmd$', md)) return(invisible())
   md = readLines(md)
   # A bit surprisingly, some headings don't start with a letter.

.ci/linters/rd/backtick_linter.R

@@ -0,0 +1,22 @@
+# ensure no markdown-style backticks wind up in Rd where \code is intended
+options_documentation_linter = function(rd_file) {
+  rd = tools::parse_Rd(rd_file)
+
+  error_if_backtick = function(rd_obj) {
+    if (!is.recursive(rd_obj)) {
+      if (any(grepl("`", rd_obj, fixed=TRUE))) {
+        stop(sprintf(
+          "Rd is not markdown -- backticks (`) don't render as code! Use \\code{...}.\nObserved in string '%s' in file %s",
+          trimws(rd_obj), rd_file
+        ))
+      }
+      return(invisible())
+    }
+    tags = vapply(rd_obj, \(x) attr(x, "Rd_tag") %||% "", FUN.VALUE="")
+     # backtick is valid inside R code (e.g. \examples, \code, \preformatted)
+    rd_obj = rd_obj[!tags %in% c("RCODE", "VERB")]
+    lapply(rd_obj, error_if_backtick)
+  }
+
+  invisible(error_if_backtick(rd))
+}

.ci/linters/rd/options_doc_check.R …inters/rd/options_documentation_linter.R.ci/linters/rd/options_doc_check.R renamed to .ci/linters/rd/options_documentation_linter.R .ci/linters/rd/options_doc_check.R renamed to .ci/linters/rd/options_documentation_linter.R

@@ -562,9 +562,9 @@ ls -1 *.tar.gz | grep -E 'Chicago|dada2|flowWorkspace|LymphoSeq' | TZ='UTC' para
 #  3) dllVersion() at the end of init.c
 # DO NOT push to GitHub's master branch. Prevents even a slim possibility of user getting premature version. 
 # Even release numbers must have been obtained from CRAN and only CRAN. There were too many support problems in the past before this procedure was brought in.
-du -k inst/tests                # 1.5MB before
+du -k inst/tests                # 1.5MiB before
 bzip2 inst/tests/*.Rraw         # compress *.Rraw just for release to CRAN; do not commit compressed *.Rraw to git
-du -k inst/tests                # 0.75MB after
+du -k inst/tests                # 0.75MiB after
 R CMD build .
 export GITHUB_PAT="f1c.. github personal access token ..7ad"
 Rdevel -q -e "packageVersion('xml2')"   # ensure installed

.dev/CRAN_Release.cmd

@@ -67,7 +67,7 @@ options(repos = BiocManager::repositories())
 
 options(warn=1)  # warning at the time so we can more easily see what's going on package by package when we scroll through output
 cat("options()$timeout==", options()$timeout," set by R_DEFAULT_INTERNET_TIMEOUT in .dev/.bash_aliases revdepsh\n",sep="")
-# R's default is 60. Before Dec 2020, we used 300 but that wasn't enough to download Bioc package BSgenome.Hsapiens.UCSC.hg19 (677GB) which is
+# R's default is 60. Before Dec 2020, we used 300 but that wasn't enough to download Bioc package BSgenome.Hsapiens.UCSC.hg19 (677MiB) which is
 # suggested by CRAN package CNVScope which imports data.table. From Dec 2020 we use 3600.
 
 if (is.null(utils::old.packages(.libPaths()[2]))) {

.dev/revdep.R

@@ -151,7 +151,7 @@ test-lin-rel-cran:
     _R_CHECK_CRAN_INCOMING_: "TRUE"           ## stricter --as-cran checks should run in dev pipelines continuously (not sure what they are though)
     _R_CHECK_CRAN_INCOMING_REMOTE_: "FALSE"   ## Other than no URL checking (takes many minutes) or 'Days since last update 0' NOTEs needed, #3284
     _R_CHECK_CRAN_INCOMING_TARBALL_THRESHOLD_: "7500000" ## bytes
-    _R_CHECK_PKG_SIZES_THRESHOLD_: "10"        ## MB 'checking installed package size' NOTE increased due to po
+    _R_CHECK_PKG_SIZES_THRESHOLD_: "10"        ## MiB 'checking installed package size' NOTE increased due to po
   script:
     - *install-deps
     - echo 'CFLAGS=-g -O2 -fopenmp -Wall -pedantic -fstack-protector-strong -D_FORTIFY_SOURCE=2' > ~/.R/Makevars