closes Rdatatable#1268, on= retains/discards keys properly.

christianhomberg · Mar 9, 2016 · 7ca42a3 · 7ca42a3
1 parent 2e9ce2f
commit 7ca42a3
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 1 deletion.
diff --git a/R/data.table.R b/R/data.table.R
@@ -1243,7  1243,10 @@ chmatch2 <- function(x, table, nomatch=NA_integer_) {
             if (haskey(x)) {
                 keylen = which.first(!key(x) %chin% ansvars)-1L
                 if (is.na(keylen)) keylen = length(key(x))
-                if (keylen > length(rightcols) && !.Call(CisOrderedSubset, irows, nrow(x))) keylen = length(rightcols)
                 len = length(rightcols)
                 if (keylen > len && !.Call(CisOrderedSubset, irows, nrow(x))) {
                     keylen = if (missing(on) || identical(names(on), head(key(x), len))) len else 0L # fix for #1268
                 }
                 if (keylen && ((is.data.table(i) && haskey(i)) || is.logical(i) || (.Call(CisOrderedSubset, irows, nrow(x)) && ((roll == FALSE) || length(irows) == 1L)))) # see #1010. don't set key when i has no key, but irows is ordered and roll != FALSE
                     setattr(ans,"sorted",head(key(x),keylen))
             }

diff --git a/README.md b/README.md
@@ -168,6  168,8 @@
 
   49. UTF8 BOM header is excluded properly in `fread()`, [#1087](https://github.com/Rdatatable/data.table/issues/1087) and [#1465](https://github.com/Rdatatable/data.table/issues/1465). Thanks to @nigmastar and @MichaelChirico.
 
   50. Joins using `on=` retains (and discards) keys properly, [#1268](https://github.com/Rdatatable/data.table/issues/1268). Thanks @DouglasClark for [this SO post](http://stackoverflow.com/q/29918595/559784) that helped discover the issue.
 
 #### NOTES
 
   1. Updated error message on invalid joins to reflect the new `on=` syntax, [#1368](https://github.com/Rdatatable/data.table/issues/1368). Thanks @MichaelChirico.

diff --git a/inst/tests/tests.Rraw b/inst/tests/tests.Rraw
@@ -7873,6  7873,11 @@ test(1630.4, copy(dt1)[id>5, z := 2], data.table(id = 1:2, x = 3:4, z = NA_real_
 test(1630.5, copy(dt1)[dt2, z := y, on="id"], data.table(id = 1:2, x = 3:4, z = NA_integer_))
 test(1630.6, copy(dt1)[dt2, z := y, on="id", by=.EACHI], data.table(id = 1:2, x = 3:4, z = NA_integer_))
 
 # fix for #1268, on= retains keys correctly.
 A = data.table(site=rep(c("A","B"), each=3), date=rep(1:3, times=2), x=rep(1:3*10, times=2), key="site,date")
 B = data.table(x=c(10,20), y=c(100,200), key="x")
 test(1631, key(A[B, on="x"]), NULL)
 
 ##########################
 
 # TODO: Tests involving GForce functions needs to be run with optimisation level 1 and 2, so that both functions are tested all the time.