Merge branch 'master' into issue6846

Author: venom1204

.dev/lsan.supp

@@ -0,0 +1 @@
+leak:libfontconfig.so

.gitlab-ci.yml

@@ -212,6 +212,24 @@ test-lin-ancient-cran:
     # Restore checking vignettes if upgrading our R dependency means knitr can be installed.
     - R CMD check --no-manual --no-build-vignettes --ignore-vignettes $(ls -1t data.table_*.tar.gz | head -n 1)
 
+# run the main checks with Address(+Leak),UBSanitizer enabled
+test-lin-san:
+  <<: *test-lin
+  image: registry.gitlab.com/rdatatable/dockerfiles/r-devel-clang-san
+  variables:
+    # must be set for most of the process because there are pseudo-leaks everywhere
+    ASAN_OPTIONS: "detect_leaks=0"
+    # fontconfig is known to leak; add more suppressions as discovered
+    LSAN_OPTIONS: "suppressions=$CI_PROJECT_DIR/.dev/lsan.supp"
+    UBSAN_OPTIONS: "print_stacktrace=1"
+  script:
+    - *install-deps
+    - |
+        res1=0; ASAN_OPTIONS=detect_leaks=1 R CMD check --no-manual $(ls -1t data.table_*.tar.gz | head -n 1) || res1=$?
+        res2=0; perl -nle '(print, $a=1) if /: runtime error: |ERROR: LeakSanitizer/../SUMMARY.*Sanitizer/ }{ exit $a' data.table.Rcheck/**/*.Rout* || res2=$?
+        # fail if R CMD check had failed or if sanitizer output found
+        if [ $res1 -ne 0 ] || [ $res2 -ne 0 ]; then exit 1; fi
+
 .test-win-template: &test-win
   <<: *test
   tags:
@@ -311,7 +329,7 @@ integration:
     - saas-linux-medium-amd64
   only:
     - master
-  needs: ["mirror-packages","build","test-lin-rel","test-lin-rel-cran","test-lin-dev-gcc-strict-cran","test-lin-dev-clang-cran","test-lin-rel-vanilla","test-lin-ancient-cran","test-win-rel","test-win-dev" ,"test-win-old","test-mac-rel","test-mac-old"]
+  needs: ["mirror-packages","build","test-lin-rel","test-lin-rel-cran","test-lin-dev-gcc-strict-cran","test-lin-dev-clang-cran","test-lin-rel-vanilla","test-lin-ancient-cran","test-lin-san","test-win-rel","test-win-dev" ,"test-win-old","test-mac-rel","test-mac-old"]
   script:
     - R --version
     - *install-deps ## markdown pkg not present in r-pkgdown image

NEWS.md

@@ -12,10 +12,19 @@
 
 2. `fwrite(compress="gzip")` once again produces a gzip header when the column names are missing or disabled, [@6852](https://github.com/Rdatatable/data.table/issues/6852). Thanks @maxscheiber for the report and @aitap for the fix.
 
+3. `fread(keepLeadingZeros=TRUE)` now correctly parses dates with components with leading zeros as dates instead of strings, [#6851](https://github.com/Rdatatable/data.table/issues/6851). Thanks @TurnaevEvgeny for the report and @ben-schwen 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/.
 
+2. The following in-progress deprecations have proceeded:
+
+   + Argument `logicalAsInt` to `fwrite()` has been removed.
+   + Argument `autostart` to `fread()` has been removed.
+   + Argument `in.place` to `droplevels` has been removed.
+   + It's now an error to set `datatable.nomatch`, which has been warning since 1.15.0.
+
 # data.table [v1.17.0](https://github.com/Rdatatable/data.table/milestone/34)  (20 Feb 2025)
 
 ## POTENTIALLY BREAKING CHANGES

R/data.table.R

@@ -686,10 +686,7 @@ replace_dot_alias = function(e) {
     if (is.null(jsub)) return(NULL)
 
     if (!with) {
-      if (jsub %iscall% ":=") {
-        # TODO(>=1.18.0): Simplify this error
-        stopf("with=FALSE together with := was deprecated in v1.9.4 released Oct 2014; this has been warning since v1.15.0. Please wrap the LHS of := with parentheses; e.g., DT[,(myVar):=sum(b),by=a] to assign to column name(s) held in variable myVar. See ?':=' for other examples.")
-      }
+      if (jsub %iscall% ":=") stopf("`:=` is only supported under with=TRUE, see ?`:=`.")
       # missingby was already checked above before dealing with i
       if (jsub %iscall% c("!", "-") && length(jsub)==2L) {  # length 2 to only match unary, #2109
         notj = TRUE

R/fdroplevels.R

@@ -8,8 +8,7 @@ fdroplevels = function(x, exclude = if (anyNA(levels(x))) NULL else NA, ...) {
   ans
 }
 
