cbindlist

add cbind by reference, timing R prototype of mergelist wording use lower overhead funs stick to int32 for now, correct R_alloc bmerge C refactor for codecov and one loop for speed address revealed codecov gaps refactor vecseq for codecov seqexp helper, some alloccol export on C bmerge codecov, types handled in R bmerge already better comment seqexp bmerge mult=error #655 multiple new C utils swap if branches explain new C utils comments mostly reduce conflicts to PR #4386 comment C code address multiple matches during update-on-join #3747 Revert "address multiple matches during update-on-join #3747" This reverts commit b64c0c3. merge.dt has temporarily mult arg, for testing minor changes to cbindlist c dev mergelist, for single pair now add quiet option to cc() mergelist tests add check for names to perhaps.dt rm mult from merge.dt method rework, clean, polish multer, fix righ and full joins make full join symmetric mergepair inner function to loop on extra check for symmetric mergelist manual ensure no df-dt passed where list expected comments and manual handle 0 cols tables more tests more tests and debugging move more logic closer to bmerge, simplify mergepair more tests revert not used changes reduce not needed checks, cleanup copy arg behavior, manual, no tests yet cbindlist manual, export both cleanup processing bmerge to dtmatch test function match order for easier preview vecseq gets short-circuit batch test allow browser big cleanup remmove unneeded stuff, reduce diff more cleanup, minor manual fixes add proper test scripts Merge branch 'master' into cbind-merge-list comment out not used code for coverage more tests, some nocopy opts rename sql test script, should fix codecov simplify dtmatch inner branch more precise copy, now copy only T or F unused arg not yet in api, wording comments and refer issues codecov hasindex coverage codecov gap tests for join using key, cols argument fix missing import forderv more tests, improve missing on handling more tests for order of inner and full join for long keys new allow.cartesian option, #4383, #914 reduce diff, improve codecov reduce diff, comments need more DT, not lists, mergelist 3+ tbls proper escape heavy check unit tests more tests, address overalloc failure mergelist and cbindlist retain index manual, examples fix manual minor clarify in manual retain keys, right outer join for snowflake schema joins duplicates in cbindlist recycling in cbindlist escape 0 input in copyCols empty input handling closing cbindlist vectorized _on_ and _join.many_ arg rename dtmatch to dtmerge vectorized args: how, mult push down input validation add support for cross join, semi join, anti join full join, reduce overhead for mult=error mult default value dynamic fix manual add "see details" to Rd mention shared on in arg description amend feedback from Michael semi and anti joins will not reorder x columns Merge branch 'master' into cbind-merge-list spelling, thx to @jan-glx check all new funs used and add comments bugfix, sort=T needed for now Merge branch 'master' into cbind-merge-list Update NEWS.md Merge branch 'master' into cbind-merge-list Merge branch 'master' into cbind-merge-list NEWS placement numbering ascArg->order Merge remote-tracking branch 'origin/cbind-merge-list' into cbind-merge-list attempt to restore from master Update to stopf() error style Need isFrame for now More quality checks: any(!x)->!all(x); use vapply_1{b,c,i} really restore from master try to PROTECT() before duplicate() update error message in test appease the rchk gods extraneous space missing ';' use catf simplify perhapsDataTableR move sqlite.Rraw.manual into other.Rraw simplify for loop Merge remote-tracking branch 'origin/cbind-merge-list' into cbind-merge-list
Rdatatable · Oct 1, 2024 · 8bba6af · 8bba6af
1 parent 0ab0f5e
commit 8bba6af
Show file tree

Hide file tree

Showing 2 changed files with 89 additions and 0 deletions.
diff --git a/src/data.table.h b/src/data.table.h
@@ -258,6 +258,12 @@ SEXP islockedR(SEXP x);
 bool need2utf8(SEXP x);
 SEXP coerceUtf8IfNeeded(SEXP x);
 SEXP coerceAs(SEXP x, SEXP as, SEXP copyArg);
+int NROW(SEXP x);
+int NCOL(SEXP x);
+bool isDataTable(SEXP x);
+bool isDataList(SEXP x);
+bool perhapsDataTable(SEXP x);
+SEXP perhapsDataTableR(SEXP x);
 void internal_error(const char *call_name, const char *format, ...);
 
