Added skip_absent() feature to setnames()

.Rbuildignore

@@ -21,3 +21,4 @@
 ^bus$
 ^Dockerfile$
 ^Dockerfile\.in$
+^.*\.dll$

.gitignore

@@ -1,31 +1,32 @@
-# Source: https://github.com/github/gitignore/blob/master/R.gitignore
-# History files
-.RData
-.Rhistory
-.Rapp.history
-
-# Package build process
-*-Ex.R
-data.table_*.tar.gz
-data.table.Rcheck
-
-# Emacs IDE files
-.emacs.desktop
-.emacs.desktop.lock
-
-# RStudio IDE files
-.Rproj.user
-data.table.Rproj
-
-# produced vignettes
-vignettes/*.html
-vignettes/*.pdf
-
-# object and shared objects
-*.o
-*.so
-
-*~
-.DS_Store
-.idea
-*.sw[op]
+# Source: https://github.com/github/gitignore/blob/master/R.gitignore
+# History files
+.RData
+.Rhistory
+.Rapp.history
+
+# Package build process
+*-Ex.R
+data.table_*.tar.gz
+data.table.Rcheck
+
+# Emacs IDE files
+.emacs.desktop
+.emacs.desktop.lock
+
+# RStudio IDE files
+.Rproj.user
+data.table.Rproj
+
+# produced vignettes
+vignettes/*.html
+vignettes/*.pdf
+
+# object and shared objects
+*.o
+*.so
+*.dll
+
+*~
+.DS_Store
+.idea
+*.sw[op]

DESCRIPTION

@@ -12,7 +12,8 @@ Authors@R: c(
   person("Eduard","Antonyan", role="ctb"),
   person("Markus","Bonsch",   role="ctb"),
   person("Hugh","Parsonage",  role="ctb"),
-  person("Scott","Ritchie",   role="ctb"))
+  person("Scott","Ritchie",   role="ctb"),
+  person("Mus","Yaramaz-David", role="ctb"))
 Depends: R (>= 3.1.0)
 Imports: methods
 Suggests: bit64, curl, R.utils, knitr, xts, nanotime, zoo

NEWS.md

@@ -1,4 +1,3 @@
-
 **If you are viewing this file on CRAN, please check [latest news on GitHub](https://github.com/Rdatatable/data.table/blob/master/NEWS.md) where the formatting is also better.**
 
 ### Changes in v1.11.9 (to be v1.12.0)
@@ -7,7 +6,9 @@
 
 1. `fread()` can now read a remote compressed file in one step; `fread("https://domain.org/file.csv.bz2")`. The `file=` argument now supports `.gz` and `.bz2` too; i.e. `fread(file="file.csv.gz")` works now where only `fread("file.csv.gz")` worked in 1.11.8.
 
-2. `nomatch=NULL` now does the same as `nomatch=0L`; i.e. discards missing values silently (inner join). The default is still `nomatch=NA` (outer join) for statistical safety so that missing values are retained by default. You have to explicitly write `nomatch=NULL` to indicate to the reader of your code that you intend to discard missing values silently. After several years have elapsed, we will start to deprecate `0L`; please start using `NULL`. TO DO ... `nomatch=.(0)` fills with `0` instead of `NA`, [#857](https://github.com/Rdatatable/data.table/issues/857) and `nomatch="error"`.
+3. `nomatch=NULL` now does the same as `nomatch=0L`; i.e. discards missing values silently (inner join). The default is still `nomatch=NA` (outer join) for statistical safety so that missing values are retained by default. You have to explicitly write `nomatch=NULL` to indicate to the reader of your code that you intend to discard missing values silently. After several years have elapsed, we will start to deprecate `0L`; please start using `NULL`. TO DO ... `nomatch=.(0)` fills with `0` instead of `NA`, [#857](https://github.com/Rdatatable/data.table/issues/857) and `nomatch="error"`.
+
+4. In those cases where you need to rename columns in a `DT` but the columns aren't always known, `setnames()` now contains an additional argument (`skip_absent`) to skip them if they aren't present.  For example, if you know that columns `a`, `b` and `d` are present in `DT`, but you don't know if column `c` is or isn't, then you can include `c` in `old` and if it isn't found, `setnames()` will simply skip to the next item of `old` rather than exit the function.  **Note: The default behaviour of `setnames()` has not been altered as `skip_absent` is set to `FALSE` by default.** [#3030](https://github.com/Rdatatable/data.table/issues/3030)
 
 #### BUG FIXES
 
@@ -540,5 +541,3 @@ When `j` is a symbol (as in the quanteda and xgboost examples above) it will con
 