-droplevels.data.table = function(x, except=NULL, exclude, in.place=NULL, ...){
-  if (!is.null(in.place)) stopf("droplevels() with in.place=TRUE is deprecated. Use setdroplevels() instead.")
+droplevels.data.table = function(x, except=NULL, exclude, ...){
   x = copy(x)
   if (missing(exclude)) exclude = NULL
   setdroplevels(x, except, exclude)[]

R/fread.R

@@ -7,7 +7,7 @@ showProgress=getOption("datatable.showProgress",interactive()), data.table=getOp
 nThread=getDTthreads(verbose), logical01=getOption("datatable.logical01",FALSE),
 logicalYN=getOption("datatable.logicalYN", FALSE),
 keepLeadingZeros=getOption("datatable.keepLeadingZeros",FALSE),
-yaml=FALSE, autostart=NULL, tmpdir=tempdir(), tz="UTC")
+yaml=FALSE, tmpdir=tempdir(), tz="UTC")
 {
   if (missing(input)+is.null(file)+is.null(text)+is.null(cmd) < 3L) stopf("Used more than one of the arguments input=, file=, text= and cmd=.")
   input_has_vars = length(all.vars(substitute(input)))>0L  # see news for v1.11.6
@@ -124,7 +124,6 @@ yaml=FALSE, autostart=NULL, tmpdir=tempdir(), tz="UTC")
 
     input = file
   }
-  if (!is.null(autostart)) stopf("'autostart' is deprecated. Consider skip='string' or skip=n. This argument will be removed in the next release.");
   if (is.logical(colClasses)) {
     if (!allNA(colClasses)) stopf("colClasses is type 'logical' which is ok if all NA but it has some TRUE or FALSE values in it which is not allowed. Please consider the drop= or select= argument instead. See ?fread.")
     colClasses = NULL

R/fwrite.R

@@ -3,8 +3,7 @@ fwrite = function(x, file="", append=FALSE, quote="auto",
            sep2=c("","|",""), eol=if (.Platform$OS.type=="windows") "\r\n" else "\n",
            na="", dec=".", row.names=FALSE, col.names=TRUE,
            qmethod=c("double","escape"),
-           logical01=getOption("datatable.logical01", FALSE), # due to change to TRUE; see NEWS
-           logicalAsInt=NULL,
+           logical01=getOption("datatable.logical01", FALSE),
            scipen=getOption('scipen', 0L),
            dateTimeAs = c("ISO","squash","epoch","write.csv"),
            buffMB=8L, nThread=getDTthreads(verbose),
@@ -23,9 +22,6 @@ fwrite = function(x, file="", append=FALSE, quote="auto",
   compress = match.arg(compress)
   dateTimeAs = match.arg(dateTimeAs)
   dateTimeAs = chmatch(dateTimeAs, c("ISO", "squash", "epoch", "write.csv")) - 1L
-  if (!is.null(logicalAsInt)) {
-    stopf("logicalAsInt has been renamed logical01 for consistency with fread.")
-  }
   scipen = if (is.numeric(scipen)) as.integer(scipen) else 0L
   buffMB = as.integer(buffMB)
   nThread = as.integer(nThread)

R/onLoad.R

@@ -1,15 +1,8 @@
 # nocov start
 
-.pkg.store = new.env()
-.pkg.store$.unsafe.done = FALSE
 .unsafe.opt = function() {
-  if (.pkg.store$.unsafe.done) return(invisible())
-  val = getOption("datatable.nomatch")
-  if (is.null(val)) return(invisible())  # not defined (it hasn't been defined in .onLoad since v1.12.4)
-  warningf("Option 'datatable.nomatch' is defined but is now ignored. Please see note 11 in v1.12.4 NEWS (Oct 2019), and note 14 in v1.14.2.")
-  # leave this as warning for a long time
-  .pkg.store$.unsafe.done = TRUE
-  invisible()
+  if (!is.null(getOption("datatable.nomatch")))
+    stopf("Option 'datatable.nomatch' is defined but is now ignored. Please see note 11 in v1.12.4 NEWS (Oct 2019), and note 14 in v1.14.2.")
 }
 
 .Last.updated = vector("integer", 1L) # exported variable; number of rows updated by the last := or set(), #1885

inst/tests/tests.Rraw

@@ -4629,7 +4629,7 @@ test(1241, DT[order(x,-y)],       # optimized to forder()
 
 DT = data.table(a=1:3, b=4:6)
 myCol = "a"
-test(1242.1, DT[2,myCol:=6L,with=FALSE], error="with=FALSE together with := was deprecated in v1.9.4")
+test(1242.1, DT[2,myCol:=6L,with=FALSE], error="`:=` is only supported under with=TRUE.")
 test(1242.2, DT[2,(myCol):=7L], data.table(a=INT(1,7,3), b=4:6))
 
