Merge branch 'master' into R_4_5_isCharASCII

Author: MichaelChirico

.Rbuildignore

@@ -1,4 +1,5 @@
 .dir-locals.el
+.check.translations.R
 ^\.Rprofile$
 ^data\.table_.*\.tar\.gz$
 ^config\.log$
@@ -16,6 +17,7 @@
 ^\.devcontainer$
 ^\.graphics$
 ^\.github$
+^\.vscode$
 ^\.zed$
 
 ^\.gitlab-ci\.yml$
@@ -27,6 +29,7 @@
 ^src/Makevars$
 ^CODEOWNERS$
 ^GOVERNANCE\.md$
+^Seal_of_Approval\.md$
 
 ^\.RData$
 ^\.Rhistory$

.ci/.lintr.R

@@ -9,10 +9,10 @@ linters = c(dt_linters, all_linters(
   packages = "lintr", # TODO(lintr->3.2.0): Remove this.
   # eq_assignment_linter(),
   brace_linter(allow_single_line = TRUE),
+  implicit_integer_linter(allow_colon = TRUE),
   # TODO(michaelchirico): Activate these incrementally. These are the
   #   parameterizations that match our style guide.
   # implicit_assignment_linter(allow_lazy = TRUE, allow_scoped = TRUE),
-  # implicit_integer_linter(allow_colon = TRUE),
   # system_time_linter = undesirable_function_linter(c(
   #   system.time = "Only run timings in benchmark.Rraw"
   # )),
@@ -26,7 +26,8 @@ linters = c(dt_linters, all_linters(
   #   setwd = NULL
   # )),
   undesirable_operator_linter(),
-  # TODO(lintr#2441): Use upstream implementation.
+  # TODO(lintr#2765): Use upstream implementation.
+  # assignment_linter(operator = "="),
   assignment_linter = NULL,
   absolute_path_linter = NULL, # too many false positives
   # TODO(lintr#2442): Use this once x[ , j, by] is supported.
@@ -84,7 +85,9 @@ exclusions = c(local({
       infix_spaces_linter = Inf,
       undesirable_function_linter = Inf
     )),
-    exclusion_for_dir("vignettes", list(
+    exclusion_for_dir(c("vignettes", "vignettes/fr", "vignettes/ru"), list(
+      # assignment_linter = Inf,
+      implicit_integer_linter = Inf,
       quotes_linter = Inf,
       sample_int_linter = Inf
       # strings_as_factors_linter = Inf

.ci/README.md

@@ -1,6 +1,6 @@
 # data.table continuous integration and deployment
 
-On each Pull Request opened in GitHub we run GitHub Actions test jobs to provide prompt feedback about the status of PR. Our main CI pipeline runs on GitLab CI nightly. GitLab repository automatically mirrors our GitHub repository and runs pipeline on `master` branch every night. It tests more environments and different configurations. It publish variety of artifacts.
+On each Pull Request opened in GitHub we run GitHub Actions test jobs to provide prompt feedback about the status of PR. Our more thorough main CI pipeline runs nightly on GitLab CI. GitLab repository automatically mirrors our GitHub repository and runs pipeline on `master` branch every night. It tests more environments and different configurations. It publishes a variety of artifacts such as our [homepage](https://rdatatable.gitlab.io/data.table/) and [CRAN-like website for dev version](https://rdatatable.gitlab.io/data.table/web/packages/data.table/index.html), including windows binaries for the dev version.
 