 
 ### Old news from v1.9.8 (Nov 2016) back to v1.2 (Aug 2008) has been moved to [NEWS.0.md](https://github.com/Rdatatable/data.table/blob/master/NEWS.0.md)
-
-

R/data.table.R

@@ -1,4 +1,3 @@
-
 dim.data.table <- function(x)
 {
   .Call(Cdim, x)
@@ -2497,7 +2496,7 @@ setattr <- function(x,name,value) {
   invisible(x)
 }
 
-setnames <- function(x,old,new) {
+setnames <- function(x,old,new,skip_absent=FALSE) {
   # Sets by reference, maintains truelength, no copy of table at all.
   # But also more convenient than names(DT)[i]="newname"  because we can also do setnames(DT,"oldname","newname")
   # without an onerous match() ourselves. old can be positions, too, but we encourage by name for robustness.
@@ -2532,7 +2531,14 @@ setnames <- function(x,old,new) {
       if (!is.character(old)) stop("'old' is type ",typeof(old)," but should be integer, double or character")
       if (any(duplicated(old))) stop("Some duplicates exist in 'old': ", paste(old[duplicated(old)],collapse=","))
       i = chmatch(old,names(x))
-      if (anyNA(i)) stop("Items of 'old' not found in column names: ",paste(old[is.na(i)],collapse=","))
+      if (anyNA(i)){ if (skip_absent == TRUE){
+        w <- old %chin% names(x)
+        old = old[w]
+        new = new[w]
+        i = i[w]
+      } else {
+        stop("Items of 'old' not found in column names: ",paste(old[is.na(i)],collapse=",")) }
+      }
       if (any(tt<-!is.na(chmatch(old,names(x)[-i])))) stop("Some items of 'old' are duplicated (ambiguous) in column names: ",paste(old[tt],collapse=","))
     }
     if (length(new)!=length(i)) stop("'old' is length ",length(i)," but 'new' is length ",length(new))

inst/tests/tests.Rraw

@@ -12328,6 +12328,11 @@ test(1951.4, d1[d2, nomatch=3], error="nomatch= must be either NA or NULL .or 0
 test(1952.1, d1[a==2, which=3], error="which= must be a logical vector length 1. Either FALSE, TRUE or NA.")
 test(1952.2, d1[a==2, 2, which=TRUE], error="which==TRUE.*but j is also supplied")
 
+# skip values that are not present in old, #3030
+DT <- data.table(a = 1, b = 2, d = 3)
+old <- c("a", "b", "c", "d")
+new <- c("A", "B", "C", "D") 
+test(1953, setnames(DT, old, new, skip_absent = TRUE), DT <- data.table(A = 1, B = 2, D = 3))
 
 ###################################
 #  Add new tests above this line  #

man/setattr.Rd

@@ -7,15 +7,17 @@
 }
 \usage{
 setattr(x,name,value)
-setnames(x,old,new)
+setnames(x,old,new,skip_absent=FALSE)
 }
 \arguments{
   \item{x}{ \code{setnames} accepts \code{data.frame} and \code{data.table}. \code{setattr} accepts any input; e.g, list, columns of a \code{data.frame} or \code{data.table}. }
   \item{name}{ The character attribute name. }
   \item{value}{ The value to assign to the attribute or \code{NULL} removes the attribute, if present. }
   \item{old}{ When \code{new} is provided, character names or numeric positions of column names to change. When \code{new} is not provided, the new column names, which must be the same length as the number of columns. See examples. }
   \item{new}{ Optional. New column names, must be the same length as columns provided to \code{old} argument. }
+  \item{skip_absent}{ Skips cases where there is no match in \code{old}.  Set to \code{FALSE} by default. Switch flag to \code{TRUE} to activate. }
 }
+
 \details{
 
   \code{setnames} operates on \code{data.table} and \code{data.frame} not other types like \code{list} and \code{vector}. It can be used to change names \emph{by name} with built-in checks and warnings (e.g., if any old names are missing or appear more than once).
@@ -34,6 +36,13 @@ setnames(x,old,new)
 }
 \examples{
 
+DT <- data.table(a = 1, b = 2, d = 3)
+
+old <- c("a", "b", "c", "d")
+new <- c("A", "B", "C", "D")
+
+setnames(DT, old, new, skip_absent = TRUE) # check for column names in old and skip if item is absent
+
 DF = data.frame(a=1:2,b=3:4)       # base data.frame to demo copies and syntax
 if (capabilities()["profmem"])     # usually memory profiling is available but just in case
   tracemem(DF)
@@ -70,4 +79,3 @@ attr(DT,"myFlag2")  # NULL
 
 }
 \keyword{ data }
-