 # consistency of output type of mult, #340
@@ -10933,7 +10933,7 @@ test(1736.03, fwrite(DT, sep2=c("",",","")), error="sep.*,.*sep2.*,.*must all be
 test(1736.04, fwrite(DT, sep2=c("","||","")), error="nchar.*sep2.*2")
 test(1736.05, capture.output(fwrite(DT, sep='|', sep2=c("c(",",",")"), logical01=FALSE)), c("A|B|C", "1|c(1,2,3,4,5,6,7,8,9,10)|c(s,t,u,v,w)",
  "2|c(15,16,17,18)|c(1.2,2.3,3.4,3.14159265358979,-9)", "3|c(7)|c(foo,bar)", "4|c(9,10)|c(TRUE,TRUE,FALSE)"))
-test(1736.06, fwrite(DT, sep='|', sep2=c("{",",","}"), logicalAsInt=TRUE), error="logicalAsInt has been renamed logical01")
+# 1736.06 was of defunct logicalAsInt argument
 DT = data.table(A=c("foo","ba|r","baz"))
 test(1736.07, capture.output(fwrite(DT,na="")), c("A","foo","ba|r","baz"))    # no list column so no need to quote
 test(1736.08, capture.output(fwrite(DT)), c("A","foo","ba|r","baz"))
@@ -13178,7 +13178,7 @@ test(1925.10, as.ITime(x),               structure(c(12L, 67L), class="ITime"))
 test(1925.11, as.ITime(x, ms='nearest'), structure(c(12L, 68L), class="ITime"))
 test(1925.12, as.ITime(x, ms='ceil'),    structure(c(13L, 68L), class="ITime"))
 
-test(1936.1, fread("A,B\n1,3\n2,4", autostart=1), error="autostart.*deprecated.*Consider skip")
+# 1936.1 was of defunct argument autostart
 if (.Platform$OS.type == "unix") test(1936.2, is.data.table(fread("ls .")))
 
 # add helpful error to %between%
@@ -13930,7 +13930,7 @@ test(1967.42, x[3, rollends = rep(TRUE, 10L)], error = 'rollends must be length
 test(1967.43, x[ , ..], error = 'symbol .. is invalid')
 test(1967.44, x[NULL], data.table(NULL))
 test(1967.45, x[ , NULL], NULL)
-test(1967.46, x[ , 'b' := 6:10, with=FALSE], error='with=FALSE together with :=')
+test(1967.46, x[ , 'b' := 6:10, with=FALSE], error='`:=` is only supported under with=TRUE.')
 x[, b := 6:10]
 test(1967.47, x[ , -1L, with = FALSE], data.table(b = 6:10))
 test(1967.48, x[ , b, .SDcols = 'a'], 6:10,
@@ -17788,7 +17788,7 @@ if (base::getRversion() >= "3.4.0") {
 }
 test(2214.06, droplevels(DT)[["a"]], droplevels(DT[1:5,a]))
 test(2214.07, droplevels(DT, 1)[["a"]], x[1:5])
-test(2214.08, droplevels(DT, in.place=TRUE), error="droplevels() with in.place=TRUE is deprecated.")
+# 2214.08 was of defunct in.place argument
 # support ordered factors in fdroplevels
 o = factor(letters[1:10], ordered=TRUE)
 test(2214.09, fdroplevels(o[1:5]), droplevels(o[1:5]))
@@ -21079,3 +21079,8 @@ setindex(DT, b)
 # make sure that print(DT) doesn't warn due to the header missing index column types, #6806
 # can't use output= here because the print() call is outside withCallingHandlers(...)
 test(2307, { capture.output(print(DT, class = TRUE, show.indices = TRUE)); TRUE })
+
+# fread with colClasses and keepLeadingZeros=TRUE #6851
+dt = data.table(date=as.IDate(c(NA, "2014-12-05")))
+test(2308.01, fread("date\nNA\n2014-12-05", keepLeadingZeros=TRUE), dt)
+test(2308.02, fread("date\nNA\n2014-12-05", keepLeadingZeros=FALSE), dt)

man/fdroplevels.Rd

@@ -12,13 +12,12 @@
 fdroplevels(x, exclude = if (anyNA(levels(x))) NULL else NA, \dots)
 setdroplevels(x, except = NULL, exclude = NULL)
 
-\method{droplevels}{data.table}(x, except = NULL, exclude, in.place = NULL, \dots)
+\method{droplevels}{data.table}(x, except = NULL, exclude, \dots)
 }
 \arguments{
   \item{x}{ \code{factor} or \code{data.table} where unused levels should be dropped. }
   \item{exclude}{ A \code{character} vector of factor levels which are dropped no matter of presented or not. }
   \item{except}{ An \code{integer} vector of indices of data.table columns which are not modified by dropping levels. }
-  \item{in.place}{ Deprecated. Use \code{setdroplevels} for in-place modification. }
   \item{\dots}{ further arguments passed to methods }
 }