From 7947a54dddece0ab3e6f9aa55427539916ea7bc1 Mon Sep 17 00:00:00 2001
From: Zilong-Li <zimusen94@gmail.com>
Date: Mon, 26 Feb 2024 12:37:58 +0100
Subject: [PATCH] v0.4.0

---
 DESCRIPTION                     | 4 ++--
 NEWS.md                         | 5 +++++
 R/vcf-tables.R                  | 5 ++++-
 cran-comments.md                | 4 +---
 man/vcftable.Rd                 | 5 ++++-
 tests/testthat/test-vcf-table.R | 5 +++++
 6 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index 751d1f4..c3ad394 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: vcfppR
 Title: Rapid Manipulation of the Variant Call Format (VCF)
-Version: 0.3.8
+Version: 0.4.0
 Authors@R: c(
     person("Zilong", "Li", , "zilong.dk@gmail.com", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0001-5859-2078")),
@@ -11,7 +11,7 @@ Description: The 'vcfpp.h' (<https://github.com/Zilong-Li/vcfpp>) provides an ea
 Encoding: UTF-8
 Depends: R (>= 3.6.0)
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.1
 Suggests: 
     testthat (>= 3.0.0)
 Config/testthat/edition: 3
diff --git a/NEWS.md b/NEWS.md
index ca5f10a..4e8b2dc 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,3 +1,8 @@
+# vcfppR 0.4.0
+
+* add `setid` option for vcftable
+* patches for upcoming Rtools on windows
+
 # vcfppR 0.3.8
 
 * fix issues on M1 Mac
diff --git a/R/vcf-tables.R b/R/vcf-tables.R
index 2551ab0..78ae6b7 100644
--- a/R/vcf-tables.R
+++ b/R/vcf-tables.R
@@ -36,6 +36,8 @@
 #'                 If the FORMAT to extract is not "GT", then with collapse=TRUE it will try to turn a list of the extracted vector into a matrix.
 #'                 However, this raises issues when one variant is mutliallelic resulting in more vaules than others.
 #'
+#' @param setid logical. reset ID column as CHR_POS_REF_ALT.
+#'
 #' @return Return a list containing the following components:
 #'\describe{
 #'\item{samples}{: character vector; \cr
@@ -87,7 +89,7 @@
 #' str(res)
 #' @export
 vcftable <- function(vcffile, region = "", samples = "-", vartype = "all", format = "GT", ids = NULL,
-                     qual = 0, pass = FALSE, info = TRUE, collapse = TRUE) {
+                     qual = 0, pass = FALSE, info = TRUE, collapse = TRUE, setid = FALSE) {
   snps <- FALSE
   indels <- FALSE
   svs <- FALSE
@@ -117,6 +119,7 @@ vcftable <- function(vcffile, region = "", samples = "-", vartype = "all", forma
     res <- tableFormat(vcffile, region, samples, format, ids, qual, pass, info, snps, indels, multiallelics, multisnps, svs)
     if(is.list(res[[10]]) && collapse) res[[10]] <- do.call("rbind", res[[10]])
   }
+  if(setid) res$id <- paste(res$chr, res$pos, res$ref, res$alt, sep = "_")
   return(res)
 }
 
diff --git a/cran-comments.md b/cran-comments.md
index c174243..2948016 100644
--- a/cran-comments.md
+++ b/cran-comments.md
@@ -1,4 +1,2 @@
-Fix issues on M1 Mac 
-
-https://cran.r-project.org/web/checks/check_results_vcfppR.html
+Fix issue for upcoming Rtools on windows
 
diff --git a/man/vcftable.Rd b/man/vcftable.Rd
index 63167da..5f61d03 100644
--- a/man/vcftable.Rd
+++ b/man/vcftable.Rd
@@ -14,7 +14,8 @@ vcftable(
   qual = 0,
   pass = FALSE,
   info = TRUE,
-  collapse = TRUE
+  collapse = TRUE,
+  setid = FALSE
 )
 }
 \arguments{
@@ -43,6 +44,8 @@ where M is #markers and N is #samples. default TRUE will collapse the genotypes
 Set this to FALSE if one wants to maintain the phasing order, e.g. "1|0" is parsed as c(1, 0) with collapse=FALSE.
 If the FORMAT to extract is not "GT", then with collapse=TRUE it will try to turn a list of the extracted vector into a matrix.
 However, this raises issues when one variant is mutliallelic resulting in more vaules than others.}
+
+\item{setid}{logical. reset ID column as CHR_POS_REF_ALT.}
 }
 \value{
 Return a list containing the following components:
diff --git a/tests/testthat/test-vcf-table.R b/tests/testthat/test-vcf-table.R
index acfbe81..d330762 100644
--- a/tests/testthat/test-vcf-table.R
+++ b/tests/testthat/test-vcf-table.R
@@ -14,6 +14,11 @@ test_that("extract GT for all SNPs", {
   expect_identical(sum(res$alt!=""), length(res$alt))
 })
 
+test_that("extract SNPs by ID and reset ID afterwards", {
+  res <- vcftable(vcffile, vartype = "snps", id = c("chr21:5030516:G:A"), setid = TRUE)
+  expect_identical(res$id, "chr21_5030516_G_A")
+})
+
 test_that("extract GT for a indel with FILTER not displaying PASS", {
   res <- vcftable(vcffile, id = c("chr21:5030240:AC:A"), vartype = "indels", pass = TRUE)
   expect_equal(length(res$gt), 0)