indices can now return list of character vectors, closes #1589

NEWS.md

@@ -1,6 +1,10 @@
 
 ### Changes in v1.9.9  ( in development on GitHub )
 
+#### NEW FEATURES
+
+1. `indices()` function gain new argument `vectors` default `FALSE`, when `TRUE` provided then list of vector is returned, single vector refers to single index. Closes #1589.
+
 #### BUG FIXES
 
 1. `fwrite(..., quote='auto')` already quoted a field if it contained a `sep` or `\n`, or `sep2[2]` when `list` columns are present. Now it also quotes a field if it contains a double quote (`"`) as documented, [#1925](https://github.com/Rdatatable/data.table/issues/1925). Thanks to Aki Matsuo for reporting. Tests added. The `qmethod` tests did test escaping embedded double quotes, but only when `sep` or `\n` was present in the field as well to trigger the quoting of the field.

R/setkey.R

@@ -86,10 +86,13 @@ key2 <- function(x) {
     if (is.null(ans)) return(ans) # otherwise character() gets returned by next line
     gsub("^__","",ans)
 }
-indices <- function(x) {
+indices <- function(x, vectors = FALSE) {
     ans = names(attributes(attr(x,"index",exact=TRUE)))
     if (is.null(ans)) return(ans) # otherwise character() gets returned by next line
-    gsub("^__","",ans)
+    ans <- gsub("^__","",ans)
+    if (isTRUE(vectors))
+        ans <- strsplit(ans, "__", fixed = TRUE)
+    ans
 }
 
 get2key <- function(x, col) attr(attr(x,"index",exact=TRUE),paste("__",col,sep=""),exact=TRUE)   # work in progress, not yet exported

inst/tests/tests.Rraw

@@ -9737,6 +9737,15 @@ test(1746.2, DT[ids, print(A), by=.EACHI, nomatch=0],
 test(1746.3, DT[ids, {print(A);A}, by=.EACHI, nomatch=0],                               # reliable crash in v1.9.6 and v1.9.8
              data.table(A=c("c","d"),V1=c("c","d")), output="\"c\".*\"d\"")
 
+# indices() can return list of vectors, #1589
+DT = data.table(A=5:1,B=letters[5:1])
+setindex(DT)
+setindex(DT, A)
+setindex(DT, B)
+indices(DT, vectors = TRUE)
+test(1747.1, indices(DT), c("A__B","A","B"))
+test(1747.2, indices(DT, vectors = TRUE), list(c("A","B"),"A","B"))
+
 
 ##########################
 

man/setkey.Rd

@@ -36,7 +36,7 @@ setkeyv(x, cols, verbose=getOption("datatable.verbose"), physical = TRUE)
 setindex(...)
 setindexv(...)
 key(x)
-indices(x)
+indices(x, vectors = FALSE)
 haskey(x)
 key(x) <- value   #  DEPRECATED, please use setkey or setkeyv instead.
 }
@@ -51,6 +51,8 @@ names.}
 \item{verbose}{ Output status and information. }
 \item{physical}{ TRUE changes the order of the data in RAM. FALSE adds a 
 secondary key a.k.a. index. }
+\item{vectors}{ logical scalar default \code{FALSE}, when set to \code{TRUE}
+then list of character vectors is returned, each vector refers to one index. }
 }
 \details{
 \code{setkey} reorders (or sorts) the rows of a data.table by the columns 
@@ -155,6 +157,13 @@ DT = data.table(A=5:1,B=letters[5:1])
 DT2 = copy(DT)        # explicit copy() needed to copy a data.table
 setkey(DT2,B)         # now just changes DT2
 identical(DT,DT2)     # FALSE. DT and DT2 are now different tables
+
+DT = data.table(A=5:1,B=letters[5:1])
+setindex(DT)          # set indices
+setindex(DT, A)
+setindex(DT, B)
+indices(DT)           # get indices single vector
+indices(DT, vectors = TRUE) # get indices list
 }
 \keyword{ data }