# HG changeset patch
# User davidvanzessen
# Date 1440168554 14400
# Node ID 02cf2dd19564e1ee85e50c006b786f2cb73f180c

Uploaded

diff -r 000000000000 -r 02cf2dd19564 extract_duplicates.r
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/extract_duplicates.r	Fri Aug 21 10:49:14 2015 -0400
@@ -0,0 +1,16 @@
+args <- commandArgs(trailingOnly = TRUE)
+
+input=args[1]
+column=as.numeric(args[2])
+header=(args[3] == "yes")
+out_file=args[4]
+
+dat = read.table(input, header=header, sep="\t", fill=T, stringsAsFactors=F)
+
+duplicates = dat[duplicated(dat[,column]),column]
+
+dat = dat[dat[,column] %in% duplicates,]
+
+dat = dat[order(dat[,column]),]
+
+write.table(dat, out_file, sep="\t", row.names=F, col.names=header, quote=F)
diff -r 000000000000 -r 02cf2dd19564 extract_duplicates.sh
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/extract_duplicates.sh	Fri Aug 21 10:49:14 2015 -0400
@@ -0,0 +1,7 @@
+input=$1
+column=$2
+header=$3
+out_file=$4
+
+dir="$(cd "$(dirname "$0")" && pwd)"
+Rscript --verbose $dir/extract_duplicates.r ${input} ${column} ${header} ${out_file} 2>&1
diff -r 000000000000 -r 02cf2dd19564 extract_duplicates.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/extract_duplicates.xml	Fri Aug 21 10:49:14 2015 -0400
@@ -0,0 +1,16 @@
+<tool id="extract_duplicates" name="Extract Duplicates" version="1.1.0">
+  <description>to a new dataset</description>
+  <command interpreter="bash">
+    extract_duplicates.sh $input $column $header $out_file
+  </command>
+  <inputs>
+    <param format="tabular" name="input" type="data" label="Input"/>
+		<param name="column" label="on column" type="data_column" data_ref="input" accept_default="true" />
+		<param name="header" type="boolean" checked="False" truevalue="yes" falsevalue="no" label="Input file has a header?" help="if checked, the first line of the input will be treated as a header"/>
+  </inputs>
+  <outputs>
+    <data format="input" name="out_file" metadata_source="input"/>
+  </outputs>
+  <help>
+</help>
+</tool>