add subset and dogroups support for columns of type expression (#5631)

* add subset and dogroups support for columns of type expression * narrow NEWS item --------- Co-authored-by: Michael Chirico <[email protected]> Co-authored-by: Michael Chirico <[email protected]>
Rdatatable · Sep 8, 2024 · 6a2bf2e · 6a2bf2e
1 parent f0aaaf9
commit 6a2bf2e
Show file tree

Hide file tree

Showing 4 changed files with 9 additions and 2 deletions.
diff --git a/NEWS.md b/NEWS.md
@@ -25,6 +25,8 @@ rowwiseDT(
 #> 3:     5     6      c ~a + b
 ```
 
+2. Limited support for subsetting or aggregating columns of type `expression`, [#5596](https://github.com/Rdatatable/data.table/issues/5596). Thanks to @tsp for the report, and @ben-schwen for the fix.
+
 ## BUG FIXES
 
 1. Using `print.data.table()` with character truncation using `datatable.prettyprint.char` no longer errors with `NA` entries, [#6441](https://github.com/Rdatatable/data.table/issues/6441). Thanks to @r2evans for the bug report, and @joshhwuu for the fix.

diff --git a/inst/tests/tests.Rraw b/inst/tests/tests.Rraw
@@ -19222,3 +19222,8 @@ if (test_bit64) {
   test(2288.5, rbind(a,d), data.table(list(as.integer64(1), as.integer64(2), 3.5, 4L)))
   test(2288.6, rbind(d,a), data.table(list(3.5, 4L, as.integer64(1), as.integer64(2))))
 }
+
+# support column type 'expression' #5596
+dt = data.table(a=1:2, b=expression(1,2))
+test(2289.1, dt[1,], data.table(a=1L, b=expression(1)))
+test(2289.2, dt[,b,a], dt)
diff --git a/src/dogroups.c b/src/dogroups.c
@@ -140,7 +140,7 @@ SEXP dogroups(SEXP dt, SEXP dtcols, SEXP groups, SEXP grpcols, SEXP jiscols, SEX
 
   for(int i=0; i<length(SDall); ++i) {
     SEXP this = VECTOR_ELT(SDall, i);
-    if (SIZEOF(this)==0)
+    if (SIZEOF(this)==0 && TYPEOF(this)!=EXPRSXP)
       internal_error(__func__, "size-0 type %d in .SD column %d should have been caught earlier", TYPEOF(this), i); // # nocov
     if (LENGTH(this) != maxGrpSize)
       internal_error(__func__, "SDall %d length = %d != %d", i+1, LENGTH(this), maxGrpSize); // # nocov

diff --git a/src/subset.c b/src/subset.c
@@ -79,7 +79,7 @@ void subsetVectorRaw(SEXP ans, SEXP source, SEXP idx, const bool anyNA)
       for (int i=0; i<n; i++) {                     SET_STRING_ELT(ans, i, sp[idxp[i]-1]); }
     }
   } break;
-  case VECSXP : {
+  case VECSXP: case EXPRSXP: {
     const SEXP *sp = SEXPPTR_RO(source);
     if (anyNA) {
       for (int i=0; i<n; i++) { int elem = idxp[i]; SET_VECTOR_ELT(ans, i, elem==NA_INTEGER ? R_NilValue : sp[elem-1]); }