 ## Environments
 
@@ -44,3 +44,22 @@ Base R implemented helper script, [originally proposed to base R](https://svn.r-
 ### [`publish.R`](./publish.R)
 
 Base R implemented helper script to orchestrate generation of most artifacts and to arrange them nicely. It is being used only in [_integration_ stage in GitLab CI pipeline](./../.gitlab-ci.yml).
+
+## GitLab Open Source Program
+
+We are currently part of the [GitLab for Open Source Program](https://about.gitlab.com/solutions/open-source/). This gives us 50,000 compute minutes per month for our GitLab CI. Our license needs to be renewed yearly (around July) and is currently managed by @ben-schwen.
+
+## Updating CI pipeline
+
+Basic CI checks are also run on every push to the GitLab repository. This can **and should** be used for PRs changing the CI pipeline before merging them to master.
+
+```shell
+# fetch changes from remote (GitHub) and push them to GitLab 
+git fetch [email protected]:Rdatatable/data.table.git new_branch:new_branch
+git push
+# after updating on GitHub, pull changes from remote and push to GitLab
+git pull [email protected]:Rdatatable/data.table.git new_branch
+git push
+```
+
+Make sure to include a link to the pipeline results in your PR. 

.ci/atime/tests.R

@@ -111,7 +111,7 @@ mirror.packages <-
 function(pkgs,
          which = c("Depends", "Imports", "LinkingTo"),
          repos = getOption("repos"),
-         type = c("source", "mac.binary", "win.binary"),
+         type = c("source", "mac.binary.big-sur-arm64", "win.binary"),
          repodir,
          except.repodir = repodir,
          except.priority = "base",
@@ -169,7 +169,8 @@ function(pkgs,
     newpkgs <- newpkgs[availpkgs]
   }
 
-  pkgsext <- switch(type,
+  typeshort <- if (startsWith(type, "mac.binary.")) "mac.binary" else type
+  pkgsext <- switch(typeshort,
                     "source" = "tar.gz",
                     "mac.binary" = "tgz",
                     "win.binary" = "zip")
@@ -181,7 +182,7 @@ function(pkgs,
   dp <- utils::download.packages(pkgs = newpkgs, destdir = destdir,
                                  available = db, contriburl = repos.url,
                                  type = type, method = method, quiet = quiet)
-  tools::write_PACKAGES(dir = destdir, type = type, ...)
+  tools::write_PACKAGES(dir = destdir, type = typeshort, ...)
   dp
 }
 

.ci/ci.R

@@ -4,8 +4,9 @@
 #   2. Check the next line for a check like 'if (!x || !y)'
 alloc_linter = function(c_obj) {
   lines = c_obj$lines
-  # Be a bit more precise to avoid mentions in comments
-  alloc_lines = grep(R"{=\s*([(]\w+\s*[*][)])?[mc]alloc[(]}", lines)
+  # Be a bit more precise to avoid mentions in comments, and allow
+  #   malloc(0) to be used for convenience (e.g. #6757)
+  alloc_lines = grep(R"{=\s*([(]\w+\s*[*][)])?[mc]alloc[(][^0]}", lines)
   if (!length(alloc_lines)) return()
   # int *tmp=(int*)malloc(...); or just int tmp=malloc(...);
   alloc_keys = lines[alloc_lines] |>

.ci/linters/c/alloc_linter.R

@@ -0,0 +1,20 @@
+cocci_linter = if (!nzchar(Sys.which("spatch"))) function(...) {} else function(c_obj) {
+  bad <- FALSE
+  for (spfile in list.files(".ci/linters/cocci", full.names = TRUE)) {
+    # Coccinelle parser gets confused sometimes, so ignore stderr and the exit code
+    out = suppressWarnings(system2(
+      "spatch",
+      shQuote(c(
+        "--sp-file", spfile, c_obj$path, "--recursive-includes",
+        "-I", R.home("include"), "-I", "src"
+      )),
+      stdout = TRUE, stderr = FALSE
+    ))
+    if (length(out) > 0) {
+      cat(sprintf("In file '%s', Coccinelle patch '%s' recommends the following changes:\n", c_obj$path, spfile))
+      writeLines(out)
+      bad <- TRUE
+    }
+  }
+  if (bad) stop("Please apply the changes above or fix the linter")
+}

