implement option, add regresion tests

Author: MichaelChirico

NEWS.md

@@ -4,6 +4,10 @@
 
 ## data.table [v1.17.99](https://github.com/Rdatatable/data.table/milestone/35)  (in development)
 
+### POTENTIALLY BREAKING CHANGES
+
+1. `data.table(x=1, <expr>)`, where `<expr>` is an expression resulting in a 1-column matrix without column names, will eventually have names `x` and `V2`, not `x` and `V1`, consistent with `data.table(x=1, <expr>)` where `<expr>` results in an atomic vector, for example `data.table(x=1, cbind(1))` and `data.table(x=1, 1)` will both have columns named `x` and `V2`. In this release, the matrix case continues to be named `V1`, but the new behavior can be activated by setting `options(datatable.old.matrix.autoname)` to `FALSE`. See point 14 under Bug Fixes for more context; this change will provide more internal consistency as well as more consistency with `data.frame()`.
+
 ### NEW FEATURES
 
 1. New `sort_by()` method for data.tables, [#6662](https://github.com/Rdatatable/data.table/issues/6662). It uses `forder()` to improve upon the data.frame method and also match `DT[order(...)]` behavior with respect to locale. Thanks @rikivillalba for the suggestion and PR.

R/as.data.table.R

@@ -162,7 +162,7 @@ as.data.table.list = function(x,
       xi = x[[i]] = as.POSIXct(xi)
     } else if (is.matrix(xi) || is.data.frame(xi)) {
       if (!is.data.table(xi)) {
-        if (is.matrix(xi) && NCOL(xi)<=1L && is.null(colnames(xi))) { # 1 column matrix naming #4124
+        if (is.matrix(xi) && NCOL(xi)<=1L && is.null(colnames(xi)) && isFALSE(getOption('datatable.old.matrix.autoname'))) { # 1 column matrix naming #4124
           xi = x[[i]] = c(xi)
         } else {
           xi = x[[i]] = as.data.table(xi, keep.rownames=keep.rownames)  # we will never allow a matrix to be a column; always unpack the columns

R/onLoad.R

@@ -73,7 +73,8 @@
   # In fread and fwrite we have moved back to using getOption's default argument since it is unlikely fread and fread will be called in a loop many times, plus they
   # are relatively heavy functions where the overhead in getOption() would not be noticed.  It's only really [.data.table where getOption default bit.
   # Improvement to base::getOption() now submitted (100x; 5s down to 0.05s):  https://bugs.r-project.org/bugzilla/show_bug.cgi?id=17394
-  opts = c("datatable.verbose"="FALSE",        # datatable.<argument name>
+  opts = c(
+       "datatable.verbose"="FALSE",            # datatable.<argument name>
        "datatable.optimize"="Inf",             # datatable.<argument name>
        "datatable.print.nrows"="100L",         # datatable.<argument name>
        "datatable.print.topn"="5L",            # datatable.<argument name>
@@ -85,12 +86,14 @@
        "datatable.show.indices"="FALSE",       # for print.data.table
        "datatable.allow.cartesian"="FALSE",    # datatable.<argument name>
        "datatable.join.many"="TRUE",           # mergelist, [.data.table #4383 #914
-       "datatable.dfdispatchwarn"="TRUE",                   # not a function argument
-       "datatable.warnredundantby"="TRUE",                  # not a function argument
+       "datatable.dfdispatchwarn"="TRUE",      # not a function argument
+       "datatable.warnredundantby"="TRUE",     # not a function argument
        "datatable.alloccol"="1024L",           # argument 'n' of alloc.col. Over-allocate 1024 spare column slots
        "datatable.auto.index"="TRUE",          # DT[col=="val"] to auto add index so 2nd time faster
        "datatable.use.index"="TRUE",           # global switch to address #1422
-       "datatable.prettyprint.char" = NULL     # FR #1091
+       "datatable.prettyprint.char" = NULL,    # FR #1091
+       "datatable.old.matrix.autoname"="TRUE", # #7145: how data.table(x=1, matrix(1)) is auto-named set to change
+       NULL
        )
   for (i in setdiff(names(opts),names(options()))) {
     eval(parse(text=paste0("options(",i,"=",opts[i],")")))

inst/tests/tests.Rraw

@@ -21317,6 +21317,10 @@ colnames(M) = c('A', '')
 test(2321.26, as.data.table(M), data.table(A=1:3, V2=4:6))
 test(2321.27, as.data.table(M, keep.rownames='id'), data.table(id=c('a', 'b', 'c'), A=1:3, V2=4:6))
 
+# also respect old auto-naming rules by default (to be deprecated)
+test(2321.28, names(data.table(a=1, cbind(2), c=3, 4)), c("a", "V1", "c", "V4"))
+test(2321.29, options=c(datatable.old.matrix.autoname=FALSE), names(data.table(a=1, cbind(2), c=3, 4)), c("a", "V2", "c", "V4"))
+
 # New fctr() helper: like factor() but retaining order by default #4837
 test(2322.01, levels(fctr(c("b","a","c"))), c("b","a","c"))
 test(2322.02, levels(fctr(c(3,1,2))), c("3","1","2"))

man/data.table-options.Rd

@@ -108,6 +108,15 @@
   }
 }
 
+\section{Back-compatibility Options}{
+  \describe{
+    \item{\code{datatable.old.matrix.autoname}}{Logical, default \code{TRUE}. Governs how the output of
+      expressions like \code{data.table(x=1, cbind(1))} will be named. When \code{TRUE}, it will be named
+      \code{V1}, otherwise it will be named \code{V2}.
+    }
+  }
+}
+
 \seealso{
   \code{\link[base]{options}},
   \code{\link[base]{getOption}},