cbindlist, mergelist

NAMESPACE

@@ -58,6 +58,8 @@ export(nafill)
 export(setnafill)
 export(.Last.updated)
 export(fcoalesce)
+export(cbindlist)
+export(mergelist)
 export(substitute2)
 #export(DT)  # mtcars |> DT(i,j,by)  #4872 #5472
 

NEWS.md

@@ -6,6 +6,10 @@
 
 1. In `DT[, variable := value]`, when value is class `POSIXlt`, we automatically coerce it to class `POSIXct` instead, [#1724](https://github.com/Rdatatable/data.table/issues/1724). Thanks to @linzhp for the report, and Benjamin Schwendinger for the fix.
 
+## NEW FEATURES
+
+1. (add example here?) New functions `cbindlist` and `mergelist` have been implemented and exported. Works like `cbind`/`merge` but takes `list` of data.tables on input. `merge` happens in `Reduce` fashion. Supports `how` (_left_, _inner_, _full_, _right_, _semi_, _anti_, _cross_) joins and `mult` argument, closes [#599](https://github.com/Rdatatable/data.table/issues/599) and [#2576](https://github.com/Rdatatable/data.table/issues/2576).
+
 ## NOTES
 
 1. Tests run again when some Suggests packages are missing, [#6411](https://github.com/Rdatatable/data.table/issues/6411). Thanks @aadler for the note and @MichaelChirico for the fix.

R/data.table.R

@@ -199,7 +199,7 @@ replace_dot_alias = function(e) {
     }
     return(x)
   }
-  if (!mult %chin% c("first","last","all")) stopf("mult argument can only be 'first', 'last' or 'all'")
+  if (!mult %chin% c("first", "last", "all", "error")) stopf("mult argument can only be 'first', 'last', 'all' or 'error'")
   missingroll = missing(roll)
   if (length(roll)!=1L || is.na(roll)) stopf("roll must be a single TRUE, FALSE, positive/negative integer/double including +Inf and -Inf or 'nearest'")
   if (is.character(roll)) {
@@ -495,6 +495,7 @@ replace_dot_alias = function(e) {
       }
       i = .shallow(i, retain.key = TRUE)
       ans = bmerge(i, x, leftcols, rightcols, roll, rollends, nomatch, mult, ops, verbose=verbose)
+      if (mult=="error") mult="all"
       xo = ans$xo ## to make it available for further use.
       # temp fix for issue spotted by Jan, test #1653.1. TODO: avoid this
       # 'setorder', as there's another 'setorder' in generating 'irows' below...
@@ -516,13 +517,22 @@ replace_dot_alias = function(e) {
         if (!byjoin || nqbyjoin) {
           # Really, `anyDuplicated` in base is AWESOME!
           # allow.cartesian shouldn't error if a) not-join, b) 'i' has no duplicates
-          if (verbose) {last.started.at=proc.time();catf("Constructing irows for '!byjoin || nqbyjoin' ... ");flush.console()}
-          irows = if (allLen1) f__ else vecseq(f__,len__,
-            if (allow.cartesian ||
-                notjoin || # #698. When notjoin=TRUE, ignore allow.cartesian. Rows in answer will never be > nrow(x).
-                !anyDuplicated(f__, incomparables = c(0L, NA_integer_))) {
-              NULL # #742. If 'i' has no duplicates, ignore
-            } else as.double(nrow(x)+nrow(i))) # rows in i might not match to x so old max(nrow(x),nrow(i)) wasn't enough. But this limit now only applies when there are duplicates present so the reason now for nrow(x)+nrow(i) is just to nail it down and be bigger than max(nrow(x),nrow(i)).
+          if (verbose) {last.started.at=proc.time();cat("Constructing irows for '!byjoin || nqbyjoin' ... ");flush.console()}
+          irows = if (allLen1) f__ else {
+            join.many = getOption("datatable.join.many") # #914, default TRUE for backward compatibility
+            anyDups = if (!join.many && length(f__)==1L && len__==nrow(x)) {
+              NULL # special case of scalar i match to const duplicated x, not handled by anyDuplicate: data.table(x=c(1L,1L))[data.table(x=1L), on="x"]
+            } else if (!notjoin && ( # #698. When notjoin=TRUE, ignore allow.cartesian. Rows in answer will never be > nrow(x).
+              !allow.cartesian ||
+              !join.many))
+              as.logical(anyDuplicated(f__, incomparables = c(0L, NA_integer_)))
+            limit = if (!is.null(anyDups) && anyDups) { # #742. If 'i' has no duplicates, ignore
+              if (!join.many) stopf("Joining resulted in many-to-many join. Perform quality check on your data, use mult!='all', or set 'datatable.join.many' option to TRUE to allow rows explosion.")
+              else if (!allow.cartesian && !notjoin) as.double(nrow(x)+nrow(i))
+              else internal_error("checking allow.cartesian and join.many, unexpected else branch reached") # nocov
+            }
+            vecseq(f__, len__, limit)
+          } # rows in i might not match to x so old max(nrow(x),nrow(i)) wasn't enough. But this limit now only applies when there are duplicates present so the reason now for nrow(x)+nrow(i) is just to nail it down and be bigger than max(nrow(x),nrow(i)).
           if (verbose) {cat(timetaken(last.started.at),"\n"); flush.console()}
           # Fix for #1092 and #1074
           # TODO: implement better version of "any"/"all"/"which" to avoid