.ci/linters/c/cocci_linter.R

@@ -0,0 +1,6 @@
+@@
+type T;
+T* E;
+@@
+- (T*)
+  E

.ci/linters/cocci/redundant_cast_to_same_pointer_type.cocci

@@ -0,0 +1,26 @@
+any_mismatch = FALSE
+
+# ensure that ids are limited to alphanumerics and dashes
+# (in particular, dots and underscores break the links)
+check_header_ids = function(md) {
+  # A bit surprisingly, some headings don't start with a letter.
+  # We're interested in those that set an id to link to, i.e., end with {#id}.
+  heading_captures = regmatches(md, regexec("^#+ \\S.*[{]#([^}]*)[}]$", md))
+  lines_with_id = which(lengths(heading_captures) > 0)
+  ids = vapply(heading_captures[lines_with_id], `[`, '', 2)
+  # ids must start with a letter and consist of alphanumerics or dashes.
+  good_ids = grepl('^[A-Za-z][A-Za-z0-9-]*$', ids)
+  for (line in lines_with_id[!good_ids]) cat(sprintf(
+    "On line %d, bad heading id '%s':\n%s\n",
+    line, heading_captures[[line]][2], heading_captures[[line]][1]
+  ))
+  !all(good_ids)
+}
+
+any_error = FALSE
+for (vignette in list.files('vignettes', pattern = "[.]Rmd$", recursive = TRUE, full.name = TRUE)) {
+  cat(sprintf("Checking vignette file %s...\n", vignette))
+  rmd_lines = readLines(vignette)
+  any_error = check_header_ids(rmd_lines) || any_error
+}
+if (any_error) stop("Please fix the vignette issues above.")

.ci/linters/md/heading_id_linter.R

@@ -0,0 +1,45 @@
+# Use msgfmt to check for untranslated/fuzzy messages, and for whether
+#   the implied .mo compiled form matches that which is already checked in
+msgfmt_linter <- function(po_file) {
+  mo_tmp <- tempfile()
+  on.exit(unlink(mo_tmp))
+
+  res = system2("msgfmt", c("--statistics", po_file, "-o", mo_tmp), stdout=TRUE, stderr=TRUE)
+  if (any(grepl("untranslated message|fuzzy translation", res))) {
+    cat(sprintf("In %s, found incomplete translations:\n%s\n", po_file, paste(res, collapse="\n")))
+    stop("Please fix.")
+  }
+
+  mo_ref = sprintf(
+    "inst/%s/LC_MESSAGES/%sdata.table.mo",
+    gsub("^R-|[.]po$", "", po_file),
+    if (startsWith(basename(po_file), "R-")) "R-" else ""
+  )
+
+  if (!file.exists(mo_ref)) {
+    stop(po_file, " has not been compiled as ", mo_ref, ". Please fix.")
+  }
+  if (tools::md5sum(mo_ref) == tools::md5sum(mo_tmp)) return(invisible())
+  # TODO(#6517): Re-activate this part of the check to ensure .mo is up to date.
+  cat(sprintf("Note: MD5 sum of msgfmt output for %s does not match %s.\n", po_file, mo_ref))
+  return(invisible())
+
+  # NB: file.mtime() will probably be wrong, it will reflect the check-out time of the git repo.
+  last_edit_time = system2("git",
+    c("log", "-1", '--format="%ad"', "--date=format:'%Y-%m-%d %H:%M:%S'", "--", mo_ref),
+    stdout=TRUE
+  )
+  cat(sprintf(
+    ".mo compilation %s of .po translation %s appears out of date! It was last updated %s\n",
+    mo_ref, po_file, last_edit_time
+  ))
+
+  unmo_tmp = tempfile()
+  unmo_ref = tempfile()
+  on.exit(unlink(c(unmo_tmp, unmo_ref)), add=TRUE)
+  system2("msgunfmt", c(mo_tmp, "-o", unmo_tmp))
+  system2("msgunfmt", c(mo_ref, "-o", unmo_ref))
+  cat("Here are the observed differences after converting back to .po:\n\n")
+  system2("diff", c(unmo_tmp, unmo_ref))
+  stop("Please fix.")
+}