Merge branch 'master' into old-include-only

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

@@ -1,6 +1,6 @@
 on:
   schedule:
-   - cron: '17 13 12 * *' # 12th of month at 13:17 UTC
+   - cron: '17 13 13 * *' # 13th of month at 13:17 UTC
 
 # A more complete suite of checks to run monthly; each PR/merge need not pass all these, but they should pass before CRAN release
 name: R-CMD-check-occasional
@@ -42,6 +42,7 @@ jobs:
             r: '4.1'
 
     env:
+      R_LIBS_USER: /home/runner/work/r-lib
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
 
@@ -157,5 +158,5 @@ jobs:
         if: failure()
         uses: actions/upload-artifact@main
         with:
-          name: ${{ runner.os }}-r${{ matrix.r }}-results
+          name: ${{ runner.os }}-r${{ matrix.r }}-l${{ matrix.locale }}results
           path: check

R/data.table.R

@@ -1121,6 +1121,11 @@ replace_dot_alias = function(e) {
           if (is.name(lhs)) {
             lhs = as.character(lhs)
           } else {
+            #6033 revdep. Slowly deprecate in 1.17.0. Caller has given us `dt[, substitute(names(.SD))]` which means
+            # jsub is actually substitute(names(.SD)) instead of just names(.SD)
+            if (lhs %iscall% 'substitute')
+              lhs = eval(lhs, parent.frame(), parent.frame())
+
             # lhs is e.g. (MyVar) or get("MyVar") or names(.SD) || setdiff(names(.SD), cols)
             lhs = eval(lhs, list(.SD = setNames(logical(length(sdvars)), sdvars)), parent.frame())
           }

R/test.data.table.R

@@ -235,6 +235,7 @@ test.data.table = function(script="tests.Rraw", verbose=FALSE, pkg=".", silent=F
     ", Sys.getlocale()=='", Sys.getlocale(), "'",
     ", l10n_info()=='", paste0(names(l10n_info()), "=", l10n_info(), collapse="; "), "'",
     ", getDTthreads()=='", paste(gsub("[ ][ ]+","==",gsub("^[ ]+","",capture.output(invisible(getDTthreads(verbose=TRUE))))), collapse="; "), "'",
+    ", .libPaths()==", paste0("'", .libPaths(), "'", collapse = ","),
     ", ", .Call(Cdt_zlib_version),
     "\n", sep="")
 

inst/tests/tests.Rraw

@@ -18388,10 +18388,13 @@ test(2250.11, dt[, names(.SD(2)) := lapply(.SD, .I)], error=base_messages$missin
 dt = data.table(a = 1:3, b = 5:7, grp = c('a', 'a', 'b'))
 test(2250.12, dt[, names(.SD) := lapply(.SD, function(x) x + b), .SDcols = "a"], data.table(a = 1:3 + 5:7, b = 5:7, grp = c('a', 'a', 'b')))
 
-
 dt = data.table(a = 1L, b = 2L, c = 3L, d = 4L, e = 5L, f = 6L)
 test(2250.13, dt[, names(.SD)[1:5] := sum(.SD)], data.table(a = 21L, b = 21L, c = 21L, d = 21L, e = 21L, f = 6L))
 
+dt = data.table(a = 1) #6033 revdep follow-up
+my_col = "a"
+test(2250.14, dt[, substitute(my_col) := .(3)], data.table(a = 3))
+
 # fread(...,fill) can also be used to specify a guess on the maximum number of columns #2691 #1812 #4130 #3436 #2727
 dt_str = paste(rep(c("1,2\n", "1,2,3\n"), each=100), collapse="")
 ans = data.table(1L, 2L, rep(c(NA, 3L), each=100L))

man/fread.Rd

@@ -129,7 +129,6 @@ When \code{input} begins with http://, https://, ftp://, ftps://, or file://, \c
 Background :\cr
 \url{https://cran.r-project.org/doc/manuals/R-data.html}\cr
 \url{https://stackoverflow.com/questions/1727772/quickly-reading-very-large-tables-as-dataframes-in-r}\cr
-\url{https://cerebralmastication.com/2009/11/loading-big-data-into-r/}\cr
 \url{https://stackoverflow.com/questions/9061736/faster-than-scan-with-rcpp}\cr
 \url{https://stackoverflow.com/questions/415515/how-can-i-read-and-manipulate-csv-file-data-in-c}\cr
 \url{https://stackoverflow.com/questions/9352887/strategies-for-reading-in-csv-files-in-pieces}\cr
@@ -141,7 +140,7 @@ Background :\cr
 
 finagler = "to get or achieve by guile or manipulation" \url{https://dictionary.reference.com/browse/finagler}
 
-On YAML, see \url{https://yaml.org/}; on csvy, see \url{https://csvy.org/}.
+On YAML, see \url{https://yaml.org/}.
 }
 \seealso{
   \code{\link[utils:read.table]{read.csv}}, \code{\link[base:connections]{url}}, \code{\link[base:locales]{Sys.setlocale}}, \code{\link{setDTthreads}}, \code{\link{fwrite}}, \href{https://CRAN.R-project.org/package=bit64}{\code{bit64::integer64}}

src/data.table.h

@@ -10,9 +10,6 @@
 #if !defined(R_VERSION) || R_VERSION < R_Version(3, 4, 0)
 #  define SET_GROWABLE_BIT(x)  // #3292
 #endif
-#if !defined(R_VERSION) || R_VERSION < R_Version(4, 5, 0)
-# define isDataFrame(x) isFrame(x)
-#endif
 #include <Rinternals.h>
 #define SEXPPTR_RO(x) ((const SEXP *)DATAPTR_RO(x))  // to avoid overhead of looped STRING_ELT and VECTOR_ELT
 #include <stdint.h>    // for uint64_t rather than unsigned long long

src/dogroups.c

@@ -276,7 +276,7 @@ SEXP dogroups(SEXP dt, SEXP dtcols, SEXP groups, SEXP grpcols, SEXP jiscols, SEX
       for (int j=0; j<LENGTH(jval); ++j) {
         thiscol = VECTOR_ELT(jval,j);
         if (isNull(thiscol)) continue;
-        if (!isVector(thiscol) || isDataFrame(thiscol))
+        if (!isVector(thiscol) || isFrame(thiscol))
           error(_("Entry %d for group %d in j=list(...) should be atomic vector or list. If you are trying something like j=list(.SD,newcol=mean(colA)) then use := by group instead (much quicker), or cbind or merge afterwards."), j+1, i+1);
         if (isArray(thiscol)) {
           SEXP dims = PROTECT(getAttrib(thiscol, R_DimSymbol));