Merge branch 'master' of https://github.com/Rdatatable/data.table into issue_6882

Author: venom1204

.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

@@ -63,7 +63,7 @@ Functionality that is out of current scope:
 ## Committer
 
 * Definition: permission to commit to, and merge PRs into, master branch. 
-* How to obtain this role: after a Reviewer has a consistent history of careful reviews of others' PRs, then a current Committer should ask all other current Committers if they approve promoting the Reviewer to Committer, and it should be done if there is Consensus among active Committers. 
+* How to obtain this role: after a Reviewer has a consistent history of careful reviews of others' substantial PRs, then a current Committer should ask all other current Committers if they approve promoting the Reviewer to Committer, and it should be done if there is Consensus among active Committers. 
 * How this role is recognized: credited via role="aut" in DESCRIPTION (so they appear in Author list on CRAN), and added to https://github.com/orgs/Rdatatable/teams/committers which gives permission to merge PRs into master branch. 
 
 ## CRAN Maintainer
@@ -139,6 +139,8 @@ data.table Version line in DESCRIPTION typically has the following meanings
 
 # Governance history
 
+July 2025: require potential new committers' considered history to be of "substantial" PRs
+
 May 2025: update Finance and CoC language for NumFOCUS incorporation.
 
 Feb 2025: add Finances and Funding section, update Code of Conduct section to be a brief summary and reference the broader CoC document.

GOVERNANCE.md

@@ -40,7 +40,7 @@
     # 2:     2     6     4     5
     ```
 
-8. `groupingsets()` gets a new argument `enclos` for use together with the `jj` argument in functions wrapping `groupingsets()`, including the existing wrappers `rollup()` and `cube()`. When forwarding a `j`-expression as `groupingsets(jj = substitute(j))`, make sure to pass `enclos = parent.frame()` as well, so that the `j`-expression will be evaluated in the right context. This makes it possible for `j` to refer to variables outside the `data.table`.
+8. `groupingsets()` gets a new argument `enclos` for use together with the `jj` argument in functions wrapping `groupingsets()`, including the existing wrappers `rollup()` and `cube()`, [#5560](https://github.com/Rdatatable/data.table/issues/5560). When forwarding a `j`-expression as `groupingsets(jj = substitute(j))`, make sure to pass `enclos = parent.frame()` as well, so that the `j`-expression will be evaluated in the right context. This makes it possible for `j` to refer to variables outside the `data.table`. Thanks @sindribaldur for the report and @aitap for the fix.
 
 ### BUG FIXES
 
@@ -82,6 +82,8 @@
 
 19. Spurious warnings from internal code in `cube()`, `rollup()`, and `groupingsets()` are no longer surfaced to the caller, [#6964](https://github.com/Rdatatable/data.table/issues/6964). Thanks @ferenci-tamas for the report and @venom1204 for the fix.
  
+20. `droplevels()` works on 0-row data.tables, [#7043](https://github.com/Rdatatable/data.table/issues/7043). The result will have factor columns `factor(character())`, consistent with the data.frame method. Thanks @advieser for the report and @MichaelChirico for the fix.
+
 ### NOTES
 
 1. Continued work to remove non-API C functions, [#6180](https://github.com/Rdatatable/data.table/issues/6180). Thanks Ivan Krylov for the PRs and for writing a clear and concise guide about the R API: https://aitap.codeberg.page/R-api/.

NEWS.md

@@ -1,6 +1,7 @@
 # 647 fast droplevels.data.table method
 fdroplevels = function(x, exclude = if (anyNA(levels(x))) NULL else NA, ...) {
   stopifnot(inherits(x, "factor"))
+  if (!length(x)) return(structure(integer(), class='factor', levels=character())) # skip factor() overhead
   lev = which(tabulate(x, nlevels(x)) & (!match(levels(x), exclude, 0L)))
   ans = match(as.integer(x), lev)
   setattr(ans, 'levels', levels(x)[lev])
@@ -15,7 +16,6 @@ droplevels.data.table = function(x, except=NULL, exclude, ...){
 }
 
 setdroplevels = function(x, except=NULL, exclude=NULL) {
-  if (!nrow(x)) return(invisible(x))
   ix = vapply_1b(x, is.factor)
   if (!is.null(except)) {
     stopifnot(is.numeric(except), except >= 1L, except <= length(x))

R/fdroplevels.R

@@ -21359,10 +21359,17 @@ test(2327.2, cube(DT, .(as.numeric(base::min(value, na.rm=TRUE))), "var"),
      data.table(var = c("a", "b", "c", "d", NA), V1 = c(1.0, 2.0, 3.0, Inf, 1.0)),
      warning="no non-missing arguments to min")
 
+# droplevels should still work on a 0-row table, #7043
+DT = data.table(f=factor(character(), levels='a'))
+test(2328.1, levels(droplevels(DT)$f), character())
+DT[, i := integer()]
+DT[, f2 := factor()]
+test(2328.2, droplevels(DT), data.table(f=factor(), i=integer(), f2=factor()))
+
 #6882 print() output with col.names="none"
 dt = data.table(short = 1:3, verylongcolumnname = 4:6)
-test(2328.1, print(dt, col.names = "none"), output = "1: 1 4\n2: 2 5\n3: 3 6\n")
+test(2329.1, print(dt, col.names = "none"), output = "1: 1 4\n2: 2 5\n3: 3 6\n")
 dt = data.table(x = 123456, y = "wide_string")
-test(2328.2, print(dt, col.names = "none"), output = "1: 123456 wide_string\n")
+test(2329.2, print(dt, col.names = "none"), output = "1: 123456 wide_string\n")
 dt = data.table(a = NA_integer_, b = NaN)
-test(2328.3, print(dt, col.names = "none"), output = "1: NA NaN\n")
+test(2329.3, print(dt, col.names = "none"), output = "1: NA NaN\n")

inst/tests/tests.Rraw

@@ -205,7 +205,7 @@ accounting for both year transitions and varying day counts per week.
    for second, minute, hour, day of year, day of week,
    day of month, week, month, quarter, and year, respectively.
    \code{yearmon} and \code{yearqtr} return double values representing
-   respectively `year + (month-1) / 12` and `year + (quarter-1) / 4`.
+   respectively \code{year + (month-1) / 12} and \code{year + (quarter-1) / 4}.
 
    \code{second}, \code{minute}, \code{hour} are taken directly from
    the \code{POSIXlt} representation.
@@ -217,7 +217,7 @@ accounting for both year transitions and varying day counts per week.
 }
 \references{
 
-  G. Grothendieck and T. Petzoldt, ``Date and Time Classes in R,''
+  G. Grothendieck and T. Petzoldt, \dQuote{Date and Time Classes in R},
   R News, vol. 4, no. 1, June 2004.
 
   H. Wickham, https://gist.github.com/hadley/10238.