seqDigest with a file name

zhengxwen · zhengxwen · commit 0416f4a776ca · 2025-06-01T14:18:05.000-05:00
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -2,8 +2,8 @@ Package: SeqArray
 Type: Package
 Title: Data management of large-scale whole-genome sequence variant calls
         using GDS files
-Version: 1.48.0
-Date: 2025-04-04
+Version: 1.49.1
+Date: 2025-05-30
 Depends: R (>= 3.5.0), gdsfmt (>= 1.31.1)
 Imports: methods, parallel, digest, S4Vectors, IRanges, GenomicRanges,
         GenomeInfoDb, Biostrings
diff --git a/NEWS b/NEWS
@@ -1,3 +1,11 @@
+CHANGES IN VERSION 1.49.1
+-------------------------
+
+UTILITIES
+
+    o `seqDigest()` allows a GDS file name in the first argument
+
+
 CHANGES IN VERSION 1.48.0
 -------------------------
 
diff --git a/R/Summary.R b/R/Summary.R
@@ -772,12 +772,18 @@ seqSummary <- function(gdsfile, varname=NULL,
 
 
 #######################################################################
-# summarize
+# Digest to generate hash code
 #
 seqDigest <- function(gdsfile, varname, algo=c("md5"), verbose=FALSE)
 {
     # check
-    stopifnot(inherits(gdsfile, "SeqVarGDSClass"))
+    if (is.character(gdsfile))
+    {
+        gdsfile <- seqOpen(gdsfile, allow.duplicate=TRUE)
+        on.exit(seqClose(gdsfile))
+    } else {
+        stopifnot(inherits(gdsfile, "SeqVarGDSClass"))
+    }
     stopifnot(is.character(varname), length(varname)==1L)
     algo <- match.arg(algo)
 
@@ -793,7 +799,7 @@ seqDigest <- function(gdsfile, varname, algo=c("md5"), verbose=FALSE)
 
 
 #######################################################################
-# summarize
+# Get system information
 #
 seqSystem <- function()
 {
diff --git a/man/seqDigest.Rd b/man/seqDigest.Rd
@@ -8,7 +8,7 @@
 seqDigest(gdsfile, varname, algo=c("md5"), verbose=FALSE)
 }
 \arguments{
-    \item{gdsfile}{a \code{\link{SeqVarGDSClass}} object}
+    \item{gdsfile}{a \code{\link{SeqVarGDSClass}} object or a GDS file name}
     \item{varname}{the variable name(s), see details}
     \item{algo}{the digest hash algorithm: "md5"}
     \item{verbose}{if \code{TRUE}, show progress information}
diff --git a/man/seqGetData.Rd b/man/seqGetData.Rd
@@ -9,7 +9,7 @@ seqGetData(gdsfile, var.name, .useraw=FALSE, .padNA=TRUE, .tolist=FALSE,
     .envir=NULL)
 }
 \arguments{
-    \item{gdsfile}{a \code{\link{SeqVarGDSClass}} object}
+    \item{gdsfile}{a \code{\link{SeqVarGDSClass}} object or a GDS file name}
     \item{var.name}{a variable name or a character vector, see details;
         if \code{character()}, return \code{NULL}}
     \item{.useraw}{\code{TRUE}, force to use RAW instead of INTEGER for

Original file line number	Diff line number	Diff line change
`@@ -772,12 +772,18 @@ seqSummary <- function(gdsfile, varname=NULL,`
`772`	`772`
`773`	`773`
`774`	`774`	`#######################################################################`
`775`		`-# summarize`
	`775`	`+# Digest to generate hash code`
`776`	`776`	`#`
`777`	`777`	`seqDigest <- function(gdsfile, varname, algo=c("md5"), verbose=FALSE)`
`778`	`778`	`{`
`779`	`779`	`# check`
`780`		`- stopifnot(inherits(gdsfile, "SeqVarGDSClass"))`
	`780`	`+ if (is.character(gdsfile))`
	`781`	`+ {`
	`782`	`+ gdsfile <- seqOpen(gdsfile, allow.duplicate=TRUE)`
	`783`	`+ on.exit(seqClose(gdsfile))`
	`784`	`+ } else {`
	`785`	`+ stopifnot(inherits(gdsfile, "SeqVarGDSClass"))`
	`786`	`+ }`
`781`	`787`	`stopifnot(is.character(varname), length(varname)==1L)`
`782`	`788`	`algo <- match.arg(algo)`
`783`	`789`
`@@ -793,7 +799,7 @@ seqDigest <- function(gdsfile, varname, algo=c("md5"), verbose=FALSE)`
`793`	`799`
`794`	`800`
`795`	`801`	`#######################################################################`
`796`		`-# summarize`
	`802`	`+# Get system information`
`797`	`803`	`#`
`798`	`804`	`seqSystem <- function()`
`799`	`805`	`{`
Original file line number	Diff line number	Diff line change
`@@ -8,7 +8,7 @@`
`8`	`8`	`seqDigest(gdsfile, varname, algo=c("md5"), verbose=FALSE)`
`9`	`9`	`}`
`10`	`10`	`\arguments{`
`11`		`- \item{gdsfile}{a \code{\link{SeqVarGDSClass}} object}`
	`11`	`+ \item{gdsfile}{a \code{\link{SeqVarGDSClass}} object or a GDS file name}`
`12`	`12`	`\item{varname}{the variable name(s), see details}`
`13`	`13`	`\item{algo}{the digest hash algorithm: "md5"}`
`14`	`14`	`\item{verbose}{if \code{TRUE}, show progress information}`
Original file line number	Diff line number	Diff line change
`@@ -9,7 +9,7 @@ seqGetData(gdsfile, var.name, .useraw=FALSE, .padNA=TRUE, .tolist=FALSE,`
`9`	`9`	`.envir=NULL)`
`10`	`10`	`}`
`11`	`11`	`\arguments{`
`12`		`- \item{gdsfile}{a \code{\link{SeqVarGDSClass}} object}`
	`12`	`+ \item{gdsfile}{a \code{\link{SeqVarGDSClass}} object or a GDS file name}`
`13`	`13`	`\item{var.name}{a variable name or a character vector, see details;`
`14`	`14`	`if \code{character()}, return \code{NULL}}`
`15`	`15`	`\item{.useraw}{\code{TRUE}, force to use RAW instead of INTEGER for`