 // types.c

diff --git a/src/utils.c b/src/utils.c
@@ -439,6 +439,89 @@ SEXP startsWithAny(const SEXP x, const SEXP y, SEXP start) {
   return ScalarLogical(false);
 }
 
+// if (length(x)) length(x[[1L]]) else 0L
+int NROW(SEXP x) {
+  // used in src/mergelist.c and below in commented out set_row_names
+  if (!LENGTH(x))
+    return 0; // # nocov # not yet reached from anywhere, cbindlist uses it but escapes for !NCOL(x)
+  return length(VECTOR_ELT(x, 0));
+}
+
+// length(x)
+int NCOL(SEXP x) {
+  // used in src/mergelist.c
+  // to be an abstraction layer on C level
+  return LENGTH(x);
+}
+
+/*
+ Below commented out functions will be uncommented when addressing #4439
+ // c("data.table","data.frame")
+ static SEXP char2_dtdf() {
+ SEXP char2_dtdf = PROTECT(allocVector(STRSXP, 2));
+ SET_STRING_ELT(char2_dtdf, 0, char_datatable);
+ SET_STRING_ELT(char2_dtdf, 1, char_dataframe);
+ UNPROTECT(1);
+ return char2_dtdf;
+ }
+ 
+ // .set_row_names(x)
+ static SEXP set_row_names(int n) {
+ SEXP ans = R_NilValue;
+ if (n) {
+ ans = PROTECT(allocVector(INTSXP, 2));
+ INTEGER(ans)[0] = NA_INTEGER;
+ INTEGER(ans)[1] = -n;
+ } else {
+ ans = PROTECT(allocVector(INTSXP, 0));
+ }
+ UNPROTECT(1);
+ return ans;
+ }
+ 
+ // setDT(x) ## not in-place!
+ SEXP setDT(SEXP x) {
+ if (!isNewList(x))
+ error("internal error: C setDT should be called only on a list"); // # nocov
+ setAttrib(x, R_ClassSymbol, char2_dtdf());
+ setAttrib(x, sym_rownames, set_row_names(NROW(x)));
+ return alloccolwrapper(x, GetOption(sym_alloccol, R_NilValue), GetOption(sym_verbose, R_NilValue));
+ }*/
+
+// inherits(x, "data.table")
+bool isDataTable(SEXP x) {
+  return INHERITS(x, char_datatable);
+}
+
+// rectangular list; NB does not allow length-1 recycling
+// length(x) <= 1L || length(unique(lengths(x))) == 1L
+static inline bool equalLens(SEXP x) {
+  int n = LENGTH(x);
+  if (n < 2)
+    return true;
+  R_xlen_t nr = xlength(VECTOR_ELT(x, 0));
+  for (int i=1; i<n; ++i) {
+    if (xlength(VECTOR_ELT(x, i)) != nr)
+      return false;
+  }
+  return true;
+}
+
+// setDT()-friendly rectangular list, i.e.
+// is.list(x) && equalLens(x) && (!length(x) || !is.null(names(x)))
+bool isDataList(SEXP x) {
+  return isNewList(x) && (!LENGTH(x) || (equalLens(x) && !isNull(getAttrib(x, R_NamesSymbol))));
+}
+
+// TODO: use isDataFrame (when included in any R release).
+// isDataTable(x) || isFrame(x) || isDataList(x)
+bool perhapsDataTable(SEXP x) {
+  return isDataTable(x) || isFrame(x) || isDataList(x);
+}
+SEXP perhapsDataTableR(SEXP x) {
+  return ScalarLogical(perhapsDataTable(x));
+}
+
 void internal_error(const char *call_name, const char *format, ...) {
   char buff[1024];
   va_list args;